summary refs log tree commit diff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/include/asm/atomic.h17
-rw-r--r--arch/alpha/include/asm/barrier.h59
-rw-r--r--arch/alpha/include/asm/pgtable.h10
-rw-r--r--arch/alpha/include/asm/rwonce.h35
-rw-r--r--arch/arc/Kconfig15
-rw-r--r--arch/arc/Makefile21
-rw-r--r--arch/arc/include/asm/atomic.h2
-rw-r--r--arch/arc/include/asm/elf.h2
-rw-r--r--arch/arc/include/asm/irqflags-compact.h5
-rw-r--r--arch/arc/kernel/entry.S16
-rw-r--r--arch/arc/kernel/head.S8
-rw-r--r--arch/arc/kernel/setup.c19
-rw-r--r--arch/arm/boot/dts/am335x-baltos.dtsi2
-rw-r--r--arch/arm/boot/dts/am335x-boneblack-common.dtsi1
-rw-r--r--arch/arm/boot/dts/am335x-boneblack-wireless.dts1
-rw-r--r--arch/arm/boot/dts/am335x-boneblue.dts1
-rw-r--r--arch/arm/boot/dts/am335x-bonegreen-wireless.dts1
-rw-r--r--arch/arm/boot/dts/am335x-evm.dts3
-rw-r--r--arch/arm/boot/dts/am335x-evmsk.dts2
-rw-r--r--arch/arm/boot/dts/am335x-lxm.dts2
-rw-r--r--arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi2
-rw-r--r--arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts2
-rw-r--r--arch/arm/boot/dts/am335x-pepper.dts4
-rw-r--r--arch/arm/boot/dts/am335x-phycore-som.dtsi2
-rw-r--r--arch/arm/boot/dts/am335x-pocketbeagle.dts1
-rw-r--r--arch/arm/boot/dts/am33xx-l4.dtsi6
-rw-r--r--arch/arm/boot/dts/am33xx.dtsi7
-rw-r--r--arch/arm/boot/dts/am4372.dtsi3
-rw-r--r--arch/arm/boot/dts/am437x-cm-t43.dts2
-rw-r--r--arch/arm/boot/dts/am437x-gp-evm.dts20
-rw-r--r--arch/arm/boot/dts/am437x-l4.dtsi19
-rw-r--r--arch/arm/boot/dts/am437x-sk-evm.dts18
-rw-r--r--arch/arm/boot/dts/am43x-epos-evm.dts16
-rw-r--r--arch/arm/boot/dts/am5729-beagleboneai.dts2
-rw-r--r--arch/arm/boot/dts/armada-38x.dtsi3
-rw-r--r--arch/arm/boot/dts/bcm-nsp.dtsi10
-rw-r--r--arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts1
-rw-r--r--arch/arm/boot/dts/bcm958522er.dts4
-rw-r--r--arch/arm/boot/dts/bcm958525er.dts4
-rw-r--r--arch/arm/boot/dts/bcm958525xmc.dts4
-rw-r--r--arch/arm/boot/dts/bcm958622hr.dts4
-rw-r--r--arch/arm/boot/dts/bcm958623hr.dts4
-rw-r--r--arch/arm/boot/dts/bcm958625hr.dts4
-rw-r--r--arch/arm/boot/dts/bcm958625k.dts4
-rw-r--r--arch/arm/boot/dts/dra7-evm-common.dtsi20
-rw-r--r--arch/arm/boot/dts/dra7-l4.dtsi34
-rw-r--r--arch/arm/boot/dts/imx6qdl-gw551x.dtsi2
-rw-r--r--arch/arm/boot/dts/imx6qdl-icore.dtsi3
-rw-r--r--arch/arm/boot/dts/imx6sx-sabreauto.dts2
-rw-r--r--arch/arm/boot/dts/imx6sx-sdb.dtsi2
-rw-r--r--arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi13
-rw-r--r--arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi13
-rw-r--r--arch/arm/boot/dts/keystone-k2g-evm.dts2
-rw-r--r--arch/arm/boot/dts/meson.dtsi2
-rw-r--r--arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi4
-rw-r--r--arch/arm/boot/dts/omap3-n900.dts12
-rw-r--r--arch/arm/boot/dts/omap4-duovero-parlor.dts2
-rw-r--r--arch/arm/boot/dts/omap4.dtsi2
-rw-r--r--arch/arm/boot/dts/socfpga.dtsi2
-rw-r--r--arch/arm/boot/dts/socfpga_arria10.dtsi2
-rw-r--r--arch/arm/boot/dts/sun4i-a10.dtsi2
-rw-r--r--arch/arm/boot/dts/sun5i.dtsi2
-rw-r--r--arch/arm/boot/dts/sun7i-a20.dtsi2
-rw-r--r--arch/arm/boot/dts/vexpress-v2m-rs1.dtsi146
-rw-r--r--arch/arm/crypto/crc32-ce-core.S2
-rw-r--r--arch/arm/crypto/ghash-ce-glue.c51
-rw-r--r--arch/arm/crypto/sha1-armv4-large.S2
-rw-r--r--arch/arm/crypto/sha256-armv4.pl2
-rw-r--r--arch/arm/crypto/sha256-core.S_shipped2
-rw-r--r--arch/arm/crypto/sha512-armv4.pl4
-rw-r--r--arch/arm/crypto/sha512-core.S_shipped4
-rw-r--r--arch/arm/include/asm/atomic.h2
-rw-r--r--arch/arm/include/asm/efi.h7
-rw-r--r--arch/arm/include/asm/percpu.h2
-rw-r--r--arch/arm/include/asm/thread_info.h5
-rw-r--r--arch/arm/include/asm/topology.h3
-rw-r--r--arch/arm/include/asm/vdso/gettimeofday.h1
-rw-r--r--arch/arm/kernel/asm-offsets.c9
-rw-r--r--arch/arm/kernel/ftrace.c3
-rw-r--r--arch/arm/kernel/hw_breakpoint.c27
-rw-r--r--arch/arm/kernel/kgdb.c2
-rw-r--r--arch/arm/kernel/traps.c2
-rw-r--r--arch/arm/kernel/vdso.c1
-rw-r--r--arch/arm/mach-bcm/Kconfig1
-rw-r--r--arch/arm/mach-imx/devices/devices-common.h2
-rw-r--r--arch/arm/mach-imx/devices/platform-gpio-mxc.c5
-rw-r--r--arch/arm/mach-imx/devices/platform-imx-dma.c6
-rw-r--r--arch/arm/mach-imx/mm-imx21.c3
-rw-r--r--arch/arm/mach-imx/mm-imx27.c3
-rw-r--r--arch/arm/mach-imx/pm-imx5.c6
-rw-r--r--arch/arm/mach-imx/pm-imx6.c10
-rw-r--r--arch/arm/mach-omap2/omap_hwmod.c16
-rw-r--r--arch/arm/mach-sti/board-dt.c9
-rw-r--r--arch/arm/mm/alignment.c4
-rw-r--r--arch/arm/mm/mmu.c2
-rw-r--r--arch/arm/xen/enlighten.c1
-rw-r--r--arch/arm64/Kconfig31
-rw-r--r--arch/arm64/Kconfig.debug15
-rw-r--r--arch/arm64/Makefile15
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi1
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi8
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts1
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts7
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts2
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts2
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi24
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl.dtsi5
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi4
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-evk.dts4
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts4
-rw-r--r--arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts1
-rw-r--r--arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts5
-rw-r--r--arch/arm64/configs/defconfig3
-rw-r--r--arch/arm64/crypto/ghash-ce-glue.c257
-rw-r--r--arch/arm64/include/asm/acpi.h15
-rw-r--r--arch/arm64/include/asm/alternative.h18
-rw-r--r--arch/arm64/include/asm/arch_gicv3.h2
-rw-r--r--arch/arm64/include/asm/arch_timer.h1
-rw-r--r--arch/arm64/include/asm/atomic.h2
-rw-r--r--arch/arm64/include/asm/checksum.h5
-rw-r--r--arch/arm64/include/asm/cpucaps.h4
-rw-r--r--arch/arm64/include/asm/cpufeature.h9
-rw-r--r--arch/arm64/include/asm/cputype.h2
-rw-r--r--arch/arm64/include/asm/debug-monitors.h2
-rw-r--r--arch/arm64/include/asm/hugetlb.h2
-rw-r--r--arch/arm64/include/asm/hwcap.h1
-rw-r--r--arch/arm64/include/asm/kernel-pgtable.h2
-rw-r--r--arch/arm64/include/asm/kvm_host.h11
-rw-r--r--arch/arm64/include/asm/linkage.h6
-rw-r--r--arch/arm64/include/asm/memory.h12
-rw-r--r--arch/arm64/include/asm/mmu.h3
-rw-r--r--arch/arm64/include/asm/mmu_context.h6
-rw-r--r--arch/arm64/include/asm/perf_event.h27
-rw-r--r--arch/arm64/include/asm/pgtable-hwdef.h23
-rw-r--r--arch/arm64/include/asm/pgtable-prot.h2
-rw-r--r--arch/arm64/include/asm/pgtable.h12
-rw-r--r--arch/arm64/include/asm/ptrace.h2
-rw-r--r--arch/arm64/include/asm/smp.h1
-rw-r--r--arch/arm64/include/asm/stage2_pgtable.h9
-rw-r--r--arch/arm64/include/asm/syscall.h12
-rw-r--r--arch/arm64/include/asm/sysreg.h49
-rw-r--r--arch/arm64/include/asm/thread_info.h1
-rw-r--r--arch/arm64/include/asm/tlb.h29
-rw-r--r--arch/arm64/include/asm/tlbflush.h177
-rw-r--r--arch/arm64/include/asm/topology.h3
-rw-r--r--arch/arm64/include/asm/uaccess.h1
-rw-r--r--arch/arm64/include/asm/vdso.h2
-rw-r--r--arch/arm64/include/asm/vdso/clocksource.h7
-rw-r--r--arch/arm64/include/asm/vdso/compat_gettimeofday.h21
-rw-r--r--arch/arm64/include/asm/vdso/gettimeofday.h9
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h1
-rw-r--r--arch/arm64/include/uapi/asm/sigcontext.h2
-rw-r--r--arch/arm64/kernel/Makefile2
-rw-r--r--arch/arm64/kernel/acpi.c75
-rw-r--r--arch/arm64/kernel/alternative.c16
-rw-r--r--arch/arm64/kernel/cpu_errata.c24
-rw-r--r--arch/arm64/kernel/cpufeature.c153
-rw-r--r--arch/arm64/kernel/cpuinfo.c1
-rw-r--r--arch/arm64/kernel/crash_core.c10
-rw-r--r--arch/arm64/kernel/debug-monitors.c24
-rw-r--r--arch/arm64/kernel/entry-common.c2
-rw-r--r--arch/arm64/kernel/entry.S148
-rw-r--r--arch/arm64/kernel/fpsimd.c31
-rw-r--r--arch/arm64/kernel/hw_breakpoint.c44
-rw-r--r--arch/arm64/kernel/insn.c4
-rw-r--r--arch/arm64/kernel/kgdb.c2
-rw-r--r--arch/arm64/kernel/machine_kexec_file.c3
-rw-r--r--arch/arm64/kernel/module-plts.c46
-rw-r--r--arch/arm64/kernel/perf_event.c89
-rw-r--r--arch/arm64/kernel/perf_regs.c25
-rw-r--r--arch/arm64/kernel/probes/kprobes.c12
-rw-r--r--arch/arm64/kernel/ptrace.c49
-rw-r--r--arch/arm64/kernel/setup.c24
-rw-r--r--arch/arm64/kernel/signal.c11
-rw-r--r--arch/arm64/kernel/signal32.c27
-rw-r--r--arch/arm64/kernel/stacktrace.c2
-rw-r--r--arch/arm64/kernel/syscall.c21
-rw-r--r--arch/arm64/kernel/traps.c5
-rw-r--r--arch/arm64/kernel/vdso.c197
-rw-r--r--arch/arm64/kernel/vdso/Makefile7
-rw-r--r--arch/arm64/kernel/vdso/sigreturn.S54
-rw-r--r--arch/arm64/kernel/vdso/vdso.lds.S5
-rw-r--r--arch/arm64/kernel/vdso32/Makefile3
-rw-r--r--arch/arm64/kernel/vdso32/sigreturn.S58
-rw-r--r--arch/arm64/kernel/vdso32/vdso.lds.S17
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S4
-rw-r--r--arch/arm64/kvm/hyp-init.S12
-rw-r--r--arch/arm64/kvm/mmu.c11
-rw-r--r--arch/arm64/kvm/pmu.c7
-rw-r--r--arch/arm64/kvm/pvtime.c15
-rw-r--r--arch/arm64/kvm/reset.c10
-rw-r--r--arch/arm64/kvm/sys_regs.c68
-rw-r--r--arch/arm64/kvm/vgic/vgic-v4.c8
-rw-r--r--arch/arm64/mm/context.c10
-rw-r--r--arch/arm64/mm/hugetlbpage.c42
-rw-r--r--arch/arm64/mm/init.c33
-rw-r--r--arch/arm64/mm/mmu.c1
-rw-r--r--arch/csky/kernel/ftrace.c5
-rw-r--r--arch/h8300/include/asm/atomic.h2
-rw-r--r--arch/hexagon/include/asm/atomic.h2
-rw-r--r--arch/ia64/include/asm/atomic.h1
-rw-r--r--arch/ia64/include/asm/sections.h2
-rw-r--r--arch/ia64/kernel/ftrace.c6
-rw-r--r--arch/ia64/kernel/unwind_i.h2
-rw-r--r--arch/m68k/Kbuild19
-rw-r--r--arch/m68k/Makefile73
-rw-r--r--arch/m68k/configs/amiga_defconfig3
-rw-r--r--arch/m68k/configs/apollo_defconfig3
-rw-r--r--arch/m68k/configs/atari_defconfig3
-rw-r--r--arch/m68k/configs/bvme6000_defconfig3
-rw-r--r--arch/m68k/configs/hp300_defconfig3
-rw-r--r--arch/m68k/configs/mac_defconfig3
-rw-r--r--arch/m68k/configs/multi_defconfig3
-rw-r--r--arch/m68k/configs/mvme147_defconfig3
-rw-r--r--arch/m68k/configs/mvme16x_defconfig3
-rw-r--r--arch/m68k/configs/q40_defconfig3
-rw-r--r--arch/m68k/configs/sun3_defconfig3
-rw-r--r--arch/m68k/configs/sun3x_defconfig3
-rw-r--r--arch/m68k/emu/nfblock.c8
-rw-r--r--arch/m68k/include/asm/atomic.h2
-rw-r--r--arch/m68k/include/asm/raw_io.h6
-rw-r--r--arch/m68k/kernel/setup_no.c3
-rw-r--r--arch/m68k/kernel/signal.c32
-rw-r--r--arch/m68k/mac/iop.c60
-rw-r--r--arch/m68k/mm/mcfmmu.c2
-rw-r--r--arch/m68k/sun3/Makefile2
-rw-r--r--arch/mips/boot/dts/ingenic/gcw0.dts2
-rw-r--r--arch/mips/include/asm/atomic.h1
-rw-r--r--arch/mips/include/asm/unroll.h8
-rw-r--r--arch/mips/kernel/kprobes.c6
-rw-r--r--arch/mips/kernel/traps.c9
-rw-r--r--arch/mips/kvm/emulate.c4
-rw-r--r--arch/mips/kvm/mips.c2
-rw-r--r--arch/mips/lantiq/xway/sysctrl.c8
-rw-r--r--arch/mips/pci/pci-xtalk-bridge.c8
-rw-r--r--arch/nds32/kernel/ftrace.c5
-rw-r--r--arch/openrisc/kernel/dma.c5
-rw-r--r--arch/parisc/include/asm/atomic.h4
-rw-r--r--arch/parisc/include/asm/cmpxchg.h2
-rw-r--r--arch/parisc/kernel/ftrace.c2
-rw-r--r--arch/parisc/kernel/kgdb.c4
-rw-r--r--arch/parisc/kernel/process.c2
-rw-r--r--arch/parisc/lib/bitops.c12
-rw-r--r--arch/parisc/lib/memcpy.c2
-rw-r--r--arch/powerpc/include/asm/atomic.h2
-rw-r--r--arch/powerpc/include/asm/dtl.h52
-rw-r--r--arch/powerpc/include/asm/icswx.h2
-rw-r--r--arch/powerpc/include/asm/lppaca.h44
-rw-r--r--arch/powerpc/include/asm/nohash/32/pgtable.h18
-rw-r--r--arch/powerpc/include/asm/paca.h2
-rw-r--r--arch/powerpc/include/asm/sections.h2
-rw-r--r--arch/powerpc/include/uapi/asm/papr_pdsm.h132
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S20
-rw-r--r--arch/powerpc/kernel/kgdb.c2
-rw-r--r--arch/powerpc/kernel/kprobes.c2
-rw-r--r--arch/powerpc/kernel/module_64.c6
-rw-r--r--arch/powerpc/kernel/paca.c2
-rw-r--r--arch/powerpc/kernel/process.c25
-rw-r--r--arch/powerpc/kernel/time.c2
-rw-r--r--arch/powerpc/kernel/trace/ftrace.c4
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c7
-rw-r--r--arch/powerpc/kvm/book3s_hv.c1
-rw-r--r--arch/powerpc/lib/inst.c12
-rw-r--r--arch/powerpc/mm/book3s64/hash_utils.c25
-rw-r--r--arch/powerpc/mm/book3s64/pkeys.c15
-rw-r--r--arch/powerpc/mm/nohash/kaslr_booke.c1
-rw-r--r--arch/powerpc/oprofile/backtrace.c6
-rw-r--r--arch/powerpc/perf/callchain_32.c2
-rw-r--r--arch/powerpc/perf/callchain_64.c2
-rw-r--r--arch/powerpc/perf/core-book3s.c12
-rw-r--r--arch/powerpc/platforms/cell/spu_callbacks.c2
-rw-r--r--arch/powerpc/platforms/powernv/vas-fault.c2
-rw-r--r--arch/powerpc/platforms/pseries/dtl.c1
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c1
-rw-r--r--arch/powerpc/platforms/pseries/papr_scm.c420
-rw-r--r--arch/powerpc/platforms/pseries/setup.c1
-rw-r--r--arch/powerpc/platforms/pseries/svm.c1
-rw-r--r--arch/powerpc/sysdev/fsl_pci.c6
-rw-r--r--arch/riscv/Kconfig2
-rw-r--r--arch/riscv/include/asm/atomic.h2
-rw-r--r--arch/riscv/include/asm/barrier.h10
-rw-r--r--arch/riscv/include/asm/cmpxchg.h8
-rw-r--r--arch/riscv/include/asm/gdb_xml.h3
-rw-r--r--arch/riscv/include/asm/kgdb.h5
-rw-r--r--arch/riscv/include/asm/thread_info.h4
-rw-r--r--arch/riscv/include/asm/vdso/gettimeofday.h1
-rw-r--r--arch/riscv/kernel/ftrace.c3
-rw-r--r--arch/riscv/kernel/kgdb.c18
-rw-r--r--arch/riscv/kernel/patch.c4
-rw-r--r--arch/riscv/kernel/sys_riscv.c6
-rw-r--r--arch/riscv/kernel/traps.c4
-rw-r--r--arch/riscv/kernel/vdso/Makefile5
-rw-r--r--arch/riscv/kernel/vdso/vgettimeofday.c6
-rw-r--r--arch/riscv/mm/init.c66
-rw-r--r--arch/riscv/mm/kasan_init.c4
-rw-r--r--arch/riscv/mm/pageattr.c14
-rw-r--r--arch/s390/Kconfig8
-rw-r--r--arch/s390/appldata/appldata_os.c6
-rw-r--r--arch/s390/configs/debug_defconfig44
-rw-r--r--arch/s390/configs/defconfig43
-rw-r--r--arch/s390/configs/zfcpdump_defconfig5
-rw-r--r--arch/s390/crypto/prng.c14
-rw-r--r--arch/s390/include/asm/asm-const.h12
-rw-r--r--arch/s390/include/asm/atomic.h2
-rw-r--r--arch/s390/include/asm/debug.h18
-rw-r--r--arch/s390/include/asm/extable.h52
-rw-r--r--arch/s390/include/asm/kvm_host.h8
-rw-r--r--arch/s390/include/asm/linkage.h35
-rw-r--r--arch/s390/include/asm/pci_dma.h11
-rw-r--r--arch/s390/include/asm/pgtable.h2
-rw-r--r--arch/s390/include/asm/ptrace.h5
-rw-r--r--arch/s390/include/asm/smp.h5
-rw-r--r--arch/s390/include/asm/syscall.h12
-rw-r--r--arch/s390/include/asm/syscall_wrapper.h6
-rw-r--r--arch/s390/include/asm/thread_info.h1
-rw-r--r--arch/s390/include/asm/timex.h5
-rw-r--r--arch/s390/include/asm/vdso.h1
-rw-r--r--arch/s390/include/uapi/asm/debug.h35
-rw-r--r--arch/s390/include/uapi/asm/zcrypt.h140
-rw-r--r--arch/s390/kernel/asm-offsets.c2
-rw-r--r--arch/s390/kernel/crash_dump.c6
-rw-r--r--arch/s390/kernel/debug.c45
-rw-r--r--arch/s390/kernel/early.c2
-rw-r--r--arch/s390/kernel/entry.S6
-rw-r--r--arch/s390/kernel/ftrace.c4
-rw-r--r--arch/s390/kernel/idle.c4
-rw-r--r--arch/s390/kernel/ipl.c2
-rw-r--r--arch/s390/kernel/kprobes.c4
-rw-r--r--arch/s390/kernel/lgr.c2
-rw-r--r--arch/s390/kernel/perf_cpum_cf_events.c4
-rw-r--r--arch/s390/kernel/perf_cpum_sf.c11
-rw-r--r--arch/s390/kernel/ptrace.c83
-rw-r--r--arch/s390/kernel/setup.c9
-rw-r--r--arch/s390/kernel/smp.c5
-rw-r--r--arch/s390/kernel/time.c56
-rw-r--r--arch/s390/kernel/topology.c4
-rw-r--r--arch/s390/kernel/traps.c7
-rw-r--r--arch/s390/kernel/uv.c8
-rw-r--r--arch/s390/kernel/vdso64/Makefile10
-rw-r--r--arch/s390/kernel/vdso64/clock_getres.S10
-rw-r--r--arch/s390/lib/Makefile2
-rw-r--r--arch/s390/lib/error-inject.c14
-rw-r--r--arch/s390/mm/cmm.c2
-rw-r--r--arch/s390/mm/extmem.c32
-rw-r--r--arch/s390/mm/fault.c8
-rw-r--r--arch/s390/mm/hugetlbpage.c2
-rw-r--r--arch/s390/mm/maccess.c14
-rw-r--r--arch/s390/mm/vmem.c703
-rw-r--r--arch/s390/net/bpf_jit_comp.c139
-rw-r--r--arch/s390/pci/pci_event.c13
-rw-r--r--arch/s390/pci/pci_mmio.c20
-rw-r--r--arch/sh/include/asm/atomic.h2
-rw-r--r--arch/sh/include/asm/pgalloc.h10
-rw-r--r--arch/sh/kernel/entry-common.S6
-rw-r--r--arch/sh/kernel/ftrace.c6
-rw-r--r--arch/sh/kernel/traps.c2
-rw-r--r--arch/sparc/crypto/sha256_glue.c14
-rw-r--r--arch/sparc/include/asm/atomic_32.h2
-rw-r--r--arch/sparc/include/asm/atomic_64.h1
-rw-r--r--arch/sparc/include/asm/percpu_64.h2
-rw-r--r--arch/sparc/include/asm/trap_block.h2
-rw-r--r--arch/um/kernel/maccess.c2
-rw-r--r--arch/unicore32/.gitignore22
-rw-r--r--arch/unicore32/Kconfig200
-rw-r--r--arch/unicore32/Kconfig.debug29
-rw-r--r--arch/unicore32/Makefile59
-rw-r--r--arch/unicore32/boot/Makefile39
-rw-r--r--arch/unicore32/boot/compressed/Makefile64
-rw-r--r--arch/unicore32/boot/compressed/head.S201
-rw-r--r--arch/unicore32/boot/compressed/misc.c123
-rw-r--r--arch/unicore32/boot/compressed/piggy.S.in6
-rw-r--r--arch/unicore32/boot/compressed/vmlinux.lds.S58
-rw-r--r--arch/unicore32/configs/defconfig214
-rw-r--r--arch/unicore32/include/asm/Kbuild7
-rw-r--r--arch/unicore32/include/asm/assembler.h128
-rw-r--r--arch/unicore32/include/asm/barrier.h16
-rw-r--r--arch/unicore32/include/asm/bitops.h46
-rw-r--r--arch/unicore32/include/asm/bug.h20
-rw-r--r--arch/unicore32/include/asm/cache.h24
-rw-r--r--arch/unicore32/include/asm/cacheflush.h186
-rw-r--r--arch/unicore32/include/asm/checksum.h38
-rw-r--r--arch/unicore32/include/asm/cmpxchg.h58
-rw-r--r--arch/unicore32/include/asm/cpu-single.h42
-rw-r--r--arch/unicore32/include/asm/cputype.h30
-rw-r--r--arch/unicore32/include/asm/delay.h49
-rw-r--r--arch/unicore32/include/asm/dma.h20
-rw-r--r--arch/unicore32/include/asm/elf.h90
-rw-r--r--arch/unicore32/include/asm/fpstate.h23
-rw-r--r--arch/unicore32/include/asm/fpu-ucf64.h50
-rw-r--r--arch/unicore32/include/asm/gpio.h101
-rw-r--r--arch/unicore32/include/asm/hwcap.h29
-rw-r--r--arch/unicore32/include/asm/hwdef-copro.h45
-rw-r--r--arch/unicore32/include/asm/io.h69
-rw-r--r--arch/unicore32/include/asm/irq.h102
-rw-r--r--arch/unicore32/include/asm/irqflags.h50
-rw-r--r--arch/unicore32/include/asm/linkage.h19
-rw-r--r--arch/unicore32/include/asm/memblock.h43
-rw-r--r--arch/unicore32/include/asm/memory.h102
-rw-r--r--arch/unicore32/include/asm/mmu.h14
-rw-r--r--arch/unicore32/include/asm/mmu_context.h98
-rw-r--r--arch/unicore32/include/asm/page.h74
-rw-r--r--arch/unicore32/include/asm/pci.h20
-rw-r--r--arch/unicore32/include/asm/pgalloc.h87
-rw-r--r--arch/unicore32/include/asm/pgtable-hwdef.h51
-rw-r--r--arch/unicore32/include/asm/pgtable.h267
-rw-r--r--arch/unicore32/include/asm/processor.h74
-rw-r--r--arch/unicore32/include/asm/ptrace.h58
-rw-r--r--arch/unicore32/include/asm/stacktrace.h28
-rw-r--r--arch/unicore32/include/asm/string.h35
-rw-r--r--arch/unicore32/include/asm/suspend.h26
-rw-r--r--arch/unicore32/include/asm/switch_to.h27
-rw-r--r--arch/unicore32/include/asm/syscall.h12
-rw-r--r--arch/unicore32/include/asm/thread_info.h133
-rw-r--r--arch/unicore32/include/asm/timex.h31
-rw-r--r--arch/unicore32/include/asm/tlb.h24
-rw-r--r--arch/unicore32/include/asm/tlbflush.h192
-rw-r--r--arch/unicore32/include/asm/traps.h18
-rw-r--r--arch/unicore32/include/asm/uaccess.h38
-rw-r--r--arch/unicore32/include/asm/vmalloc.h4
-rw-r--r--arch/unicore32/include/mach/PKUnity.h95
-rw-r--r--arch/unicore32/include/mach/bitfield.h21
-rw-r--r--arch/unicore32/include/mach/dma.h45
-rw-r--r--arch/unicore32/include/mach/hardware.h30
-rw-r--r--arch/unicore32/include/mach/map.h17
-rw-r--r--arch/unicore32/include/mach/memory.h54
-rw-r--r--arch/unicore32/include/mach/ocd.h33
-rw-r--r--arch/unicore32/include/mach/pm.h37
-rw-r--r--arch/unicore32/include/mach/regs-ac97.h33
-rw-r--r--arch/unicore32/include/mach/regs-dmac.h82
-rw-r--r--arch/unicore32/include/mach/regs-gpio.h71
-rw-r--r--arch/unicore32/include/mach/regs-i2c.h64
-rw-r--r--arch/unicore32/include/mach/regs-intc.h29
-rw-r--r--arch/unicore32/include/mach/regs-nand.h80
-rw-r--r--arch/unicore32/include/mach/regs-ost.h91
-rw-r--r--arch/unicore32/include/mach/regs-pci.h95
-rw-r--r--arch/unicore32/include/mach/regs-pm.h127
-rw-r--r--arch/unicore32/include/mach/regs-ps2.h21
-rw-r--r--arch/unicore32/include/mach/regs-resetc.h35
-rw-r--r--arch/unicore32/include/mach/regs-rtc.h38
-rw-r--r--arch/unicore32/include/mach/regs-sdc.h157
-rw-r--r--arch/unicore32/include/mach/regs-spi.h99
-rw-r--r--arch/unicore32/include/mach/regs-uart.h3
-rw-r--r--arch/unicore32/include/mach/regs-umal.h230
-rw-r--r--arch/unicore32/include/mach/regs-unigfx.h201
-rw-r--r--arch/unicore32/include/mach/uncompress.h31
-rw-r--r--arch/unicore32/include/uapi/asm/Kbuild2
-rw-r--r--arch/unicore32/include/uapi/asm/byteorder.h25
-rw-r--r--arch/unicore32/include/uapi/asm/ptrace.h91
-rw-r--r--arch/unicore32/include/uapi/asm/sigcontext.h30
-rw-r--r--arch/unicore32/include/uapi/asm/unistd.h21
-rw-r--r--arch/unicore32/kernel/Makefile31
-rw-r--r--arch/unicore32/kernel/asm-offsets.c108
-rw-r--r--arch/unicore32/kernel/clock.c387
-rw-r--r--arch/unicore32/kernel/debug-macro.S86
-rw-r--r--arch/unicore32/kernel/debug.S82
-rw-r--r--arch/unicore32/kernel/dma.c179
-rw-r--r--arch/unicore32/kernel/early_printk.c46
-rw-r--r--arch/unicore32/kernel/elf.c35
-rw-r--r--arch/unicore32/kernel/entry.S802
-rw-r--r--arch/unicore32/kernel/fpu-ucf64.c117
-rw-r--r--arch/unicore32/kernel/gpio.c121
-rw-r--r--arch/unicore32/kernel/head.S249
-rw-r--r--arch/unicore32/kernel/hibernate.c159
-rw-r--r--arch/unicore32/kernel/hibernate_asm.S114
-rw-r--r--arch/unicore32/kernel/irq.c371
-rw-r--r--arch/unicore32/kernel/ksyms.c57
-rw-r--r--arch/unicore32/kernel/ksyms.h14
-rw-r--r--arch/unicore32/kernel/module.c105
-rw-r--r--arch/unicore32/kernel/pci.c371
-rw-r--r--arch/unicore32/kernel/pm.c121
-rw-r--r--arch/unicore32/kernel/process.c319
-rw-r--r--arch/unicore32/kernel/ptrace.c147
-rw-r--r--arch/unicore32/kernel/puv3-core.c276
-rw-r--r--arch/unicore32/kernel/puv3-nb0916.c147
-rw-r--r--arch/unicore32/kernel/setup.c352
-rw-r--r--arch/unicore32/kernel/setup.h36
-rw-r--r--arch/unicore32/kernel/signal.c424
-rw-r--r--arch/unicore32/kernel/sleep.S199
-rw-r--r--arch/unicore32/kernel/stacktrace.c127
-rw-r--r--arch/unicore32/kernel/sys.c37
-rw-r--r--arch/unicore32/kernel/time.c128
-rw-r--r--arch/unicore32/kernel/traps.c322
-rw-r--r--arch/unicore32/kernel/vmlinux.lds.S59
-rw-r--r--arch/unicore32/lib/Makefile28
-rw-r--r--arch/unicore32/lib/backtrace.S168
-rw-r--r--arch/unicore32/lib/clear_user.S54
-rw-r--r--arch/unicore32/lib/copy_from_user.S101
-rw-r--r--arch/unicore32/lib/copy_page.S36
-rw-r--r--arch/unicore32/lib/copy_template.S211
-rw-r--r--arch/unicore32/lib/copy_to_user.S93
-rw-r--r--arch/unicore32/lib/delay.S48
-rw-r--r--arch/unicore32/lib/findbit.S97
-rw-r--r--arch/unicore32/lib/strncpy_from_user.S42
-rw-r--r--arch/unicore32/lib/strnlen_user.S39
-rw-r--r--arch/unicore32/mm/Kconfig41
-rw-r--r--arch/unicore32/mm/Makefile14
-rw-r--r--arch/unicore32/mm/alignment.c524
-rw-r--r--arch/unicore32/mm/cache-ucv2.S209
-rw-r--r--arch/unicore32/mm/extable.c21
-rw-r--r--arch/unicore32/mm/fault.c481
-rw-r--r--arch/unicore32/mm/flush.c94
-rw-r--r--arch/unicore32/mm/init.c261
-rw-r--r--arch/unicore32/mm/ioremap.c242
-rw-r--r--arch/unicore32/mm/mm.h31
-rw-r--r--arch/unicore32/mm/mmu.c513
-rw-r--r--arch/unicore32/mm/pgd.c102
-rw-r--r--arch/unicore32/mm/proc-macros.S142
-rw-r--r--arch/unicore32/mm/proc-syms.c19
-rw-r--r--arch/unicore32/mm/proc-ucv2.S131
-rw-r--r--arch/unicore32/mm/tlb-ucv2.S86
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/Kconfig.debug3
-rw-r--r--arch/x86/boot/compressed/Makefile4
-rw-r--r--arch/x86/boot/compressed/head_64.S11
-rw-r--r--arch/x86/crypto/aes_ctrby8_avx-x86_64.S15
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S739
-rw-r--r--arch/x86/crypto/aesni-intel_avx-x86_64.S1
-rw-r--r--arch/x86/crypto/chacha-ssse3-x86_64.S16
-rw-r--r--arch/x86/crypto/chacha_glue.c17
-rw-r--r--arch/x86/crypto/crc32-pclmul_asm.S47
-rw-r--r--arch/x86/crypto/crc32c-pcl-intel-asm_64.S7
-rw-r--r--arch/x86/crypto/curve25519-x86_64.c6
-rw-r--r--arch/x86/crypto/ghash-clmulni-intel_asm.S17
-rw-r--r--arch/x86/entry/Makefile14
-rw-r--r--arch/x86/entry/common.c139
-rw-r--r--arch/x86/entry/entry_32.S5
-rw-r--r--arch/x86/entry/entry_64_compat.S31
-rw-r--r--arch/x86/events/Makefile2
-rw-r--r--arch/x86/events/core.c28
-rw-r--r--arch/x86/events/intel/core.c127
-rw-r--r--arch/x86/events/intel/ds.c6
-rw-r--r--arch/x86/events/intel/lbr.c733
-rw-r--r--arch/x86/events/intel/uncore.c26
-rw-r--r--arch/x86/events/intel/uncore.h37
-rw-r--r--arch/x86/events/intel/uncore_snb.c80
-rw-r--r--arch/x86/events/intel/uncore_snbep.c208
-rw-r--r--arch/x86/events/perf_event.h125
-rw-r--r--arch/x86/events/rapl.c3
-rw-r--r--arch/x86/events/zhaoxin/core.c2
-rw-r--r--arch/x86/hyperv/hv_init.c5
-rw-r--r--arch/x86/include/asm/atomic.h2
-rw-r--r--arch/x86/include/asm/bitops.h6
-rw-r--r--arch/x86/include/asm/bug.h7
-rw-r--r--arch/x86/include/asm/cpu.h5
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/cpumask.h18
-rw-r--r--arch/x86/include/asm/div64.h14
-rw-r--r--arch/x86/include/asm/fpu/internal.h52
-rw-r--r--arch/x86/include/asm/fpu/types.h27
-rw-r--r--arch/x86/include/asm/fpu/xstate.h36
-rw-r--r--arch/x86/include/asm/idtentry.h96
-rw-r--r--arch/x86/include/asm/inst.h163
-rw-r--r--arch/x86/include/asm/io_bitmap.h16
-rw-r--r--arch/x86/include/asm/iosf_mbi.h1
-rw-r--r--arch/x86/include/asm/kprobes.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h4
-rw-r--r--arch/x86/include/asm/msr-index.h16
-rw-r--r--arch/x86/include/asm/mwait.h2
-rw-r--r--arch/x86/include/asm/paravirt.h5
-rw-r--r--arch/x86/include/asm/paravirt_types.h1
-rw-r--r--arch/x86/include/asm/perf_event.h82
-rw-r--r--arch/x86/include/asm/pgtable_types.h2
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/ptrace.h4
-rw-r--r--arch/x86/include/asm/topology.h2
-rw-r--r--arch/x86/include/uapi/asm/kvm.h5
-rw-r--r--arch/x86/kernel/alternative.c37
-rw-r--r--arch/x86/kernel/apic/io_apic.c15
-rw-r--r--arch/x86/kernel/apic/msi.c18
-rw-r--r--arch/x86/kernel/apic/vector.c27
-rw-r--r--arch/x86/kernel/cpu/centaur.c1
-rw-r--r--arch/x86/kernel/cpu/common.c24
-rw-r--r--arch/x86/kernel/cpu/cpu.h4
-rw-r--r--arch/x86/kernel/cpu/intel.c11
-rw-r--r--arch/x86/kernel/cpu/mce/core.c6
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c8
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h1
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c1
-rw-r--r--arch/x86/kernel/cpu/umwait.c6
-rw-r--r--arch/x86/kernel/cpu/zhaoxin.c1
-rw-r--r--arch/x86/kernel/dumpstack.c27
-rw-r--r--arch/x86/kernel/fpu/core.c45
-rw-r--r--arch/x86/kernel/fpu/xstate.c91
-rw-r--r--arch/x86/kernel/ftrace.c10
-rw-r--r--arch/x86/kernel/i8259.c2
-rw-r--r--arch/x86/kernel/kgdb.c6
-rw-r--r--arch/x86/kernel/kprobes/core.c36
-rw-r--r--arch/x86/kernel/kprobes/opt.c40
-rw-r--r--arch/x86/kernel/kvm.c6
-rw-r--r--arch/x86/kernel/ldt.c26
-rw-r--r--arch/x86/kernel/nmi.c11
-rw-r--r--arch/x86/kernel/paravirt.c3
-rw-r--r--arch/x86/kernel/probe_roms.c24
-rw-r--r--arch/x86/kernel/process.c18
-rw-r--r--arch/x86/kernel/smpboot.c50
-rw-r--r--arch/x86/kernel/stacktrace.c5
-rw-r--r--arch/x86/kernel/traps.c118
-rw-r--r--arch/x86/kernel/unwind_orc.c8
-rw-r--r--arch/x86/kernel/vmlinux.lds.S1
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h2
-rw-r--r--arch/x86/kvm/lapic.c52
-rw-r--r--arch/x86/kvm/mmu.h2
-rw-r--r--arch/x86/kvm/mmu/mmu.c6
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h16
-rw-r--r--arch/x86/kvm/svm/svm.c11
-rw-r--r--arch/x86/kvm/vmx/nested.c21
-rw-r--r--arch/x86/kvm/vmx/nested.h5
-rw-r--r--arch/x86/kvm/vmx/vmcs.h32
-rw-r--r--arch/x86/kvm/vmx/vmx.c40
-rw-r--r--arch/x86/kvm/vmx/vmx.h2
-rw-r--r--arch/x86/kvm/x86.c12
-rw-r--r--arch/x86/lib/memcpy_64.S4
-rw-r--r--arch/x86/lib/usercopy_64.c1
-rw-r--r--arch/x86/math-emu/wm_sqrt.S2
-rw-r--r--arch/x86/mm/fault.c14
-rw-r--r--arch/x86/mm/init_32.c2
-rw-r--r--arch/x86/mm/maccess.c4
-rw-r--r--arch/x86/mm/pat/set_memory.c2
-rw-r--r--arch/x86/pci/pcbios.c2
-rw-r--r--arch/x86/platform/intel-mid/sfi.c4
-rw-r--r--arch/x86/platform/uv/uv_irq.c3
-rw-r--r--arch/x86/power/cpu.c6
-rw-r--r--arch/x86/purgatory/Makefile1
-rw-r--r--arch/x86/xen/enlighten_pv.c42
-rw-r--r--arch/x86/xen/xen-asm_64.S25
-rw-r--r--arch/xtensa/include/asm/atomic.h2
-rw-r--r--arch/xtensa/include/asm/checksum.h2
-rw-r--r--arch/xtensa/kernel/perf_event.c4
-rw-r--r--arch/xtensa/kernel/setup.c3
-rw-r--r--arch/xtensa/kernel/xtensa_ksyms.c4
-rw-r--r--arch/xtensa/platforms/iss/simdisk.c11
631 files changed, 6741 insertions, 19199 deletions
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 2144530d1428..e41c113c6688 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -16,15 +16,14 @@
 
 /*
  * To ensure dependency ordering is preserved for the _relaxed and
- * _release atomics, an smp_read_barrier_depends() is unconditionally
- * inserted into the _relaxed variants, which are used to build the
- * barriered versions. Avoid redundant back-to-back fences in the
- * _acquire and _fence versions.
+ * _release atomics, an smp_mb() is unconditionally inserted into the
+ * _relaxed variants, which are used to build the barriered versions.
+ * Avoid redundant back-to-back fences in the _acquire and _fence
+ * versions.
  */
 #define __atomic_acquire_fence()
 #define __atomic_post_full_fence()
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
@@ -70,7 +69,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -88,7 +87,7 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -123,7 +122,7 @@ static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -141,7 +140,7 @@ static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index 92ec486a4f9e..c56bfffc9918 100644
--- a/arch/alpha/include/asm/barrier.h
+++ b/arch/alpha/include/asm/barrier.h
@@ -2,64 +2,15 @@
 #ifndef __BARRIER_H
 #define __BARRIER_H
 
-#include <asm/compiler.h>
-
 #define mb()	__asm__ __volatile__("mb": : :"memory")
 #define rmb()	__asm__ __volatile__("mb": : :"memory")
 #define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
+#define __smp_load_acquire(p)						\
+({									\
+	compiletime_assert_atomic_type(*p);				\
+	__READ_ONCE(*p);						\
+})
 
 #ifdef CONFIG_SMP
 #define __ASM_SMP_MB	"\tmb\n"
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index 162c17b2631f..660b14ce1317 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -277,9 +277,9 @@ extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; retur
 extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
 
 /*
- * The smp_read_barrier_depends() in the following functions are required to
- * order the load of *dir (the pointer in the top level page table) with any
- * subsequent load of the returned pmd_t *ret (ret is data dependent on *dir).
+ * The smp_rmb() in the following functions are required to order the load of
+ * *dir (the pointer in the top level page table) with any subsequent load of
+ * the returned pmd_t *ret (ret is data dependent on *dir).
  *
  * If this ordering is not enforced, the CPU might load an older value of
  * *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for
@@ -293,7 +293,7 @@ extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; retu
 extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address)
 {
 	pmd_t *ret = (pmd_t *) pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
-	smp_read_barrier_depends(); /* see above */
+	smp_rmb(); /* see above */
 	return ret;
 }
 #define pmd_offset pmd_offset
@@ -303,7 +303,7 @@ extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
 {
 	pte_t *ret = (pte_t *) pmd_page_vaddr(*dir)
 		+ ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1));
-	smp_read_barrier_depends(); /* see above */
+	smp_rmb(); /* see above */
 	return ret;
 }
 #define pte_offset_kernel pte_offset_kernel
diff --git a/arch/alpha/include/asm/rwonce.h b/arch/alpha/include/asm/rwonce.h
new file mode 100644
index 000000000000..35542bcf92b3
--- /dev/null
+++ b/arch/alpha/include/asm/rwonce.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Google LLC.
+ */
+#ifndef __ASM_RWONCE_H
+#define __ASM_RWONCE_H
+
+#ifdef CONFIG_SMP
+
+#include <asm/barrier.h>
+
+/*
+ * Alpha is apparently daft enough to reorder address-dependent loads
+ * on some CPU implementations. Knock some common sense into it with
+ * a memory barrier in READ_ONCE().
+ *
+ * For the curious, more information about this unusual reordering is
+ * available in chapter 15 of the "perfbook":
+ *
+ *  https://kernel.org/pub/linux/kernel/people/paulmck/perfbook/perfbook.html
+ *
+ */
+#define __READ_ONCE(x)							\
+({									\
+	__unqual_scalar_typeof(x) __x =					\
+		(*(volatile typeof(__x) *)(&(x)));			\
+	mb();								\
+	(typeof(x))__x;							\
+})
+
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/rwonce.h>
+
+#endif /* __ASM_RWONCE_H */
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index fddc70029727..197896cfbd23 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -170,6 +170,15 @@ config ARC_CPU_HS
 
 endchoice
 
+config ARC_TUNE_MCPU
+	string "Override default -mcpu compiler flag"
+	default ""
+	help
+	  Override default -mcpu=xxx compiler flag (which is set depending on
+	  the ISA version) with the specified value.
+	  NOTE: If specified flag isn't supported by current compiler the
+	  ISA default value will be used as a fallback.
+
 config CPU_BIG_ENDIAN
 	bool "Enable Big Endian Mode"
 	help
@@ -465,6 +474,12 @@ config ARC_IRQ_NO_AUTOSAVE
 	  This is programmable and can be optionally disabled in which case
 	  software INTERRUPT_PROLOGUE/EPILGUE do the needed work
 
+config ARC_LPB_DISABLE
+	bool "Disable loop buffer (LPB)"
+	help
+	  On HS cores, loop buffer (LPB) is programmable in runtime and can
+	  be optionally disabled.
+
 endif # ISA_ARCV2
 
 endmenu   # "ARC CPU Configuration"
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 20e9ab6cc521..d00f8b8afd08 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -10,8 +10,25 @@ CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-)
 endif
 
 cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
-cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
-cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=hs38
+
+tune-mcpu-def-$(CONFIG_ISA_ARCOMPACT)	:= -mcpu=arc700
+tune-mcpu-def-$(CONFIG_ISA_ARCV2)	:= -mcpu=hs38
+
+ifeq ($(CONFIG_ARC_TUNE_MCPU),"")
+cflags-y				+= $(tune-mcpu-def-y)
+else
+tune-mcpu				:= $(shell echo $(CONFIG_ARC_TUNE_MCPU))
+tune-mcpu-ok 				:= $(call cc-option-yn, $(tune-mcpu))
+ifeq ($(tune-mcpu-ok),y)
+cflags-y				+= $(tune-mcpu)
+else
+# The flag provided by 'CONFIG_ARC_TUNE_MCPU' option isn't known by this compiler
+# (probably the compiler is too old). Use ISA default mcpu flag instead as a safe option.
+$(warning ** WARNING ** CONFIG_ARC_TUNE_MCPU flag '$(tune-mcpu)' is unknown, fallback to '$(tune-mcpu-def-y)')
+cflags-y				+= $(tune-mcpu-def-y)
+endif
+endif
+
 
 ifdef CONFIG_ARC_CURR_IN_REG
 # For a global register defintion, make sure it gets passed to every file
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 7298ce84762e..c614857eb209 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -14,8 +14,6 @@
 #include <asm/barrier.h>
 #include <asm/smp.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifndef CONFIG_ARC_PLAT_EZNPS
 
 #define atomic_read(v)  READ_ONCE((v)->counter)
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index c77a0e3671ac..0284ace0e1ab 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -19,7 +19,7 @@
 #define  R_ARC_32_PCREL		0x31
 
 /*to set parameters in the core dumps */
-#define ELF_ARCH		EM_ARCOMPACT
+#define ELF_ARCH		EM_ARC_INUSE
 #define ELF_CLASS		ELFCLASS32
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index 7fc73fef5e29..863d63ad18d6 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -90,6 +90,9 @@ static inline void arch_local_irq_restore(unsigned long flags)
 /*
  * Unconditionally Enable IRQs
  */
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+extern void arch_local_irq_enable(void);
+#else
 static inline void arch_local_irq_enable(void)
 {
 	unsigned long temp;
@@ -102,7 +105,7 @@ static inline void arch_local_irq_enable(void)
 	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
 	: "cc", "memory");
 }
-
+#endif
 
 /*
  * Unconditionally Disable IRQs
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 60406ec62eb8..ea00c8a17f07 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -165,7 +165,6 @@ END(EV_Extension)
 tracesys:
 	; save EFA in case tracer wants the PC of traced task
 	; using ERET won't work since next-PC has already committed
-	lr  r12, [efa]
 	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
 	st  r12, [r11, THREAD_FAULT_ADDR]	; thread.fault_address
 
@@ -208,15 +207,9 @@ tracesys_exit:
 ; Breakpoint TRAP
 ; ---------------------------------------------
 trap_with_param:
-
-	; stop_pc info by gdb needs this info
-	lr  r0, [efa]
+	mov r0, r12	; EFA in case ptracer/gdb wants stop_pc
 	mov r1, sp
 
-	; Now that we have read EFA, it is safe to do "fake" rtie
-	;   and get out of CPU exception mode
-	FAKE_RET_FROM_EXCPN
-
 	; Save callee regs in case gdb wants to have a look
 	; SP will grow up by size of CALLEE Reg-File
 	; NOTE: clobbers r12
@@ -243,6 +236,10 @@ ENTRY(EV_Trap)
 
 	EXCEPTION_PROLOGUE
 
+	lr  r12, [efa]
+
+	FAKE_RET_FROM_EXCPN
+
 	;============ TRAP 1   :breakpoints
 	; Check ECR for trap with arg (PROLOGUE ensures r10 has ECR)
 	bmsk.f 0, r10, 7
@@ -250,9 +247,6 @@ ENTRY(EV_Trap)
 
 	;============ TRAP  (no param): syscall top level
 
-	; First return from Exception to pure K mode (Exception/IRQs renabled)
-	FAKE_RET_FROM_EXCPN
-
 	; If syscall tracing ongoing, invoke pre-post-hooks
 	GET_CURR_THR_INFO_FLAGS   r10
 	btst r10, TIF_SYSCALL_TRACE
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 6eb23f1545ee..17fd1ed700cc 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -59,6 +59,14 @@
 	bclr	r5, r5, STATUS_AD_BIT
 #endif
 	kflag	r5
+
+#ifdef CONFIG_ARC_LPB_DISABLE
+	lr	r5, [ARC_REG_LPB_BUILD]
+	breq    r5, 0, 1f		; LPB doesn't exist
+	mov	r5, 1
+	sr	r5, [ARC_REG_LPB_CTRL]
+1:
+#endif /* CONFIG_ARC_LPB_DISABLE */
 #endif
 	; Config DSP_CTRL properly, so kernel may use integer multiply,
 	; multiply-accumulate, and divide operations
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index dad8a656a2f1..41f07b3e594e 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -58,10 +58,12 @@ static const struct id_to_str arc_legacy_rel[] = {
 	{ 0x00,		NULL   }
 };
 
-static const struct id_to_str arc_cpu_rel[] = {
+static const struct id_to_str arc_hs_ver54_rel[] = {
 	/* UARCH.MAJOR,	Release */
 	{  0,		"R3.10a"},
 	{  1,		"R3.50a"},
+	{  2,		"R3.60a"},
+	{  3,		"R4.00a"},
 	{  0xFF,	NULL   }
 };
 
@@ -117,12 +119,6 @@ static void decode_arc_core(struct cpuinfo_arc *cpu)
 	struct bcr_uarch_build_arcv2 uarch;
 	const struct id_to_str *tbl;
 
-	/*
-	 * Up until (including) the first core4 release (0x54) things were
-	 * simple: AUX IDENTITY.ARCVER was sufficient to identify arc family
-	 * and release: 0x50 to 0x53 was HS38, 0x54 was HS48 (dual issue)
-	 */
-
 	if (cpu->core.family < 0x54) { /* includes arc700 */
 
 		for (tbl = &arc_legacy_rel[0]; tbl->id != 0; tbl++) {
@@ -143,11 +139,10 @@ static void decode_arc_core(struct cpuinfo_arc *cpu)
 	}
 
 	/*
-	 * However the subsequent HS release (same 0x54) allow HS38 or HS48
-	 * configurations and encode this info in a different BCR.
-	 * The BCR was introduced in 0x54 so can't be read unconditionally.
+	 * Initial HS cores bumped AUX IDENTITY.ARCVER for each release until
+	 * ARCVER 0x54 which introduced AUX MICRO_ARCH_BUILD and subsequent
+	 * releases only update it.
 	 */
-
 	READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
 
 	if (uarch.prod == 4) {
@@ -158,7 +153,7 @@ static void decode_arc_core(struct cpuinfo_arc *cpu)
 		cpu->name = "HS38";
 	}
 
-	for (tbl = &arc_cpu_rel[0]; tbl->id != 0xFF; tbl++) {
+	for (tbl = &arc_hs_ver54_rel[0]; tbl->id != 0xFF; tbl++) {
 		if (uarch.maj == tbl->id) {
 			cpu->release = tbl->str;
 			break;
diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi
index 05e7b5d4a95b..04f0b1227efe 100644
--- a/arch/arm/boot/dts/am335x-baltos.dtsi
+++ b/arch/arm/boot/dts/am335x-baltos.dtsi
@@ -369,7 +369,7 @@
 &mmc2 {
 	status = "okay";
 	vmmc-supply = <&wl12xx_vmmc>;
-	ti,non-removable;
+	non-removable;
 	bus-width = <4>;
 	cap-power-off-card;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/am335x-boneblack-common.dtsi b/arch/arm/boot/dts/am335x-boneblack-common.dtsi
index 91f93bc89716..dd932220a8bf 100644
--- a/arch/arm/boot/dts/am335x-boneblack-common.dtsi
+++ b/arch/arm/boot/dts/am335x-boneblack-common.dtsi
@@ -22,6 +22,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	bus-width = <8>;
 	status = "okay";
+	non-removable;
 };
 
 &am33xx_pinmux {
diff --git a/arch/arm/boot/dts/am335x-boneblack-wireless.dts b/arch/arm/boot/dts/am335x-boneblack-wireless.dts
index 3124d94c0b3c..e07dd7979586 100644
--- a/arch/arm/boot/dts/am335x-boneblack-wireless.dts
+++ b/arch/arm/boot/dts/am335x-boneblack-wireless.dts
@@ -75,7 +75,6 @@
 	bus-width = <4>;
 	non-removable;
 	cap-power-off-card;
-	ti,needs-special-hs-handling;
 	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins &wl18xx_pins>;
diff --git a/arch/arm/boot/dts/am335x-boneblue.dts b/arch/arm/boot/dts/am335x-boneblue.dts
index 5811fb8d4fdf..83f9452c9cd3 100644
--- a/arch/arm/boot/dts/am335x-boneblue.dts
+++ b/arch/arm/boot/dts/am335x-boneblue.dts
@@ -367,7 +367,6 @@
 	bus-width = <4>;
 	non-removable;
 	cap-power-off-card;
-	ti,needs-special-hs-handling;
 	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins &wl18xx_pins>;
diff --git a/arch/arm/boot/dts/am335x-bonegreen-wireless.dts b/arch/arm/boot/dts/am335x-bonegreen-wireless.dts
index 4092cd193b8a..609c8db687ec 100644
--- a/arch/arm/boot/dts/am335x-bonegreen-wireless.dts
+++ b/arch/arm/boot/dts/am335x-bonegreen-wireless.dts
@@ -75,7 +75,6 @@
 	bus-width = <4>;
 	non-removable;
 	cap-power-off-card;
-	ti,needs-special-hs-handling;
 	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins &wl18xx_pins>;
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index 68252dab32c3..a4fc6b168a85 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -743,8 +743,7 @@
 	bus-width = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins &wlan_pins>;
-	ti,non-removable;
-	ti,needs-special-hs-handling;
+	non-removable;
 	cap-power-off-card;
 	keep-power-in-suspend;
 
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 32f515a295ee..78b6e1f594c9 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -655,7 +655,7 @@
 &mmc2 {
 	status = "okay";
 	vmmc-supply = <&wl12xx_vmmc>;
-	ti,non-removable;
+	non-removable;
 	bus-width = <4>;
 	cap-power-off-card;
 	keep-power-in-suspend;
diff --git a/arch/arm/boot/dts/am335x-lxm.dts b/arch/arm/boot/dts/am335x-lxm.dts
index fef582852820..dbedf729205c 100644
--- a/arch/arm/boot/dts/am335x-lxm.dts
+++ b/arch/arm/boot/dts/am335x-lxm.dts
@@ -339,7 +339,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	vmmc-supply = <&vmmcsd_fixed>;
 	bus-width = <8>;
-	ti,non-removable;
+	non-removable;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi b/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi
index 6495a125c01f..4e90f9c23d2e 100644
--- a/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi
+++ b/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi
@@ -159,7 +159,7 @@
 	vmmc-supply = <&vmmcsd_fixed>;
 	bus-width = <8>;
 	pinctrl-0 = <&mmc1_pins_default>;
-	ti,non-removable;
+	non-removable;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts b/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts
index 244df9c5a537..f03e72cada41 100644
--- a/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts
+++ b/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts
@@ -451,7 +451,7 @@
 	vmmc-supply = <&vmmcsd_fixed>;
 	bus-width = <8>;
 	pinctrl-0 = <&mmc2_pins_default>;
-	ti,non-removable;
+	non-removable;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts
index 6d7608d9377b..f9a027b47962 100644
--- a/arch/arm/boot/dts/am335x-pepper.dts
+++ b/arch/arm/boot/dts/am335x-pepper.dts
@@ -341,7 +341,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	vmmc-supply = <&ldo3_reg>;
 	bus-width = <8>;
-	ti,non-removable;
+	non-removable;
 };
 
 &mmc3 {
@@ -351,7 +351,7 @@
 	pinctrl-0 = <&wireless_pins>;
 	vmmmc-supply = <&v3v3c_reg>;
 	bus-width = <4>;
-	ti,non-removable;
+	non-removable;
 	dmas = <&edma_xbar 12 0 1
 		&edma_xbar 13 0 2>;
 	dma-names = "tx", "rx";
diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi
index 3d0672b53d77..7e46b4c02709 100644
--- a/arch/arm/boot/dts/am335x-phycore-som.dtsi
+++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi
@@ -69,7 +69,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	vmmc-supply = <&vmmc_reg>;
 	bus-width = <8>;
-	ti,non-removable;
+	non-removable;
 	status = "disabled";
 };
 
diff --git a/arch/arm/boot/dts/am335x-pocketbeagle.dts b/arch/arm/boot/dts/am335x-pocketbeagle.dts
index 4da719098028..f0b222201b86 100644
--- a/arch/arm/boot/dts/am335x-pocketbeagle.dts
+++ b/arch/arm/boot/dts/am335x-pocketbeagle.dts
@@ -88,7 +88,6 @@
 			AM33XX_PADCONF(AM335X_PIN_MMC0_DAT3, PIN_INPUT_PULLUP, MUX_MODE0)
 			AM33XX_PADCONF(AM335X_PIN_MMC0_CMD, PIN_INPUT_PULLUP, MUX_MODE0)
 			AM33XX_PADCONF(AM335X_PIN_MMC0_CLK, PIN_INPUT_PULLUP, MUX_MODE0)
-			AM33XX_PADCONF(AM335X_PIN_MCASP0_ACLKR, PIN_INPUT, MUX_MODE4)		/* (B12) mcasp0_aclkr.mmc0_sdwp */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi
index 7ff11d6bf0f2..a9cbefc80c0c 100644
--- a/arch/arm/boot/dts/am33xx-l4.dtsi
+++ b/arch/arm/boot/dts/am33xx-l4.dtsi
@@ -1335,10 +1335,8 @@
 			ranges = <0x0 0x60000 0x1000>;
 
 			mmc1: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
-				ti,dual-volt;
+				compatible = "ti,am335-sdhci";
 				ti,needs-special-reset;
-				ti,needs-special-hs-handling;
 				dmas = <&edma_xbar 24 0 0
 					&edma_xbar 25 0 0>;
 				dma-names = "tx", "rx";
@@ -1816,7 +1814,7 @@
 			ranges = <0x0 0xd8000 0x1000>;
 
 			mmc2: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am335-sdhci";
 				ti,needs-special-reset;
 				dmas = <&edma 2 0
 					&edma 3 0>;
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 3b177c9c4412..5fdce106edbb 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -322,10 +322,11 @@
 			ranges = <0x0 0x47810000 0x1000>;
 
 			mmc3: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am335-sdhci";
 				ti,needs-special-reset;
 				interrupts = <29>;
 				reg = <0x0 0x1000>;
+				status = "disabled";
 			};
 		};
 
@@ -335,7 +336,7 @@
 			      <0x47400010 0x4>;
 			reg-names = "rev", "sysc";
 			ti,sysc-mask = <(SYSC_OMAP4_FREEEMU |
-					 SYSC_OMAP2_SOFTRESET)>;
+					 SYSC_OMAP4_SOFTRESET)>;
 			ti,sysc-midle = <SYSC_IDLE_FORCE>,
 					<SYSC_IDLE_NO>,
 					<SYSC_IDLE_SMART>;
@@ -347,7 +348,7 @@
 			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges = <0x0 0x47400000 0x5000>;
+			ranges = <0x0 0x47400000 0x8000>;
 
 			usb0_phy: usb-phy@1300 {
 				compatible = "ti,am335x-usb-phy";
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index b4861f70f178..51ad9e881a62 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -316,10 +316,11 @@
 			ranges = <0x0 0x47810000 0x1000>;
 
 			mmc3: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am437-sdhci";
 				ti,needs-special-reset;
 				interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x0 0x1000>;
+				status = "disabled";
 			};
 		};
 
diff --git a/arch/arm/boot/dts/am437x-cm-t43.dts b/arch/arm/boot/dts/am437x-cm-t43.dts
index 063113a5da2d..a6b4fca8626a 100644
--- a/arch/arm/boot/dts/am437x-cm-t43.dts
+++ b/arch/arm/boot/dts/am437x-cm-t43.dts
@@ -291,7 +291,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	vmmc-supply = <&vmmc_3v3>;
 	bus-width = <8>;
-	ti,non-removable;
+	non-removable;
 };
 
 &spi0 {
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index d692e3b2812a..77378630e5ec 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -91,22 +91,6 @@
 
 		backlight = <&lcd_bl>;
 
-		panel-timing {
-			clock-frequency = <33000000>;
-			hactive = <800>;
-			vactive = <480>;
-			hfront-porch = <210>;
-			hback-porch = <16>;
-			hsync-len = <30>;
-			vback-porch = <10>;
-			vfront-porch = <22>;
-			vsync-len = <13>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
-
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
@@ -869,7 +853,7 @@
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&emmc_pins_default>;
 	pinctrl-1 = <&emmc_pins_sleep>;
-	ti,non-removable;
+	non-removable;
 };
 
 &mmc3 {
@@ -886,7 +870,7 @@
 	pinctrl-1 = <&mmc3_pins_sleep>;
 	cap-power-off-card;
 	keep-power-in-suspend;
-	ti,non-removable;
+	non-removable;
 
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi
index 0d0f9fe4a882..906ac29f017d 100644
--- a/arch/arm/boot/dts/am437x-l4.dtsi
+++ b/arch/arm/boot/dts/am437x-l4.dtsi
@@ -1083,9 +1083,8 @@
 			ranges = <0x0 0x60000 0x1000>;
 
 			mmc1: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am437-sdhci";
 				reg = <0x0 0x1000>;
-				ti,dual-volt;
 				ti,needs-special-reset;
 				dmas = <&edma 24 0>,
 					<&edma 25 0>;
@@ -1541,8 +1540,9 @@
 			reg = <0xcc020 0x4>;
 			reg-names = "rev";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>;
-			clock-names = "fck";
+			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>,
+			<&dcan0_fck>;
+			clock-names = "fck", "osc";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0xcc000 0x2000>;
@@ -1550,6 +1550,8 @@
 			dcan0: can@0 {
 				compatible = "ti,am4372-d_can", "ti,am3352-d_can";
 				reg = <0x0 0x2000>;
+				clocks = <&dcan0_fck>;
+				clock-names = "fck";
 				syscon-raminit = <&scm_conf 0x644 0>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
@@ -1561,8 +1563,9 @@
 			reg = <0xd0020 0x4>;
 			reg-names = "rev";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>;
-			clock-names = "fck";
+			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>,
+			<&dcan1_fck>;
+			clock-names = "fck", "osc";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0xd0000 0x2000>;
@@ -1570,6 +1573,8 @@
 			dcan1: can@0 {
 				compatible = "ti,am4372-d_can", "ti,am3352-d_can";
 				reg = <0x0 0x2000>;
+				clocks = <&dcan1_fck>;
+				clock-name = "fck";
 				syscon-raminit = <&scm_conf 0x644 1>;
 				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
@@ -1598,7 +1603,7 @@
 			ranges = <0x0 0xd8000 0x1000>;
 
 			mmc2: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am437-sdhci";
 				reg = <0x0 0x1000>;
 				ti,needs-special-reset;
 				dmas = <&edma 2 0>,
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 4d5a7ca2e25d..08eabf0f3cbd 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -134,22 +134,6 @@
 
 		enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
 
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <2>;
-			hback-porch = <2>;
-			hsync-len = <41>;
-			vfront-porch = <2>;
-			vback-porch = <2>;
-			vsync-len = <10>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
-
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
@@ -719,7 +703,7 @@
 	pinctrl-1 = <&mmc3_pins_sleep>;
 	cap-power-off-card;
 	keep-power-in-suspend;
-	ti,non-removable;
+	non-removable;
 
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 27259fd6f741..7d4e0dffde7a 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -47,22 +47,6 @@
 
 		backlight = <&lcd_bl>;
 
-		panel-timing {
-			clock-frequency = <33000000>;
-			hactive = <800>;
-			vactive = <480>;
-			hfront-porch = <210>;
-			hback-porch = <16>;
-			hsync-len = <30>;
-			vback-porch = <10>;
-			vfront-porch = <22>;
-			vsync-len = <13>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
-
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
diff --git a/arch/arm/boot/dts/am5729-beagleboneai.dts b/arch/arm/boot/dts/am5729-beagleboneai.dts
index 9877d7709d41..4c51c6b05e64 100644
--- a/arch/arm/boot/dts/am5729-beagleboneai.dts
+++ b/arch/arm/boot/dts/am5729-beagleboneai.dts
@@ -505,7 +505,7 @@
 
 &cpsw_emac0 {
 	phy-handle = <&phy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 };
 
 &ocp {
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 348116501aa2..9b1a24cc5e91 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -342,7 +342,8 @@
 
 			comphy: phy@18300 {
 				compatible = "marvell,armada-380-comphy";
-				reg = <0x18300 0x100>;
+				reg-names = "comphy", "conf";
+				reg = <0x18300 0x100>, <0x18460 4>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index da6d70f09ef1..3175266ede64 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -200,7 +200,7 @@
 			status = "disabled";
 		};
 
-		dma@20000 {
+		dma: dma@20000 {
 			compatible = "arm,pl330", "arm,primecell";
 			reg = <0x20000 0x1000>;
 			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
@@ -215,6 +215,8 @@
 			clocks = <&iprocslow>;
 			clock-names = "apb_pclk";
 			#dma-cells = <1>;
+			dma-coherent;
+			status = "disabled";
 		};
 
 		sdio: sdhci@21000 {
@@ -257,10 +259,10 @@
 			status = "disabled";
 		};
 
-		mailbox: mailbox@25000 {
+		mailbox: mailbox@25c00 {
 			compatible = "brcm,iproc-fa2-mbox";
-			reg = <0x25000 0x445>;
-			interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
+			reg = <0x25c00 0x400>;
+			interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 			#mbox-cells = <1>;
 			brcm,rx-status-len = <32>;
 			brcm,use-bcm-hdr;
diff --git a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts
index 334325390aed..29bbecd36f65 100644
--- a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts
+++ b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts
@@ -17,6 +17,7 @@
 	};
 
 	memory {
+		device_type = "memory";
 		reg = <0x00000000 0x08000000
 		       0x88000000 0x18000000>;
 	};
diff --git a/arch/arm/boot/dts/bcm958522er.dts b/arch/arm/boot/dts/bcm958522er.dts
index 8c388eb8a08f..7be4c4e628e0 100644
--- a/arch/arm/boot/dts/bcm958522er.dts
+++ b/arch/arm/boot/dts/bcm958522er.dts
@@ -58,6 +58,10 @@
 
 /* USB 3 support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958525er.dts b/arch/arm/boot/dts/bcm958525er.dts
index c339771bb22e..e58ed7e95346 100644
--- a/arch/arm/boot/dts/bcm958525er.dts
+++ b/arch/arm/boot/dts/bcm958525er.dts
@@ -58,6 +58,10 @@
 
 /* USB 3 support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts
index 1c72ec8288de..716da62f5788 100644
--- a/arch/arm/boot/dts/bcm958525xmc.dts
+++ b/arch/arm/boot/dts/bcm958525xmc.dts
@@ -58,6 +58,10 @@
 
 /* XHCI support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958622hr.dts b/arch/arm/boot/dts/bcm958622hr.dts
index 96a021cebd97..a49c2fd21f4a 100644
--- a/arch/arm/boot/dts/bcm958622hr.dts
+++ b/arch/arm/boot/dts/bcm958622hr.dts
@@ -58,6 +58,10 @@
 
 /* USB 3 and SLIC support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts
index b2c7f21d471e..dd6dff6452b8 100644
--- a/arch/arm/boot/dts/bcm958623hr.dts
+++ b/arch/arm/boot/dts/bcm958623hr.dts
@@ -58,6 +58,10 @@
 
 /* USB 3 and SLIC support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
index 536fb24f38bb..a71371b4065e 100644
--- a/arch/arm/boot/dts/bcm958625hr.dts
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -69,6 +69,10 @@
 	status = "okay";
 };
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958625k.dts b/arch/arm/boot/dts/bcm958625k.dts
index 3fcca12d83c2..7b84b54436ed 100644
--- a/arch/arm/boot/dts/bcm958625k.dts
+++ b/arch/arm/boot/dts/bcm958625k.dts
@@ -48,6 +48,10 @@
 	};
 };
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/dra7-evm-common.dtsi b/arch/arm/boot/dts/dra7-evm-common.dtsi
index f89a64cbcd53..2cf6a529d4ad 100644
--- a/arch/arm/boot/dts/dra7-evm-common.dtsi
+++ b/arch/arm/boot/dts/dra7-evm-common.dtsi
@@ -245,26 +245,6 @@
 	rx-num-evt = <32>;
 };
 
-&mailbox5 {
-	status = "okay";
-	mbox_ipu1_ipc3x: mbox_ipu1_ipc3x {
-		status = "okay";
-	};
-	mbox_dsp1_ipc3x: mbox_dsp1_ipc3x {
-		status = "okay";
-	};
-};
-
-&mailbox6 {
-	status = "okay";
-	mbox_ipu2_ipc3x: mbox_ipu2_ipc3x {
-		status = "okay";
-	};
-	mbox_dsp2_ipc3x: mbox_dsp2_ipc3x {
-		status = "okay";
-	};
-};
-
 &pcie1_rc {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi
index 62ca89551219..0c6f26605506 100644
--- a/arch/arm/boot/dts/dra7-l4.dtsi
+++ b/arch/arm/boot/dts/dra7-l4.dtsi
@@ -1207,9 +1207,8 @@
 					<SYSC_IDLE_SMART>,
 					<SYSC_IDLE_SMART_WKUP>;
 			/* Domains (P, C): l4per_pwrdm, l4per_clkdm */
-			clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 0>,
-				 <&timer_sys_clk_div>;
-			clock-names = "fck", "timer_sys_ck";
+			clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x36000 0x1000>;
@@ -3352,8 +3351,8 @@
 					<SYSC_IDLE_SMART>,
 					<SYSC_IDLE_SMART_WKUP>;
 			/* Domains (P, C): ipu_pwrdm, ipu_clkdm */
-			clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 0>, <&timer_sys_clk_div>;
-			clock-names = "fck", "timer_sys_ck";
+			clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x20000 0x1000>;
@@ -3361,8 +3360,8 @@
 			timer5: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
@@ -3379,9 +3378,8 @@
 					<SYSC_IDLE_SMART>,
 					<SYSC_IDLE_SMART_WKUP>;
 			/* Domains (P, C): ipu_pwrdm, ipu_clkdm */
-			clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 0>,
-				 <&timer_sys_clk_div>;
-			clock-names = "fck", "timer_sys_ck";
+			clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x22000 0x1000>;
@@ -3389,8 +3387,8 @@
 			timer6: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
@@ -3498,8 +3496,8 @@
 			timer14: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>;
 				ti,timer-pwm;
 			};
@@ -3526,8 +3524,8 @@
 			timer15: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>;
 				ti,timer-pwm;
 			};
@@ -3554,8 +3552,8 @@
 			timer16: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>;
 				ti,timer-pwm;
 			};
diff --git a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
index c38e86eedcc0..8c33510c9519 100644
--- a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
@@ -110,7 +110,7 @@
 		simple-audio-card,frame-master = <&sound_codec>;
 
 		sound_cpu: simple-audio-card,cpu {
-			sound-dai = <&ssi2>;
+			sound-dai = <&ssi1>;
 		};
 
 		sound_codec: simple-audio-card,codec {
diff --git a/arch/arm/boot/dts/imx6qdl-icore.dtsi b/arch/arm/boot/dts/imx6qdl-icore.dtsi
index 756f3a9f1b4f..12997dae35d9 100644
--- a/arch/arm/boot/dts/imx6qdl-icore.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-icore.dtsi
@@ -397,7 +397,7 @@
 
 	pinctrl_usbotg: usbotggrp {
 		fsl,pins = <
-			MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059
+			MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
 		>;
 	};
 
@@ -409,6 +409,7 @@
 			MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17070
 			MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17070
 			MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17070
+			MX6QDL_PAD_GPIO_1__GPIO1_IO01  0x1b0b0
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index 825924448ab4..14fd1de52a68 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -99,7 +99,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy0>;
 	fsl,magic-packet;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index 3e5fb72f21fc..c99aa273c296 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -213,7 +213,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy2>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi
index f05e91841202..53a25fba34f6 100644
--- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi
+++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi
@@ -232,13 +232,6 @@
 	status = "okay";
 };
 
-&wdog1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_wdog>;
-	fsl,ext-reset-output;
-	status = "okay";
-};
-
 &iomuxc {
 	pinctrl-0 = <&pinctrl_reset_out &pinctrl_gpio>;
 
@@ -409,10 +402,4 @@
 			MX6UL_PAD_NAND_DATA03__USDHC2_DATA3	0x170f9
 		>;
 	};
-
-	pinctrl_wdog: wdoggrp {
-		fsl,pins = <
-			MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY	0x30b0
-		>;
-	};
 };
diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
index a17af4d9bfdf..61ba21a605a8 100644
--- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
+++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
@@ -57,6 +57,13 @@
 	status = "okay";
 };
 
+&wdog1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	fsl,ext-reset-output;
+	status = "okay";
+};
+
 &iomuxc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_reset_out>;
@@ -106,4 +113,10 @@
 			MX6UL_PAD_SNVS_TAMPER9__GPIO5_IO09      0x1b0b0
 		>;
 	};
+
+	pinctrl_wdog: wdoggrp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY    0x18b0
+		>;
+	};
 };
diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts
index db640bab8c1d..8b3d64c913d8 100644
--- a/arch/arm/boot/dts/keystone-k2g-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2g-evm.dts
@@ -402,7 +402,7 @@
 
 &gbe0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii-id";
+	phy-mode = "rgmii-rxid";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi
index ae89deaa8c9c..91129dc70d83 100644
--- a/arch/arm/boot/dts/meson.dtsi
+++ b/arch/arm/boot/dts/meson.dtsi
@@ -11,7 +11,7 @@
 	#size-cells = <1>;
 	interrupt-parent = <&gic>;
 
-	L2: l2-cache-controller@c4200000 {
+	L2: cache-controller@c4200000 {
 		compatible = "arm,pl310-cache";
 		reg = <0xc4200000 0x1000>;
 		cache-unified;
diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
index e39eee628afd..08a7d3ce383f 100644
--- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
+++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
@@ -13,8 +13,10 @@
 		#interrupt-cells = <2>;
 		#address-cells = <1>;
 		#size-cells = <0>;
-		spi-max-frequency = <3000000>;
+		spi-max-frequency = <9600000>;
 		spi-cs-high;
+		spi-cpol;
+		spi-cpha;
 
 		cpcap_adc: adc {
 			compatible = "motorola,mapphone-cpcap-adc";
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 4089d97405c9..3dbcae3d60d2 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -105,6 +105,14 @@
 			linux,code = <SW_FRONT_PROXIMITY>;
 			linux,can-disable;
 		};
+
+		machine_cover {
+			label = "Machine Cover";
+			gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */
+			linux,input-type = <EV_SW>;
+			linux,code = <SW_MACHINE_COVER>;
+			linux,can-disable;
+		};
 	};
 
 	isp1707: isp1707 {
@@ -819,10 +827,6 @@
 	pinctrl-0 = <&mmc1_pins>;
 	vmmc-supply = <&vmmc1>;
 	bus-width = <4>;
-	/* For debugging, it is often good idea to remove this GPIO.
-	   It means you can remove back cover (to reboot by removing
-	   battery) and still use the MMC card. */
-	cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */
 };
 
 /* most boards use vaux3, only some old versions use vmmc2 instead */
diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts
index 8047e8cdb3af..4548d87534e3 100644
--- a/arch/arm/boot/dts/omap4-duovero-parlor.dts
+++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts
@@ -139,7 +139,7 @@
 	ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio2>;
-		interrupts = <12 IRQ_TYPE_EDGE_FALLING>;	/* gpio_44 */
+		interrupts = <12 IRQ_TYPE_LEVEL_LOW>;		/* gpio_44 */
 
 		phy-mode = "mii";
 
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 6c2b07f0704d..4400f5f8e099 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -662,6 +662,6 @@
 	ti,no-idle;
 	timer@0 {
 		assigned-clocks = <&l4_wkup_clkctrl OMAP4_TIMER1_CLKCTRL 24>;
-		assigned-clock-parents = <&sys_clkin_ck>;
+		assigned-clock-parents = <&sys_32k_ck>;
 	};
 };
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index c2b54af417a2..78f3267d9cbf 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -726,7 +726,7 @@
 			};
 		};
 
-		L2: l2-cache@fffef000 {
+		L2: cache-controller@fffef000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffef000 0x1000>;
 			interrupts = <0 38 0x04>;
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index 3b8571b8b412..8f614c4b0e3e 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -636,7 +636,7 @@
 			reg = <0xffcfb100 0x80>;
 		};
 
-		L2: l2-cache@fffff000 {
+		L2: cache-controller@fffff000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffff000 0x1000>;
 			interrupts = <0 18 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index bf531efc0610..0f95a6ef8543 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -198,7 +198,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi
index e6b036734a64..c2b4fbf552a3 100644
--- a/arch/arm/boot/dts/sun5i.dtsi
+++ b/arch/arm/boot/dts/sun5i.dtsi
@@ -117,7 +117,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index ffe1d10a1a84..6d6a37940db2 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -181,7 +181,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index e6308fb76183..a88ee5294d35 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -100,79 +100,6 @@
 		};
 	};
 
-	mcc {
-		compatible = "arm,vexpress,config-bus";
-		arm,vexpress,config-bridge = <&v2m_sysreg>;
-
-		oscclk0 {
-			/* MCC static memory clock */
-			compatible = "arm,vexpress-osc";
-			arm,vexpress-sysreg,func = <1 0>;
-			freq-range = <25000000 60000000>;
-			#clock-cells = <0>;
-			clock-output-names = "v2m:oscclk0";
-		};
-
-		v2m_oscclk1: oscclk1 {
-			/* CLCD clock */
-			compatible = "arm,vexpress-osc";
-			arm,vexpress-sysreg,func = <1 1>;
-			freq-range = <23750000 65000000>;
-			#clock-cells = <0>;
-			clock-output-names = "v2m:oscclk1";
-		};
-
-		v2m_oscclk2: oscclk2 {
-			/* IO FPGA peripheral clock */
-			compatible = "arm,vexpress-osc";
-			arm,vexpress-sysreg,func = <1 2>;
-			freq-range = <24000000 24000000>;
-			#clock-cells = <0>;
-			clock-output-names = "v2m:oscclk2";
-		};
-
-		volt-vio {
-			/* Logic level voltage */
-			compatible = "arm,vexpress-volt";
-			arm,vexpress-sysreg,func = <2 0>;
-			regulator-name = "VIO";
-			regulator-always-on;
-			label = "VIO";
-		};
-
-		temp-mcc {
-			/* MCC internal operating temperature */
-			compatible = "arm,vexpress-temp";
-			arm,vexpress-sysreg,func = <4 0>;
-			label = "MCC";
-		};
-
-		reset {
-			compatible = "arm,vexpress-reset";
-			arm,vexpress-sysreg,func = <5 0>;
-		};
-
-		muxfpga {
-			compatible = "arm,vexpress-muxfpga";
-			arm,vexpress-sysreg,func = <7 0>;
-		};
-
-		shutdown {
-			compatible = "arm,vexpress-shutdown";
-			arm,vexpress-sysreg,func = <8 0>;
-		};
-
-		reboot {
-			compatible = "arm,vexpress-reboot";
-			arm,vexpress-sysreg,func = <9 0>;
-		};
-
-		dvimode {
-			compatible = "arm,vexpress-dvimode";
-			arm,vexpress-sysreg,func = <11 0>;
-		};
-	};
-
 	bus@8000000 {
 		motherboard-bus {
 			model = "V2M-P1";
@@ -435,6 +362,79 @@
 						};
 					};
 				};
+
+				mcc {
+					compatible = "arm,vexpress,config-bus";
+					arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+					oscclk0 {
+						/* MCC static memory clock */
+						compatible = "arm,vexpress-osc";
+						arm,vexpress-sysreg,func = <1 0>;
+						freq-range = <25000000 60000000>;
+						#clock-cells = <0>;
+						clock-output-names = "v2m:oscclk0";
+					};
+
+					v2m_oscclk1: oscclk1 {
+						/* CLCD clock */
+						compatible = "arm,vexpress-osc";
+						arm,vexpress-sysreg,func = <1 1>;
+						freq-range = <23750000 65000000>;
+						#clock-cells = <0>;
+						clock-output-names = "v2m:oscclk1";
+					};
+
+					v2m_oscclk2: oscclk2 {
+						/* IO FPGA peripheral clock */
+						compatible = "arm,vexpress-osc";
+						arm,vexpress-sysreg,func = <1 2>;
+						freq-range = <24000000 24000000>;
+						#clock-cells = <0>;
+						clock-output-names = "v2m:oscclk2";
+					};
+
+					volt-vio {
+						/* Logic level voltage */
+						compatible = "arm,vexpress-volt";
+						arm,vexpress-sysreg,func = <2 0>;
+						regulator-name = "VIO";
+						regulator-always-on;
+						label = "VIO";
+					};
+
+					temp-mcc {
+						/* MCC internal operating temperature */
+						compatible = "arm,vexpress-temp";
+						arm,vexpress-sysreg,func = <4 0>;
+						label = "MCC";
+					};
+
+					reset {
+						compatible = "arm,vexpress-reset";
+						arm,vexpress-sysreg,func = <5 0>;
+					};
+
+					muxfpga {
+						compatible = "arm,vexpress-muxfpga";
+						arm,vexpress-sysreg,func = <7 0>;
+					};
+
+					shutdown {
+						compatible = "arm,vexpress-shutdown";
+						arm,vexpress-sysreg,func = <8 0>;
+					};
+
+					reboot {
+						compatible = "arm,vexpress-reboot";
+						arm,vexpress-sysreg,func = <9 0>;
+					};
+
+					dvimode {
+						compatible = "arm,vexpress-dvimode";
+						arm,vexpress-sysreg,func = <11 0>;
+					};
+				};
 			};
 		};
 	};
diff --git a/arch/arm/crypto/crc32-ce-core.S b/arch/arm/crypto/crc32-ce-core.S
index 5cbd4a6fedad..3f13a76b9066 100644
--- a/arch/arm/crypto/crc32-ce-core.S
+++ b/arch/arm/crypto/crc32-ce-core.S
@@ -39,7 +39,7 @@
  * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
  * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
  * at:
- * http://www.intel.com/products/processor/manuals/
+ * https://www.intel.com/products/processor/manuals/
  * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
  * Volume 2B: Instruction Set Reference, N-Z
  *
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index a00fd329255f..f13401f3e669 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -16,6 +16,7 @@
 #include <crypto/gf128mul.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
+#include <linux/jump_label.h>
 #include <linux/module.h>
 
 MODULE_DESCRIPTION("GHASH hash function using ARMv8 Crypto Extensions");
@@ -27,12 +28,8 @@ MODULE_ALIAS_CRYPTO("ghash");
 #define GHASH_DIGEST_SIZE	16
 
 struct ghash_key {
-	u64	h[2];
-	u64	h2[2];
-	u64	h3[2];
-	u64	h4[2];
-
 	be128	k;
+	u64	h[][2];
 };
 
 struct ghash_desc_ctx {
@@ -46,16 +43,12 @@ struct ghash_async_ctx {
 };
 
 asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
-				       struct ghash_key const *k,
-				       const char *head);
+				       u64 const h[][2], const char *head);
 
 asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
-				      struct ghash_key const *k,
-				      const char *head);
+				      u64 const h[][2], const char *head);
 
-static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
-				  struct ghash_key const *k,
-				  const char *head);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_p64);
 
 static int ghash_init(struct shash_desc *desc)
 {
@@ -70,7 +63,10 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src,
 {
 	if (likely(crypto_simd_usable())) {
 		kernel_neon_begin();
-		pmull_ghash_update(blocks, dg, src, key, head);
+		if (static_branch_likely(&use_p64))
+			pmull_ghash_update_p64(blocks, dg, src, key->h, head);
+		else
+			pmull_ghash_update_p8(blocks, dg, src, key->h, head);
 		kernel_neon_end();
 	} else {
 		be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
@@ -161,25 +157,26 @@ static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *inkey, unsigned int keylen)
 {
 	struct ghash_key *key = crypto_shash_ctx(tfm);
-	be128 h;
 
 	if (keylen != GHASH_BLOCK_SIZE)
 		return -EINVAL;
 
 	/* needed for the fallback */
 	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
-	ghash_reflect(key->h, &key->k);
+	ghash_reflect(key->h[0], &key->k);
 
-	h = key->k;
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h2, &h);
+	if (static_branch_likely(&use_p64)) {
+		be128 h = key->k;
 
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h3, &h);
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[1], &h);
 
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h4, &h);
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[2], &h);
 
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[3], &h);
+	}
 	return 0;
 }
 
@@ -195,7 +192,7 @@ static struct shash_alg ghash_alg = {
 	.base.cra_driver_name	= "ghash-ce-sync",
 	.base.cra_priority	= 300 - 1,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct ghash_key),
+	.base.cra_ctxsize	= sizeof(struct ghash_key) + sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
 };
 
@@ -354,10 +351,10 @@ static int __init ghash_ce_mod_init(void)
 	if (!(elf_hwcap & HWCAP_NEON))
 		return -ENODEV;
 
-	if (elf_hwcap2 & HWCAP2_PMULL)
-		pmull_ghash_update = pmull_ghash_update_p64;
-	else
-		pmull_ghash_update = pmull_ghash_update_p8;
+	if (elf_hwcap2 & HWCAP2_PMULL) {
+		ghash_alg.base.cra_ctxsize += 3 * sizeof(u64[2]);
+		static_branch_enable(&use_p64);
+	}
 
 	err = crypto_register_shash(&ghash_alg);
 	if (err)
diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S
index f82cd8cf5a09..1c8b685149f2 100644
--- a/arch/arm/crypto/sha1-armv4-large.S
+++ b/arch/arm/crypto/sha1-armv4-large.S
@@ -13,7 +13,7 @@
 @ Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
 @ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see http://www.openssl.org/~appro/cryptogams/.
+@ details see https://www.openssl.org/~appro/cryptogams/.
 @ ====================================================================
 
 @ sha1_block procedure for ARMv4.
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
index a03cf4dfb781..9f96ff48e4a8 100644
--- a/arch/arm/crypto/sha256-armv4.pl
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -13,7 +13,7 @@
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
-# details see http://www.openssl.org/~appro/cryptogams/.
+# details see https://www.openssl.org/~appro/cryptogams/.
 # ====================================================================
 
 # SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
index 054aae0edfce..ea04b2ab0c33 100644
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ b/arch/arm/crypto/sha256-core.S_shipped
@@ -12,7 +12,7 @@
 @ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
 @ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see http://www.openssl.org/~appro/cryptogams/.
+@ details see https://www.openssl.org/~appro/cryptogams/.
 @ ====================================================================
 
 @ SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
index 788c17b56ecc..69df68981acd 100644
--- a/arch/arm/crypto/sha512-armv4.pl
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -13,7 +13,7 @@
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
-# details see http://www.openssl.org/~appro/cryptogams/.
+# details see https://www.openssl.org/~appro/cryptogams/.
 # ====================================================================
 
 # SHA512 block procedure for ARMv4. September 2007.
@@ -43,7 +43,7 @@
 # terms it's 22.6 cycles per byte, which is disappointing result.
 # Technical writers asserted that 3-way S4 pipeline can sustain
 # multiple NEON instructions per cycle, but dual NEON issue could
-# not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+# not be observed, see https://www.openssl.org/~appro/Snapdragon-S4.html
 # for further details. On side note Cortex-A15 processes one byte in
 # 16 cycles.
 
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
index 710ea309769e..cb147db5cbfe 100644
--- a/arch/arm/crypto/sha512-core.S_shipped
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -12,7 +12,7 @@
 @ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
 @ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see http://www.openssl.org/~appro/cryptogams/.
+@ details see https://www.openssl.org/~appro/cryptogams/.
 @ ====================================================================
 
 @ SHA512 block procedure for ARMv4. September 2007.
@@ -42,7 +42,7 @@
 @ terms it's 22.6 cycles per byte, which is disappointing result.
 @ Technical writers asserted that 3-way S4 pipeline can sustain
 @ multiple NEON instructions per cycle, but dual NEON issue could
-@ not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+@ not be observed, see https://www.openssl.org/~appro/Snapdragon-S4.html
 @ for further details. On side note Cortex-A15 processes one byte in
 @ 16 cycles.
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 75bb2c543e59..455eb19a5ac1 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -15,8 +15,6 @@
 #include <asm/barrier.h>
 #include <asm/cmpxchg.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifdef __KERNEL__
 
 /*
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 84dc0ba822f5..5dcf3c6011b7 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -87,4 +87,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 	return dram_base + SZ_512M;
 }
 
+struct efi_arm_entry_state {
+	u32	cpsr_before_ebs;
+	u32	sctlr_before_ebs;
+	u32	cpsr_after_ebs;
+	u32	sctlr_after_ebs;
+};
+
 #endif /* _ASM_ARM_EFI_H */
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
index f44f448537f2..e2fcb3cfd3de 100644
--- a/arch/arm/include/asm/percpu.h
+++ b/arch/arm/include/asm/percpu.h
@@ -5,6 +5,8 @@
 #ifndef _ASM_ARM_PERCPU_H_
 #define _ASM_ARM_PERCPU_H_
 
+register unsigned long current_stack_pointer asm ("sp");
+
 /*
  * Same as asm-generic/percpu.h, except that we store the per cpu offset
  * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 3609a6980c34..536b6b979f63 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -76,11 +76,6 @@ struct thread_info {
 }
 
 /*
- * how to get the current stack pointer in C
- */
-register unsigned long current_stack_pointer asm ("sp");
-
-/*
  * how to get the thread information struct from C
  */
 static inline struct thread_info *current_thread_info(void) __attribute_const__;
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 435aba289fc5..e0593cf095d0 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -16,8 +16,9 @@
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure retrieve API */
+/* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_set_thermal_pressure   topology_set_thermal_pressure
 
 #else
 
diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h
index 36dc18553ed8..1b207cf07697 100644
--- a/arch/arm/include/asm/vdso/gettimeofday.h
+++ b/arch/arm/include/asm/vdso/gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/errno.h>
 #include <asm/unistd.h>
 #include <asm/vdso/cp15.h>
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index c036a4a2f8e2..a1570c8bab25 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -31,15 +31,6 @@
 #if defined(__APCS_26__)
 #error Sorry, your compiler targets APCS-26 but this kernel requires APCS-32
 #endif
-/*
- * GCC 4.8.0-4.8.2: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58854
- *	      miscompiles find_get_entry(), and can result in EXT3 and EXT4
- *	      filesystem corruption (possibly other FS too).
- */
-#if defined(GCC_VERSION) && GCC_VERSION >= 40800 && GCC_VERSION < 40803
-#error Your compiler is too buggy; it is known to miscompile kernels
-#error and result in filesystem corruption and oopses.
-#endif
 
 int main(void)
 {
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 10499d44964a..9a79ef6b1876 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -84,7 +84,8 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old,
 		old = __opcode_to_mem_arm(old);
 
 	if (validate) {
-		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+		if (copy_from_kernel_nofault(&replaced, (void *)pc,
+				MCOUNT_INSN_SIZE))
 			return -EFAULT;
 
 		if (replaced != old)
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 02ca7adf5375..7fff88e61252 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -683,6 +683,12 @@ static void disable_single_step(struct perf_event *bp)
 	arch_install_hw_breakpoint(bp);
 }
 
+static int watchpoint_fault_on_uaccess(struct pt_regs *regs,
+				       struct arch_hw_breakpoint *info)
+{
+	return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER;
+}
+
 static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 			       struct pt_regs *regs)
 {
@@ -742,16 +748,27 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 		}
 
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
+
+		/*
+		 * If we triggered a user watchpoint from a uaccess routine,
+		 * then handle the stepping ourselves since userspace really
+		 * can't help us with this.
+		 */
+		if (watchpoint_fault_on_uaccess(regs, info))
+			goto step;
+
 		perf_bp_event(wp, regs);
 
 		/*
-		 * If no overflow handler is present, insert a temporary
-		 * mismatch breakpoint so we can single-step over the
-		 * watchpoint trigger.
+		 * Defer stepping to the overflow handler if one is installed.
+		 * Otherwise, insert a temporary mismatch breakpoint so that
+		 * we can single-step over the watchpoint trigger.
 		 */
-		if (is_default_overflow_handler(wp))
-			enable_single_step(wp, instruction_pointer(regs));
+		if (!is_default_overflow_handler(wp))
+			goto unlock;
 
+step:
+		enable_single_step(wp, instruction_pointer(regs));
 unlock:
 		rcu_read_unlock();
 	}
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index 6a95b9296640..7bd30c0a4280 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -236,7 +236,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	/* patch_text() only supports int-sized breakpoints */
 	BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE);
 
-	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+	err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
 				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 65a3b1e75480..17d5a785df28 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -396,7 +396,7 @@ int is_valid_bugaddr(unsigned long pc)
 	u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
 #endif
 
-	if (probe_kernel_address((unsigned *)pc, bkpt))
+	if (get_kernel_nofault(bkpt, (void *)pc))
 		return 0;
 
 	return bkpt == insn;
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 6bfdca4769a7..fddd08a6e063 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -184,6 +184,7 @@ static void __init patch_vdso(void *ehdr)
 	if (!cntvct_ok) {
 		vdso_nullpatch_one(&einfo, "__vdso_gettimeofday");
 		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime");
+		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime64");
 	}
 }
 
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index 6aa938b949db..1df0ee01ee02 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -53,6 +53,7 @@ config ARCH_BCM_NSP
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
 	select ARM_ERRATA_764369 if SMP
+	select ARM_TIMER_SP804
 	select THERMAL
 	select THERMAL_OF
 	help
diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h
index 2a685adec1df..ae84c08e11fa 100644
--- a/arch/arm/mach-imx/devices/devices-common.h
+++ b/arch/arm/mach-imx/devices/devices-common.h
@@ -289,6 +289,6 @@ struct platform_device *__init imx_add_spi_imx(
 		const struct spi_imx_master *pdata);
 
 struct platform_device *imx_add_imx_dma(char *name, resource_size_t iobase,
-					int irq, int irq_err);
+					int irq);
 struct platform_device *imx_add_imx_sdma(char *name,
 	resource_size_t iobase, int irq, struct sdma_platform_data *pdata);
diff --git a/arch/arm/mach-imx/devices/platform-gpio-mxc.c b/arch/arm/mach-imx/devices/platform-gpio-mxc.c
index 78628ef12672..355de845224c 100644
--- a/arch/arm/mach-imx/devices/platform-gpio-mxc.c
+++ b/arch/arm/mach-imx/devices/platform-gpio-mxc.c
@@ -24,7 +24,8 @@ struct platform_device *__init mxc_register_gpio(char *name, int id,
 			.flags = IORESOURCE_IRQ,
 		},
 	};
+	unsigned int nres;
 
-	return platform_device_register_resndata(&mxc_aips_bus,
-			name, id, res, ARRAY_SIZE(res), NULL, 0);
+	nres = irq_high ? ARRAY_SIZE(res) : ARRAY_SIZE(res) - 1;
+	return platform_device_register_resndata(&mxc_aips_bus, name, id, res, nres, NULL, 0);
 }
diff --git a/arch/arm/mach-imx/devices/platform-imx-dma.c b/arch/arm/mach-imx/devices/platform-imx-dma.c
index 26b47b36257b..12656f24ad0d 100644
--- a/arch/arm/mach-imx/devices/platform-imx-dma.c
+++ b/arch/arm/mach-imx/devices/platform-imx-dma.c
@@ -6,7 +6,7 @@
 #include "devices-common.h"
 
 struct platform_device __init __maybe_unused *imx_add_imx_dma(char *name,
-	resource_size_t iobase, int irq, int irq_err)
+	resource_size_t iobase, int irq)
 {
 	struct resource res[] = {
 		{
@@ -17,10 +17,6 @@ struct platform_device __init __maybe_unused *imx_add_imx_dma(char *name,
 			.start = irq,
 			.end = irq,
 			.flags = IORESOURCE_IRQ,
-		}, {
-			.start = irq_err,
-			.end = irq_err,
-			.flags = IORESOURCE_IRQ,
 		},
 	};
 
diff --git a/arch/arm/mach-imx/mm-imx21.c b/arch/arm/mach-imx/mm-imx21.c
index 50a2edac8513..b834026e4615 100644
--- a/arch/arm/mach-imx/mm-imx21.c
+++ b/arch/arm/mach-imx/mm-imx21.c
@@ -78,8 +78,7 @@ void __init imx21_soc_init(void)
 	mxc_register_gpio("imx21-gpio", 5, MX21_GPIO6_BASE_ADDR, SZ_256, MX21_INT_GPIO, 0);
 
 	pinctrl_provide_dummies();
-	imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR,
-			MX21_INT_DMACH0, 0); /* No ERR irq */
+	imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR, MX21_INT_DMACH0);
 	platform_device_register_simple("imx21-audmux", 0, imx21_audmux_res,
 					ARRAY_SIZE(imx21_audmux_res));
 }
diff --git a/arch/arm/mach-imx/mm-imx27.c b/arch/arm/mach-imx/mm-imx27.c
index 4e4125140025..2717614f101d 100644
--- a/arch/arm/mach-imx/mm-imx27.c
+++ b/arch/arm/mach-imx/mm-imx27.c
@@ -79,8 +79,7 @@ void __init imx27_soc_init(void)
 	mxc_register_gpio("imx21-gpio", 5, MX27_GPIO6_BASE_ADDR, SZ_256, MX27_INT_GPIO, 0);
 
 	pinctrl_provide_dummies();
-	imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR,
-			MX27_INT_DMACH0, 0); /* No ERR irq */
+	imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR, MX27_INT_DMACH0);
 	/* imx27 has the imx21 type audmux */
 	platform_device_register_simple("imx21-audmux", 0, imx27_audmux_res,
 					ARRAY_SIZE(imx27_audmux_res));
diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c
index f057df813f83..e9962b48e30c 100644
--- a/arch/arm/mach-imx/pm-imx5.c
+++ b/arch/arm/mach-imx/pm-imx5.c
@@ -295,14 +295,14 @@ static int __init imx_suspend_alloc_ocram(
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, size);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	phys = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -312,6 +312,8 @@ static int __init imx_suspend_alloc_ocram(
 	if (virt_out)
 		*virt_out = virt;
 
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(node);
 
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index dd34dff13762..40c74b4c4d73 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -493,14 +493,14 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -523,7 +523,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 	ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat);
 	if (ret) {
 		pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret);
-		goto put_node;
+		goto put_device;
 	}
 
 	ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat);
@@ -570,7 +570,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 		&imx6_suspend,
 		MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info));
 
-	goto put_node;
+	goto put_device;
 
 pl310_cache_map_failed:
 	iounmap(pm_info->gpc_base.vbase);
@@ -580,6 +580,8 @@ iomuxc_map_failed:
 	iounmap(pm_info->src_base.vbase);
 src_map_failed:
 	iounmap(pm_info->mmdc_base.vbase);
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(node);
 
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 82706af307de..15b29a179c8a 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -3435,7 +3435,7 @@ static int omap_hwmod_allocate_module(struct device *dev, struct omap_hwmod *oh,
 		regs = ioremap(data->module_pa,
 			       data->module_size);
 		if (!regs)
-			return -ENOMEM;
+			goto out_free_sysc;
 	}
 
 	/*
@@ -3445,13 +3445,13 @@ static int omap_hwmod_allocate_module(struct device *dev, struct omap_hwmod *oh,
 	if (oh->class->name && strcmp(oh->class->name, data->name)) {
 		class = kmemdup(oh->class, sizeof(*oh->class), GFP_KERNEL);
 		if (!class)
-			return -ENOMEM;
+			goto out_unmap;
 	}
 
 	if (list_empty(&oh->slave_ports)) {
 		oi = kcalloc(1, sizeof(*oi), GFP_KERNEL);
 		if (!oi)
-			return -ENOMEM;
+			goto out_free_class;
 
 		/*
 		 * Note that we assume interconnect interface clocks will be
@@ -3478,6 +3478,14 @@ static int omap_hwmod_allocate_module(struct device *dev, struct omap_hwmod *oh,
 	spin_unlock_irqrestore(&oh->_lock, flags);
 
 	return 0;
+
+out_free_class:
+	kfree(class);
+out_unmap:
+	iounmap(regs);
+out_free_sysc:
+	kfree(sysc);
+	return -ENOMEM;
 }
 
 static const struct omap_hwmod_reset omap24xx_reset_quirks[] = {
@@ -3489,7 +3497,7 @@ static const struct omap_hwmod_reset dra7_reset_quirks[] = {
 };
 
 static const struct omap_hwmod_reset omap_reset_quirks[] = {
-	{ .match = "dss", .len = 3, .reset = omap_dss_reset, },
+	{ .match = "dss_core", .len = 8, .reset = omap_dss_reset, },
 	{ .match = "hdq1w", .len = 5, .reset = omap_hdq1w_reset, },
 	{ .match = "i2c", .len = 3, .reset = omap_i2c_reset, },
 	{ .match = "wd_timer", .len = 8, .reset = omap2_wd_timer_reset, },
diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c
index dcb98937fcf5..ffecbf29646f 100644
--- a/arch/arm/mach-sti/board-dt.c
+++ b/arch/arm/mach-sti/board-dt.c
@@ -20,14 +20,6 @@ static const char *const stih41x_dt_match[] __initconst = {
 	NULL
 };
 
-static void sti_l2_write_sec(unsigned long val, unsigned reg)
-{
-	/*
-	 * We can't write to secure registers as we are in non-secure
-	 * mode, until we have some SMI service available.
-	 */
-}
-
 DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree")
 	.dt_compat	= stih41x_dt_match,
 	.l2c_aux_val	= L2C_AUX_CTRL_SHARED_OVERRIDE |
@@ -36,5 +28,4 @@ DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree")
 			  L2C_AUX_CTRL_WAY_SIZE(4),
 	.l2c_aux_mask	= 0xc0000fff,
 	.smp		= smp_ops(sti_smp_ops),
-	.l2c_write_sec	= sti_l2_write_sec,
 MACHINE_END
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 84718eddae60..81a627e6e1c5 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -774,7 +774,7 @@ static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst)
 	if (user_mode(regs))
 		fault = get_user(instr, ip);
 	else
-		fault = probe_kernel_address(ip, instr);
+		fault = get_kernel_nofault(instr, ip);
 
 	*inst = __mem_to_opcode_arm(instr);
 
@@ -789,7 +789,7 @@ static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)
 	if (user_mode(regs))
 		fault = get_user(instr, ip);
 	else
-		fault = probe_kernel_address(ip, instr);
+		fault = get_kernel_nofault(instr, ip);
 
 	*inst = __mem_to_opcode_thumb16(instr);
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 628028bfbb92..bcd82614c25d 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -966,7 +966,7 @@ void __init create_mapping_late(struct mm_struct *mm, struct map_desc *md,
 	pud_t *pud;
 
 	p4d = p4d_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
-	if (!WARN_ON(!p4d))
+	if (WARN_ON(!p4d))
 		return;
 	pud = pud_alloc(mm, p4d, md->virtual);
 	if (WARN_ON(!pud))
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index fd4e1ce1daf9..e93145d72c26 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -241,7 +241,6 @@ static int __init fdt_find_hyper_node(unsigned long node, const char *uname,
  * see Documentation/devicetree/bindings/arm/xen.txt for the
  * documentation of the Xen Device Tree format.
  */
-#define GRANT_TABLE_PHYSADDR 0
 void __init xen_early_init(void)
 {
 	of_scan_flat_dt(fdt_find_hyper_node, NULL);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 31380da53689..73aee7290cdf 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -118,6 +118,7 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_TIME_NS
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_PCI
@@ -1327,6 +1328,8 @@ config SWP_EMULATION
 	  ARMv8 obsoletes the use of A32 SWP/SWPB instructions such that
 	  they are always undefined. Say Y here to enable software
 	  emulation of these instructions for userspace using LDXR/STXR.
+	  This feature can be controlled at runtime with the abi.swp
+	  sysctl which is disabled by default.
 
 	  In some older versions of glibc [<=2.8] SWP is used during futex
 	  trylock() operations with the assumption that the code will not
@@ -1353,7 +1356,8 @@ config CP15_BARRIER_EMULATION
 	  Say Y here to enable software emulation of these
 	  instructions for AArch32 userspace code. When this option is
 	  enabled, CP15 barrier usage is traced which can help
-	  identify software that needs updating.
+	  identify software that needs updating. This feature can be
+	  controlled at runtime with the abi.cp15_barrier sysctl.
 
 	  If unsure, say Y
 
@@ -1364,7 +1368,8 @@ config SETEND_EMULATION
 	  AArch32 EL0, and is deprecated in ARMv8.
 
 	  Say Y here to enable software emulation of the instruction
-	  for AArch32 userspace code.
+	  for AArch32 userspace code. This feature can be controlled
+	  at runtime with the abi.setend sysctl.
 
 	  Note: All the cpus on the system must have mixed endian support at EL0
 	  for this feature to be enabled. If a new CPU - which doesn't support mixed
@@ -1518,9 +1523,9 @@ config ARM64_PTR_AUTH
 	default y
 	depends on !KVM || ARM64_VHE
 	depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
-	# GCC 9.1 and later inserts a .note.gnu.property section note for PAC
+	# Modern compilers insert a .note.gnu.property section note for PAC
 	# which is only understood by binutils starting with version 2.33.1.
-	depends on !CC_IS_GCC || GCC_VERSION < 90100 || LD_VERSION >= 233010000
+	depends on LD_IS_LLD || LD_VERSION >= 233010000 || (CC_IS_GCC && GCC_VERSION < 90100)
 	depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE
 	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
 	help
@@ -1564,7 +1569,7 @@ config CC_HAS_SIGN_RETURN_ADDRESS
 	def_bool $(cc-option,-msign-return-address=all)
 
 config AS_HAS_PAC
-	def_bool $(as-option,-Wa$(comma)-march=armv8.3-a)
+	def_bool $(cc-option,-Wa$(comma)-march=armv8.3-a)
 
 config AS_HAS_CFI_NEGATE_RA_STATE
 	def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n)
@@ -1596,6 +1601,20 @@ config ARM64_AMU_EXTN
 	  correctly reflect reality. Most commonly, the value read will be 0,
 	  indicating that the counter is not enabled.
 
+config AS_HAS_ARMV8_4
+	def_bool $(cc-option,-Wa$(comma)-march=armv8.4-a)
+
+config ARM64_TLB_RANGE
+	bool "Enable support for tlbi range feature"
+	default y
+	depends on AS_HAS_ARMV8_4
+	help
+	  ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
+	  range of input addresses.
+
+	  The feature introduces new assembly instructions, and they were
+	  support when binutils >= 2.30.
+
 endmenu
 
 menu "ARMv8.5 architectural features"
@@ -1630,6 +1649,8 @@ config ARM64_BTI_KERNEL
 	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
 	depends on !CC_IS_GCC || GCC_VERSION >= 100100
+	# https://reviews.llvm.org/rGb8ae3fdfa579dbf366b1bb1cbfdbf8c51db7fa55
+	depends on !CC_IS_CLANG || CLANG_VERSION >= 100001
 	depends on !(CC_IS_CLANG && GCOV_KERNEL)
 	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
 	help
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index cdf7ec0b975e..265c4461031f 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -8,21 +8,6 @@ config PID_IN_CONTEXTIDR
 	  instructions during context switch. Say Y here only if you are
 	  planning to use hardware trace tools with this kernel.
 
-config ARM64_RANDOMIZE_TEXT_OFFSET
-	bool "Randomize TEXT_OFFSET at build time"
-	help
-	  Say Y here if you want the image load offset (AKA TEXT_OFFSET)
-	  of the kernel to be randomized at build-time. When selected,
-	  this option will cause TEXT_OFFSET to be randomized upon any
-	  build of the kernel, and the offset will be reflected in the
-	  text_offset field of the resulting Image. This can be used to
-	  fuzz-test bootloaders which respect text_offset.
-
-	  This option is intended for bootloader and/or kernel testing
-	  only. Bootloaders must make no assumptions regarding the value
-	  of TEXT_OFFSET and platforms must not require a specific
-	  value.
-
 config DEBUG_EFI
 	depends on EFI && DEBUG_INFO
 	bool "UEFI debugging"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 76359cfb328a..55bc8546d9c7 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -82,11 +82,18 @@ endif
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
 # integrated assemblers.
+ifneq ($(CONFIG_AS_HAS_ARMV8_4), y)
 branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
 endif
+endif
 
 KBUILD_CFLAGS += $(branch-prot-flags-y)
 
+ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
+# make sure to pass the newest target architecture to -march.
+KBUILD_CFLAGS	+= -Wa,-march=armv8.4-a
+endif
+
 ifeq ($(CONFIG_SHADOW_CALL_STACK), y)
 KBUILD_CFLAGS	+= -ffixed-x18
 endif
@@ -121,13 +128,7 @@ endif
 head-y		:= arch/arm64/kernel/head.o
 
 # The byte offset of the kernel image in RAM from the start of RAM.
-ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
-TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \
-		 int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \
-		 rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}")
-else
 TEXT_OFFSET := 0x0
-endif
 
 ifeq ($(CONFIG_KASAN_SW_TAGS), y)
 KASAN_SHADOW_SCALE_SHIFT := 4
@@ -143,7 +144,7 @@ export	TEXT_OFFSET
 
 core-y		+= arch/arm64/
 libs-y		:= arch/arm64/lib/ $(libs-y)
-core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 
 # Default target when executing plain make
 boot		:= arch/arm64/boot
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
index 78b1361dfbb9..9ce78a7b117d 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
@@ -161,6 +161,7 @@
 			resets = <&ccu RST_BUS_VE>;
 			interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 			allwinner,sram = <&ve_sram 1>;
+			iommus = <&iommu 3>;
 		};
 
 		gpu: gpu@1800000 {
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index d1fc9c2055f4..9498d1de730c 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -77,7 +77,7 @@
 		method = "smc";
 	};
 
-	intc: intc@fffc1000 {
+	intc: interrupt-controller@fffc1000 {
 		compatible = "arm,gic-400", "arm,cortex-a15-gic";
 		#interrupt-cells = <3>;
 		interrupt-controller;
@@ -302,7 +302,7 @@
 			status = "disabled";
 		};
 
-		nand: nand@ffb90000 {
+		nand: nand-controller@ffb90000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "altr,socfpga-denali-nand";
@@ -445,7 +445,7 @@
 			clock-names = "timer";
 		};
 
-		uart0: serial0@ffc02000 {
+		uart0: serial@ffc02000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0xffc02000 0x100>;
 			interrupts = <0 108 4>;
@@ -456,7 +456,7 @@
 			status = "disabled";
 		};
 
-		uart1: serial1@ffc02100 {
+		uart1: serial@ffc02100 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0xffc02100 0x100>;
 			interrupts = <0 109 4>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index f6c4a15079d3..feadd21bc0dc 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -155,6 +155,7 @@
 };
 
 &qspi {
+	status = "okay";
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
index 9946515b8afd..c07966740e14 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
@@ -188,6 +188,7 @@
 };
 
 &qspi {
+	status = "okay";
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -211,12 +212,12 @@
 
 			qspi_boot: partition@0 {
 				label = "Boot and fpga data";
-				reg = <0x0 0x034B0000>;
+				reg = <0x0 0x03FE0000>;
 			};
 
-			qspi_rootfs: partition@4000000 {
+			qspi_rootfs: partition@3FE0000 {
 				label = "Root Filesystem - JFFS2";
-				reg = <0x034B0000 0x0EB50000>;
+				reg = <0x03FE0000 0x0C020000>;
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
index 6a226faab183..9e43f4dca90d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
@@ -10,7 +10,7 @@
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/sound/meson-aiu.h>
 
-#include "meson-gxl-s905x.dtsi"
+#include "meson-gxl-s805x.dtsi"
 
 / {
 	compatible = "libretech,aml-s805x-ac", "amlogic,s805x",
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
index 867e30f1d62b..eb7f5a3fefd4 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
@@ -9,7 +9,7 @@
 
 #include <dt-bindings/input/input.h>
 
-#include "meson-gxl-s905x.dtsi"
+#include "meson-gxl-s805x.dtsi"
 
 / {
 	compatible = "amlogic,p241", "amlogic,s805x", "amlogic,meson-gxl";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi
new file mode 100644
index 000000000000..f9d705648426
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2020 BayLibre SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include "meson-gxl-s905x.dtsi"
+
+/ {
+	compatible = "amlogic,s805x", "amlogic,meson-gxl";
+};
+
+/* The S805X Package doesn't seem to handle the 744MHz OPP correctly */
+&mali {
+	assigned-clocks = <&clkc CLKID_MALI_0_SEL>,
+			  <&clkc CLKID_MALI_0>,
+			  <&clkc CLKID_MALI>; /* Glitch free mux */
+	assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>,
+				 <0>, /* Do Nothing */
+				 <&clkc CLKID_MALI_0>;
+	assigned-clock-rates = <0>, /* Do Nothing */
+			       <666666666>,
+			       <0>; /* Do Nothing */
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index fc59c8534c0f..6c8b189884ca 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -337,6 +337,11 @@
 	};
 };
 
+&hwrng {
+	clocks = <&clkc CLKID_RNG0>;
+	clock-names = "core";
+};
+
 &i2c_A {
 	clocks = <&clkc CLKID_I2C>;
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
index fb0137a8611c..94911b1707ef 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
@@ -136,7 +136,7 @@
 
 			ldo1_reg: LDO1 {
 				regulator-name = "LDO1";
-				regulator-min-microvolt = <3000000>;
+				regulator-min-microvolt = <1600000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -144,7 +144,7 @@
 
 			ldo2_reg: LDO2 {
 				regulator-name = "LDO2";
-				regulator-min-microvolt = <900000>;
+				regulator-min-microvolt = <800000>;
 				regulator-max-microvolt = <900000>;
 				regulator-boot-on;
 				regulator-always-on;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts
index e5ec8322796d..0f1d7f8aeac4 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts
@@ -208,7 +208,7 @@
 
 			ldo1_reg: LDO1 {
 				regulator-name = "LDO1";
-				regulator-min-microvolt = <3000000>;
+				regulator-min-microvolt = <1600000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -216,7 +216,7 @@
 
 			ldo2_reg: LDO2 {
 				regulator-name = "LDO2";
-				regulator-min-microvolt = <900000>;
+				regulator-min-microvolt = <800000>;
 				regulator-max-microvolt = <900000>;
 				regulator-boot-on;
 				regulator-always-on;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
index d07e0e6a00cc..a1e5483dbbbe 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
@@ -113,7 +113,7 @@
 
 			ldo1_reg: LDO1 {
 				regulator-name = "LDO1";
-				regulator-min-microvolt = <3000000>;
+				regulator-min-microvolt = <1600000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -121,7 +121,7 @@
 
 			ldo2_reg: LDO2 {
 				regulator-name = "LDO2";
-				regulator-min-microvolt = <900000>;
+				regulator-min-microvolt = <800000>;
 				regulator-max-microvolt = <900000>;
 				regulator-boot-on;
 				regulator-always-on;
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
index 51d948323bfd..92f478def723 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
@@ -98,6 +98,7 @@
 };
 
 &qspi {
+	status = "okay";
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
index c8243da71041..eb01cc96ba7a 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
@@ -454,10 +454,7 @@
 	status = "okay";
 	phy-mode = "2500base-x";
 	phys = <&cp1_comphy5 2>;
-	fixed-link {
-		speed = <2500>;
-		full-duplex;
-	};
+	managed = "in-band-status";
 };
 
 &cp1_spi1 {
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 883e8bace3ed..39273b5c14be 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -66,6 +66,7 @@ CONFIG_SCHED_SMT=y
 CONFIG_NUMA=y
 CONFIG_SECCOMP=y
 CONFIG_KEXEC=y
+CONFIG_KEXEC_FILE=y
 CONFIG_CRASH_DUMP=y
 CONFIG_XEN=y
 CONFIG_COMPAT=y
@@ -194,7 +195,7 @@ CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_ACPI=y
 CONFIG_PCI_AARDVARK=y
 CONFIG_PCI_TEGRA=y
-CONFIG_PCIE_RCAR=y
+CONFIG_PCIE_RCAR_HOST=y
 CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCI_XGENE=y
 CONFIG_PCIE_ALTERA=y
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 22831d3b7f62..da1034867aaa 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -31,12 +31,8 @@ MODULE_ALIAS_CRYPTO("ghash");
 #define GCM_IV_SIZE		12
 
 struct ghash_key {
-	u64			h[2];
-	u64			h2[2];
-	u64			h3[2];
-	u64			h4[2];
-
 	be128			k;
+	u64			h[][2];
 };
 
 struct ghash_desc_ctx {
@@ -51,22 +47,18 @@ struct gcm_aes_ctx {
 };
 
 asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
-				       struct ghash_key const *k,
-				       const char *head);
+				       u64 const h[][2], const char *head);
 
 asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
-				      struct ghash_key const *k,
-				      const char *head);
+				      u64 const h[][2], const char *head);
 
 asmlinkage void pmull_gcm_encrypt(int bytes, u8 dst[], const u8 src[],
-				  struct ghash_key const *k, u64 dg[],
-				  u8 ctr[], u32 const rk[], int rounds,
-				  u8 tag[]);
+				  u64 const h[][2], u64 dg[], u8 ctr[],
+				  u32 const rk[], int rounds, u8 tag[]);
 
 asmlinkage void pmull_gcm_decrypt(int bytes, u8 dst[], const u8 src[],
-				  struct ghash_key const *k, u64 dg[],
-				  u8 ctr[], u32 const rk[], int rounds,
-				  u8 tag[]);
+				  u64 const h[][2], u64 dg[], u8 ctr[],
+				  u32 const rk[], int rounds, u8 tag[]);
 
 static int ghash_init(struct shash_desc *desc)
 {
@@ -77,48 +69,51 @@ static int ghash_init(struct shash_desc *desc)
 }
 
 static void ghash_do_update(int blocks, u64 dg[], const char *src,
-			    struct ghash_key *key, const char *head,
-			    void (*simd_update)(int blocks, u64 dg[],
-						const char *src,
-						struct ghash_key const *k,
-						const char *head))
+			    struct ghash_key *key, const char *head)
 {
-	if (likely(crypto_simd_usable() && simd_update)) {
-		kernel_neon_begin();
-		simd_update(blocks, dg, src, key, head);
-		kernel_neon_end();
-	} else {
-		be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
+	be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
 
-		do {
-			const u8 *in = src;
-
-			if (head) {
-				in = head;
-				blocks++;
-				head = NULL;
-			} else {
-				src += GHASH_BLOCK_SIZE;
-			}
+	do {
+		const u8 *in = src;
+
+		if (head) {
+			in = head;
+			blocks++;
+			head = NULL;
+		} else {
+			src += GHASH_BLOCK_SIZE;
+		}
 
-			crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
-			gf128mul_lle(&dst, &key->k);
-		} while (--blocks);
+		crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
+		gf128mul_lle(&dst, &key->k);
+	} while (--blocks);
 
-		dg[0] = be64_to_cpu(dst.b);
-		dg[1] = be64_to_cpu(dst.a);
+	dg[0] = be64_to_cpu(dst.b);
+	dg[1] = be64_to_cpu(dst.a);
+}
+
+static __always_inline
+void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
+			  struct ghash_key *key, const char *head,
+			  void (*simd_update)(int blocks, u64 dg[],
+					      const char *src,
+					      u64 const h[][2],
+					      const char *head))
+{
+	if (likely(crypto_simd_usable())) {
+		kernel_neon_begin();
+		simd_update(blocks, dg, src, key->h, head);
+		kernel_neon_end();
+	} else {
+		ghash_do_update(blocks, dg, src, key, head);
 	}
 }
 
 /* avoid hogging the CPU for too long */
 #define MAX_BLOCKS	(SZ_64K / GHASH_BLOCK_SIZE)
 
-static int __ghash_update(struct shash_desc *desc, const u8 *src,
-			  unsigned int len,
-			  void (*simd_update)(int blocks, u64 dg[],
-					      const char *src,
-					      struct ghash_key const *k,
-					      const char *head))
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+			unsigned int len)
 {
 	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
@@ -143,9 +138,9 @@ static int __ghash_update(struct shash_desc *desc, const u8 *src,
 		do {
 			int chunk = min(blocks, MAX_BLOCKS);
 
-			ghash_do_update(chunk, ctx->digest, src, key,
-					partial ? ctx->buf : NULL,
-					simd_update);
+			ghash_do_simd_update(chunk, ctx->digest, src, key,
+					     partial ? ctx->buf : NULL,
+					     pmull_ghash_update_p8);
 
 			blocks -= chunk;
 			src += chunk * GHASH_BLOCK_SIZE;
@@ -157,39 +152,7 @@ static int __ghash_update(struct shash_desc *desc, const u8 *src,
 	return 0;
 }
 
-static int ghash_update_p8(struct shash_desc *desc, const u8 *src,
-			   unsigned int len)
-{
-	return __ghash_update(desc, src, len, pmull_ghash_update_p8);
-}
-
-static int ghash_update_p64(struct shash_desc *desc, const u8 *src,
-			    unsigned int len)
-{
-	return __ghash_update(desc, src, len, pmull_ghash_update_p64);
-}
-
-static int ghash_final_p8(struct shash_desc *desc, u8 *dst)
-{
-	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
-	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
-
-	if (partial) {
-		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
-
-		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
-
-		ghash_do_update(1, ctx->digest, ctx->buf, key, NULL,
-				pmull_ghash_update_p8);
-	}
-	put_unaligned_be64(ctx->digest[1], dst);
-	put_unaligned_be64(ctx->digest[0], dst + 8);
-
-	*ctx = (struct ghash_desc_ctx){};
-	return 0;
-}
-
-static int ghash_final_p64(struct shash_desc *desc, u8 *dst)
+static int ghash_final(struct shash_desc *desc, u8 *dst)
 {
 	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
@@ -199,8 +162,8 @@ static int ghash_final_p64(struct shash_desc *desc, u8 *dst)
 
 		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
 
-		ghash_do_update(1, ctx->digest, ctx->buf, key, NULL,
-				pmull_ghash_update_p64);
+		ghash_do_simd_update(1, ctx->digest, ctx->buf, key, NULL,
+				     pmull_ghash_update_p8);
 	}
 	put_unaligned_be64(ctx->digest[1], dst);
 	put_unaligned_be64(ctx->digest[0], dst + 8);
@@ -220,29 +183,6 @@ static void ghash_reflect(u64 h[], const be128 *k)
 		h[1] ^= 0xc200000000000000UL;
 }
 
-static int __ghash_setkey(struct ghash_key *key,
-			  const u8 *inkey, unsigned int keylen)
-{
-	be128 h;
-
-	/* needed for the fallback */
-	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
-
-	ghash_reflect(key->h, &key->k);
-
-	h = key->k;
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h2, &h);
-
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h3, &h);
-
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h4, &h);
-
-	return 0;
-}
-
 static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *inkey, unsigned int keylen)
 {
@@ -251,38 +191,28 @@ static int ghash_setkey(struct crypto_shash *tfm,
 	if (keylen != GHASH_BLOCK_SIZE)
 		return -EINVAL;
 
-	return __ghash_setkey(key, inkey, keylen);
+	/* needed for the fallback */
+	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
+
+	ghash_reflect(key->h[0], &key->k);
+	return 0;
 }
 
-static struct shash_alg ghash_alg[] = {{
+static struct shash_alg ghash_alg = {
 	.base.cra_name		= "ghash",
 	.base.cra_driver_name	= "ghash-neon",
 	.base.cra_priority	= 150,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct ghash_key),
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= GHASH_DIGEST_SIZE,
-	.init			= ghash_init,
-	.update			= ghash_update_p8,
-	.final			= ghash_final_p8,
-	.setkey			= ghash_setkey,
-	.descsize		= sizeof(struct ghash_desc_ctx),
-}, {
-	.base.cra_name		= "ghash",
-	.base.cra_driver_name	= "ghash-ce",
-	.base.cra_priority	= 200,
-	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct ghash_key),
+	.base.cra_ctxsize	= sizeof(struct ghash_key) + sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
 
 	.digestsize		= GHASH_DIGEST_SIZE,
 	.init			= ghash_init,
-	.update			= ghash_update_p64,
-	.final			= ghash_final_p64,
+	.update			= ghash_update,
+	.final			= ghash_final,
 	.setkey			= ghash_setkey,
 	.descsize		= sizeof(struct ghash_desc_ctx),
-}};
+};
 
 static int num_rounds(struct crypto_aes_ctx *ctx)
 {
@@ -301,6 +231,7 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 {
 	struct gcm_aes_ctx *ctx = crypto_aead_ctx(tfm);
 	u8 key[GHASH_BLOCK_SIZE];
+	be128 h;
 	int ret;
 
 	ret = aes_expandkey(&ctx->aes_key, inkey, keylen);
@@ -309,7 +240,22 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 
 	aes_encrypt(&ctx->aes_key, key, (u8[AES_BLOCK_SIZE]){});
 
-	return __ghash_setkey(&ctx->ghash_key, key, sizeof(be128));
+	/* needed for the fallback */
+	memcpy(&ctx->ghash_key.k, key, GHASH_BLOCK_SIZE);
+
+	ghash_reflect(ctx->ghash_key.h[0], &ctx->ghash_key.k);
+
+	h = ctx->ghash_key.k;
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[1], &h);
+
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[2], &h);
+
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[3], &h);
+
+	return 0;
 }
 
 static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
@@ -341,9 +287,9 @@ static void gcm_update_mac(u64 dg[], const u8 *src, int count, u8 buf[],
 	if (count >= GHASH_BLOCK_SIZE || *buf_count == GHASH_BLOCK_SIZE) {
 		int blocks = count / GHASH_BLOCK_SIZE;
 
-		ghash_do_update(blocks, dg, src, &ctx->ghash_key,
-				*buf_count ? buf : NULL,
-				pmull_ghash_update_p64);
+		ghash_do_simd_update(blocks, dg, src, &ctx->ghash_key,
+				     *buf_count ? buf : NULL,
+				     pmull_ghash_update_p64);
 
 		src += blocks * GHASH_BLOCK_SIZE;
 		count %= GHASH_BLOCK_SIZE;
@@ -387,8 +333,8 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[])
 
 	if (buf_count) {
 		memset(&buf[buf_count], 0, GHASH_BLOCK_SIZE - buf_count);
-		ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL,
-				pmull_ghash_update_p64);
+		ghash_do_simd_update(1, dg, buf, &ctx->ghash_key, NULL,
+				     pmull_ghash_update_p64);
 	}
 }
 
@@ -433,8 +379,8 @@ static int gcm_encrypt(struct aead_request *req)
 			}
 
 			kernel_neon_begin();
-			pmull_gcm_encrypt(nbytes, dst, src, &ctx->ghash_key, dg,
-					  iv, ctx->aes_key.key_enc, nrounds,
+			pmull_gcm_encrypt(nbytes, dst, src, ctx->ghash_key.h,
+					  dg, iv, ctx->aes_key.key_enc, nrounds,
 					  tag);
 			kernel_neon_end();
 
@@ -464,7 +410,7 @@ static int gcm_encrypt(struct aead_request *req)
 			} while (--remaining > 0);
 
 			ghash_do_update(blocks, dg, walk.dst.virt.addr,
-					&ctx->ghash_key, NULL, NULL);
+					&ctx->ghash_key, NULL);
 
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
@@ -483,7 +429,7 @@ static int gcm_encrypt(struct aead_request *req)
 
 		tag = (u8 *)&lengths;
 		ghash_do_update(1, dg, tag, &ctx->ghash_key,
-				walk.nbytes ? buf : NULL, NULL);
+				walk.nbytes ? buf : NULL);
 
 		if (walk.nbytes)
 			err = skcipher_walk_done(&walk, 0);
@@ -547,8 +493,8 @@ static int gcm_decrypt(struct aead_request *req)
 			}
 
 			kernel_neon_begin();
-			pmull_gcm_decrypt(nbytes, dst, src, &ctx->ghash_key, dg,
-					  iv, ctx->aes_key.key_enc, nrounds,
+			pmull_gcm_decrypt(nbytes, dst, src, ctx->ghash_key.h,
+					  dg, iv, ctx->aes_key.key_enc, nrounds,
 					  tag);
 			kernel_neon_end();
 
@@ -568,7 +514,7 @@ static int gcm_decrypt(struct aead_request *req)
 			u8 *dst = walk.dst.virt.addr;
 
 			ghash_do_update(blocks, dg, walk.src.virt.addr,
-					&ctx->ghash_key, NULL, NULL);
+					&ctx->ghash_key, NULL);
 
 			do {
 				aes_encrypt(&ctx->aes_key, buf, iv);
@@ -591,7 +537,7 @@ static int gcm_decrypt(struct aead_request *req)
 
 		tag = (u8 *)&lengths;
 		ghash_do_update(1, dg, tag, &ctx->ghash_key,
-				walk.nbytes ? buf : NULL, NULL);
+				walk.nbytes ? buf : NULL);
 
 		if (walk.nbytes) {
 			aes_encrypt(&ctx->aes_key, buf, iv);
@@ -635,43 +581,28 @@ static struct aead_alg gcm_aes_alg = {
 	.base.cra_driver_name	= "gcm-aes-ce",
 	.base.cra_priority	= 300,
 	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct gcm_aes_ctx),
+	.base.cra_ctxsize	= sizeof(struct gcm_aes_ctx) +
+				  4 * sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
 };
 
 static int __init ghash_ce_mod_init(void)
 {
-	int ret;
-
 	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
 	if (cpu_have_named_feature(PMULL))
-		ret = crypto_register_shashes(ghash_alg,
-					      ARRAY_SIZE(ghash_alg));
-	else
-		/* only register the first array element */
-		ret = crypto_register_shash(ghash_alg);
+		return crypto_register_aead(&gcm_aes_alg);
 
-	if (ret)
-		return ret;
-
-	if (cpu_have_named_feature(PMULL)) {
-		ret = crypto_register_aead(&gcm_aes_alg);
-		if (ret)
-			crypto_unregister_shashes(ghash_alg,
-						  ARRAY_SIZE(ghash_alg));
-	}
-	return ret;
+	return crypto_register_shash(&ghash_alg);
 }
 
 static void __exit ghash_ce_mod_exit(void)
 {
 	if (cpu_have_named_feature(PMULL))
-		crypto_unregister_shashes(ghash_alg, ARRAY_SIZE(ghash_alg));
+		crypto_unregister_aead(&gcm_aes_alg);
 	else
-		crypto_unregister_shash(ghash_alg);
-	crypto_unregister_aead(&gcm_aes_alg);
+		crypto_unregister_shash(&ghash_alg);
 }
 
 static const struct cpu_feature ghash_cpu_feature[] = {
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index a45366c3909b..bd68e1b7f29f 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -47,20 +47,7 @@
 pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
 
 /* ACPI table mapping after acpi_permanent_mmap is set */
-static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
-					    acpi_size size)
-{
-	/* For normal memory we already have a cacheable mapping. */
-	if (memblock_is_map_memory(phys))
-		return (void __iomem *)__phys_to_virt(phys);
-
-	/*
-	 * We should still honor the memory's attribute here because
-	 * crash dump kernel possibly excludes some ACPI (reclaim)
-	 * regions from memblock list.
-	 */
-	return __ioremap(phys, size, __acpi_get_mem_attribute(phys));
-}
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
 #define acpi_os_ioremap acpi_os_ioremap
 
 typedef u64 phys_cpuid_t;
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 5e5dc05d63a0..619db9b4c9d5 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -73,13 +73,13 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 	".pushsection .altinstructions,\"a\"\n"				\
 	ALTINSTR_ENTRY(feature)						\
 	".popsection\n"							\
-	".pushsection .altinstr_replacement, \"a\"\n"			\
+	".subsection 1\n"						\
 	"663:\n\t"							\
 	newinstr "\n"							\
 	"664:\n\t"							\
-	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
-	".org	. - (662b-661b) + (664b-663b)\n"			\
+	".org	. - (662b-661b) + (664b-663b)\n\t"			\
+	".previous\n"							\
 	".endif\n"
 
 #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb)	\
@@ -117,9 +117,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 662:	.pushsection .altinstructions, "a"
 	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 663:	\insn2
-664:	.popsection
+664:	.previous
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
 	.endif
@@ -160,7 +160,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 	.pushsection .altinstructions, "a"
 	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.align 2	/* So GAS knows label 661 is suitably aligned */
 661:
 .endm
@@ -179,9 +179,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 .macro alternative_else
 662:
 	.if .Lasm_alt_mode==0
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.else
-	.popsection
+	.previous
 	.endif
 663:
 .endm
@@ -192,7 +192,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 .macro alternative_endif
 664:
 	.if .Lasm_alt_mode==0
-	.popsection
+	.previous
 	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index a358e97572c1..6647ae4f0231 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -109,7 +109,7 @@ static inline u32 gic_read_pmr(void)
 	return read_sysreg_s(SYS_ICC_PMR_EL1);
 }
 
-static inline void gic_write_pmr(u32 val)
+static __always_inline void gic_write_pmr(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_PMR_EL1);
 }
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 7ae54d7d333a..9f0ec21d6327 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -58,6 +58,7 @@ struct arch_timer_erratum_workaround {
 	u64 (*read_cntvct_el0)(void);
 	int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
 	int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
+	bool disable_compat_vdso;
 };
 
 DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index a08890da696c..015ddffaf6ca 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -99,8 +99,6 @@ static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define arch_atomic_read(v)			__READ_ONCE((v)->counter)
 #define arch_atomic_set(v, i)			__WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index b6f7bc6da5fb..93a161b3bf3f 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -24,16 +24,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
 	__uint128_t tmp;
 	u64 sum;
+	int n = ihl; /* we want it signed */
 
 	tmp = *(const __uint128_t *)iph;
 	iph += 16;
-	ihl -= 4;
+	n -= 4;
 	tmp += ((tmp >> 64) | (tmp << 64));
 	sum = tmp >> 64;
 	do {
 		sum += *(const u32 *)iph;
 		iph += 4;
-	} while (--ihl);
+	} while (--n > 0);
 
 	sum += ((sum >> 32) | (sum << 32));
 	return csum_fold((__force u32)(sum >> 32));
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index d7b3bb0cb180..07b643a70710 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -62,7 +62,9 @@
 #define ARM64_HAS_GENERIC_AUTH			52
 #define ARM64_HAS_32BIT_EL1			53
 #define ARM64_BTI				54
+#define ARM64_HAS_ARMv8_4_TTL			55
+#define ARM64_HAS_TLB_RANGE			56
 
-#define ARM64_NCAPS				55
+#define ARM64_NCAPS				57
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 5d1f4ae42799..89b4f0142c28 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -675,7 +675,7 @@ static inline bool system_supports_generic_auth(void)
 		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
 }
 
-static inline bool system_uses_irq_prio_masking(void)
+static __always_inline bool system_uses_irq_prio_masking(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
@@ -692,6 +692,12 @@ static inline bool system_supports_bti(void)
 	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
 }
 
+static inline bool system_supports_tlb_range(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) &&
+		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
+}
+
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1
@@ -774,6 +780,7 @@ static inline unsigned int get_vmid_bits(u64 mmfr1)
 }
 
 u32 get_kvm_ipa_limit(void);
+void dump_cpu_features(void);
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index a87a93f67671..7219cddeba66 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -86,6 +86,7 @@
 #define QCOM_CPU_PART_FALKOR		0xC00
 #define QCOM_CPU_PART_KRYO		0x200
 #define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
+#define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
 #define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
 
 #define NVIDIA_CPU_PART_DENVER		0x003
@@ -114,6 +115,7 @@
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
 #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
+#define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
 #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index e5ceea213e39..0b298f48f5bf 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -109,6 +109,8 @@ void disable_debug_monitors(enum dbg_active_el el);
 
 void user_rewind_single_step(struct task_struct *task);
 void user_fastforward_single_step(struct task_struct *task);
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task);
 
 void kernel_enable_single_step(struct pt_regs *regs);
 void kernel_disable_single_step(void);
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 94ba0c5bced2..5abf91e3494c 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -49,6 +49,8 @@ extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, unsigned long sz);
 #define set_huge_swap_pte_at set_huge_swap_pte_at
 
+void __init arm64_hugetlb_cma_reserve(void);
+
 #include <asm-generic/hugetlb.h>
 
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index d683bcbf1e7c..22f73fe09030 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -95,6 +95,7 @@
 #define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
 #define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
 #define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
+/* reserved for KERNEL_HWCAP_MTE	__khwcap2_feature(MTE) */
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 3bf626f6fe0c..329fb15f6bac 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -8,7 +8,7 @@
 #ifndef __ASM_KERNEL_PGTABLE_H
 #define __ASM_KERNEL_PGTABLE_H
 
-#include <linux/pgtable.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/sparsemem.h>
 
 /*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index c3e6fcc664b1..e21d4a01372f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -380,9 +380,14 @@ struct kvm_vcpu_arch {
 #define vcpu_has_sve(vcpu) (system_supports_sve() && \
 			    ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE))
 
-#define vcpu_has_ptrauth(vcpu)	((system_supports_address_auth() || \
-				  system_supports_generic_auth()) && \
-				 ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH))
+#ifdef CONFIG_ARM64_PTR_AUTH
+#define vcpu_has_ptrauth(vcpu)						\
+	((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) ||		\
+	  cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) &&		\
+	 (vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH)
+#else
+#define vcpu_has_ptrauth(vcpu)		false
+#endif
 
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
 
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index 81fefd2a1d02..ba89a9af820a 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -12,7 +12,6 @@
  * instead.
  */
 #define BTI_C hint 34 ;
-#define BTI_J hint 36 ;
 
 /*
  * When using in-kernel BTI we need to ensure that PCS-conformant assembly
@@ -43,11 +42,6 @@
 	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
 	BTI_C
 
-#define SYM_INNER_LABEL(name, linkage)			\
-	.type name SYM_T_NONE ASM_NL			\
-	SYM_ENTRY(name, linkage, SYM_A_NONE)		\
-	BTI_J
-
 #endif
 
 /*
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index a1871bb32bb1..afa722504bfd 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -10,11 +10,8 @@
 #ifndef __ASM_MEMORY_H
 #define __ASM_MEMORY_H
 
-#include <linux/compiler.h>
 #include <linux/const.h>
 #include <linux/sizes.h>
-#include <linux/types.h>
-#include <asm/bug.h>
 #include <asm/page-def.h>
 
 /*
@@ -157,11 +154,15 @@
 #endif
 
 #ifndef __ASSEMBLY__
-extern u64			vabits_actual;
-#define PAGE_END		(_PAGE_END(vabits_actual))
 
 #include <linux/bitops.h>
+#include <linux/compiler.h>
 #include <linux/mmdebug.h>
+#include <linux/types.h>
+#include <asm/bug.h>
+
+extern u64			vabits_actual;
+#define PAGE_END		(_PAGE_END(vabits_actual))
 
 extern s64			physvirt_offset;
 extern s64			memstart_addr;
@@ -322,6 +323,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
 })
 
+void dump_mem_limit(void);
 #endif /* !ASSEMBLY */
 
 /*
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 68140fdd89d6..8444df000181 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -19,6 +19,9 @@
 
 typedef struct {
 	atomic64_t	id;
+#ifdef CONFIG_COMPAT
+	void		*sigpage;
+#endif
 	void		*vdso;
 	unsigned long	flags;
 } mm_context_t;
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index b0bd9b55594c..f2d7537d6f83 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -175,7 +175,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp)
  * take CPU migration into account.
  */
 #define destroy_context(mm)		do { } while(0)
-void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
+void check_and_switch_context(struct mm_struct *mm);
 
 #define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
@@ -214,8 +214,6 @@ enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 
 static inline void __switch_mm(struct mm_struct *next)
 {
-	unsigned int cpu = smp_processor_id();
-
 	/*
 	 * init_mm.pgd does not contain any user mappings and it is always
 	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
@@ -225,7 +223,7 @@ static inline void __switch_mm(struct mm_struct *next)
 		return;
 	}
 
-	check_and_switch_context(next, cpu);
+	check_and_switch_context(next);
 }
 
 static inline void
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index e7765b62c712..2c2d7dbe8a02 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -72,6 +72,13 @@
 #define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD				0x36
 #define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD			0x37
 #define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD			0x38
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD			0x39
+#define ARMV8_PMUV3_PERFCTR_OP_RETIRED				0x3A
+#define ARMV8_PMUV3_PERFCTR_OP_SPEC				0x3B
+#define ARMV8_PMUV3_PERFCTR_STALL				0x3C
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND			0x3D
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND			0x3E
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT				0x3F
 
 /* Statistical profiling extension microarchitectural events */
 #define	ARMV8_SPE_PERFCTR_SAMPLE_POP				0x4000
@@ -79,6 +86,26 @@
 #define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE			0x4002
 #define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION			0x4003
 
+/* AMUv1 architecture events */
+#define	ARMV8_AMU_PERFCTR_CNT_CYCLES				0x4004
+#define	ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM			0x4005
+
+/* long-latency read miss events */
+#define	ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS			0x4006
+#define	ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD			0x4009
+#define	ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS			0x400A
+#define	ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD			0x400B
+
+/* additional latency from alignment events */
+#define	ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT			0x4020
+#define	ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT			0x4021
+#define	ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT			0x4022
+
+/* Armv8.5 Memory Tagging Extension events */
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED			0x4024
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD			0x4025
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR			0x4026
+
 /* ARMv8 recommended implementation defined event types */
 #define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD			0x40
 #define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR			0x41
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 9c91a8f93a0e..d400a4d9aee2 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -29,7 +29,7 @@
  * Size mapped by an entry at level n ( 0 <= n <= 3)
  * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
  * in the final page. The maximum number of translation levels supported by
- * the architecture is 4. Hence, starting at at level n, we have further
+ * the architecture is 4. Hence, starting at level n, we have further
  * ((4 - n) - 1) levels of translation excluding the offset within the page.
  * So, the total number of bits mapped by an entry at level n is :
  *
@@ -82,23 +82,23 @@
  * Contiguous page definitions.
  */
 #ifdef CONFIG_ARM64_64K_PAGES
-#define CONT_PTE_SHIFT		5
-#define CONT_PMD_SHIFT		5
+#define CONT_PTE_SHIFT		(5 + PAGE_SHIFT)
+#define CONT_PMD_SHIFT		(5 + PMD_SHIFT)
 #elif defined(CONFIG_ARM64_16K_PAGES)
-#define CONT_PTE_SHIFT		7
-#define CONT_PMD_SHIFT		5
+#define CONT_PTE_SHIFT		(7 + PAGE_SHIFT)
+#define CONT_PMD_SHIFT		(5 + PMD_SHIFT)
 #else
-#define CONT_PTE_SHIFT		4
-#define CONT_PMD_SHIFT		4
+#define CONT_PTE_SHIFT		(4 + PAGE_SHIFT)
+#define CONT_PMD_SHIFT		(4 + PMD_SHIFT)
 #endif
 
-#define CONT_PTES		(1 << CONT_PTE_SHIFT)
+#define CONT_PTES		(1 << (CONT_PTE_SHIFT - PAGE_SHIFT))
 #define CONT_PTE_SIZE		(CONT_PTES * PAGE_SIZE)
 #define CONT_PTE_MASK		(~(CONT_PTE_SIZE - 1))
-#define CONT_PMDS		(1 << CONT_PMD_SHIFT)
+#define CONT_PMDS		(1 << (CONT_PMD_SHIFT - PMD_SHIFT))
 #define CONT_PMD_SIZE		(CONT_PMDS * PMD_SIZE)
 #define CONT_PMD_MASK		(~(CONT_PMD_SIZE - 1))
-/* the the numerical offset of the PTE within a range of CONT_PTES */
+/* the numerical offset of the PTE within a range of CONT_PTES */
 #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
 
 /*
@@ -178,10 +178,12 @@
 #define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
 #define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 #define PTE_S2_XN		(_AT(pteval_t, 2) << 53)  /* XN[1:0] */
+#define PTE_S2_SW_RESVD		(_AT(pteval_t, 15) << 55) /* Reserved for SW */
 
 #define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 #define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
+#define PMD_S2_SW_RESVD		(_AT(pmdval_t, 15) << 55) /* Reserved for SW */
 
 #define PUD_S2_RDONLY		(_AT(pudval_t, 1) << 6)   /* HAP[2:1] */
 #define PUD_S2_RDWR		(_AT(pudval_t, 3) << 6)   /* HAP[2:1] */
@@ -216,6 +218,7 @@
 #define TCR_TxSZ(x)		(TCR_T0SZ(x) | TCR_T1SZ(x))
 #define TCR_TxSZ_WIDTH		6
 #define TCR_T0SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
+#define TCR_T1SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T1SZ_OFFSET)
 
 #define TCR_EPD0_SHIFT		7
 #define TCR_EPD0_MASK		(UL(1) << TCR_EPD0_SHIFT)
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2e7e0f452301..4d867c6446c4 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -67,7 +67,7 @@ extern bool arm64_use_ng_mappings;
 #define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
 #define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
 #define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
-#define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
+#define PAGE_HYP_DEVICE		__pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN)
 
 #define PAGE_S2_MEMATTR(attr)						\
 	({								\
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 6dbd267ab931..d5d3fbe73953 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -40,6 +40,16 @@ extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pud_error(const char *file, int line, unsigned long val);
 extern void __pgd_error(const char *file, int line, unsigned long val);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+
+/* Set stride and tlb_level in flush_*_tlb_range */
+#define flush_pmd_tlb_range(vma, addr, end)	\
+	__flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2)
+#define flush_pud_tlb_range(vma, addr, end)	\
+	__flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -416,7 +426,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
 
 #define pgprot_nx(prot) \
-	__pgprot_modify(prot, 0, PTE_PXN)
+	__pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN)
 
 /*
  * Mark the prot value as uncacheable and unbufferable.
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 953b6a1ce549..966ed30ed5f7 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -27,7 +27,7 @@
  *
  * Some code sections either automatically switch back to PSR.I or explicitly
  * require to not use priority masking. If bit GIC_PRIO_PSR_I_SET is included
- * in the  the priority mask, it indicates that PSR.I should be set and
+ * in the priority mask, it indicates that PSR.I should be set and
  * interrupt disabling temporarily does not rely on IRQ priorities.
  */
 #define GIC_PRIO_IRQON			0xe0
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index ea268d88b6f7..a0c8a0b65259 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -30,7 +30,6 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
-#include <asm/pointer_auth.h>
 
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index b767904f28b1..996bf98f0cab 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -256,4 +256,13 @@ stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
+/*
+ * Level values for the ARMv8.4-TTL extension, mapping PUD/PMD/PTE and
+ * the architectural page-table level.
+ */
+#define S2_NO_LEVEL_HINT	0
+#define S2_PUD_LEVEL		1
+#define S2_PMD_LEVEL		2
+#define S2_PTE_LEVEL		3
+
 #endif	/* __ARM64_S2_PGTABLE_H_ */
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 65299a2dcf9c..cfc0672013f6 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -34,6 +34,10 @@ static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
 	unsigned long error = regs->regs[0];
+
+	if (is_compat_thread(task_thread_info(task)))
+		error = sign_extend64(error, 31);
+
 	return IS_ERR_VALUE(error) ? error : 0;
 }
 
@@ -47,7 +51,13 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	regs->regs[0] = (long) error ? error : val;
+	if (error)
+		val = error;
+
+	if (is_compat_thread(task_thread_info(task)))
+		val = lower_32_bits(val);
+
+	regs->regs[0] = val;
 }
 
 #define SYSCALL_MAX_ARGS 6
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 463175f80341..554a7e8ecb07 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -421,9 +421,9 @@
  */
 
 #define SYS_AMEVCNTR0_EL0(n)		SYS_AM_EL0(4 + ((n) >> 3), (n) & 7)
-#define SYS_AMEVTYPE0_EL0(n)		SYS_AM_EL0(6 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPER0_EL0(n)		SYS_AM_EL0(6 + ((n) >> 3), (n) & 7)
 #define SYS_AMEVCNTR1_EL0(n)		SYS_AM_EL0(12 + ((n) >> 3), (n) & 7)
-#define SYS_AMEVTYPE1_EL0(n)		SYS_AM_EL0(14 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPER1_EL0(n)		SYS_AM_EL0(14 + ((n) >> 3), (n) & 7)
 
 /* AMU v1: Fixed (architecturally defined) activity monitors */
 #define SYS_AMEVCNTR0_CORE_EL0		SYS_AMEVCNTR0_EL0(0)
@@ -617,6 +617,9 @@
 #define ID_AA64ISAR0_SHA1_SHIFT		8
 #define ID_AA64ISAR0_AES_SHIFT		4
 
+#define ID_AA64ISAR0_TLB_RANGE_NI	0x0
+#define ID_AA64ISAR0_TLB_RANGE		0x2
+
 /* id_aa64isar1 */
 #define ID_AA64ISAR1_I8MM_SHIFT		52
 #define ID_AA64ISAR1_DGH_SHIFT		48
@@ -706,6 +709,9 @@
 #define ID_AA64ZFR0_SVEVER_SVE2		0x1
 
 /* id_aa64mmfr0 */
+#define ID_AA64MMFR0_ECV_SHIFT		60
+#define ID_AA64MMFR0_FGT_SHIFT		56
+#define ID_AA64MMFR0_EXS_SHIFT		44
 #define ID_AA64MMFR0_TGRAN4_2_SHIFT	40
 #define ID_AA64MMFR0_TGRAN64_2_SHIFT	36
 #define ID_AA64MMFR0_TGRAN16_2_SHIFT	32
@@ -734,6 +740,10 @@
 #endif
 
 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_ETS_SHIFT		36
+#define ID_AA64MMFR1_TWED_SHIFT		32
+#define ID_AA64MMFR1_XNX_SHIFT		28
+#define ID_AA64MMFR1_SPECSEI_SHIFT	24
 #define ID_AA64MMFR1_PAN_SHIFT		20
 #define ID_AA64MMFR1_LOR_SHIFT		16
 #define ID_AA64MMFR1_HPD_SHIFT		12
@@ -746,8 +756,15 @@
 
 /* id_aa64mmfr2 */
 #define ID_AA64MMFR2_E0PD_SHIFT		60
+#define ID_AA64MMFR2_EVT_SHIFT		56
+#define ID_AA64MMFR2_BBM_SHIFT		52
+#define ID_AA64MMFR2_TTL_SHIFT		48
 #define ID_AA64MMFR2_FWB_SHIFT		40
+#define ID_AA64MMFR2_IDS_SHIFT		36
 #define ID_AA64MMFR2_AT_SHIFT		32
+#define ID_AA64MMFR2_ST_SHIFT		28
+#define ID_AA64MMFR2_NV_SHIFT		24
+#define ID_AA64MMFR2_CCIDX_SHIFT	20
 #define ID_AA64MMFR2_LVA_SHIFT		16
 #define ID_AA64MMFR2_IESB_SHIFT		12
 #define ID_AA64MMFR2_LSM_SHIFT		8
@@ -755,6 +772,7 @@
 #define ID_AA64MMFR2_CNP_SHIFT		0
 
 /* id_aa64dfr0 */
+#define ID_AA64DFR0_DOUBLELOCK_SHIFT	36
 #define ID_AA64DFR0_PMSVER_SHIFT	32
 #define ID_AA64DFR0_CTX_CMPS_SHIFT	28
 #define ID_AA64DFR0_WRPS_SHIFT		20
@@ -807,18 +825,40 @@
 #define ID_ISAR6_DP_SHIFT		4
 #define ID_ISAR6_JSCVT_SHIFT		0
 
+#define ID_MMFR0_INNERSHR_SHIFT		28
+#define ID_MMFR0_FCSE_SHIFT		24
+#define ID_MMFR0_AUXREG_SHIFT		20
+#define ID_MMFR0_TCM_SHIFT		16
+#define ID_MMFR0_SHARELVL_SHIFT		12
+#define ID_MMFR0_OUTERSHR_SHIFT		8
+#define ID_MMFR0_PMSA_SHIFT		4
+#define ID_MMFR0_VMSA_SHIFT		0
+
 #define ID_MMFR4_EVT_SHIFT		28
 #define ID_MMFR4_CCIDX_SHIFT		24
 #define ID_MMFR4_LSM_SHIFT		20
 #define ID_MMFR4_HPDS_SHIFT		16
 #define ID_MMFR4_CNP_SHIFT		12
 #define ID_MMFR4_XNX_SHIFT		8
+#define ID_MMFR4_AC2_SHIFT		4
 #define ID_MMFR4_SPECSEI_SHIFT		0
 
 #define ID_MMFR5_ETS_SHIFT		0
 
 #define ID_PFR0_DIT_SHIFT		24
 #define ID_PFR0_CSV2_SHIFT		16
+#define ID_PFR0_STATE3_SHIFT		12
+#define ID_PFR0_STATE2_SHIFT		8
+#define ID_PFR0_STATE1_SHIFT		4
+#define ID_PFR0_STATE0_SHIFT		0
+
+#define ID_DFR0_PERFMON_SHIFT		24
+#define ID_DFR0_MPROFDBG_SHIFT		20
+#define ID_DFR0_MMAPTRC_SHIFT		16
+#define ID_DFR0_COPTRC_SHIFT		12
+#define ID_DFR0_MMAPDBG_SHIFT		8
+#define ID_DFR0_COPSDBG_SHIFT		4
+#define ID_DFR0_COPDBG_SHIFT		0
 
 #define ID_PFR2_SSBS_SHIFT		4
 #define ID_PFR2_CSV3_SHIFT		0
@@ -861,6 +901,11 @@
 #define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN64_SUPPORTED
 #endif
 
+#define MVFR2_FPMISC_SHIFT		4
+#define MVFR2_SIMDMISC_SHIFT		0
+
+#define DCZID_DZP_SHIFT			4
+#define DCZID_BS_SHIFT			0
 
 /*
  * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 6ea8b6a26ae9..5e784e16ee89 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -93,6 +93,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_FSCHECK		(1 << TIF_FSCHECK)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
 
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index b76df828e6b7..61c97d3b58c7 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -21,11 +21,37 @@ static void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
 
+/*
+ * get the tlbi levels in arm64.  Default value is 0 if more than one
+ * of cleared_* is set or neither is set.
+ * Arm64 doesn't support p4ds now.
+ */
+static inline int tlb_get_level(struct mmu_gather *tlb)
+{
+	if (tlb->cleared_ptes && !(tlb->cleared_pmds ||
+				   tlb->cleared_puds ||
+				   tlb->cleared_p4ds))
+		return 3;
+
+	if (tlb->cleared_pmds && !(tlb->cleared_ptes ||
+				   tlb->cleared_puds ||
+				   tlb->cleared_p4ds))
+		return 2;
+
+	if (tlb->cleared_puds && !(tlb->cleared_ptes ||
+				   tlb->cleared_pmds ||
+				   tlb->cleared_p4ds))
+		return 1;
+
+	return 0;
+}
+
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
 	bool last_level = !tlb->freed_tables;
 	unsigned long stride = tlb_get_unmap_size(tlb);
+	int tlb_level = tlb_get_level(tlb);
 
 	/*
 	 * If we're tearing down the address space then we only care about
@@ -38,7 +64,8 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 		return;
 	}
 
-	__flush_tlb_range(&vma, tlb->start, tlb->end, stride, last_level);
+	__flush_tlb_range(&vma, tlb->start, tlb->end, stride,
+			  last_level, tlb_level);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index bc3949064725..d493174415db 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -10,6 +10,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bitfield.h>
 #include <linux/mm_types.h>
 #include <linux/sched.h>
 #include <asm/cputype.h>
@@ -60,6 +61,102 @@
 	})
 
 /*
+ * Get translation granule of the system, which is decided by
+ * PAGE_SIZE.  Used by TTL.
+ *  - 4KB	: 1
+ *  - 16KB	: 2
+ *  - 64KB	: 3
+ */
+#define TLBI_TTL_TG_4K		1
+#define TLBI_TTL_TG_16K		2
+#define TLBI_TTL_TG_64K		3
+
+static inline unsigned long get_trans_granule(void)
+{
+	switch (PAGE_SIZE) {
+	case SZ_4K:
+		return TLBI_TTL_TG_4K;
+	case SZ_16K:
+		return TLBI_TTL_TG_16K;
+	case SZ_64K:
+		return TLBI_TTL_TG_64K;
+	default:
+		return 0;
+	}
+}
+
+/*
+ * Level-based TLBI operations.
+ *
+ * When ARMv8.4-TTL exists, TLBI operations take an additional hint for
+ * the level at which the invalidation must take place. If the level is
+ * wrong, no invalidation may take place. In the case where the level
+ * cannot be easily determined, a 0 value for the level parameter will
+ * perform a non-hinted invalidation.
+ *
+ * For Stage-2 invalidation, use the level values provided to that effect
+ * in asm/stage2_pgtable.h.
+ */
+#define TLBI_TTL_MASK		GENMASK_ULL(47, 44)
+
+#define __tlbi_level(op, addr, level) do {				\
+	u64 arg = addr;							\
+									\
+	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) &&		\
+	    level) {							\
+		u64 ttl = level & 3;					\
+		ttl |= get_trans_granule() << 2;			\
+		arg &= ~TLBI_TTL_MASK;					\
+		arg |= FIELD_PREP(TLBI_TTL_MASK, ttl);			\
+	}								\
+									\
+	__tlbi(op, arg);						\
+} while(0)
+
+#define __tlbi_user_level(op, arg, level) do {				\
+	if (arm64_kernel_unmapped_at_el0())				\
+		__tlbi_level(op, (arg | USER_ASID_FLAG), level);	\
+} while (0)
+
+/*
+ * This macro creates a properly formatted VA operand for the TLB RANGE.
+ * The value bit assignments are:
+ *
+ * +----------+------+-------+-------+-------+----------------------+
+ * |   ASID   |  TG  | SCALE |  NUM  |  TTL  |        BADDR         |
+ * +-----------------+-------+-------+-------+----------------------+
+ * |63      48|47  46|45   44|43   39|38   37|36                   0|
+ *
+ * The address range is determined by below formula:
+ * [BADDR, BADDR + (NUM + 1) * 2^(5*SCALE + 1) * PAGESIZE)
+ *
+ */
+#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl)		\
+	({							\
+		unsigned long __ta = (addr) >> PAGE_SHIFT;	\
+		__ta &= GENMASK_ULL(36, 0);			\
+		__ta |= (unsigned long)(ttl) << 37;		\
+		__ta |= (unsigned long)(num) << 39;		\
+		__ta |= (unsigned long)(scale) << 44;		\
+		__ta |= get_trans_granule() << 46;		\
+		__ta |= (unsigned long)(asid) << 48;		\
+		__ta;						\
+	})
+
+/* These macros are used by the TLBI RANGE feature. */
+#define __TLBI_RANGE_PAGES(num, scale)	\
+	((unsigned long)((num) + 1) << (5 * (scale) + 1))
+#define MAX_TLBI_RANGE_PAGES		__TLBI_RANGE_PAGES(31, 3)
+
+/*
+ * Generate 'num' values from -1 to 30 with -1 rejected by the
+ * __flush_tlb_range() loop below.
+ */
+#define TLBI_RANGE_MASK			GENMASK_ULL(4, 0)
+#define __TLBI_RANGE_NUM(pages, scale)	\
+	((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1)
+
+/*
  *	TLB Invalidation
  *	================
  *
@@ -179,34 +276,83 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
-				     unsigned long stride, bool last_level)
+				     unsigned long stride, bool last_level,
+				     int tlb_level)
 {
+	int num = 0;
+	int scale = 0;
 	unsigned long asid = ASID(vma->vm_mm);
 	unsigned long addr;
+	unsigned long pages;
 
 	start = round_down(start, stride);
 	end = round_up(end, stride);
+	pages = (end - start) >> PAGE_SHIFT;
 
-	if ((end - start) >= (MAX_TLBI_OPS * stride)) {
+	/*
+	 * When not uses TLB range ops, we can handle up to
+	 * (MAX_TLBI_OPS - 1) pages;
+	 * When uses TLB range ops, we can handle up to
+	 * (MAX_TLBI_RANGE_PAGES - 1) pages.
+	 */
+	if ((!system_supports_tlb_range() &&
+	     (end - start) >= (MAX_TLBI_OPS * stride)) ||
+	    pages >= MAX_TLBI_RANGE_PAGES) {
 		flush_tlb_mm(vma->vm_mm);
 		return;
 	}
 
-	/* Convert the stride into units of 4k */
-	stride >>= 12;
+	dsb(ishst);
 
-	start = __TLBI_VADDR(start, asid);
-	end = __TLBI_VADDR(end, asid);
+	/*
+	 * When the CPU does not support TLB range operations, flush the TLB
+	 * entries one by one at the granularity of 'stride'. If the the TLB
+	 * range ops are supported, then:
+	 *
+	 * 1. If 'pages' is odd, flush the first page through non-range
+	 *    operations;
+	 *
+	 * 2. For remaining pages: the minimum range granularity is decided
+	 *    by 'scale', so multiple range TLBI operations may be required.
+	 *    Start from scale = 0, flush the corresponding number of pages
+	 *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
+	 *    until no pages left.
+	 *
+	 * Note that certain ranges can be represented by either num = 31 and
+	 * scale or num = 0 and scale + 1. The loop below favours the latter
+	 * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
+	 */
+	while (pages > 0) {
+		if (!system_supports_tlb_range() ||
+		    pages % 2 == 1) {
+			addr = __TLBI_VADDR(start, asid);
+			if (last_level) {
+				__tlbi_level(vale1is, addr, tlb_level);
+				__tlbi_user_level(vale1is, addr, tlb_level);
+			} else {
+				__tlbi_level(vae1is, addr, tlb_level);
+				__tlbi_user_level(vae1is, addr, tlb_level);
+			}
+			start += stride;
+			pages -= stride >> PAGE_SHIFT;
+			continue;
+		}
 
-	dsb(ishst);
-	for (addr = start; addr < end; addr += stride) {
-		if (last_level) {
-			__tlbi(vale1is, addr);
-			__tlbi_user(vale1is, addr);
-		} else {
-			__tlbi(vae1is, addr);
-			__tlbi_user(vae1is, addr);
+		num = __TLBI_RANGE_NUM(pages, scale);
+		if (num >= 0) {
+			addr = __TLBI_VADDR_RANGE(start, asid, scale,
+						  num, tlb_level);
+			if (last_level) {
+				__tlbi(rvale1is, addr);
+				__tlbi_user(rvale1is, addr);
+			} else {
+				__tlbi(rvae1is, addr);
+				__tlbi_user(rvae1is, addr);
+			}
+			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT;
+			pages -= __TLBI_RANGE_PAGES(num, scale);
 		}
+		scale++;
 	}
 	dsb(ish);
 }
@@ -217,8 +363,9 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	/*
 	 * We cannot use leaf-only invalidation here, since we may be invalidating
 	 * table entries as part of collapsing hugepages or moving page tables.
+	 * Set the tlb_level to 0 because we can not get enough information here.
 	 */
-	__flush_tlb_range(vma, start, end, PAGE_SIZE, false);
+	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 0cc835ddfcd1..e042f6527981 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -34,8 +34,9 @@ void topology_scale_freq_tick(void);
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure retrieve API */
+/* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_set_thermal_pressure   topology_set_thermal_pressure
 
 #include <asm-generic/topology.h>
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index bc5c7b091152..8d7c466f809b 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -19,6 +19,7 @@
 #include <linux/string.h>
 
 #include <asm/cpufeature.h>
+#include <asm/mmu.h>
 #include <asm/ptrace.h>
 #include <asm/memory.h>
 #include <asm/extable.h>
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index 07468428fd29..f99dcb94b438 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -12,6 +12,8 @@
  */
 #define VDSO_LBASE	0x0
 
+#define __VVAR_PAGES    2
+
 #ifndef __ASSEMBLY__
 
 #include <generated/vdso-offsets.h>
diff --git a/arch/arm64/include/asm/vdso/clocksource.h b/arch/arm64/include/asm/vdso/clocksource.h
index df6ea65c1dec..b054d9febfb5 100644
--- a/arch/arm64/include/asm/vdso/clocksource.h
+++ b/arch/arm64/include/asm/vdso/clocksource.h
@@ -2,7 +2,10 @@
 #ifndef __ASM_VDSOCLOCKSOURCE_H
 #define __ASM_VDSOCLOCKSOURCE_H
 
-#define VDSO_ARCH_CLOCKMODES	\
-	VDSO_CLOCKMODE_ARCHTIMER
+#define VDSO_ARCH_CLOCKMODES					\
+	/* vdso clocksource for both 32 and 64bit tasks */	\
+	VDSO_CLOCKMODE_ARCHTIMER,				\
+	/* vdso clocksource for 64bit tasks only */		\
+	VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT
 
 #endif
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index b6907ae78e53..75cbae60455b 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 #include <asm/errno.h>
 
@@ -111,7 +112,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
 	 * update. Return something. Core will do another round and then
 	 * see the mode change and fallback to the syscall.
 	 */
-	if (clock_mode == VDSO_CLOCKMODE_NONE)
+	if (clock_mode != VDSO_CLOCKMODE_ARCHTIMER)
 		return 0;
 
 	/*
@@ -152,6 +153,24 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
 	return ret;
 }
 
+#ifdef CONFIG_TIME_NS
+static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	const struct vdso_data *ret;
+
+	/* See __arch_get_vdso_data(). */
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_timens_data));
+
+	return ret;
+}
+#endif
+
+static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+{
+	return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
+}
+#define vdso_clocksource_ok	vdso_clocksource_ok
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index afba6ba332f8..9c29ad3049f8 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 
 #define VDSO_HAS_CLOCK_GETRES		1
@@ -96,6 +97,14 @@ const struct vdso_data *__arch_get_vdso_data(void)
 	return _vdso_data;
 }
 
+#ifdef CONFIG_TIME_NS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	return _timens_data;
+}
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 2d6ba1c2592e..912162f73529 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -74,5 +74,6 @@
 #define HWCAP2_DGH		(1 << 15)
 #define HWCAP2_RNG		(1 << 16)
 #define HWCAP2_BTI		(1 << 17)
+/* reserved for HWCAP2_MTE	(1 << 18) */
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index 8b0ebce92427..0c796c795dbe 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -179,7 +179,7 @@ struct sve_context {
  * The same convention applies when returning from a signal: a caller
  * will need to remove or resize the sve_context block if it wants to
  * make the SVE registers live when they were previously non-live or
- * vice-versa.  This may require the the caller to allocate fresh
+ * vice-versa.  This may require the caller to allocate fresh
  * memory and/or move other context blocks in the signal frame.
  *
  * Changing the vector length during signal return is not permitted:
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 151f28521f1e..a561cbb91d4d 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -29,9 +29,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 
 obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
 					   sys_compat.o
-ifneq ($(CONFIG_COMPAT_VDSO), y)
 obj-$(CONFIG_COMPAT)			+= sigreturn32.o
-endif
 obj-$(CONFIG_KUSER_HELPERS)		+= kuser32.o
 obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
 obj-$(CONFIG_MODULES)			+= module.o
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index a7586a4db142..455966401102 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -261,6 +261,81 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 	return __pgprot(PROT_DEVICE_nGnRnE);
 }
 
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
+{
+	efi_memory_desc_t *md, *region = NULL;
+	pgprot_t prot;
+
+	if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP)))
+		return NULL;
+
+	for_each_efi_memory_desc(md) {
+		u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
+
+		if (phys < md->phys_addr || phys >= end)
+			continue;
+
+		if (phys + size > end) {
+			pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n");
+			return NULL;
+		}
+		region = md;
+		break;
+	}
+
+	/*
+	 * It is fine for AML to remap regions that are not represented in the
+	 * EFI memory map at all, as it only describes normal memory, and MMIO
+	 * regions that require a virtual mapping to make them accessible to
+	 * the EFI runtime services.
+	 */
+	prot = __pgprot(PROT_DEVICE_nGnRnE);
+	if (region) {
+		switch (region->type) {
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
+		case EFI_BOOT_SERVICES_CODE:
+		case EFI_BOOT_SERVICES_DATA:
+		case EFI_CONVENTIONAL_MEMORY:
+		case EFI_PERSISTENT_MEMORY:
+			pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
+			return NULL;
+
+		case EFI_RUNTIME_SERVICES_CODE:
+			/*
+			 * This would be unusual, but not problematic per se,
+			 * as long as we take care not to create a writable
+			 * mapping for executable code.
+			 */
+			prot = PAGE_KERNEL_RO;
+			break;
+
+		case EFI_ACPI_RECLAIM_MEMORY:
+			/*
+			 * ACPI reclaim memory is used to pass firmware tables
+			 * and other data that is intended for consumption by
+			 * the OS only, which may decide it wants to reclaim
+			 * that memory and use it for something else. We never
+			 * do that, but we usually add it to the linear map
+			 * anyway, in which case we should use the existing
+			 * mapping.
+			 */
+			if (memblock_is_map_memory(phys))
+				return (void __iomem *)__phys_to_virt(phys);
+			/* fall through */
+
+		default:
+			if (region->attribute & EFI_MEMORY_WB)
+				prot = PAGE_KERNEL;
+			else if (region->attribute & EFI_MEMORY_WT)
+				prot = __pgprot(PROT_NORMAL_WT);
+			else if (region->attribute & EFI_MEMORY_WC)
+				prot = __pgprot(PROT_NORMAL_NC);
+		}
+	}
+	return __ioremap(phys, size, prot);
+}
+
 /*
  * Claim Synchronous External Aborts as a firmware first notification.
  *
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d1757ef1b1e7..73039949b5ce 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature)
  */
 static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	unsigned long replptr;
-
-	if (kernel_text_address(pc))
-		return true;
-
-	replptr = (unsigned long)ALT_REPL_PTR(alt);
-	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return false;
-
-	/*
-	 * Branching into *another* alternate sequence is doomed, and
-	 * we're not even trying to fix it up.
-	 */
-	BUG();
+	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
+	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
 }
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index ad06d6802d2e..79728bfb5351 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -460,6 +460,8 @@ static const struct midr_range arm64_ssb_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
 	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 	{},
 };
 
@@ -470,12 +472,7 @@ static bool
 has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry,
 			       int scope)
 {
-	u32 midr = read_cpuid_id();
-	/* Cortex-A76 r0p0 - r3p1 */
-	struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1);
-
-	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode();
+	return is_affected_midr_range_list(entry, scope) && is_kernel_in_hyp_mode();
 }
 #endif
 
@@ -726,6 +723,8 @@ static const struct midr_range erratum_1418040_list[] = {
 	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1),
 	/* Neoverse-N1 r0p0 to r3p1 */
 	MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 3, 1),
+	/* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */
+	MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf),
 	{},
 };
 #endif
@@ -770,11 +769,23 @@ static const struct midr_range erratum_speculative_at_list[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1530923
 	/* Cortex A55 r0p0 to r2p0 */
 	MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0),
+	/* Kryo4xx Silver (rdpe => r1p0) */
+	MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe),
 #endif
 	{},
 };
 #endif
 
+#ifdef CONFIG_ARM64_ERRATUM_1463225
+static const struct midr_range erratum_1463225[] = {
+	/* Cortex-A76 r0p0 - r3p1 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1),
+	/* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */
+	MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf),
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -914,6 +925,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_WORKAROUND_1463225,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_cortex_a76_erratum_1463225,
+		.midr_range_list = erratum_1463225,
 	},
 #endif
 #ifdef CONFIG_CAVIUM_TX2_ERRATUM_219
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4ae41670c2e6..a389b999482e 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -119,25 +119,12 @@ static inline void finalize_system_capabilities(void)
 	static_branch_enable(&arm64_const_caps_ready);
 }
 
-static int dump_cpu_hwcaps(struct notifier_block *self, unsigned long v, void *p)
+void dump_cpu_features(void)
 {
 	/* file-wide pr_fmt adds "CPU features: " prefix */
 	pr_emerg("0x%*pb\n", ARM64_NCAPS, &cpu_hwcaps);
-	return 0;
 }
 
-static struct notifier_block cpu_hwcaps_notifier = {
-	.notifier_call = dump_cpu_hwcaps
-};
-
-static int __init register_cpu_hwcaps_dumper(void)
-{
-	atomic_notifier_chain_register(&panic_notifier_list,
-				       &cpu_hwcaps_notifier);
-	return 0;
-}
-__initcall(register_cpu_hwcaps_dumper);
-
 DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcap_keys);
 
@@ -269,6 +256,9 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EXS_SHIFT, 4, 0),
 	/*
 	 * Page size not being supported at Stage-2 is not fatal. You
 	 * just give up KVM if PAGE_SIZE isn't supported there. Go fix
@@ -312,6 +302,10 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_ETS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TWED_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_XNX_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64MMFR1_SPECSEI_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HPD_SHIFT, 4, 0),
@@ -323,8 +317,15 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_E0PD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EVT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_BBM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_TTL_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IDS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_ST_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_NV_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CCIDX_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
@@ -345,7 +346,7 @@ static const struct arm64_ftr_bits ftr_ctr[] = {
 	 * make use of *minLine.
 	 * If we have differing I-cache policies, report it as the weakest - VIPT.
 	 */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_VIPT),	/* L1Ip */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, CTR_L1IP_SHIFT, 2, ICACHE_POLICY_VIPT),	/* L1Ip */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IMINLINE_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
@@ -356,19 +357,19 @@ struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0xf),	/* InnerShr */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0),	/* FCSE */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* AuxReg */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),	/* TCM */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),	/* ShareLvl */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0xf),	/* OuterShr */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),	/* PMSA */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* VMSA */
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_INNERSHR_SHIFT, 4, 0xf),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_FCSE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_MMFR0_AUXREG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_TCM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_SHARELVL_SHIFT, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_OUTERSHR_SHIFT, 4, 0xf),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_PMSA_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_VMSA_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 36, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_DOUBLELOCK_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_PMSVER_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
@@ -384,14 +385,14 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_mvfr2[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),		/* FPMisc */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),		/* SIMDMisc */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_dczid[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 4, 1, 1),		/* DZP */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* BS */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, DCZID_DZP_SHIFT, 1, 1),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, DCZID_BS_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -423,7 +424,8 @@ static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_HPDS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_CNP_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_XNX_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),	/* ac2 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_AC2_SHIFT, 4, 0),
+
 	/*
 	 * SpecSEI = 1 indicates that the PE might generate an SError on an
 	 * external abort on speculative read. It is safe to assume that an
@@ -465,10 +467,10 @@ static const struct arm64_ftr_bits ftr_id_isar6[] = {
 static const struct arm64_ftr_bits ftr_id_pfr0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_DIT_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR0_CSV2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),		/* State3 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0),		/* State2 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),		/* State1 */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),		/* State0 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE1_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE0_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -492,13 +494,13 @@ static const struct arm64_ftr_bits ftr_id_pfr2[] = {
 
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	/* [31:28] TraceFilt */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf),	/* PerfMon */
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_PERFMON_SHIFT, 4, 0xf),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MPROFDBG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPTRC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPTRC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPDBG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPSDBG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPDBG_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -697,11 +699,52 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new,
 
 static void __init sort_ftr_regs(void)
 {
-	int i;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(arm64_ftr_regs); i++) {
+		const struct arm64_ftr_reg *ftr_reg = arm64_ftr_regs[i].reg;
+		const struct arm64_ftr_bits *ftr_bits = ftr_reg->ftr_bits;
+		unsigned int j = 0;
+
+		/*
+		 * Features here must be sorted in descending order with respect
+		 * to their shift values and should not overlap with each other.
+		 */
+		for (; ftr_bits->width != 0; ftr_bits++, j++) {
+			unsigned int width = ftr_reg->ftr_bits[j].width;
+			unsigned int shift = ftr_reg->ftr_bits[j].shift;
+			unsigned int prev_shift;
+
+			WARN((shift  + width) > 64,
+				"%s has invalid feature at shift %d\n",
+				ftr_reg->name, shift);
+
+			/*
+			 * Skip the first feature. There is nothing to
+			 * compare against for now.
+			 */
+			if (j == 0)
+				continue;
+
+			prev_shift = ftr_reg->ftr_bits[j - 1].shift;
+			WARN((shift + width) > prev_shift,
+				"%s has feature overlap at shift %d\n",
+				ftr_reg->name, shift);
+		}
 
-	/* Check that the array is sorted so that we can do the binary search */
-	for (i = 1; i < ARRAY_SIZE(arm64_ftr_regs); i++)
+		/*
+		 * Skip the first register. There is nothing to
+		 * compare against for now.
+		 */
+		if (i == 0)
+			continue;
+		/*
+		 * Registers here must be sorted in ascending order with respect
+		 * to sys_id for subsequent binary search in get_arm64_ftr_reg()
+		 * to work correctly.
+		 */
 		BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id);
+	}
 }
 
 /*
@@ -1290,6 +1333,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 		MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 		{ /* sentinel */ }
 	};
 	char const *str = "kpti command line option";
@@ -1406,6 +1451,8 @@ static bool cpu_has_broken_dbm(void)
 	static const struct midr_range cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1024718
 		MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 1, 0),  // A55 r0p0 -r1p0
+		/* Kryo4xx Silver (rdpe => r1p0) */
+		MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe),
 #endif
 		{},
 	};
@@ -1880,6 +1927,26 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.cpu_enable = cpu_has_fwb,
 	},
+	{
+		.desc = "ARMv8.4 Translation Table Level",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_HAS_ARMv8_4_TTL,
+		.sys_reg = SYS_ID_AA64MMFR2_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR2_TTL_SHIFT,
+		.min_field_value = 1,
+		.matches = has_cpuid_feature,
+	},
+	{
+		.desc = "TLB range maintenance instructions",
+		.capability = ARM64_HAS_TLB_RANGE,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR0_EL1,
+		.field_pos = ID_AA64ISAR0_TLB_SHIFT,
+		.sign = FTR_UNSIGNED,
+		.min_field_value = ID_AA64ISAR0_TLB_RANGE,
+	},
 #ifdef CONFIG_ARM64_HW_AFDBM
 	{
 		/*
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 86637466daa8..393c6fb1f1cb 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -93,6 +93,7 @@ static const char *const hwcap_str[] = {
 	"dgh",
 	"rng",
 	"bti",
+	/* reserved for "mte" */
 	NULL
 };
 
diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c
index 1f646b07e3e9..314391a156ee 100644
--- a/arch/arm64/kernel/crash_core.c
+++ b/arch/arm64/kernel/crash_core.c
@@ -7,6 +7,14 @@
 #include <linux/crash_core.h>
 #include <asm/cpufeature.h>
 #include <asm/memory.h>
+#include <asm/pgtable-hwdef.h>
+
+static inline u64 get_tcr_el1_t1sz(void);
+
+static inline u64 get_tcr_el1_t1sz(void)
+{
+	return (read_sysreg(tcr_el1) & TCR_T1SZ_MASK) >> TCR_T1SZ_OFFSET;
+}
 
 void arch_crash_save_vmcoreinfo(void)
 {
@@ -16,6 +24,8 @@ void arch_crash_save_vmcoreinfo(void)
 						kimage_voffset);
 	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
 						PHYS_OFFSET);
+	vmcoreinfo_append_str("NUMBER(TCR_EL1_T1SZ)=0x%llx\n",
+						get_tcr_el1_t1sz());
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
 	vmcoreinfo_append_str("NUMBER(KERNELPACMASK)=0x%llx\n",
 						system_supports_address_auth() ?
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 5df49366e9ab..7310a4f7f993 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init);
 /*
  * Single step API and exception handling.
  */
-static void set_regs_spsr_ss(struct pt_regs *regs)
+static void set_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(set_regs_spsr_ss);
+NOKPROBE_SYMBOL(set_user_regs_spsr_ss);
 
-static void clear_regs_spsr_ss(struct pt_regs *regs)
+static void clear_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(clear_regs_spsr_ss);
+NOKPROBE_SYMBOL(clear_user_regs_spsr_ss);
+
+#define set_regs_spsr_ss(r)	set_user_regs_spsr_ss(&(r)->user_regs)
+#define clear_regs_spsr_ss(r)	clear_user_regs_spsr_ss(&(r)->user_regs)
 
 static DEFINE_SPINLOCK(debug_hook_lock);
 static LIST_HEAD(user_step_hook);
@@ -391,17 +394,26 @@ void user_rewind_single_step(struct task_struct *task)
 	 * If single step is active for this thread, then set SPSR.SS
 	 * to 1 to avoid returning to the active-pending state.
 	 */
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		clear_regs_spsr_ss(task_pt_regs(task));
 }
 
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		set_user_regs_spsr_ss(regs);
+	else
+		clear_user_regs_spsr_ss(regs);
+}
+
 /* Kernel API */
 void kernel_enable_single_step(struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 3dbdf9752b11..d3be9dbf5490 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -57,7 +57,7 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
 	/*
 	 * The CPU masked interrupts, and we are leaving them masked during
 	 * do_debug_exception(). Update PMR as if we had called
-	 * local_mask_daif().
+	 * local_daif_mask().
 	 */
 	if (system_uses_irq_prio_masking())
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 5304d193c79d..2646178c8329 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -15,6 +15,7 @@
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/asm_pointer_auth.h>
+#include <asm/bug.h>
 #include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
@@ -126,8 +127,10 @@ alternative_else_nop_endif
 	add	\dst, \dst, #(\sym - .entry.tramp.text)
 	.endm
 
-	// This macro corrupts x0-x3. It is the caller's duty
-	// to save/restore them if required.
+	/*
+	 * This macro corrupts x0-x3. It is the caller's duty  to save/restore
+	 * them if required.
+	 */
 	.macro	apply_ssbd, state, tmp1, tmp2
 #ifdef CONFIG_ARM64_SSBD
 alternative_cb	arm64_enable_wa2_handling
@@ -167,13 +170,28 @@ alternative_cb_end
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
+	.if	\regsize == 32
+	/*
+	 * If we're returning from a 32-bit task on a system affected by
+	 * 1418040 then re-enable userspace access to the virtual counter.
+	 */
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if ARM64_WORKAROUND_1418040
+	mrs	x0, cntkctl_el1
+	orr	x0, x0, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x0
+alternative_else_nop_endif
+#endif
+	.endif
 	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20
 	msr	sp_el0, tsk
 
-	// Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
-	// when scheduling.
+	/*
+	 * Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
+	 * when scheduling.
+	 */
 	ldr	x19, [tsk, #TSK_TI_FLAGS]
 	disable_step_tsk x19, x20
 
@@ -209,28 +227,9 @@ alternative_cb_end
 	add	x29, sp, #S_STACKFRAME
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
-	/*
-	 * Set the TTBR0 PAN bit in SPSR. When the exception is taken from
-	 * EL0, there is no need to check the state of TTBR0_EL1 since
-	 * accesses are always enabled.
-	 * Note that the meaning of this bit differs from the ARMv8.1 PAN
-	 * feature as all TTBR0_EL1 accesses are disabled, not just those to
-	 * user mappings.
-	 */
-alternative_if ARM64_HAS_PAN
-	b	1f				// skip TTBR0 PAN
+alternative_if_not ARM64_HAS_PAN
+	bl	__swpan_entry_el\el
 alternative_else_nop_endif
-
-	.if	\el != 0
-	mrs	x21, ttbr0_el1
-	tst	x21, #TTBR_ASID_MASK		// Check for the reserved ASID
-	orr	x23, x23, #PSR_PAN_BIT		// Set the emulated PAN in the saved SPSR
-	b.eq	1f				// TTBR0 access already disabled
-	and	x23, x23, #~PSR_PAN_BIT		// Clear the emulated PAN in the saved SPSR
-	.endif
-
-	__uaccess_ttbr0_disable x21
-1:
 #endif
 
 	stp	x22, x23, [sp, #S_PC]
@@ -284,34 +283,9 @@ alternative_else_nop_endif
 	.endif
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
-	/*
-	 * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR
-	 * PAN bit checking.
-	 */
-alternative_if ARM64_HAS_PAN
-	b	2f				// skip TTBR0 PAN
+alternative_if_not ARM64_HAS_PAN
+	bl	__swpan_exit_el\el
 alternative_else_nop_endif
-
-	.if	\el != 0
-	tbnz	x22, #22, 1f			// Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
-	.endif
-
-	__uaccess_ttbr0_enable x0, x1
-
-	.if	\el == 0
-	/*
-	 * Enable errata workarounds only if returning to user. The only
-	 * workaround currently required for TTBR0_EL1 changes are for the
-	 * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
-	 * corruption).
-	 */
-	bl	post_ttbr_update_workaround
-	.endif
-1:
-	.if	\el != 0
-	and	x22, x22, #~PSR_PAN_BIT		// ARMv8.0 CPUs do not understand this bit
-	.endif
-2:
 #endif
 
 	.if	\el == 0
@@ -320,6 +294,14 @@ alternative_else_nop_endif
 	tst	x22, #PSR_MODE32_BIT		// native task?
 	b.eq	3f
 
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if ARM64_WORKAROUND_1418040
+	mrs	x0, cntkctl_el1
+	bic	x0, x0, #2			// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x0
+alternative_else_nop_endif
+#endif
+
 #ifdef CONFIG_ARM64_ERRATUM_845719
 alternative_if ARM64_WORKAROUND_845719
 #ifdef CONFIG_PID_IN_CONTEXTIDR
@@ -331,21 +313,6 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
-#ifdef CONFIG_ARM64_ERRATUM_1418040
-alternative_if_not ARM64_WORKAROUND_1418040
-	b	4f
-alternative_else_nop_endif
-	/*
-	 * if (x22.mode32 == cntkctl_el1.el0vcten)
-	 *     cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten
-	 */
-	mrs	x1, cntkctl_el1
-	eon	x0, x1, x22, lsr #3
-	tbz	x0, #1, 4f
-	eor	x1, x1, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
-	msr	cntkctl_el1, x1
-4:
-#endif
 	scs_save tsk, x0
 
 	/* No kernel C function calls after this as user keys are set. */
@@ -377,11 +344,11 @@ alternative_else_nop_endif
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	bne	5f
+	bne	4f
 	msr	far_el1, x30
 	tramp_alias	x30, tramp_exit_native
 	br	x30
-5:
+4:
 	tramp_alias	x30, tramp_exit_compat
 	br	x30
 #endif
@@ -391,6 +358,49 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 	sb
 	.endm
 
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	/*
+	 * Set the TTBR0 PAN bit in SPSR. When the exception is taken from
+	 * EL0, there is no need to check the state of TTBR0_EL1 since
+	 * accesses are always enabled.
+	 * Note that the meaning of this bit differs from the ARMv8.1 PAN
+	 * feature as all TTBR0_EL1 accesses are disabled, not just those to
+	 * user mappings.
+	 */
+SYM_CODE_START_LOCAL(__swpan_entry_el1)
+	mrs	x21, ttbr0_el1
+	tst	x21, #TTBR_ASID_MASK		// Check for the reserved ASID
+	orr	x23, x23, #PSR_PAN_BIT		// Set the emulated PAN in the saved SPSR
+	b.eq	1f				// TTBR0 access already disabled
+	and	x23, x23, #~PSR_PAN_BIT		// Clear the emulated PAN in the saved SPSR
+SYM_INNER_LABEL(__swpan_entry_el0, SYM_L_LOCAL)
+	__uaccess_ttbr0_disable x21
+1:	ret
+SYM_CODE_END(__swpan_entry_el1)
+
+	/*
+	 * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR
+	 * PAN bit checking.
+	 */
+SYM_CODE_START_LOCAL(__swpan_exit_el1)
+	tbnz	x22, #22, 1f			// Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
+	__uaccess_ttbr0_enable x0, x1
+1:	and	x22, x22, #~PSR_PAN_BIT		// ARMv8.0 CPUs do not understand this bit
+	ret
+SYM_CODE_END(__swpan_exit_el1)
+
+SYM_CODE_START_LOCAL(__swpan_exit_el0)
+	__uaccess_ttbr0_enable x0, x1
+	/*
+	 * Enable errata workarounds only if returning to user. The only
+	 * workaround currently required for TTBR0_EL1 changes are for the
+	 * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
+	 * corruption).
+	 */
+	b	post_ttbr_update_workaround
+SYM_CODE_END(__swpan_exit_el0)
+#endif
+
 	.macro	irq_stack_entry
 	mov	x19, sp			// preserve the original sp
 #ifdef CONFIG_SHADOW_CALL_STACK
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 35cb5e66c504..55c8f3ec6705 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -12,6 +12,7 @@
 #include <linux/bug.h>
 #include <linux/cache.h>
 #include <linux/compat.h>
+#include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
@@ -119,10 +120,20 @@ struct fpsimd_last_state_struct {
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
 
 /* Default VL for tasks that don't set it explicitly: */
-static int sve_default_vl = -1;
+static int __sve_default_vl = -1;
+
+static int get_sve_default_vl(void)
+{
+	return READ_ONCE(__sve_default_vl);
+}
 
 #ifdef CONFIG_ARM64_SVE
 
+static void set_sve_default_vl(int val)
+{
+	WRITE_ONCE(__sve_default_vl, val);
+}
+
 /* Maximum supported vector length across all CPUs (initially poisoned) */
 int __ro_after_init sve_max_vl = SVE_VL_MIN;
 int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN;
@@ -338,13 +349,13 @@ static unsigned int find_supported_vector_length(unsigned int vl)
 	return sve_vl_from_vq(__bit_to_vq(bit));
 }
 
-#ifdef CONFIG_SYSCTL
+#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL)
 
 static int sve_proc_do_default_vl(struct ctl_table *table, int write,
 				  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
-	int vl = sve_default_vl;
+	int vl = get_sve_default_vl();
 	struct ctl_table tmp_table = {
 		.data = &vl,
 		.maxlen = sizeof(vl),
@@ -361,7 +372,7 @@ static int sve_proc_do_default_vl(struct ctl_table *table, int write,
 	if (!sve_vl_valid(vl))
 		return -EINVAL;
 
-	sve_default_vl = find_supported_vector_length(vl);
+	set_sve_default_vl(find_supported_vector_length(vl));
 	return 0;
 }
 
@@ -383,9 +394,9 @@ static int __init sve_sysctl_init(void)
 	return 0;
 }
 
-#else /* ! CONFIG_SYSCTL */
+#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 static int __init sve_sysctl_init(void) { return 0; }
-#endif /* ! CONFIG_SYSCTL */
+#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
@@ -868,7 +879,7 @@ void __init sve_setup(void)
 	 * For the default VL, pick the maximum supported value <= 64.
 	 * VL == 64 is guaranteed not to grow the signal frame.
 	 */
-	sve_default_vl = find_supported_vector_length(64);
+	set_sve_default_vl(find_supported_vector_length(64));
 
 	bitmap_andnot(tmp_map, sve_vq_partial_map, sve_vq_map,
 		      SVE_VQ_MAX);
@@ -889,7 +900,7 @@ void __init sve_setup(void)
 	pr_info("SVE: maximum available vector length %u bytes per vector\n",
 		sve_max_vl);
 	pr_info("SVE: default vector length %u bytes per vector\n",
-		sve_default_vl);
+		get_sve_default_vl());
 
 	/* KVM decides whether to support mismatched systems. Just warn here: */
 	if (sve_max_virtualisable_vl < sve_max_vl)
@@ -1029,13 +1040,13 @@ void fpsimd_flush_thread(void)
 		 * vector length configured: no kernel task can become a user
 		 * task without an exec and hence a call to this function.
 		 * By the time the first call to this function is made, all
-		 * early hardware probing is complete, so sve_default_vl
+		 * early hardware probing is complete, so __sve_default_vl
 		 * should be valid.
 		 * If a bug causes this to go wrong, we make some noise and
 		 * try to fudge thread.sve_vl to a safe value here.
 		 */
 		vl = current->thread.sve_vl_onexec ?
-			current->thread.sve_vl_onexec : sve_default_vl;
+			current->thread.sve_vl_onexec : get_sve_default_vl();
 
 		if (WARN_ON(!sve_vl_valid(vl)))
 			vl = SVE_VL_MIN;
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 0b727edf4104..af234a1e08b7 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -730,6 +730,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
 		return 0;
 }
 
+static int watchpoint_report(struct perf_event *wp, unsigned long addr,
+			     struct pt_regs *regs)
+{
+	int step = is_default_overflow_handler(wp);
+	struct arch_hw_breakpoint *info = counter_arch_bp(wp);
+
+	info->trigger = addr;
+
+	/*
+	 * If we triggered a user watchpoint from a uaccess routine, then
+	 * handle the stepping ourselves since userspace really can't help
+	 * us with this.
+	 */
+	if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0)
+		step = 1;
+	else
+		perf_bp_event(wp, regs);
+
+	return step;
+}
+
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -739,7 +760,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	u64 val;
 	struct perf_event *wp, **slots;
 	struct debug_info *debug_info;
-	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = this_cpu_ptr(wp_on_reg);
@@ -777,25 +797,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		if (dist != 0)
 			continue;
 
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
-
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
+		step = watchpoint_report(wp, addr, regs);
 	}
-	if (min_dist > 0 && min_dist != -1) {
-		/* No exact match found. */
-		wp = slots[closest_match];
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
 
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
-	}
+	/* No exact match found? */
+	if (min_dist > 0 && min_dist != -1)
+		step = watchpoint_report(slots[closest_match], addr, regs);
+
 	rcu_read_unlock();
 
 	if (!step)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 684d871ae38d..a107375005bc 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -135,7 +135,7 @@ int __kprobes aarch64_insn_read(void *addr, u32 *insnp)
 	int ret;
 	__le32 val;
 
-	ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE);
+	ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE);
 	if (!ret)
 		*insnp = le32_to_cpu(val);
 
@@ -151,7 +151,7 @@ static int __kprobes __aarch64_insn_write(void *addr, __le32 insn)
 	raw_spin_lock_irqsave(&patch_lock, flags);
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
-	ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE);
+	ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE);
 
 	patch_unmap(FIX_TEXT_POKE0);
 	raw_spin_unlock_irqrestore(&patch_lock, flags);
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 43119922341f..1a157ca33262 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
-	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 522e6f517ec0..361a1143e09e 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -219,8 +219,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 					MEMBLOCK_NONE, &start, &end, NULL)
 		nr_ranges++;
 
-	cmem = kmalloc(sizeof(struct crash_mem) +
-			sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL);
+	cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL);
 	if (!cmem)
 		return -ENOMEM;
 
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index 65b08a74aec6..0ce3a28e3347 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -253,6 +253,40 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num,
 	return ret;
 }
 
+static bool branch_rela_needs_plt(Elf64_Sym *syms, Elf64_Rela *rela,
+				  Elf64_Word dstidx)
+{
+
+	Elf64_Sym *s = syms + ELF64_R_SYM(rela->r_info);
+
+	if (s->st_shndx == dstidx)
+		return false;
+
+	return ELF64_R_TYPE(rela->r_info) == R_AARCH64_JUMP26 ||
+	       ELF64_R_TYPE(rela->r_info) == R_AARCH64_CALL26;
+}
+
+/* Group branch PLT relas at the front end of the array. */
+static int partition_branch_plt_relas(Elf64_Sym *syms, Elf64_Rela *rela,
+				      int numrels, Elf64_Word dstidx)
+{
+	int i = 0, j = numrels - 1;
+
+	if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		return 0;
+
+	while (i < j) {
+		if (branch_rela_needs_plt(syms, &rela[i], dstidx))
+			i++;
+		else if (branch_rela_needs_plt(syms, &rela[j], dstidx))
+			swap(rela[i], rela[j]);
+		else
+			j--;
+	}
+
+	return i;
+}
+
 int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			      char *secstrings, struct module *mod)
 {
@@ -290,7 +324,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 
 	for (i = 0; i < ehdr->e_shnum; i++) {
 		Elf64_Rela *rels = (void *)ehdr + sechdrs[i].sh_offset;
-		int numrels = sechdrs[i].sh_size / sizeof(Elf64_Rela);
+		int nents, numrels = sechdrs[i].sh_size / sizeof(Elf64_Rela);
 		Elf64_Shdr *dstsec = sechdrs + sechdrs[i].sh_info;
 
 		if (sechdrs[i].sh_type != SHT_RELA)
@@ -300,8 +334,14 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		if (!(dstsec->sh_flags & SHF_EXECINSTR))
 			continue;
 
-		/* sort by type, symbol index and addend */
-		sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL);
+		/*
+		 * sort branch relocations requiring a PLT by type, symbol index
+		 * and addend
+		 */
+		nents = partition_branch_plt_relas(syms, rels, numrels,
+						   sechdrs[i].sh_info);
+		if (nents)
+			sort(rels, nents, sizeof(Elf64_Rela), cmp_rela, NULL);
 
 		if (!str_has_prefix(secstrings + dstsec->sh_name, ".init"))
 			core_plts += count_plts(syms, rels, numrels,
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 4d7879484cec..462f9a9cc44b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -13,12 +13,15 @@
 #include <asm/sysreg.h>
 #include <asm/virt.h>
 
+#include <clocksource/arm_arch_timer.h>
+
 #include <linux/acpi.h>
 #include <linux/clocksource.h>
 #include <linux/kvm_host.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
+#include <linux/sched_clock.h>
 #include <linux/smp.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
@@ -155,7 +158,7 @@ armv8pmu_events_sysfs_show(struct device *dev,
 
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
 
-	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
 }
 
 #define ARMV8_EVENT_ATTR(name, config)						\
@@ -222,10 +225,29 @@ static struct attribute *armv8_pmuv3_event_attrs[] = {
 	ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD),
 	ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD),
 	ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD),
+	ARMV8_EVENT_ATTR(l1d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(op_retired, ARMV8_PMUV3_PERFCTR_OP_RETIRED),
+	ARMV8_EVENT_ATTR(op_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC),
+	ARMV8_EVENT_ATTR(stall, ARMV8_PMUV3_PERFCTR_STALL),
+	ARMV8_EVENT_ATTR(stall_slot_backend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND),
+	ARMV8_EVENT_ATTR(stall_slot_frontend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND),
+	ARMV8_EVENT_ATTR(stall_slot, ARMV8_PMUV3_PERFCTR_STALL_SLOT),
 	ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP),
 	ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED),
 	ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE),
 	ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION),
+	ARMV8_EVENT_ATTR(cnt_cycles, ARMV8_AMU_PERFCTR_CNT_CYCLES),
+	ARMV8_EVENT_ATTR(stall_backend_mem, ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM),
+	ARMV8_EVENT_ATTR(l1i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS),
+	ARMV8_EVENT_ATTR(l2d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(l2i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS),
+	ARMV8_EVENT_ATTR(l3d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(ldst_align_lat, ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(ld_align_lat, ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(st_align_lat, ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(mem_access_checked, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED),
+	ARMV8_EVENT_ATTR(mem_access_checked_rd, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD),
+	ARMV8_EVENT_ATTR(mem_access_checked_wr, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR),
 	NULL,
 };
 
@@ -244,10 +266,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,
 	    test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
 		return attr->mode;
 
-	pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
-	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
-	    test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap))
-		return attr->mode;
+	if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) {
+		u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+
+		if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+		    test_bit(id, cpu_pmu->pmceid_ext_bitmap))
+			return attr->mode;
+	}
 
 	return 0;
 }
@@ -1165,28 +1190,54 @@ device_initcall(armv8_pmu_driver_init)
 void arch_perf_update_userpage(struct perf_event *event,
 			       struct perf_event_mmap_page *userpg, u64 now)
 {
-	u32 freq;
-	u32 shift;
+	struct clock_read_data *rd;
+	unsigned int seq;
+	u64 ns;
 
-	/*
-	 * Internal timekeeping for enabled/running/stopped times
-	 * is always computed with the sched_clock.
-	 */
-	freq = arch_timer_get_rate();
-	userpg->cap_user_time = 1;
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_time_short = 0;
+
+	do {
+		rd = sched_clock_read_begin(&seq);
+
+		if (rd->read_sched_clock != arch_timer_read_counter)
+			return;
+
+		userpg->time_mult = rd->mult;
+		userpg->time_shift = rd->shift;
+		userpg->time_zero = rd->epoch_ns;
+		userpg->time_cycles = rd->epoch_cyc;
+		userpg->time_mask = rd->sched_clock_mask;
+
+		/*
+		 * Subtract the cycle base, such that software that
+		 * doesn't know about cap_user_time_short still 'works'
+		 * assuming no wraps.
+		 */
+		ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
+		userpg->time_zero -= ns;
+
+	} while (sched_clock_read_retry(seq));
+
+	userpg->time_offset = userpg->time_zero - now;
 
-	clocks_calc_mult_shift(&userpg->time_mult, &shift, freq,
-			NSEC_PER_SEC, 0);
 	/*
 	 * time_shift is not expected to be greater than 31 due to
 	 * the original published conversion algorithm shifting a
 	 * 32-bit value (now specifies a 64-bit value) - refer
 	 * perf_event_mmap_page documentation in perf_event.h.
 	 */
-	if (shift == 32) {
-		shift = 31;
+	if (userpg->time_shift == 32) {
+		userpg->time_shift = 31;
 		userpg->time_mult >>= 1;
 	}
-	userpg->time_shift = (u16)shift;
-	userpg->time_offset = -now;
+
+	/*
+	 * Internal timekeeping for enabled/running/stopped times
+	 * is always computed with the sched_clock.
+	 */
+	userpg->cap_user_time = 1;
+	userpg->cap_user_time_zero = 1;
+	userpg->cap_user_time_short = 1;
 }
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 0bbac612146e..666b225aeb3a 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 		return 0;
 
 	/*
-	 * Compat (i.e. 32 bit) mode:
-	 * - PC has been set in the pt_regs struct in kernel_entry,
-	 * - Handle SP and LR here.
+	 * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but
+	 * we're stuck with it for ABI compatability reasons.
+	 *
+	 * For a 32-bit consumer inspecting a 32-bit task, then it will look at
+	 * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h).
+	 * These correspond directly to a prefix of the registers saved in our
+	 * 'struct pt_regs', with the exception of the PC, so we copy that down
+	 * (x15 corresponds to SP_hyp in the architecture).
+	 *
+	 * So far, so good.
+	 *
+	 * The oddity arises when a 64-bit consumer looks at a 32-bit task and
+	 * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return
+	 * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and
+	 * PC registers would normally live. The initial idea was to allow a
+	 * 64-bit unwinder to unwind a 32-bit task and, although it's not clear
+	 * how well that works in practice, somebody might be relying on it.
+	 *
+	 * At the time we make a sample, we don't know whether the consumer is
+	 * 32-bit or 64-bit, so we have to cater for both possibilities.
 	 */
 	if (compat_user_mode(regs)) {
 		if ((u32)idx == PERF_REG_ARM64_SP)
 			return regs->compat_sp;
 		if ((u32)idx == PERF_REG_ARM64_LR)
 			return regs->compat_lr;
+		if (idx == 15)
+			return regs->pc;
 	}
 
 	if ((u32)idx == PERF_REG_ARM64_SP)
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d1c95dcf1d78..5290f17a4d80 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -120,15 +120,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 
 void *alloc_insn_page(void)
 {
-	void *page;
-
-	page = vmalloc_exec(PAGE_SIZE);
-	if (page) {
-		set_memory_ro((unsigned long)page, 1);
-		set_vm_flush_reset_perms(page);
-	}
-
-	return page;
+	return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 /* arm kprobe: install breakpoint in text */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 68b7f34a08f5..1e02e98e68dd 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1811,19 +1811,42 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	unsigned long saved_reg;
 
 	/*
-	 * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
-	 * used to denote syscall entry/exit:
+	 * We have some ABI weirdness here in the way that we handle syscall
+	 * exit stops because we indicate whether or not the stop has been
+	 * signalled from syscall entry or syscall exit by clobbering a general
+	 * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee
+	 * and restoring its old value after the stop. This means that:
+	 *
+	 * - Any writes by the tracer to this register during the stop are
+	 *   ignored/discarded.
+	 *
+	 * - The actual value of the register is not available during the stop,
+	 *   so the tracer cannot save it and restore it later.
+	 *
+	 * - Syscall stops behave differently to seccomp and pseudo-step traps
+	 *   (the latter do not nobble any registers).
 	 */
 	regno = (is_compat_task() ? 12 : 7);
 	saved_reg = regs->regs[regno];
 	regs->regs[regno] = dir;
 
-	if (dir == PTRACE_SYSCALL_EXIT)
+	if (dir == PTRACE_SYSCALL_ENTER) {
+		if (tracehook_report_syscall_entry(regs))
+			forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else if (!test_thread_flag(TIF_SINGLESTEP)) {
 		tracehook_report_syscall_exit(regs, 0);
-	else if (tracehook_report_syscall_entry(regs))
-		forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else {
+		regs->regs[regno] = saved_reg;
 
-	regs->regs[regno] = saved_reg;
+		/*
+		 * Signal a pseudo-step exception since we are stepping but
+		 * tracer modifications to the registers may have rewound the
+		 * state machine.
+		 */
+		tracehook_report_syscall_exit(regs, 1);
+	}
 }
 
 int syscall_trace_enter(struct pt_regs *regs)
@@ -1833,12 +1856,12 @@ int syscall_trace_enter(struct pt_regs *regs)
 	if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) {
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
 		if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU))
-			return -1;
+			return NO_SYSCALL;
 	}
 
 	/* Do the secure computing after ptrace; failures should be fast. */
 	if (secure_computing() == -1)
-		return -1;
+		return NO_SYSCALL;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, regs->syscallno);
@@ -1851,12 +1874,14 @@ int syscall_trace_enter(struct pt_regs *regs)
 
 void syscall_trace_exit(struct pt_regs *regs)
 {
+	unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
 	audit_syscall_exit(regs);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (flags & _TIF_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, regs_return_value(regs));
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 
 	rseq_syscall(regs);
@@ -1934,8 +1959,8 @@ static int valid_native_regs(struct user_pt_regs *regs)
  */
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
-		regs->pstate &= ~DBG_SPSR_SS;
+	/* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */
+	user_regs_reset_single_step(regs, task);
 
 	if (is_compat_thread(task_thread_info(task)))
 		return valid_compat_regs(regs);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 93b3844cf442..c793276ec7ad 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -400,11 +400,7 @@ static int __init topology_init(void)
 }
 subsys_initcall(topology_init);
 
-/*
- * Dump out kernel offset information on panic.
- */
-static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
-			      void *p)
+static void dump_kernel_offset(void)
 {
 	const unsigned long offset = kaslr_offset();
 
@@ -415,17 +411,25 @@ static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
 	} else {
 		pr_emerg("Kernel Offset: disabled\n");
 	}
+}
+
+static int arm64_panic_block_dump(struct notifier_block *self,
+				  unsigned long v, void *p)
+{
+	dump_kernel_offset();
+	dump_cpu_features();
+	dump_mem_limit();
 	return 0;
 }
 
-static struct notifier_block kernel_offset_notifier = {
-	.notifier_call = dump_kernel_offset
+static struct notifier_block arm64_panic_block = {
+	.notifier_call = arm64_panic_block_dump
 };
 
-static int __init register_kernel_offset_dumper(void)
+static int __init register_arm64_panic_block(void)
 {
 	atomic_notifier_chain_register(&panic_notifier_list,
-				       &kernel_offset_notifier);
+				       &arm64_panic_block);
 	return 0;
 }
-__initcall(register_kernel_offset_dumper);
+device_initcall(register_arm64_panic_block);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 801d56cdf701..3b4f31f35e45 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -800,7 +800,6 @@ static void setup_restart_syscall(struct pt_regs *regs)
  */
 static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
 	sigset_t *oldset = sigmask_to_save();
 	int usig = ksig->sig;
 	int ret;
@@ -824,14 +823,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	 */
 	ret |= !valid_user_regs(&regs->user_regs, current);
 
-	/*
-	 * Fast forward the stepping logic so we step into the signal
-	 * handler.
-	 */
-	if (!ret)
-		user_fastforward_single_step(tsk);
-
-	signal_setup_done(ret, ksig, 0);
+	/* Step into the signal handler if we are stepping */
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
 
 /*
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 82feca6f7052..2f507f565c48 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -342,38 +342,13 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
 	} else {
 		/* Set up sigreturn pointer */
-#ifdef CONFIG_COMPAT_VDSO
-		void *vdso_base = current->mm->context.vdso;
-		void *vdso_trampoline;
-
-		if (ka->sa.sa_flags & SA_SIGINFO) {
-			if (thumb) {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_rt_sigreturn_thumb);
-			} else {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_rt_sigreturn_arm);
-			}
-		} else {
-			if (thumb) {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_sigreturn_thumb);
-			} else {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_sigreturn_arm);
-			}
-		}
-
-		retcode = ptr_to_compat(vdso_trampoline) + thumb;
-#else
 		unsigned int idx = thumb << 1;
 
 		if (ka->sa.sa_flags & SA_SIGINFO)
 			idx += 3;
 
-		retcode = (unsigned long)current->mm->context.vdso +
+		retcode = (unsigned long)current->mm->context.sigpage +
 			  (idx << 2) + thumb;
-#endif
 	}
 
 	regs->regs[0]	= usig;
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 139679c745bf..2dd8e3b8b94b 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -199,12 +199,12 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 
 	put_task_stack(tsk);
 }
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	__save_stack_trace(tsk, trace, 1);
 }
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 void save_stack_trace(struct stack_trace *trace)
 {
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 5f5b868292f5..5f0c04863d2c 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = do_ni_syscall(regs, scno);
 	}
 
+	if (is_compat_task())
+		ret = lower_32_bits(ret);
+
 	regs->regs[0] = ret;
 }
 
@@ -121,7 +124,21 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	user_exit();
 
 	if (has_syscall_work(flags)) {
-		/* set default errno for user-issued syscall(-1) */
+		/*
+		 * The de-facto standard way to skip a system call using ptrace
+		 * is to set the system call to -1 (NO_SYSCALL) and set x0 to a
+		 * suitable error code for consumption by userspace. However,
+		 * this cannot be distinguished from a user-issued syscall(-1)
+		 * and so we must set x0 to -ENOSYS here in case the tracer doesn't
+		 * issue the skip and we fall into trace_exit with x0 preserved.
+		 *
+		 * This is slightly odd because it also means that if a tracer
+		 * sets the system call number to -1 but does not initialise x0,
+		 * then x0 will be preserved for all system calls apart from a
+		 * user-issued syscall(-1). However, requesting a skip and not
+		 * setting the return value is unlikely to do anything sensible
+		 * anyway.
+		 */
 		if (scno == NO_SYSCALL)
 			regs->regs[0] = -ENOSYS;
 		scno = syscall_trace_enter(regs);
@@ -139,7 +156,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags)) {
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
 			/*
 			 * We're off to userspace, where interrupts are
 			 * always enabled after we restore the flags from
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 50cc30acf106..13ebd5ca2070 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -376,7 +376,7 @@ static int call_undef_hook(struct pt_regs *regs)
 
 	if (!user_mode(regs)) {
 		__le32 instr_le;
-		if (probe_kernel_address((__force __le32 *)pc, instr_le))
+		if (get_kernel_nofault(instr_le, (__force __le32 *)pc))
 			goto exit;
 		instr = le32_to_cpu(instr_le);
 	} else if (compat_thumb_mode(regs)) {
@@ -813,6 +813,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 		handler[reason], smp_processor_id(), esr,
 		esr_get_class_string(esr));
 
+	__show_regs(regs);
 	local_daif_mask();
 	panic("bad mode");
 }
@@ -854,7 +855,7 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs)
 	pr_emerg("Task stack:     [0x%016lx..0x%016lx]\n",
 		 tsk_stk, tsk_stk + THREAD_SIZE);
 	pr_emerg("IRQ stack:      [0x%016lx..0x%016lx]\n",
-		 irq_stk, irq_stk + THREAD_SIZE);
+		 irq_stk, irq_stk + IRQ_STACK_SIZE);
 	pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n",
 		 ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE);
 
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 4e016574bd91..d4202a32abc9 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -18,6 +18,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
+#include <linux/time_namespace.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/vmalloc.h>
 #include <vdso/datapage.h>
@@ -40,6 +41,12 @@ enum vdso_abi {
 #endif /* CONFIG_COMPAT_VDSO */
 };
 
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
 struct vdso_abi_info {
 	const char *name;
 	const char *vdso_code_start;
@@ -107,25 +114,122 @@ static int __vdso_init(enum vdso_abi abi)
 			vdso_info[abi].vdso_code_start) >>
 			PAGE_SHIFT;
 
-	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages + 1,
+	vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages,
 				sizeof(struct page *),
 				GFP_KERNEL);
 	if (vdso_pagelist == NULL)
 		return -ENOMEM;
 
-	/* Grab the vDSO data page. */
-	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
-
-
 	/* Grab the vDSO code pages. */
 	pfn = sym_to_pfn(vdso_info[abi].vdso_code_start);
 
 	for (i = 0; i < vdso_info[abi].vdso_pages; i++)
-		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+		vdso_pagelist[i] = pfn_to_page(pfn + i);
+
+	vdso_info[abi].cm->pages = vdso_pagelist;
+
+	return 0;
+}
+
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_data *)(vvar_page);
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+
+	mmap_read_lock(mm);
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
+			zap_page_range(vma, vma->vm_start, size);
+#ifdef CONFIG_COMPAT_VDSO
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
+			zap_page_range(vma, vma->vm_start, size);
+#endif
+	}
+
+	mmap_read_unlock(mm);
+	return 0;
+}
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops.
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+#else
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#endif
 
-	vdso_info[abi].dm->pages = &vdso_pagelist[0];
-	vdso_info[abi].cm->pages = &vdso_pagelist[1];
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long pfn;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		if (timens_page)
+			pfn = page_to_pfn(timens_page);
+		else
+			pfn = sym_to_pfn(vdso_data);
+		break;
+#ifdef CONFIG_TIME_NS
+	case VVAR_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = sym_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+static int vvar_mremap(const struct vm_special_mapping *sm,
+		       struct vm_area_struct *new_vma)
+{
+	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
+
+	if (new_size != VVAR_NR_PAGES * PAGE_SIZE)
+		return -EINVAL;
 
 	return 0;
 }
@@ -139,9 +243,11 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	unsigned long gp_flags = 0;
 	void *ret;
 
+	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+
 	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+	vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
 
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
@@ -149,8 +255,8 @@ static int __setup_additional_pages(enum vdso_abi abi,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
-				       VM_READ|VM_MAYREAD,
+	ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
+				       VM_READ|VM_MAYREAD|VM_PFNMAP,
 				       vdso_info[abi].dm);
 	if (IS_ERR(ret))
 		goto up_fail;
@@ -158,7 +264,7 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
 		gp_flags = VM_ARM64_BTI;
 
-	vdso_base += PAGE_SIZE;
+	vdso_base += VVAR_NR_PAGES * PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
 				       VM_READ|VM_EXEC|gp_flags|
@@ -191,15 +297,12 @@ enum aarch32_map {
 #ifdef CONFIG_COMPAT_VDSO
 	AA32_MAP_VVAR,
 	AA32_MAP_VDSO,
-#else
-	AA32_MAP_SIGPAGE
 #endif
+	AA32_MAP_SIGPAGE
 };
 
 static struct page *aarch32_vectors_page __ro_after_init;
-#ifndef CONFIG_COMPAT_VDSO
 static struct page *aarch32_sig_page __ro_after_init;
-#endif
 
 static struct vm_special_mapping aarch32_vdso_maps[] = {
 	[AA32_MAP_VECTORS] = {
@@ -209,17 +312,18 @@ static struct vm_special_mapping aarch32_vdso_maps[] = {
 #ifdef CONFIG_COMPAT_VDSO
 	[AA32_MAP_VVAR] = {
 		.name = "[vvar]",
+		.fault = vvar_fault,
+		.mremap = vvar_mremap,
 	},
 	[AA32_MAP_VDSO] = {
 		.name = "[vdso]",
 		.mremap = aarch32_vdso_mremap,
 	},
-#else
+#endif /* CONFIG_COMPAT_VDSO */
 	[AA32_MAP_SIGPAGE] = {
 		.name	= "[sigpage]", /* ABI */
 		.pages	= &aarch32_sig_page,
 	},
-#endif /* CONFIG_COMPAT_VDSO */
 };
 
 static int aarch32_alloc_kuser_vdso_page(void)
@@ -242,27 +346,11 @@ static int aarch32_alloc_kuser_vdso_page(void)
 	return 0;
 }
 
-#ifdef CONFIG_COMPAT_VDSO
-static int __aarch32_alloc_vdso_pages(void)
-{
-	int ret;
-
-	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
-	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
-
-	ret = __vdso_init(VDSO_ABI_AA32);
-	if (ret)
-		return ret;
-
-	return aarch32_alloc_kuser_vdso_page();
-}
-#else
-static int __aarch32_alloc_vdso_pages(void)
+static int aarch32_alloc_sigpage(void)
 {
 	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
 	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
 	unsigned long sigpage;
-	int ret;
 
 	sigpage = get_zeroed_page(GFP_ATOMIC);
 	if (!sigpage)
@@ -271,18 +359,34 @@ static int __aarch32_alloc_vdso_pages(void)
 	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
 	aarch32_sig_page = virt_to_page(sigpage);
 	flush_dcache_page(aarch32_sig_page);
+	return 0;
+}
 
-	ret = aarch32_alloc_kuser_vdso_page();
-	if (ret)
-		free_page(sigpage);
+#ifdef CONFIG_COMPAT_VDSO
+static int __aarch32_alloc_vdso_pages(void)
+{
+	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
+	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
 
-	return ret;
+	return __vdso_init(VDSO_ABI_AA32);
 }
 #endif /* CONFIG_COMPAT_VDSO */
 
 static int __init aarch32_alloc_vdso_pages(void)
 {
-	return __aarch32_alloc_vdso_pages();
+	int ret;
+
+#ifdef CONFIG_COMPAT_VDSO
+	ret = __aarch32_alloc_vdso_pages();
+	if (ret)
+		return ret;
+#endif
+
+	ret = aarch32_alloc_sigpage();
+	if (ret)
+		return ret;
+
+	return aarch32_alloc_kuser_vdso_page();
 }
 arch_initcall(aarch32_alloc_vdso_pages);
 
@@ -305,7 +409,6 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 	return PTR_ERR_OR_ZERO(ret);
 }
 
-#ifndef CONFIG_COMPAT_VDSO
 static int aarch32_sigreturn_setup(struct mm_struct *mm)
 {
 	unsigned long addr;
@@ -328,12 +431,11 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm)
 	if (IS_ERR(ret))
 		goto out;
 
-	mm->context.vdso = (void *)addr;
+	mm->context.sigpage = (void *)addr;
 
 out:
 	return PTR_ERR_OR_ZERO(ret);
 }
-#endif /* !CONFIG_COMPAT_VDSO */
 
 int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
@@ -352,10 +454,11 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 				       mm,
 				       bprm,
 				       uses_interp);
-#else
-	ret = aarch32_sigreturn_setup(mm);
+	if (ret)
+		goto out;
 #endif /* CONFIG_COMPAT_VDSO */
 
+	ret = aarch32_sigreturn_setup(mm);
 out:
 	mmap_write_unlock(mm);
 	return ret;
@@ -376,6 +479,8 @@ enum aarch64_map {
 static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
 	[AA64_MAP_VVAR] = {
 		.name	= "[vvar]",
+		.fault = vvar_fault,
+		.mremap = vvar_mremap,
 	},
 	[AA64_MAP_VDSO] = {
 		.name	= "[vdso]",
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 556d424c6f52..45d5cfe46429 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -23,13 +23,14 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti
 # potential future proofing if we end up with internal calls to the exported
 # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
 # preparation in build-time C")).
-ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
-		-Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T
+ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv	\
+	     -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id -n	\
+	     $(btildflags-y) -T
 
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING
 
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS)
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS)
 KBUILD_CFLAGS			+= $(DISABLE_LTO)
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S
index 620a3ef837b7..0e18729abc3b 100644
--- a/arch/arm64/kernel/vdso/sigreturn.S
+++ b/arch/arm64/kernel/vdso/sigreturn.S
@@ -18,29 +18,40 @@
 
 	.text
 
+/*
+ * NOTE!!!  You may notice that all of the .cfi directives in this file have
+ * been commented out. This is because they have been shown to trigger segfaults
+ * in libgcc when unwinding out of a SIGCANCEL handler to invoke pthread
+ * cleanup handlers during the thread cancellation dance. By omitting the
+ * directives, we trigger an arm64-specific fallback path in the unwinder which
+ * recognises the signal frame and restores many of the registers directly from
+ * the sigcontext. Re-enabling the cfi directives here therefore needs to be
+ * much more comprehensive to reduce the risk of further regressions.
+ */
+
 /* Ensure that the mysterious NOP can be associated with a function. */
-	.cfi_startproc
+//	.cfi_startproc
 
 /*
- * .cfi_signal_frame causes the corresponding Frame Description Entry in the
- * .eh_frame section to be annotated as a signal frame. This allows DWARF
- * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits
- * unwinding out of the signal trampoline without the need for the mysterious
- * NOP.
+ * .cfi_signal_frame causes the corresponding Frame Description Entry (FDE) in
+ * the .eh_frame section to be annotated as a signal frame. This allows DWARF
+ * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo() and identify
+ * the next frame using the unmodified return address instead of subtracting 1,
+ * which may yield the wrong FDE.
  */
-	.cfi_signal_frame
+//	.cfi_signal_frame
 
 /*
  * Tell the unwinder where to locate the frame record linking back to the
- * interrupted context. We don't provide unwind info for registers other
- * than the frame pointer and the link register here; in practice, this
- * is sufficient for unwinding in C/C++ based runtimes and the values in
- * the sigcontext may have been modified by this point anyway. Debuggers
+ * interrupted context. We don't provide unwind info for registers other than
+ * the frame pointer and the link register here; in practice, this is likely to
+ * be insufficient for unwinding in C/C++ based runtimes, especially without a
+ * means to restore the stack pointer. Thankfully, unwinders and debuggers
  * already have baked-in strategies for attempting to unwind out of signals.
  */
-	.cfi_def_cfa    x29, 0
-	.cfi_offset     x29, 0 * 8
-	.cfi_offset     x30, 1 * 8
+//	.cfi_def_cfa    x29, 0
+//	.cfi_offset     x29, 0 * 8
+//	.cfi_offset     x30, 1 * 8
 
 /*
  * This mysterious NOP is required for some unwinders (e.g. libc++) that
@@ -51,16 +62,19 @@
 	nop	// Mysterious NOP
 
 /*
- * GDB relies on being able to identify the sigreturn instruction sequence to
- * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START()
- * here, as it will emit a BTI C instruction and break the unwinder. Thankfully,
- * this function is only ever called from a RET and so omitting the landing pad
- * is perfectly fine.
+ * GDB, libgcc and libunwind rely on being able to identify the sigreturn
+ * instruction sequence to unwind from signal handlers. We cannot, therefore,
+ * use SYM_FUNC_START() here, as it will emit a BTI C instruction and break the
+ * unwinder. Thankfully, this function is only ever called from a RET and so
+ * omitting the landing pad is perfectly fine.
  */
 SYM_CODE_START(__kernel_rt_sigreturn)
+//	PLEASE DO NOT MODIFY
 	mov	x8, #__NR_rt_sigreturn
+//	PLEASE DO NOT MODIFY
 	svc	#0
-	.cfi_endproc
+//	PLEASE DO NOT MODIFY
+//	.cfi_endproc
 SYM_CODE_END(__kernel_rt_sigreturn)
 
 emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index 7ad2d3a0cd48..d808ad31e01f 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -17,7 +17,10 @@ OUTPUT_ARCH(aarch64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - PAGE_SIZE);
+	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
+#ifdef CONFIG_TIME_NS
+	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
+#endif
 	. = VDSO_LBASE + SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 7ea1e827e505..5139a5f19256 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -14,7 +14,7 @@ COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit))
 COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..)
 
 CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
-CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)
+CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE_COMPAT))
 CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments
 ifneq ($(COMPAT_GCC_TOOLCHAIN),)
 CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN)
@@ -140,7 +140,6 @@ hostprogs := $(munge)
 
 c-obj-vdso := note.o
 c-obj-vdso-gettimeofday := vgettimeofday.o
-asm-obj-vdso := sigreturn.o
 
 ifneq ($(c-gettimeofday-y),)
 VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y)
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
deleted file mode 100644
index b0091064c3d6..000000000000
--- a/arch/arm64/kernel/vdso32/sigreturn.S
+++ /dev/null
@@ -1,58 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * This file provides both A32 and T32 versions, in accordance with the
- * arm sigreturn code.
- *
- * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to
- * understand some of the craziness in here.
- *
- * Copyright (C) 2018 ARM Limited
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-
-	.text
-
-	.arm
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_sigreturn_arm)
-	mov r7, #__NR_compat_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_sigreturn_arm)
-
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_rt_sigreturn_arm)
-	mov r7, #__NR_compat_rt_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_rt_sigreturn_arm)
-
-	.thumb
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_sigreturn_thumb)
-	mov r7, #__NR_compat_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_sigreturn_thumb)
-
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_rt_sigreturn_thumb)
-	mov r7, #__NR_compat_rt_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
index a3944927eaeb..3348ce5ea306 100644
--- a/arch/arm64/kernel/vdso32/vdso.lds.S
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -17,7 +17,10 @@ OUTPUT_ARCH(arm)
 
 SECTIONS
 {
-	PROVIDE_HIDDEN(_vdso_data = . - PAGE_SIZE);
+	PROVIDE_HIDDEN(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
+#ifdef CONFIG_TIME_NS
+	PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE);
+#endif
 	. = VDSO_LBASE + SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
@@ -64,19 +67,7 @@ VERSION
 		__vdso_clock_gettime;
 		__vdso_gettimeofday;
 		__vdso_clock_getres;
-		__kernel_sigreturn_arm;
-		__kernel_sigreturn_thumb;
-		__kernel_rt_sigreturn_arm;
-		__kernel_rt_sigreturn_thumb;
 		__vdso_clock_gettime64;
 	local: *;
 	};
 }
-
-/*
- * Make the sigreturn code visible to the kernel.
- */
-VDSO_compat_sigreturn_arm	= __kernel_sigreturn_arm;
-VDSO_compat_sigreturn_thumb	= __kernel_sigreturn_thumb;
-VDSO_compat_rt_sigreturn_arm	= __kernel_rt_sigreturn_arm;
-VDSO_compat_rt_sigreturn_thumb	= __kernel_rt_sigreturn_thumb;
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 6827da7f3aa5..ec8e894684a7 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -10,7 +10,6 @@
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
-#include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/page.h>
 
@@ -165,9 +164,6 @@ SECTIONS
 		*(.altinstructions)
 		__alt_instructions_end = .;
 	}
-	.altinstr_replacement : {
-		*(.altinstr_replacement)
-	}
 
 	. = ALIGN(SEGMENT_ALIGN);
 	__inittext_end = .;
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 6e6ed5581eed..86971fe26f3d 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -6,6 +6,7 @@
 
 #include <linux/linkage.h>
 
+#include <asm/alternative.h>
 #include <asm/assembler.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
@@ -136,11 +137,15 @@ SYM_CODE_START(__kvm_handle_stub_hvc)
 
 1:	cmp	x0, #HVC_RESET_VECTORS
 	b.ne	1f
-reset:
+
 	/*
-	 * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
-	 * case we coming via HVC_SOFT_RESTART.
+	 * Set the HVC_RESET_VECTORS return code before entering the common
+	 * path so that we do not clobber x0-x2 in case we are coming via
+	 * HVC_SOFT_RESTART.
 	 */
+	mov	x0, xzr
+reset:
+	/* Reset kvm back to the hyp stub. */
 	mrs	x5, sctlr_el2
 	mov_q	x6, SCTLR_ELx_FLAGS
 	bic	x5, x5, x6		// Clear SCTL_M and etc
@@ -151,7 +156,6 @@ reset:
 	/* Install stub vectors */
 	adr_l	x5, __hyp_stub_vectors
 	msr	vbar_el2, x5
-	mov	x0, xzr
 	eret
 
 1:	/* Bad stub call */
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c0035cab6b6..31058e6e7c2a 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1326,7 +1326,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
 	return true;
 }
 
-static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz)
 {
 	pud_t *pudp;
 	pmd_t *pmdp;
@@ -1338,11 +1338,11 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
 		return false;
 
 	if (pudp)
-		return kvm_s2pud_exec(pudp);
+		return sz <= PUD_SIZE && kvm_s2pud_exec(pudp);
 	else if (pmdp)
-		return kvm_s2pmd_exec(pmdp);
+		return sz <= PMD_SIZE && kvm_s2pmd_exec(pmdp);
 	else
-		return kvm_s2pte_exec(ptep);
+		return sz == PAGE_SIZE && kvm_s2pte_exec(ptep);
 }
 
 static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
@@ -1958,7 +1958,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * execute permissions, and we preserve whatever we have.
 	 */
 	needs_exec = exec_fault ||
-		(fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
+		(fault_status == FSC_PERM &&
+		 stage2_is_exec(kvm, fault_ipa, vma_pagesize));
 
 	if (vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index b5ae3a5d509e..3c224162b3dd 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -159,7 +159,10 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events)
 }
 
 /*
- * On VHE ensure that only guest events have EL0 counting enabled
+ * On VHE ensure that only guest events have EL0 counting enabled.
+ * This is called from both vcpu_{load,put} and the sysreg handling.
+ * Since the latter is preemptible, special care must be taken to
+ * disable preemption.
  */
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 {
@@ -169,12 +172,14 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 	if (!has_vhe())
 		return;
 
+	preempt_disable();
 	host = this_cpu_ptr(&kvm_host_data);
 	events_guest = host->pmu_events.events_guest;
 	events_host = host->pmu_events.events_host;
 
 	kvm_vcpu_pmu_enable_el0(events_guest);
 	kvm_vcpu_pmu_disable_el0(events_host);
+	preempt_enable();
 }
 
 /*
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index 1e0f4c284888..f7b52ce1557e 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -3,6 +3,7 @@
 
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
+#include <linux/sched/stat.h>
 
 #include <asm/kvm_mmu.h>
 #include <asm/pvclock-abi.h>
@@ -73,6 +74,11 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
+static bool kvm_arm_pvtime_supported(void)
+{
+	return !!sched_info_on();
+}
+
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr)
 {
@@ -82,7 +88,8 @@ int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 	int ret = 0;
 	int idx;
 
-	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+	if (!kvm_arm_pvtime_supported() ||
+	    attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
 		return -ENXIO;
 
 	if (get_user(ipa, user))
@@ -110,7 +117,8 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
 	u64 __user *user = (u64 __user *)attr->addr;
 	u64 ipa;
 
-	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+	if (!kvm_arm_pvtime_supported() ||
+	    attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
 		return -ENXIO;
 
 	ipa = vcpu->arch.steal.base;
@@ -125,7 +133,8 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 {
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_PVTIME_IPA:
-		return 0;
+		if (kvm_arm_pvtime_supported())
+			return 0;
 	}
 	return -ENXIO;
 }
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d3b209023727..6ed36be51b4b 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -245,7 +245,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
-	int ret = -EINVAL;
+	int ret;
 	bool loaded;
 	u32 pstate;
 
@@ -269,15 +269,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
 	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
-		if (kvm_vcpu_enable_ptrauth(vcpu))
+		if (kvm_vcpu_enable_ptrauth(vcpu)) {
+			ret = -EINVAL;
 			goto out;
+		}
 	}
 
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
+			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
+				ret = -EINVAL;
 				goto out;
+			}
 			pstate = VCPU_RESET_PSTATE_SVC;
 		} else {
 			pstate = VCPU_RESET_PSTATE_EL1;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index baf5ce9225ce..d3196671c590 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1024,9 +1024,9 @@ static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 /* Macro to expand the AMU counter and type registers*/
 #define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu }
-#define AMU_AMEVTYPE0_EL0(n) { SYS_DESC(SYS_AMEVTYPE0_EL0(n)), access_amu }
+#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu }
 #define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu }
-#define AMU_AMEVTYPE1_EL0(n) { SYS_DESC(SYS_AMEVTYPE1_EL0(n)), access_amu }
+#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu }
 
 static bool trap_ptrauth(struct kvm_vcpu *vcpu,
 			 struct sys_reg_params *p,
@@ -1629,22 +1629,22 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	AMU_AMEVCNTR0_EL0(13),
 	AMU_AMEVCNTR0_EL0(14),
 	AMU_AMEVCNTR0_EL0(15),
-	AMU_AMEVTYPE0_EL0(0),
-	AMU_AMEVTYPE0_EL0(1),
-	AMU_AMEVTYPE0_EL0(2),
-	AMU_AMEVTYPE0_EL0(3),
-	AMU_AMEVTYPE0_EL0(4),
-	AMU_AMEVTYPE0_EL0(5),
-	AMU_AMEVTYPE0_EL0(6),
-	AMU_AMEVTYPE0_EL0(7),
-	AMU_AMEVTYPE0_EL0(8),
-	AMU_AMEVTYPE0_EL0(9),
-	AMU_AMEVTYPE0_EL0(10),
-	AMU_AMEVTYPE0_EL0(11),
-	AMU_AMEVTYPE0_EL0(12),
-	AMU_AMEVTYPE0_EL0(13),
-	AMU_AMEVTYPE0_EL0(14),
-	AMU_AMEVTYPE0_EL0(15),
+	AMU_AMEVTYPER0_EL0(0),
+	AMU_AMEVTYPER0_EL0(1),
+	AMU_AMEVTYPER0_EL0(2),
+	AMU_AMEVTYPER0_EL0(3),
+	AMU_AMEVTYPER0_EL0(4),
+	AMU_AMEVTYPER0_EL0(5),
+	AMU_AMEVTYPER0_EL0(6),
+	AMU_AMEVTYPER0_EL0(7),
+	AMU_AMEVTYPER0_EL0(8),
+	AMU_AMEVTYPER0_EL0(9),
+	AMU_AMEVTYPER0_EL0(10),
+	AMU_AMEVTYPER0_EL0(11),
+	AMU_AMEVTYPER0_EL0(12),
+	AMU_AMEVTYPER0_EL0(13),
+	AMU_AMEVTYPER0_EL0(14),
+	AMU_AMEVTYPER0_EL0(15),
 	AMU_AMEVCNTR1_EL0(0),
 	AMU_AMEVCNTR1_EL0(1),
 	AMU_AMEVCNTR1_EL0(2),
@@ -1661,22 +1661,22 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	AMU_AMEVCNTR1_EL0(13),
 	AMU_AMEVCNTR1_EL0(14),
 	AMU_AMEVCNTR1_EL0(15),
-	AMU_AMEVTYPE1_EL0(0),
-	AMU_AMEVTYPE1_EL0(1),
-	AMU_AMEVTYPE1_EL0(2),
-	AMU_AMEVTYPE1_EL0(3),
-	AMU_AMEVTYPE1_EL0(4),
-	AMU_AMEVTYPE1_EL0(5),
-	AMU_AMEVTYPE1_EL0(6),
-	AMU_AMEVTYPE1_EL0(7),
-	AMU_AMEVTYPE1_EL0(8),
-	AMU_AMEVTYPE1_EL0(9),
-	AMU_AMEVTYPE1_EL0(10),
-	AMU_AMEVTYPE1_EL0(11),
-	AMU_AMEVTYPE1_EL0(12),
-	AMU_AMEVTYPE1_EL0(13),
-	AMU_AMEVTYPE1_EL0(14),
-	AMU_AMEVTYPE1_EL0(15),
+	AMU_AMEVTYPER1_EL0(0),
+	AMU_AMEVTYPER1_EL0(1),
+	AMU_AMEVTYPER1_EL0(2),
+	AMU_AMEVTYPER1_EL0(3),
+	AMU_AMEVTYPER1_EL0(4),
+	AMU_AMEVTYPER1_EL0(5),
+	AMU_AMEVTYPER1_EL0(6),
+	AMU_AMEVTYPER1_EL0(7),
+	AMU_AMEVTYPER1_EL0(8),
+	AMU_AMEVTYPER1_EL0(9),
+	AMU_AMEVTYPER1_EL0(10),
+	AMU_AMEVTYPER1_EL0(11),
+	AMU_AMEVTYPER1_EL0(12),
+	AMU_AMEVTYPER1_EL0(13),
+	AMU_AMEVTYPER1_EL0(14),
+	AMU_AMEVTYPER1_EL0(15),
 
 	{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer },
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index 27ac833e5ec7..b5fa73c9fd35 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -90,7 +90,15 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 	    !irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
 		disable_irq_nosync(irq);
 
+	/*
+	 * The v4.1 doorbell can fire concurrently with the vPE being
+	 * made non-resident. Ensure we only update pending_last
+	 * *after* the non-residency sequence has completed.
+	 */
+	raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
+	raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
+
 	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
 
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index d702d60e64da..a206655a39a5 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -198,9 +198,10 @@ set_asid:
 	return idx2asid(asid) | generation;
 }
 
-void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
+void check_and_switch_context(struct mm_struct *mm)
 {
 	unsigned long flags;
+	unsigned int cpu;
 	u64 asid, old_active_asid;
 
 	if (system_supports_cnp())
@@ -222,9 +223,9 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	 *   relaxed xchg in flush_context will treat us as reserved
 	 *   because atomic RmWs are totally ordered for a given location.
 	 */
-	old_active_asid = atomic64_read(&per_cpu(active_asids, cpu));
+	old_active_asid = atomic64_read(this_cpu_ptr(&active_asids));
 	if (old_active_asid && asid_gen_match(asid) &&
-	    atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu),
+	    atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_asids),
 				     old_active_asid, asid))
 		goto switch_mm_fastpath;
 
@@ -236,10 +237,11 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 		atomic64_set(&mm->context.id, asid);
 	}
 
+	cpu = smp_processor_id();
 	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending))
 		local_flush_tlb_all();
 
-	atomic64_set(&per_cpu(active_asids, cpu), asid);
+	atomic64_set(this_cpu_ptr(&active_asids), asid);
 	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
 
 switch_mm_fastpath:
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 0a52ce46f020..aa421bf4956e 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -19,6 +19,44 @@
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
 
+/*
+ * HugeTLB Support Matrix
+ *
+ * ---------------------------------------------------
+ * | Page Size | CONT PTE |  PMD  | CONT PMD |  PUD  |
+ * ---------------------------------------------------
+ * |     4K    |   64K    |   2M  |    32M   |   1G  |
+ * |    16K    |    2M    |  32M  |     1G   |       |
+ * |    64K    |    2M    | 512M  |    16G   |       |
+ * ---------------------------------------------------
+ */
+
+/*
+ * Reserve CMA areas for the largest supported gigantic
+ * huge page when requested. Any other smaller gigantic
+ * huge pages could still be served from those areas.
+ */
+#ifdef CONFIG_CMA
+void __init arm64_hugetlb_cma_reserve(void)
+{
+	int order;
+
+#ifdef CONFIG_ARM64_4K_PAGES
+	order = PUD_SHIFT - PAGE_SHIFT;
+#else
+	order = CONT_PMD_SHIFT + PMD_SHIFT - PAGE_SHIFT;
+#endif
+	/*
+	 * HugeTLB CMA reservation is required for gigantic
+	 * huge pages which could not be allocated via the
+	 * page allocator. Just warn if there is any change
+	 * breaking this assumption.
+	 */
+	WARN_ON(order <= MAX_ORDER);
+	hugetlb_cma_reserve(order);
+}
+#endif /* CONFIG_CMA */
+
 #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
 bool arch_hugetlb_migration_supported(struct hstate *h)
 {
@@ -457,9 +495,9 @@ static int __init hugetlbpage_init(void)
 #ifdef CONFIG_ARM64_4K_PAGES
 	hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 #endif
-	hugetlb_add_hstate((CONT_PMD_SHIFT + PMD_SHIFT) - PAGE_SHIFT);
+	hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT);
 	hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
-	hugetlb_add_hstate((CONT_PTE_SHIFT + PAGE_SHIFT) - PAGE_SHIFT);
+	hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT);
 
 	return 0;
 }
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index e631e6425165..f8c19c6c8e71 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -404,11 +404,6 @@ void __init arm64_memblock_init(void)
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
 	dma_contiguous_reserve(arm64_dma32_phys_limit);
-
-#ifdef CONFIG_ARM64_4K_PAGES
-	hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
-#endif
-
 }
 
 void __init bootmem_init(void)
@@ -424,6 +419,16 @@ void __init bootmem_init(void)
 	min_low_pfn = min;
 
 	arm64_numa_init();
+
+	/*
+	 * must be done after arm64_numa_init() which calls numa_init() to
+	 * initialize node_online_map that gets used in hugetlb_cma_reserve()
+	 * while allocating required CMA size across online nodes.
+	 */
+#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
+	arm64_hugetlb_cma_reserve();
+#endif
+
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
 	 * done after the fixed reservations.
@@ -558,27 +563,11 @@ void free_initmem(void)
 	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
 }
 
-/*
- * Dump out memory limit information on panic.
- */
-static int dump_mem_limit(struct notifier_block *self, unsigned long v, void *p)
+void dump_mem_limit(void)
 {
 	if (memory_limit != PHYS_ADDR_MAX) {
 		pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20);
 	} else {
 		pr_emerg("Memory Limit: none\n");
 	}
-	return 0;
-}
-
-static struct notifier_block mem_limit_notifier = {
-	.notifier_call = dump_mem_limit,
-};
-
-static int __init register_mem_limit_dumper(void)
-{
-	atomic_notifier_chain_register(&panic_notifier_list,
-				       &mem_limit_notifier);
-	return 0;
 }
-__initcall(register_mem_limit_dumper);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 990929c8837e..1df25f26571d 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -723,6 +723,7 @@ int kern_addr_valid(unsigned long addr)
 	pmd_t *pmdp, pmd;
 	pte_t *ptep, pte;
 
+	addr = arch_kasan_reset_tag(addr);
 	if ((((long)addr) >> VA_BITS) != -1UL)
 		return 0;
 
diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c
index 3c425b84e3be..b4a7ec1517ff 100644
--- a/arch/csky/kernel/ftrace.c
+++ b/arch/csky/kernel/ftrace.c
@@ -72,7 +72,8 @@ static int ftrace_check_current_nop(unsigned long hook)
 	uint16_t olds[7];
 	unsigned long hook_pos = hook - 2;
 
-	if (probe_kernel_read((void *)olds, (void *)hook_pos, sizeof(nops)))
+	if (copy_from_kernel_nofault((void *)olds, (void *)hook_pos,
+			sizeof(nops)))
 		return -EFAULT;
 
 	if (memcmp((void *)nops, (void *)olds, sizeof(nops))) {
@@ -97,7 +98,7 @@ static int ftrace_modify_code(unsigned long hook, unsigned long target,
 
 	make_jbsr(target, hook, call, nolr);
 
-	ret = probe_kernel_write((void *)hook_pos, enable ? call : nops,
+	ret = copy_to_kernel_nofault((void *)hook_pos, enable ? call : nops,
 				 sizeof(nops));
 	if (ret)
 		return -EPERM;
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index c6b6a06231b2..a990d151f163 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -12,8 +12,6 @@
  * resource counting etc..
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 0231d69c8bf2..4ab895d7111f 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -12,8 +12,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
-
 /*  Normal writes in our arch don't clear lock reservations  */
 
 static inline void atomic_set(atomic_t *v, int new)
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 50440f3ddc43..f267d956458f 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -19,7 +19,6 @@
 #include <asm/barrier.h>
 
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h
index cea15f2dd38d..3a033d2008b3 100644
--- a/arch/ia64/include/asm/sections.h
+++ b/arch/ia64/include/asm/sections.h
@@ -35,7 +35,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 	struct fdesc *desc = ptr;
 	void *p;
 
-	if (!probe_kernel_address(&desc->ip, p))
+	if (!get_kernel_nofault(p, (void *)&desc->ip))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c
index cee411e647ca..b2ab2d58fb30 100644
--- a/arch/ia64/kernel/ftrace.c
+++ b/arch/ia64/kernel/ftrace.c
@@ -108,7 +108,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		goto skip_check;
 
 	/* read the text we want to modify */
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/* Make sure it is what we expect it to be */
@@ -117,7 +117,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 
 skip_check:
 	/* replace the text with the new text */
-	if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE))
+	if (copy_to_kernel_nofault(((void *)ip), new_code, MCOUNT_INSN_SIZE))
 		return -EPERM;
 	flush_icache_range(ip, ip + MCOUNT_INSN_SIZE);
 
@@ -129,7 +129,7 @@ static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr)
 	unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE];
 	unsigned long ip = rec->ip;
 
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 	if (rec->flags & FTRACE_FL_CONVERTED) {
 		struct ftrace_call_insn *call_insn, *tmp_call;
diff --git a/arch/ia64/kernel/unwind_i.h b/arch/ia64/kernel/unwind_i.h
index 67994a7e5816..1dd57ba44327 100644
--- a/arch/ia64/kernel/unwind_i.h
+++ b/arch/ia64/kernel/unwind_i.h
@@ -42,7 +42,7 @@ enum unw_register_index {
 
 struct unw_info_block {
 	u64 header;
-	u64 desc[0];		/* unwind descriptors */
+	u64 desc[];		/* unwind descriptors */
 	/* personality routine and language-specific data follow behind descriptors */
 };
 
diff --git a/arch/m68k/Kbuild b/arch/m68k/Kbuild
new file mode 100644
index 000000000000..18abb35c26a1
--- /dev/null
+++ b/arch/m68k/Kbuild
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-y				+= kernel/ mm/
+obj-$(CONFIG_Q40)		+= q40/
+obj-$(CONFIG_AMIGA)		+= amiga/
+obj-$(CONFIG_ATARI)		+= atari/
+obj-$(CONFIG_MAC)		+= mac/
+obj-$(CONFIG_HP300)		+= hp300/
+obj-$(CONFIG_APOLLO)		+= apollo/
+obj-$(CONFIG_MVME147)		+= mvme147/
+obj-$(CONFIG_MVME16x)		+= mvme16x/
+obj-$(CONFIG_BVME6000)		+= bvme6000/
+obj-$(CONFIG_SUN3X)		+= sun3x/ sun3/
+obj-$(CONFIG_SUN3)		+= sun3/
+obj-$(CONFIG_NATFEAT)		+= emu/
+obj-$(CONFIG_M68040)		+= fpsp040/
+obj-$(CONFIG_M68060)		+= ifpsp060/
+obj-$(CONFIG_M68KFPU_EMU)	+= math-emu/
+obj-$(CONFIG_M68000)		+= 68000/
+obj-$(CONFIG_COLDFIRE)		+= coldfire/
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 0415d28dbe4f..4438ffb4bbe1 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -32,30 +32,33 @@ endif
 #	compiler cpu type flag.
 #
 ifndef CONFIG_M68040
-cpuflags-$(CONFIG_M68060)	:= -m68060
+cpuflags-$(CONFIG_M68060)	= -m68060
 endif
 ifndef CONFIG_M68060
-cpuflags-$(CONFIG_M68040)	:= -m68040
+cpuflags-$(CONFIG_M68040)	= -m68040
 endif
-cpuflags-$(CONFIG_M68030)	:=
-cpuflags-$(CONFIG_M68020)	:=
-cpuflags-$(CONFIG_M68000)	:= -m68000
-cpuflags-$(CONFIG_M5441x)	:= $(call cc-option,-mcpu=54455,-mcfv4e)
-cpuflags-$(CONFIG_M54xx)	:= $(call cc-option,-mcpu=5475,-m5200)
-cpuflags-$(CONFIG_M5407)	:= $(call cc-option,-mcpu=5407,-m5200)
-cpuflags-$(CONFIG_M532x)	:= $(call cc-option,-mcpu=532x,-m5307)
-cpuflags-$(CONFIG_M537x)	:= $(call cc-option,-mcpu=537x,-m5307)
-cpuflags-$(CONFIG_M5307)	:= $(call cc-option,-mcpu=5307,-m5200)
-cpuflags-$(CONFIG_M528x)	:= $(call cc-option,-mcpu=528x,-m5307)
-cpuflags-$(CONFIG_M5275)	:= $(call cc-option,-mcpu=5275,-m5307)
-cpuflags-$(CONFIG_M5272)	:= $(call cc-option,-mcpu=5272,-m5307)
-cpuflags-$(CONFIG_M5271)	:= $(call cc-option,-mcpu=5271,-m5307)
-cpuflags-$(CONFIG_M523x)	:= $(call cc-option,-mcpu=523x,-m5307)
-cpuflags-$(CONFIG_M525x)	:= $(call cc-option,-mcpu=5253,-m5200)
-cpuflags-$(CONFIG_M5249)	:= $(call cc-option,-mcpu=5249,-m5200)
-cpuflags-$(CONFIG_M520x)	:= $(call cc-option,-mcpu=5208,-m5200)
-cpuflags-$(CONFIG_M5206e)	:= $(call cc-option,-mcpu=5206e,-m5200)
-cpuflags-$(CONFIG_M5206)	:= $(call cc-option,-mcpu=5206,-m5200)
+cpuflags-$(CONFIG_M68030)	=
+cpuflags-$(CONFIG_M68020)	=
+cpuflags-$(CONFIG_M68000)	= -m68000
+cpuflags-$(CONFIG_M5441x)	= $(call cc-option,-mcpu=54455,-mcfv4e)
+cpuflags-$(CONFIG_M54xx)	= $(call cc-option,-mcpu=5475,-m5200)
+cpuflags-$(CONFIG_M5407)	= $(call cc-option,-mcpu=5407,-m5200)
+cpuflags-$(CONFIG_M532x)	= $(call cc-option,-mcpu=532x,-m5307)
+cpuflags-$(CONFIG_M537x)	= $(call cc-option,-mcpu=537x,-m5307)
+cpuflags-$(CONFIG_M5307)	= $(call cc-option,-mcpu=5307,-m5200)
+cpuflags-$(CONFIG_M528x)	= $(call cc-option,-mcpu=528x,-m5307)
+cpuflags-$(CONFIG_M5275)	= $(call cc-option,-mcpu=5275,-m5307)
+cpuflags-$(CONFIG_M5272)	= $(call cc-option,-mcpu=5272,-m5307)
+cpuflags-$(CONFIG_M5271)	= $(call cc-option,-mcpu=5271,-m5307)
+cpuflags-$(CONFIG_M523x)	= $(call cc-option,-mcpu=523x,-m5307)
+cpuflags-$(CONFIG_M525x)	= $(call cc-option,-mcpu=5253,-m5200)
+cpuflags-$(CONFIG_M5249)	= $(call cc-option,-mcpu=5249,-m5200)
+cpuflags-$(CONFIG_M520x)	= $(call cc-option,-mcpu=5208,-m5200)
+cpuflags-$(CONFIG_M5206e)	= $(call cc-option,-mcpu=5206e,-m5200)
+cpuflags-$(CONFIG_M5206)	= $(call cc-option,-mcpu=5206,-m5200)
+
+# Evaluate tune cc-option calls now
+cpuflags-y := $(cpuflags-y)
 
 KBUILD_AFLAGS += $(cpuflags-y)
 KBUILD_CFLAGS += $(cpuflags-y)
@@ -67,9 +70,8 @@ ifdef CONFIG_MMU
 KBUILD_CFLAGS += -fno-strength-reduce -ffixed-a2
 else
 # we can use a m68k-linux-gcc toolchain with these in place
-KBUILD_CFLAGS += -DUTS_SYSNAME=\"uClinux\"
-KBUILD_CFLAGS += -D__uClinux__
-KBUILD_AFLAGS += -D__uClinux__
+KBUILD_CPPFLAGS += -DUTS_SYSNAME=\"uClinux\"
+KBUILD_CPPFLAGS += -D__uClinux__
 endif
 
 KBUILD_LDFLAGS := -m m68kelf
@@ -97,27 +99,9 @@ head-$(CONFIG_SUN3)		:= arch/m68k/kernel/sun3-head.o
 head-$(CONFIG_M68000)		:= arch/m68k/68000/head.o
 head-$(CONFIG_COLDFIRE)		:= arch/m68k/coldfire/head.o
 
-core-y				+= arch/m68k/kernel/	arch/m68k/mm/
+core-y				+= arch/m68k/
 libs-y				+= arch/m68k/lib/
 
-core-$(CONFIG_Q40)		+= arch/m68k/q40/
-core-$(CONFIG_AMIGA)		+= arch/m68k/amiga/
-core-$(CONFIG_ATARI)		+= arch/m68k/atari/
-core-$(CONFIG_MAC)		+= arch/m68k/mac/
-core-$(CONFIG_HP300)		+= arch/m68k/hp300/
-core-$(CONFIG_APOLLO)		+= arch/m68k/apollo/
-core-$(CONFIG_MVME147)		+= arch/m68k/mvme147/
-core-$(CONFIG_MVME16x)		+= arch/m68k/mvme16x/
-core-$(CONFIG_BVME6000)		+= arch/m68k/bvme6000/
-core-$(CONFIG_SUN3X)		+= arch/m68k/sun3x/	arch/m68k/sun3/
-core-$(CONFIG_SUN3)		+= arch/m68k/sun3/	arch/m68k/sun3/prom/
-core-$(CONFIG_NATFEAT)		+= arch/m68k/emu/
-core-$(CONFIG_M68040)		+= arch/m68k/fpsp040/
-core-$(CONFIG_M68060)		+= arch/m68k/ifpsp060/
-core-$(CONFIG_M68KFPU_EMU)	+= arch/m68k/math-emu/
-core-$(CONFIG_M68000)		+= arch/m68k/68000/
-core-$(CONFIG_COLDFIRE)		+= arch/m68k/coldfire/
-
 
 all:	zImage
 
@@ -154,8 +138,7 @@ else
 	$(KBZIP2) -1c vmlinux >vmlinux.bz2
 endif
 
-archclean:
-	rm -f vmlinux.gz vmlinux.bz2
+CLEAN_FILES += vmlinux.gz vmlinux.bz2
 
 archheaders:
 	$(Q)$(MAKE) $(build)=arch/m68k/kernel/syscalls all
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 888b75e7fd79..f9f4fa595e13 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -594,6 +594,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -615,6 +616,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -643,6 +645,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 45303846b659..f4828e86d547 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -550,6 +550,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -571,6 +572,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -599,6 +601,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index de824c1bc3d3..e7911f141de1 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -572,6 +572,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -593,6 +594,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -621,6 +623,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 071839ca6a59..d574e438e6db 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -543,6 +543,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -564,6 +565,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -592,6 +594,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 37ac7b019ec1..c7ce206e6138 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -552,6 +552,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -573,6 +574,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -601,6 +603,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 608779866260..522dcf624aa5 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -574,6 +574,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -595,6 +596,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -623,6 +625,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 0abb53c38c20..2433409f4369 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -660,6 +660,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -681,6 +682,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -709,6 +711,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index cb14c234d3ad..5568aa7d9d41 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -542,6 +542,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -563,6 +564,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -591,6 +593,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index e8a1920aded7..5b1e72ce53f8 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -543,6 +543,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -564,6 +565,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -592,6 +594,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 2cbf416fc725..c3a3dcf30fb9 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -561,6 +561,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -582,6 +583,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -610,6 +612,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index fed3cc7abcc4..3c00e52f1bf0 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -545,6 +545,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -566,6 +567,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -593,6 +595,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 0954fde256e6..241242d73cbd 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -544,6 +544,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -565,6 +566,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC32_SELFTEST=m
 CONFIG_CRC64=m
 CONFIG_XZ_DEC_TEST=m
@@ -593,6 +595,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index c3a630440512..92d26c812441 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -59,9 +59,9 @@ struct nfhd_device {
 	struct gendisk *disk;
 };
 
-static blk_qc_t nfhd_make_request(struct request_queue *queue, struct bio *bio)
+static blk_qc_t nfhd_submit_bio(struct bio *bio)
 {
-	struct nfhd_device *dev = queue->queuedata;
+	struct nfhd_device *dev = bio->bi_disk->private_data;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 	int dir, len, shift;
@@ -93,6 +93,7 @@ static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 
 static const struct block_device_operations nfhd_ops = {
 	.owner	= THIS_MODULE,
+	.submit_bio = nfhd_submit_bio,
 	.getgeo	= nfhd_getgeo,
 };
 
@@ -118,11 +119,10 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->bsize = bsize;
 	dev->bshift = ffs(bsize) - 10;
 
-	dev->queue = blk_alloc_queue(nfhd_make_request, NUMA_NO_NODE);
+	dev->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (dev->queue == NULL)
 		goto free_dev;
 
-	dev->queue->queuedata = dev;
 	blk_queue_logical_block_size(dev->queue, bsize);
 
 	dev->disk = alloc_disk(16);
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 47228b0d4163..756c5cc58f94 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -16,8 +16,6 @@
  * We do not have SMP m68k systems, so we don't have to deal with that.
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/m68k/include/asm/raw_io.h b/arch/m68k/include/asm/raw_io.h
index 8a6dc6e5a279..911826ea83ce 100644
--- a/arch/m68k/include/asm/raw_io.h
+++ b/arch/m68k/include/asm/raw_io.h
@@ -80,14 +80,14 @@
 	({ u16 __v = le16_to_cpu(*(__force volatile u16 *) (addr)); __v; })
 
 #define rom_out_8(addr, b)	\
-	({u8 __w, __v = (b);  u32 _addr = ((u32) (addr)); \
+	({u8 __maybe_unused __w, __v = (b);  u32 _addr = ((u32) (addr)); \
 	__w = ((*(__force volatile u8 *)  ((_addr | 0x10000) + (__v<<1)))); })
 #define rom_out_be16(addr, w)	\
-	({u16 __w, __v = (w); u32 _addr = ((u32) (addr)); \
+	({u16 __maybe_unused __w, __v = (w); u32 _addr = ((u32) (addr)); \
 	__w = ((*(__force volatile u16 *) ((_addr & 0xFFFF0000UL) + ((__v & 0xFF)<<1)))); \
 	__w = ((*(__force volatile u16 *) ((_addr | 0x10000) + ((__v >> 8)<<1)))); })
 #define rom_out_le16(addr, w)	\
-	({u16 __w, __v = (w); u32 _addr = ((u32) (addr)); \
+	({u16 __maybe_unused __w, __v = (w); u32 _addr = ((u32) (addr)); \
 	__w = ((*(__force volatile u16 *) ((_addr & 0xFFFF0000UL) + ((__v >> 8)<<1)))); \
 	__w = ((*(__force volatile u16 *) ((_addr | 0x10000) + ((__v & 0xFF)<<1)))); })
 
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index e779b19e0193..f66f4b1d062e 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -138,7 +138,8 @@ void __init setup_arch(char **cmdline_p)
 	pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ",
 		 __bss_stop, memory_start, memory_start, memory_end);
 
-	memblock_add(memory_start, memory_end - memory_start);
+	memblock_add(_rambase, memory_end - _rambase);
+	memblock_reserve(_rambase, memory_start - _rambase);
 
 	/* Keep a copy of command line */
 	*cmdline_p = &command_line[0];
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index b3ff39588f36..fc034fd19798 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -61,25 +61,25 @@
 #define	FMT4SIZE	0
 #else
 #define	FORMAT		0
-#define	FMT4SIZE	sizeof(((struct frame *)0)->un.fmt4)
+#define	FMT4SIZE	sizeof_field(struct frame, un.fmt4)
 #endif
 
 static const int frame_size_change[16] = {
-  [1]	= -1, /* sizeof(((struct frame *)0)->un.fmt1), */
-  [2]	= sizeof(((struct frame *)0)->un.fmt2),
-  [3]	= sizeof(((struct frame *)0)->un.fmt3),
+  [1]	= -1, /* sizeof_field(struct frame, un.fmt1), */
+  [2]	= sizeof_field(struct frame, un.fmt2),
+  [3]	= sizeof_field(struct frame, un.fmt3),
   [4]	= FMT4SIZE,
-  [5]	= -1, /* sizeof(((struct frame *)0)->un.fmt5), */
-  [6]	= -1, /* sizeof(((struct frame *)0)->un.fmt6), */
-  [7]	= sizeof(((struct frame *)0)->un.fmt7),
-  [8]	= -1, /* sizeof(((struct frame *)0)->un.fmt8), */
-  [9]	= sizeof(((struct frame *)0)->un.fmt9),
-  [10]	= sizeof(((struct frame *)0)->un.fmta),
-  [11]	= sizeof(((struct frame *)0)->un.fmtb),
-  [12]	= -1, /* sizeof(((struct frame *)0)->un.fmtc), */
-  [13]	= -1, /* sizeof(((struct frame *)0)->un.fmtd), */
-  [14]	= -1, /* sizeof(((struct frame *)0)->un.fmte), */
-  [15]	= -1, /* sizeof(((struct frame *)0)->un.fmtf), */
+  [5]	= -1, /* sizeof_field(struct frame, un.fmt5), */
+  [6]	= -1, /* sizeof_field(struct frame, un.fmt6), */
+  [7]	= sizeof_field(struct frame, un.fmt7),
+  [8]	= -1, /* sizeof_field(struct frame, un.fmt8), */
+  [9]	= sizeof_field(struct frame, un.fmt9),
+  [10]	= sizeof_field(struct frame, un.fmta),
+  [11]	= sizeof_field(struct frame, un.fmtb),
+  [12]	= -1, /* sizeof_field(struct frame, un.fmtc), */
+  [13]	= -1, /* sizeof_field(struct frame, un.fmtd), */
+  [14]	= -1, /* sizeof_field(struct frame, un.fmte), */
+  [15]	= -1, /* sizeof_field(struct frame, un.fmtf), */
 };
 
 static inline int frame_extra_sizes(int f)
@@ -651,7 +651,7 @@ static int mangle_kernel_stack(struct pt_regs *regs, int formatvec,
 	} else {
 		struct switch_stack *sw = (struct switch_stack *)regs - 1;
 		/* yes, twice as much as max(sizeof(frame.un.fmt<x>)) */
-		unsigned long buf[sizeof(((struct frame *)0)->un) / 2];
+		unsigned long buf[sizeof_field(struct frame, un) / 2];
 
 		/* that'll make sure that expansion won't crap over data */
 		if (copy_from_user(buf + fsize / 4, fp, fsize))
diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
index d3775afb0f07..c669a7644301 100644
--- a/arch/m68k/mac/iop.c
+++ b/arch/m68k/mac/iop.c
@@ -183,7 +183,7 @@ static __inline__ void iop_writeb(volatile struct mac_iop *iop, __u16 addr, __u8
 
 static __inline__ void iop_stop(volatile struct mac_iop *iop)
 {
-	iop->status_ctrl &= ~IOP_RUN;
+	iop->status_ctrl = IOP_AUTOINC;
 }
 
 static __inline__ void iop_start(volatile struct mac_iop *iop)
@@ -191,14 +191,9 @@ static __inline__ void iop_start(volatile struct mac_iop *iop)
 	iop->status_ctrl = IOP_RUN | IOP_AUTOINC;
 }
 
-static __inline__ void iop_bypass(volatile struct mac_iop *iop)
-{
-	iop->status_ctrl |= IOP_BYPASS;
-}
-
 static __inline__ void iop_interrupt(volatile struct mac_iop *iop)
 {
-	iop->status_ctrl |= IOP_IRQ;
+	iop->status_ctrl = IOP_IRQ | IOP_RUN | IOP_AUTOINC;
 }
 
 static int iop_alive(volatile struct mac_iop *iop)
@@ -244,7 +239,6 @@ void __init iop_preinit(void)
 		} else {
 			iop_base[IOP_NUM_SCC] = (struct mac_iop *) SCC_IOP_BASE_QUADRA;
 		}
-		iop_base[IOP_NUM_SCC]->status_ctrl = 0x87;
 		iop_scc_present = 1;
 	} else {
 		iop_base[IOP_NUM_SCC] = NULL;
@@ -256,7 +250,7 @@ void __init iop_preinit(void)
 		} else {
 			iop_base[IOP_NUM_ISM] = (struct mac_iop *) ISM_IOP_BASE_QUADRA;
 		}
-		iop_base[IOP_NUM_ISM]->status_ctrl = 0;
+		iop_stop(iop_base[IOP_NUM_ISM]);
 		iop_ism_present = 1;
 	} else {
 		iop_base[IOP_NUM_ISM] = NULL;
@@ -353,8 +347,8 @@ void iop_complete_message(struct iop_msg *msg)
 	int chan = msg->channel;
 	int i,offset;
 
-	iop_pr_debug("msg %p iop_num %d channel %d\n", msg, msg->iop_num,
-	             msg->channel);
+	iop_pr_debug("iop_num %d chan %d reply %*ph\n",
+		     msg->iop_num, msg->channel, IOP_MSG_LEN, msg->reply);
 
 	offset = IOP_ADDR_RECV_MSG + (msg->channel * IOP_MSG_LEN);
 
@@ -378,6 +372,9 @@ static void iop_do_send(struct iop_msg *msg)
 	volatile struct mac_iop *iop = iop_base[msg->iop_num];
 	int i,offset;
 
+	iop_pr_debug("iop_num %d chan %d message %*ph\n",
+		     msg->iop_num, msg->channel, IOP_MSG_LEN, msg->message);
+
 	offset = IOP_ADDR_SEND_MSG + (msg->channel * IOP_MSG_LEN);
 
 	for (i = 0 ; i < IOP_MSG_LEN ; i++, offset++) {
@@ -400,8 +397,6 @@ static void iop_handle_send(uint iop_num, uint chan)
 	struct iop_msg *msg;
 	int i,offset;
 
-	iop_pr_debug("iop_num %d chan %d\n", iop_num, chan);
-
 	iop_writeb(iop, IOP_ADDR_SEND_STATE + chan, IOP_MSG_IDLE);
 
 	if (!(msg = iop_send_queue[iop_num][chan])) return;
@@ -411,11 +406,15 @@ static void iop_handle_send(uint iop_num, uint chan)
 	for (i = 0 ; i < IOP_MSG_LEN ; i++, offset++) {
 		msg->reply[i] = iop_readb(iop, offset);
 	}
+	iop_pr_debug("iop_num %d chan %d reply %*ph\n",
+		     iop_num, chan, IOP_MSG_LEN, msg->reply);
+
 	if (msg->handler) (*msg->handler)(msg);
 	msg->status = IOP_MSGSTATUS_UNUSED;
 	msg = msg->next;
 	iop_send_queue[iop_num][chan] = msg;
-	if (msg) iop_do_send(msg);
+	if (msg && iop_readb(iop, IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE)
+		iop_do_send(msg);
 }
 
 /*
@@ -429,8 +428,6 @@ static void iop_handle_recv(uint iop_num, uint chan)
 	int i,offset;
 	struct iop_msg *msg;
 
-	iop_pr_debug("iop_num %d chan %d\n", iop_num, chan);
-
 	msg = iop_get_unused_msg();
 	msg->iop_num = iop_num;
 	msg->channel = chan;
@@ -442,6 +439,8 @@ static void iop_handle_recv(uint iop_num, uint chan)
 	for (i = 0 ; i < IOP_MSG_LEN ; i++, offset++) {
 		msg->message[i] = iop_readb(iop, offset);
 	}
+	iop_pr_debug("iop_num %d chan %d message %*ph\n",
+		     iop_num, chan, IOP_MSG_LEN, msg->message);
 
 	iop_writeb(iop, IOP_ADDR_RECV_STATE + chan, IOP_MSG_RCVD);
 
@@ -451,9 +450,7 @@ static void iop_handle_recv(uint iop_num, uint chan)
 	if (msg->handler) {
 		(*msg->handler)(msg);
 	} else {
-		iop_pr_debug("unclaimed message on iop_num %d chan %d\n",
-		             iop_num, chan);
-		iop_pr_debug("%*ph\n", IOP_MSG_LEN, msg->message);
+		memset(msg->reply, 0, IOP_MSG_LEN);
 		iop_complete_message(msg);
 	}
 }
@@ -489,16 +486,12 @@ int iop_send_message(uint iop_num, uint chan, void *privdata,
 
 	if (!(q = iop_send_queue[iop_num][chan])) {
 		iop_send_queue[iop_num][chan] = msg;
+		iop_do_send(msg);
 	} else {
 		while (q->next) q = q->next;
 		q->next = msg;
 	}
 
-	if (iop_readb(iop_base[iop_num],
-	    IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE) {
-		iop_do_send(msg);
-	}
-
 	return 0;
 }
 
@@ -567,35 +560,34 @@ irqreturn_t iop_ism_irq(int irq, void *dev_id)
 	int i,state;
 	u8 events = iop->status_ctrl & (IOP_INT0 | IOP_INT1);
 
-	iop_pr_debug("status %02X\n", iop->status_ctrl);
-
 	do {
+		iop_pr_debug("iop_num %d status %02X\n", iop_num,
+			     iop->status_ctrl);
+
 		/* INT0 indicates state change on an outgoing message channel */
 		if (events & IOP_INT0) {
 			iop->status_ctrl = IOP_INT0 | IOP_RUN | IOP_AUTOINC;
-			iop_pr_debug("new status %02X, send states",
-				     iop->status_ctrl);
 			for (i = 0; i < NUM_IOP_CHAN; i++) {
 				state = iop_readb(iop, IOP_ADDR_SEND_STATE + i);
-				iop_pr_cont(" %02X", state);
 				if (state == IOP_MSG_COMPLETE)
 					iop_handle_send(iop_num, i);
+				else if (state != IOP_MSG_IDLE)
+					iop_pr_debug("chan %d send state %02X\n",
+						     i, state);
 			}
-			iop_pr_cont("\n");
 		}
 
 		/* INT1 for incoming messages */
 		if (events & IOP_INT1) {
 			iop->status_ctrl = IOP_INT1 | IOP_RUN | IOP_AUTOINC;
-			iop_pr_debug("new status %02X, recv states",
-				     iop->status_ctrl);
 			for (i = 0; i < NUM_IOP_CHAN; i++) {
 				state = iop_readb(iop, IOP_ADDR_RECV_STATE + i);
-				iop_pr_cont(" %02X", state);
 				if (state == IOP_MSG_NEW)
 					iop_handle_recv(iop_num, i);
+				else if (state != IOP_MSG_IDLE)
+					iop_pr_debug("chan %d recv state %02X\n",
+						     i, state);
 			}
-			iop_pr_cont("\n");
 		}
 
 		events = iop->status_ctrl & (IOP_INT0 | IOP_INT1);
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 29f47923aa46..7d04210d34f0 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -174,7 +174,7 @@ void __init cf_bootmem_alloc(void)
 	m68k_memory[0].addr = _rambase;
 	m68k_memory[0].size = _ramend - _rambase;
 
-	memblock_add(m68k_memory[0].addr, m68k_memory[0].size);
+	memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0);
 
 	/* compute total pages in system */
 	num_pages = PFN_DOWN(_ramend - _rambase);
diff --git a/arch/m68k/sun3/Makefile b/arch/m68k/sun3/Makefile
index 9960c46d303c..4e99e17d82ea 100644
--- a/arch/m68k/sun3/Makefile
+++ b/arch/m68k/sun3/Makefile
@@ -5,4 +5,4 @@
 
 obj-y	:= sun3ints.o sun3dvma.o idprom.o
 
-obj-$(CONFIG_SUN3) += config.o mmu_emu.o leds.o dvma.o intersil.o
+obj-$(CONFIG_SUN3) += config.o mmu_emu.o leds.o dvma.o intersil.o prom/
diff --git a/arch/mips/boot/dts/ingenic/gcw0.dts b/arch/mips/boot/dts/ingenic/gcw0.dts
index 8d22828787d8..bc72304a2440 100644
--- a/arch/mips/boot/dts/ingenic/gcw0.dts
+++ b/arch/mips/boot/dts/ingenic/gcw0.dts
@@ -92,7 +92,7 @@
 			"MIC1N", "Built-in Mic";
 		simple-audio-card,pin-switches = "Speaker", "Headphones";
 
-		simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_HIGH>;
+		simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_LOW>;
 		simple-audio-card,aux-devs = <&speaker_amp>, <&headphones_amp>;
 
 		simple-audio-card,bitclock-master = <&dai_codec>;
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index e5ac88392d1f..f904084fcb1f 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -45,7 +45,6 @@ static __always_inline type pfx##_xchg(pfx##_t *v, type n)		\
 	return xchg(&v->counter, n);					\
 }
 
-#define ATOMIC_INIT(i)		{ (i) }
 ATOMIC_OPS(atomic, int)
 
 #ifdef CONFIG_64BIT
diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h
index c628747d4ecd..7dd4a80e05d6 100644
--- a/arch/mips/include/asm/unroll.h
+++ b/arch/mips/include/asm/unroll.h
@@ -19,15 +19,13 @@
 								\
 	/*							\
 	 * We can't unroll if the number of iterations isn't	\
-	 * compile-time constant. Unfortunately GCC versions	\
-	 * up until 4.6 tend to miss obvious constants & cause	\
+	 * compile-time constant. Unfortunately clang versions	\
+	 * up until 8.0 tend to miss obvious constants & cause	\
 	 * this check to fail, even though they go on to	\
 	 * generate reasonable code for the switch statement,	\
 	 * so we skip the sanity check for those compilers.	\
 	 */							\
-	BUILD_BUG_ON((CONFIG_GCC_VERSION >= 40700 ||		\
-		      CONFIG_CLANG_VERSION >= 80000) &&		\
-		     !__builtin_constant_p(times));		\
+	BUILD_BUG_ON(!__builtin_constant_p(times));		\
 								\
 	switch (times) {					\
 	case 32: fn(__VA_ARGS__); /* fall through */		\
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 6cfae2411c04..d043c2f897fc 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -86,9 +86,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 		goto out;
 	}
 
-	if ((probe_kernel_read(&prev_insn, p->addr - 1,
-				sizeof(mips_instruction)) == 0) &&
-				insn_has_delayslot(prev_insn)) {
+	if (copy_from_kernel_nofault(&prev_insn, p->addr - 1,
+			sizeof(mips_instruction)) == 0 &&
+	    insn_has_delayslot(prev_insn)) {
 		pr_notice("Kprobes for branch delayslot are not supported\n");
 		ret = -EINVAL;
 		goto out;
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 7c32c956156a..f655af68176c 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -723,12 +723,14 @@ static int simulate_loongson3_cpucfg(struct pt_regs *regs,
 		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 		/* Do not emulate on unsupported core models. */
-		if (!loongson3_cpucfg_emulation_enabled(&current_cpu_data))
+		preempt_disable();
+		if (!loongson3_cpucfg_emulation_enabled(&current_cpu_data)) {
+			preempt_enable();
 			return -1;
-
+		}
 		regs->regs[rd] = loongson3_cpucfg_read_synthesized(
 			&current_cpu_data, sel);
-
+		preempt_enable();
 		return 0;
 	}
 
@@ -2169,6 +2171,7 @@ static void configure_status(void)
 
 	change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX,
 			 status_set);
+	back_to_back_c0_hazard();
 }
 
 unsigned int hwrena;
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 5ae82d925197..d242300cacc0 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1722,6 +1722,7 @@ enum emulation_result kvm_mips_emulate_store(union mips_instruction inst,
 			  vcpu->arch.gprs[rt], *(u32 *)data);
 		break;
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_KVM_MIPS_VZ)
 	case sdl_op:
 		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
 					vcpu->arch.host_cp0_badvaddr) & (~0x7);
@@ -1815,6 +1816,7 @@ enum emulation_result kvm_mips_emulate_store(union mips_instruction inst,
 			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
 			  vcpu->arch.gprs[rt], *(u64 *)data);
 		break;
+#endif
 
 #ifdef CONFIG_CPU_LOONGSON64
 	case sdc2_op:
@@ -2002,6 +2004,7 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
 		}
 		break;
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_KVM_MIPS_VZ)
 	case ldl_op:
 		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
 					vcpu->arch.host_cp0_badvaddr) & (~0x7);
@@ -2073,6 +2076,7 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
 			break;
 		}
 		break;
+#endif
 
 #ifdef CONFIG_CPU_LOONGSON64
 	case ldc2_op:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 521bd5891e84..666d3350b4ac 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -67,8 +67,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("vz_ghfc", vz_ghfc_exits),
 	VCPU_STAT("vz_gpa", vz_gpa_exits),
 	VCPU_STAT("vz_resvd", vz_resvd_exits),
+#ifdef CONFIG_CPU_LOONGSON64
 	VCPU_STAT("vz_cpucfg", vz_cpucfg_exits),
 #endif
+#endif
 	VCPU_STAT("halt_successful_poll", halt_successful_poll),
 	VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
 	VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index aa37545ebe8f..b10342018d19 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -514,8 +514,8 @@ void __init ltq_soc_init(void)
 		clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH |
 			       PMU_PPE_DP | PMU_PPE_TC);
 		clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF);
-		clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY);
-		clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 		clkdev_add_pmu("1e116000.mei", "afe", 1, 2, PMU_ANALOG_DSL_AFE);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);
@@ -538,8 +538,8 @@ void __init ltq_soc_init(void)
 				PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM |
 				PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 |
 				PMU_PPE_QSB | PMU_PPE_TOP);
-		clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY);
-		clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 3b2552fb7735..9b3cc775c55e 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -627,9 +627,10 @@ static int bridge_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	domain = irq_domain_create_hierarchy(parent, 0, 8, fn,
 					     &bridge_domain_ops, NULL);
-	irq_domain_free_fwnode(fn);
-	if (!domain)
+	if (!domain) {
+		irq_domain_free_fwnode(fn);
 		return -ENOMEM;
+	}
 
 	pci_set_flags(PCI_PROBE_ONLY);
 
@@ -727,6 +728,7 @@ err_free_resource:
 	pci_free_resource_list(&host->windows);
 err_remove_domain:
 	irq_domain_remove(domain);
+	irq_domain_free_fwnode(fn);
 	return err;
 }
 
@@ -734,8 +736,10 @@ static int bridge_remove(struct platform_device *pdev)
 {
 	struct pci_bus *bus = platform_get_drvdata(pdev);
 	struct bridge_controller *bc = BRIDGE_CONTROLLER(bus);
+	struct fwnode_handle *fn = bc->domain->fwnode;
 
 	irq_domain_remove(bc->domain);
+	irq_domain_free_fwnode(fn);
 	pci_lock_rescan_remove();
 	pci_stop_root_bus(bus);
 	pci_remove_root_bus(bus);
diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c
index 22ab77ea27ad..3763b3f8c3db 100644
--- a/arch/nds32/kernel/ftrace.c
+++ b/arch/nds32/kernel/ftrace.c
@@ -131,13 +131,14 @@ static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn,
 	unsigned long orig_insn[3];
 
 	if (validate) {
-		if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE))
+		if (copy_from_kernel_nofault(orig_insn, (void *)pc,
+				MCOUNT_INSN_SIZE))
 			return -EFAULT;
 		if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE))
 			return -EINVAL;
 	}
 
-	if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE))
+	if (copy_to_kernel_nofault((void *)pc, new_insn, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	return 0;
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index c152a68811dd..345727638d52 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -74,8 +74,11 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size)
 	 * We need to iterate through the pages, clearing the dcache for
 	 * them and setting the cache-inhibit bit.
 	 */
+	mmap_read_lock(&init_mm);
 	error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops,
 			NULL);
+	mmap_read_unlock(&init_mm);
+
 	if (error)
 		return ERR_PTR(error);
 	return cpu_addr;
@@ -85,9 +88,11 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size)
 {
 	unsigned long va = (unsigned long)cpu_addr;
 
+	mmap_read_lock(&init_mm);
 	/* walk_page_range shouldn't be able to fail here */
 	WARN_ON(walk_page_range(&init_mm, va, va + size,
 			&clear_nocache_walk_ops, NULL));
+	mmap_read_unlock(&init_mm);
 }
 
 void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 118953d41763..03862320f779 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -136,8 +136,6 @@ ATOMIC_OPS(xor, ^=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i) { (i) }
@@ -212,6 +210,8 @@ atomic64_set(atomic64_t *v, s64 i)
 	_atomic_spin_unlock_irqrestore(v, flags);
 }
 
+#define atomic64_set_release(v, i)	atomic64_set((v), (i))
+
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index ab5c215cf46c..068958575871 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -60,6 +60,7 @@ extern void __cmpxchg_called_with_bad_pointer(void);
 extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
 				   unsigned int new_);
 extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
+extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
@@ -71,6 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
 #endif
 	case 4: return __cmpxchg_u32((unsigned int *)ptr,
 				     (unsigned int)old, (unsigned int)new_);
+	case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
 	}
 	__cmpxchg_called_with_bad_pointer();
 	return old;
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index b836fc61a24f..1df0f67ed667 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -172,7 +172,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	ip = (void *)(rec->ip + 4 - size);
 
-	ret = probe_kernel_read(insn, ip, size);
+	ret = copy_from_kernel_nofault(insn, ip, size);
 	if (ret)
 		return ret;
 
diff --git a/arch/parisc/kernel/kgdb.c b/arch/parisc/kernel/kgdb.c
index 664278db9b97..c4554ac13eac 100644
--- a/arch/parisc/kernel/kgdb.c
+++ b/arch/parisc/kernel/kgdb.c
@@ -154,8 +154,8 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 
 int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
-	int ret = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
-				BREAK_INSTR_SIZE);
+	int ret = copy_from_kernel_nofault(bpt->saved_instr,
+			(char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
 	if (ret)
 		return ret;
 
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 230a6422b99f..b7abb12edd3a 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -293,7 +293,7 @@ void *dereference_function_descriptor(void *ptr)
 	Elf64_Fdesc *desc = ptr;
 	void *p;
 
-	if (!probe_kernel_address(&desc->addr, p))
+	if (!get_kernel_nofault(p, (void *)&desc->addr))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c
index 70ffbcf889b8..2e4d1f05a926 100644
--- a/arch/parisc/lib/bitops.c
+++ b/arch/parisc/lib/bitops.c
@@ -79,3 +79,15 @@ unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsign
 	_atomic_spin_unlock_irqrestore(ptr, flags);
 	return (unsigned long)prev;
 }
+
+u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new)
+{
+	unsigned long flags;
+	u8 prev;
+
+	_atomic_spin_lock_irqsave(ptr, flags);
+	if ((prev = *ptr) == old)
+		*ptr = new;
+	_atomic_spin_unlock_irqrestore(ptr, flags);
+	return prev;
+}
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index 94a9fe2702c2..4b75388190b4 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -57,7 +57,7 @@ void * memcpy(void * dst,const void *src, size_t count)
 EXPORT_SYMBOL(raw_copy_in_user);
 EXPORT_SYMBOL(memcpy);
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	if ((unsigned long)unsafe_src < PAGE_SIZE)
 		return false;
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 498785ffc25f..0311c3c42960 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -11,8 +11,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
-
 /*
  * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
  * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
diff --git a/arch/powerpc/include/asm/dtl.h b/arch/powerpc/include/asm/dtl.h
new file mode 100644
index 000000000000..1625888f27ef
--- /dev/null
+++ b/arch/powerpc/include/asm/dtl.h
@@ -0,0 +1,52 @@
+#ifndef _ASM_POWERPC_DTL_H
+#define _ASM_POWERPC_DTL_H
+
+#include <asm/lppaca.h>
+#include <linux/spinlock_types.h>
+
+/*
+ * Layout of entries in the hypervisor's dispatch trace log buffer.
+ */
+struct dtl_entry {
+	u8	dispatch_reason;
+	u8	preempt_reason;
+	__be16	processor_id;
+	__be32	enqueue_to_dispatch_time;
+	__be32	ready_to_enqueue_time;
+	__be32	waiting_to_ready_time;
+	__be64	timebase;
+	__be64	fault_addr;
+	__be64	srr0;
+	__be64	srr1;
+};
+
+#define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
+#define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
+
+/*
+ * Dispatch trace log event enable mask:
+ *   0x1: voluntary virtual processor waits
+ *   0x2: time-slice preempts
+ *   0x4: virtual partition memory page faults
+ */
+#define DTL_LOG_CEDE		0x1
+#define DTL_LOG_PREEMPT		0x2
+#define DTL_LOG_FAULT		0x4
+#define DTL_LOG_ALL		(DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT)
+
+extern struct kmem_cache *dtl_cache;
+extern rwlock_t dtl_access_lock;
+
+/*
+ * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls
+ * reading from the dispatch trace log.  If other code wants to consume
+ * DTL entries, it can set this pointer to a function that will get
+ * called once for each DTL entry that gets processed.
+ */
+extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index);
+
+extern void register_dtl_buffer(int cpu);
+extern void alloc_dtl_buffers(unsigned long *time_limit);
+extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity);
+
+#endif /* _ASM_POWERPC_DTL_H */
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
index 965b1f39b2a5..b0c70a35fd0e 100644
--- a/arch/powerpc/include/asm/icswx.h
+++ b/arch/powerpc/include/asm/icswx.h
@@ -77,6 +77,8 @@ struct coprocessor_completion_block {
 #define CSB_CC_CHAIN		(37)
 #define CSB_CC_SEQUENCE		(38)
 #define CSB_CC_HW		(39)
+/* P9 DD2 NX Workbook 3.2 (Table 4-36): Address translation fault */
+#define	CSB_CC_FAULT_ADDRESS	(250)
 
 #define CSB_SIZE		(0x10)
 #define CSB_ALIGN		CSB_SIZE
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 3b4b305796ae..c390ec377bae 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -42,7 +42,6 @@
  */
 #include <linux/cache.h>
 #include <linux/threads.h>
-#include <linux/spinlock_types.h>
 #include <asm/types.h>
 #include <asm/mmu.h>
 #include <asm/firmware.h>
@@ -146,49 +145,6 @@ struct slb_shadow {
 	} save_area[SLB_NUM_BOLTED];
 } ____cacheline_aligned;
 
-/*
- * Layout of entries in the hypervisor's dispatch trace log buffer.
- */
-struct dtl_entry {
-	u8	dispatch_reason;
-	u8	preempt_reason;
-	__be16	processor_id;
-	__be32	enqueue_to_dispatch_time;
-	__be32	ready_to_enqueue_time;
-	__be32	waiting_to_ready_time;
-	__be64	timebase;
-	__be64	fault_addr;
-	__be64	srr0;
-	__be64	srr1;
-};
-
-#define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
-#define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
-
-/*
- * Dispatch trace log event enable mask:
- *   0x1: voluntary virtual processor waits
- *   0x2: time-slice preempts
- *   0x4: virtual partition memory page faults
- */
-#define DTL_LOG_CEDE		0x1
-#define DTL_LOG_PREEMPT		0x2
-#define DTL_LOG_FAULT		0x4
-#define DTL_LOG_ALL		(DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT)
-
-extern struct kmem_cache *dtl_cache;
-extern rwlock_t dtl_access_lock;
-
-/*
- * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls
- * reading from the dispatch trace log.  If other code wants to consume
- * DTL entries, it can set this pointer to a function that will get
- * called once for each DTL entry that gets processed.
- */
-extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index);
-
-extern void register_dtl_buffer(int cpu);
-extern void alloc_dtl_buffers(unsigned long *time_limit);
 extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity);
 
 #endif /* CONFIG_PPC_BOOK3S */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index b56f14160ae5..b0afbdd07740 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -205,10 +205,6 @@ static inline void pmd_clear(pmd_t *pmdp)
 	*pmdp = __pmd(0);
 }
 
-/* to find an entry in a page-table-directory */
-#define pgd_index(address)	 ((address) >> PGDIR_SHIFT)
-#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
-
 /*
  * PTE updates. This function is called whenever an existing
  * valid PTE is updated. This does -not- include set_pte_at()
@@ -230,6 +226,8 @@ static inline void pmd_clear(pmd_t *pmdp)
  * For other page sizes, we have a single entry in the table.
  */
 #ifdef CONFIG_PPC_8xx
+static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr);
+
 static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
 				     unsigned long clr, unsigned long set, int huge)
 {
@@ -237,7 +235,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
 	pte_basic_t old = pte_val(*p);
 	pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
 	int num, i;
-	pmd_t *pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, addr), addr), addr), addr);
+	pmd_t *pmd = pmd_off(mm, addr);
 
 	if (!huge)
 		num = PAGE_SIZE / SZ_4K;
@@ -286,6 +284,16 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 	return __pte(pte_update(mm, addr, ptep, ~0, 0, 0));
 }
 
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
+#define __HAVE_ARCH_PTEP_GET
+static inline pte_t ptep_get(pte_t *ptep)
+{
+	pte_t pte = {READ_ONCE(ptep->pte), 0, 0, 0};
+
+	return pte;
+}
+#endif
+
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 45a839a7c6cf..84b2564cf5a4 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -29,7 +29,6 @@
 #include <asm/hmi.h>
 #include <asm/cpuidle.h>
 #include <asm/atomic.h>
-#include <asm/rtas-types.h>
 
 #include <asm-generic/mmiowb_types.h>
 
@@ -53,6 +52,7 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
 #define get_slb_shadow()	(get_paca()->slb_shadow_ptr)
 
 struct task_struct;
+struct rtas_args;
 
 /*
  * Defines the layout of the paca.
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index d19871763ed4..324d7b298ec3 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -85,7 +85,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 	struct ppc64_opd_entry *desc = ptr;
 	void *p;
 
-	if (!probe_kernel_address(&desc->funcaddr, p))
+	if (!get_kernel_nofault(p, (void *)&desc->funcaddr))
 		ptr = p;
 	return ptr;
 }
diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h
new file mode 100644
index 000000000000..9ccecc1d6840
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr_pdsm.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * PAPR nvDimm Specific Methods (PDSM) and structs for libndctl
+ *
+ * (C) Copyright IBM 2020
+ *
+ * Author: Vaibhav Jain <vaibhav at linux.ibm.com>
+ */
+
+#ifndef _UAPI_ASM_POWERPC_PAPR_PDSM_H_
+#define _UAPI_ASM_POWERPC_PAPR_PDSM_H_
+
+#include <linux/types.h>
+#include <linux/ndctl.h>
+
+/*
+ * PDSM Envelope:
+ *
+ * The ioctl ND_CMD_CALL exchange data between user-space and kernel via
+ * envelope which consists of 2 headers sections and payload sections as
+ * illustrated below:
+ *  +-----------------+---------------+---------------------------+
+ *  |   64-Bytes      |   8-Bytes     |       Max 184-Bytes       |
+ *  +-----------------+---------------+---------------------------+
+ *  | ND-HEADER       |  PDSM-HEADER  |      PDSM-PAYLOAD         |
+ *  +-----------------+---------------+---------------------------+
+ *  | nd_family       |               |                           |
+ *  | nd_size_out     | cmd_status    |                           |
+ *  | nd_size_in      | reserved      |     nd_pdsm_payload       |
+ *  | nd_command      | payload   --> |                           |
+ *  | nd_fw_size      |               |                           |
+ *  | nd_payload ---> |               |                           |
+ *  +---------------+-----------------+---------------------------+
+ *
+ * ND Header:
+ * This is the generic libnvdimm header described as 'struct nd_cmd_pkg'
+ * which is interpreted by libnvdimm before passed on to papr_scm. Important
+ * member fields used are:
+ * 'nd_family'		: (In) NVDIMM_FAMILY_PAPR_SCM
+ * 'nd_size_in'		: (In) PDSM-HEADER + PDSM-IN-PAYLOAD (usually 0)
+ * 'nd_size_out'        : (In) PDSM-HEADER + PDSM-RETURN-PAYLOAD
+ * 'nd_command'         : (In) One of PAPR_PDSM_XXX
+ * 'nd_fw_size'         : (Out) PDSM-HEADER + size of actual payload returned
+ *
+ * PDSM Header:
+ * This is papr-scm specific header that precedes the payload. This is defined
+ * as nd_cmd_pdsm_pkg.  Following fields aare available in this header:
+ *
+ * 'cmd_status'		: (Out) Errors if any encountered while servicing PDSM.
+ * 'reserved'		: Not used, reserved for future and should be set to 0.
+ * 'payload'            : A union of all the possible payload structs
+ *
+ * PDSM Payload:
+ *
+ * The layout of the PDSM Payload is defined by various structs shared between
+ * papr_scm and libndctl so that contents of payload can be interpreted. As such
+ * its defined as a union of all possible payload structs as
+ * 'union nd_pdsm_payload'. Based on the value of 'nd_cmd_pkg.nd_command'
+ * appropriate member of the union is accessed.
+ */
+
+/* Max payload size that we can handle */
+#define ND_PDSM_PAYLOAD_MAX_SIZE 184
+
+/* Max payload size that we can handle */
+#define ND_PDSM_HDR_SIZE \
+	(sizeof(struct nd_pkg_pdsm) - ND_PDSM_PAYLOAD_MAX_SIZE)
+
+/* Various nvdimm health indicators */
+#define PAPR_PDSM_DIMM_HEALTHY       0
+#define PAPR_PDSM_DIMM_UNHEALTHY     1
+#define PAPR_PDSM_DIMM_CRITICAL      2
+#define PAPR_PDSM_DIMM_FATAL         3
+
+/*
+ * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH
+ * Various flags indicate the health status of the dimm.
+ *
+ * extension_flags	: Any extension fields present in the struct.
+ * dimm_unarmed		: Dimm not armed. So contents wont persist.
+ * dimm_bad_shutdown	: Previous shutdown did not persist contents.
+ * dimm_bad_restore	: Contents from previous shutdown werent restored.
+ * dimm_scrubbed	: Contents of the dimm have been scrubbed.
+ * dimm_locked		: Contents of the dimm cant be modified until CEC reboot
+ * dimm_encrypted	: Contents of dimm are encrypted.
+ * dimm_health		: Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX
+ */
+struct nd_papr_pdsm_health {
+	union {
+		struct {
+			__u32 extension_flags;
+			__u8 dimm_unarmed;
+			__u8 dimm_bad_shutdown;
+			__u8 dimm_bad_restore;
+			__u8 dimm_scrubbed;
+			__u8 dimm_locked;
+			__u8 dimm_encrypted;
+			__u16 dimm_health;
+		};
+		__u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
+	};
+};
+
+/*
+ * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel
+ * via 'nd_cmd_pkg.nd_command' member of the ioctl struct
+ */
+enum papr_pdsm {
+	PAPR_PDSM_MIN = 0x0,
+	PAPR_PDSM_HEALTH,
+	PAPR_PDSM_MAX,
+};
+
+/* Maximal union that can hold all possible payload types */
+union nd_pdsm_payload {
+	struct nd_papr_pdsm_health health;
+	__u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
+} __packed;
+
+/*
+ * PDSM-header + payload expected with ND_CMD_CALL ioctl from libnvdimm
+ * Valid member of union 'payload' is identified via 'nd_cmd_pkg.nd_command'
+ * that should always precede this struct when sent to papr_scm via CMD_CALL
+ * interface.
+ */
+struct nd_pkg_pdsm {
+	__s32 cmd_status;	/* Out: Sub-cmd status returned back */
+	__u16 reserved[2];	/* Ignored and to be set as '0' */
+	union nd_pdsm_payload payload;
+} __packed;
+
+#endif /* _UAPI_ASM_POWERPC_PAPR_PDSM_H_ */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e70ebb5c318c..446e54c3f71e 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -270,7 +270,7 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	.endif
 
-	ld	r10,PACA_EXGEN+EX_CTR(r13)
+	ld	r10,IAREA+EX_CTR(r13)
 	mtctr	r10
 BEGIN_FTR_SECTION
 	ld	r10,IAREA+EX_PPR(r13)
@@ -298,7 +298,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	.if IKVM_SKIP
 89:	mtocrf	0x80,r9
-	ld	r10,PACA_EXGEN+EX_CTR(r13)
+	ld	r10,IAREA+EX_CTR(r13)
 	mtctr	r10
 	ld	r9,IAREA+EX_R9(r13)
 	ld	r10,IAREA+EX_R10(r13)
@@ -2551,7 +2551,7 @@ EXC_VIRT_NONE(0x5400, 0x100)
 INT_DEFINE_BEGIN(denorm_exception)
 	IVEC=0x1500
 	IHSRR=1
-	IBRANCH_COMMON=0
+	IBRANCH_TO_COMMON=0
 	IKVM_REAL=1
 INT_DEFINE_END(denorm_exception)
 
@@ -3072,10 +3072,18 @@ do_hash_page:
 	ori	r0,r0,DSISR_BAD_FAULT_64S@l
 	and.	r0,r5,r0		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
+
+	/*
+	 * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
+	 * don't call hash_page, just fail the fault. This is required to
+	 * prevent re-entrancy problems in the hash code, namely perf
+	 * interrupts hitting while something holds H_PAGE_BUSY, and taking a
+	 * hash fault. See the comment in hash_preload().
+	 */
 	ld	r11, PACA_THREAD_INFO(r13)
-	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
-	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
-	bne	77f			/* then don't call hash_page now */
+	lwz	r0,TI_PREEMPT(r11)
+	andis.	r0,r0,NMI_MASK@h
+	bne	77f
 
 	/*
 	 * r3 contains the trap number
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 652b2852bea3..409080208a6c 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -421,7 +421,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	unsigned int instr;
 	struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr;
 
-	err = probe_kernel_address(addr, instr);
+	err = get_kernel_nofault(instr, (unsigned *) addr);
 	if (err)
 		return err;
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 6f96f65ebfe8..9cc792a3a6a9 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -289,7 +289,7 @@ int kprobe_handler(struct pt_regs *regs)
 	if (!p) {
 		unsigned int instr;
 
-		if (probe_kernel_address(addr, instr))
+		if (get_kernel_nofault(instr, addr))
 			goto no_kprobe;
 
 		if (instr != BREAKPOINT_INSTRUCTION) {
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index f4c2fa190192..ae2b188365b1 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -756,7 +756,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr,
 
 	stub = (struct ppc64_stub_entry *)addr;
 
-	if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) {
+	if (copy_from_kernel_nofault(&magic, &stub->magic,
+			sizeof(magic))) {
 		pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name);
 		return -EFAULT;
 	}
@@ -766,7 +767,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr,
 		return -EFAULT;
 	}
 
-	if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) {
+	if (copy_from_kernel_nofault(&funcdata, &stub->funcdata,
+			sizeof(funcdata))) {
 		pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name);
                 return -EFAULT;
 	}
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 2168372b792d..74da65aacbc9 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -87,7 +87,7 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align,
 	 * This is very early in boot, so no harm done if the kernel crashes at
 	 * this point.
 	 */
-	BUG_ON(shared_lppaca_size >= shared_lppaca_total_size);
+	BUG_ON(shared_lppaca_size > shared_lppaca_total_size);
 
 	return ptr;
 }
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7bb7faf84490..4650b9bb217f 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1252,29 +1252,31 @@ struct task_struct *__switch_to(struct task_struct *prev,
 static void show_instructions(struct pt_regs *regs)
 {
 	int i;
+	unsigned long nip = regs->nip;
 	unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
 
 	printk("Instruction dump:");
 
+	/*
+	 * If we were executing with the MMU off for instructions, adjust pc
+	 * rather than printing XXXXXXXX.
+	 */
+	if (!IS_ENABLED(CONFIG_BOOKE) && !(regs->msr & MSR_IR)) {
+		pc = (unsigned long)phys_to_virt(pc);
+		nip = (unsigned long)phys_to_virt(regs->nip);
+	}
+
 	for (i = 0; i < NR_INSN_TO_PRINT; i++) {
 		int instr;
 
 		if (!(i % 8))
 			pr_cont("\n");
 
-#if !defined(CONFIG_BOOKE)
-		/* If executing with the IMMU off, adjust pc rather
-		 * than print XXXXXXXX.
-		 */
-		if (!(regs->msr & MSR_IR))
-			pc = (unsigned long)phys_to_virt(pc);
-#endif
-
 		if (!__kernel_text_address(pc) ||
-		    probe_kernel_address((const void *)pc, instr)) {
+		    get_kernel_nofault(instr, (const void *)pc)) {
 			pr_cont("XXXXXXXX ");
 		} else {
-			if (regs->nip == pc)
+			if (nip == pc)
 				pr_cont("<%08x> ", instr);
 			else
 				pr_cont("%08x ", instr);
@@ -1305,7 +1307,8 @@ void show_user_instructions(struct pt_regs *regs)
 		for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
 			int instr;
 
-			if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) {
+			if (copy_from_user_nofault(&instr, (void __user *)pc,
+					sizeof(instr))) {
 				seq_buf_printf(&s, "XXXXXXXX ");
 				continue;
 			}
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 6fcae436ae51..f85539ebb513 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -183,6 +183,8 @@ static inline unsigned long read_spurr(unsigned long tb)
 
 #ifdef CONFIG_PPC_SPLPAR
 
+#include <asm/dtl.h>
+
 /*
  * Scan the dispatch trace log and count up the stolen time.
  * Should be called with interrupts disabled.
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 5e399628f51a..c1fede6ec934 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -226,7 +226,7 @@ __ftrace_make_nop(struct module *mod,
 	unsigned long ip = rec->ip;
 	unsigned long tramp;
 
-	if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(&op, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/* Make sure that that this is still a 24bit jump */
@@ -249,7 +249,7 @@ __ftrace_make_nop(struct module *mod,
 	pr_devel("ip:%lx jumps to %lx", ip, tramp);
 
 	/* Find where the trampoline jumps to */
-	if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
+	if (copy_from_kernel_nofault(jmp, (void *)tramp, sizeof(jmp))) {
 		pr_err("Failed to read %lx\n", tramp);
 		return -EFAULT;
 	}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 3cb0c9843d01..6a73714759ba 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -40,7 +40,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
 	if (kvmhv_on_pseries())
 		return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
-					  __pa(to), __pa(from), n);
+					  (to != NULL) ? __pa(to): 0,
+					  (from != NULL) ? __pa(from): 0, n);
 
 	quadrant = 1;
 	if (!pid)
@@ -64,9 +65,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	isync();
 
 	if (is_load)
-		ret = probe_user_read(to, (const void __user *)from, n);
+		ret = copy_from_user_nofault(to, (const void __user *)from, n);
 	else
-		ret = probe_user_write((void __user *)to, from, n);
+		ret = copy_to_user_nofault((void __user *)to, from, n);
 
 	/* switch the pid first to avoid running host with unallocated pid */
 	if (quadrant == 1 && pid != old_pid)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6bf66649ab92..ebb04f331ad3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -74,6 +74,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/kvm_book3s_uvmem.h>
 #include <asm/ultravisor.h>
+#include <asm/dtl.h>
 
 #include "book3s.h"
 
diff --git a/arch/powerpc/lib/inst.c b/arch/powerpc/lib/inst.c
index aedfd6e31e53..9cc17eb62462 100644
--- a/arch/powerpc/lib/inst.c
+++ b/arch/powerpc/lib/inst.c
@@ -15,11 +15,11 @@ int probe_user_read_inst(struct ppc_inst *inst,
 	unsigned int val, suffix;
 	int err;
 
-	err = probe_user_read(&val, nip, sizeof(val));
+	err = copy_from_user_nofault(&val, nip, sizeof(val));
 	if (err)
 		return err;
 	if (get_op(val) == OP_PREFIX) {
-		err = probe_user_read(&suffix, (void __user *)nip + 4, 4);
+		err = copy_from_user_nofault(&suffix, (void __user *)nip + 4, 4);
 		*inst = ppc_inst_prefix(val, suffix);
 	} else {
 		*inst = ppc_inst(val);
@@ -33,11 +33,11 @@ int probe_kernel_read_inst(struct ppc_inst *inst,
 	unsigned int val, suffix;
 	int err;
 
-	err = probe_kernel_read(&val, src, sizeof(val));
+	err = copy_from_kernel_nofault(&val, src, sizeof(val));
 	if (err)
 		return err;
 	if (get_op(val) == OP_PREFIX) {
-		err = probe_kernel_read(&suffix, (void *)src + 4, 4);
+		err = copy_from_kernel_nofault(&suffix, (void *)src + 4, 4);
 		*inst = ppc_inst_prefix(val, suffix);
 	} else {
 		*inst = ppc_inst(val);
@@ -51,7 +51,7 @@ int probe_user_read_inst(struct ppc_inst *inst,
 	unsigned int val;
 	int err;
 
-	err = probe_user_read(&val, nip, sizeof(val));
+	err = copy_from_user_nofault(&val, nip, sizeof(val));
 	if (!err)
 		*inst = ppc_inst(val);
 
@@ -64,7 +64,7 @@ int probe_kernel_read_inst(struct ppc_inst *inst,
 	unsigned int val;
 	int err;
 
-	err = probe_kernel_read(&val, src, sizeof(val));
+	err = copy_from_kernel_nofault(&val, src, sizeof(val));
 	if (!err)
 		*inst = ppc_inst(val);
 
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 468169e33c86..9b9f92ad0e7a 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1559,6 +1559,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
 	pgd_t *pgdir;
 	int rc, ssize, update_flags = 0;
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ | (is_exec ? _PAGE_EXEC : 0);
+	unsigned long flags;
 
 	BUG_ON(get_region_id(ea) != USER_REGION_ID);
 
@@ -1592,6 +1593,28 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
 		return;
 #endif /* CONFIG_PPC_64K_PAGES */
 
+	/*
+	 * __hash_page_* must run with interrupts off, as it sets the
+	 * H_PAGE_BUSY bit. It's possible for perf interrupts to hit at any
+	 * time and may take a hash fault reading the user stack, see
+	 * read_user_stack_slow() in the powerpc/perf code.
+	 *
+	 * If that takes a hash fault on the same page as we lock here, it
+	 * will bail out when seeing H_PAGE_BUSY set, and retry the access
+	 * leading to an infinite loop.
+	 *
+	 * Disabling interrupts here does not prevent perf interrupts, but it
+	 * will prevent them taking hash faults (see the NMI test in
+	 * do_hash_page), then read_user_stack's copy_from_user_nofault will
+	 * fail and perf will fall back to read_user_stack_slow(), which
+	 * walks the Linux page tables.
+	 *
+	 * Interrupts must also be off for the duration of the
+	 * mm_is_thread_local test and update, to prevent preempt running the
+	 * mm on another CPU (XXX: this may be racy vs kthread_use_mm).
+	 */
+	local_irq_save(flags);
+
 	/* Is that local to this CPU ? */
 	if (mm_is_thread_local(mm))
 		update_flags |= HPTE_LOCAL_UPDATE;
@@ -1614,6 +1637,8 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
 				   mm_ctx_user_psize(&mm->context),
 				   mm_ctx_user_psize(&mm->context),
 				   pte_val(*ptep));
+
+	local_irq_restore(flags);
 }
 
 /*
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 1199fc2bfaec..d174106bab67 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -353,16 +353,15 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute)
 	int pkey_shift;
 	u64 amr;
 
-	if (!is_pkey_enabled(pkey))
-		return true;
-
 	pkey_shift = pkeyshift(pkey);
-	if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift)))
-		return true;
+	if (execute)
+		return !(read_iamr() & (IAMR_EX_BIT << pkey_shift));
+
+	amr = read_amr();
+	if (write)
+		return !(amr & (AMR_WR_BIT << pkey_shift));
 
-	amr = read_amr(); /* Delay reading amr until absolutely needed */
-	return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) ||
-		(write &&  !(amr & (AMR_WR_BIT << pkey_shift))));
+	return !(amr & (AMR_RD_BIT << pkey_shift));
 }
 
 bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
index 4a75f2d9bf0e..bce0e5349978 100644
--- a/arch/powerpc/mm/nohash/kaslr_booke.c
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -14,6 +14,7 @@
 #include <linux/memblock.h>
 #include <linux/libfdt.h>
 #include <linux/crash_core.h>
+#include <asm/cacheflush.h>
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
 #include <asm/kdump.h>
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index 6f347fa29f41..9db7ada79d10 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -33,7 +33,8 @@ static unsigned int user_getsp32(unsigned int sp, int is_first)
 	 * which means that we've done all that we can do from
 	 * interrupt context.
 	 */
-	if (probe_user_read(stack_frame, (void __user *)p, sizeof(stack_frame)))
+	if (copy_from_user_nofault(stack_frame, (void __user *)p,
+			sizeof(stack_frame)))
 		return 0;
 
 	if (!is_first)
@@ -51,7 +52,8 @@ static unsigned long user_getsp64(unsigned long sp, int is_first)
 {
 	unsigned long stack_frame[3];
 
-	if (probe_user_read(stack_frame, (void __user *)sp, sizeof(stack_frame)))
+	if (copy_from_user_nofault(stack_frame, (void __user *)sp,
+			sizeof(stack_frame)))
 		return 0;
 
 	if (!is_first)
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index f7d888d39cd3..542e68b8eae0 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -44,7 +44,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	    ((unsigned long)ptr & 3))
 		return -EFAULT;
 
-	rc = probe_user_read(ret, ptr, sizeof(*ret));
+	rc = copy_from_user_nofault(ret, ptr, sizeof(*ret));
 
 	if (IS_ENABLED(CONFIG_PPC64) && rc)
 		return read_user_stack_slow(ptr, ret, 4);
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 814d1c2c2b9c..fa2a1b83b9b0 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -50,7 +50,7 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
 	    ((unsigned long)ptr & 7))
 		return -EFAULT;
 
-	if (!probe_user_read(ret, ptr, sizeof(*ret)))
+	if (!copy_from_user_nofault(ret, ptr, sizeof(*ret)))
 		return 0;
 
 	return read_user_stack_slow(ptr, ret, 8);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 13b9dd5e4a76..01d70280d287 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -418,14 +418,16 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	__u64 target;
 
 	if (is_kernel_addr(addr)) {
-		if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+		if (copy_from_kernel_nofault(&instr, (void *)addr,
+				sizeof(instr)))
 			return 0;
 
 		return branch_target((struct ppc_inst *)&instr);
 	}
 
 	/* Userspace: need copy instruction here then translate it */
-	if (probe_user_read(&instr, (unsigned int __user *)addr, sizeof(instr)))
+	if (copy_from_user_nofault(&instr, (unsigned int __user *)addr,
+			sizeof(instr)))
 		return 0;
 
 	target = branch_target((struct ppc_inst *)&instr);
@@ -2177,6 +2179,12 @@ static void __perf_event_interrupt(struct pt_regs *regs)
 
 	perf_read_regs(regs);
 
+	/*
+	 * If perf interrupts hit in a local_irq_disable (soft-masked) region,
+	 * we consider them as NMIs. This is required to prevent hash faults on
+	 * user addresses when reading callchains. See the NMI test in
+	 * do_hash_page.
+	 */
 	nmi = perf_intr_is_nmi(regs);
 	if (nmi)
 		nmi_enter();
diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c
index cbee3666da07..abdef9bcf432 100644
--- a/arch/powerpc/platforms/cell/spu_callbacks.c
+++ b/arch/powerpc/platforms/cell/spu_callbacks.c
@@ -35,7 +35,7 @@
  */
 
 static void *spu_syscall_table[] = {
-#define __SYSCALL(nr, entry)	entry,
+#define __SYSCALL(nr, entry) [nr] = entry,
 #include <asm/syscall_table_spu.h>
 #undef __SYSCALL
 };
diff --git a/arch/powerpc/platforms/powernv/vas-fault.c b/arch/powerpc/platforms/powernv/vas-fault.c
index 266a6ca5e15e..3d21fce254b7 100644
--- a/arch/powerpc/platforms/powernv/vas-fault.c
+++ b/arch/powerpc/platforms/powernv/vas-fault.c
@@ -79,7 +79,7 @@ static void update_csb(struct vas_window *window,
 	csb_addr = (void __user *)be64_to_cpu(crb->csb_addr);
 
 	memset(&csb, 0, sizeof(csb));
-	csb.cc = CSB_CC_TRANSLATION;
+	csb.cc = CSB_CC_FAULT_ADDRESS;
 	csb.ce = CSB_CE_TERMINATION;
 	csb.cs = 0;
 	csb.count = 0;
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index eab8aa293743..982f069e4c31 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -12,6 +12,7 @@
 #include <asm/smp.h>
 #include <linux/uaccess.h>
 #include <asm/firmware.h>
+#include <asm/dtl.h>
 #include <asm/lppaca.h>
 #include <asm/debugfs.h>
 #include <asm/plpar_wrappers.h>
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index fd26f3d21d7b..f71ff2c94efe 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -40,6 +40,7 @@
 #include <asm/fadump.h>
 #include <asm/asm-prototypes.h>
 #include <asm/debugfs.h>
+#include <asm/dtl.h>
 
 #include "pseries.h"
 
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index f35592423380..9c569078a09f 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -12,16 +12,57 @@
 #include <linux/libnvdimm.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
+#include <linux/seq_buf.h>
 
 #include <asm/plpar_wrappers.h>
+#include <asm/papr_pdsm.h>
 
 #define BIND_ANY_ADDR (~0ul)
 
 #define PAPR_SCM_DIMM_CMD_MASK \
 	((1ul << ND_CMD_GET_CONFIG_SIZE) | \
 	 (1ul << ND_CMD_GET_CONFIG_DATA) | \
-	 (1ul << ND_CMD_SET_CONFIG_DATA))
-
+	 (1ul << ND_CMD_SET_CONFIG_DATA) | \
+	 (1ul << ND_CMD_CALL))
+
+/* DIMM health bitmap bitmap indicators */
+/* SCM device is unable to persist memory contents */
+#define PAPR_PMEM_UNARMED                   (1ULL << (63 - 0))
+/* SCM device failed to persist memory contents */
+#define PAPR_PMEM_SHUTDOWN_DIRTY            (1ULL << (63 - 1))
+/* SCM device contents are persisted from previous IPL */
+#define PAPR_PMEM_SHUTDOWN_CLEAN            (1ULL << (63 - 2))
+/* SCM device contents are not persisted from previous IPL */
+#define PAPR_PMEM_EMPTY                     (1ULL << (63 - 3))
+/* SCM device memory life remaining is critically low */
+#define PAPR_PMEM_HEALTH_CRITICAL           (1ULL << (63 - 4))
+/* SCM device will be garded off next IPL due to failure */
+#define PAPR_PMEM_HEALTH_FATAL              (1ULL << (63 - 5))
+/* SCM contents cannot persist due to current platform health status */
+#define PAPR_PMEM_HEALTH_UNHEALTHY          (1ULL << (63 - 6))
+/* SCM device is unable to persist memory contents in certain conditions */
+#define PAPR_PMEM_HEALTH_NON_CRITICAL       (1ULL << (63 - 7))
+/* SCM device is encrypted */
+#define PAPR_PMEM_ENCRYPTED                 (1ULL << (63 - 8))
+/* SCM device has been scrubbed and locked */
+#define PAPR_PMEM_SCRUBBED_AND_LOCKED       (1ULL << (63 - 9))
+
+/* Bits status indicators for health bitmap indicating unarmed dimm */
+#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED |		\
+				PAPR_PMEM_HEALTH_UNHEALTHY)
+
+/* Bits status indicators for health bitmap indicating unflushed dimm */
+#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY)
+
+/* Bits status indicators for health bitmap indicating unrestored dimm */
+#define PAPR_PMEM_BAD_RESTORE_MASK  (PAPR_PMEM_EMPTY)
+
+/* Bit status indicators for smart event notification */
+#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \
+				    PAPR_PMEM_HEALTH_FATAL |	\
+				    PAPR_PMEM_HEALTH_UNHEALTHY)
+
+/* private struct associated with each region */
 struct papr_scm_priv {
 	struct platform_device *pdev;
 	struct device_node *dn;
@@ -39,6 +80,15 @@ struct papr_scm_priv {
 	struct resource res;
 	struct nd_region *region;
 	struct nd_interleave_set nd_set;
+
+	/* Protect dimm health data from concurrent read/writes */
+	struct mutex health_mutex;
+
+	/* Last time the health information of the dimm was updated */
+	unsigned long lasthealth_jiffies;
+
+	/* Health information for the dimm */
+	u64 health_bitmap;
 };
 
 static int drc_pmem_bind(struct papr_scm_priv *p)
@@ -144,6 +194,61 @@ err_out:
 	return drc_pmem_bind(p);
 }
 
+/*
+ * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the
+ * health information.
+ */
+static int __drc_pmem_query_health(struct papr_scm_priv *p)
+{
+	unsigned long ret[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	/* issue the hcall */
+	rc = plpar_hcall(H_SCM_HEALTH, ret, p->drc_index);
+	if (rc != H_SUCCESS) {
+		dev_err(&p->pdev->dev,
+			"Failed to query health information, Err:%ld\n", rc);
+		return -ENXIO;
+	}
+
+	p->lasthealth_jiffies = jiffies;
+	p->health_bitmap = ret[0] & ret[1];
+
+	dev_dbg(&p->pdev->dev,
+		"Queried dimm health info. Bitmap:0x%016lx Mask:0x%016lx\n",
+		ret[0], ret[1]);
+
+	return 0;
+}
+
+/* Min interval in seconds for assuming stable dimm health */
+#define MIN_HEALTH_QUERY_INTERVAL 60
+
+/* Query cached health info and if needed call drc_pmem_query_health */
+static int drc_pmem_query_health(struct papr_scm_priv *p)
+{
+	unsigned long cache_timeout;
+	int rc;
+
+	/* Protect concurrent modifications to papr_scm_priv */
+	rc = mutex_lock_interruptible(&p->health_mutex);
+	if (rc)
+		return rc;
+
+	/* Jiffies offset for which the health data is assumed to be same */
+	cache_timeout = p->lasthealth_jiffies +
+		msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000);
+
+	/* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */
+	if (time_after(jiffies, cache_timeout))
+		rc = __drc_pmem_query_health(p);
+	else
+		/* Assume cached health data is valid */
+		rc = 0;
+
+	mutex_unlock(&p->health_mutex);
+	return rc;
+}
 
 static int papr_scm_meta_get(struct papr_scm_priv *p,
 			     struct nd_cmd_get_config_data_hdr *hdr)
@@ -246,16 +351,250 @@ static int papr_scm_meta_set(struct papr_scm_priv *p,
 	return 0;
 }
 
+/*
+ * Do a sanity checks on the inputs args to dimm-control function and return
+ * '0' if valid. Validation of PDSM payloads happens later in
+ * papr_scm_service_pdsm.
+ */
+static int is_cmd_valid(struct nvdimm *nvdimm, unsigned int cmd, void *buf,
+			unsigned int buf_len)
+{
+	unsigned long cmd_mask = PAPR_SCM_DIMM_CMD_MASK;
+	struct nd_cmd_pkg *nd_cmd;
+	struct papr_scm_priv *p;
+	enum papr_pdsm pdsm;
+
+	/* Only dimm-specific calls are supported atm */
+	if (!nvdimm)
+		return -EINVAL;
+
+	/* get the provider data from struct nvdimm */
+	p = nvdimm_provider_data(nvdimm);
+
+	if (!test_bit(cmd, &cmd_mask)) {
+		dev_dbg(&p->pdev->dev, "Unsupported cmd=%u\n", cmd);
+		return -EINVAL;
+	}
+
+	/* For CMD_CALL verify pdsm request */
+	if (cmd == ND_CMD_CALL) {
+		/* Verify the envelope and envelop size */
+		if (!buf ||
+		    buf_len < (sizeof(struct nd_cmd_pkg) + ND_PDSM_HDR_SIZE)) {
+			dev_dbg(&p->pdev->dev, "Invalid pkg size=%u\n",
+				buf_len);
+			return -EINVAL;
+		}
+
+		/* Verify that the nd_cmd_pkg.nd_family is correct */
+		nd_cmd = (struct nd_cmd_pkg *)buf;
+
+		if (nd_cmd->nd_family != NVDIMM_FAMILY_PAPR) {
+			dev_dbg(&p->pdev->dev, "Invalid pkg family=0x%llx\n",
+				nd_cmd->nd_family);
+			return -EINVAL;
+		}
+
+		pdsm = (enum papr_pdsm)nd_cmd->nd_command;
+
+		/* Verify if the pdsm command is valid */
+		if (pdsm <= PAPR_PDSM_MIN || pdsm >= PAPR_PDSM_MAX) {
+			dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid PDSM\n",
+				pdsm);
+			return -EINVAL;
+		}
+
+		/* Have enough space to hold returned 'nd_pkg_pdsm' header */
+		if (nd_cmd->nd_size_out < ND_PDSM_HDR_SIZE) {
+			dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid payload\n",
+				pdsm);
+			return -EINVAL;
+		}
+	}
+
+	/* Let the command be further processed */
+	return 0;
+}
+
+/* Fetch the DIMM health info and populate it in provided package. */
+static int papr_pdsm_health(struct papr_scm_priv *p,
+			    union nd_pdsm_payload *payload)
+{
+	int rc;
+
+	/* Ensure dimm health mutex is taken preventing concurrent access */
+	rc = mutex_lock_interruptible(&p->health_mutex);
+	if (rc)
+		goto out;
+
+	/* Always fetch upto date dimm health data ignoring cached values */
+	rc = __drc_pmem_query_health(p);
+	if (rc) {
+		mutex_unlock(&p->health_mutex);
+		goto out;
+	}
+
+	/* update health struct with various flags derived from health bitmap */
+	payload->health = (struct nd_papr_pdsm_health) {
+		.extension_flags = 0,
+		.dimm_unarmed = !!(p->health_bitmap & PAPR_PMEM_UNARMED_MASK),
+		.dimm_bad_shutdown = !!(p->health_bitmap & PAPR_PMEM_BAD_SHUTDOWN_MASK),
+		.dimm_bad_restore = !!(p->health_bitmap & PAPR_PMEM_BAD_RESTORE_MASK),
+		.dimm_scrubbed = !!(p->health_bitmap & PAPR_PMEM_SCRUBBED_AND_LOCKED),
+		.dimm_locked = !!(p->health_bitmap & PAPR_PMEM_SCRUBBED_AND_LOCKED),
+		.dimm_encrypted = !!(p->health_bitmap & PAPR_PMEM_ENCRYPTED),
+		.dimm_health = PAPR_PDSM_DIMM_HEALTHY,
+	};
+
+	/* Update field dimm_health based on health_bitmap flags */
+	if (p->health_bitmap & PAPR_PMEM_HEALTH_FATAL)
+		payload->health.dimm_health = PAPR_PDSM_DIMM_FATAL;
+	else if (p->health_bitmap & PAPR_PMEM_HEALTH_CRITICAL)
+		payload->health.dimm_health = PAPR_PDSM_DIMM_CRITICAL;
+	else if (p->health_bitmap & PAPR_PMEM_HEALTH_UNHEALTHY)
+		payload->health.dimm_health = PAPR_PDSM_DIMM_UNHEALTHY;
+
+	/* struct populated hence can release the mutex now */
+	mutex_unlock(&p->health_mutex);
+	rc = sizeof(struct nd_papr_pdsm_health);
+
+out:
+	return rc;
+}
+
+/*
+ * 'struct pdsm_cmd_desc'
+ * Identifies supported PDSMs' expected length of in/out payloads
+ * and pdsm service function.
+ *
+ * size_in	: Size of input payload if any in the PDSM request.
+ * size_out	: Size of output payload if any in the PDSM request.
+ * service	: Service function for the PDSM request. Return semantics:
+ *		  rc < 0 : Error servicing PDSM and rc indicates the error.
+ *		  rc >=0 : Serviced successfully and 'rc' indicate number of
+ *			bytes written to payload.
+ */
+struct pdsm_cmd_desc {
+	u32 size_in;
+	u32 size_out;
+	int (*service)(struct papr_scm_priv *dimm,
+		       union nd_pdsm_payload *payload);
+};
+
+/* Holds all supported PDSMs' command descriptors */
+static const struct pdsm_cmd_desc __pdsm_cmd_descriptors[] = {
+	[PAPR_PDSM_MIN] = {
+		.size_in = 0,
+		.size_out = 0,
+		.service = NULL,
+	},
+	/* New PDSM command descriptors to be added below */
+
+	[PAPR_PDSM_HEALTH] = {
+		.size_in = 0,
+		.size_out = sizeof(struct nd_papr_pdsm_health),
+		.service = papr_pdsm_health,
+	},
+	/* Empty */
+	[PAPR_PDSM_MAX] = {
+		.size_in = 0,
+		.size_out = 0,
+		.service = NULL,
+	},
+};
+
+/* Given a valid pdsm cmd return its command descriptor else return NULL */
+static inline const struct pdsm_cmd_desc *pdsm_cmd_desc(enum papr_pdsm cmd)
+{
+	if (cmd >= 0 || cmd < ARRAY_SIZE(__pdsm_cmd_descriptors))
+		return &__pdsm_cmd_descriptors[cmd];
+
+	return NULL;
+}
+
+/*
+ * For a given pdsm request call an appropriate service function.
+ * Returns errors if any while handling the pdsm command package.
+ */
+static int papr_scm_service_pdsm(struct papr_scm_priv *p,
+				 struct nd_cmd_pkg *pkg)
+{
+	/* Get the PDSM header and PDSM command */
+	struct nd_pkg_pdsm *pdsm_pkg = (struct nd_pkg_pdsm *)pkg->nd_payload;
+	enum papr_pdsm pdsm = (enum papr_pdsm)pkg->nd_command;
+	const struct pdsm_cmd_desc *pdsc;
+	int rc;
+
+	/* Fetch corresponding pdsm descriptor for validation and servicing */
+	pdsc = pdsm_cmd_desc(pdsm);
+
+	/* Validate pdsm descriptor */
+	/* Ensure that reserved fields are 0 */
+	if (pdsm_pkg->reserved[0] || pdsm_pkg->reserved[1]) {
+		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid reserved field\n",
+			pdsm);
+		return -EINVAL;
+	}
+
+	/* If pdsm expects some input, then ensure that the size_in matches */
+	if (pdsc->size_in &&
+	    pkg->nd_size_in != (pdsc->size_in + ND_PDSM_HDR_SIZE)) {
+		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Mismatched size_in=%d\n",
+			pdsm, pkg->nd_size_in);
+		return -EINVAL;
+	}
+
+	/* If pdsm wants to return data, then ensure that  size_out matches */
+	if (pdsc->size_out &&
+	    pkg->nd_size_out != (pdsc->size_out + ND_PDSM_HDR_SIZE)) {
+		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Mismatched size_out=%d\n",
+			pdsm, pkg->nd_size_out);
+		return -EINVAL;
+	}
+
+	/* Service the pdsm */
+	if (pdsc->service) {
+		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Servicing..\n", pdsm);
+
+		rc = pdsc->service(p, &pdsm_pkg->payload);
+
+		if (rc < 0) {
+			/* error encountered while servicing pdsm */
+			pdsm_pkg->cmd_status = rc;
+			pkg->nd_fw_size = ND_PDSM_HDR_SIZE;
+		} else {
+			/* pdsm serviced and 'rc' bytes written to payload */
+			pdsm_pkg->cmd_status = 0;
+			pkg->nd_fw_size = ND_PDSM_HDR_SIZE + rc;
+		}
+	} else {
+		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Unsupported PDSM request\n",
+			pdsm);
+		pdsm_pkg->cmd_status = -ENOENT;
+		pkg->nd_fw_size = ND_PDSM_HDR_SIZE;
+	}
+
+	return pdsm_pkg->cmd_status;
+}
+
 static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
 			  struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 			  unsigned int buf_len, int *cmd_rc)
 {
 	struct nd_cmd_get_config_size *get_size_hdr;
+	struct nd_cmd_pkg *call_pkg = NULL;
 	struct papr_scm_priv *p;
+	int rc;
 
-	/* Only dimm-specific calls are supported atm */
-	if (!nvdimm)
-		return -EINVAL;
+	rc = is_cmd_valid(nvdimm, cmd, buf, buf_len);
+	if (rc) {
+		pr_debug("Invalid cmd=0x%x. Err=%d\n", cmd, rc);
+		return rc;
+	}
+
+	/* Use a local variable in case cmd_rc pointer is NULL */
+	if (!cmd_rc)
+		cmd_rc = &rc;
 
 	p = nvdimm_provider_data(nvdimm);
 
@@ -277,7 +616,13 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
 		*cmd_rc = papr_scm_meta_set(p, buf);
 		break;
 
+	case ND_CMD_CALL:
+		call_pkg = (struct nd_cmd_pkg *)buf;
+		*cmd_rc = papr_scm_service_pdsm(p, call_pkg);
+		break;
+
 	default:
+		dev_dbg(&p->pdev->dev, "Unknown command = %d\n", cmd);
 		return -EINVAL;
 	}
 
@@ -286,6 +631,64 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
 	return 0;
 }
 
+static ssize_t flags_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *dimm = to_nvdimm(dev);
+	struct papr_scm_priv *p = nvdimm_provider_data(dimm);
+	struct seq_buf s;
+	u64 health;
+	int rc;
+
+	rc = drc_pmem_query_health(p);
+	if (rc)
+		return rc;
+
+	/* Copy health_bitmap locally, check masks & update out buffer */
+	health = READ_ONCE(p->health_bitmap);
+
+	seq_buf_init(&s, buf, PAGE_SIZE);
+	if (health & PAPR_PMEM_UNARMED_MASK)
+		seq_buf_printf(&s, "not_armed ");
+
+	if (health & PAPR_PMEM_BAD_SHUTDOWN_MASK)
+		seq_buf_printf(&s, "flush_fail ");
+
+	if (health & PAPR_PMEM_BAD_RESTORE_MASK)
+		seq_buf_printf(&s, "restore_fail ");
+
+	if (health & PAPR_PMEM_ENCRYPTED)
+		seq_buf_printf(&s, "encrypted ");
+
+	if (health & PAPR_PMEM_SMART_EVENT_MASK)
+		seq_buf_printf(&s, "smart_notify ");
+
+	if (health & PAPR_PMEM_SCRUBBED_AND_LOCKED)
+		seq_buf_printf(&s, "scrubbed locked ");
+
+	if (seq_buf_used(&s))
+		seq_buf_printf(&s, "\n");
+
+	return seq_buf_used(&s);
+}
+DEVICE_ATTR_RO(flags);
+
+/* papr_scm specific dimm attributes */
+static struct attribute *papr_nd_attributes[] = {
+	&dev_attr_flags.attr,
+	NULL,
+};
+
+static struct attribute_group papr_nd_attribute_group = {
+	.name = "papr",
+	.attrs = papr_nd_attributes,
+};
+
+static const struct attribute_group *papr_nd_attr_groups[] = {
+	&papr_nd_attribute_group,
+	NULL,
+};
+
 static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 {
 	struct device *dev = &p->pdev->dev;
@@ -312,8 +715,8 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	dimm_flags = 0;
 	set_bit(NDD_LABELING, &dimm_flags);
 
-	p->nvdimm = nvdimm_create(p->bus, p, NULL, dimm_flags,
-				  PAPR_SCM_DIMM_CMD_MASK, 0, NULL);
+	p->nvdimm = nvdimm_create(p->bus, p, papr_nd_attr_groups,
+				  dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL);
 	if (!p->nvdimm) {
 		dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn);
 		goto err;
@@ -399,6 +802,9 @@ static int papr_scm_probe(struct platform_device *pdev)
 	if (!p)
 		return -ENOMEM;
 
+	/* Initialize the dimm mutex */
+	mutex_init(&p->health_mutex);
+
 	/* optional DT properties */
 	of_property_read_u32(dn, "ibm,metadata-size", &metadata_size);
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 2db8469e475f..27094c872fd6 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -70,6 +70,7 @@
 #include <asm/idle.h>
 #include <asm/swiotlb.h>
 #include <asm/svm.h>
+#include <asm/dtl.h>
 
 #include "pseries.h"
 #include "../../../../drivers/pci/pci.h"
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index 40c0637203d5..e6d7a344d9f2 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -11,6 +11,7 @@
 #include <asm/svm.h>
 #include <asm/swiotlb.h>
 #include <asm/ultravisor.h>
+#include <asm/dtl.h>
 
 static int __init init_svm(void)
 {
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 4a8874bc1057..040b9d01c079 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1066,10 +1066,10 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs)
 
 	if (is_in_pci_mem_space(addr)) {
 		if (user_mode(regs))
-			ret = probe_user_read(&inst, (void __user *)regs->nip,
-					      sizeof(inst));
+			ret = copy_from_user_nofault(&inst,
+					(void __user *)regs->nip, sizeof(inst));
 		else
-			ret = probe_kernel_address((void *)regs->nip, inst);
+			ret = get_kernel_nofault(inst, (void *)regs->nip);
 
 		if (!ret && mcheck_handle_load(regs, inst)) {
 			regs->nip += 4;
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 128192e14ff2..3230c1d48562 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -23,6 +23,8 @@ config RISCV
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU
+	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
+	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 96f95c9ebd97..400a8c8b6de7 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define __atomic_acquire_fence()					\
 	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
 
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 3f1737f301cc..d0e24aaa2aa0 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -58,8 +58,16 @@ do {									\
  * The AQ/RL pair provides a RCpc critical section, but there's not really any
  * way we can take advantage of that here because the ordering is only enforced
  * on that one lock.  Thus, we're just doing a full fence.
+ *
+ * Since we allow writeX to be called from preemptive regions we need at least
+ * an "o" in the predecessor set to ensure device writes are visible before the
+ * task is marked as available for scheduling on a new hart.  While I don't see
+ * any concrete reason we need a full IO fence, it seems safer to just upgrade
+ * this in order to avoid any IO crossing a scheduling boundary.  In both
+ * instances the scheduler pairs this with an mb(), so nothing is necessary on
+ * the new hart.
  */
-#define smp_mb__after_spinlock()	RISCV_FENCE(rw,rw)
+#define smp_mb__after_spinlock()	RISCV_FENCE(iorw,iorw)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index d969bab4a26b..262e5bbb2776 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -179,7 +179,7 @@
 			"	bnez %1, 0b\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -224,7 +224,7 @@
 			RISCV_ACQUIRE_BARRIER				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -270,7 +270,7 @@
 			"	bnez %1, 0b\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -316,7 +316,7 @@
 			"	fence rw, rw\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
diff --git a/arch/riscv/include/asm/gdb_xml.h b/arch/riscv/include/asm/gdb_xml.h
index 041b45f5b997..09342111f227 100644
--- a/arch/riscv/include/asm/gdb_xml.h
+++ b/arch/riscv/include/asm/gdb_xml.h
@@ -3,8 +3,7 @@
 #ifndef __ASM_GDB_XML_H_
 #define __ASM_GDB_XML_H_
 
-#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature
-static const char riscv_gdb_stub_feature[64] =
+const char riscv_gdb_stub_feature[64] =
 			"PacketSize=800;qXfer:features:read+;";
 
 static const char gdb_xfer_read_target[31] = "qXfer:features:read:target.xml:";
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 8177a457caff..46677daf708b 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,7 +19,6 @@
 
 #ifndef	__ASSEMBLY__
 
-extern int kgdb_has_hit_break(unsigned long addr);
 extern unsigned long kgdb_compiled_break;
 
 static inline void arch_kgdb_breakpoint(void)
@@ -106,7 +105,9 @@ static inline void arch_kgdb_breakpoint(void)
 #define DBG_REG_BADADDR_OFF 34
 #define DBG_REG_CAUSE_OFF 35
 
-#include <asm/gdb_xml.h>
+extern const char riscv_gdb_stub_feature[64];
+
+#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature
 
 #endif
 #endif
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 1dd12a0cbb2b..464a2bbc97ea 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -12,7 +12,11 @@
 #include <linux/const.h>
 
 /* thread information allocation */
+#ifdef CONFIG_64BIT
+#define THREAD_SIZE_ORDER	(2)
+#else
 #define THREAD_SIZE_ORDER	(1)
+#endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
index c8e818688ec1..3099362d9f26 100644
--- a/arch/riscv/include/asm/vdso/gettimeofday.h
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -4,6 +4,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 #include <asm/csr.h>
 #include <uapi/linux/time.h>
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 08396614d6f4..2ff63d0cbb50 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -38,7 +38,8 @@ static int ftrace_check_current_call(unsigned long hook_pos,
 	 * Read the text we want to modify;
 	 * return must be -EFAULT on read error
 	 */
-	if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)hook_pos,
+			MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/*
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index f16ade84a11f..963ed7edcff2 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -44,25 +44,25 @@ DECLARE_INSN(c_beqz, MATCH_C_BEQZ, MASK_C_BEQZ)
 DECLARE_INSN(c_bnez, MATCH_C_BNEZ, MASK_C_BNEZ)
 DECLARE_INSN(sret, MATCH_SRET, MASK_SRET)
 
-int decode_register_index(unsigned long opcode, int offset)
+static int decode_register_index(unsigned long opcode, int offset)
 {
 	return (opcode >> offset) & 0x1F;
 }
 
-int decode_register_index_short(unsigned long opcode, int offset)
+static int decode_register_index_short(unsigned long opcode, int offset)
 {
 	return ((opcode >> offset) & 0x7) + 8;
 }
 
 /* Calculate the new address for after a step */
-int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
+static int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
 {
 	unsigned long pc = regs->epc;
 	unsigned long *regs_ptr = (unsigned long *)regs;
 	unsigned int rs1_num, rs2_num;
 	int op_code;
 
-	if (probe_kernel_address((void *)pc, op_code))
+	if (get_kernel_nofault(op_code, (void *)pc))
 		return -EINVAL;
 	if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) {
 		if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) {
@@ -136,7 +136,7 @@ int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
 	return 0;
 }
 
-int do_single_step(struct pt_regs *regs)
+static int do_single_step(struct pt_regs *regs)
 {
 	/* Determine where the target instruction will send us to */
 	unsigned long addr = 0;
@@ -146,14 +146,14 @@ int do_single_step(struct pt_regs *regs)
 		return error;
 
 	/* Store the op code in the stepped address */
-	error = probe_kernel_address((void *)addr, stepped_opcode);
+	error = get_kernel_nofault(stepped_opcode, (void *)addr);
 	if (error)
 		return error;
 
 	stepped_address = addr;
 
 	/* Replace the op code with the break instruction */
-	error = probe_kernel_write((void *)stepped_address,
+	error = copy_to_kernel_nofault((void *)stepped_address,
 				   arch_kgdb_ops.gdb_bpt_instr,
 				   BREAK_INSTR_SIZE);
 	/* Flush and return */
@@ -173,7 +173,7 @@ int do_single_step(struct pt_regs *regs)
 static void undo_single_step(struct pt_regs *regs)
 {
 	if (stepped_opcode != 0) {
-		probe_kernel_write((void *)stepped_address,
+		copy_to_kernel_nofault((void *)stepped_address,
 				   (void *)&stepped_opcode, BREAK_INSTR_SIZE);
 		flush_icache_range(stepped_address,
 				   stepped_address + BREAK_INSTR_SIZE);
@@ -320,7 +320,7 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code,
 	return err;
 }
 
-int kgdb_riscv_kgdbbreak(unsigned long addr)
+static int kgdb_riscv_kgdbbreak(unsigned long addr)
 {
 	if (stepped_address == addr)
 		return KGDB_SW_SINGLE_STEP;
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index d4a64dfed342..3fe7a5296aa5 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -63,7 +63,7 @@ static int patch_insn_write(void *addr, const void *insn, size_t len)
 
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
-	ret = probe_kernel_write(waddr, insn, len);
+	ret = copy_to_kernel_nofault(waddr, insn, len);
 
 	patch_unmap(FIX_TEXT_POKE0);
 
@@ -76,7 +76,7 @@ NOKPROBE_SYMBOL(patch_insn_write);
 #else
 static int patch_insn_write(void *addr, const void *insn, size_t len)
 {
-	return probe_kernel_write(addr, insn, len);
+	return copy_to_kernel_nofault(addr, insn, len);
 }
 NOKPROBE_SYMBOL(patch_insn_write);
 #endif /* CONFIG_MMU */
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index f3619f59d85c..12f8a7fce78b 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -8,6 +8,7 @@
 #include <linux/syscalls.h>
 #include <asm/unistd.h>
 #include <asm/cacheflush.h>
+#include <asm-generic/mman-common.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -16,6 +17,11 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 {
 	if (unlikely(offset & (~PAGE_MASK >> page_shift_offset)))
 		return -EINVAL;
+
+	if ((prot & PROT_WRITE) && (prot & PROT_EXEC))
+		if (unlikely(!(prot & PROT_READ)))
+			return -EINVAL;
+
 	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
 			       offset >> (PAGE_SHIFT - page_shift_offset));
 }
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index ecec1778e3a4..7d95cce5e47c 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -137,7 +137,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 {
 	bug_insn_t insn;
 
-	if (probe_kernel_address((bug_insn_t *)pc, insn))
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
 		return 0;
 
 	return GET_INSN_LENGTH(insn);
@@ -165,7 +165,7 @@ int is_valid_bugaddr(unsigned long pc)
 
 	if (pc < VMALLOC_START)
 		return 0;
-	if (probe_kernel_address((bug_insn_t *)pc, insn))
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
 		return 0;
 	if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
 		return (insn == __BUG_INSN_32);
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 38ba55b0eb9d..e4c7c2c8a02f 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -17,7 +17,7 @@ vdso-syms += flush_icache
 obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
 ifneq ($(c-gettimeofday-y),)
-  CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+  CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
 endif
 
 # Build rules
@@ -27,6 +27,9 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 obj-y += vdso.o vdso-syms.o
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 
+# Disable -pg to prevent insert call site
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
index d264943e2e47..cc0d80699c31 100644
--- a/arch/riscv/kernel/vdso/vgettimeofday.c
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -9,16 +9,22 @@
 #include <linux/time.h>
 #include <linux/types.h>
 
+extern
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
+extern
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
+extern
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
 int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f4adb3684f3d..79e9d55bdf1a 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -95,19 +95,40 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 static void __init setup_initrd(void)
 {
+	phys_addr_t start;
 	unsigned long size;
 
-	if (initrd_start >= initrd_end) {
-		pr_info("initrd not found or empty");
+	/* Ignore the virtul address computed during device tree parsing */
+	initrd_start = initrd_end = 0;
+
+	if (!phys_initrd_size)
+		return;
+	/*
+	 * Round the memory region to page boundaries as per free_initrd_mem()
+	 * This allows us to detect whether the pages overlapping the initrd
+	 * are in use, but more importantly, reserves the entire set of pages
+	 * as we don't want these pages allocated for other purposes.
+	 */
+	start = round_down(phys_initrd_start, PAGE_SIZE);
+	size = phys_initrd_size + (phys_initrd_start - start);
+	size = round_up(size, PAGE_SIZE);
+
+	if (!memblock_is_region_memory(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region",
+		       (u64)start, size);
 		goto disable;
 	}
-	if (__pa_symbol(initrd_end) > PFN_PHYS(max_low_pfn)) {
-		pr_err("initrd extends beyond end of memory");
+
+	if (memblock_is_region_reserved(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n",
+		       (u64)start, size);
 		goto disable;
 	}
 
-	size = initrd_end - initrd_start;
-	memblock_reserve(__pa_symbol(initrd_start), size);
+	memblock_reserve(start, size);
+	/* Now convert initrd to virtual addresses */
+	initrd_start = (unsigned long)__va(phys_initrd_start);
+	initrd_end = initrd_start + phys_initrd_size;
 	initrd_below_start_ok = 1;
 
 	pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
@@ -126,33 +147,36 @@ void __init setup_bootmem(void)
 {
 	struct memblock_region *reg;
 	phys_addr_t mem_size = 0;
+	phys_addr_t total_mem = 0;
+	phys_addr_t mem_start, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
 
 	/* Find the memory region containing the kernel */
 	for_each_memblock(memory, reg) {
-		phys_addr_t end = reg->base + reg->size;
-
-		if (reg->base <= vmlinux_start && vmlinux_end <= end) {
-			mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
-
-			/*
-			 * Remove memblock from the end of usable area to the
-			 * end of region
-			 */
-			if (reg->base + mem_size < end)
-				memblock_remove(reg->base + mem_size,
-						end - reg->base - mem_size);
-		}
+		end = reg->base + reg->size;
+		if (!total_mem)
+			mem_start = reg->base;
+		if (reg->base <= vmlinux_start && vmlinux_end <= end)
+			BUG_ON(reg->size == 0);
+		total_mem = total_mem + reg->size;
 	}
-	BUG_ON(mem_size == 0);
+
+	/*
+	 * Remove memblock from the end of usable area to the
+	 * end of region
+	 */
+	mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET);
+	if (mem_start + mem_size < end)
+		memblock_remove(mem_start + mem_size,
+				end - mem_start - mem_size);
 
 	/* Reserve from the start of the kernel to the end of the kernel */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
-	set_max_mapnr(PFN_DOWN(mem_size));
 	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
 	max_low_pfn = max_pfn;
+	set_max_mapnr(max_low_pfn);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 4a8b61806633..87b4ab3d3c77 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -44,7 +44,7 @@ asmlinkage void __init kasan_early_init(void)
 				(__pa(((uintptr_t) kasan_early_shadow_pmd))),
 				__pgprot(_PAGE_TABLE)));
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
 static void __init populate(void *start, void *end)
@@ -79,7 +79,7 @@ static void __init populate(void *start, void *end)
 			pfn_pgd(PFN_DOWN(__pa(&pmd[offset])),
 				__pgprot(_PAGE_TABLE)));
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 	memset(start, 0, end - start);
 }
 
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index ec2c70f84994..289a9a5ea5b5 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -151,6 +151,7 @@ int set_memory_nx(unsigned long addr, int numpages)
 
 int set_direct_map_invalid_noflush(struct page *page)
 {
+	int ret;
 	unsigned long start = (unsigned long)page_address(page);
 	unsigned long end = start + PAGE_SIZE;
 	struct pageattr_masks masks = {
@@ -158,11 +159,16 @@ int set_direct_map_invalid_noflush(struct page *page)
 		.clear_mask = __pgprot(_PAGE_PRESENT)
 	};
 
-	return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+	mmap_read_lock(&init_mm);
+	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+	mmap_read_unlock(&init_mm);
+
+	return ret;
 }
 
 int set_direct_map_default_noflush(struct page *page)
 {
+	int ret;
 	unsigned long start = (unsigned long)page_address(page);
 	unsigned long end = start + PAGE_SIZE;
 	struct pageattr_masks masks = {
@@ -170,7 +176,11 @@ int set_direct_map_default_noflush(struct page *page)
 		.clear_mask = __pgprot(0)
 	};
 
-	return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+	mmap_read_lock(&init_mm);
+	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+	mmap_read_unlock(&init_mm);
+
+	return ret;
 }
 
 void __kernel_map_pages(struct page *page, int numpages, int enable)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 194824932a60..9cfd8de907cb 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -102,7 +102,6 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_BH
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
-	select ARCH_KEEP_MEMBLOCK
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING
@@ -126,6 +125,7 @@ config S390
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN
 	select HAVE_ARCH_KASAN_VMALLOC
+	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
 	select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_SOFT_DIRTY
@@ -145,6 +145,7 @@ config S390
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FENTRY
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
@@ -462,6 +463,7 @@ config NUMA
 
 config NODES_SHIFT
 	int
+	depends on NEED_MULTIPLE_NODES
 	default "1"
 
 config SCHED_SMT
@@ -625,10 +627,6 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	def_bool y
 
-config FORCE_MAX_ZONEORDER
-	int
-	default "9"
-
 config MAX_PHYSMEM_BITS
 	int "Maximum size of supported physical memory in bits (42-53)"
 	range 42 53
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 5503217366ec..a363d30ce739 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -129,8 +129,7 @@ static void appldata_get_os_data(void *data)
 
 	os_data->nr_cpus = j;
 
-	new_size = sizeof(struct appldata_os_data) +
-		   (os_data->nr_cpus * sizeof(struct appldata_os_per_cpu));
+	new_size = struct_size(os_data, os_cpu, os_data->nr_cpus);
 	if (ops.size != new_size) {
 		if (ops.active) {
 			rc = appldata_diag(APPLDATA_RECORD_OS_ID,
@@ -165,8 +164,7 @@ static int __init appldata_os_init(void)
 {
 	int rc, max_size;
 
-	max_size = sizeof(struct appldata_os_data) +
-		   (num_possible_cpus() * sizeof(struct appldata_os_per_cpu));
+	max_size = struct_size(appldata_os_data, os_cpu, num_possible_cpus());
 	if (max_size > APPLDATA_MAX_REC_SIZE) {
 		pr_err("Maximum OS record size %i exceeds the maximum "
 		       "record size %i\n", max_size, APPLDATA_MAX_REC_SIZE);
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 46038bc58c9e..0cf9a82326a8 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -1,5 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_WATCH_QUEUE=y
 CONFIG_AUDIT=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -14,7 +15,6 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
@@ -31,9 +31,9 @@ CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
-CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
+CONFIG_BPF_LSM=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
@@ -51,14 +51,11 @@ CONFIG_CHSC_SCH=y
 CONFIG_VFIO_CCW=m
 CONFIG_VFIO_AP=m
 CONFIG_CRASH_DUMP=y
-CONFIG_HIBERNATION=y
-CONFIG_PM_DEBUG=y
 CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
 CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
-CONFIG_VHOST_NET=m
-CONFIG_VHOST_VSOCK=m
+CONFIG_S390_UNWIND_SELFTEST=y
 CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
@@ -77,6 +74,8 @@ CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
 CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_INLINE_ENCRYPTION=y
+CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_BSD_DISKLABEL=y
@@ -96,7 +95,6 @@ CONFIG_CMA_DEBUG=y
 CONFIG_CMA_DEBUGFS=y
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
-CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
@@ -130,6 +128,7 @@ CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESPINTCP=y
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
@@ -144,6 +143,7 @@ CONFIG_TCP_CONG_ILLINOIS=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESPINTCP=y
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
 CONFIG_IPV6_VTI=m
@@ -151,7 +151,10 @@ CONFIG_IPV6_SIT=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
+CONFIG_IPV6_RPL_LWTUNNEL=y
+CONFIG_MPTCP=y
 CONFIG_NETFILTER=y
+CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
@@ -317,6 +320,7 @@ CONFIG_L2TP_V3=y
 CONFIG_L2TP_IP=m
 CONFIG_L2TP_ETH=m
 CONFIG_BRIDGE=m
+CONFIG_BRIDGE_MRP=y
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y
 CONFIG_NET_SCHED=y
@@ -341,6 +345,7 @@ CONFIG_NET_SCH_CODEL=m
 CONFIG_NET_SCH_FQ_CODEL=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_SCH_PLUG=m
+CONFIG_NET_SCH_ETS=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
@@ -364,6 +369,7 @@ CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_GATE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_OPENVSWITCH=m
 CONFIG_VSOCKETS=m
@@ -374,6 +380,7 @@ CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
 # CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
+# CONFIG_PCIEASPM is not set
 CONFIG_PCI_DEBUG=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
@@ -435,6 +442,7 @@ CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
 CONFIG_DM_MULTIPATH_ST=m
+CONFIG_DM_MULTIPATH_HST=m
 CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
@@ -448,6 +456,8 @@ CONFIG_EQUALIZER=m
 CONFIG_IFB=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
+CONFIG_VXLAN=m
+CONFIG_BAREUDP=m
 CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
@@ -481,7 +491,6 @@ CONFIG_NLMON=m
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
 CONFIG_MLX5_CORE_EN=y
-# CONFIG_MLXFW is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_MICROCHIP is not set
 # CONFIG_NET_VENDOR_MICROSEMI is not set
@@ -514,6 +523,7 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_TI is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_NET_VENDOR_XILINX is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -561,6 +571,8 @@ CONFIG_VFIO_MDEV_DEVICE=m
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -608,6 +620,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_NTFS_FS=m
 CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
@@ -650,8 +663,8 @@ CONFIG_NLS_UTF8=m
 CONFIG_DLM=m
 CONFIG_UNICODE=y
 CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_FORTIFY_SOURCE=y
@@ -675,8 +688,11 @@ CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_CURVE25519=m
+CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -685,6 +701,7 @@ CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
+CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
@@ -701,6 +718,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -719,6 +737,9 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_STATS=y
+CONFIG_CRYPTO_LIB_BLAKE2S=m
+CONFIG_CRYPTO_LIB_CURVE25519=m
+CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
@@ -774,6 +795,7 @@ CONFIG_DEBUG_SHIRQ=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_WQ_WATCHDOG=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_DEBUG_TIMEKEEPING=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
@@ -786,7 +808,9 @@ CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=300
+# CONFIG_RCU_TRACE is not set
 CONFIG_LATENCYTOP=y
+CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
 CONFIG_IRQSOFF_TRACER=y
@@ -808,10 +832,12 @@ CONFIG_FAULT_INJECTION_DEBUG_FS=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LKDTM=m
 CONFIG_TEST_LIST_SORT=y
+CONFIG_TEST_MIN_HEAP=y
 CONFIG_TEST_SORT=y
 CONFIG_KPROBES_SANITY_TEST=y
 CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 7cd0648c1f4e..5df9759e8ff6 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -1,5 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_WATCH_QUEUE=y
 CONFIG_AUDIT=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -13,7 +14,6 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
@@ -30,9 +30,9 @@ CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
-CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
+CONFIG_BPF_LSM=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
@@ -41,7 +41,6 @@ CONFIG_LIVEPATCH=y
 CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
-# CONFIG_NUMA_EMU is not set
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
@@ -51,14 +50,11 @@ CONFIG_CHSC_SCH=y
 CONFIG_VFIO_CCW=m
 CONFIG_VFIO_AP=m
 CONFIG_CRASH_DUMP=y
-CONFIG_HIBERNATION=y
-CONFIG_PM_DEBUG=y
 CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
 CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
-CONFIG_VHOST_NET=m
-CONFIG_VHOST_VSOCK=m
+CONFIG_S390_UNWIND_SELFTEST=m
 CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
@@ -74,6 +70,8 @@ CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
 CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_INLINE_ENCRYPTION=y
+CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_BSD_DISKLABEL=y
@@ -91,7 +89,6 @@ CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
-CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
@@ -125,6 +122,7 @@ CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESPINTCP=y
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
@@ -139,6 +137,7 @@ CONFIG_TCP_CONG_ILLINOIS=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESPINTCP=y
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
 CONFIG_IPV6_VTI=m
@@ -146,7 +145,10 @@ CONFIG_IPV6_SIT=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
+CONFIG_IPV6_RPL_LWTUNNEL=y
+CONFIG_MPTCP=y
 CONFIG_NETFILTER=y
+CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
@@ -311,6 +313,7 @@ CONFIG_L2TP_V3=y
 CONFIG_L2TP_IP=m
 CONFIG_L2TP_ETH=m
 CONFIG_BRIDGE=m
+CONFIG_BRIDGE_MRP=y
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y
 CONFIG_NET_SCHED=y
@@ -335,6 +338,7 @@ CONFIG_NET_SCH_CODEL=m
 CONFIG_NET_SCH_FQ_CODEL=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_SCH_PLUG=m
+CONFIG_NET_SCH_ETS=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
@@ -358,6 +362,7 @@ CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_GATE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_OPENVSWITCH=m
 CONFIG_VSOCKETS=m
@@ -368,6 +373,7 @@ CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
 # CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
+# CONFIG_PCIEASPM is not set
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_UEVENT_HELPER=y
@@ -430,6 +436,7 @@ CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
 CONFIG_DM_MULTIPATH_ST=m
+CONFIG_DM_MULTIPATH_HST=m
 CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
@@ -444,6 +451,8 @@ CONFIG_EQUALIZER=m
 CONFIG_IFB=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
+CONFIG_VXLAN=m
+CONFIG_BAREUDP=m
 CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
@@ -477,7 +486,6 @@ CONFIG_NLMON=m
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
 CONFIG_MLX5_CORE_EN=y
-# CONFIG_MLXFW is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_MICROCHIP is not set
 # CONFIG_NET_VENDOR_MICROSEMI is not set
@@ -510,6 +518,7 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_TI is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_NET_VENDOR_XILINX is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -557,6 +566,8 @@ CONFIG_VFIO_MDEV_DEVICE=m
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -600,6 +611,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_NTFS_FS=m
 CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
@@ -642,8 +654,8 @@ CONFIG_NLS_UTF8=m
 CONFIG_DLM=m
 CONFIG_UNICODE=y
 CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_SECURITY_SELINUX=y
@@ -667,8 +679,11 @@ CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_CURVE25519=m
+CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
@@ -678,6 +693,7 @@ CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
+CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
@@ -694,6 +710,7 @@ CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -712,6 +729,9 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_STATS=y
+CONFIG_CRYPTO_LIB_BLAKE2S=m
+CONFIG_CRYPTO_LIB_CURVE25519=m
+CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
@@ -725,6 +745,7 @@ CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CORDIC=m
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC4=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
@@ -739,10 +760,12 @@ CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=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_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
+CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
 CONFIG_SCHED_TRACER=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 20c51e5d9353..4091c50449cd 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -30,6 +30,7 @@ CONFIG_IBM_PARTITION=y
 # CONFIG_BOUNCE is not set
 CONFIG_NET=y
 # CONFIG_IUCV is not set
+# CONFIG_ETHTOOL_NETLINK is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_RAM=y
 # CONFIG_BLK_DEV_XPRAM is not set
@@ -55,6 +56,8 @@ CONFIG_RAW_DRIVER=y
 # CONFIG_MONWRITER is not set
 # CONFIG_S390_VMUR is not set
 # CONFIG_HID is not set
+# CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
@@ -62,7 +65,9 @@ CONFIG_CONFIGFS_FS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
+# CONFIG_ZLIB_DFLTCC is not set
 CONFIG_PRINTK_TIME=y
+# CONFIG_SYMBOLIC_ERRNAME is not set
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index d977643fa627..e1ae23911ccd 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -693,7 +693,7 @@ static ssize_t prng_chunksize_show(struct device *dev,
 				   struct device_attribute *attr,
 				   char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size);
+	return scnprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size);
 }
 static DEVICE_ATTR(chunksize, 0444, prng_chunksize_show, NULL);
 
@@ -712,7 +712,7 @@ static ssize_t prng_counter_show(struct device *dev,
 		counter = prng_data->prngws.byte_counter;
 	mutex_unlock(&prng_data->mutex);
 
-	return snprintf(buf, PAGE_SIZE, "%llu\n", counter);
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", counter);
 }
 static DEVICE_ATTR(byte_counter, 0444, prng_counter_show, NULL);
 
@@ -721,7 +721,7 @@ static ssize_t prng_errorflag_show(struct device *dev,
 				   struct device_attribute *attr,
 				   char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag);
+	return scnprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag);
 }
 static DEVICE_ATTR(errorflag, 0444, prng_errorflag_show, NULL);
 
@@ -731,9 +731,9 @@ static ssize_t prng_mode_show(struct device *dev,
 			      char *buf)
 {
 	if (prng_mode == PRNG_MODE_TDES)
-		return snprintf(buf, PAGE_SIZE, "TDES\n");
+		return scnprintf(buf, PAGE_SIZE, "TDES\n");
 	else
-		return snprintf(buf, PAGE_SIZE, "SHA512\n");
+		return scnprintf(buf, PAGE_SIZE, "SHA512\n");
 }
 static DEVICE_ATTR(mode, 0444, prng_mode_show, NULL);
 
@@ -756,7 +756,7 @@ static ssize_t prng_reseed_limit_show(struct device *dev,
 				      struct device_attribute *attr,
 				      char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit);
+	return scnprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit);
 }
 static ssize_t prng_reseed_limit_store(struct device *dev,
 				       struct device_attribute *attr,
@@ -787,7 +787,7 @@ static ssize_t prng_strength_show(struct device *dev,
 				  struct device_attribute *attr,
 				  char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "256\n");
+	return scnprintf(buf, PAGE_SIZE, "256\n");
 }
 static DEVICE_ATTR(strength, 0444, prng_strength_show, NULL);
 
diff --git a/arch/s390/include/asm/asm-const.h b/arch/s390/include/asm/asm-const.h
new file mode 100644
index 000000000000..11f615eb0066
--- /dev/null
+++ b/arch/s390/include/asm/asm-const.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_ASM_CONST_H
+#define _ASM_S390_ASM_CONST_H
+
+#ifdef __ASSEMBLY__
+#  define stringify_in_c(...)	__VA_ARGS__
+#else
+/* This version of stringify will deal with commas... */
+#  define __stringify_in_c(...)	#__VA_ARGS__
+#  define stringify_in_c(...)	__stringify_in_c(__VA_ARGS__) " "
+#endif
+#endif /* _ASM_S390_ASM_CONST_H */
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 491ad53a0d4e..cae473a7b6f7 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,8 +15,6 @@
 #include <asm/barrier.h>
 #include <asm/cmpxchg.h>
 
-#define ATOMIC_INIT(i)  { (i) }
-
 static inline int atomic_read(const atomic_t *v)
 {
 	int c;
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index 310134015541..17a26261f288 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -12,7 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/time.h>
 #include <linux/refcount.h>
-#include <uapi/asm/debug.h>
+#include <linux/fs.h>
 
 #define DEBUG_MAX_LEVEL		   6  /* debug levels range from 0 to 6 */
 #define DEBUG_OFF_LEVEL		   -1 /* level where debug is switched off */
@@ -26,6 +26,21 @@
 #define DEBUG_DATA(entry) (char *)(entry + 1) /* data is stored behind */
 					      /* the entry information */
 
+#define __DEBUG_FEATURE_VERSION	   2  /* version of debug feature */
+
+struct __debug_entry {
+	union {
+		struct {
+			unsigned long clock	: 52;
+			unsigned long exception	:  1;
+			unsigned long level	:  3;
+			unsigned long cpuid	:  8;
+		} fields;
+		unsigned long stck;
+	} id;
+	void *caller;
+} __packed;
+
 typedef struct __debug_entry debug_entry_t;
 
 struct debug_view;
@@ -82,7 +97,6 @@ struct debug_view {
 };
 
 extern struct debug_view debug_hex_ascii_view;
-extern struct debug_view debug_raw_view;
 extern struct debug_view debug_sprintf_view;
 
 /* do NOT use the _common functions */
diff --git a/arch/s390/include/asm/extable.h b/arch/s390/include/asm/extable.h
index ae27f756b409..3beb294fd553 100644
--- a/arch/s390/include/asm/extable.h
+++ b/arch/s390/include/asm/extable.h
@@ -1,12 +1,20 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __S390_EXTABLE_H
 #define __S390_EXTABLE_H
+
+#include <asm/ptrace.h>
+#include <linux/compiler.h>
+
 /*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
+ * The exception table consists of three addresses:
+ *
+ * - Address of an instruction that is allowed to fault.
+ * - Address at which the program should continue.
+ * - Optional address of handler that takes pt_regs * argument and runs in
+ *   interrupt context.
+ *
+ * No registers are modified, so it is entirely up to the continuation code
+ * to figure out what to do.
  *
  * All the routines below use bits of fixup code that are out of line
  * with the main instruction path.  This means when everything is well,
@@ -17,6 +25,7 @@
 struct exception_table_entry
 {
 	int insn, fixup;
+	long handler;
 };
 
 extern struct exception_table_entry *__start_dma_ex_table;
@@ -29,6 +38,39 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x)
 	return (unsigned long)&x->fixup + x->fixup;
 }
 
+typedef bool (*ex_handler_t)(const struct exception_table_entry *,
+			     struct pt_regs *);
+
+static inline ex_handler_t
+ex_fixup_handler(const struct exception_table_entry *x)
+{
+	if (likely(!x->handler))
+		return NULL;
+	return (ex_handler_t)((unsigned long)&x->handler + x->handler);
+}
+
+static inline bool ex_handle(const struct exception_table_entry *x,
+			     struct pt_regs *regs)
+{
+	ex_handler_t handler = ex_fixup_handler(x);
+
+	if (unlikely(handler))
+		return handler(x, regs);
+	regs->psw.addr = extable_fixup(x);
+	return true;
+}
+
 #define ARCH_HAS_RELATIVE_EXTABLE
 
+static inline void swap_ex_entry_fixup(struct exception_table_entry *a,
+				       struct exception_table_entry *b,
+				       struct exception_table_entry tmp,
+				       int delta)
+{
+	a->fixup = b->fixup + delta;
+	b->fixup = tmp.fixup - delta;
+	a->handler = b->handler + delta;
+	b->handler = tmp.handler - delta;
+}
+
 #endif
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index cee3cb6455a2..6ea0820e7c7f 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -31,12 +31,12 @@
 #define KVM_USER_MEM_SLOTS 32
 
 /*
- * These seem to be used for allocating ->chip in the routing table,
- * which we don't use. 4096 is an out-of-thin-air value. If we need
- * to look at ->chip later on, we'll need to revisit this.
+ * These seem to be used for allocating ->chip in the routing table, which we
+ * don't use. 1 is as small as we can get to reduce the needed memory. If we
+ * need to look at ->chip later on, we'll need to revisit this.
  */
 #define KVM_NR_IRQCHIPS 1
-#define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_IRQCHIP_NUM_PINS 1
 #define KVM_HALT_POLL_NS_DEFAULT 50000
 
 /* s390-specific vcpu->requests bit members */
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index 7f22262b0e46..a0a7a2c72bd4 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -2,38 +2,27 @@
 #ifndef __ASM_LINKAGE_H
 #define __ASM_LINKAGE_H
 
+#include <asm/asm-const.h>
 #include <linux/stringify.h>
 
 #define __ALIGN .align 4, 0x07
 #define __ALIGN_STR __stringify(__ALIGN)
 
-#ifndef __ASSEMBLY__
-
 /*
  * Helper macro for exception table entries
  */
-#define EX_TABLE(_fault, _target)	\
-	".section __ex_table,\"a\"\n"	\
-	".align	4\n"			\
-	".long	(" #_fault ") - .\n"	\
-	".long	(" #_target ") - .\n"	\
-	".previous\n"
-
-#else /* __ASSEMBLY__ */
 
-#define EX_TABLE(_fault, _target)	\
-	.section __ex_table,"a"	;	\
-	.align	4 ;			\
-	.long	(_fault) - . ;		\
-	.long	(_target) - . ;		\
-	.previous
+#define __EX_TABLE(_section, _fault, _target)				\
+	stringify_in_c(.section	_section,"a";)				\
+	stringify_in_c(.align	8;)					\
+	stringify_in_c(.long	(_fault) - .;)				\
+	stringify_in_c(.long	(_target) - .;)				\
+	stringify_in_c(.quad	0;)					\
+	stringify_in_c(.previous)
 
-#define EX_TABLE_DMA(_fault, _target)	\
-	.section .dma.ex_table, "a" ;	\
-	.align	4 ;			\
-	.long	(_fault) - . ;		\
-	.long	(_target) - . ;		\
-	.previous
+#define EX_TABLE(_fault, _target)					\
+	__EX_TABLE(__ex_table, _fault, _target)
+#define EX_TABLE_DMA(_fault, _target)					\
+	__EX_TABLE(.dma.ex_table, _fault, _target)
 
-#endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index 419fac7a62c0..f62cd3ed2d44 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -131,12 +131,6 @@ static inline void validate_st_entry(unsigned long *entry)
 	*entry |= ZPCI_TABLE_VALID;
 }
 
-static inline void invalidate_table_entry(unsigned long *entry)
-{
-	*entry &= ~ZPCI_TABLE_VALID_MASK;
-	*entry |= ZPCI_TABLE_INVALID;
-}
-
 static inline void invalidate_pt_entry(unsigned long *entry)
 {
 	WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_INVALID);
@@ -173,11 +167,6 @@ static inline int pt_entry_isvalid(unsigned long entry)
 	return (entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID;
 }
 
-static inline int entry_isprotected(unsigned long entry)
-{
-	return (entry & ZPCI_TABLE_PROT_MASK) == ZPCI_TABLE_PROTECTED;
-}
-
 static inline unsigned long *get_rt_sto(unsigned long entry)
 {
 	return ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 19d603bd1f36..7eb01a5459cd 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1669,7 +1669,7 @@ static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset)
 #define kern_addr_valid(addr)   (1)
 
 extern int vmem_add_mapping(unsigned long start, unsigned long size);
-extern int vmem_remove_mapping(unsigned long start, unsigned long size);
+extern void vmem_remove_mapping(unsigned long start, unsigned long size);
 extern int s390_enable_sie(void);
 extern int s390_enable_skey(void);
 extern void s390_reset_cmma(struct mm_struct *mm);
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index f009a13afe71..16b3e4396312 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -184,5 +184,10 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 	return regs->gprs[15];
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->gprs[2] = rc;
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* _S390_PTRACE_H */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 7326f110d48c..7e155fb6c254 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -10,6 +10,7 @@
 
 #include <asm/sigp.h>
 #include <asm/lowcore.h>
+#include <asm/processor.h>
 
 #define raw_smp_processor_id()	(S390_lowcore.cpu_nr)
 
@@ -54,6 +55,10 @@ static inline int smp_get_base_cpu(int cpu)
 	return cpu - (cpu % (smp_cpu_mtid + 1));
 }
 
+static inline void smp_cpus_done(unsigned int max_cpus)
+{
+}
+
 extern int smp_rescan_cpus(void);
 extern void __noreturn cpu_die(void);
 extern void __cpu_die(unsigned int cpu);
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index f073292e9fdb..d9d5de0f67ff 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -33,7 +33,17 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0;
+	unsigned long error = regs->gprs[2];
+#ifdef CONFIG_COMPAT
+	if (test_tsk_thread_flag(task, TIF_31BIT)) {
+		/*
+		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+		 * and will match correctly in comparisons.
+		 */
+		error = (long)(int)error;
+	}
+#endif
+	return IS_ERR_VALUE(error) ? error : 0;
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h
index 3c3d6fe8e2f0..1320f4213d80 100644
--- a/arch/s390/include/asm/syscall_wrapper.h
+++ b/arch/s390/include/asm/syscall_wrapper.h
@@ -30,7 +30,7 @@
 })
 
 #define __S390_SYS_STUBx(x, name, ...)					\
-	asmlinkage long __s390_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))\
+	asmlinkage long __s390_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));\
 	ALLOW_ERROR_INJECTION(__s390_sys##name, ERRNO);			\
 	asmlinkage long __s390_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))\
 	{								\
@@ -46,7 +46,7 @@
 #define COMPAT_SYSCALL_DEFINE0(sname)					\
 	SYSCALL_METADATA(_##sname, 0);					\
 	asmlinkage long __s390_compat_sys_##sname(void);		\
-	ALLOW_ERROR_INJECTION(__s390_compat__sys_##sname, ERRNO);	\
+	ALLOW_ERROR_INJECTION(__s390_compat_sys_##sname, ERRNO);	\
 	asmlinkage long __s390_compat_sys_##sname(void)
 
 #define SYSCALL_DEFINE0(sname)						\
@@ -72,7 +72,7 @@
 	asmlinkage long __s390_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
 	asmlinkage long __s390_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
 		__attribute__((alias(__stringify(__se_compat_sys##name))));	\
-	ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO);				\
+	ALLOW_ERROR_INJECTION(__s390_compat_sys##name, ERRNO);			\
 	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
 	asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
 	asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index e582fbe59e20..13a04fcf7762 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -24,7 +24,6 @@
 #ifndef __ASSEMBLY__
 #include <asm/lowcore.h>
 #include <asm/page.h>
-#include <asm/processor.h>
 
 #define STACK_INIT_OFFSET \
 	(THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs))
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 6bf3a45ccfec..289aaff4d365 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -49,11 +49,6 @@ static inline void set_clock_comparator(__u64 time)
 	asm volatile("sckc %0" : : "Q" (time));
 }
 
-static inline void store_clock_comparator(__u64 *time)
-{
-	asm volatile("stckc %0" : "=Q" (*time));
-}
-
 void clock_comparator_work(void);
 
 void __init time_early_init(void);
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 3bcfdeb01395..0cd085cdeb4f 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -36,6 +36,7 @@ struct vdso_data {
 	__u32 tk_shift;			/* Shift used for xtime_nsec	0x60 */
 	__u32 ts_dir;			/* TOD steering direction	0x64 */
 	__u64 ts_end;			/* TOD steering end		0x68 */
+	__u32 hrtimer_res;		/* hrtimer resolution		0x70 */
 };
 
 struct vdso_per_cpu_data {
diff --git a/arch/s390/include/uapi/asm/debug.h b/arch/s390/include/uapi/asm/debug.h
deleted file mode 100644
index c7c564d9aea4..000000000000
--- a/arch/s390/include/uapi/asm/debug.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- *   S/390 debug facility
- *
- *    Copyright IBM Corp. 1999, 2000
- */
-
-#ifndef _UAPIDEBUG_H
-#define _UAPIDEBUG_H
-
-#include <linux/fs.h>
-
-/* Note:
- * struct __debug_entry must be defined outside of #ifdef __KERNEL__ 
- * in order to allow a user program to analyze the 'raw'-view.
- */
-
-struct __debug_entry{
-        union {
-                struct {
-                        unsigned long long clock:52;
-                        unsigned long long exception:1;
-                        unsigned long long level:3;
-                        unsigned long long cpuid:8;
-                } fields;
-
-                unsigned long long stck;
-        } id;
-        void* caller;
-} __attribute__((packed));
-
-
-#define __DEBUG_FEATURE_VERSION      2  /* version of debug feature */
-
-#endif /* _UAPIDEBUG_H */
diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h
index 5a2177e96e88..22fd202856bc 100644
--- a/arch/s390/include/uapi/asm/zcrypt.h
+++ b/arch/s390/include/uapi/asm/zcrypt.h
@@ -36,12 +36,12 @@
  * - length(n_modulus) = inputdatalength
  */
 struct ica_rsa_modexpo {
-	char __user  *inputdata;
-	unsigned int  inputdatalength;
-	char __user  *outputdata;
-	unsigned int  outputdatalength;
-	char __user  *b_key;
-	char __user  *n_modulus;
+	__u8 __user  *inputdata;
+	__u32	      inputdatalength;
+	__u8 __user  *outputdata;
+	__u32	      outputdatalength;
+	__u8 __user  *b_key;
+	__u8 __user  *n_modulus;
 };
 
 /**
@@ -59,15 +59,15 @@ struct ica_rsa_modexpo {
  * - length(u_mult_inv) = inputdatalength/2 + 8
  */
 struct ica_rsa_modexpo_crt {
-	char __user  *inputdata;
-	unsigned int  inputdatalength;
-	char __user  *outputdata;
-	unsigned int  outputdatalength;
-	char __user  *bp_key;
-	char __user  *bq_key;
-	char __user  *np_prime;
-	char __user  *nq_prime;
-	char __user  *u_mult_inv;
+	__u8 __user  *inputdata;
+	__u32	      inputdatalength;
+	__u8 __user  *outputdata;
+	__u32	      outputdatalength;
+	__u8 __user  *bp_key;
+	__u8 __user  *bq_key;
+	__u8 __user  *np_prime;
+	__u8 __user  *nq_prime;
+	__u8 __user  *u_mult_inv;
 };
 
 /**
@@ -83,67 +83,67 @@ struct ica_rsa_modexpo_crt {
  *	    key block
  */
 struct CPRBX {
-	unsigned short	cprb_len;	/* CPRB length	      220	 */
-	unsigned char	cprb_ver_id;	/* CPRB version id.   0x02	 */
-	unsigned char	pad_000[3];	/* Alignment pad bytes		 */
-	unsigned char	func_id[2];	/* function id	      0x5432	 */
-	unsigned char	cprb_flags[4];	/* Flags			 */
-	unsigned int	req_parml;	/* request parameter buffer len	 */
-	unsigned int	req_datal;	/* request data buffer		 */
-	unsigned int	rpl_msgbl;	/* reply  message block length	 */
-	unsigned int	rpld_parml;	/* replied parameter block len	 */
-	unsigned int	rpl_datal;	/* reply data block len		 */
-	unsigned int	rpld_datal;	/* replied data block len	 */
-	unsigned int	req_extbl;	/* request extension block len	 */
-	unsigned char	pad_001[4];	/* reserved			 */
-	unsigned int	rpld_extbl;	/* replied extension block len	 */
-	unsigned char	padx000[16 - sizeof(char *)];
-	unsigned char  *req_parmb;	/* request parm block 'address'	 */
-	unsigned char	padx001[16 - sizeof(char *)];
-	unsigned char  *req_datab;	/* request data block 'address'	 */
-	unsigned char	padx002[16 - sizeof(char *)];
-	unsigned char  *rpl_parmb;	/* reply parm block 'address'	 */
-	unsigned char	padx003[16 - sizeof(char *)];
-	unsigned char  *rpl_datab;	/* reply data block 'address'	 */
-	unsigned char	padx004[16 - sizeof(char *)];
-	unsigned char  *req_extb;	/* request extension block 'addr'*/
-	unsigned char	padx005[16 - sizeof(char *)];
-	unsigned char  *rpl_extb;	/* reply extension block 'address'*/
-	unsigned short	ccp_rtcode;	/* server return code		 */
-	unsigned short	ccp_rscode;	/* server reason code		 */
-	unsigned int	mac_data_len;	/* Mac Data Length		 */
-	unsigned char	logon_id[8];	/* Logon Identifier		 */
-	unsigned char	mac_value[8];	/* Mac Value			 */
-	unsigned char	mac_content_flgs;/* Mac content flag byte	 */
-	unsigned char	pad_002;	/* Alignment			 */
-	unsigned short	domain;		/* Domain			 */
-	unsigned char	usage_domain[4];/* Usage domain			 */
-	unsigned char	cntrl_domain[4];/* Control domain		 */
-	unsigned char	S390enf_mask[4];/* S/390 enforcement mask	 */
-	unsigned char	pad_004[36];	/* reserved			 */
+	__u16	     cprb_len;		/* CPRB length	      220	 */
+	__u8	     cprb_ver_id;	/* CPRB version id.   0x02	 */
+	__u8	     pad_000[3];	/* Alignment pad bytes		 */
+	__u8	     func_id[2];	/* function id	      0x5432	 */
+	__u8	     cprb_flags[4];	/* Flags			 */
+	__u32	     req_parml;		/* request parameter buffer len	 */
+	__u32	     req_datal;		/* request data buffer		 */
+	__u32	     rpl_msgbl;		/* reply  message block length	 */
+	__u32	     rpld_parml;	/* replied parameter block len	 */
+	__u32	     rpl_datal;		/* reply data block len		 */
+	__u32	     rpld_datal;	/* replied data block len	 */
+	__u32	     req_extbl;		/* request extension block len	 */
+	__u8	     pad_001[4];	/* reserved			 */
+	__u32	     rpld_extbl;	/* replied extension block len	 */
+	__u8	     padx000[16 - sizeof(__u8 *)];
+	__u8 __user *req_parmb;		/* request parm block 'address'	 */
+	__u8	     padx001[16 - sizeof(__u8 *)];
+	__u8 __user *req_datab;		/* request data block 'address'	 */
+	__u8	     padx002[16 - sizeof(__u8 *)];
+	__u8 __user *rpl_parmb;		/* reply parm block 'address'	 */
+	__u8	     padx003[16 - sizeof(__u8 *)];
+	__u8 __user *rpl_datab;		/* reply data block 'address'	 */
+	__u8	     padx004[16 - sizeof(__u8 *)];
+	__u8 __user *req_extb;		/* request extension block 'addr'*/
+	__u8	     padx005[16 - sizeof(__u8 *)];
+	__u8 __user *rpl_extb;		/* reply extension block 'address'*/
+	__u16	     ccp_rtcode;	/* server return code		 */
+	__u16	     ccp_rscode;	/* server reason code		 */
+	__u32	     mac_data_len;	/* Mac Data Length		 */
+	__u8	     logon_id[8];	/* Logon Identifier		 */
+	__u8	     mac_value[8];	/* Mac Value			 */
+	__u8	     mac_content_flgs;	/* Mac content flag byte	 */
+	__u8	     pad_002;		/* Alignment			 */
+	__u16	     domain;		/* Domain			 */
+	__u8	     usage_domain[4];	/* Usage domain			 */
+	__u8	     cntrl_domain[4];	/* Control domain		 */
+	__u8	     S390enf_mask[4];	/* S/390 enforcement mask	 */
+	__u8	     pad_004[36];	/* reserved			 */
 } __attribute__((packed));
 
 /**
  * xcRB
  */
 struct ica_xcRB {
-	unsigned short	agent_ID;
-	unsigned int	user_defined;
-	unsigned short	request_ID;
-	unsigned int	request_control_blk_length;
-	unsigned char	padding1[16 - sizeof(char *)];
-	char __user    *request_control_blk_addr;
-	unsigned int	request_data_length;
-	char		padding2[16 - sizeof(char *)];
-	char __user    *request_data_address;
-	unsigned int	reply_control_blk_length;
-	char		padding3[16 - sizeof(char *)];
-	char __user    *reply_control_blk_addr;
-	unsigned int	reply_data_length;
-	char		padding4[16 - sizeof(char *)];
-	char __user    *reply_data_addr;
-	unsigned short	priority_window;
-	unsigned int	status;
+	__u16	      agent_ID;
+	__u32	      user_defined;
+	__u16	      request_ID;
+	__u32	      request_control_blk_length;
+	__u8	      _padding1[16 - sizeof(__u8 *)];
+	__u8 __user  *request_control_blk_addr;
+	__u32	      request_data_length;
+	__u8	      _padding2[16 - sizeof(__u8 *)];
+	__u8 __user  *request_data_address;
+	__u32	      reply_control_blk_length;
+	__u8	      _padding3[16 - sizeof(__u8 *)];
+	__u8 __user  *reply_control_blk_addr;
+	__u32	      reply_data_length;
+	__u8	      __padding4[16 - sizeof(__u8 *)];
+	__u8 __user  *reply_data_addr;
+	__u16	      priority_window;
+	__u32	      status;
 } __attribute__((packed));
 
 /**
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 165031bd3370..5d8cc1864566 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -76,6 +76,7 @@ int main(void)
 	OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift);
 	OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir);
 	OFFSET(__VDSO_TS_END, vdso_data, ts_end);
+	OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res);
 	OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);
 	OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);
 	OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
@@ -86,7 +87,6 @@ int main(void)
 	DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
 	DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
 	DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
-	DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
 	DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
 	BLANK();
 	/* idle data offsets */
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index f96a5857bbfd..c42ce348103c 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -549,8 +549,7 @@ static int get_mem_chunk_cnt(void)
 	int cnt = 0;
 	u64 idx;
 
-	for_each_mem_range(idx, &memblock.physmem, &oldmem_type, NUMA_NO_NODE,
-			   MEMBLOCK_NONE, NULL, NULL, NULL)
+	for_each_physmem_range(idx, &oldmem_type, NULL, NULL)
 		cnt++;
 	return cnt;
 }
@@ -563,8 +562,7 @@ static void loads_init(Elf64_Phdr *phdr, u64 loads_offset)
 	phys_addr_t start, end;
 	u64 idx;
 
-	for_each_mem_range(idx, &memblock.physmem, &oldmem_type, NUMA_NO_NODE,
-			   MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_physmem_range(idx, &oldmem_type, &start, &end) {
 		phdr->p_filesz = end - start;
 		phdr->p_type = PT_LOAD;
 		phdr->p_offset = start;
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 636446003a06..beb4b44a11d1 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -90,27 +90,11 @@ static int debug_input_flush_fn(debug_info_t *id, struct debug_view *view,
 				size_t user_buf_size, loff_t *offset);
 static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view,
 				     char *out_buf, const char *in_buf);
-static int debug_raw_format_fn(debug_info_t *id,
-			       struct debug_view *view, char *out_buf,
-			       const char *in_buf);
-static int debug_raw_header_fn(debug_info_t *id, struct debug_view *view,
-			       int area, debug_entry_t *entry, char *out_buf);
-
 static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view,
 				   char *out_buf, debug_sprintf_entry_t *curr_event);
 
 /* globals */
 
-struct debug_view debug_raw_view = {
-	"raw",
-	NULL,
-	&debug_raw_header_fn,
-	&debug_raw_format_fn,
-	NULL,
-	NULL
-};
-EXPORT_SYMBOL(debug_raw_view);
-
 struct debug_view debug_hex_ascii_view = {
 	"hex_ascii",
 	NULL,
@@ -198,9 +182,10 @@ static debug_entry_t ***debug_areas_alloc(int pages_per_area, int nr_areas)
 	if (!areas)
 		goto fail_malloc_areas;
 	for (i = 0; i < nr_areas; i++) {
+		/* GFP_NOWARN to avoid user triggerable WARN, we handle fails */
 		areas[i] = kmalloc_array(pages_per_area,
 					 sizeof(debug_entry_t *),
-					 GFP_KERNEL);
+					 GFP_KERNEL | __GFP_NOWARN);
 		if (!areas[i])
 			goto fail_malloc_areas2;
 		for (j = 0; j < pages_per_area; j++) {
@@ -1385,32 +1370,6 @@ out:
 }
 
 /*
- * prints debug header in raw format
- */
-static int debug_raw_header_fn(debug_info_t *id, struct debug_view *view,
-			       int area, debug_entry_t *entry, char *out_buf)
-{
-	int rc;
-
-	rc = sizeof(debug_entry_t);
-	memcpy(out_buf, entry, sizeof(debug_entry_t));
-	return rc;
-}
-
-/*
- * prints debug data in raw format
- */
-static int debug_raw_format_fn(debug_info_t *id, struct debug_view *view,
-			       char *out_buf, const char *in_buf)
-{
-	int rc;
-
-	rc = id->buf_size;
-	memcpy(out_buf, in_buf, id->buf_size);
-	return rc;
-}
-
-/*
  * prints debug data in hex/ascii format
  */
 static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view,
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index cd241ee66eff..078277231858 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -170,6 +170,8 @@ static noinline __init void setup_lowcore_early(void)
 	psw_t psw;
 
 	psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
+	if (IS_ENABLED(CONFIG_KASAN))
+		psw.mask |= PSW_MASK_DAT;
 	psw.addr = (unsigned long) s390_base_ext_handler;
 	S390_lowcore.external_new_psw = psw;
 	psw.addr = (unsigned long) s390_base_pgm_handler;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 50ff6dd0f995..23edf196d3dc 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -370,7 +370,7 @@ EXPORT_SYMBOL(sie_exit)
 
 /*
  * SVC interrupt handler routine. System calls are synchronous events and
- * are executed with interrupts enabled.
+ * are entered with interrupts disabled.
  */
 
 ENTRY(system_call)
@@ -378,9 +378,9 @@ ENTRY(system_call)
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	BPOFF
 	lg	%r12,__LC_CURRENT
-	lghi	%r13,__TASK_thread
 	lghi	%r14,_PIF_SYSCALL
 .Lsysc_per:
+	lghi	%r13,__TASK_thread
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
 	UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
@@ -401,9 +401,9 @@ ENTRY(system_call)
 	jnz	.Lsysc_nr_ok
 	# svc 0: system call number in %r1
 	llgfr	%r1,%r1				# clear high word in r1
+	sth	%r1,__PT_INT_CODE+2(%r11)
 	cghi	%r1,NR_syscalls
 	jnl	.Lsysc_nr_ok
-	sth	%r1,__PT_INT_CODE+2(%r11)
 	slag	%r8,%r1,3
 .Lsysc_nr_ok:
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 44e01dd1e624..b388e87a08bf 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -83,7 +83,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 {
 	struct ftrace_insn orig, new, old;
 
-	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
+	if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
 		return -EFAULT;
 	if (addr == MCOUNT_ADDR) {
 		/* Initial code replacement */
@@ -105,7 +105,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
 	struct ftrace_insn orig, new, old;
 
-	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
+	if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
 		return -EFAULT;
 	/* Replace nop with an ftrace call. */
 	ftrace_generate_nop_insn(&orig);
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 0d7fbdfe995a..88bb42ca5008 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/sched/cputime.h>
+#include <trace/events/power.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include "entry.h"
@@ -32,11 +33,12 @@ void enabled_wait(void)
 		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
 	clear_cpu_flag(CIF_NOHZ_DELAY);
 
+	trace_cpu_idle_rcuidle(1, smp_processor_id());
 	local_irq_save(flags);
 	/* Call the assembler magic in entry.S */
 	psw_idle(idle, psw_mask);
 	local_irq_restore(flags);
-
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
 	write_seqcount_begin(&idle->seqcount);
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index ccea9a245867..90a2a17239b0 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -181,7 +181,7 @@ static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj,	\
 		struct kobj_attribute *attr,				\
 		char *page)						\
 {									\
-	return snprintf(page, PAGE_SIZE, _format, ##args);		\
+	return scnprintf(page, PAGE_SIZE, _format, ##args);		\
 }
 
 #define IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk)			\
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 548d0ea9808d..d2a71d872638 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -523,10 +523,8 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 		 * zero, try to fix up.
 		 */
 		entry = s390_search_extables(regs->psw.addr);
-		if (entry) {
-			regs->psw.addr = extable_fixup(entry);
+		if (entry && ex_handle(entry, regs))
 			return 1;
-		}
 
 		/*
 		 * fixup_exception() could not handle it,
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
index 452502f9a0d9..3b895971c3d0 100644
--- a/arch/s390/kernel/lgr.c
+++ b/arch/s390/kernel/lgr.c
@@ -167,7 +167,7 @@ static struct timer_list lgr_timer;
  */
 static void lgr_timer_set(void)
 {
-	mod_timer(&lgr_timer, jiffies + LGR_TIMER_INTERVAL_SECS * HZ);
+	mod_timer(&lgr_timer, jiffies + msecs_to_jiffies(LGR_TIMER_INTERVAL_SECS * MSEC_PER_SEC));
 }
 
 /*
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index 1e3df52b2b65..37265f551a11 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -292,7 +292,7 @@ CPUMF_EVENT_ATTR(cf_z15, TX_C_TABORT_SPECIAL, 0x00f5);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_ACCESS, 0x00f7);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_CYCLES, 0x00fc);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x00108);
-CPUMF_EVENT_ATTR(cf_z15, DFLT_CCERROR, 0x00109);
+CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x00109);
 CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
 
@@ -629,7 +629,7 @@ static struct attribute *cpumcf_z15_pmu_event_attr[] __initdata = {
 	CPUMF_EVENT_PTR(cf_z15, DFLT_ACCESS),
 	CPUMF_EVENT_PTR(cf_z15, DFLT_CYCLES),
 	CPUMF_EVENT_PTR(cf_z15, DFLT_CC),
-	CPUMF_EVENT_PTR(cf_z15, DFLT_CCERROR),
+	CPUMF_EVENT_PTR(cf_z15, DFLT_CCFINISH),
 	CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE),
 	CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE),
 	NULL,
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 85a711d783eb..4f9e4626df55 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -881,12 +881,21 @@ out:
 	return err;
 }
 
+static bool is_callchain_event(struct perf_event *event)
+{
+	u64 sample_type = event->attr.sample_type;
+
+	return sample_type & (PERF_SAMPLE_CALLCHAIN | PERF_SAMPLE_REGS_USER |
+			      PERF_SAMPLE_STACK_USER);
+}
+
 static int cpumsf_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
 	/* No support for taken branch sampling */
-	if (has_branch_stack(event))
+	/* No support for callchain, stacks and registers */
+	if (has_branch_stack(event) || is_callchain_event(event))
 		return -EOPNOTSUPP;
 
 	switch (event->attr.type) {
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index ce60a459a143..3cc15c066298 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -323,6 +323,25 @@ static inline void __poke_user_per(struct task_struct *child,
 		child->thread.per_user.end = data;
 }
 
+static void fixup_int_code(struct task_struct *child, addr_t data)
+{
+	struct pt_regs *regs = task_pt_regs(child);
+	int ilc = regs->int_code >> 16;
+	u16 insn;
+
+	if (ilc > 6)
+		return;
+
+	if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16),
+			&insn, sizeof(insn), FOLL_FORCE) != sizeof(insn))
+		return;
+
+	/* double check that tracee stopped on svc instruction */
+	if ((insn >> 8) != 0xa)
+		return;
+
+	regs->int_code = 0x20000 | (data & 0xffff);
+}
 /*
  * Write a word to the user area of a process at location addr. This
  * operation does have an additional problem compared to peek_user.
@@ -334,7 +353,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 	struct user *dummy = NULL;
 	addr_t offset;
 
+
 	if (addr < (addr_t) &dummy->regs.acrs) {
+		struct pt_regs *regs = task_pt_regs(child);
 		/*
 		 * psw and gprs are stored on the stack
 		 */
@@ -352,7 +373,11 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 				/* Invalid addressing mode bits */
 				return -EINVAL;
 		}
-		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
+
+		if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+			addr == offsetof(struct user, regs.gprs[2]))
+			fixup_int_code(child, data);
+		*(addr_t *)((addr_t) &regs->psw + addr) = data;
 
 	} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
 		/*
@@ -718,6 +743,10 @@ static int __poke_user_compat(struct task_struct *child,
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
 				(__u64)(tmp & PSW32_ADDR_AMODE);
 		} else {
+
+			if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+				addr == offsetof(struct compat_user, regs.gprs[2]))
+				fixup_int_code(child, data);
 			/* gpr 0-15 */
 			*(__u32*)((addr_t) &regs->psw + addr*2 + 4) = tmp;
 		}
@@ -837,40 +866,66 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	unsigned long mask = -1UL;
+	long ret = -1;
+
+	if (is_compat_task())
+		mask = 0xffffffff;
 
 	/*
 	 * The sysc_tracesys code in entry.S stored the system
 	 * call number to gprs[2].
 	 */
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    (tracehook_report_syscall_entry(regs) ||
-	     regs->gprs[2] >= NR_syscalls)) {
+	    tracehook_report_syscall_entry(regs)) {
 		/*
-		 * Tracing decided this syscall should not happen or the
-		 * debugger stored an invalid system call number. Skip
+		 * Tracing decided this syscall should not happen. Skip
 		 * the system call and the system call restart handling.
 		 */
-		clear_pt_regs_flag(regs, PIF_SYSCALL);
-		return -1;
+		goto skip;
 	}
 
+#ifdef CONFIG_SECCOMP
 	/* Do the secure computing check after ptrace. */
-	if (secure_computing()) {
-		/* seccomp failures shouldn't expose any additional code. */
-		return -1;
+	if (unlikely(test_thread_flag(TIF_SECCOMP))) {
+		struct seccomp_data sd;
+
+		if (is_compat_task()) {
+			sd.instruction_pointer = regs->psw.addr & 0x7fffffff;
+			sd.arch = AUDIT_ARCH_S390;
+		} else {
+			sd.instruction_pointer = regs->psw.addr;
+			sd.arch = AUDIT_ARCH_S390X;
+		}
+
+		sd.nr = regs->int_code & 0xffff;
+		sd.args[0] = regs->orig_gpr2 & mask;
+		sd.args[1] = regs->gprs[3] & mask;
+		sd.args[2] = regs->gprs[4] & mask;
+		sd.args[3] = regs->gprs[5] & mask;
+		sd.args[4] = regs->gprs[6] & mask;
+		sd.args[5] = regs->gprs[7] & mask;
+
+		if (__secure_computing(&sd) == -1)
+			goto skip;
 	}
+#endif /* CONFIG_SECCOMP */
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_enter(regs, regs->gprs[2]);
+		trace_sys_enter(regs, regs->int_code & 0xffff);
 
-	if (is_compat_task())
-		mask = 0xffffffff;
 
-	audit_syscall_entry(regs->gprs[2], regs->orig_gpr2 & mask,
+	audit_syscall_entry(regs->int_code & 0xffff, regs->orig_gpr2 & mask,
 			    regs->gprs[3] &mask, regs->gprs[4] &mask,
 			    regs->gprs[5] &mask);
 
+	if ((signed long)regs->gprs[2] >= NR_syscalls) {
+		regs->gprs[2] = -ENOSYS;
+		ret = -ENOSYS;
+	}
 	return regs->gprs[2];
+skip:
+	clear_pt_regs_flag(regs, PIF_SYSCALL);
+	return ret;
 }
 
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 5853c9872dfe..0c4194d407ac 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1100,6 +1100,7 @@ void __init setup_arch(char **cmdline_p)
 	if (IS_ENABLED(CONFIG_EXPOLINE_AUTO))
 		nospec_auto_detect();
 
+	jump_label_init();
 	parse_early_param();
 #ifdef CONFIG_CRASH_DUMP
 	/* Deactivate elfcorehdr= kernel parameter */
@@ -1126,14 +1127,6 @@ void __init setup_arch(char **cmdline_p)
 	free_mem_detect_info();
 	remove_oldmem();
 
-	/*
-	 * Make sure all chunks are MAX_ORDER aligned so we don't need the
-	 * extra checks that HOLES_IN_ZONE would require.
-	 *
-	 * Is this still required?
-	 */
-	memblock_trim_memory(1UL << (MAX_ORDER - 1 + PAGE_SHIFT));
-
 	if (is_prot_virt_host())
 		setup_uv();
 	setup_memory_end();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index e6be63ff162a..f685a38f166d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -1012,10 +1012,6 @@ void __init smp_prepare_boot_cpu(void)
 	smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);
 }
 
-void __init smp_cpus_done(unsigned int max_cpus)
-{
-}
-
 void __init smp_setup_processor_id(void)
 {
 	pcpu_devices[0].address = stap();
@@ -1145,6 +1141,7 @@ static int smp_cpu_online(unsigned int cpu)
 
 	return sysfs_create_group(&s->kobj, &cpu_online_attr_group);
 }
+
 static int smp_cpu_pre_down(unsigned int cpu)
 {
 	struct device *s = &per_cpu(cpu_device, cpu)->dev;
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index f9d070d016e3..513e59d08a55 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -237,7 +237,7 @@ static u64 read_tod_clock(struct clocksource *cs)
 	preempt_disable(); /* protect from changes to steering parameters */
 	now = get_tod_clock();
 	adj = tod_steering_end - now;
-	if (unlikely((s64) adj >= 0))
+	if (unlikely((s64) adj > 0))
 		/*
 		 * manually steer by 1 cycle every 2^16 cycles. This
 		 * corresponds to shifting the tod delta by 15. 1s is
@@ -253,7 +253,7 @@ static struct clocksource clocksource_tod = {
 	.name		= "tod",
 	.rating		= 400,
 	.read		= read_tod_clock,
-	.mask		= -1ULL,
+	.mask		= CLOCKSOURCE_MASK(64),
 	.mult		= 1000,
 	.shift		= 12,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
@@ -301,6 +301,7 @@ void update_vsyscall(struct timekeeper *tk)
 
 	vdso_data->tk_mult = tk->tkr_mono.mult;
 	vdso_data->tk_shift = tk->tkr_mono.shift;
+	vdso_data->hrtimer_res = hrtimer_resolution;
 	smp_wmb();
 	++vdso_data->tb_update_count;
 }
@@ -668,7 +669,7 @@ static void stp_work_fn(struct work_struct *work)
 		 * There is a usable clock but the synchonization failed.
 		 * Retry after a second.
 		 */
-		mod_timer(&stp_timer, jiffies + HZ);
+		mod_timer(&stp_timer, jiffies + msecs_to_jiffies(MSEC_PER_SEC));
 
 out_unlock:
 	mutex_unlock(&stp_work_mutex);
@@ -682,7 +683,7 @@ static struct bus_type stp_subsys = {
 	.dev_name	= "stp",
 };
 
-static ssize_t stp_ctn_id_show(struct device *dev,
+static ssize_t ctn_id_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
@@ -692,9 +693,9 @@ static ssize_t stp_ctn_id_show(struct device *dev,
 		       *(unsigned long long *) stp_info.ctnid);
 }
 
-static DEVICE_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL);
+static DEVICE_ATTR_RO(ctn_id);
 
-static ssize_t stp_ctn_type_show(struct device *dev,
+static ssize_t ctn_type_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
@@ -703,9 +704,9 @@ static ssize_t stp_ctn_type_show(struct device *dev,
 	return sprintf(buf, "%i\n", stp_info.ctn);
 }
 
-static DEVICE_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL);
+static DEVICE_ATTR_RO(ctn_type);
 
-static ssize_t stp_dst_offset_show(struct device *dev,
+static ssize_t dst_offset_show(struct device *dev,
 				   struct device_attribute *attr,
 				   char *buf)
 {
@@ -714,9 +715,9 @@ static ssize_t stp_dst_offset_show(struct device *dev,
 	return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
 }
 
-static DEVICE_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL);
+static DEVICE_ATTR_RO(dst_offset);
 
-static ssize_t stp_leap_seconds_show(struct device *dev,
+static ssize_t leap_seconds_show(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
 {
@@ -725,9 +726,9 @@ static ssize_t stp_leap_seconds_show(struct device *dev,
 	return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
 }
 
-static DEVICE_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL);
+static DEVICE_ATTR_RO(leap_seconds);
 
-static ssize_t stp_stratum_show(struct device *dev,
+static ssize_t stratum_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
@@ -736,9 +737,9 @@ static ssize_t stp_stratum_show(struct device *dev,
 	return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
 }
 
-static DEVICE_ATTR(stratum, 0400, stp_stratum_show, NULL);
+static DEVICE_ATTR_RO(stratum);
 
-static ssize_t stp_time_offset_show(struct device *dev,
+static ssize_t time_offset_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
@@ -747,9 +748,9 @@ static ssize_t stp_time_offset_show(struct device *dev,
 	return sprintf(buf, "%i\n", (int) stp_info.tto);
 }
 
-static DEVICE_ATTR(time_offset, 0400, stp_time_offset_show, NULL);
+static DEVICE_ATTR_RO(time_offset);
 
-static ssize_t stp_time_zone_offset_show(struct device *dev,
+static ssize_t time_zone_offset_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
@@ -758,10 +759,9 @@ static ssize_t stp_time_zone_offset_show(struct device *dev,
 	return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
 }
 
-static DEVICE_ATTR(time_zone_offset, 0400,
-			 stp_time_zone_offset_show, NULL);
+static DEVICE_ATTR_RO(time_zone_offset);
 
-static ssize_t stp_timing_mode_show(struct device *dev,
+static ssize_t timing_mode_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
@@ -770,9 +770,9 @@ static ssize_t stp_timing_mode_show(struct device *dev,
 	return sprintf(buf, "%i\n", stp_info.tmd);
 }
 
-static DEVICE_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL);
+static DEVICE_ATTR_RO(timing_mode);
 
-static ssize_t stp_timing_state_show(struct device *dev,
+static ssize_t timing_state_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
@@ -781,16 +781,16 @@ static ssize_t stp_timing_state_show(struct device *dev,
 	return sprintf(buf, "%i\n", stp_info.tst);
 }
 
-static DEVICE_ATTR(timing_state, 0400, stp_timing_state_show, NULL);
+static DEVICE_ATTR_RO(timing_state);
 
-static ssize_t stp_online_show(struct device *dev,
+static ssize_t online_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
 	return sprintf(buf, "%i\n", stp_online);
 }
 
-static ssize_t stp_online_store(struct device *dev,
+static ssize_t online_store(struct device *dev,
 				struct device_attribute *attr,
 				const char *buf, size_t count)
 {
@@ -816,18 +816,14 @@ static ssize_t stp_online_store(struct device *dev,
  * Can't use DEVICE_ATTR because the attribute should be named
  * stp/online but dev_attr_online already exists in this file ..
  */
-static struct device_attribute dev_attr_stp_online = {
-	.attr = { .name = "online", .mode = 0600 },
-	.show	= stp_online_show,
-	.store	= stp_online_store,
-};
+static DEVICE_ATTR_RW(online);
 
 static struct device_attribute *stp_attributes[] = {
 	&dev_attr_ctn_id,
 	&dev_attr_ctn_type,
 	&dev_attr_dst_offset,
 	&dev_attr_leap_seconds,
-	&dev_attr_stp_online,
+	&dev_attr_online,
 	&dev_attr_stratum,
 	&dev_attr_time_offset,
 	&dev_attr_time_zone_offset,
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 332b542548cd..ca47141a5be9 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -356,9 +356,9 @@ static atomic_t topology_poll = ATOMIC_INIT(0);
 static void set_topology_timer(void)
 {
 	if (atomic_add_unless(&topology_poll, -1, 0))
-		mod_timer(&topology_timer, jiffies + HZ / 10);
+		mod_timer(&topology_timer, jiffies + msecs_to_jiffies(100));
 	else
-		mod_timer(&topology_timer, jiffies + HZ * 60);
+		mod_timer(&topology_timer, jiffies + msecs_to_jiffies(60 * MSEC_PER_SEC));
 }
 
 void topology_expect_change(void)
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index ff9cc4c3290e..8d1e8a1a97df 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -50,11 +50,8 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
         } else {
                 const struct exception_table_entry *fixup;
 		fixup = s390_search_extables(regs->psw.addr);
-                if (fixup)
-			regs->psw.addr = extable_fixup(fixup);
-		else {
+		if (!fixup || !ex_handle(fixup, regs))
 			die(regs, str);
-		}
         }
 }
 
@@ -251,7 +248,7 @@ void monitor_event_exception(struct pt_regs *regs)
 	case BUG_TRAP_TYPE_NONE:
 		fixup = s390_search_extables(regs->psw.addr);
 		if (fixup)
-			regs->psw.addr = extable_fixup(fixup);
+			ex_handle(fixup, regs);
 		break;
 	case BUG_TRAP_TYPE_WARN:
 		break;
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 66e89b2866d7..c296e5c8dbf9 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -331,7 +331,7 @@ EXPORT_SYMBOL_GPL(arch_make_page_accessible);
 static ssize_t uv_query_facilities(struct kobject *kobj,
 				   struct kobj_attribute *attr, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n",
+	return scnprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n",
 			uv_info.inst_calls_list[0],
 			uv_info.inst_calls_list[1],
 			uv_info.inst_calls_list[2],
@@ -344,7 +344,7 @@ static struct kobj_attribute uv_query_facilities_attr =
 static ssize_t uv_query_max_guest_cpus(struct kobject *kobj,
 				       struct kobj_attribute *attr, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "%d\n",
+	return scnprintf(page, PAGE_SIZE, "%d\n",
 			uv_info.max_guest_cpus);
 }
 
@@ -354,7 +354,7 @@ static struct kobj_attribute uv_query_max_guest_cpus_attr =
 static ssize_t uv_query_max_guest_vms(struct kobject *kobj,
 				      struct kobj_attribute *attr, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "%d\n",
+	return scnprintf(page, PAGE_SIZE, "%d\n",
 			uv_info.max_num_sec_conf);
 }
 
@@ -364,7 +364,7 @@ static struct kobj_attribute uv_query_max_guest_vms_attr =
 static ssize_t uv_query_max_guest_addr(struct kobject *kobj,
 				       struct kobj_attribute *attr, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "%lx\n",
+	return scnprintf(page, PAGE_SIZE, "%lx\n",
 			uv_info.max_sec_stor_addr);
 }
 
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index bec19e7e6e1c..4a66a1cb919b 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -18,8 +18,8 @@ KBUILD_AFLAGS_64 += -m64 -s
 
 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
-KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
-		    -Wl,--hash-style=both
+ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \
+	     --hash-style=both --build-id -T
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
 $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
@@ -37,8 +37,8 @@ KASAN_SANITIZE := n
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
-	$(call if_changed,vdso64ld)
+$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE
+	$(call if_changed,ld)
 
 # strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -50,8 +50,6 @@ $(obj-vdso64): %.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
 
 # actual build commands
-quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
index 081435398e0a..0c79caa32b59 100644
--- a/arch/s390/kernel/vdso64/clock_getres.S
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -17,12 +17,14 @@
 	.type  __kernel_clock_getres,@function
 __kernel_clock_getres:
 	CFI_STARTPROC
-	larl	%r1,4f
+	larl	%r1,3f
+	lg	%r0,0(%r1)
 	cghi	%r2,__CLOCK_REALTIME_COARSE
 	je	0f
 	cghi	%r2,__CLOCK_MONOTONIC_COARSE
 	je	0f
-	larl	%r1,3f
+	larl	%r1,_vdso_data
+	llgf	%r0,__VDSO_CLOCK_REALTIME_RES(%r1)
 	cghi	%r2,__CLOCK_REALTIME
 	je	0f
 	cghi	%r2,__CLOCK_MONOTONIC
@@ -36,7 +38,6 @@ __kernel_clock_getres:
 	jz	2f
 0:	ltgr	%r3,%r3
 	jz	1f				/* res == NULL */
-	lg	%r0,0(%r1)
 	xc	0(8,%r3),0(%r3)			/* set tp->tv_sec to zero */
 	stg	%r0,8(%r3)			/* store tp->tv_usec */
 1:	lghi	%r2,0
@@ -45,6 +46,5 @@ __kernel_clock_getres:
 	svc	0
 	br	%r14
 	CFI_ENDPROC
-3:	.quad	__CLOCK_REALTIME_RES
-4:	.quad	__CLOCK_COARSE_RES
+3:	.quad	__CLOCK_COARSE_RES
 	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 28fd66d558ff..678333936f78 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -14,3 +14,5 @@ KASAN_SANITIZE_uaccess.o := n
 
 obj-$(CONFIG_S390_UNWIND_SELFTEST) += test_unwind.o
 CFLAGS_test_unwind.o += -fno-optimize-sibling-calls
+
+lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff --git a/arch/s390/lib/error-inject.c b/arch/s390/lib/error-inject.c
new file mode 100644
index 000000000000..8c9d4da87eef
--- /dev/null
+++ b/arch/s390/lib/error-inject.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <asm/ptrace.h>
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	/*
+	 * Emulate 'br 14'. 'regs' is captured by kprobes on entry to some
+	 * kernel function.
+	 */
+	regs->psw.addr = regs->gprs[14];
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 36bce727897b..5c15ae3daf71 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -189,7 +189,7 @@ static void cmm_set_timer(void)
 			del_timer(&cmm_timer);
 		return;
 	}
-	mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds * HZ);
+	mod_timer(&cmm_timer, jiffies + msecs_to_jiffies(cmm_timeout_seconds * MSEC_PER_SEC));
 }
 
 static void cmm_timer_fn(struct timer_list *unused)
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 9e0aa7aa03ba..5060956b8e7d 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -313,15 +313,10 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 		goto out_free;
 	}
 
-	rc = vmem_add_mapping(seg->start_addr, seg->end - seg->start_addr + 1);
-
-	if (rc)
-		goto out_free;
-
 	seg->res = kzalloc(sizeof(struct resource), GFP_KERNEL);
 	if (seg->res == NULL) {
 		rc = -ENOMEM;
-		goto out_shared;
+		goto out_free;
 	}
 	seg->res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
 	seg->res->start = seg->start_addr;
@@ -335,12 +330,17 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 	if (rc == SEG_TYPE_SC ||
 	    ((rc == SEG_TYPE_SR || rc == SEG_TYPE_ER) && !do_nonshared))
 		seg->res->flags |= IORESOURCE_READONLY;
+
+	/* Check for overlapping resources before adding the mapping. */
 	if (request_resource(&iomem_resource, seg->res)) {
 		rc = -EBUSY;
-		kfree(seg->res);
-		goto out_shared;
+		goto out_free_resource;
 	}
 
+	rc = vmem_add_mapping(seg->start_addr, seg->end - seg->start_addr + 1);
+	if (rc)
+		goto out_resource;
+
 	if (do_nonshared)
 		diag_cc = dcss_diag(&loadnsr_scode, seg->dcss_name,
 				&start_addr, &end_addr);
@@ -351,14 +351,14 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 		dcss_diag(&purgeseg_scode, seg->dcss_name,
 				&dummy, &dummy);
 		rc = diag_cc;
-		goto out_resource;
+		goto out_mapping;
 	}
 	if (diag_cc > 1) {
 		pr_warn("Loading DCSS %s failed with rc=%ld\n", name, end_addr);
 		rc = dcss_diag_translate_rc(end_addr);
 		dcss_diag(&purgeseg_scode, seg->dcss_name,
 				&dummy, &dummy);
-		goto out_resource;
+		goto out_mapping;
 	}
 	seg->start_addr = start_addr;
 	seg->end = end_addr;
@@ -377,11 +377,12 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 			(void*) seg->end, segtype_string[seg->vm_segtype]);
 	}
 	goto out;
+ out_mapping:
+	vmem_remove_mapping(seg->start_addr, seg->end - seg->start_addr + 1);
  out_resource:
 	release_resource(seg->res);
+ out_free_resource:
 	kfree(seg->res);
- out_shared:
-	vmem_remove_mapping(seg->start_addr, seg->end - seg->start_addr + 1);
  out_free:
 	kfree(seg);
  out:
@@ -400,8 +401,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
  * -EIO     : could not perform query or load diagnose
  * -ENOENT  : no such segment
  * -EOPNOTSUPP: multi-part segment cannot be used with linux
- * -ENOSPC  : segment cannot be used (overlaps with storage)
- * -EBUSY   : segment can temporarily not be used (overlaps with dcss)
+ * -EBUSY   : segment cannot be used (overlaps with dcss or storage)
  * -ERANGE  : segment cannot be used (exceeds kernel mapping range)
  * -EPERM   : segment is currently loaded with incompatible permissions
  * -ENOMEM  : out of memory
@@ -626,10 +626,6 @@ void segment_warning(int rc, char *seg_name)
 		pr_err("DCSS %s has multiple page ranges and cannot be "
 		       "loaded or queried\n", seg_name);
 		break;
-	case -ENOSPC:
-		pr_err("DCSS %s overlaps with used storage and cannot "
-		       "be loaded\n", seg_name);
-		break;
 	case -EBUSY:
 		pr_err("%s needs used memory resources and cannot be "
 		       "loaded or queried\n", seg_name);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 6a24751557f0..aebf9183bedd 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -105,7 +105,7 @@ static int bad_address(void *p)
 {
 	unsigned long dummy;
 
-	return probe_kernel_address((unsigned long *)p, dummy);
+	return get_kernel_nofault(dummy, (unsigned long *)p);
 }
 
 static void dump_pagetable(unsigned long asce, unsigned long address)
@@ -255,10 +255,8 @@ static noinline void do_no_context(struct pt_regs *regs)
 
 	/* Are we prepared to handle this kernel fault?  */
 	fixup = s390_search_extables(regs->psw.addr);
-	if (fixup) {
-		regs->psw.addr = extable_fixup(fixup);
+	if (fixup && ex_handle(fixup, regs))
 		return;
-	}
 
 	/*
 	 * Oops. The kernel tried to access some bad page. We'll have to
@@ -376,7 +374,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int access,
  * routines.
  *
  * interruption code (int_code):
- *   04       Protection           ->  Write-Protection  (suprression)
+ *   04       Protection           ->  Write-Protection  (suppression)
  *   10       Segment translation  ->  Not present       (nullification)
  *   11       Page translation     ->  Not present       (nullification)
  *   3b       Region third trans.  ->  Not present       (nullification)
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 82df06d720e8..3b5a4d25ca9b 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -117,7 +117,7 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 					     _PAGE_YOUNG);
 #ifdef CONFIG_MEM_SOFT_DIRTY
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY,
-					     _PAGE_DIRTY);
+					     _PAGE_SOFT_DIRTY);
 #endif
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC,
 					     _PAGE_NOEXEC);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 22a0be655f27..1d17413b319a 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -62,11 +62,15 @@ notrace void *s390_kernel_write(void *dst, const void *src, size_t size)
 	long copied;
 
 	spin_lock_irqsave(&s390_kernel_write_lock, flags);
-	while (size) {
-		copied = s390_kernel_write_odd(tmp, src, size);
-		tmp += copied;
-		src += copied;
-		size -= copied;
+	if (!(flags & PSW_MASK_DAT)) {
+		memcpy(dst, src, size);
+	} else {
+		while (size) {
+			copied = s390_kernel_write_odd(tmp, src, size);
+			tmp += copied;
+			src += copied;
+			size -= copied;
+		}
 	}
 	spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
 
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 8b6282cf7d13..1aed1a4dfc2d 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -20,14 +20,6 @@
 
 static DEFINE_MUTEX(vmem_mutex);
 
-struct memory_segment {
-	struct list_head list;
-	unsigned long start;
-	unsigned long size;
-};
-
-static LIST_HEAD(mem_segs);
-
 static void __ref *vmem_alloc_pages(unsigned int order)
 {
 	unsigned long size = PAGE_SIZE << order;
@@ -37,6 +29,15 @@ static void __ref *vmem_alloc_pages(unsigned int order)
 	return (void *) memblock_phys_alloc(size, size);
 }
 
+static void vmem_free_pages(unsigned long addr, int order)
+{
+	/* We don't expect boot memory to be removed ever. */
+	if (!slab_is_available() ||
+	    WARN_ON_ONCE(PageReserved(phys_to_page(addr))))
+		return;
+	free_pages(addr, order);
+}
+
 void *vmem_crst_alloc(unsigned long val)
 {
 	unsigned long *table;
@@ -62,332 +63,486 @@ pte_t __ref *vmem_pte_alloc(void)
 	return pte;
 }
 
+static void vmem_pte_free(unsigned long *table)
+{
+	/* We don't expect boot memory to be removed ever. */
+	if (!slab_is_available() ||
+	    WARN_ON_ONCE(PageReserved(virt_to_page(table))))
+		return;
+	page_table_free(&init_mm, table);
+}
+
+#define PAGE_UNUSED 0xFD
+
 /*
- * Add a physical memory range to the 1:1 mapping.
+ * The unused vmemmap range, which was not yet memset(PAGE_UNUSED) ranges
+ * from unused_pmd_start to next PMD_SIZE boundary.
  */
-static int vmem_add_mem(unsigned long start, unsigned long size)
+static unsigned long unused_pmd_start;
+
+static void vmemmap_flush_unused_pmd(void)
 {
-	unsigned long pgt_prot, sgt_prot, r3_prot;
-	unsigned long pages4k, pages1m, pages2g;
-	unsigned long end = start + size;
-	unsigned long address = start;
-	pgd_t *pg_dir;
-	p4d_t *p4_dir;
-	pud_t *pu_dir;
-	pmd_t *pm_dir;
-	pte_t *pt_dir;
-	int ret = -ENOMEM;
+	if (!unused_pmd_start)
+		return;
+	memset(__va(unused_pmd_start), PAGE_UNUSED,
+	       ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
+	unused_pmd_start = 0;
+}
+
+static void __vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
+{
+	/*
+	 * As we expect to add in the same granularity as we remove, it's
+	 * sufficient to mark only some piece used to block the memmap page from
+	 * getting removed (just in case the memmap never gets initialized,
+	 * e.g., because the memory block never gets onlined).
+	 */
+	memset(__va(start), 0, sizeof(struct page));
+}
 
-	pgt_prot = pgprot_val(PAGE_KERNEL);
-	sgt_prot = pgprot_val(SEGMENT_KERNEL);
-	r3_prot = pgprot_val(REGION3_KERNEL);
-	if (!MACHINE_HAS_NX) {
-		pgt_prot &= ~_PAGE_NOEXEC;
-		sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
-		r3_prot &= ~_REGION_ENTRY_NOEXEC;
+static void vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
+{
+	/*
+	 * We only optimize if the new used range directly follows the
+	 * previously unused range (esp., when populating consecutive sections).
+	 */
+	if (unused_pmd_start == start) {
+		unused_pmd_start = end;
+		if (likely(IS_ALIGNED(unused_pmd_start, PMD_SIZE)))
+			unused_pmd_start = 0;
+		return;
 	}
-	pages4k = pages1m = pages2g = 0;
-	while (address < end) {
-		pg_dir = pgd_offset_k(address);
-		if (pgd_none(*pg_dir)) {
-			p4_dir = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
-			if (!p4_dir)
-				goto out;
-			pgd_populate(&init_mm, pg_dir, p4_dir);
-		}
-		p4_dir = p4d_offset(pg_dir, address);
-		if (p4d_none(*p4_dir)) {
-			pu_dir = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
-			if (!pu_dir)
-				goto out;
-			p4d_populate(&init_mm, p4_dir, pu_dir);
-		}
-		pu_dir = pud_offset(p4_dir, address);
-		if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
-		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end) &&
-		     !debug_pagealloc_enabled()) {
-			pud_val(*pu_dir) = address | r3_prot;
-			address += PUD_SIZE;
-			pages2g++;
-			continue;
-		}
-		if (pud_none(*pu_dir)) {
-			pm_dir = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
-			if (!pm_dir)
-				goto out;
-			pud_populate(&init_mm, pu_dir, pm_dir);
-		}
-		pm_dir = pmd_offset(pu_dir, address);
-		if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
-		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end) &&
-		    !debug_pagealloc_enabled()) {
-			pmd_val(*pm_dir) = address | sgt_prot;
-			address += PMD_SIZE;
-			pages1m++;
+	vmemmap_flush_unused_pmd();
+	__vmemmap_use_sub_pmd(start, end);
+}
+
+static void vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
+{
+	void *page = __va(ALIGN_DOWN(start, PMD_SIZE));
+
+	vmemmap_flush_unused_pmd();
+
+	/* Could be our memmap page is filled with PAGE_UNUSED already ... */
+	__vmemmap_use_sub_pmd(start, end);
+
+	/* Mark the unused parts of the new memmap page PAGE_UNUSED. */
+	if (!IS_ALIGNED(start, PMD_SIZE))
+		memset(page, PAGE_UNUSED, start - __pa(page));
+	/*
+	 * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of
+	 * consecutive sections. Remember for the last added PMD the last
+	 * unused range in the populated PMD.
+	 */
+	if (!IS_ALIGNED(end, PMD_SIZE))
+		unused_pmd_start = end;
+}
+
+/* Returns true if the PMD is completely unused and can be freed. */
+static bool vmemmap_unuse_sub_pmd(unsigned long start, unsigned long end)
+{
+	void *page = __va(ALIGN_DOWN(start, PMD_SIZE));
+
+	vmemmap_flush_unused_pmd();
+	memset(__va(start), PAGE_UNUSED, end - start);
+	return !memchr_inv(page, PAGE_UNUSED, PMD_SIZE);
+}
+
+/* __ref: we'll only call vmemmap_alloc_block() via vmemmap_populate() */
+static int __ref modify_pte_table(pmd_t *pmd, unsigned long addr,
+				  unsigned long end, bool add, bool direct)
+{
+	unsigned long prot, pages = 0;
+	int ret = -ENOMEM;
+	pte_t *pte;
+
+	prot = pgprot_val(PAGE_KERNEL);
+	if (!MACHINE_HAS_NX)
+		prot &= ~_PAGE_NOEXEC;
+
+	pte = pte_offset_kernel(pmd, addr);
+	for (; addr < end; addr += PAGE_SIZE, pte++) {
+		if (!add) {
+			if (pte_none(*pte))
+				continue;
+			if (!direct)
+				vmem_free_pages(pfn_to_phys(pte_pfn(*pte)), 0);
+			pte_clear(&init_mm, addr, pte);
+		} else if (pte_none(*pte)) {
+			if (!direct) {
+				void *new_page = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE);
+
+				if (!new_page)
+					goto out;
+				pte_val(*pte) = __pa(new_page) | prot;
+			} else {
+				pte_val(*pte) = addr | prot;
+			}
+		} else {
 			continue;
 		}
-		if (pmd_none(*pm_dir)) {
-			pt_dir = vmem_pte_alloc();
-			if (!pt_dir)
-				goto out;
-			pmd_populate(&init_mm, pm_dir, pt_dir);
-		}
-
-		pt_dir = pte_offset_kernel(pm_dir, address);
-		pte_val(*pt_dir) = address | pgt_prot;
-		address += PAGE_SIZE;
-		pages4k++;
+		pages++;
 	}
 	ret = 0;
 out:
-	update_page_count(PG_DIRECT_MAP_4K, pages4k);
-	update_page_count(PG_DIRECT_MAP_1M, pages1m);
-	update_page_count(PG_DIRECT_MAP_2G, pages2g);
+	if (direct)
+		update_page_count(PG_DIRECT_MAP_4K, add ? pages : -pages);
 	return ret;
 }
 
-/*
- * Remove a physical memory range from the 1:1 mapping.
- * Currently only invalidates page table entries.
- */
-static void vmem_remove_range(unsigned long start, unsigned long size)
+static void try_free_pte_table(pmd_t *pmd, unsigned long start)
 {
-	unsigned long pages4k, pages1m, pages2g;
-	unsigned long end = start + size;
-	unsigned long address = start;
-	pgd_t *pg_dir;
-	p4d_t *p4_dir;
-	pud_t *pu_dir;
-	pmd_t *pm_dir;
-	pte_t *pt_dir;
-
-	pages4k = pages1m = pages2g = 0;
-	while (address < end) {
-		pg_dir = pgd_offset_k(address);
-		if (pgd_none(*pg_dir)) {
-			address += PGDIR_SIZE;
-			continue;
-		}
-		p4_dir = p4d_offset(pg_dir, address);
-		if (p4d_none(*p4_dir)) {
-			address += P4D_SIZE;
-			continue;
-		}
-		pu_dir = pud_offset(p4_dir, address);
-		if (pud_none(*pu_dir)) {
-			address += PUD_SIZE;
-			continue;
-		}
-		if (pud_large(*pu_dir)) {
-			pud_clear(pu_dir);
-			address += PUD_SIZE;
-			pages2g++;
-			continue;
-		}
-		pm_dir = pmd_offset(pu_dir, address);
-		if (pmd_none(*pm_dir)) {
-			address += PMD_SIZE;
-			continue;
-		}
-		if (pmd_large(*pm_dir)) {
-			pmd_clear(pm_dir);
-			address += PMD_SIZE;
-			pages1m++;
-			continue;
-		}
-		pt_dir = pte_offset_kernel(pm_dir, address);
-		pte_clear(&init_mm, address, pt_dir);
-		address += PAGE_SIZE;
-		pages4k++;
+	pte_t *pte;
+	int i;
+
+	/* We can safely assume this is fully in 1:1 mapping & vmemmap area */
+	pte = pte_offset_kernel(pmd, start);
+	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
+		if (!pte_none(*pte))
+			return;
 	}
-	flush_tlb_kernel_range(start, end);
-	update_page_count(PG_DIRECT_MAP_4K, -pages4k);
-	update_page_count(PG_DIRECT_MAP_1M, -pages1m);
-	update_page_count(PG_DIRECT_MAP_2G, -pages2g);
+	vmem_pte_free(__va(pmd_deref(*pmd)));
+	pmd_clear(pmd);
 }
 
-/*
- * Add a backed mem_map array to the virtual mem_map array.
- */
-int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
-		struct vmem_altmap *altmap)
+/* __ref: we'll only call vmemmap_alloc_block() via vmemmap_populate() */
+static int __ref modify_pmd_table(pud_t *pud, unsigned long addr,
+				  unsigned long end, bool add, bool direct)
 {
-	unsigned long pgt_prot, sgt_prot;
-	unsigned long address = start;
-	pgd_t *pg_dir;
-	p4d_t *p4_dir;
-	pud_t *pu_dir;
-	pmd_t *pm_dir;
-	pte_t *pt_dir;
+	unsigned long next, prot, pages = 0;
 	int ret = -ENOMEM;
+	pmd_t *pmd;
+	pte_t *pte;
 
-	pgt_prot = pgprot_val(PAGE_KERNEL);
-	sgt_prot = pgprot_val(SEGMENT_KERNEL);
-	if (!MACHINE_HAS_NX) {
-		pgt_prot &= ~_PAGE_NOEXEC;
-		sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
-	}
-	for (address = start; address < end;) {
-		pg_dir = pgd_offset_k(address);
-		if (pgd_none(*pg_dir)) {
-			p4_dir = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
-			if (!p4_dir)
-				goto out;
-			pgd_populate(&init_mm, pg_dir, p4_dir);
-		}
+	prot = pgprot_val(SEGMENT_KERNEL);
+	if (!MACHINE_HAS_NX)
+		prot &= ~_SEGMENT_ENTRY_NOEXEC;
 
-		p4_dir = p4d_offset(pg_dir, address);
-		if (p4d_none(*p4_dir)) {
-			pu_dir = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
-			if (!pu_dir)
-				goto out;
-			p4d_populate(&init_mm, p4_dir, pu_dir);
-		}
+	pmd = pmd_offset(pud, addr);
+	for (; addr < end; addr = next, pmd++) {
+		next = pmd_addr_end(addr, end);
+		if (!add) {
+			if (pmd_none(*pmd))
+				continue;
+			if (pmd_large(*pmd) && !add) {
+				if (IS_ALIGNED(addr, PMD_SIZE) &&
+				    IS_ALIGNED(next, PMD_SIZE)) {
+					if (!direct)
+						vmem_free_pages(pmd_deref(*pmd), get_order(PMD_SIZE));
+					pmd_clear(pmd);
+					pages++;
+				} else if (!direct && vmemmap_unuse_sub_pmd(addr, next)) {
+					vmem_free_pages(pmd_deref(*pmd), get_order(PMD_SIZE));
+					pmd_clear(pmd);
+				}
+				continue;
+			}
+		} else if (pmd_none(*pmd)) {
+			if (IS_ALIGNED(addr, PMD_SIZE) &&
+			    IS_ALIGNED(next, PMD_SIZE) &&
+			    MACHINE_HAS_EDAT1 && addr && direct &&
+			    !debug_pagealloc_enabled()) {
+				pmd_val(*pmd) = addr | prot;
+				pages++;
+				continue;
+			} else if (!direct && MACHINE_HAS_EDAT1) {
+				void *new_page;
 
-		pu_dir = pud_offset(p4_dir, address);
-		if (pud_none(*pu_dir)) {
-			pm_dir = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
-			if (!pm_dir)
+				/*
+				 * Use 1MB frames for vmemmap if available. We
+				 * always use large frames even if they are only
+				 * partially used. Otherwise we would have also
+				 * page tables since vmemmap_populate gets
+				 * called for each section separately.
+				 */
+				new_page = vmemmap_alloc_block(PMD_SIZE, NUMA_NO_NODE);
+				if (new_page) {
+					pmd_val(*pmd) = __pa(new_page) | prot;
+					if (!IS_ALIGNED(addr, PMD_SIZE) ||
+					    !IS_ALIGNED(next, PMD_SIZE)) {
+						vmemmap_use_new_sub_pmd(addr, next);
+					}
+					continue;
+				}
+			}
+			pte = vmem_pte_alloc();
+			if (!pte)
 				goto out;
-			pud_populate(&init_mm, pu_dir, pm_dir);
+			pmd_populate(&init_mm, pmd, pte);
+		} else if (pmd_large(*pmd)) {
+			if (!direct)
+				vmemmap_use_sub_pmd(addr, next);
+			continue;
 		}
+		ret = modify_pte_table(pmd, addr, next, add, direct);
+		if (ret)
+			goto out;
+		if (!add)
+			try_free_pte_table(pmd, addr & PMD_MASK);
+	}
+	ret = 0;
+out:
+	if (direct)
+		update_page_count(PG_DIRECT_MAP_1M, add ? pages : -pages);
+	return ret;
+}
 
-		pm_dir = pmd_offset(pu_dir, address);
-		if (pmd_none(*pm_dir)) {
-			/* Use 1MB frames for vmemmap if available. We always
-			 * use large frames even if they are only partially
-			 * used.
-			 * Otherwise we would have also page tables since
-			 * vmemmap_populate gets called for each section
-			 * separately. */
-			if (MACHINE_HAS_EDAT1) {
-				void *new_page;
+static void try_free_pmd_table(pud_t *pud, unsigned long start)
+{
+	const unsigned long end = start + PUD_SIZE;
+	pmd_t *pmd;
+	int i;
+
+	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+	if (end > VMALLOC_START)
+		return;
+#ifdef CONFIG_KASAN
+	if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+		return;
+#endif
+	pmd = pmd_offset(pud, start);
+	for (i = 0; i < PTRS_PER_PMD; i++, pmd++)
+		if (!pmd_none(*pmd))
+			return;
+	vmem_free_pages(pud_deref(*pud), CRST_ALLOC_ORDER);
+	pud_clear(pud);
+}
 
-				new_page = vmemmap_alloc_block(PMD_SIZE, node);
-				if (!new_page)
-					goto out;
-				pmd_val(*pm_dir) = __pa(new_page) | sgt_prot;
-				address = (address + PMD_SIZE) & PMD_MASK;
+static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end,
+			    bool add, bool direct)
+{
+	unsigned long next, prot, pages = 0;
+	int ret = -ENOMEM;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	prot = pgprot_val(REGION3_KERNEL);
+	if (!MACHINE_HAS_NX)
+		prot &= ~_REGION_ENTRY_NOEXEC;
+	pud = pud_offset(p4d, addr);
+	for (; addr < end; addr = next, pud++) {
+		next = pud_addr_end(addr, end);
+		if (!add) {
+			if (pud_none(*pud))
+				continue;
+			if (pud_large(*pud)) {
+				if (IS_ALIGNED(addr, PUD_SIZE) &&
+				    IS_ALIGNED(next, PUD_SIZE)) {
+					pud_clear(pud);
+					pages++;
+				}
+				continue;
+			}
+		} else if (pud_none(*pud)) {
+			if (IS_ALIGNED(addr, PUD_SIZE) &&
+			    IS_ALIGNED(next, PUD_SIZE) &&
+			    MACHINE_HAS_EDAT2 && addr && direct &&
+			    !debug_pagealloc_enabled()) {
+				pud_val(*pud) = addr | prot;
+				pages++;
 				continue;
 			}
-			pt_dir = vmem_pte_alloc();
-			if (!pt_dir)
+			pmd = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
+			if (!pmd)
 				goto out;
-			pmd_populate(&init_mm, pm_dir, pt_dir);
-		} else if (pmd_large(*pm_dir)) {
-			address = (address + PMD_SIZE) & PMD_MASK;
+			pud_populate(&init_mm, pud, pmd);
+		} else if (pud_large(*pud)) {
 			continue;
 		}
+		ret = modify_pmd_table(pud, addr, next, add, direct);
+		if (ret)
+			goto out;
+		if (!add)
+			try_free_pmd_table(pud, addr & PUD_MASK);
+	}
+	ret = 0;
+out:
+	if (direct)
+		update_page_count(PG_DIRECT_MAP_2G, add ? pages : -pages);
+	return ret;
+}
 
-		pt_dir = pte_offset_kernel(pm_dir, address);
-		if (pte_none(*pt_dir)) {
-			void *new_page;
+static void try_free_pud_table(p4d_t *p4d, unsigned long start)
+{
+	const unsigned long end = start + P4D_SIZE;
+	pud_t *pud;
+	int i;
+
+	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+	if (end > VMALLOC_START)
+		return;
+#ifdef CONFIG_KASAN
+	if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+		return;
+#endif
+
+	pud = pud_offset(p4d, start);
+	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
+		if (!pud_none(*pud))
+			return;
+	}
+	vmem_free_pages(p4d_deref(*p4d), CRST_ALLOC_ORDER);
+	p4d_clear(p4d);
+}
 
-			new_page = vmemmap_alloc_block(PAGE_SIZE, node);
-			if (!new_page)
+static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end,
+			    bool add, bool direct)
+{
+	unsigned long next;
+	int ret = -ENOMEM;
+	p4d_t *p4d;
+	pud_t *pud;
+
+	p4d = p4d_offset(pgd, addr);
+	for (; addr < end; addr = next, p4d++) {
+		next = p4d_addr_end(addr, end);
+		if (!add) {
+			if (p4d_none(*p4d))
+				continue;
+		} else if (p4d_none(*p4d)) {
+			pud = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
+			if (!pud)
 				goto out;
-			pte_val(*pt_dir) = __pa(new_page) | pgt_prot;
 		}
-		address += PAGE_SIZE;
+		ret = modify_pud_table(p4d, addr, next, add, direct);
+		if (ret)
+			goto out;
+		if (!add)
+			try_free_pud_table(p4d, addr & P4D_MASK);
 	}
 	ret = 0;
 out:
 	return ret;
 }
 
-void vmemmap_free(unsigned long start, unsigned long end,
-		struct vmem_altmap *altmap)
+static void try_free_p4d_table(pgd_t *pgd, unsigned long start)
 {
+	const unsigned long end = start + PGDIR_SIZE;
+	p4d_t *p4d;
+	int i;
+
+	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+	if (end > VMALLOC_START)
+		return;
+#ifdef CONFIG_KASAN
+	if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+		return;
+#endif
+
+	p4d = p4d_offset(pgd, start);
+	for (i = 0; i < PTRS_PER_P4D; i++, p4d++) {
+		if (!p4d_none(*p4d))
+			return;
+	}
+	vmem_free_pages(pgd_deref(*pgd), CRST_ALLOC_ORDER);
+	pgd_clear(pgd);
 }
 
-/*
- * Add memory segment to the segment list if it doesn't overlap with
- * an already present segment.
- */
-static int insert_memory_segment(struct memory_segment *seg)
+static int modify_pagetable(unsigned long start, unsigned long end, bool add,
+			    bool direct)
 {
-	struct memory_segment *tmp;
+	unsigned long addr, next;
+	int ret = -ENOMEM;
+	pgd_t *pgd;
+	p4d_t *p4d;
 
-	if (seg->start + seg->size > VMEM_MAX_PHYS ||
-	    seg->start + seg->size < seg->start)
-		return -ERANGE;
+	if (WARN_ON_ONCE(!PAGE_ALIGNED(start | end)))
+		return -EINVAL;
+	for (addr = start; addr < end; addr = next) {
+		next = pgd_addr_end(addr, end);
+		pgd = pgd_offset_k(addr);
 
-	list_for_each_entry(tmp, &mem_segs, list) {
-		if (seg->start >= tmp->start + tmp->size)
-			continue;
-		if (seg->start + seg->size <= tmp->start)
-			continue;
-		return -ENOSPC;
+		if (!add) {
+			if (pgd_none(*pgd))
+				continue;
+		} else if (pgd_none(*pgd)) {
+			p4d = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
+			if (!p4d)
+				goto out;
+			pgd_populate(&init_mm, pgd, p4d);
+		}
+		ret = modify_p4d_table(pgd, addr, next, add, direct);
+		if (ret)
+			goto out;
+		if (!add)
+			try_free_p4d_table(pgd, addr & PGDIR_MASK);
 	}
-	list_add(&seg->list, &mem_segs);
-	return 0;
+	ret = 0;
+out:
+	if (!add)
+		flush_tlb_kernel_range(start, end);
+	return ret;
+}
+
+static int add_pagetable(unsigned long start, unsigned long end, bool direct)
+{
+	return modify_pagetable(start, end, true, direct);
+}
+
+static int remove_pagetable(unsigned long start, unsigned long end, bool direct)
+{
+	return modify_pagetable(start, end, false, direct);
 }
 
 /*
- * Remove memory segment from the segment list.
+ * Add a physical memory range to the 1:1 mapping.
  */
-static void remove_memory_segment(struct memory_segment *seg)
+static int vmem_add_range(unsigned long start, unsigned long size)
 {
-	list_del(&seg->list);
+	return add_pagetable(start, start + size, true);
 }
 
-static void __remove_shared_memory(struct memory_segment *seg)
+/*
+ * Remove a physical memory range from the 1:1 mapping.
+ */
+static void vmem_remove_range(unsigned long start, unsigned long size)
 {
-	remove_memory_segment(seg);
-	vmem_remove_range(seg->start, seg->size);
+	remove_pagetable(start, start + size, true);
 }
 
-int vmem_remove_mapping(unsigned long start, unsigned long size)
+/*
+ * Add a backed mem_map array to the virtual mem_map array.
+ */
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
+			       struct vmem_altmap *altmap)
 {
-	struct memory_segment *seg;
 	int ret;
 
 	mutex_lock(&vmem_mutex);
+	/* We don't care about the node, just use NUMA_NO_NODE on allocations */
+	ret = add_pagetable(start, end, false);
+	if (ret)
+		remove_pagetable(start, end, false);
+	mutex_unlock(&vmem_mutex);
+	return ret;
+}
 
-	ret = -ENOENT;
-	list_for_each_entry(seg, &mem_segs, list) {
-		if (seg->start == start && seg->size == size)
-			break;
-	}
-
-	if (seg->start != start || seg->size != size)
-		goto out;
+void vmemmap_free(unsigned long start, unsigned long end,
+		  struct vmem_altmap *altmap)
+{
+	mutex_lock(&vmem_mutex);
+	remove_pagetable(start, end, false);
+	mutex_unlock(&vmem_mutex);
+}
 
-	ret = 0;
-	__remove_shared_memory(seg);
-	kfree(seg);
-out:
+void vmem_remove_mapping(unsigned long start, unsigned long size)
+{
+	mutex_lock(&vmem_mutex);
+	vmem_remove_range(start, size);
 	mutex_unlock(&vmem_mutex);
-	return ret;
 }
 
 int vmem_add_mapping(unsigned long start, unsigned long size)
 {
-	struct memory_segment *seg;
 	int ret;
 
-	mutex_lock(&vmem_mutex);
-	ret = -ENOMEM;
-	seg = kzalloc(sizeof(*seg), GFP_KERNEL);
-	if (!seg)
-		goto out;
-	seg->start = start;
-	seg->size = size;
-
-	ret = insert_memory_segment(seg);
-	if (ret)
-		goto out_free;
+	if (start + size > VMEM_MAX_PHYS ||
+	    start + size < start)
+		return -ERANGE;
 
-	ret = vmem_add_mem(start, size);
+	mutex_lock(&vmem_mutex);
+	ret = vmem_add_range(start, size);
 	if (ret)
-		goto out_remove;
-	goto out;
-
-out_remove:
-	__remove_shared_memory(seg);
-out_free:
-	kfree(seg);
-out:
+		vmem_remove_range(start, size);
 	mutex_unlock(&vmem_mutex);
 	return ret;
 }
@@ -402,7 +557,7 @@ void __init vmem_map_init(void)
 	struct memblock_region *reg;
 
 	for_each_memblock(memory, reg)
-		vmem_add_mem(reg->base, reg->size);
+		vmem_add_range(reg->base, reg->size);
 	__set_memory((unsigned long)_stext,
 		     (unsigned long)(_etext - _stext) >> PAGE_SHIFT,
 		     SET_MEMORY_RO | SET_MEMORY_X);
@@ -421,27 +576,3 @@ void __init vmem_map_init(void)
 	pr_info("Write protected kernel read-only data: %luk\n",
 		(unsigned long)(__end_rodata - _stext) >> 10);
 }
-
-/*
- * Convert memblock.memory  to a memory segment list so there is a single
- * list that contains all memory segments.
- */
-static int __init vmem_convert_memory_chunk(void)
-{
-	struct memblock_region *reg;
-	struct memory_segment *seg;
-
-	mutex_lock(&vmem_mutex);
-	for_each_memblock(memory, reg) {
-		seg = kzalloc(sizeof(*seg), GFP_KERNEL);
-		if (!seg)
-			panic("Out of memory...\n");
-		seg->start = reg->base;
-		seg->size = reg->size;
-		insert_memory_segment(seg);
-	}
-	mutex_unlock(&vmem_mutex);
-	return 0;
-}
-
-core_initcall(vmem_convert_memory_chunk);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index f4242b894cf2..8fe7bdfc8d15 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -49,6 +49,7 @@ struct bpf_jit {
 	int r1_thunk_ip;	/* Address of expoline thunk for 'br %r1' */
 	int r14_thunk_ip;	/* Address of expoline thunk for 'br %r14' */
 	int tail_call_start;	/* Tail call start offset */
+	int excnt;		/* Number of exception table entries */
 	int labels[1];		/* Labels for local jumps */
 };
 
@@ -588,6 +589,84 @@ 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.
+	 */
+	if (insn[0] != 0xe3) /* common llgc, llgh, llgf and lg prefix */
+		return -1;
+	if (insn[5] != 0x90 && /* llgc */
+	    insn[5] != 0x91 && /* llgh */
+	    insn[5] != 0x16 && /* llgf */
+	    insn[5] != 0x04) /* lg */
+		return -1;
+	return insn[1] >> 4;
+}
+
+static bool ex_handler_bpf(const struct exception_table_entry *x,
+			   struct pt_regs *regs)
+{
+	int regno;
+	u8 *insn;
+
+	regs->psw.addr = extable_fixup(x);
+	insn = (u8 *)__rewind_psw(regs->psw, regs->int_code >> 16);
+	regno = get_probe_mem_regno(insn);
+	if (WARN_ON_ONCE(regno < 0))
+		/* JIT bug - unexpected instruction. */
+		return false;
+	regs->gprs[regno] = 0;
+	return true;
+}
+
+static int bpf_jit_probe_mem(struct bpf_jit *jit, struct bpf_prog *fp,
+			     int probe_prg, int nop_prg)
+{
+	struct exception_table_entry *ex;
+	s64 delta;
+	u8 *insn;
+	int prg;
+	int i;
+
+	if (!fp->aux->extable)
+		/* Do nothing during early JIT passes. */
+		return 0;
+	insn = jit->prg_buf + probe_prg;
+	if (WARN_ON_ONCE(get_probe_mem_regno(insn) < 0))
+		/* JIT bug - unexpected probe instruction. */
+		return -1;
+	if (WARN_ON_ONCE(probe_prg + insn_length(*insn) != nop_prg))
+		/* JIT bug - gap between probe and nop instructions. */
+		return -1;
+	for (i = 0; i < 2; i++) {
+		if (WARN_ON_ONCE(jit->excnt >= fp->aux->num_exentries))
+			/* Verifier bug - not enough entries. */
+			return -1;
+		ex = &fp->aux->extable[jit->excnt];
+		/* Add extable entries for probe and nop instructions. */
+		prg = i == 0 ? probe_prg : nop_prg;
+		delta = jit->prg_buf + prg - (u8 *)&ex->insn;
+		if (WARN_ON_ONCE(delta < INT_MIN || delta > INT_MAX))
+			/* JIT bug - code and extable must be close. */
+			return -1;
+		ex->insn = delta;
+		/*
+		 * Always land on the nop. Note that extable infrastructure
+		 * ignores fixup field, it is handled by ex_handler_bpf().
+		 */
+		delta = jit->prg_buf + nop_prg - (u8 *)&ex->fixup;
+		if (WARN_ON_ONCE(delta < INT_MIN || delta > INT_MAX))
+			/* JIT bug - landing pad and extable must be close. */
+			return -1;
+		ex->fixup = delta;
+		ex->handler = (u8 *)ex_handler_bpf - (u8 *)&ex->handler;
+		jit->excnt++;
+	}
+	return 0;
+}
+
 /*
  * Compile one eBPF instruction into s390x code
  *
@@ -604,7 +683,14 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 	u32 *addrs = jit->addrs;
 	s32 imm = insn->imm;
 	s16 off = insn->off;
+	int probe_prg = -1;
 	unsigned int mask;
+	int nop_prg;
+	int err;
+
+	if (BPF_CLASS(insn->code) == BPF_LDX &&
+	    BPF_MODE(insn->code) == BPF_PROBE_MEM)
+		probe_prg = jit->prg;
 
 	switch (insn->code) {
 	/*
@@ -1119,6 +1205,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 	 * BPF_LDX
 	 */
 	case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src + off) */
+	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
 		/* llgc %dst,0(off,%src) */
 		EMIT6_DISP_LH(0xe3000000, 0x0090, dst_reg, src_reg, REG_0, off);
 		jit->seen |= SEEN_MEM;
@@ -1126,6 +1213,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 			insn_count = 2;
 		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) */
 		EMIT6_DISP_LH(0xe3000000, 0x0091, dst_reg, src_reg, REG_0, off);
 		jit->seen |= SEEN_MEM;
@@ -1133,6 +1221,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 			insn_count = 2;
 		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) */
 		jit->seen |= SEEN_MEM;
 		EMIT6_DISP_LH(0xe3000000, 0x0016, dst_reg, src_reg, REG_0, off);
@@ -1140,6 +1229,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 			insn_count = 2;
 		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) */
 		jit->seen |= SEEN_MEM;
 		EMIT6_DISP_LH(0xe3000000, 0x0004, dst_reg, src_reg, REG_0, off);
@@ -1485,6 +1575,23 @@ branch_oc:
 		pr_err("Unknown opcode %02x\n", insn->code);
 		return -1;
 	}
+
+	if (probe_prg != -1) {
+		/*
+		 * Handlers of certain exceptions leave psw.addr pointing to
+		 * the instruction directly after the failing one. Therefore,
+		 * create two exception table entries and also add a nop in
+		 * case two probing instructions come directly after each
+		 * other.
+		 */
+		nop_prg = jit->prg;
+		/* bcr 0,%0 */
+		_EMIT2(0x0700);
+		err = bpf_jit_probe_mem(jit, fp, probe_prg, nop_prg);
+		if (err < 0)
+			return err;
+	}
+
 	return insn_count;
 }
 
@@ -1527,6 +1634,7 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp,
 	jit->lit32 = jit->lit32_start;
 	jit->lit64 = jit->lit64_start;
 	jit->prg = 0;
+	jit->excnt = 0;
 
 	bpf_jit_prologue(jit, stack_depth);
 	if (bpf_set_addr(jit, 0) < 0)
@@ -1551,6 +1659,12 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp,
 		jit->lit64_start = ALIGN(jit->lit64_start, 8);
 	jit->size = jit->lit64_start + lit64_size;
 	jit->size_prg = jit->prg;
+
+	if (WARN_ON_ONCE(fp->aux->extable &&
+			 jit->excnt != fp->aux->num_exentries))
+		/* Verifier bug - too many entries. */
+		return -1;
+
 	return 0;
 }
 
@@ -1565,6 +1679,29 @@ struct s390_jit_data {
 	int pass;
 };
 
+static struct bpf_binary_header *bpf_jit_alloc(struct bpf_jit *jit,
+					       struct bpf_prog *fp)
+{
+	struct bpf_binary_header *header;
+	u32 extable_size;
+	u32 code_size;
+
+	/* We need two entries per insn. */
+	fp->aux->num_exentries *= 2;
+
+	code_size = roundup(jit->size,
+			    __alignof__(struct exception_table_entry));
+	extable_size = fp->aux->num_exentries *
+		sizeof(struct exception_table_entry);
+	header = bpf_jit_binary_alloc(code_size + extable_size, &jit->prg_buf,
+				      8, jit_fill_hole);
+	if (!header)
+		return NULL;
+	fp->aux->extable = (struct exception_table_entry *)
+		(jit->prg_buf + code_size);
+	return header;
+}
+
 /*
  * Compile eBPF program "fp"
  */
@@ -1631,7 +1768,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	/*
 	 * Final pass: Allocate and generate program
 	 */
-	header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 8, jit_fill_hole);
+	header = bpf_jit_alloc(&jit, fp);
 	if (!header) {
 		fp = orig_fp;
 		goto free_addrs;
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 08e1d619398e..fdebd286f402 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -94,7 +94,18 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		}
 		zdev->fh = ccdf->fh;
 		zdev->state = ZPCI_FN_STATE_CONFIGURED;
-		zpci_create_device(zdev);
+		ret = zpci_enable_device(zdev);
+		if (ret)
+			break;
+
+		pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn);
+		if (!pdev)
+			break;
+
+		pci_bus_add_device(pdev);
+		pci_lock_rescan_remove();
+		pci_bus_add_devices(zdev->zbus->bus);
+		pci_unlock_rescan_remove();
 		break;
 	case 0x0302: /* Reserved -> Standby */
 		if (!zdev) {
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 38efa3e852c4..401cf670a243 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -155,10 +155,12 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 		return -EINVAL;
 
 	/*
-	 * Only support read access to MIO capable devices on a MIO enabled
-	 * system. Otherwise we would have to check for every address if it is
-	 * a special ZPCI_ADDR and we would have to do a get_pfn() which we
-	 * don't need for MIO capable devices.
+	 * We only support write access to MIO capable devices if we are on
+	 * a MIO enabled system. Otherwise we would have to check for every
+	 * address if it is a special ZPCI_ADDR and would have to do
+	 * a get_pfn() which we don't need for MIO capable devices.  Currently
+	 * ISM devices are the only devices without MIO support and there is no
+	 * known need for accessing these from userspace.
 	 */
 	if (static_branch_likely(&have_mio)) {
 		ret = __memcpy_toio_inuser((void  __iomem *) mmio_addr,
@@ -282,10 +284,12 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 		return -EINVAL;
 
 	/*
-	 * Only support write access to MIO capable devices on a MIO enabled
-	 * system. Otherwise we would have to check for every address if it is
-	 * a special ZPCI_ADDR and we would have to do a get_pfn() which we
-	 * don't need for MIO capable devices.
+	 * We only support read access to MIO capable devices if we are on
+	 * a MIO enabled system. Otherwise we would have to check for every
+	 * address if it is a special ZPCI_ADDR and would have to do
+	 * a get_pfn() which we don't need for MIO capable devices.  Currently
+	 * ISM devices are the only devices without MIO support and there is no
+	 * known need for accessing these from userspace.
 	 */
 	if (static_branch_likely(&have_mio)) {
 		ret = __memcpy_fromio_inuser(
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index f37b95a80232..7c2a8a703b9a 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v,i)		WRITE_ONCE((v)->counter, (i))
 
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 22d968bfe9bb..d770da3f8b6f 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -12,6 +12,7 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
 extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address);
 extern void pmd_free(struct mm_struct *mm, pmd_t *pmd);
+#define __pmd_free_tlb(tlb, pmdp, addr)		pmd_free((tlb)->mm, (pmdp))
 #endif
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
@@ -33,13 +34,4 @@ do {							\
 	tlb_remove_page((tlb), (pte));			\
 } while (0)
 
-#if CONFIG_PGTABLE_LEVELS > 2
-#define __pmd_free_tlb(tlb, pmdp, addr)			\
-do {							\
-	struct page *page = virt_to_page(pmdp);		\
-	pgtable_pmd_page_dtor(page);			\
-	tlb_remove_page((tlb), page);			\
-} while (0);
-#endif
-
 #endif /* __ASM_SH_PGALLOC_H */
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 956a7a03b0c8..9bac5bbb67f3 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -199,7 +199,7 @@ syscall_trace_entry:
 	mov.l	@(OFF_R7,r15), r7   ! arg3
 	mov.l	@(OFF_R3,r15), r3   ! syscall_nr
 	!
-	mov.l	2f, r10			! Number of syscalls
+	mov.l	6f, r10			! Number of syscalls
 	cmp/hs	r10, r3
 	bf	syscall_call
 	mov	#-ENOSYS, r0
@@ -353,7 +353,7 @@ ENTRY(system_call)
 	tst	r9, r8
 	bf	syscall_trace_entry
 	!
-	mov.l	2f, r8			! Number of syscalls
+	mov.l	6f, r8			! Number of syscalls
 	cmp/hs	r8, r3
 	bt	syscall_badsys
 	!
@@ -392,7 +392,7 @@ syscall_exit:
 #if !defined(CONFIG_CPU_SH2)
 1:	.long	TRA
 #endif
-2:	.long	NR_syscalls
+6:	.long	NR_syscalls
 3:	.long	sys_call_table
 7:	.long	do_syscall_trace_enter
 8:	.long	do_syscall_trace_leave
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 1b04270e5460..0646c5961846 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -119,7 +119,7 @@ static void ftrace_mod_code(void)
 	 * But if one were to fail, then they all should, and if one were
 	 * to succeed, then they all should.
 	 */
-	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
+	mod_code_status = copy_to_kernel_nofault(mod_code_ip, mod_code_newcode,
 					     MCOUNT_INSN_SIZE);
 
 	/* if we fail, then kill any new writers */
@@ -203,7 +203,7 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	 */
 
 	/* read the text we want to modify */
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/* Make sure it is what we expect it to be */
@@ -268,7 +268,7 @@ static int ftrace_mod(unsigned long ip, unsigned long old_addr,
 {
 	unsigned char code[MCOUNT_INSN_SIZE];
 
-	if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(code, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	if (old_addr != __raw_readl((unsigned long *)code))
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index a33025451fcd..9c3d32b80038 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -118,7 +118,7 @@ int is_valid_bugaddr(unsigned long addr)
 
 	if (addr < PAGE_OFFSET)
 		return 0;
-	if (probe_kernel_address((insn_size_t *)addr, opcode))
+	if (get_kernel_nofault(opcode, (insn_size_t *)addr))
 		return 0;
 	if (opcode == TRAPA_BUG_OPCODE)
 		return 1;
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index 286bc8ecf15b..ca2547df9652 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -156,7 +156,7 @@ static int sha256_sparc64_import(struct shash_desc *desc, const void *in)
 	return 0;
 }
 
-static struct shash_alg sha256 = {
+static struct shash_alg sha256_alg = {
 	.digestsize	=	SHA256_DIGEST_SIZE,
 	.init		=	sha256_sparc64_init,
 	.update		=	sha256_sparc64_update,
@@ -174,7 +174,7 @@ static struct shash_alg sha256 = {
 	}
 };
 
-static struct shash_alg sha224 = {
+static struct shash_alg sha224_alg = {
 	.digestsize	=	SHA224_DIGEST_SIZE,
 	.init		=	sha224_sparc64_init,
 	.update		=	sha256_sparc64_update,
@@ -206,13 +206,13 @@ static bool __init sparc64_has_sha256_opcode(void)
 static int __init sha256_sparc64_mod_init(void)
 {
 	if (sparc64_has_sha256_opcode()) {
-		int ret = crypto_register_shash(&sha224);
+		int ret = crypto_register_shash(&sha224_alg);
 		if (ret < 0)
 			return ret;
 
-		ret = crypto_register_shash(&sha256);
+		ret = crypto_register_shash(&sha256_alg);
 		if (ret < 0) {
-			crypto_unregister_shash(&sha224);
+			crypto_unregister_shash(&sha224_alg);
 			return ret;
 		}
 
@@ -225,8 +225,8 @@ static int __init sha256_sparc64_mod_init(void)
 
 static void __exit sha256_sparc64_mod_fini(void)
 {
-	crypto_unregister_shash(&sha224);
-	crypto_unregister_shash(&sha256);
+	crypto_unregister_shash(&sha224_alg);
+	crypto_unregister_shash(&sha256_alg);
 }
 
 module_init(sha256_sparc64_mod_init);
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 94c930f0bc62..efad5532f169 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -18,8 +18,6 @@
 #include <asm/barrier.h>
 #include <asm-generic/atomic64.h>
 
-#define ATOMIC_INIT(i)  { (i) }
-
 int atomic_add_return(int, atomic_t *);
 int atomic_fetch_add(int, atomic_t *);
 int atomic_fetch_and(int, atomic_t *);
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index b60448397d4f..6b235d3d1d9d 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -12,7 +12,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
diff --git a/arch/sparc/include/asm/percpu_64.h b/arch/sparc/include/asm/percpu_64.h
index 32ef6f05cc56..a8786a4b90b6 100644
--- a/arch/sparc/include/asm/percpu_64.h
+++ b/arch/sparc/include/asm/percpu_64.h
@@ -4,7 +4,9 @@
 
 #include <linux/compiler.h>
 
+#ifndef BUILD_VDSO
 register unsigned long __local_per_cpu_offset asm("g5");
+#endif
 
 #ifdef CONFIG_SMP
 
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 0f6d0c4f6683..ace0d48e837e 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -2,6 +2,8 @@
 #ifndef _SPARC_TRAP_BLOCK_H
 #define _SPARC_TRAP_BLOCK_H
 
+#include <linux/threads.h>
+
 #include <asm/hypervisor.h>
 #include <asm/asi.h>
 
diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c
index e929c0966696..8ccd56813f68 100644
--- a/arch/um/kernel/maccess.c
+++ b/arch/um/kernel/maccess.c
@@ -7,7 +7,7 @@
 #include <linux/kernel.h>
 #include <os.h>
 
-bool probe_kernel_read_allowed(const void *src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *src, size_t size)
 {
 	void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
 
diff --git a/arch/unicore32/.gitignore b/arch/unicore32/.gitignore
deleted file mode 100644
index e82f3fb57ba0..000000000000
--- a/arch/unicore32/.gitignore
+++ /dev/null
@@ -1,22 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Generated include files
-#
-include/generated
-#
-# Generated ld script file
-#
-kernel/vmlinux.lds
-#
-# Generated images in boot
-#
-boot/Image
-boot/zImage
-boot/uImage
-#
-# Generated files in boot/compressed
-#
-boot/compressed/piggy.S
-boot/compressed/piggy.gzip
-boot/compressed/vmlinux
-boot/compressed/vmlinux.lds
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
deleted file mode 100644
index 11ba1839d198..000000000000
--- a/arch/unicore32/Kconfig
+++ /dev/null
@@ -1,200 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config UNICORE32
-	def_bool y
-	select ARCH_32BIT_OFF_T
-	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select ARCH_HAS_KEEPINITRD
-	select ARCH_MIGHT_HAVE_PC_PARPORT
-	select ARCH_MIGHT_HAVE_PC_SERIO
-	select HAVE_KERNEL_GZIP
-	select HAVE_KERNEL_BZIP2
-	select GENERIC_ATOMIC64
-	select HAVE_KERNEL_LZO
-	select HAVE_KERNEL_LZMA
-	select HAVE_PCI
-	select VIRT_TO_BUS
-	select ARCH_HAVE_CUSTOM_GPIO_H
-	select GENERIC_FIND_FIRST_BIT
-	select GENERIC_IRQ_PROBE
-	select GENERIC_IRQ_SHOW
-	select ARCH_WANT_FRAME_POINTERS
-	select GENERIC_IOMAP
-	select MODULES_USE_ELF_REL
-	select NEED_DMA_MAP_STATE
-	select MMU_GATHER_NO_RANGE if MMU
-	help
-	  UniCore-32 is 32-bit Instruction Set Architecture,
-	  including a series of low-power-consumption RISC chip
-	  designs licensed by PKUnity Ltd.
-	  Please see web page at <http://www.pkunity.com/>.
-
-config GENERIC_CSUM
-	def_bool y
-
-config NO_IOPORT_MAP
-	bool
-
-config STACKTRACE_SUPPORT
-	def_bool y
-
-config LOCKDEP_SUPPORT
-	def_bool y
-
-config ARCH_HAS_ILOG2_U32
-	bool
-
-config ARCH_HAS_ILOG2_U64
-	bool
-
-config GENERIC_HWEIGHT
-	def_bool y
-
-config GENERIC_CALIBRATE_DELAY
-	def_bool y
-
-config ARCH_MAY_HAVE_PC_FDC
-	bool
-
-config ZONE_DMA
-	def_bool y
-
-menu "System Type"
-
-config MMU
-	def_bool y
-
-config ARCH_FPGA
-	bool
-
-config ARCH_PUV3
-	def_bool y
-	select CPU_UCV2
-	select GENERIC_CLOCKEVENTS
-	select HAVE_LEGACY_CLK
-	select GPIOLIB
-
-# CONFIGs for ARCH_PUV3
-
-if ARCH_PUV3
-
-choice
-	prompt "Board Selection"
-	default PUV3_DB0913
-
-config PUV3_FPGA_DLX200
-	select ARCH_FPGA
-	bool "FPGA board"
-
-config PUV3_DB0913
-	bool "DEBUG board (0913)"
-
-config PUV3_NB0916
-	bool "NetBook board (0916)"
-	select PWM
-	select PWM_PUV3
-
-config PUV3_SMW0919
-	bool "Security Mini-Workstation board (0919)"
-
-endchoice
-
-config PUV3_PM
-	def_bool y if !ARCH_FPGA
-
-endif
-
-source "arch/unicore32/mm/Kconfig"
-
-comment "Floating point support"
-
-config UNICORE_FPU_F64
-	def_bool y if !ARCH_FPGA
-
-endmenu
-
-menu "Kernel Features"
-
-source "kernel/Kconfig.hz"
-
-config LEDS
-	def_bool y
-	depends on GPIOLIB
-
-config ALIGNMENT_TRAP
-	def_bool y
-	help
-	  Unicore processors can not fetch/store information which is not
-	  naturally aligned on the bus, i.e., a 4 byte fetch must start at an
-	  address divisible by 4. On 32-bit Unicore processors, these non-aligned
-	  fetch/store instructions will be emulated in software if you say
-	  here, which has a severe performance impact. This is necessary for
-	  correct operation of some network protocols. With an IP-only
-	  configuration it is safe to say N, otherwise say Y.
-
-endmenu
-
-menu "Boot options"
-
-config CMDLINE
-	string "Default kernel command string"
-	default ""
-
-config CMDLINE_FORCE
-	bool "Always use the default kernel command string"
-	depends on CMDLINE != ""
-	help
-	  Always use the default kernel command string, even if the boot
-	  loader passes other arguments to the kernel.
-	  This is useful if you cannot or don't want to change the
-	  command-line options your boot loader passes to the kernel.
-
-	  If unsure, say N.
-
-endmenu
-
-menu "Power management options"
-
-source "kernel/power/Kconfig"
-
-source "drivers/cpufreq/Kconfig"
-
-config ARCH_SUSPEND_POSSIBLE
-	def_bool y if !ARCH_FPGA
-
-config ARCH_HIBERNATION_POSSIBLE
-	def_bool y if !ARCH_FPGA
-
-endmenu
-
-if ARCH_PUV3
-
-config PUV3_GPIO
-	bool
-	depends on !ARCH_FPGA
-	select GPIO_SYSFS
-	default y
-
-if PUV3_NB0916
-
-menu "PKUnity NetBook-0916 Features"
-
-config I2C_BATTERY_BQ27200
-	tristate "I2C Battery BQ27200 Support"
-	select I2C_PUV3
-	select POWER_SUPPLY
-	select BATTERY_BQ27XXX
-
-config I2C_EEPROM_AT24
-	tristate "I2C EEPROMs AT24 support"
-	select I2C_PUV3
-	select EEPROM_AT24
-
-config LCD_BACKLIGHT
-	tristate "LCD Backlight support"
-	select BACKLIGHT_PWM
-
-endmenu
-
-endif
-
-endif
diff --git a/arch/unicore32/Kconfig.debug b/arch/unicore32/Kconfig.debug
deleted file mode 100644
index ca0ff97657ef..000000000000
--- a/arch/unicore32/Kconfig.debug
+++ /dev/null
@@ -1,29 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-config EARLY_PRINTK
-	def_bool DEBUG_OCD
-	help
-	  Write kernel log output directly into the ocd or to a serial port.
-
-	  This is useful for kernel debugging when your machine crashes very
-	  early before the console code is initialized. For normal operation
-	  it is not recommended because it looks ugly and doesn't cooperate
-	  with klogd/syslogd or the X server. You should normally N here,
-	  unless you want to debug such a crash.
-
-# These options are only for real kernel hackers who want to get their hands dirty.
-config DEBUG_LL
-	bool "Kernel low-level debugging functions"
-	depends on DEBUG_KERNEL
-	help
-	  Say Y here to include definitions of printascii, printch, printhex
-	  in the kernel.  This is helpful if you are debugging code that
-	  executes before the console is initialized.
-
-config DEBUG_OCD
-	bool "Kernel low-level debugging via On-Chip-Debugger"
-	depends on DEBUG_LL
-	default y
-	help
-	  Say Y here if you want the debug print routines to direct their
-	  output to the UniCore On-Chip-Debugger channel using CP #1.
diff --git a/arch/unicore32/Makefile b/arch/unicore32/Makefile
deleted file mode 100644
index 390819947c37..000000000000
--- a/arch/unicore32/Makefile
+++ /dev/null
@@ -1,59 +0,0 @@
-#
-# arch/unicore32/Makefile
-#
-# This file is included by the global makefile so that you can add your own
-# architecture-specific flags and dependencies.
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-# Copyright (C) 2002~2010 by Guan Xue-tao
-#
-ifneq ($(SUBARCH),$(ARCH))
-	ifeq ($(CROSS_COMPILE),)
-		CROSS_COMPILE := $(call cc-cross-prefix, unicore32-linux-)
-	endif
-endif
-
-LDFLAGS_vmlinux		:= -p --no-undefined -X
-
-OBJCOPYFLAGS		:= -O binary -R .note -R .note.gnu.build-id -R .comment -S
-
-# Never generate .eh_frame
-KBUILD_CFLAGS		+= $(call cc-option,-fno-dwarf2-cfi-asm)
-
-# Never use hard float in kernel
-KBUILD_CFLAGS		+= -msoft-float
-
-ifeq ($(CONFIG_FRAME_POINTER),y)
-KBUILD_CFLAGS		+= -mno-sched-prolog
-endif
-
-CHECKFLAGS		+= -D__unicore32__
-
-head-y			:= arch/unicore32/kernel/head.o
-
-core-y			+= arch/unicore32/kernel/
-core-y			+= arch/unicore32/mm/
-
-libs-y			+= arch/unicore32/lib/
-
-boot			:= arch/unicore32/boot
-
-# Default target when executing plain make
-KBUILD_IMAGE		:= $(boot)/zImage
-
-all:	zImage
-
-zImage Image uImage: vmlinux
-	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-
-archclean:
-	$(Q)$(MAKE) $(clean)=$(boot)
-
-define archhelp
-  echo  '* zImage        - Compressed kernel image (arch/$(ARCH)/boot/zImage)'
-  echo  '  Image         - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
-  echo  '  uImage        - U-Boot wrapped zImage'
-endef
diff --git a/arch/unicore32/boot/Makefile b/arch/unicore32/boot/Makefile
deleted file mode 100644
index 828855007b29..000000000000
--- a/arch/unicore32/boot/Makefile
+++ /dev/null
@@ -1,39 +0,0 @@
-#
-# arch/unicore32/boot/Makefile
-#
-# This file is included by the global makefile so that you can add your own
-# architecture-specific flags and dependencies.
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-# Copyright (C) 2001~2010 GUAN Xue-tao
-#
-
-targets := Image zImage uImage
-
-$(obj)/Image: vmlinux FORCE
-	$(call if_changed,objcopy)
-	@echo '  Kernel: $@ is ready'
-
-$(obj)/compressed/vmlinux: $(obj)/Image FORCE
-	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
-
-$(obj)/zImage: $(obj)/compressed/vmlinux FORCE
-	$(call if_changed,objcopy)
-	@echo '  Kernel: $@ is ready'
-
-UIMAGE_ARCH = unicore
-UIMAGE_LOADADDR = 0x0
-
-$(obj)/uImage: $(obj)/zImage FORCE
-	$(call if_changed,uimage)
-	@echo '  Image $@ is ready'
-
-PHONY += initrd
-initrd:
-	@test "$(INITRD)" != "" || \
-	(echo You must specify INITRD; exit -1)
-
-subdir- := compressed
diff --git a/arch/unicore32/boot/compressed/Makefile b/arch/unicore32/boot/compressed/Makefile
deleted file mode 100644
index 150fafc32fb0..000000000000
--- a/arch/unicore32/boot/compressed/Makefile
+++ /dev/null
@@ -1,64 +0,0 @@
-#
-# linux/arch/unicore32/boot/compressed/Makefile
-#
-# create a compressed vmlinuz image from the original vmlinux
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-# Copyright (C) 2001~2010 GUAN Xue-tao
-#
-
-ccflags-y	:= -fpic -fno-builtin
-asflags-y	:= -Wa,-march=all
-
-OBJS		:= misc.o
-
-# font.c and font.o
-CFLAGS_font.o	:= -Dstatic=
-$(obj)/font.c: $(srctree)/lib/fonts/font_8x8.c
-	$(call cmd,shipped)
-
-# piggy.S and piggy.o
-suffix_$(CONFIG_KERNEL_GZIP)	:= gzip
-suffix_$(CONFIG_KERNEL_BZIP2)	:= bz2
-suffix_$(CONFIG_KERNEL_LZO)	:= lzo
-suffix_$(CONFIG_KERNEL_LZMA)	:= lzma
-
-$(obj)/piggy.$(suffix_y): $(obj)/../Image FORCE
-	$(call if_changed,$(suffix_y))
-
-SEDFLAGS_piggy	= s/DECOMP_SUFFIX/$(suffix_y)/
-$(obj)/piggy.S: $(obj)/piggy.S.in
-	@sed "$(SEDFLAGS_piggy)" < $< > $@
-
-$(obj)/piggy.o:  $(obj)/piggy.$(suffix_y) $(obj)/piggy.S FORCE
-
-targets		:= vmlinux vmlinux.lds font.o font.c head.o misc.o \
-			piggy.$(suffix_y) piggy.o piggy.S \
-
-# Make sure files are removed during clean
-extra-y		+= piggy.gzip piggy.bz2 piggy.lzo piggy.lzma
-
-# ?
-LDFLAGS_vmlinux += -p
-# Report unresolved symbol references
-LDFLAGS_vmlinux += --no-undefined
-# Delete all temporary local symbols
-LDFLAGS_vmlinux += -X
-# Next argument is a linker script
-LDFLAGS_vmlinux += -T
-
-# For uidivmod
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head.o $(obj)/piggy.o \
-		$(obj)/misc.o FORCE
-	$(call if_changed,ld)
-
-# We now have a PIC decompressor implementation.  Decompressors running
-# from RAM should not define ZTEXTADDR.  Decompressors running directly
-# from ROM or Flash must define ZTEXTADDR (preferably via the config)
-ZTEXTADDR	:= 0x03000000
-ZBSSADDR	:= ALIGN(4)
-
-CPPFLAGS_vmlinux.lds = -DTEXT_START="$(ZTEXTADDR)" -DBSS_START="$(ZBSSADDR)"
diff --git a/arch/unicore32/boot/compressed/head.S b/arch/unicore32/boot/compressed/head.S
deleted file mode 100644
index 5f72662cd294..000000000000
--- a/arch/unicore32/boot/compressed/head.S
+++ /dev/null
@@ -1,201 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/boot/compressed/head.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/linkage.h>
-#include <mach/memory.h>
-
-#define csub	cmpsub
-#define cand	cmpand
-#define nop8	nop; nop; nop; nop; nop; nop; nop; nop
-
-		.section ".start", #alloc, #execinstr
-		.text
-start:
-		.type	start,#function
-
-		/* Initialize ASR, PRIV mode and INTR off */
-		mov	r0, #0xD3
-		mov.a	asr, r0
-
-		adr	r0, LC0
-		ldm	(r1, r2, r3, r5, r6, r7, r8), [r0]+
-		ldw	sp, [r0+], #28
-		sub.a	r0, r0, r1		@ calculate the delta offset
-
-		/*
-		 * if delta is zero, we are running at the address
-		 * we were linked at.
-		 */
-		beq	not_relocated
-
-		/*
-		 * We're running at a different address.  We need to fix
-		 * up various pointers:
-		 *   r5 - zImage base address (_start)
-		 *   r7 - GOT start
-		 *   r8 - GOT end
-		 */
-		add	r5, r5, r0
-		add	r7, r7, r0
-		add	r8, r8, r0
-
-		/*
-		 * we need to fix up pointers into the BSS region.
-		 *   r2 - BSS start
-		 *   r3 - BSS end
-		 *   sp - stack pointer
-		 */
-		add	r2, r2, r0
-		add	r3, r3, r0
-		add	sp, sp, r0
-
-		/*
-		 * Relocate all entries in the GOT table.
-		 * This fixes up the C references.
-		 *   r7 - GOT start
-		 *   r8 - GOT end
-		 */
-1001:		ldw	r1, [r7+], #0
-		add	r1, r1, r0
-		stw.w	r1, [r7]+, #4
-		csub.a	r7, r8
-		bub	1001b
-
-not_relocated:
-		/*
-		 * Clear BSS region.
-		 *   r2 - BSS start
-		 *   r3 - BSS end
-		 */
-		mov	r0, #0
-1002:		stw.w	r0, [r2]+, #4
-		csub.a	r2, r3
-		bub	1002b
-
-		/*
-		 * Turn on the cache.
-		 */
-                mov     r0, #0
-                movc    p0.c5, r0, #28		@ cache invalidate all
-                nop8
-                movc    p0.c6, r0, #6		@ tlb invalidate all
-                nop8
-
-                mov     r0, #0x1c		@ en icache and wb dcache
-                movc    p0.c1, r0, #0
-                nop8
-
-		/*
-		 * Set up some pointers, for starting decompressing.
-		 */
-
-		mov	r1, sp			@ malloc space above stack
-		add	r2, sp, #0x10000	@ 64k max
-
-		/*
-		 * Check to see if we will overwrite ourselves.
-		 *   r4 = final kernel address
-		 *   r5 = start of this image
-		 *   r6 = size of decompressed image
-		 *   r2 = end of malloc space (and therefore this image)
-		 * We basically want:
-		 *   r4 >= r2 -> OK
-		 *   r4 + image length <= r5 -> OK
-		 */
-		ldw	r4, =KERNEL_IMAGE_START
-		csub.a	r4, r2
-		bea	wont_overwrite
-		add	r0, r4, r6
-		csub.a	r0, r5
-		beb	wont_overwrite
-
-		/*
-		 * If overwrite, just print error message
-		 */
-		b	__error_overwrite
-
-		/*
-		 * We're not in danger of overwriting ourselves.
-		 * Do this the simple way.
-		 */
-wont_overwrite:
-		/*
-		 * decompress_kernel:
-		 *   r0: output_start
-		 *   r1: free_mem_ptr_p
-		 *   r2: free_mem_ptr_end_p
-		 */
-		mov	r0, r4
-		b.l	decompress_kernel	@ C functions
-
-		/*
-		 * Clean and flush the cache to maintain consistency.
-		 */
-		mov	r0, #0
-                movc    p0.c5, r0, #14		@ flush dcache
-		nop8
-                movc    p0.c5, r0, #20		@ icache invalidate all
-                nop8
-
-		/*
-		 * Turn off the Cache and MMU.
-		 */
-		mov	r0, #0			@ disable i/d cache and MMU
-		movc	p0.c1, r0, #0
-                nop8
-
-		mov	r0, #0			@ must be zero
-		ldw	r4, =KERNEL_IMAGE_START
-		mov	pc, r4			@ call kernel
-
-
-		.align	2
-		.type	LC0, #object
-LC0:		.word	LC0			@ r1
-		.word	__bss_start		@ r2
-		.word	_end			@ r3
-		.word	_start			@ r5
-		.word	_image_size		@ r6
-		.word	_got_start		@ r7
-		.word	_got_end		@ r8
-		.word	decompress_stack_end	@ sp
-		.size	LC0, . - LC0
-
-print_string:
-#ifdef CONFIG_DEBUG_OCD
-2001:		ldb.w	r1, [r0]+, #1
-		csub.a	r1, #0
-		bne	2002f
-		mov	pc, lr
-2002:
-		movc	r2, p1.c0, #0
-		cand.a	r2, #2
-		bne	2002b
-		movc	p1.c1, r1, #1
-		csub.a	r1, #'\n'
-		cmoveq	r1, #'\r'
-		beq	2002b
-		b	2001b
-#else
-		mov	pc, lr
-#endif
-
-__error_overwrite:
-		adr	r0, str_error
-		b.l	print_string
-2001:		nop8
-		b	2001b
-str_error:	.asciz	"\nError: Kernel address OVERWRITE\n"
-		.align
-
-		.ltorg
-
-		.align	4
-		.section ".stack", "aw", %nobits
-decompress_stack:	.space	4096
-decompress_stack_end:
diff --git a/arch/unicore32/boot/compressed/misc.c b/arch/unicore32/boot/compressed/misc.c
deleted file mode 100644
index 450d3355de20..000000000000
--- a/arch/unicore32/boot/compressed/misc.c
+++ /dev/null
@@ -1,123 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/boot/compressed/misc.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#include <asm/unaligned.h>
-#include <mach/uncompress.h>
-
-/*
- * gzip delarations
- */
-unsigned char *output_data;
-unsigned long output_ptr;
-
-unsigned int free_mem_ptr;
-unsigned int free_mem_end_ptr;
-
-#define STATIC static
-#define STATIC_RW_DATA	/* non-static please */
-
-/*
- * arch-dependent implementations
- */
-#ifndef ARCH_HAVE_DECOMP_ERROR
-#define arch_decomp_error(x)
-#endif
-
-#ifndef ARCH_HAVE_DECOMP_SETUP
-#define arch_decomp_setup()
-#endif
-
-#ifndef ARCH_HAVE_DECOMP_PUTS
-#define arch_decomp_puts(p)
-#endif
-
-void *memcpy(void *dest, const void *src, size_t n)
-{
-	int i = 0;
-	unsigned char *d = (unsigned char *)dest, *s = (unsigned char *)src;
-
-	for (i = n >> 3; i > 0; i--) {
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (n & 1 << 2) {
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (n & 1 << 1) {
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (n & 1)
-		*d++ = *s++;
-
-	return dest;
-}
-
-void error(char *x)
-{
-	arch_decomp_puts("\n\n");
-	arch_decomp_puts(x);
-	arch_decomp_puts("\n\n -- System halted");
-
-	arch_decomp_error(x);
-
-	for (;;)
-		; /* Halt */
-}
-
-/* Heap size should be adjusted for different decompress method */
-#ifdef CONFIG_KERNEL_GZIP
-#include "../../../../lib/decompress_inflate.c"
-#endif
-
-#ifdef CONFIG_KERNEL_BZIP2
-#include "../../../../lib/decompress_bunzip2.c"
-#endif
-
-#ifdef CONFIG_KERNEL_LZO
-#include "../../../../lib/decompress_unlzo.c"
-#endif
-
-#ifdef CONFIG_KERNEL_LZMA
-#include "../../../../lib/decompress_unlzma.c"
-#endif
-
-unsigned long decompress_kernel(unsigned long output_start,
-		unsigned long free_mem_ptr_p,
-		unsigned long free_mem_ptr_end_p)
-{
-	unsigned char *tmp;
-
-	output_data		= (unsigned char *)output_start;
-	free_mem_ptr		= free_mem_ptr_p;
-	free_mem_end_ptr	= free_mem_ptr_end_p;
-
-	arch_decomp_setup();
-
-	tmp = (unsigned char *) (((unsigned long)input_data_end) - 4);
-	output_ptr = get_unaligned_le32(tmp);
-
-	arch_decomp_puts("Uncompressing Linux...");
-	__decompress(input_data, input_data_end - input_data, NULL, NULL,
-			output_data, 0, NULL, error);
-	arch_decomp_puts(" done, booting the kernel.\n");
-	return output_ptr;
-}
diff --git a/arch/unicore32/boot/compressed/piggy.S.in b/arch/unicore32/boot/compressed/piggy.S.in
deleted file mode 100644
index b79704d58026..000000000000
--- a/arch/unicore32/boot/compressed/piggy.S.in
+++ /dev/null
@@ -1,6 +0,0 @@
-	.section .piggydata,#alloc
-	.globl	input_data
-input_data:
-	.incbin	"arch/unicore32/boot/compressed/piggy.DECOMP_SUFFIX"
-	.globl	input_data_end
-input_data_end:
diff --git a/arch/unicore32/boot/compressed/vmlinux.lds.S b/arch/unicore32/boot/compressed/vmlinux.lds.S
deleted file mode 100644
index edda4ddfa357..000000000000
--- a/arch/unicore32/boot/compressed/vmlinux.lds.S
+++ /dev/null
@@ -1,58 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore/boot/compressed/vmlinux.lds.in
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-OUTPUT_ARCH(unicore32)
-ENTRY(_start)
-SECTIONS
-{
-  /DISCARD/ : {
-    /*
-     * Discard any r/w data - this produces a link error if we have any,
-     * which is required for PIC decompression.  Local data generates
-     * GOTOFF relocations, which prevents it being relocated independently
-     * of the text/got segments.
-     */
-    *(.data)
-  }
-
-  . = TEXT_START;
-  _text = .;
-
-  .text : {
-    _start = .;
-    *(.start)
-    *(.text)
-    *(.text.*)
-    *(.fixup)
-    *(.gnu.warning)
-    *(.rodata)
-    *(.rodata.*)
-    *(.piggydata)
-    . = ALIGN(4);
-  }
-
-  _etext = .;
-
-  /* Assume size of decompressed image is 4x the compressed image */
-  _image_size = (_etext - _text) * 4;
-
-  _got_start = .;
-  .got			: { *(.got) }
-  _got_end = .;
-  .got.plt		: { *(.got.plt) }
-  _edata = .;
-
-  . = BSS_START;
-  __bss_start = .;
-  .bss			: { *(.bss) }
-  _end = .;
-
-  .stack		: { *(.stack) }
-  .comment 0		: { *(.comment) }
-}
-
diff --git a/arch/unicore32/configs/defconfig b/arch/unicore32/configs/defconfig
deleted file mode 100644
index 360cc9abcdb0..000000000000
--- a/arch/unicore32/configs/defconfig
+++ /dev/null
@@ -1,214 +0,0 @@
-### General setup
-CONFIG_EXPERIMENTAL=y
-CONFIG_LOCALVERSION="-unicore32"
-CONFIG_SWAP=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_HOTPLUG=y
-#	Initial RAM filesystem and RAM disk (initramfs/initrd) support
-#CONFIG_BLK_DEV_INITRD=y
-#CONFIG_INITRAMFS_SOURCE="arch/unicore/ramfs/ramfs_config"
-
-### Enable loadable module support
-CONFIG_MODULES=n
-CONFIG_MODULE_UNLOAD=y
-
-### System Type
-CONFIG_ARCH_PUV3=y
-#	Board Selection
-CONFIG_PUV3_NB0916=y
-#	Processor Features
-CONFIG_CPU_DCACHE_LINE_DISABLE=y
-CONFIG_CPU_TLB_SINGLE_ENTRY_DISABLE=n
-
-### Bus support
-CONFIG_PCI=y
-CONFIG_PCI_LEGACY=n
-
-### Boot options
-#	for debug, adding: earlyprintk=ocd,keep initcall_debug
-#	others support: test_suspend=mem root=/dev/sda
-#	hibernate support: resume=/dev/sda3
-CONFIG_CMDLINE="earlyprintk=ocd,keep ignore_loglevel"
-# TODO: mem=512M video=unifb:1024x600-16@75
-# for nfs: root=/dev/nfs rw nfsroot=192.168.10.88:/home/udb/nfs/,rsize=1024,wsize=1024
-#	ip=192.168.10.83:192.168.10.88:192.168.10.1:255.255.255.0::eth0:off
-CONFIG_CMDLINE_FORCE=y
-
-### Power management options
-CONFIG_PM=y
-CONFIG_HIBERNATION=y
-CONFIG_PM_STD_PARTITION="/dev/sda3"
-CONFIG_CPU_FREQ=n
-CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
-
-### Networking support
-CONFIG_NET=y
-#	Networking options
-CONFIG_PACKET=m
-CONFIG_UNIX=m
-#	TCP/IP networking
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IPV6=n
-#	Wireless
-CONFIG_WIRELESS=y
-CONFIG_WIRELESS_EXT=y
-CONFIG_MAC80211=m
-
-### PKUnity SoC Features
-CONFIG_USB_WLAN_HED_AQ3=n
-CONFIG_USB_CMMB_INNOFIDEI=n
-CONFIG_I2C_BATTERY_BQ27200=n
-CONFIG_I2C_EEPROM_AT24=n
-CONFIG_LCD_BACKLIGHT=n
-
-CONFIG_PUV3_UMAL=y
-CONFIG_PUV3_MUSB=n
-CONFIG_PUV3_AC97=n
-CONFIG_PUV3_NAND=n
-CONFIG_PUV3_MMC=n
-CONFIG_PUV3_UART=n
-
-### Device Drivers
-#	Memory Technology Device (MTD) support
-CONFIG_MTD=m
-CONFIG_MTD_UBI=m
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CHAR=m
-CONFIG_MTD_BLKDEVS=m
-#	RAM/ROM/Flash chip drivers
-CONFIG_MTD_CFI=m
-CONFIG_MTD_JEDECPROBE=m
-CONFIG_MTD_CFI_AMDSTD=m
-#	Mapping drivers for chip access
-CONFIG_MTD_PHYSMAP=m
-
-#	Block devices
-CONFIG_BLK_DEV_LOOP=m
-
-#	SCSI device support
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_BLK_DEV_SR=m
-CONFIG_CHR_DEV_SG=m
-
-#	Serial ATA (prod) and Parallel ATA (experimental) drivers
-CONFIG_ATA=y
-CONFIG_SATA_VIA=y
-
-#	Network device support
-CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_NETDEV_1000=y
-#	Wireless LAN
-CONFIG_WLAN_80211=n
-CONFIG_RT2X00=n
-CONFIG_RT73USB=n
-
-#	Input device support
-CONFIG_INPUT_EVDEV=m
-#	Keyboards
-CONFIG_KEYBOARD_GPIO=m
-
-#	I2C support
-CONFIG_I2C=y
-CONFIG_I2C_PUV3=y
-
-#	Hardware Monitoring support
-#CONFIG_SENSORS_LM75=m
-#	Generic Thermal sysfs driver
-#CONFIG_THERMAL=y
-#CONFIG_THERMAL_HWMON=y
-
-#	Multimedia support
-CONFIG_MEDIA_SUPPORT=n
-CONFIG_VIDEO_DEV=n
-CONFIG_USB_VIDEO_CLASS=n
-
-#	Graphics support
-CONFIG_FB=y
-CONFIG_FB_PUV3_UNIGFX=y
-#	Console display driver support
-CONFIG_VGA_CONSOLE=n
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FONTS=y
-CONFIG_FONT_8x8=y
-CONFIG_FONT_8x16=y
-#	Bootup logo
-CONFIG_LOGO=n
-
-#	Sound card support
-CONFIG_SOUND=m
-#	Advanced Linux Sound Architecture
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-
-#	USB support
-CONFIG_USB_ARCH_HAS_HCD=n
-CONFIG_USB=n
-CONFIG_USB_PRINTER=n
-CONFIG_USB_STORAGE=n
-#	Inventra Highspeed Dual Role Controller
-CONFIG_USB_MUSB_HDRC=n
-
-#	LED Support
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-#	LED Triggers
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_DISK=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-
-#	Real Time Clock
-CONFIG_RTC_LIB=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_PUV3=y
-
-### File systems
-CONFIG_EXT2_FS=m
-CONFIG_EXT3_FS=y
-CONFIG_EXT4_FS=y
-CONFIG_FUSE_FS=m
-#	CD-ROM/DVD Filesystems
-CONFIG_ISO9660_FS=m
-CONFIG_JOLIET=y
-CONFIG_UDF_FS=m
-#	DOS/FAT/NT Filesystems
-CONFIG_VFAT_FS=m
-#	Pseudo filesystems
-CONFIG_PROC_FS=y
-CONFIG_SYSFS=y
-CONFIG_TMPFS=y
-#	Miscellaneous filesystems
-CONFIG_MISC_FILESYSTEMS=y
-CONFIG_JFFS2_FS=m
-CONFIG_UBIFS_FS=m
-#	Network File Systems
-CONFIG_NETWORK_FILESYSTEMS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_ROOT_NFS=y
-#	Partition Types
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MSDOS_PARTITION=y
-#	Native language support
-CONFIG_NLS=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_936=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-
-### Kernel hacking
-CONFIG_FRAME_WARN=8096
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_PROVE_LOCKING=n
-CONFIG_DEBUG_BUGVERBOSE=y
-CONFIG_FRAME_POINTER=y
-CONFIG_DEBUG_LL=y
-
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
deleted file mode 100644
index 55026e8240d8..000000000000
--- a/arch/unicore32/include/asm/Kbuild
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-generic-y += extable.h
-generic-y += kvm_para.h
-generic-y += mcs_spinlock.h
-generic-y += parport.h
-generic-y += syscalls.h
-generic-y += user.h
diff --git a/arch/unicore32/include/asm/assembler.h b/arch/unicore32/include/asm/assembler.h
deleted file mode 100644
index 3de843d92850..000000000000
--- a/arch/unicore32/include/asm/assembler.h
+++ /dev/null
@@ -1,128 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/assembler.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  Do not include any C declarations in this file - it is included by
- *  assembler source.
- */
-#ifndef __ASSEMBLY__
-#error "Only include this from assembly code"
-#endif
-
-#include <asm/ptrace.h>
-
-/*
- * Little Endian independent macros for shifting bytes within registers.
- */
-#define pull            >>
-#define push            <<
-#define get_byte_0      << #0
-#define get_byte_1	>> #8
-#define get_byte_2	>> #16
-#define get_byte_3	>> #24
-#define put_byte_0      << #0
-#define put_byte_1	<< #8
-#define put_byte_2	<< #16
-#define put_byte_3	<< #24
-
-#define cadd		cmpadd
-#define cand		cmpand
-#define csub		cmpsub
-#define cxor		cmpxor
-
-/*
- * Enable and disable interrupts
- */
-	.macro disable_irq, temp
-	mov	\temp, asr
-	andn     \temp, \temp, #0xFF
-	or	\temp, \temp, #PSR_I_BIT | PRIV_MODE
-	mov.a	asr, \temp
-	.endm
-
-	.macro enable_irq, temp
-	mov	\temp, asr
-	andn     \temp, \temp, #0xFF
-	or	\temp, \temp, #PRIV_MODE
-	mov.a	asr, \temp
-	.endm
-
-#define USER(x...)				\
-9999:	x;					\
-	.pushsection __ex_table, "a";		\
-	.align	3;				\
-	.long	9999b, 9001f;			\
-	.popsection
-
-	.macro	notcond, cond, nexti = .+8
-	.ifc	\cond, eq
-		bne	\nexti
-	.else;	.ifc	\cond, ne
-		beq	\nexti
-	.else;	.ifc	\cond, ea
-		bub	\nexti
-	.else;	.ifc	\cond, ub
-		bea	\nexti
-	.else;	.ifc	\cond, fs
-		bns	\nexti
-	.else;	.ifc	\cond, ns
-		bfs	\nexti
-	.else;	.ifc	\cond, fv
-		bnv	\nexti
-	.else;	.ifc	\cond, nv
-		bfv	\nexti
-	.else;	.ifc	\cond, ua
-		beb	\nexti
-	.else;	.ifc	\cond, eb
-		bua	\nexti
-	.else;	.ifc	\cond, eg
-		bsl	\nexti
-	.else;	.ifc	\cond, sl
-		beg	\nexti
-	.else;	.ifc	\cond, sg
-		bel	\nexti
-	.else;	.ifc	\cond, el
-		bsg	\nexti
-	.else;	.ifnc	\cond, al
-		.error  "Unknown cond in notcond macro argument"
-	.endif;	.endif;	.endif;	.endif;	.endif;	.endif;	.endif
-	.endif;	.endif;	.endif;	.endif;	.endif;	.endif;	.endif
-	.endif
-	.endm
-
-	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort
-	.rept	\rept
-	notcond	\cond, .+8
-9999 :
-	.if	\inc == 1
-	\instr\()b.u \reg, [\ptr], #\inc
-	.elseif	\inc == 4
-	\instr\()w.u \reg, [\ptr], #\inc
-	.else
-	.error	"Unsupported inc macro argument"
-	.endif
-
-	.pushsection __ex_table, "a"
-	.align	3
-	.long	9999b, \abort
-	.popsection
-	.endr
-	.endm
-
-	.macro	strusr, reg, ptr, inc, cond = al, rept = 1, abort = 9001f
-	usracc	st, \reg, \ptr, \inc, \cond, \rept, \abort
-	.endm
-
-	.macro	ldrusr, reg, ptr, inc, cond = al, rept = 1, abort = 9001f
-	usracc	ld, \reg, \ptr, \inc, \cond, \rept, \abort
-	.endm
-
-	.macro	nop8
-	.rept	8
-		nop
-	.endr
-	.endm
diff --git a/arch/unicore32/include/asm/barrier.h b/arch/unicore32/include/asm/barrier.h
deleted file mode 100644
index efb81de87507..000000000000
--- a/arch/unicore32/include/asm/barrier.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Memory barrier implementations for PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2012 GUAN Xue-tao
- */
-#ifndef __UNICORE_BARRIER_H__
-#define __UNICORE_BARRIER_H__
-
-#define isb() __asm__ __volatile__ ("" : : : "memory")
-#define dsb() __asm__ __volatile__ ("" : : : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
-
-#include <asm-generic/barrier.h>
-
-#endif /* __UNICORE_BARRIER_H__ */
diff --git a/arch/unicore32/include/asm/bitops.h b/arch/unicore32/include/asm/bitops.h
deleted file mode 100644
index deeb2163f35e..000000000000
--- a/arch/unicore32/include/asm/bitops.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/bitops.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_BITOPS_H__
-#define __UNICORE_BITOPS_H__
-
-#define _ASM_GENERIC_BITOPS_FLS_H_
-#define _ASM_GENERIC_BITOPS___FLS_H_
-#define _ASM_GENERIC_BITOPS_FFS_H_
-#define _ASM_GENERIC_BITOPS___FFS_H_
-/*
- * On UNICORE, those functions can be implemented around
- * the cntlz instruction for much better code efficiency.
- */
-
-static inline int fls(unsigned int x)
-{
-	int ret;
-
-	asm("cntlz\t%0, %1" : "=r" (ret) : "r" (x) : "cc");
-	ret = 32 - ret;
-
-	return ret;
-}
-
-#define __fls(x) (fls(x) - 1)
-#define ffs(x) ({ unsigned long __t = (x); fls(__t & -__t); })
-#define __ffs(x) (ffs(x) - 1)
-
-#include <asm-generic/bitops.h>
-
-/* following definitions: to avoid using codes in lib/find_*.c */
-#define find_next_bit		find_next_bit
-#define find_next_zero_bit	find_next_zero_bit
-#define find_first_bit		find_first_bit
-#define find_first_zero_bit	find_first_zero_bit
-
-#include <asm-generic/bitops/find.h>
-
-#endif /* __UNICORE_BITOPS_H__ */
diff --git a/arch/unicore32/include/asm/bug.h b/arch/unicore32/include/asm/bug.h
deleted file mode 100644
index 99acea84a865..000000000000
--- a/arch/unicore32/include/asm/bug.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Bug handling for PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2012 GUAN Xue-tao
- */
-#ifndef __UNICORE_BUG_H__
-#define __UNICORE_BUG_H__
-
-#include <asm-generic/bug.h>
-
-struct pt_regs;
-struct siginfo;
-
-extern void die(const char *msg, struct pt_regs *regs, int err);
-extern void uc32_notify_die(const char *str, struct pt_regs *regs,
-		int sig, int code, void __user *addr,
-		unsigned long err, unsigned long trap);
-
-#endif /* __UNICORE_BUG_H__ */
diff --git a/arch/unicore32/include/asm/cache.h b/arch/unicore32/include/asm/cache.h
deleted file mode 100644
index 44ecd1f300fe..000000000000
--- a/arch/unicore32/include/asm/cache.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/cache.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_CACHE_H__
-#define __UNICORE_CACHE_H__
-
-#define L1_CACHE_SHIFT		(5)
-#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
-
-/*
- * Memory returned by kmalloc() may be used for DMA, so we must make
- * sure that all such allocations are cache aligned. Otherwise,
- * unrelated code may cause parts of the buffer to be read into the
- * cache before the transfer is done, causing old data to be seen by
- * the CPU.
- */
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
-
-#endif
diff --git a/arch/unicore32/include/asm/cacheflush.h b/arch/unicore32/include/asm/cacheflush.h
deleted file mode 100644
index ff0be92ebc32..000000000000
--- a/arch/unicore32/include/asm/cacheflush.h
+++ /dev/null
@@ -1,186 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/cacheflush.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_CACHEFLUSH_H__
-#define __UNICORE_CACHEFLUSH_H__
-
-#include <linux/mm.h>
-
-#include <asm/shmparam.h>
-
-#define CACHE_COLOUR(vaddr)	((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
-
-/*
- * This flag is used to indicate that the page pointed to by a pte is clean
- * and does not require cleaning before returning it to the user.
- */
-#define PG_dcache_clean PG_arch_1
-
-/*
- *	MM Cache Management
- *	===================
- *
- *	The arch/unicore32/mm/cache.S files implement these methods.
- *
- *	Start addresses are inclusive and end addresses are exclusive;
- *	start addresses should be rounded down, end addresses up.
- *
- *	See Documentation/core-api/cachetlb.rst for more information.
- *	Please note that the implementation of these, and the required
- *	effects are cache-type (VIVT/VIPT/PIPT) specific.
- *
- *	flush_icache_all()
- *
- *		Unconditionally clean and invalidate the entire icache.
- *		Currently only needed for cache-v6.S and cache-v7.S, see
- *		__flush_icache_all for the generic implementation.
- *
- *	flush_kern_all()
- *
- *		Unconditionally clean and invalidate the entire cache.
- *
- *	flush_user_all()
- *
- *		Clean and invalidate all user space cache entries
- *		before a change of page tables.
- *
- *	flush_user_range(start, end, flags)
- *
- *		Clean and invalidate a range of cache entries in the
- *		specified address space before a change of page tables.
- *		- start - user start address (inclusive, page aligned)
- *		- end   - user end address   (exclusive, page aligned)
- *		- flags - vma->vm_flags field
- *
- *	coherent_kern_range(start, end)
- *
- *		Ensure coherency between the Icache and the Dcache in the
- *		region described by start, end.  If you have non-snooping
- *		Harvard caches, you need to implement this function.
- *		- start  - virtual start address
- *		- end    - virtual end address
- *
- *	coherent_user_range(start, end)
- *
- *		Ensure coherency between the Icache and the Dcache in the
- *		region described by start, end.  If you have non-snooping
- *		Harvard caches, you need to implement this function.
- *		- start  - virtual start address
- *		- end    - virtual end address
- *
- *	flush_kern_dcache_area(kaddr, size)
- *
- *		Ensure that the data held in page is written back.
- *		- kaddr  - page address
- *		- size   - region size
- *
- *	DMA Cache Coherency
- *	===================
- *
- *	dma_flush_range(start, end)
- *
- *		Clean and invalidate the specified virtual address range.
- *		- start  - virtual start address
- *		- end    - virtual end address
- */
-
-extern void __cpuc_flush_icache_all(void);
-extern void __cpuc_flush_kern_all(void);
-extern void __cpuc_flush_user_all(void);
-extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
-extern void __cpuc_coherent_kern_range(unsigned long, unsigned long);
-extern void __cpuc_coherent_user_range(unsigned long, unsigned long);
-extern void __cpuc_flush_dcache_area(void *, size_t);
-extern void __cpuc_flush_kern_dcache_area(void *addr, size_t size);
-
-/*
- * Copy user data from/to a page which is mapped into a different
- * processes address space.  Really, we want to allow our "user
- * space" model to handle this.
- */
-extern void copy_to_user_page(struct vm_area_struct *, struct page *,
-	unsigned long, void *, const void *, unsigned long);
-#define copy_from_user_page(vma, page, vaddr, dst, src, len)	\
-	do {							\
-		memcpy(dst, src, len);				\
-	} while (0)
-
-/*
- * Convert calls to our calling convention.
- */
-/* Invalidate I-cache */
-static inline void __flush_icache_all(void)
-{
-	asm("movc	p0.c5, %0, #20;\n"
-	    "nop; nop; nop; nop; nop; nop; nop; nop\n"
-	    :
-	    : "r" (0));
-}
-
-#define flush_cache_all()		__cpuc_flush_kern_all()
-
-extern void flush_cache_mm(struct mm_struct *mm);
-extern void flush_cache_range(struct vm_area_struct *vma,
-		unsigned long start, unsigned long end);
-extern void flush_cache_page(struct vm_area_struct *vma,
-		unsigned long user_addr, unsigned long pfn);
-
-#define flush_cache_dup_mm(mm) flush_cache_mm(mm)
-
-/*
- * Perform necessary cache operations to ensure that data previously
- * stored within this range of addresses can be executed by the CPU.
- */
-#define flush_icache_range(s, e)	__cpuc_coherent_kern_range(s, e)
-
-/*
- * Perform necessary cache operations to ensure that the TLB will
- * see data written in the specified area.
- */
-#define clean_dcache_area(start, size)	cpu_dcache_clean_area(start, size)
-
-/*
- * flush_dcache_page is used when the kernel has written to the page
- * cache page at virtual address page->virtual.
- *
- * If this page isn't mapped (ie, page_mapping == NULL), or it might
- * have userspace mappings, then we _must_ always clean + invalidate
- * the dcache entries associated with the kernel mapping.
- *
- * Otherwise we can defer the operation, and clean the cache when we are
- * about to change to user space.  This is the same method as used on SPARC64.
- * See update_mmu_cache for the user space part.
- */
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *);
-
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-
-/*
- * We don't appear to need to do anything here.  In fact, if we did, we'd
- * duplicate cache flushing elsewhere performed by flush_dcache_page().
- */
-#define flush_icache_page(vma, page)	do { } while (0)
-
-/*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
- */
-static inline void flush_cache_vmap(unsigned long start, unsigned long end)
-{
-}
-
-static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
-{
-}
-
-#endif
diff --git a/arch/unicore32/include/asm/checksum.h b/arch/unicore32/include/asm/checksum.h
deleted file mode 100644
index e774ca268c15..000000000000
--- a/arch/unicore32/include/asm/checksum.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/checksum.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * IP checksum routines
- */
-#ifndef __UNICORE_CHECKSUM_H__
-#define __UNICORE_CHECKSUM_H__
-
-/*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-
-static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
-		   __u8 proto, __wsum sum)
-{
-	__asm__(
-	"add.a	%0, %1, %2\n"
-	"addc.a	%0, %0, %3\n"
-	"addc.a	%0, %0, %4 << #8\n"
-	"addc.a	%0, %0, %5\n"
-	"addc	%0, %0, #0\n"
-	: "=&r"(sum)
-	: "r" (sum), "r" (daddr), "r" (saddr), "r" (len), "Ir" (htons(proto))
-	: "cc");
-	return sum;
-}
-#define csum_tcpudp_nofold	csum_tcpudp_nofold
-
-#include <asm-generic/checksum.h>
-
-#endif
diff --git a/arch/unicore32/include/asm/cmpxchg.h b/arch/unicore32/include/asm/cmpxchg.h
deleted file mode 100644
index 87f960a2e4f0..000000000000
--- a/arch/unicore32/include/asm/cmpxchg.h
+++ /dev/null
@@ -1,58 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Atomics xchg/cmpxchg for PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2012 GUAN Xue-tao
- */
-#ifndef __UNICORE_CMPXCHG_H__
-#define __UNICORE_CMPXCHG_H__
-
-/*
- * Generate a link failure on undefined symbol if the pointer points to a value
- * of unsupported size.
- */
-extern void __xchg_bad_pointer(void);
-
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
-		int size)
-{
-	unsigned long ret;
-
-	switch (size) {
-	case 1:
-		asm volatile("swapb	%0, %1, [%2]"
-			: "=&r" (ret)
-			: "r" (x), "r" (ptr)
-			: "memory", "cc");
-		break;
-	case 4:
-		asm volatile("swapw	%0, %1, [%2]"
-			: "=&r" (ret)
-			: "r" (x), "r" (ptr)
-			: "memory", "cc");
-		break;
-	default:
-		__xchg_bad_pointer();
-	}
-
-	return ret;
-}
-
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-
-#include <asm-generic/cmpxchg-local.h>
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)					\
-		((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr),	\
-		(unsigned long)(o), (unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n)					\
-		__cmpxchg64_local_generic((ptr), (o), (n))
-
-#include <asm-generic/cmpxchg.h>
-
-#endif /* __UNICORE_CMPXCHG_H__ */
diff --git a/arch/unicore32/include/asm/cpu-single.h b/arch/unicore32/include/asm/cpu-single.h
deleted file mode 100644
index 1b419d697fd1..000000000000
--- a/arch/unicore32/include/asm/cpu-single.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/cpu-single.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_CPU_SINGLE_H__
-#define __UNICORE_CPU_SINGLE_H__
-
-#include <asm/page.h>
-#include <asm/memory.h>
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#define cpu_switch_mm(pgd, mm) cpu_do_switch_mm(virt_to_phys(pgd), mm)
-
-#define cpu_get_pgd()					\
-	({						\
-		unsigned long pg;			\
-		__asm__("movc	%0, p0.c2, #0"		\
-			 : "=r" (pg) : : "cc");		\
-		pg &= ~0x0fff;				\
-		(pgd_t *)phys_to_virt(pg);		\
-	})
-
-struct mm_struct;
-
-/* declare all the functions as extern */
-extern void cpu_proc_fin(void);
-extern int cpu_do_idle(void);
-extern void cpu_dcache_clean_area(void *, int);
-extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
-extern void cpu_set_pte(pte_t *ptep, pte_t pte);
-extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#endif /* __UNICORE_CPU_SINGLE_H__ */
diff --git a/arch/unicore32/include/asm/cputype.h b/arch/unicore32/include/asm/cputype.h
deleted file mode 100644
index 08a47e3bdbcc..000000000000
--- a/arch/unicore32/include/asm/cputype.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/cputype.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_CPUTYPE_H__
-#define __UNICORE_CPUTYPE_H__
-
-#include <linux/stringify.h>
-
-#define CPUID_CPUID	0
-#define CPUID_CACHETYPE	1
-
-#define read_cpuid(reg)							\
-	({								\
-		unsigned int __val;					\
-		asm("movc	%0, p0.c0, #" __stringify(reg)		\
-		    : "=r" (__val)					\
-		    :							\
-		    : "cc");						\
-		__val;							\
-	})
-
-#define uc32_cpuid		read_cpuid(CPUID_CPUID)
-#define uc32_cachetype		read_cpuid(CPUID_CACHETYPE)
-
-#endif
diff --git a/arch/unicore32/include/asm/delay.h b/arch/unicore32/include/asm/delay.h
deleted file mode 100644
index 934193edfa66..000000000000
--- a/arch/unicore32/include/asm/delay.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/delay.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * Delay routines, using a pre-computed "loops_per_second" value.
- */
-#ifndef __UNICORE_DELAY_H__
-#define __UNICORE_DELAY_H__
-
-#include <asm/param.h>	/* HZ */
-
-extern void __delay(int loops);
-
-/*
- * This function intentionally does not exist; if you see references to
- * it, it means that you're calling udelay() with an out of range value.
- *
- * With currently imposed limits, this means that we support a max delay
- * of 2000us. Further limits: HZ<=1000 and bogomips<=3355
- */
-extern void __bad_udelay(void);
-
-/*
- * division by multiplication: you don't have to worry about
- * loss of precision.
- *
- * Use only for very small delays ( < 1 msec).  Should probably use a
- * lookup table, really, as the multiplications take much too long with
- * short delays.  This is a "reasonable" implementation, though (and the
- * first constant multiplications gets optimized away if the delay is
- * a constant)
- */
-extern void __udelay(unsigned long usecs);
-extern void __const_udelay(unsigned long);
-
-#define MAX_UDELAY_MS 2
-
-#define udelay(n)							\
-	(__builtin_constant_p(n) ?					\
-	  ((n) > (MAX_UDELAY_MS * 1000) ? __bad_udelay() :		\
-			__const_udelay((n) * ((2199023U*HZ)>>11))) :	\
-	  __udelay(n))
-
-#endif /* __UNICORE_DELAY_H__ */
-
diff --git a/arch/unicore32/include/asm/dma.h b/arch/unicore32/include/asm/dma.h
deleted file mode 100644
index 1326310b21e6..000000000000
--- a/arch/unicore32/include/asm/dma.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/dma.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_DMA_H__
-#define __UNICORE_DMA_H__
-
-#include <asm/memory.h>
-#include <asm-generic/dma.h>
-
-#ifdef CONFIG_PCI
-extern int isa_dma_bridge_buggy;
-#endif
-
-#endif /* __UNICORE_DMA_H__ */
diff --git a/arch/unicore32/include/asm/elf.h b/arch/unicore32/include/asm/elf.h
deleted file mode 100644
index a464ed5f05d4..000000000000
--- a/arch/unicore32/include/asm/elf.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/elf.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_ELF_H__
-#define __UNICORE_ELF_H__
-
-#include <asm/hwcap.h>
-
-/*
- * ELF register definitions..
- */
-#include <asm/ptrace.h>
-#include <linux/elf-em.h>
-
-typedef unsigned long elf_greg_t;
-typedef unsigned long elf_freg_t[3];
-
-#define ELF_NGREG (sizeof(struct pt_regs) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct fp_state elf_fpregset_t;
-
-#define R_UNICORE_NONE		0
-#define R_UNICORE_PC24		1
-#define R_UNICORE_ABS32		2
-#define R_UNICORE_CALL		28
-#define R_UNICORE_JUMP24	29
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS	ELFCLASS32
-#define ELF_DATA	ELFDATA2LSB
-#define ELF_ARCH	EM_UNICORE
-
-/*
- * This yields a string that ld.so will use to load implementation
- * specific libraries for optimization.  This is more specific in
- * intent than poking at uname or /proc/cpuinfo.
- *
- */
-#define ELF_PLATFORM_SIZE 8
-#define ELF_PLATFORM	(elf_platform)
-
-extern char elf_platform[];
-
-struct elf32_hdr;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-extern int elf_check_arch(const struct elf32_hdr *);
-#define elf_check_arch elf_check_arch
-
-struct task_struct;
-int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
-#define ELF_CORE_COPY_TASK_REGS dump_task_regs
-
-#define ELF_EXEC_PAGESIZE	4096
-
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE	(2 * TASK_SIZE / 3)
-
-/* When the program starts, a1 contains a pointer to a function to be
-   registered with atexit, as per the SVR4 ABI.  A value of 0 means we
-   have no such handler.  */
-#define ELF_PLAT_INIT(_r, load_addr)	{(_r)->UCreg_00 = 0; }
-
-extern void elf_set_personality(const struct elf32_hdr *);
-#define SET_PERSONALITY(ex)	elf_set_personality(&(ex))
-
-struct mm_struct;
-extern unsigned long arch_randomize_brk(struct mm_struct *mm);
-#define arch_randomize_brk arch_randomize_brk
-
-extern int vectors_user_mapping(void);
-#define arch_setup_additional_pages(bprm, uses_interp) vectors_user_mapping()
-#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
-
-#endif
diff --git a/arch/unicore32/include/asm/fpstate.h b/arch/unicore32/include/asm/fpstate.h
deleted file mode 100644
index 5811293e7a7e..000000000000
--- a/arch/unicore32/include/asm/fpstate.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/fpstate.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_FPSTATE_H__
-#define __UNICORE_FPSTATE_H__
-
-#ifndef __ASSEMBLY__
-
-#define FP_REGS_NUMBER		33
-
-struct fp_state {
-	unsigned int regs[FP_REGS_NUMBER];
-} __attribute__((aligned(8)));
-
-#endif
-
-#endif
diff --git a/arch/unicore32/include/asm/fpu-ucf64.h b/arch/unicore32/include/asm/fpu-ucf64.h
deleted file mode 100644
index 7a0c8a9e05d4..000000000000
--- a/arch/unicore32/include/asm/fpu-ucf64.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/fpu-ucf64.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-#define FPSCR			s31
-
-/* FPSCR bits */
-#define FPSCR_DEFAULT_NAN	(1<<25)
-
-#define FPSCR_CMPINSTR_BIT	(1<<31)
-
-#define FPSCR_CON		(1<<29)
-#define FPSCR_TRAP		(1<<27)
-
-/* RND mode */
-#define FPSCR_ROUND_NEAREST	(0<<0)
-#define FPSCR_ROUND_PLUSINF	(2<<0)
-#define FPSCR_ROUND_MINUSINF	(3<<0)
-#define FPSCR_ROUND_TOZERO	(1<<0)
-#define FPSCR_RMODE_BIT		(0)
-#define FPSCR_RMODE_MASK	(7 << FPSCR_RMODE_BIT)
-
-/* trap enable */
-#define FPSCR_IOE		(1<<16)
-#define FPSCR_OFE		(1<<14)
-#define FPSCR_UFE		(1<<13)
-#define FPSCR_IXE		(1<<12)
-#define FPSCR_HIE		(1<<11)
-#define FPSCR_NDE		(1<<10)	/* non denomal */
-
-/* flags */
-#define FPSCR_IDC		(1<<24)
-#define FPSCR_HIC		(1<<23)
-#define FPSCR_IXC		(1<<22)
-#define FPSCR_OFC		(1<<21)
-#define FPSCR_UFC		(1<<20)
-#define FPSCR_IOC		(1<<19)
-
-/* stick bits */
-#define FPSCR_IOS		(1<<9)
-#define FPSCR_OFS		(1<<7)
-#define FPSCR_UFS		(1<<6)
-#define FPSCR_IXS		(1<<5)
-#define FPSCR_HIS		(1<<4)
-#define FPSCR_NDS		(1<<3)	/*non denomal */
diff --git a/arch/unicore32/include/asm/gpio.h b/arch/unicore32/include/asm/gpio.h
deleted file mode 100644
index dfad04ca0a65..000000000000
--- a/arch/unicore32/include/asm/gpio.h
+++ /dev/null
@@ -1,101 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/gpio.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_GPIO_H__
-#define __UNICORE_GPIO_H__
-
-#include <linux/io.h>
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <asm-generic/gpio.h>
-
-#define GPI_OTP_INT             0
-#define GPI_PCI_INTA            1
-#define GPI_PCI_INTB            2
-#define GPI_PCI_INTC            3
-#define GPI_PCI_INTD            4
-#define GPI_BAT_DET             5
-#define GPI_SD_CD               6
-#define GPI_SOFF_REQ            7
-#define GPI_SD_WP               8
-#define GPI_LCD_CASE_OFF        9
-#define GPO_WIFI_EN             10
-#define GPO_HDD_LED             11
-#define GPO_VGA_EN              12
-#define GPO_LCD_EN              13
-#define GPO_LED_DATA            14
-#define GPO_LED_CLK             15
-#define GPO_CAM_PWR_EN          16
-#define GPO_LCD_VCC_EN          17
-#define GPO_SOFT_OFF            18
-#define GPO_BT_EN               19
-#define GPO_FAN_ON              20
-#define GPO_SPKR                21
-#define GPO_SET_V1              23
-#define GPO_SET_V2              24
-#define GPO_CPU_HEALTH          25
-#define GPO_LAN_SEL             26
-
-#ifdef CONFIG_PUV3_NB0916
-#define GPI_BTN_TOUCH		14
-#define GPIO_IN			0x000043ff /* 1 for input */
-#define GPIO_OUT		0x0fffbc00 /* 1 for output */
-#endif	/* CONFIG_PUV3_NB0916 */
-
-#ifdef CONFIG_PUV3_SMW0919
-#define GPIO_IN			0x000003ff /* 1 for input */
-#define GPIO_OUT		0x0ffffc00 /* 1 for output */
-#endif  /* CONFIG_PUV3_SMW0919 */
-
-#ifdef CONFIG_PUV3_DB0913
-#define GPIO_IN			0x000001df /* 1 for input */
-#define GPIO_OUT		0x03fee800 /* 1 for output */
-#endif  /* CONFIG_PUV3_DB0913 */
-
-#define GPIO_DIR                (~((GPIO_IN) | 0xf0000000))
-				/* 0 input, 1 output */
-
-static inline int gpio_get_value(unsigned gpio)
-{
-	if (__builtin_constant_p(gpio) && (gpio <= GPIO_MAX))
-		return readl(GPIO_GPLR) & GPIO_GPIO(gpio);
-	else
-		return __gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(unsigned gpio, int value)
-{
-	if (__builtin_constant_p(gpio) && (gpio <= GPIO_MAX))
-		if (value)
-			writel(GPIO_GPIO(gpio), GPIO_GPSR);
-		else
-			writel(GPIO_GPIO(gpio), GPIO_GPCR);
-	else
-		__gpio_set_value(gpio, value);
-}
-
-#define gpio_cansleep	__gpio_cansleep
-
-static inline unsigned gpio_to_irq(unsigned gpio)
-{
-	if ((gpio < IRQ_GPIOHIGH) && (FIELD(1, 1, gpio) & readl(GPIO_GPIR)))
-		return IRQ_GPIOLOW0 + gpio;
-	else
-		return IRQ_GPIO0 + gpio;
-}
-
-static inline unsigned irq_to_gpio(unsigned irq)
-{
-	if (irq < IRQ_GPIOHIGH)
-		return irq - IRQ_GPIOLOW0;
-	else
-		return irq - IRQ_GPIO0;
-}
-
-#endif /* __UNICORE_GPIO_H__ */
diff --git a/arch/unicore32/include/asm/hwcap.h b/arch/unicore32/include/asm/hwcap.h
deleted file mode 100644
index 2e15ffbe8391..000000000000
--- a/arch/unicore32/include/asm/hwcap.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/hwcap.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_HWCAP_H__
-#define __UNICORE_HWCAP_H__
-
-/*
- * HWCAP flags
- */
-#define HWCAP_MSP		1
-#define HWCAP_UNICORE16		2
-#define HWCAP_CMOV		4
-#define HWCAP_UNICORE_F64       8
-#define HWCAP_TLS		0x80
-
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
-/*
- * This yields a mask that user programs can use to figure out what
- * instruction set this cpu supports.
- */
-#define ELF_HWCAP		(HWCAP_CMOV | HWCAP_UNICORE_F64)
-#endif
-
-#endif
diff --git a/arch/unicore32/include/asm/hwdef-copro.h b/arch/unicore32/include/asm/hwdef-copro.h
deleted file mode 100644
index 2db8cf864e43..000000000000
--- a/arch/unicore32/include/asm/hwdef-copro.h
+++ /dev/null
@@ -1,45 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Co-processor register definitions for PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2012 GUAN Xue-tao
- */
-#ifndef __UNICORE_HWDEF_COPRO_H__
-#define __UNICORE_HWDEF_COPRO_H__
-
-/*
- * Control Register bits (CP#0 CR1)
- */
-#define CR_M	(1 << 0)	/* MMU enable				*/
-#define CR_A	(1 << 1)	/* Alignment abort enable		*/
-#define CR_D	(1 << 2)	/* Dcache enable			*/
-#define CR_I	(1 << 3)	/* Icache enable			*/
-#define CR_B	(1 << 4)	/* Dcache write mechanism: write back	*/
-#define CR_T	(1 << 5)	/* Burst enable				*/
-#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
-
-#ifndef __ASSEMBLY__
-
-#define vectors_high()		(cr_alignment & CR_V)
-
-extern unsigned long cr_no_alignment;	/* defined in entry.S */
-extern unsigned long cr_alignment;	/* defined in entry.S */
-
-static inline unsigned int get_cr(void)
-{
-	unsigned int val;
-	asm("movc %0, p0.c1, #0" : "=r" (val) : : "cc");
-	return val;
-}
-
-static inline void set_cr(unsigned int val)
-{
-	asm volatile("movc p0.c1, %0, #0" : : "r" (val) : "cc");
-	isb();
-}
-
-extern void adjust_cr(unsigned long mask, unsigned long set);
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __UNICORE_HWDEF_COPRO_H__ */
diff --git a/arch/unicore32/include/asm/io.h b/arch/unicore32/include/asm/io.h
deleted file mode 100644
index bd4e7c332f85..000000000000
--- a/arch/unicore32/include/asm/io.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/io.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_IO_H__
-#define __UNICORE_IO_H__
-
-#ifdef __KERNEL__
-
-#include <asm/byteorder.h>
-#include <asm/memory.h>
-
-#define PCI_IOBASE	PKUNITY_PCILIO_BASE
-#include <asm-generic/io.h>
-
-/*
- * __uc32_ioremap takes CPU physical address.
- */
-extern void __iomem *__uc32_ioremap(unsigned long, size_t);
-extern void __uc32_iounmap(volatile void __iomem *addr);
-
-/*
- * ioremap and friends.
- *
- * ioremap takes a PCI memory address, as specified in
- * Documentation/driver-api/io-mapping.rst.
- *
- */
-#define ioremap(cookie, size)		__uc32_ioremap(cookie, size)
-#define iounmap(cookie)			__uc32_iounmap(cookie)
-
-#define readb_relaxed readb
-#define readw_relaxed readw
-#define readl_relaxed readl
-
-#define HAVE_ARCH_PIO_SIZE
-#define PIO_OFFSET		(unsigned int)(PCI_IOBASE)
-#define PIO_MASK		(unsigned int)(IO_SPACE_LIMIT)
-#define PIO_RESERVED		(PIO_OFFSET + PIO_MASK + 1)
-
-#ifdef CONFIG_STRICT_DEVMEM
-
-#include <linux/ioport.h>
-#include <linux/mm.h>
-
-/*
- * devmem_is_allowed() checks to see if /dev/mem access to a certain
- * address is valid. The argument is a physical page number.
- * We mimic x86 here by disallowing access to system RAM as well as
- * device-exclusive MMIO regions. This effectively disable read()/write()
- * on /dev/mem.
- */
-static inline int devmem_is_allowed(unsigned long pfn)
-{
-	if (iomem_is_exclusive(pfn << PAGE_SHIFT))
-		return 0;
-	if (!page_is_ram(pfn))
-		return 1;
-	return 0;
-}
-
-#endif /* CONFIG_STRICT_DEVMEM */
-
-#endif	/* __KERNEL__ */
-#endif	/* __UNICORE_IO_H__ */
diff --git a/arch/unicore32/include/asm/irq.h b/arch/unicore32/include/asm/irq.h
deleted file mode 100644
index 3f7f07c0338c..000000000000
--- a/arch/unicore32/include/asm/irq.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/irq.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_IRQ_H__
-#define __UNICORE_IRQ_H__
-
-#include <asm-generic/irq.h>
-
-#define	IRQ_GPIOLOW0		0x00
-#define	IRQ_GPIOLOW1		0x01
-#define	IRQ_GPIOLOW2		0x02
-#define	IRQ_GPIOLOW3		0x03
-#define	IRQ_GPIOLOW4		0x04
-#define	IRQ_GPIOLOW5		0x05
-#define	IRQ_GPIOLOW6		0x06
-#define	IRQ_GPIOLOW7		0x07
-#define IRQ_GPIOHIGH		0x08
-#define IRQ_USB			0x09
-#define IRQ_SDC			0x0a
-#define IRQ_AC97		0x0b
-#define IRQ_SATA		0x0c
-#define IRQ_MME			0x0d
-#define IRQ_PCI_BRIDGE		0x0e
-#define	IRQ_DDR			0x0f
-#define	IRQ_SPI			0x10
-#define	IRQ_UNIGFX		0x11
-#define	IRQ_I2C			0x11
-#define	IRQ_UART1		0x12
-#define	IRQ_UART0		0x13
-#define IRQ_UMAL		0x14
-#define IRQ_NAND		0x15
-#define IRQ_PS2_KBD		0x16
-#define IRQ_PS2_AUX		0x17
-#define IRQ_DMA			0x18
-#define IRQ_DMAERR		0x19
-#define	IRQ_TIMER0		0x1a
-#define	IRQ_TIMER1		0x1b
-#define	IRQ_TIMER2		0x1c
-#define	IRQ_TIMER3		0x1d
-#define	IRQ_RTC			0x1e
-#define	IRQ_RTCAlarm		0x1f
-
-#define	IRQ_GPIO0		0x20
-#define	IRQ_GPIO1		0x21
-#define	IRQ_GPIO2		0x22
-#define	IRQ_GPIO3		0x23
-#define	IRQ_GPIO4		0x24
-#define	IRQ_GPIO5		0x25
-#define	IRQ_GPIO6		0x26
-#define	IRQ_GPIO7		0x27
-#define IRQ_GPIO8		0x28
-#define IRQ_GPIO9		0x29
-#define IRQ_GPIO10		0x2a
-#define IRQ_GPIO11		0x2b
-#define IRQ_GPIO12		0x2c
-#define IRQ_GPIO13		0x2d
-#define IRQ_GPIO14		0x2e
-#define IRQ_GPIO15		0x2f
-#define IRQ_GPIO16		0x30
-#define IRQ_GPIO17		0x31
-#define IRQ_GPIO18		0x32
-#define IRQ_GPIO19		0x33
-#define IRQ_GPIO20		0x34
-#define IRQ_GPIO21		0x35
-#define IRQ_GPIO22		0x36
-#define IRQ_GPIO23		0x37
-#define IRQ_GPIO24		0x38
-#define IRQ_GPIO25		0x39
-#define IRQ_GPIO26		0x3a
-#define IRQ_GPIO27		0x3b
-
-#ifdef CONFIG_ARCH_FPGA
-#define IRQ_PCIINTA             IRQ_GPIOLOW2
-#define IRQ_PCIINTB             IRQ_GPIOLOW1
-#define IRQ_PCIINTC             IRQ_GPIOLOW0
-#define IRQ_PCIINTD             IRQ_GPIOLOW6
-#endif
-
-#if defined(CONFIG_PUV3_DB0913) || defined(CONFIG_PUV3_NB0916)	\
-	|| defined(CONFIG_PUV3_SMW0919)
-#define IRQ_PCIINTA             IRQ_GPIOLOW1
-#define IRQ_PCIINTB             IRQ_GPIOLOW2
-#define IRQ_PCIINTC             IRQ_GPIOLOW3
-#define IRQ_PCIINTD             IRQ_GPIOLOW4
-#endif
-
-#define IRQ_SD_CD               IRQ_GPIO6 /* falling or rising trigger */
-
-#ifndef __ASSEMBLY__
-struct pt_regs;
-
-extern void asm_do_IRQ(unsigned int, struct pt_regs *);
-
-#endif
-
-#endif
-
diff --git a/arch/unicore32/include/asm/irqflags.h b/arch/unicore32/include/asm/irqflags.h
deleted file mode 100644
index f64c82e3eae6..000000000000
--- a/arch/unicore32/include/asm/irqflags.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/irqflags.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_IRQFLAGS_H__
-#define __UNICORE_IRQFLAGS_H__
-
-#ifdef __KERNEL__
-
-#include <asm/ptrace.h>
-
-#define ARCH_IRQ_DISABLED	(PRIV_MODE | PSR_I_BIT)
-#define ARCH_IRQ_ENABLED	(PRIV_MODE)
-
-/*
- * Save the current interrupt enable state.
- */
-static inline unsigned long arch_local_save_flags(void)
-{
-	unsigned long temp;
-
-	asm volatile("mov %0, asr" : "=r" (temp) : : "memory", "cc");
-
-	return temp & PSR_c;
-}
-
-/*
- * restore saved IRQ state
- */
-static inline void arch_local_irq_restore(unsigned long flags)
-{
-	unsigned long temp;
-
-	asm volatile(
-		"mov	%0, asr\n"
-		"mov.a	asr, %1\n"
-		"mov.f	asr, %0"
-		: "=&r" (temp)
-		: "r" (flags)
-		: "memory", "cc");
-}
-
-#include <asm-generic/irqflags.h>
-
-#endif
-#endif
diff --git a/arch/unicore32/include/asm/linkage.h b/arch/unicore32/include/asm/linkage.h
deleted file mode 100644
index 8e341ba7bc4a..000000000000
--- a/arch/unicore32/include/asm/linkage.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/linkage.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_LINKAGE_H__
-#define __UNICORE_LINKAGE_H__
-
-#define __ALIGN .align 0
-#define __ALIGN_STR ".align 0"
-
-#define ENDPROC(name) \
-	.type name, %function; \
-	END(name)
-
-#endif
diff --git a/arch/unicore32/include/asm/memblock.h b/arch/unicore32/include/asm/memblock.h
deleted file mode 100644
index eb56a6ddce83..000000000000
--- a/arch/unicore32/include/asm/memblock.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/memblock.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_MEMBLOCK_H__
-#define __UNICORE_MEMBLOCK_H__
-
-/*
- * Memory map description
- */
-# define NR_BANKS 8
-
-struct membank {
-	unsigned long start;
-	unsigned long size;
-	unsigned int highmem;
-};
-
-struct meminfo {
-	int nr_banks;
-	struct membank bank[NR_BANKS];
-};
-
-extern struct meminfo meminfo;
-
-#define for_each_bank(iter, mi)				\
-	for (iter = 0; iter < (mi)->nr_banks; iter++)
-
-#define bank_pfn_start(bank)	__phys_to_pfn((bank)->start)
-#define bank_pfn_end(bank)	__phys_to_pfn((bank)->start + (bank)->size)
-#define bank_pfn_size(bank)	((bank)->size >> PAGE_SHIFT)
-#define bank_phys_start(bank)	((bank)->start)
-#define bank_phys_end(bank)	((bank)->start + (bank)->size)
-#define bank_phys_size(bank)	((bank)->size)
-
-extern void uc32_memblock_init(struct meminfo *);
-
-#endif
diff --git a/arch/unicore32/include/asm/memory.h b/arch/unicore32/include/asm/memory.h
deleted file mode 100644
index 66285178dd9b..000000000000
--- a/arch/unicore32/include/asm/memory.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/memory.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  Note: this file should not be included by non-asm/.h files
- */
-#ifndef __UNICORE_MEMORY_H__
-#define __UNICORE_MEMORY_H__
-
-#include <linux/compiler.h>
-#include <linux/const.h>
-#include <linux/sizes.h>
-#include <mach/memory.h>
-
-/*
- * PAGE_OFFSET - the virtual address of the start of the kernel image
- * TASK_SIZE - the maximum size of a user space task.
- * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
- */
-#define PAGE_OFFSET		UL(0xC0000000)
-#define TASK_SIZE		(PAGE_OFFSET - UL(0x41000000))
-#define TASK_UNMAPPED_BASE	(PAGE_OFFSET / 3)
-
-/*
- * The module space lives between the addresses given by TASK_SIZE
- * and PAGE_OFFSET - it must be within 32MB of the kernel text.
- */
-#define MODULES_VADDR		(PAGE_OFFSET - 16*1024*1024)
-#if TASK_SIZE > MODULES_VADDR
-#error Top of user space clashes with start of module space
-#endif
-
-#define MODULES_END		(PAGE_OFFSET)
-
-/*
- * Allow 16MB-aligned ioremap pages
- */
-#define IOREMAP_MAX_ORDER	24
-
-/*
- * Physical vs virtual RAM address space conversion.  These are
- * private definitions which should NOT be used outside memory.h
- * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
- */
-#ifndef __virt_to_phys
-#define __virt_to_phys(x)	((x) - PAGE_OFFSET + PHYS_OFFSET)
-#define __phys_to_virt(x)	((x) - PHYS_OFFSET + PAGE_OFFSET)
-#endif
-
-/*
- * Convert a page to/from a physical address
- */
-#define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
-#define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
-
-#ifndef __ASSEMBLY__
-
-#ifndef arch_adjust_zones
-#define arch_adjust_zones(max_zone_pfn) do { } while (0)
-#endif
-
-/*
- * PFNs are used to describe any physical page; this means
- * PFN 0 == physical address 0.
- *
- * This is the PFN of the first RAM page in the kernel
- * direct-mapped view.  We assume this is the first page
- * of RAM in the mem_map as well.
- */
-#define PHYS_PFN_OFFSET	(PHYS_OFFSET >> PAGE_SHIFT)
-
-/*
- * Drivers should NOT use these either.
- */
-#define __pa(x)			__virt_to_phys((unsigned long)(x))
-#define __va(x)			((void *)__phys_to_virt((unsigned long)(x)))
-#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
-
-/*
- * Conversion between a struct page and a physical address.
- *
- *  page_to_pfn(page)	convert a struct page * to a PFN number
- *  pfn_to_page(pfn)	convert a _valid_ PFN number to struct page *
- *
- *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
- *  virt_addr_valid(k)	indicates whether a virtual address is valid
- */
-#define ARCH_PFN_OFFSET		PHYS_PFN_OFFSET
-
-#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr)	((unsigned long)(kaddr) >= PAGE_OFFSET && \
-		(unsigned long)(kaddr) < (unsigned long)high_memory)
-
-#endif
-
-#include <asm-generic/memory_model.h>
-
-#endif
diff --git a/arch/unicore32/include/asm/mmu.h b/arch/unicore32/include/asm/mmu.h
deleted file mode 100644
index 8ad4e7eae17b..000000000000
--- a/arch/unicore32/include/asm/mmu.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/mmu.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_MMU_H__
-#define __UNICORE_MMU_H__
-
-typedef	unsigned long mm_context_t;
-
-#endif
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
deleted file mode 100644
index 388c0c811c68..000000000000
--- a/arch/unicore32/include/asm/mmu_context.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/mmu_context.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_MMU_CONTEXT_H__
-#define __UNICORE_MMU_CONTEXT_H__
-
-#include <linux/compiler.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/vmacache.h>
-#include <linux/io.h>
-
-#include <asm/cacheflush.h>
-#include <asm/cpu-single.h>
-
-#define init_new_context(tsk, mm)	0
-
-#define destroy_context(mm)		do { } while (0)
-
-/*
- * This is called when "tsk" is about to enter lazy TLB mode.
- *
- * mm:  describes the currently active mm context
- * tsk: task which is entering lazy tlb
- * cpu: cpu number which is entering lazy tlb
- *
- * tsk->mm will be NULL
- */
-static inline void
-enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-/*
- * This is the actual mm switch as far as the scheduler
- * is concerned.  No registers are touched.  We avoid
- * calling the CPU specific function when the mm hasn't
- * actually changed.
- */
-static inline void
-switch_mm(struct mm_struct *prev, struct mm_struct *next,
-	  struct task_struct *tsk)
-{
-	unsigned int cpu = smp_processor_id();
-
-	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
-		cpu_switch_mm(next->pgd, next);
-}
-
-#define deactivate_mm(tsk, mm)	do { } while (0)
-#define activate_mm(prev, next)	switch_mm(prev, next, NULL)
-
-/*
- * We are inserting a "fake" vma for the user-accessible vector page so
- * gdb and friends can get to it through ptrace and /proc/<pid>/mem.
- * But we also want to remove it before the generic code gets to see it
- * during process exit or the unmapping of it would  cause total havoc.
- * (the macro is used as remove_vma() is static to mm/mmap.c)
- */
-#define arch_exit_mmap(mm) \
-do { \
-	struct vm_area_struct *high_vma = find_vma(mm, 0xffff0000); \
-	if (high_vma) { \
-		BUG_ON(high_vma->vm_next);  /* it should be last */ \
-		if (high_vma->vm_prev) \
-			high_vma->vm_prev->vm_next = NULL; \
-		else \
-			mm->mmap = NULL; \
-		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
-		vmacache_invalidate(mm); \
-		mm->map_count--; \
-		remove_vma(high_vma); \
-	} \
-} while (0)
-
-static inline int arch_dup_mmap(struct mm_struct *oldmm,
-				struct mm_struct *mm)
-{
-	return 0;
-}
-
-static inline void arch_unmap(struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-}
-
-static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
-		bool write, bool execute, bool foreign)
-{
-	/* by default, allow everything */
-	return true;
-}
-#endif
diff --git a/arch/unicore32/include/asm/page.h b/arch/unicore32/include/asm/page.h
deleted file mode 100644
index 96d6bdf180bd..000000000000
--- a/arch/unicore32/include/asm/page.h
+++ /dev/null
@@ -1,74 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/page.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_PAGE_H__
-#define __UNICORE_PAGE_H__
-
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT		12
-#define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
-#define PAGE_MASK		(~(PAGE_SIZE-1))
-
-#ifndef __ASSEMBLY__
-
-struct page;
-struct vm_area_struct;
-
-#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
-extern void copy_page(void *to, const void *from);
-
-#define clear_user_page(page, vaddr, pg)	clear_page(page)
-#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
-
-#undef STRICT_MM_TYPECHECKS
-
-#ifdef STRICT_MM_TYPECHECKS
-/*
- * These are used to make use of C type-checking..
- */
-typedef struct { unsigned long pte; } pte_t;
-typedef struct { unsigned long pgd; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
-
-#define pte_val(x)      ((x).pte)
-#define pgd_val(x)	((x).pgd)
-#define pgprot_val(x)   ((x).pgprot)
-
-#define __pte(x)        ((pte_t) { (x) })
-#define __pgd(x)	((pgd_t) { (x) })
-#define __pgprot(x)     ((pgprot_t) { (x) })
-
-#else
-/*
- * .. while these make it easier on the compiler
- */
-typedef unsigned long pte_t;
-typedef unsigned long pgd_t;
-typedef unsigned long pgprot_t;
-
-#define pte_val(x)      (x)
-#define pgd_val(x)      (x)
-#define pgprot_val(x)   (x)
-
-#define __pte(x)        (x)
-#define __pgd(x)	(x)
-#define __pgprot(x)     (x)
-
-#endif /* STRICT_MM_TYPECHECKS */
-
-typedef struct page *pgtable_t;
-
-extern int pfn_valid(unsigned long);
-
-#include <asm/memory.h>
-
-#endif /* !__ASSEMBLY__ */
-
-#include <asm-generic/getorder.h>
-
-#endif
diff --git a/arch/unicore32/include/asm/pci.h b/arch/unicore32/include/asm/pci.h
deleted file mode 100644
index 3efa8ee1afce..000000000000
--- a/arch/unicore32/include/asm/pci.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/pci.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_PCI_H__
-#define __UNICORE_PCI_H__
-
-#ifdef __KERNEL__
-#include <asm-generic/pci.h>
-#include <mach/hardware.h> /* for PCIBIOS_MIN_* */
-
-#define HAVE_PCI_MMAP
-#define ARCH_GENERIC_PCI_MMAP_RESOURCE
-
-#endif /* __KERNEL__ */
-#endif
diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h
deleted file mode 100644
index ba1c9a79993b..000000000000
--- a/arch/unicore32/include/asm/pgalloc.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/pgalloc.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_PGALLOC_H__
-#define __UNICORE_PGALLOC_H__
-
-#include <asm/pgtable-hwdef.h>
-#include <asm/processor.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
-#define __HAVE_ARCH_PTE_ALLOC_ONE
-#include <asm-generic/pgalloc.h>
-
-#define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_PRESENT)
-#define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_PRESENT)
-
-extern pgd_t *get_pgd_slow(struct mm_struct *mm);
-extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
-
-#define pgd_alloc(mm)			get_pgd_slow(mm)
-#define pgd_free(mm, pgd)		free_pgd_slow(mm, pgd)
-
-/*
- * Allocate one PTE table.
- */
-static inline pte_t *
-pte_alloc_one_kernel(struct mm_struct *mm)
-{
-	pte_t *pte = __pte_alloc_one_kernel(mm);
-
-	if (pte)
-		clean_dcache_area(pte, PTRS_PER_PTE * sizeof(pte_t));
-
-	return pte;
-}
-
-static inline pgtable_t
-pte_alloc_one(struct mm_struct *mm)
-{
-	struct page *pte;
-
-	pte = __pte_alloc_one(mm, GFP_PGTABLE_USER);
-	if (!pte)
-		return NULL;
-	if (!PageHighMem(pte))
-		clean_pte_table(page_address(pte));
-	return pte;
-}
-
-static inline void __pmd_populate(pmd_t *pmdp, unsigned long pmdval)
-{
-	set_pmd(pmdp, __pmd(pmdval));
-	flush_pmd_entry(pmdp);
-}
-
-/*
- * Populate the pmdp entry with a pointer to the pte.  This pmd is part
- * of the mm address space.
- */
-static inline void
-pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
-{
-	unsigned long pte_ptr = (unsigned long)ptep;
-
-	/*
-	 * The pmd must be loaded with the physical
-	 * address of the PTE table
-	 */
-	__pmd_populate(pmdp, __pa(pte_ptr) | _PAGE_KERNEL_TABLE);
-}
-
-static inline void
-pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
-{
-	__pmd_populate(pmdp,
-			page_to_pfn(ptep) << PAGE_SHIFT | _PAGE_USER_TABLE);
-}
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-#endif
diff --git a/arch/unicore32/include/asm/pgtable-hwdef.h b/arch/unicore32/include/asm/pgtable-hwdef.h
deleted file mode 100644
index f28b58c61db9..000000000000
--- a/arch/unicore32/include/asm/pgtable-hwdef.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/pgtable-hwdef.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_PGTABLE_HWDEF_H__
-#define __UNICORE_PGTABLE_HWDEF_H__
-
-/*
- * Hardware page table definitions.
- *
- * + Level 1 descriptor (PMD)
- *   - common
- */
-#define PMD_TYPE_MASK		(3 << 0)
-#define PMD_TYPE_TABLE		(0 << 0)
-/*#define PMD_TYPE_LARGE	(1 << 0) */
-#define PMD_TYPE_INVALID	(2 << 0)
-#define PMD_TYPE_SECT		(3 << 0)
-
-#define PMD_PRESENT		(1 << 2)
-#define PMD_YOUNG		(1 << 3)
-
-/*#define PMD_SECT_DIRTY	(1 << 4) */
-#define PMD_SECT_CACHEABLE	(1 << 5)
-#define PMD_SECT_EXEC		(1 << 6)
-#define PMD_SECT_WRITE		(1 << 7)
-#define PMD_SECT_READ		(1 << 8)
-
-/*
- * + Level 2 descriptor (PTE)
- *   - common
- */
-#define PTE_TYPE_MASK		(3 << 0)
-#define PTE_TYPE_SMALL		(0 << 0)
-#define PTE_TYPE_MIDDLE		(1 << 0)
-#define PTE_TYPE_LARGE		(2 << 0)
-#define PTE_TYPE_INVALID	(3 << 0)
-
-#define PTE_PRESENT		(1 << 2)
-#define PTE_YOUNG		(1 << 3)
-#define PTE_DIRTY		(1 << 4)
-#define PTE_CACHEABLE		(1 << 5)
-#define PTE_EXEC		(1 << 6)
-#define PTE_WRITE		(1 << 7)
-#define PTE_READ		(1 << 8)
-
-#endif
diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h
deleted file mode 100644
index 97f564c8ecba..000000000000
--- a/arch/unicore32/include/asm/pgtable.h
+++ /dev/null
@@ -1,267 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/pgtable.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_PGTABLE_H__
-#define __UNICORE_PGTABLE_H__
-
-#include <asm-generic/pgtable-nopmd.h>
-#include <asm/cpu-single.h>
-
-#include <asm/memory.h>
-#include <asm/pgtable-hwdef.h>
-
-/*
- * Just any arbitrary offset to the start of the vmalloc VM area: the
- * current 8MB value just means that there will be a 8MB "hole" after the
- * physical memory until the kernel virtual memory starts.  That means that
- * any out-of-bounds memory accesses will hopefully be caught.
- * The vmalloc() routines leaves a hole of 4kB between each vmalloced
- * area for the same reason. ;)
- *
- * Note that platforms may override VMALLOC_START, but they must provide
- * VMALLOC_END.  VMALLOC_END defines the (exclusive) limit of this space,
- * which may not overlap IO space.
- */
-#ifndef VMALLOC_START
-#define VMALLOC_OFFSET		SZ_8M
-#define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) \
-					& ~(VMALLOC_OFFSET-1))
-#define VMALLOC_END		(0xff000000UL)
-#endif
-
-#define PTRS_PER_PTE		1024
-#define PTRS_PER_PGD		1024
-
-/*
- * PGDIR_SHIFT determines what a third-level page table entry can map
- */
-#define PGDIR_SHIFT		22
-
-#ifndef __ASSEMBLY__
-extern void __pte_error(const char *file, int line, unsigned long val);
-extern void __pgd_error(const char *file, int line, unsigned long val);
-
-#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
-#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
-#endif /* !__ASSEMBLY__ */
-
-#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK		(~(PGDIR_SIZE-1))
-
-/*
- * This is the lowest virtual address we can permit any user space
- * mapping to be mapped at.  This is particularly important for
- * non-high vector CPUs.
- */
-#define FIRST_USER_ADDRESS	PAGE_SIZE
-
-#define FIRST_USER_PGD_NR	1
-#define USER_PTRS_PER_PGD	((TASK_SIZE/PGDIR_SIZE) - FIRST_USER_PGD_NR)
-
-/*
- * section address mask and size definitions.
- */
-#define SECTION_SHIFT		22
-#define SECTION_SIZE		(1UL << SECTION_SHIFT)
-#define SECTION_MASK		(~(SECTION_SIZE-1))
-
-#ifndef __ASSEMBLY__
-
-/*
- * The pgprot_* and protection_map entries will be fixed up in runtime
- * to include the cachable bits based on memory policy, as well as any
- * architecture dependent bits.
- */
-#define _PTE_DEFAULT		(PTE_PRESENT | PTE_YOUNG | PTE_CACHEABLE)
-
-extern pgprot_t pgprot_user;
-extern pgprot_t pgprot_kernel;
-
-#define PAGE_NONE		pgprot_user
-#define PAGE_SHARED		__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_WRITE))
-#define PAGE_SHARED_EXEC	__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_WRITE \
-								| PTE_EXEC))
-#define PAGE_COPY		__pgprot(pgprot_val(pgprot_user | PTE_READ)
-#define PAGE_COPY_EXEC		__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_EXEC))
-#define PAGE_READONLY		__pgprot(pgprot_val(pgprot_user | PTE_READ))
-#define PAGE_READONLY_EXEC	__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_EXEC))
-#define PAGE_KERNEL		pgprot_kernel
-#define PAGE_KERNEL_EXEC	__pgprot(pgprot_val(pgprot_kernel | PTE_EXEC))
-
-#define __PAGE_NONE		__pgprot(_PTE_DEFAULT)
-#define __PAGE_SHARED		__pgprot(_PTE_DEFAULT | PTE_READ \
-							| PTE_WRITE)
-#define __PAGE_SHARED_EXEC	__pgprot(_PTE_DEFAULT | PTE_READ \
-							| PTE_WRITE \
-							| PTE_EXEC)
-#define __PAGE_COPY		__pgprot(_PTE_DEFAULT | PTE_READ)
-#define __PAGE_COPY_EXEC	__pgprot(_PTE_DEFAULT | PTE_READ \
-							| PTE_EXEC)
-#define __PAGE_READONLY		__pgprot(_PTE_DEFAULT | PTE_READ)
-#define __PAGE_READONLY_EXEC	__pgprot(_PTE_DEFAULT | PTE_READ \
-							| PTE_EXEC)
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * The table below defines the page protection levels that we insert into our
- * Linux page table version.  These get translated into the best that the
- * architecture can perform.  Note that on UniCore hardware:
- *  1) We cannot do execute protection
- *  2) If we could do execute protection, then read is implied
- *  3) write implies read permissions
- */
-#define __P000  __PAGE_NONE
-#define __P001  __PAGE_READONLY
-#define __P010  __PAGE_COPY
-#define __P011  __PAGE_COPY
-#define __P100  __PAGE_READONLY_EXEC
-#define __P101  __PAGE_READONLY_EXEC
-#define __P110  __PAGE_COPY_EXEC
-#define __P111  __PAGE_COPY_EXEC
-
-#define __S000  __PAGE_NONE
-#define __S001  __PAGE_READONLY
-#define __S010  __PAGE_SHARED
-#define __S011  __PAGE_SHARED
-#define __S100  __PAGE_READONLY_EXEC
-#define __S101  __PAGE_READONLY_EXEC
-#define __S110  __PAGE_SHARED_EXEC
-#define __S111  __PAGE_SHARED_EXEC
-
-#ifndef __ASSEMBLY__
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern struct page *empty_zero_page;
-#define ZERO_PAGE(vaddr)		(empty_zero_page)
-
-#define pte_pfn(pte)			(pte_val(pte) >> PAGE_SHIFT)
-#define pfn_pte(pfn, prot)		(__pte(((pfn) << PAGE_SHIFT) \
-						| pgprot_val(prot)))
-
-#define pte_none(pte)			(!pte_val(pte))
-#define pte_clear(mm, addr, ptep)	set_pte(ptep, __pte(0))
-#define pte_page(pte)			(pfn_to_page(pte_pfn(pte)))
-
-#define set_pte(ptep, pte)	cpu_set_pte(ptep, pte)
-
-#define set_pte_at(mm, addr, ptep, pteval)	\
-	do {					\
-		set_pte(ptep, pteval);          \
-	} while (0)
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-#define pte_present(pte)	(pte_val(pte) & PTE_PRESENT)
-#define pte_write(pte)		(pte_val(pte) & PTE_WRITE)
-#define pte_dirty(pte)		(pte_val(pte) & PTE_DIRTY)
-#define pte_young(pte)		(pte_val(pte) & PTE_YOUNG)
-#define pte_exec(pte)		(pte_val(pte) & PTE_EXEC)
-
-#define PTE_BIT_FUNC(fn, op) \
-static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
-
-PTE_BIT_FUNC(wrprotect, &= ~PTE_WRITE);
-PTE_BIT_FUNC(mkwrite,   |= PTE_WRITE);
-PTE_BIT_FUNC(mkclean,   &= ~PTE_DIRTY);
-PTE_BIT_FUNC(mkdirty,   |= PTE_DIRTY);
-PTE_BIT_FUNC(mkold,     &= ~PTE_YOUNG);
-PTE_BIT_FUNC(mkyoung,   |= PTE_YOUNG);
-
-/*
- * Mark the prot value as uncacheable.
- */
-#define pgprot_noncached(prot)		\
-	__pgprot(pgprot_val(prot) & ~PTE_CACHEABLE)
-#define pgprot_writecombine(prot)	\
-	__pgprot(pgprot_val(prot) & ~PTE_CACHEABLE)
-
-#define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd) & PMD_PRESENT)
-#define pmd_bad(pmd)		(((pmd_val(pmd) &		\
-				(PMD_PRESENT | PMD_TYPE_MASK))	\
-				!= (PMD_PRESENT | PMD_TYPE_TABLE)))
-
-#define set_pmd(pmdpd, pmdval)		\
-	do {				\
-		*(pmdpd) = pmdval;	\
-	} while (0)
-
-#define pmd_clear(pmdp)			\
-	do {				\
-		set_pmd(pmdp, __pmd(0));\
-		clean_pmd_entry(pmdp);	\
-	} while (0)
-
-#define pmd_page_vaddr(pmd) ((pte_t *)__va(pmd_val(pmd) & PAGE_MASK))
-#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
-
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
-	const unsigned long mask = PTE_EXEC | PTE_WRITE | PTE_READ;
-	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
-	return pte;
-}
-
-extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-
-/*
- * Encode and decode a swap entry.  Swap entries are stored in the Linux
- * page tables as follows:
- *
- *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
- *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
- *   <--------------- offset --------------> <--- type --> 0 0 0 0 0
- *
- * This gives us up to 127 swap files and 32GB per swap file.  Note that
- * the offset field is always non-zero.
- */
-#define __SWP_TYPE_SHIFT	5
-#define __SWP_TYPE_BITS		7
-#define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
-#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
-
-#define __swp_type(x)		(((x).val >> __SWP_TYPE_SHIFT)		\
-				& __SWP_TYPE_MASK)
-#define __swp_offset(x)		((x).val >> __SWP_OFFSET_SHIFT)
-#define __swp_entry(type, offset) ((swp_entry_t) {			\
-				((type) << __SWP_TYPE_SHIFT) |		\
-				((offset) << __SWP_OFFSET_SHIFT) })
-
-#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
-#define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })
-
-/*
- * It is an error for the kernel to have more swap files than we can
- * encode in the PTEs.  This ensures that we know when MAX_SWAPFILES
- * is increased beyond what we presently support.
- */
-#define MAX_SWAPFILES_CHECK()	\
-	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
-
-/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
-/* FIXME: this is not correct */
-#define kern_addr_valid(addr)	(1)
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __UNICORE_PGTABLE_H__ */
diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h
deleted file mode 100644
index 6f01620da3d1..000000000000
--- a/arch/unicore32/include/asm/processor.h
+++ /dev/null
@@ -1,74 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/processor.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_PROCESSOR_H__
-#define __UNICORE_PROCESSOR_H__
-
-#ifdef __KERNEL__
-
-#include <asm/ptrace.h>
-#include <asm/types.h>
-
-#ifdef __KERNEL__
-#define STACK_TOP	TASK_SIZE
-#define STACK_TOP_MAX	TASK_SIZE
-#endif
-
-struct debug_entry {
-	u32			address;
-	u32			insn;
-};
-
-struct debug_info {
-	int			nsaved;
-	struct debug_entry	bp[2];
-};
-
-struct thread_struct {
-							/* fault info	  */
-	unsigned long		address;
-	unsigned long		trap_no;
-	unsigned long		error_code;
-							/* debugging	  */
-	struct debug_info	debug;
-};
-
-#define INIT_THREAD  {	}
-
-#define start_thread(regs, pc, sp)					\
-({									\
-	unsigned long *stack = (unsigned long *)sp;			\
-	memset(regs->uregs, 0, sizeof(regs->uregs));			\
-	regs->UCreg_asr = USER_MODE;					\
-	regs->UCreg_pc = pc & ~1;	/* pc */                        \
-	regs->UCreg_sp = sp;		/* sp */                        \
-	regs->UCreg_02 = stack[2];	/* r2 (envp) */                 \
-	regs->UCreg_01 = stack[1];	/* r1 (argv) */                 \
-	regs->UCreg_00 = stack[0];	/* r0 (argc) */                 \
-})
-
-/* Forward declaration, a strange C thing */
-struct task_struct;
-
-/* Free all resources held by a thread. */
-extern void release_thread(struct task_struct *);
-
-unsigned long get_wchan(struct task_struct *p);
-
-#define cpu_relax()			barrier()
-
-#define task_pt_regs(p) \
-	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
-
-#define KSTK_EIP(tsk)	(task_pt_regs(tsk)->UCreg_pc)
-#define KSTK_ESP(tsk)	(task_pt_regs(tsk)->UCreg_sp)
-
-#endif
-
-#endif /* __UNICORE_PROCESSOR_H__ */
diff --git a/arch/unicore32/include/asm/ptrace.h b/arch/unicore32/include/asm/ptrace.h
deleted file mode 100644
index bb4cbc42c321..000000000000
--- a/arch/unicore32/include/asm/ptrace.h
+++ /dev/null
@@ -1,58 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/ptrace.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_PTRACE_H__
-#define __UNICORE_PTRACE_H__
-
-#include <uapi/asm/ptrace.h>
-
-#ifndef __ASSEMBLY__
-
-#define user_mode(regs)	\
-	(processor_mode(regs) == USER_MODE)
-
-#define processor_mode(regs) \
-	((regs)->UCreg_asr & MODE_MASK)
-
-#define interrupts_enabled(regs) \
-	(!((regs)->UCreg_asr & PSR_I_BIT))
-
-#define fast_interrupts_enabled(regs) \
-	(!((regs)->UCreg_asr & PSR_R_BIT))
-
-/* Are the current registers suitable for user mode?
- * (used to maintain security in signal handlers)
- */
-static inline int valid_user_regs(struct pt_regs *regs)
-{
-	unsigned long mode = regs->UCreg_asr & MODE_MASK;
-
-	/*
-	 * Always clear the R (REAL) bits
-	 */
-	regs->UCreg_asr &= ~(PSR_R_BIT);
-
-	if ((regs->UCreg_asr & PSR_I_BIT) == 0) {
-		if (mode == USER_MODE)
-			return 1;
-	}
-
-	/*
-	 * Force ASR to something logical...
-	 */
-	regs->UCreg_asr &= PSR_f | USER_MODE;
-
-	return 0;
-}
-
-#define instruction_pointer(regs)	((regs)->UCreg_pc)
-#define user_stack_pointer(regs)	((regs)->UCreg_sp)
-#define profile_pc(regs)		instruction_pointer(regs)
-
-#endif /* __ASSEMBLY__ */
-#endif
diff --git a/arch/unicore32/include/asm/stacktrace.h b/arch/unicore32/include/asm/stacktrace.h
deleted file mode 100644
index 3e59f9d2faed..000000000000
--- a/arch/unicore32/include/asm/stacktrace.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/stacktrace.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_STACKTRACE_H__
-#define __UNICORE_STACKTRACE_H__
-
-struct stackframe {
-	unsigned long fp;
-	unsigned long sp;
-	unsigned long lr;
-	unsigned long pc;
-};
-
-#ifdef CONFIG_FRAME_POINTER
-extern int unwind_frame(struct stackframe *frame);
-#else
-#define unwind_frame(f) (-EINVAL)
-#endif
-extern void walk_stackframe(struct stackframe *frame,
-			    int (*fn)(struct stackframe *, void *), void *data);
-
-#endif	/* __UNICORE_STACKTRACE_H__ */
diff --git a/arch/unicore32/include/asm/string.h b/arch/unicore32/include/asm/string.h
deleted file mode 100644
index 1649b0e4271b..000000000000
--- a/arch/unicore32/include/asm/string.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/string.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_STRING_H__
-#define __UNICORE_STRING_H__
-
-/*
- * We don't do inline string functions, since the
- * optimised inline asm versions are not small.
- */
-
-#define __HAVE_ARCH_STRRCHR
-extern char *strrchr(const char *s, int c);
-
-#define __HAVE_ARCH_STRCHR
-extern char *strchr(const char *s, int c);
-
-#define __HAVE_ARCH_MEMCPY
-extern void *memcpy(void *, const void *, __kernel_size_t);
-
-#define __HAVE_ARCH_MEMMOVE
-extern void *memmove(void *, const void *, __kernel_size_t);
-
-#define __HAVE_ARCH_MEMCHR
-extern void *memchr(const void *, int, __kernel_size_t);
-
-#define __HAVE_ARCH_MEMSET
-extern void *memset(void *, int, __kernel_size_t);
-
-#endif
diff --git a/arch/unicore32/include/asm/suspend.h b/arch/unicore32/include/asm/suspend.h
deleted file mode 100644
index 72bd89c44d10..000000000000
--- a/arch/unicore32/include/asm/suspend.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/suspend.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_SUSPEND_H__
-#define __UNICORE_SUSPEND_H__
-
-#ifndef __ASSEMBLY__
-
-#include <asm/ptrace.h>
-
-struct swsusp_arch_regs {
-	struct cpu_context_save	cpu_context;	/* cpu context */
-#ifdef CONFIG_UNICORE_FPU_F64
-	struct fp_state		fpstate __attribute__((aligned(8)));
-#endif
-};
-#endif
-
-#endif /* __UNICORE_SUSPEND_H__ */
-
diff --git a/arch/unicore32/include/asm/switch_to.h b/arch/unicore32/include/asm/switch_to.h
deleted file mode 100644
index 12e534b3bfa5..000000000000
--- a/arch/unicore32/include/asm/switch_to.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Task switching for PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2012 GUAN Xue-tao
- */
-#ifndef __UNICORE_SWITCH_TO_H__
-#define __UNICORE_SWITCH_TO_H__
-
-struct task_struct;
-struct thread_info;
-
-/*
- * switch_to(prev, next) should switch from task `prev' to `next'
- * `prev' will never be the same as `next'.  schedule() itself
- * contains the memory barrier to tell GCC not to cache `current'.
- */
-extern struct task_struct *__switch_to(struct task_struct *,
-		struct thread_info *, struct thread_info *);
-
-#define switch_to(prev, next, last)					\
-	do {								\
-		last = __switch_to(prev, task_thread_info(prev),	\
-					task_thread_info(next));	\
-	} while (0)
-
-#endif /* __UNICORE_SWITCH_TO_H__ */
diff --git a/arch/unicore32/include/asm/syscall.h b/arch/unicore32/include/asm/syscall.h
deleted file mode 100644
index 607961797fff..000000000000
--- a/arch/unicore32/include/asm/syscall.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_UNICORE_SYSCALL_H
-#define _ASM_UNICORE_SYSCALL_H
-
-#include <uapi/linux/audit.h>
-
-static inline int syscall_get_arch(struct task_struct *task)
-{
-	return AUDIT_ARCH_UNICORE;
-}
-
-#endif	/* _ASM_UNICORE_SYSCALL_H */
diff --git a/arch/unicore32/include/asm/thread_info.h b/arch/unicore32/include/asm/thread_info.h
deleted file mode 100644
index d8a6d6b7a403..000000000000
--- a/arch/unicore32/include/asm/thread_info.h
+++ /dev/null
@@ -1,133 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/thread_info.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_THREAD_INFO_H__
-#define __UNICORE_THREAD_INFO_H__
-
-#ifdef __KERNEL__
-
-#include <linux/compiler.h>
-#include <asm/fpstate.h>
-
-#define THREAD_SIZE_ORDER	1
-#define THREAD_SIZE		8192
-#define THREAD_START_SP		(THREAD_SIZE - 8)
-
-#ifndef __ASSEMBLY__
-
-struct task_struct;
-
-#include <asm/types.h>
-
-typedef struct {
-	unsigned long seg;
-} mm_segment_t;
-
-struct cpu_context_save {
-	__u32	r4;
-	__u32	r5;
-	__u32	r6;
-	__u32	r7;
-	__u32	r8;
-	__u32	r9;
-	__u32	r10;
-	__u32	r11;
-	__u32	r12;
-	__u32	r13;
-	__u32	r14;
-	__u32	r15;
-	__u32	r16;
-	__u32	r17;
-	__u32	r18;
-	__u32	r19;
-	__u32	r20;
-	__u32	r21;
-	__u32	r22;
-	__u32	r23;
-	__u32	r24;
-	__u32	r25;
-	__u32	r26;
-	__u32	fp;
-	__u32	sp;
-	__u32	pc;
-};
-
-/*
- * low level task data that entry.S needs immediate access to.
- * __switch_to() assumes cpu_context follows immediately after cpu_domain.
- */
-struct thread_info {
-	unsigned long		flags;		/* low level flags */
-	int			preempt_count;	/* 0 => preemptable */
-						/* <0 => bug */
-	mm_segment_t		addr_limit;	/* address limit */
-	struct task_struct	*task;		/* main task structure */
-	__u32			cpu;		/* cpu */
-	struct cpu_context_save	cpu_context;	/* cpu context */
-	__u32			syscall;	/* syscall number */
-	__u8			used_cp[16];	/* thread used copro */
-#ifdef CONFIG_UNICORE_FPU_F64
-	struct fp_state		fpstate __attribute__((aligned(8)));
-#endif
-};
-
-#define INIT_THREAD_INFO(tsk)						\
-{									\
-	.task		= &tsk,						\
-	.flags		= 0,						\
-	.preempt_count	= INIT_PREEMPT_COUNT,				\
-	.addr_limit	= KERNEL_DS,					\
-}
-
-/*
- * how to get the thread information struct from C
- */
-static inline struct thread_info *current_thread_info(void) __attribute_const__;
-
-static inline struct thread_info *current_thread_info(void)
-{
-	register unsigned long sp asm ("sp");
-	return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
-}
-
-#define thread_saved_pc(tsk)	\
-	((unsigned long)(task_thread_info(tsk)->cpu_context.pc))
-#define thread_saved_sp(tsk)	\
-	((unsigned long)(task_thread_info(tsk)->cpu_context.sp))
-#define thread_saved_fp(tsk)	\
-	((unsigned long)(task_thread_info(tsk)->cpu_context.fp))
-
-#endif
-
-/*
- * thread information flags:
- *  TIF_SYSCALL_TRACE	- syscall trace active
- *  TIF_SIGPENDING	- signal pending
- *  TIF_NEED_RESCHED	- rescheduling necessary
- *  TIF_NOTIFY_RESUME	- callback before returning to user
- */
-#define TIF_SIGPENDING		0
-#define TIF_NEED_RESCHED	1
-#define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
-#define TIF_SYSCALL_TRACE	8
-#define TIF_MEMDIE		18
-#define TIF_RESTORE_SIGMASK	20
-
-#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
-#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-
-/*
- * Change these and you break ASM code in entry-common.S
- */
-#define _TIF_WORK_MASK \
-	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_NOTIFY_RESUME)
-
-#endif /* __KERNEL__ */
-#endif /* __UNICORE_THREAD_INFO_H__ */
diff --git a/arch/unicore32/include/asm/timex.h b/arch/unicore32/include/asm/timex.h
deleted file mode 100644
index d714af3dbce1..000000000000
--- a/arch/unicore32/include/asm/timex.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/timex.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __UNICORE_TIMEX_H__
-#define __UNICORE_TIMEX_H__
-
-#ifdef	CONFIG_ARCH_FPGA
-
-/* in FPGA, APB clock is 33M, and OST clock is 32K, */
-/* so, 1M is selected for timer interrupt correctly */
-#define	CLOCK_TICK_RATE		(32*1024)
-
-#endif
-
-#if defined(CONFIG_PUV3_DB0913)		\
-	|| defined(CONFIG_PUV3_NB0916)	\
-	|| defined(CONFIG_PUV3_SMW0919)
-
-#define  CLOCK_TICK_RATE         (14318000)
-
-#endif
-
-#include <asm-generic/timex.h>
-
-#endif
diff --git a/arch/unicore32/include/asm/tlb.h b/arch/unicore32/include/asm/tlb.h
deleted file mode 100644
index 4663d8cc80ef..000000000000
--- a/arch/unicore32/include/asm/tlb.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/tlb.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_TLB_H__
-#define __UNICORE_TLB_H__
-
-/*
- * unicore32 lacks an efficient flush_tlb_range(), use flush_tlb_mm().
- */
-
-#define __pte_free_tlb(tlb, pte, addr)				\
-	do {							\
-		pgtable_pte_page_dtor(pte);			\
-		tlb_remove_page((tlb), (pte));			\
-	} while (0)
-
-#include <asm-generic/tlb.h>
-
-#endif
diff --git a/arch/unicore32/include/asm/tlbflush.h b/arch/unicore32/include/asm/tlbflush.h
deleted file mode 100644
index 1cf18ef55515..000000000000
--- a/arch/unicore32/include/asm/tlbflush.h
+++ /dev/null
@@ -1,192 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/tlbflush.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_TLBFLUSH_H__
-#define __UNICORE_TLBFLUSH_H__
-
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-
-extern void __cpu_flush_user_tlb_range(unsigned long, unsigned long,
-					struct vm_area_struct *);
-extern void __cpu_flush_kern_tlb_range(unsigned long, unsigned long);
-
-/*
- *	TLB Management
- *	==============
- *
- *	The arch/unicore/mm/tlb-*.S files implement these methods.
- *
- *	The TLB specific code is expected to perform whatever tests it
- *	needs to determine if it should invalidate the TLB for each
- *	call.  Start addresses are inclusive and end addresses are
- *	exclusive; it is safe to round these addresses down.
- *
- *	flush_tlb_all()
- *
- *		Invalidate the entire TLB.
- *
- *	flush_tlb_mm(mm)
- *
- *		Invalidate all TLB entries in a particular address
- *		space.
- *		- mm	- mm_struct describing address space
- *
- *	flush_tlb_range(mm,start,end)
- *
- *		Invalidate a range of TLB entries in the specified
- *		address space.
- *		- mm	- mm_struct describing address space
- *		- start - start address (may not be aligned)
- *		- end	- end address (exclusive, may not be aligned)
- *
- *	flush_tlb_page(vaddr,vma)
- *
- *		Invalidate the specified page in the specified address range.
- *		- vaddr - virtual address (may not be aligned)
- *		- vma	- vma_struct describing address range
- *
- *	flush_kern_tlb_page(kaddr)
- *
- *		Invalidate the TLB entry for the specified page.  The address
- *		will be in the kernels virtual memory space.  Current uses
- *		only require the D-TLB to be invalidated.
- *		- kaddr - Kernel virtual memory address
- */
-
-static inline void local_flush_tlb_all(void)
-{
-	const int zero = 0;
-
-	/* TLB invalidate all */
-	asm("movc p0.c6, %0, #6; nop; nop; nop; nop; nop; nop; nop; nop"
-		: : "r" (zero) : "cc");
-}
-
-static inline void local_flush_tlb_mm(struct mm_struct *mm)
-{
-	const int zero = 0;
-
-	if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
-		/* TLB invalidate all */
-		asm("movc p0.c6, %0, #6; nop; nop; nop; nop; nop; nop; nop; nop"
-			: : "r" (zero) : "cc");
-	}
-	put_cpu();
-}
-
-static inline void
-local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
-{
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-#ifndef CONFIG_CPU_TLB_SINGLE_ENTRY_DISABLE
-		/* iTLB invalidate page */
-		asm("movc p0.c6, %0, #5; nop; nop; nop; nop; nop; nop; nop; nop"
-			: : "r" (uaddr & PAGE_MASK) : "cc");
-		/* dTLB invalidate page */
-		asm("movc p0.c6, %0, #3; nop; nop; nop; nop; nop; nop; nop; nop"
-			: : "r" (uaddr & PAGE_MASK) : "cc");
-#else
-		/* TLB invalidate all */
-		asm("movc p0.c6, %0, #6; nop; nop; nop; nop; nop; nop; nop; nop"
-			: : "r" (uaddr & PAGE_MASK) : "cc");
-#endif
-	}
-}
-
-static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
-{
-#ifndef CONFIG_CPU_TLB_SINGLE_ENTRY_DISABLE
-	/* iTLB invalidate page */
-	asm("movc p0.c6, %0, #5; nop; nop; nop; nop; nop; nop; nop; nop"
-		: : "r" (kaddr & PAGE_MASK) : "cc");
-	/* dTLB invalidate page */
-	asm("movc p0.c6, %0, #3; nop; nop; nop; nop; nop; nop; nop; nop"
-		: : "r" (kaddr & PAGE_MASK) : "cc");
-#else
-	/* TLB invalidate all */
-	asm("movc p0.c6, %0, #6; nop; nop; nop; nop; nop; nop; nop; nop"
-		: : "r" (kaddr & PAGE_MASK) : "cc");
-#endif
-}
-
-/*
- *	flush_pmd_entry
- *
- *	Flush a PMD entry (word aligned, or double-word aligned) to
- *	RAM if the TLB for the CPU we are running on requires this.
- *	This is typically used when we are creating PMD entries.
- *
- *	clean_pmd_entry
- *
- *	Clean (but don't drain the write buffer) if the CPU requires
- *	these operations.  This is typically used when we are removing
- *	PMD entries.
- */
-static inline void flush_pmd_entry(pmd_t *pmd)
-{
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-	/* flush dcache line, see dcacheline_flush in proc-macros.S */
-	asm("mov	r1, %0 << #20\n"
-		"ldw	r2, =_stext\n"
-		"add	r2, r2, r1 >> #20\n"
-		"ldw	r1, [r2+], #0x0000\n"
-		"ldw	r1, [r2+], #0x1000\n"
-		"ldw	r1, [r2+], #0x2000\n"
-		"ldw	r1, [r2+], #0x3000\n"
-		: : "r" (pmd) : "r1", "r2");
-#else
-	/* flush dcache all */
-	asm("movc p0.c5, %0, #14; nop; nop; nop; nop; nop; nop; nop; nop"
-		: : "r" (pmd) : "cc");
-#endif
-}
-
-static inline void clean_pmd_entry(pmd_t *pmd)
-{
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-	/* clean dcache line */
-	asm("movc p0.c5, %0, #11; nop; nop; nop; nop; nop; nop; nop; nop"
-		: : "r" (__pa(pmd) & ~(L1_CACHE_BYTES - 1)) : "cc");
-#else
-	/* clean dcache all */
-	asm("movc p0.c5, %0, #10; nop; nop; nop; nop; nop; nop; nop; nop"
-		: : "r" (pmd) : "cc");
-#endif
-}
-
-/*
- * Convert calls to our calling convention.
- */
-#define local_flush_tlb_range(vma, start, end)	\
-	__cpu_flush_user_tlb_range(start, end, vma)
-#define local_flush_tlb_kernel_range(s, e)	\
-	__cpu_flush_kern_tlb_range(s, e)
-
-#define flush_tlb_all		local_flush_tlb_all
-#define flush_tlb_mm		local_flush_tlb_mm
-#define flush_tlb_page		local_flush_tlb_page
-#define flush_tlb_kernel_page	local_flush_tlb_kernel_page
-#define flush_tlb_range		local_flush_tlb_range
-#define flush_tlb_kernel_range	local_flush_tlb_kernel_range
-
-/*
- * if PG_dcache_clean is not set for the page, we need to ensure that any
- * cache entries for the kernels virtual memory range are written
- * back to the page.
- */
-extern void update_mmu_cache(struct vm_area_struct *vma,
-		unsigned long addr, pte_t *ptep);
-
-extern void do_bad_area(unsigned long addr, unsigned int fsr,
-		struct pt_regs *regs);
-
-#endif
-
-#endif
diff --git a/arch/unicore32/include/asm/traps.h b/arch/unicore32/include/asm/traps.h
deleted file mode 100644
index ad1508a9a903..000000000000
--- a/arch/unicore32/include/asm/traps.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/traps.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_TRAP_H__
-#define __UNICORE_TRAP_H__
-
-extern void __init early_trap_init(void);
-extern void dump_backtrace_entry(unsigned long where,
-		unsigned long from, unsigned long frame);
-
-extern void do_DataAbort(unsigned long addr, unsigned int fsr,
-		 struct pt_regs *regs);
-#endif
diff --git a/arch/unicore32/include/asm/uaccess.h b/arch/unicore32/include/asm/uaccess.h
deleted file mode 100644
index 33c24f430511..000000000000
--- a/arch/unicore32/include/asm/uaccess.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/asm/uaccess.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_UACCESS_H__
-#define __UNICORE_UACCESS_H__
-
-#include <asm/memory.h>
-
-#define __strncpy_from_user	__strncpy_from_user
-#define __strnlen_user		__strnlen_user
-#define __clear_user		__clear_user
-
-#define __kernel_ok		(uaccess_kernel())
-#define __user_ok(addr, size)	(((size) <= TASK_SIZE)			\
-				&& ((addr) <= TASK_SIZE - (size)))
-#define __access_ok(addr, size)	(__kernel_ok || __user_ok((addr), (size)))
-
-extern unsigned long __must_check
-raw_copy_from_user(void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check
-raw_copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check
-__clear_user(void __user *addr, unsigned long n);
-extern unsigned long __must_check
-__strncpy_from_user(char *to, const char __user *from, unsigned long count);
-extern unsigned long
-__strnlen_user(const char __user *s, long n);
-#define INLINE_COPY_FROM_USER
-#define INLINE_COPY_TO_USER
-
-#include <asm-generic/uaccess.h>
-
-#endif /* __UNICORE_UACCESS_H__ */
diff --git a/arch/unicore32/include/asm/vmalloc.h b/arch/unicore32/include/asm/vmalloc.h
deleted file mode 100644
index 054435818a14..000000000000
--- a/arch/unicore32/include/asm/vmalloc.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef _ASM_UNICORE32_VMALLOC_H
-#define _ASM_UNICORE32_VMALLOC_H
-
-#endif /* _ASM_UNICORE32_VMALLOC_H */
diff --git a/arch/unicore32/include/mach/PKUnity.h b/arch/unicore32/include/mach/PKUnity.h
deleted file mode 100644
index 78f77517c1c7..000000000000
--- a/arch/unicore32/include/mach/PKUnity.h
+++ /dev/null
@@ -1,95 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/mach/PKUnity.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-/* Be sure that virtual mapping is defined right */
-#ifndef __MACH_PUV3_HARDWARE_H__
-#error You must include hardware.h not PKUnity.h
-#endif
-
-#include <mach/bitfield.h>
-
-/*
- * Memory Definitions
- */
-#define PKUNITY_SDRAM_BASE		0x00000000 /* 0x00000000 - 0x7FFFFFFF 2GB */
-#define PKUNITY_MMIO_BASE		0x80000000 /* 0x80000000 - 0xFFFFFFFF 2GB */
-
-/*
- * PKUNITY System Bus Addresses (PCI): 0x80000000 - 0xBFFFFFFF (1GB)
- * 0x80000000 - 0x8000000B 12B    PCI Configuration regs
- * 0x80010000 - 0x80010250 592B   PCI Bridge Base
- * 0x80030000 - 0x8003FFFF 64KB   PCI Legacy IO
- * 0x90000000 - 0x97FFFFFF 128MB  PCI AHB-PCI MEM-mapping
- * 0x98000000 - 0x9FFFFFFF 128MB  PCI PCI-AHB MEM-mapping
- */
-#define PKUNITY_PCI_BASE		io_p2v(0x80000000) /* 0x80000000 - 0xBFFFFFFF 1GB */
-#include <mach/regs-pci.h>
-
-#define PKUNITY_PCICFG_BASE		(PKUNITY_PCI_BASE + 0x0)
-#define PKUNITY_PCIBRI_BASE		(PKUNITY_PCI_BASE + 0x00010000)
-#define PKUNITY_PCILIO_BASE		(PKUNITY_PCI_BASE + 0x00030000)
-#define PKUNITY_PCIMEM_BASE		(PKUNITY_PCI_BASE + 0x10000000)
-#define PKUNITY_PCIAHB_BASE		(PKUNITY_PCI_BASE + 0x18000000)
-
-/*
- * PKUNITY System Bus Addresses (AHB): 0xC0000000 - 0xEDFFFFFF (640MB)
- */
-#define PKUNITY_AHB_BASE		io_p2v(0xC0000000)
-
-/* AHB-0 is DDR2 SDRAM */
-/* AHB-1 is PCI Space */
-#define PKUNITY_ARBITER_BASE		(PKUNITY_AHB_BASE + 0x000000) /* AHB-2 */
-#define PKUNITY_DDR2CTRL_BASE		(PKUNITY_AHB_BASE + 0x100000) /* AHB-3 */
-#define PKUNITY_DMAC_BASE		(PKUNITY_AHB_BASE + 0x200000) /* AHB-4 */
-#include <mach/regs-dmac.h>
-#define PKUNITY_UMAL_BASE		(PKUNITY_AHB_BASE + 0x300000) /* AHB-5 */
-#include <mach/regs-umal.h>
-#define PKUNITY_USB_BASE		(PKUNITY_AHB_BASE + 0x400000) /* AHB-6 */
-#define PKUNITY_SATA_BASE		(PKUNITY_AHB_BASE + 0x500000) /* AHB-7 */
-#define PKUNITY_SMC_BASE		(PKUNITY_AHB_BASE + 0x600000) /* AHB-8 */
-/* AHB-9 is for APB bridge */
-#define PKUNITY_MME_BASE		(PKUNITY_AHB_BASE + 0x700000) /* AHB-10 */
-#define PKUNITY_UNIGFX_BASE		(PKUNITY_AHB_BASE + 0x800000) /* AHB-11 */
-#include <mach/regs-unigfx.h>
-#define PKUNITY_NAND_BASE		(PKUNITY_AHB_BASE + 0x900000) /* AHB-12 */
-#include <mach/regs-nand.h>
-#define PKUNITY_H264D_BASE		(PKUNITY_AHB_BASE + 0xA00000) /* AHB-13 */
-#define PKUNITY_H264E_BASE		(PKUNITY_AHB_BASE + 0xB00000) /* AHB-14 */
-
-/*
- * PKUNITY Peripheral Bus Addresses (APB): 0xEE000000 - 0xEFFFFFFF (128MB)
- */
-#define PKUNITY_APB_BASE		io_p2v(0xEE000000)
-
-#define PKUNITY_UART0_BASE		(PKUNITY_APB_BASE + 0x000000) /* APB-0 */
-#define PKUNITY_UART1_BASE		(PKUNITY_APB_BASE + 0x100000) /* APB-1 */
-#include <mach/regs-uart.h>
-#define PKUNITY_I2C_BASE		(PKUNITY_APB_BASE + 0x200000) /* APB-2 */
-#include <mach/regs-i2c.h>
-#define PKUNITY_SPI_BASE		(PKUNITY_APB_BASE + 0x300000) /* APB-3 */
-#include <mach/regs-spi.h>
-#define PKUNITY_AC97_BASE		(PKUNITY_APB_BASE + 0x400000) /* APB-4 */
-#include <mach/regs-ac97.h>
-#define PKUNITY_GPIO_BASE		(PKUNITY_APB_BASE + 0x500000) /* APB-5 */
-#include <mach/regs-gpio.h>
-#define PKUNITY_INTC_BASE		(PKUNITY_APB_BASE + 0x600000) /* APB-6 */
-#include <mach/regs-intc.h>
-#define PKUNITY_RTC_BASE		(PKUNITY_APB_BASE + 0x700000) /* APB-7 */
-#include <mach/regs-rtc.h>
-#define PKUNITY_OST_BASE		(PKUNITY_APB_BASE + 0x800000) /* APB-8 */
-#include <mach/regs-ost.h>
-#define PKUNITY_RESETC_BASE		(PKUNITY_APB_BASE + 0x900000) /* APB-9 */
-#include <mach/regs-resetc.h>
-#define PKUNITY_PM_BASE			(PKUNITY_APB_BASE + 0xA00000) /* APB-10 */
-#include <mach/regs-pm.h>
-#define PKUNITY_PS2_BASE		(PKUNITY_APB_BASE + 0xB00000) /* APB-11 */
-#include <mach/regs-ps2.h>
-#define PKUNITY_SDC_BASE		(PKUNITY_APB_BASE + 0xC00000) /* APB-12 */
-#include <mach/regs-sdc.h>
-
diff --git a/arch/unicore32/include/mach/bitfield.h b/arch/unicore32/include/mach/bitfield.h
deleted file mode 100644
index 766b7f01f1cd..000000000000
--- a/arch/unicore32/include/mach/bitfield.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/mach/bitfield.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __MACH_PUV3_BITFIELD_H__
-#define __MACH_PUV3_BITFIELD_H__
-
-#ifndef __ASSEMBLY__
-#define UData(Data)	((unsigned long) (Data))
-#else
-#define UData(Data)	(Data)
-#endif
-
-#define FIELD(val, vmask, vshift)	(((val) & ((UData(1) << (vmask)) - 1)) << (vshift))
-#define FMASK(vmask, vshift)		(((UData(1) << (vmask)) - 1) << (vshift))
-
-#endif /* __MACH_PUV3_BITFIELD_H__ */
diff --git a/arch/unicore32/include/mach/dma.h b/arch/unicore32/include/mach/dma.h
deleted file mode 100644
index 271001cd13c4..000000000000
--- a/arch/unicore32/include/mach/dma.h
+++ /dev/null
@@ -1,45 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/mach/dma.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __MACH_PUV3_DMA_H__
-#define __MACH_PUV3_DMA_H__
-
-/*
- * The PKUnity has six internal DMA channels.
- */
-#define MAX_DMA_CHANNELS	6
-
-typedef enum {
-	DMA_PRIO_HIGH = 0,
-	DMA_PRIO_MEDIUM = 1,
-	DMA_PRIO_LOW = 2
-} puv3_dma_prio;
-
-/*
- * DMA registration
- */
-
-extern int puv3_request_dma(char *name,
-			 puv3_dma_prio prio,
-			 void (*irq_handler)(int, void *),
-			 void (*err_handler)(int, void *),
-			 void *data);
-
-extern void puv3_free_dma(int dma_ch);
-
-static inline void puv3_stop_dma(int ch)
-{
-	writel(readl(DMAC_CONFIG(ch)) & ~DMAC_CONFIG_EN, DMAC_CONFIG(ch));
-}
-
-static inline void puv3_resume_dma(int ch)
-{
-	writel(readl(DMAC_CONFIG(ch)) | DMAC_CONFIG_EN, DMAC_CONFIG(ch));
-}
-
-#endif /* __MACH_PUV3_DMA_H__ */
diff --git a/arch/unicore32/include/mach/hardware.h b/arch/unicore32/include/mach/hardware.h
deleted file mode 100644
index 2d7571cbd1d0..000000000000
--- a/arch/unicore32/include/mach/hardware.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/mach/hardware.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * This file contains the hardware definitions for PKUnity architecture
- */
-
-#ifndef __MACH_PUV3_HARDWARE_H__
-#define __MACH_PUV3_HARDWARE_H__
-
-#include <mach/PKUnity.h>
-
-#ifndef __ASSEMBLY__
-#define io_p2v(x)	(void __iomem *)((x) - PKUNITY_MMIO_BASE)
-#define io_v2p(x)	(phys_addr_t)((x) + PKUNITY_MMIO_BASE)
-#else
-#define io_p2v(x)	((x) - PKUNITY_MMIO_BASE)
-#define io_v2p(x)	((x) + PKUNITY_MMIO_BASE)
-#endif
-
-#define PCIBIOS_MIN_IO			0x4000 /* should lower than 64KB */
-#define PCIBIOS_MIN_MEM			io_v2p(PKUNITY_PCIMEM_BASE)
-
-#define pcibios_assign_all_busses()	1
-
-#endif  /* __MACH_PUV3_HARDWARE_H__ */
diff --git a/arch/unicore32/include/mach/map.h b/arch/unicore32/include/mach/map.h
deleted file mode 100644
index 7a83eeeb1287..000000000000
--- a/arch/unicore32/include/mach/map.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/mach/map.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  Page table mapping constructs and function prototypes
- */
-#define MT_DEVICE		0
-#define MT_DEVICE_CACHED	2
-#define MT_KUSER		7
-#define MT_HIGH_VECTORS		8
-#define MT_MEMORY		9
-#define MT_ROM			10
-
diff --git a/arch/unicore32/include/mach/memory.h b/arch/unicore32/include/mach/memory.h
deleted file mode 100644
index b4e6035cb9a3..000000000000
--- a/arch/unicore32/include/mach/memory.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/mach/memory.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __MACH_PUV3_MEMORY_H__
-#define __MACH_PUV3_MEMORY_H__
-
-#include <mach/hardware.h>
-
-/* Physical DRAM offset. */
-#define PHYS_OFFSET	UL(0x00000000)
-/* The base address of exception vectors. */
-#define VECTORS_BASE	UL(0xffff0000)
-/* The base address of kuser area. */
-#define KUSER_BASE	UL(0x80000000)
-
-#ifdef __ASSEMBLY__
-/* The byte offset of the kernel image in RAM from the start of RAM. */
-#define KERNEL_IMAGE_START	0x00408000
-#endif
-
-#if !defined(__ASSEMBLY__) && defined(CONFIG_PCI)
-
-void puv3_pci_adjust_zones(unsigned long *max_zone_pfn);
-
-#define arch_adjust_zones(max_zone_pfn) \
-	puv3_pci_adjust_zones(max_zone_pfn)
-
-#endif
-
-/*
- * PCI controller in PKUnity-3 masks highest 5-bit for upstream channel,
- * so we must limit the DMA allocation within 128M physical memory for
- * supporting PCI devices.
- */
-#define PCI_DMA_THRESHOLD	(PHYS_OFFSET + SZ_128M - 1)
-
-#define is_pcibus_device(dev)	(dev &&			\
-				(strncmp(dev->bus->name, "pci", 3) == 0))
-
-#define __virt_to_pcibus(x)     (__virt_to_phys((x) + PKUNITY_PCIAHB_BASE))
-#define __pcibus_to_virt(x)     (__phys_to_virt(x) - PKUNITY_PCIAHB_BASE)
-
-/* kuser area */
-#define KUSER_VECPAGE_BASE	(KUSER_BASE + UL(0x3fff0000))
-/* kuser_vecpage (0xbfff0000) is ro, and vectors page (0xffff0000) is rw */
-#define kuser_vecpage_to_vectors(x)	((x) - (KUSER_VECPAGE_BASE)	\
-					+ (VECTORS_BASE))
-
-#endif
diff --git a/arch/unicore32/include/mach/ocd.h b/arch/unicore32/include/mach/ocd.h
deleted file mode 100644
index 2a814929e389..000000000000
--- a/arch/unicore32/include/mach/ocd.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/mach/ocd.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __MACH_PUV3_OCD_H__
-#define __MACH_PUV3_OCD_H__
-
-#if defined(CONFIG_DEBUG_OCD)
-static inline void ocd_putc(unsigned int c)
-{
-	int status, i = 0x2000000;
-
-	do {
-		if (--i < 0)
-			return;
-
-		asm volatile ("movc %0, p1.c0, #0" : "=r" (status));
-	} while (status & 2);
-
-	asm("movc p1.c1, %0, #1" : : "r" (c));
-}
-
-#define putc(ch)	ocd_putc(ch)
-#else
-#define putc(ch)
-#endif
-
-#endif
diff --git a/arch/unicore32/include/mach/pm.h b/arch/unicore32/include/mach/pm.h
deleted file mode 100644
index cb40b8490a57..000000000000
--- a/arch/unicore32/include/mach/pm.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore/include/mach/pm.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __PUV3_PM_H__
-#define __PUV3_PM_H__
-
-#include <linux/suspend.h>
-
-struct puv3_cpu_pm_fns {
-	int	save_count;
-	void	(*save)(unsigned long *);
-	void	(*restore)(unsigned long *);
-	int	(*valid)(suspend_state_t state);
-	void	(*enter)(suspend_state_t state);
-	int	(*prepare)(void);
-	void	(*finish)(void);
-};
-
-extern struct puv3_cpu_pm_fns *puv3_cpu_pm_fns;
-
-/* sleep.S */
-extern void puv3_cpu_suspend(unsigned int);
-
-extern void puv3_cpu_resume(void);
-
-extern int puv3_pm_enter(suspend_state_t state);
-
-/* Defined in hibernate_asm.S */
-extern int restore_image(pgd_t *resume_pg_dir, struct pbe *restore_pblist);
-
-extern struct pbe *restore_pblist;
-#endif
diff --git a/arch/unicore32/include/mach/regs-ac97.h b/arch/unicore32/include/mach/regs-ac97.h
deleted file mode 100644
index 85c601898d02..000000000000
--- a/arch/unicore32/include/mach/regs-ac97.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity AC97 Registers
- */
-
-#define PKUNITY_AC97_CONR		(PKUNITY_AC97_BASE + 0x0000)
-#define PKUNITY_AC97_OCR		(PKUNITY_AC97_BASE + 0x0004)
-#define PKUNITY_AC97_ICR		(PKUNITY_AC97_BASE + 0x0008)
-#define PKUNITY_AC97_CRAC		(PKUNITY_AC97_BASE + 0x000C)
-#define PKUNITY_AC97_INTR		(PKUNITY_AC97_BASE + 0x0010)
-#define PKUNITY_AC97_INTRSTAT		(PKUNITY_AC97_BASE + 0x0014)
-#define PKUNITY_AC97_INTRCLEAR		(PKUNITY_AC97_BASE + 0x0018)
-#define PKUNITY_AC97_ENABLE		(PKUNITY_AC97_BASE + 0x001C)
-#define PKUNITY_AC97_OUT_FIFO		(PKUNITY_AC97_BASE + 0x0020)
-#define PKUNITY_AC97_IN_FIFO		(PKUNITY_AC97_BASE + 0x0030)
-
-#define AC97_CODEC_REG(v)               FIELD((v), 7, 16)
-#define AC97_CODEC_VAL(v)               FIELD((v), 16, 0)
-#define AC97_CODEC_WRITECOMPLETE        FIELD(1, 1, 2)
-
-/*
- * VAR PLAY SAMPLE RATE
- */
-#define AC97_CMD_VPSAMPLE		(FIELD(3, 2, 16) | FIELD(3, 2, 0))
-
-/*
- * FIX CAPTURE SAMPLE RATE
- */
-#define AC97_CMD_FCSAMPLE		FIELD(7, 3, 0)
-
-#define AC97_CMD_RESET			FIELD(1, 1, 0)
-#define AC97_CMD_ENABLE			FIELD(1, 1, 0)
-#define AC97_CMD_DISABLE		FIELD(0, 1, 0)
diff --git a/arch/unicore32/include/mach/regs-dmac.h b/arch/unicore32/include/mach/regs-dmac.h
deleted file mode 100644
index bbdc52d06a98..000000000000
--- a/arch/unicore32/include/mach/regs-dmac.h
+++ /dev/null
@@ -1,82 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity Direct Memory Access Controller (DMAC)
- */
-
-/*
- * Interrupt Status Reg DMAC_ISR.
- */
-#define DMAC_ISR		(PKUNITY_DMAC_BASE + 0x0020)
-/*
- * Interrupt Transfer Complete Status Reg DMAC_ITCSR.
- */
-#define DMAC_ITCSR		(PKUNITY_DMAC_BASE + 0x0050)
-/*
- * Interrupt Transfer Complete Clear Reg DMAC_ITCCR.
- */
-#define DMAC_ITCCR		(PKUNITY_DMAC_BASE + 0x0060)
-/*
- * Interrupt Error Status Reg DMAC_IESR.
- */
-#define DMAC_IESR		(PKUNITY_DMAC_BASE + 0x0080)
-/*
- * Interrupt Error Clear Reg DMAC_IECR.
- */
-#define DMAC_IECR		(PKUNITY_DMAC_BASE + 0x0090)
-/*
- * Enable Channels Reg DMAC_ENCH.
- */
-#define DMAC_ENCH		(PKUNITY_DMAC_BASE + 0x00B0)
-
-/*
- * DMA control reg. Space [byte]
- */
-#define DMASp                   0x00000100
-
-/*
- * Source Addr DMAC_SRCADDR(ch).
- */
-#define DMAC_SRCADDR(ch)	(PKUNITY_DMAC_BASE + (ch)*DMASp + 0x00)
-/*
- * Destination Addr DMAC_DESTADDR(ch).
- */
-#define DMAC_DESTADDR(ch)	(PKUNITY_DMAC_BASE + (ch)*DMASp + 0x04)
-/*
- * Control Reg DMAC_CONTROL(ch).
- */
-#define DMAC_CONTROL(ch)	(PKUNITY_DMAC_BASE + (ch)*DMASp + 0x0C)
-/*
- * Configuration Reg DMAC_CONFIG(ch).
- */
-#define DMAC_CONFIG(ch)		(PKUNITY_DMAC_BASE + (ch)*DMASp + 0x10)
-
-#define DMAC_IR_MASK            FMASK(6, 0)
-/*
- * select channel (ch)
- */
-#define DMAC_CHANNEL(ch)	FIELD(1, 1, (ch))
-
-#define DMAC_CONTROL_SIZE_BYTE(v)       (FIELD((v), 12, 14) | \
-					FIELD(0, 3, 9) | FIELD(0, 3, 6))
-#define DMAC_CONTROL_SIZE_HWORD(v)      (FIELD((v) >> 1, 12, 14) | \
-					FIELD(1, 3, 9) | FIELD(1, 3, 6))
-#define DMAC_CONTROL_SIZE_WORD(v)       (FIELD((v) >> 2, 12, 14) | \
-					FIELD(2, 3, 9) | FIELD(2, 3, 6))
-#define DMAC_CONTROL_DI                 FIELD(1, 1, 13)
-#define DMAC_CONTROL_SI                 FIELD(1, 1, 12)
-#define DMAC_CONTROL_BURST_1BYTE        (FIELD(0, 3, 3) | FIELD(0, 3, 0))
-#define DMAC_CONTROL_BURST_4BYTE        (FIELD(3, 3, 3) | FIELD(3, 3, 0))
-#define DMAC_CONTROL_BURST_8BYTE        (FIELD(5, 3, 3) | FIELD(5, 3, 0))
-#define DMAC_CONTROL_BURST_16BYTE       (FIELD(7, 3, 3) | FIELD(7, 3, 0))
-
-#define	DMAC_CONFIG_UART0_WR    (FIELD(2, 4, 11) | FIELD(1, 2, 1))
-#define	DMAC_CONFIG_UART0_RD    (FIELD(2, 4, 7)  | FIELD(2, 2, 1))
-#define	DMAC_CONFIG_UART1_WR    (FIELD(3, 4, 11) | FIELD(1, 2, 1))
-#define	DMAC_CONFIG_UART1RD     (FIELD(3, 4, 7)  | FIELD(2, 2, 1))
-#define	DMAC_CONFIG_AC97WR      (FIELD(4, 4, 11) | FIELD(1, 2, 1))
-#define	DMAC_CONFIG_AC97RD      (FIELD(4, 4, 7)  | FIELD(2, 2, 1))
-#define	DMAC_CONFIG_MMCWR       (FIELD(7, 4, 11) | FIELD(1, 2, 1))
-#define	DMAC_CONFIG_MMCRD       (FIELD(7, 4, 7)  | FIELD(2, 2, 1))
-#define DMAC_CONFIG_MASKITC     FIELD(1, 1, 4)
-#define DMAC_CONFIG_MASKIE      FIELD(1, 1, 3)
-#define DMAC_CONFIG_EN          FIELD(1, 1, 0)
diff --git a/arch/unicore32/include/mach/regs-gpio.h b/arch/unicore32/include/mach/regs-gpio.h
deleted file mode 100644
index 5fc701ee33e3..000000000000
--- a/arch/unicore32/include/mach/regs-gpio.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity General-Purpose Input/Output (GPIO) Registers
- */
-
-/*
- * Voltage Status Reg GPIO_GPLR.
- */
-#define GPIO_GPLR	(PKUNITY_GPIO_BASE + 0x0000)
-/*
- * Pin Direction Reg GPIO_GPDR.
- */
-#define GPIO_GPDR	(PKUNITY_GPIO_BASE + 0x0004)
-/*
- * Output Pin Set Reg GPIO_GPSR.
- */
-#define GPIO_GPSR	(PKUNITY_GPIO_BASE + 0x0008)
-/*
- * Output Pin Clear Reg GPIO_GPCR.
- */
-#define GPIO_GPCR	(PKUNITY_GPIO_BASE + 0x000C)
-/*
- * Raise Edge Detect Reg GPIO_GRER.
- */
-#define GPIO_GRER	(PKUNITY_GPIO_BASE + 0x0010)
-/*
- * Fall Edge Detect Reg GPIO_GFER.
- */
-#define GPIO_GFER	(PKUNITY_GPIO_BASE + 0x0014)
-/*
- * Edge Status Reg GPIO_GEDR.
- */
-#define GPIO_GEDR	(PKUNITY_GPIO_BASE + 0x0018)
-/*
- * Special Voltage Detect Reg GPIO_GPIR.
- */
-#define GPIO_GPIR	(PKUNITY_GPIO_BASE + 0x0020)
-
-#define GPIO_MIN	(0)
-#define GPIO_MAX	(27)
-
-#define GPIO_GPIO(Nb)	(0x00000001 << (Nb))	/* GPIO [0..27] */
-#define GPIO_GPIO0	GPIO_GPIO(0)	/* GPIO  [0] */
-#define GPIO_GPIO1	GPIO_GPIO(1)	/* GPIO  [1] */
-#define GPIO_GPIO2	GPIO_GPIO(2)	/* GPIO  [2] */
-#define GPIO_GPIO3	GPIO_GPIO(3)	/* GPIO  [3] */
-#define GPIO_GPIO4	GPIO_GPIO(4)	/* GPIO  [4] */
-#define GPIO_GPIO5	GPIO_GPIO(5)	/* GPIO  [5] */
-#define GPIO_GPIO6	GPIO_GPIO(6)	/* GPIO  [6] */
-#define GPIO_GPIO7	GPIO_GPIO(7)	/* GPIO  [7] */
-#define GPIO_GPIO8	GPIO_GPIO(8)	/* GPIO  [8] */
-#define GPIO_GPIO9	GPIO_GPIO(9)	/* GPIO  [9] */
-#define GPIO_GPIO10	GPIO_GPIO(10)	/* GPIO [10] */
-#define GPIO_GPIO11	GPIO_GPIO(11)	/* GPIO [11] */
-#define GPIO_GPIO12	GPIO_GPIO(12)	/* GPIO [12] */
-#define GPIO_GPIO13	GPIO_GPIO(13)	/* GPIO [13] */
-#define GPIO_GPIO14	GPIO_GPIO(14)	/* GPIO [14] */
-#define GPIO_GPIO15	GPIO_GPIO(15)	/* GPIO [15] */
-#define GPIO_GPIO16	GPIO_GPIO(16)	/* GPIO [16] */
-#define GPIO_GPIO17	GPIO_GPIO(17)	/* GPIO [17] */
-#define GPIO_GPIO18	GPIO_GPIO(18)	/* GPIO [18] */
-#define GPIO_GPIO19	GPIO_GPIO(19)	/* GPIO [19] */
-#define GPIO_GPIO20	GPIO_GPIO(20)	/* GPIO [20] */
-#define GPIO_GPIO21	GPIO_GPIO(21)	/* GPIO [21] */
-#define GPIO_GPIO22	GPIO_GPIO(22)	/* GPIO [22] */
-#define GPIO_GPIO23	GPIO_GPIO(23)	/* GPIO [23] */
-#define GPIO_GPIO24	GPIO_GPIO(24)	/* GPIO [24] */
-#define GPIO_GPIO25	GPIO_GPIO(25)	/* GPIO [25] */
-#define GPIO_GPIO26	GPIO_GPIO(26)	/* GPIO [26] */
-#define GPIO_GPIO27	GPIO_GPIO(27)	/* GPIO [27] */
-
diff --git a/arch/unicore32/include/mach/regs-i2c.h b/arch/unicore32/include/mach/regs-i2c.h
deleted file mode 100644
index b41aa7c92430..000000000000
--- a/arch/unicore32/include/mach/regs-i2c.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity Inter-integrated Circuit (I2C) Registers
- */
-
-/*
- * Control Reg I2C_CON.
- */
-#define I2C_CON		(PKUNITY_I2C_BASE + 0x0000)
-/*
- * Target Address Reg I2C_TAR.
- */
-#define I2C_TAR		(PKUNITY_I2C_BASE + 0x0004)
-/*
- * Data buffer and command Reg I2C_DATACMD.
- */
-#define I2C_DATACMD	(PKUNITY_I2C_BASE + 0x0010)
-/*
- * Enable Reg I2C_ENABLE.
- */
-#define I2C_ENABLE	(PKUNITY_I2C_BASE + 0x006C)
-/*
- * Status Reg I2C_STATUS.
- */
-#define I2C_STATUS	(PKUNITY_I2C_BASE + 0x0070)
-/*
- * Tx FIFO Length Reg I2C_TXFLR.
- */
-#define I2C_TXFLR	(PKUNITY_I2C_BASE + 0x0074)
-/*
- * Rx FIFO Length Reg I2C_RXFLR.
- */
-#define I2C_RXFLR	(PKUNITY_I2C_BASE + 0x0078)
-/*
- * Enable Status Reg I2C_ENSTATUS.
- */
-#define I2C_ENSTATUS	(PKUNITY_I2C_BASE + 0x009C)
-
-#define I2C_CON_MASTER          FIELD(1, 1, 0)
-#define I2C_CON_SPEED_STD       FIELD(1, 2, 1)
-#define I2C_CON_SPEED_FAST      FIELD(2, 2, 1)
-#define I2C_CON_RESTART         FIELD(1, 1, 5)
-#define I2C_CON_SLAVEDISABLE    FIELD(1, 1, 6)
-
-#define I2C_DATACMD_READ        FIELD(1, 1, 8)
-#define I2C_DATACMD_WRITE       FIELD(0, 1, 8)
-#define I2C_DATACMD_DAT_MASK    FMASK(8, 0)
-#define I2C_DATACMD_DAT(v)      FIELD((v), 8, 0)
-
-#define I2C_ENABLE_ENABLE       FIELD(1, 1, 0)
-#define I2C_ENABLE_DISABLE      FIELD(0, 1, 0)
-
-#define I2C_STATUS_RFF          FIELD(1, 1, 4)
-#define I2C_STATUS_RFNE         FIELD(1, 1, 3)
-#define I2C_STATUS_TFE          FIELD(1, 1, 2)
-#define I2C_STATUS_TFNF         FIELD(1, 1, 1)
-#define I2C_STATUS_ACTIVITY     FIELD(1, 1, 0)
-
-#define I2C_ENSTATUS_ENABLE	FIELD(1, 1, 0)
-
-#define I2C_TAR_THERMAL	0x4f
-#define I2C_TAR_SPD	0x50
-#define I2C_TAR_PWIC    0x55
-#define I2C_TAR_EEPROM	0x57
diff --git a/arch/unicore32/include/mach/regs-intc.h b/arch/unicore32/include/mach/regs-intc.h
deleted file mode 100644
index 4eb1b5b571bb..000000000000
--- a/arch/unicore32/include/mach/regs-intc.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUNITY Interrupt Controller (INTC) Registers
- */
-/*
- * INTC Level Reg INTC_ICLR.
- */
-#define INTC_ICLR	(PKUNITY_INTC_BASE + 0x0000)
-/*
- * INTC Mask Reg INTC_ICMR.
- */
-#define INTC_ICMR	(PKUNITY_INTC_BASE + 0x0004)
-/*
- * INTC Pending Reg INTC_ICPR.
- */
-#define INTC_ICPR	(PKUNITY_INTC_BASE + 0x0008)
-/*
- * INTC IRQ Pending Reg INTC_ICIP.
- */
-#define INTC_ICIP	(PKUNITY_INTC_BASE + 0x000C)
-/*
- * INTC REAL Pending Reg INTC_ICFP.
- */
-#define INTC_ICFP	(PKUNITY_INTC_BASE + 0x0010)
-/*
- * INTC Control Reg INTC_ICCR.
- */
-#define INTC_ICCR	(PKUNITY_INTC_BASE + 0x0014)
-
diff --git a/arch/unicore32/include/mach/regs-nand.h b/arch/unicore32/include/mach/regs-nand.h
deleted file mode 100644
index 7f29939251ef..000000000000
--- a/arch/unicore32/include/mach/regs-nand.h
+++ /dev/null
@@ -1,80 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity NAND Controller Registers
- */
-/*
- * ID Reg. 0 NAND_IDR0
- */
-#define NAND_IDR0	(PKUNITY_NAND_BASE + 0x0000)
-/*
- * ID Reg. 1 NAND_IDR1
- */
-#define NAND_IDR1	(PKUNITY_NAND_BASE + 0x0004)
-/*
- * ID Reg. 2 NAND_IDR2
- */
-#define NAND_IDR2	(PKUNITY_NAND_BASE + 0x0008)
-/*
- * ID Reg. 3 NAND_IDR3
- */
-#define NAND_IDR3	(PKUNITY_NAND_BASE + 0x000C)
-/*
- * Page Address Reg 0 NAND_PAR0
- */
-#define NAND_PAR0	(PKUNITY_NAND_BASE + 0x0010)
-/*
- * Page Address Reg 1 NAND_PAR1
- */
-#define NAND_PAR1	(PKUNITY_NAND_BASE + 0x0014)
-/*
- * Page Address Reg 2 NAND_PAR2
- */
-#define NAND_PAR2	(PKUNITY_NAND_BASE + 0x0018)
-/*
- * ECC Enable Reg NAND_ECCEN
- */
-#define NAND_ECCEN	(PKUNITY_NAND_BASE + 0x001C)
-/*
- * Buffer Reg NAND_BUF
- */
-#define NAND_BUF	(PKUNITY_NAND_BASE + 0x0020)
-/*
- * ECC Status Reg NAND_ECCSR
- */
-#define NAND_ECCSR	(PKUNITY_NAND_BASE + 0x0024)
-/*
- * Command Reg NAND_CMD
- */
-#define NAND_CMD	(PKUNITY_NAND_BASE + 0x0028)
-/*
- * DMA Configure Reg NAND_DMACR
- */
-#define NAND_DMACR	(PKUNITY_NAND_BASE + 0x002C)
-/*
- * Interrupt Reg NAND_IR
- */
-#define NAND_IR		(PKUNITY_NAND_BASE + 0x0030)
-/*
- * Interrupt Mask Reg NAND_IMR
- */
-#define NAND_IMR	(PKUNITY_NAND_BASE + 0x0034)
-/*
- * Chip Enable Reg NAND_CHIPEN
- */
-#define NAND_CHIPEN	(PKUNITY_NAND_BASE + 0x0038)
-/*
- * Address Reg NAND_ADDR
- */
-#define NAND_ADDR	(PKUNITY_NAND_BASE + 0x003C)
-
-/*
- * Command bits NAND_CMD_CMD_MASK
- */
-#define NAND_CMD_CMD_MASK		FMASK(4, 4)
-#define NAND_CMD_CMD_READPAGE		FIELD(0x0, 4, 4)
-#define NAND_CMD_CMD_ERASEBLOCK		FIELD(0x6, 4, 4)
-#define NAND_CMD_CMD_READSTATUS		FIELD(0x7, 4, 4)
-#define NAND_CMD_CMD_WRITEPAGE		FIELD(0x8, 4, 4)
-#define NAND_CMD_CMD_READID		FIELD(0x9, 4, 4)
-#define NAND_CMD_CMD_RESET		FIELD(0xf, 4, 4)
-
diff --git a/arch/unicore32/include/mach/regs-ost.h b/arch/unicore32/include/mach/regs-ost.h
deleted file mode 100644
index 6c63e7b7569e..000000000000
--- a/arch/unicore32/include/mach/regs-ost.h
+++ /dev/null
@@ -1,91 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity Operating System Timer (OST) Registers
- */
-/*
- * Match Reg 0 OST_OSMR0
- */
-#define OST_OSMR0	(PKUNITY_OST_BASE + 0x0000)
-/*
- * Match Reg 1 OST_OSMR1
- */
-#define OST_OSMR1	(PKUNITY_OST_BASE + 0x0004)
-/*
- * Match Reg 2 OST_OSMR2
- */
-#define OST_OSMR2	(PKUNITY_OST_BASE + 0x0008)
-/*
- * Match Reg 3 OST_OSMR3
- */
-#define OST_OSMR3	(PKUNITY_OST_BASE + 0x000C)
-/*
- * Counter Reg OST_OSCR
- */
-#define OST_OSCR	(PKUNITY_OST_BASE + 0x0010)
-/*
- * Status Reg OST_OSSR
- */
-#define OST_OSSR	(PKUNITY_OST_BASE + 0x0014)
-/*
- * Watchdog Enable Reg OST_OWER
- */
-#define OST_OWER	(PKUNITY_OST_BASE + 0x0018)
-/*
- * Interrupt Enable Reg OST_OIER
- */
-#define OST_OIER	(PKUNITY_OST_BASE + 0x001C)
-
-/*
- * PWM Registers: IO base address: PKUNITY_OST_BASE + 0x80
- *      PWCR: Pulse Width Control Reg
- *      DCCR: Duty Cycle Control Reg
- *      PCR: Period Control Reg
- */
-#define OST_PWM_PWCR	(0x00)
-#define OST_PWM_DCCR	(0x04)
-#define OST_PWM_PCR 	(0x08)
-
-/*
- * Match detected 0 OST_OSSR_M0
- */
-#define OST_OSSR_M0		FIELD(1, 1, 0)
-/*
- * Match detected 1 OST_OSSR_M1
- */
-#define OST_OSSR_M1		FIELD(1, 1, 1)
-/*
- * Match detected 2 OST_OSSR_M2
- */
-#define OST_OSSR_M2		FIELD(1, 1, 2)
-/*
- * Match detected 3 OST_OSSR_M3
- */
-#define OST_OSSR_M3		FIELD(1, 1, 3)
-
-/*
- * Interrupt enable 0 OST_OIER_E0
- */
-#define OST_OIER_E0		FIELD(1, 1, 0)
-/*
- * Interrupt enable 1 OST_OIER_E1
- */
-#define OST_OIER_E1		FIELD(1, 1, 1)
-/*
- * Interrupt enable 2 OST_OIER_E2
- */
-#define OST_OIER_E2		FIELD(1, 1, 2)
-/*
- * Interrupt enable 3 OST_OIER_E3
- */
-#define OST_OIER_E3		FIELD(1, 1, 3)
-
-/*
- * Watchdog Match Enable OST_OWER_WME
- */
-#define OST_OWER_WME		FIELD(1, 1, 0)
-
-/*
- * PWM Full Duty Cycle OST_PWMDCCR_FDCYCLE
- */
-#define OST_PWMDCCR_FDCYCLE	FIELD(1, 1, 10)
-
diff --git a/arch/unicore32/include/mach/regs-pci.h b/arch/unicore32/include/mach/regs-pci.h
deleted file mode 100644
index 25bb307b87c3..000000000000
--- a/arch/unicore32/include/mach/regs-pci.h
+++ /dev/null
@@ -1,95 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity AHB-PCI Bridge Registers
- */
-
-/*
- * AHB/PCI fixed physical address for pci addess configuration
- */
-/*
- * PCICFG Bridge Base Reg.
- */
-#define PCICFG_BRIBASE          (PKUNITY_PCICFG_BASE + 0x0000)
-/*
- * PCICFG Address Reg.
- */
-#define PCICFG_ADDR             (PKUNITY_PCICFG_BASE + 0x0004)
-/*
- * PCICFG Address Reg.
- */
-#define PCICFG_DATA             (PKUNITY_PCICFG_BASE + 0x0008)
-
-/*
- * PCI Bridge configuration space
- */
-#define PCIBRI_ID		(PKUNITY_PCIBRI_BASE + 0x0000)
-#define PCIBRI_CMD		(PKUNITY_PCIBRI_BASE + 0x0004)
-#define PCIBRI_CLASS		(PKUNITY_PCIBRI_BASE + 0x0008)
-#define PCIBRI_LTR		(PKUNITY_PCIBRI_BASE + 0x000C)
-#define PCIBRI_BAR0		(PKUNITY_PCIBRI_BASE + 0x0010)
-#define PCIBRI_BAR1		(PKUNITY_PCIBRI_BASE + 0x0014)
-#define PCIBRI_BAR2		(PKUNITY_PCIBRI_BASE + 0x0018)
-#define PCIBRI_BAR3		(PKUNITY_PCIBRI_BASE + 0x001C)
-#define PCIBRI_BAR4		(PKUNITY_PCIBRI_BASE + 0x0020)
-#define PCIBRI_BAR5		(PKUNITY_PCIBRI_BASE + 0x0024)
-
-#define PCIBRI_PCICTL0		(PKUNITY_PCIBRI_BASE + 0x0100)
-#define PCIBRI_PCIBAR0		(PKUNITY_PCIBRI_BASE + 0x0104)
-#define PCIBRI_PCIAMR0		(PKUNITY_PCIBRI_BASE + 0x0108)
-#define PCIBRI_PCITAR0		(PKUNITY_PCIBRI_BASE + 0x010C)
-#define PCIBRI_PCICTL1		(PKUNITY_PCIBRI_BASE + 0x0110)
-#define PCIBRI_PCIBAR1		(PKUNITY_PCIBRI_BASE + 0x0114)
-#define PCIBRI_PCIAMR1		(PKUNITY_PCIBRI_BASE + 0x0118)
-#define PCIBRI_PCITAR1		(PKUNITY_PCIBRI_BASE + 0x011C)
-#define PCIBRI_PCICTL2		(PKUNITY_PCIBRI_BASE + 0x0120)
-#define PCIBRI_PCIBAR2		(PKUNITY_PCIBRI_BASE + 0x0124)
-#define PCIBRI_PCIAMR2		(PKUNITY_PCIBRI_BASE + 0x0128)
-#define PCIBRI_PCITAR2		(PKUNITY_PCIBRI_BASE + 0x012C)
-#define PCIBRI_PCICTL3		(PKUNITY_PCIBRI_BASE + 0x0130)
-#define PCIBRI_PCIBAR3		(PKUNITY_PCIBRI_BASE + 0x0134)
-#define PCIBRI_PCIAMR3		(PKUNITY_PCIBRI_BASE + 0x0138)
-#define PCIBRI_PCITAR3		(PKUNITY_PCIBRI_BASE + 0x013C)
-#define PCIBRI_PCICTL4		(PKUNITY_PCIBRI_BASE + 0x0140)
-#define PCIBRI_PCIBAR4		(PKUNITY_PCIBRI_BASE + 0x0144)
-#define PCIBRI_PCIAMR4		(PKUNITY_PCIBRI_BASE + 0x0148)
-#define PCIBRI_PCITAR4		(PKUNITY_PCIBRI_BASE + 0x014C)
-#define PCIBRI_PCICTL5		(PKUNITY_PCIBRI_BASE + 0x0150)
-#define PCIBRI_PCIBAR5		(PKUNITY_PCIBRI_BASE + 0x0154)
-#define PCIBRI_PCIAMR5		(PKUNITY_PCIBRI_BASE + 0x0158)
-#define PCIBRI_PCITAR5		(PKUNITY_PCIBRI_BASE + 0x015C)
-
-#define PCIBRI_AHBCTL0		(PKUNITY_PCIBRI_BASE + 0x0180)
-#define PCIBRI_AHBBAR0		(PKUNITY_PCIBRI_BASE + 0x0184)
-#define PCIBRI_AHBAMR0		(PKUNITY_PCIBRI_BASE + 0x0188)
-#define PCIBRI_AHBTAR0		(PKUNITY_PCIBRI_BASE + 0x018C)
-#define PCIBRI_AHBCTL1		(PKUNITY_PCIBRI_BASE + 0x0190)
-#define PCIBRI_AHBBAR1		(PKUNITY_PCIBRI_BASE + 0x0194)
-#define PCIBRI_AHBAMR1		(PKUNITY_PCIBRI_BASE + 0x0198)
-#define PCIBRI_AHBTAR1		(PKUNITY_PCIBRI_BASE + 0x019C)
-#define PCIBRI_AHBCTL2		(PKUNITY_PCIBRI_BASE + 0x01A0)
-#define PCIBRI_AHBBAR2		(PKUNITY_PCIBRI_BASE + 0x01A4)
-#define PCIBRI_AHBAMR2		(PKUNITY_PCIBRI_BASE + 0x01A8)
-#define PCIBRI_AHBTAR2		(PKUNITY_PCIBRI_BASE + 0x01AC)
-#define PCIBRI_AHBCTL3		(PKUNITY_PCIBRI_BASE + 0x01B0)
-#define PCIBRI_AHBBAR3		(PKUNITY_PCIBRI_BASE + 0x01B4)
-#define PCIBRI_AHBAMR3		(PKUNITY_PCIBRI_BASE + 0x01B8)
-#define PCIBRI_AHBTAR3		(PKUNITY_PCIBRI_BASE + 0x01BC)
-#define PCIBRI_AHBCTL4		(PKUNITY_PCIBRI_BASE + 0x01C0)
-#define PCIBRI_AHBBAR4		(PKUNITY_PCIBRI_BASE + 0x01C4)
-#define PCIBRI_AHBAMR4		(PKUNITY_PCIBRI_BASE + 0x01C8)
-#define PCIBRI_AHBTAR4		(PKUNITY_PCIBRI_BASE + 0x01CC)
-#define PCIBRI_AHBCTL5		(PKUNITY_PCIBRI_BASE + 0x01D0)
-#define PCIBRI_AHBBAR5		(PKUNITY_PCIBRI_BASE + 0x01D4)
-#define PCIBRI_AHBAMR5		(PKUNITY_PCIBRI_BASE + 0x01D8)
-#define PCIBRI_AHBTAR5		(PKUNITY_PCIBRI_BASE + 0x01DC)
-
-#define PCIBRI_CTLx_AT          FIELD(1, 1, 2)
-#define PCIBRI_CTLx_PREF        FIELD(1, 1, 1)
-#define PCIBRI_CTLx_MRL         FIELD(1, 1, 0)
-
-#define PCIBRI_BARx_ADDR        FIELD(0xFFFFFFFC, 30, 2)
-#define PCIBRI_BARx_IO          FIELD(1, 1, 0)
-#define PCIBRI_BARx_MEM         FIELD(0, 1, 0)
-
-#define PCIBRI_CMD_IO           FIELD(1, 1, 0)
-#define PCIBRI_CMD_MEM          FIELD(1, 1, 1)
diff --git a/arch/unicore32/include/mach/regs-pm.h b/arch/unicore32/include/mach/regs-pm.h
deleted file mode 100644
index 777b1ace39b9..000000000000
--- a/arch/unicore32/include/mach/regs-pm.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUNITY Power Manager (PM) Registers
- */
-/*
- * PM Control Reg PM_PMCR
- */
-#define PM_PMCR                 (PKUNITY_PM_BASE + 0x0000)
-/*
- * PM General Conf. Reg PM_PGCR
- */
-#define PM_PGCR                 (PKUNITY_PM_BASE + 0x0004)
-/*
- * PM PLL Conf. Reg PM_PPCR
- */
-#define PM_PPCR                 (PKUNITY_PM_BASE + 0x0008)
-/*
- * PM Wakeup Enable Reg PM_PWER
- */
-#define PM_PWER                 (PKUNITY_PM_BASE + 0x000C)
-/*
- * PM GPIO Sleep Status Reg PM_PGSR
- */
-#define PM_PGSR                 (PKUNITY_PM_BASE + 0x0010)
-/*
- * PM Clock Gate Reg PM_PCGR
- */
-#define PM_PCGR                 (PKUNITY_PM_BASE + 0x0014)
-/*
- * PM SYS PLL Conf. Reg PM_PLLSYSCFG
- */
-#define PM_PLLSYSCFG            (PKUNITY_PM_BASE + 0x0018)
-/*
- * PM DDR PLL Conf. Reg PM_PLLDDRCFG
- */
-#define PM_PLLDDRCFG            (PKUNITY_PM_BASE + 0x001C)
-/*
- * PM VGA PLL Conf. Reg PM_PLLVGACFG
- */
-#define PM_PLLVGACFG            (PKUNITY_PM_BASE + 0x0020)
-/*
- * PM Div Conf. Reg PM_DIVCFG
- */
-#define PM_DIVCFG               (PKUNITY_PM_BASE + 0x0024)
-/*
- * PM SYS PLL Status Reg PM_PLLSYSSTATUS
- */
-#define PM_PLLSYSSTATUS         (PKUNITY_PM_BASE + 0x0028)
-/*
- * PM DDR PLL Status Reg PM_PLLDDRSTATUS
- */
-#define PM_PLLDDRSTATUS         (PKUNITY_PM_BASE + 0x002C)
-/*
- * PM VGA PLL Status Reg PM_PLLVGASTATUS
- */
-#define PM_PLLVGASTATUS         (PKUNITY_PM_BASE + 0x0030)
-/*
- * PM Div Status Reg PM_DIVSTATUS
- */
-#define PM_DIVSTATUS            (PKUNITY_PM_BASE + 0x0034)
-/*
- * PM Software Reset Reg PM_SWRESET
- */
-#define PM_SWRESET              (PKUNITY_PM_BASE + 0x0038)
-/*
- * PM DDR2 PAD Start Reg PM_DDR2START
- */
-#define PM_DDR2START            (PKUNITY_PM_BASE + 0x003C)
-/*
- * PM DDR2 PAD Status Reg PM_DDR2CAL0
- */
-#define PM_DDR2CAL0             (PKUNITY_PM_BASE + 0x0040)
-/*
- * PM PLL DFC Done Reg PM_PLLDFCDONE
- */
-#define PM_PLLDFCDONE           (PKUNITY_PM_BASE + 0x0044)
-
-#define PM_PMCR_SFB             FIELD(1, 1, 0)
-#define PM_PMCR_IFB             FIELD(1, 1, 1)
-#define PM_PMCR_CFBSYS          FIELD(1, 1, 2)
-#define PM_PMCR_CFBDDR          FIELD(1, 1, 3)
-#define PM_PMCR_CFBVGA          FIELD(1, 1, 4)
-#define PM_PMCR_CFBDIVBCLK      FIELD(1, 1, 5)
-
-/*
- * GPIO 8~27 wake-up enable PM_PWER_GPIOHIGH
- */
-#define PM_PWER_GPIOHIGH        FIELD(1, 1, 8)
-/*
- * RTC alarm wake-up enable PM_PWER_RTC
- */
-#define PM_PWER_RTC             FIELD(1, 1, 31)
-
-#define PM_PCGR_BCLK64DDR	FIELD(1, 1, 0)
-#define PM_PCGR_BCLK64VGA	FIELD(1, 1, 1)
-#define PM_PCGR_BCLKDDR		FIELD(1, 1, 2)
-#define PM_PCGR_BCLKPCI		FIELD(1, 1, 4)
-#define PM_PCGR_BCLKDMAC	FIELD(1, 1, 5)
-#define PM_PCGR_BCLKUMAL	FIELD(1, 1, 6)
-#define PM_PCGR_BCLKUSB		FIELD(1, 1, 7)
-#define PM_PCGR_BCLKMME		FIELD(1, 1, 10)
-#define PM_PCGR_BCLKNAND	FIELD(1, 1, 11)
-#define PM_PCGR_BCLKH264E	FIELD(1, 1, 12)
-#define PM_PCGR_BCLKVGA		FIELD(1, 1, 13)
-#define PM_PCGR_BCLKH264D	FIELD(1, 1, 14)
-#define PM_PCGR_VECLK		FIELD(1, 1, 15)
-#define PM_PCGR_HECLK		FIELD(1, 1, 16)
-#define PM_PCGR_HDCLK		FIELD(1, 1, 17)
-#define PM_PCGR_NANDCLK		FIELD(1, 1, 18)
-#define PM_PCGR_GECLK		FIELD(1, 1, 19)
-#define PM_PCGR_VGACLK          FIELD(1, 1, 20)
-#define PM_PCGR_PCICLK		FIELD(1, 1, 21)
-#define PM_PCGR_SATACLK		FIELD(1, 1, 25)
-
-/*
- * [23:20]PM_DIVCFG_VGACLK(v)
- */
-#define PM_DIVCFG_VGACLK_MASK   FMASK(4, 20)
-#define PM_DIVCFG_VGACLK(v)	FIELD((v), 4, 20)
-
-#define PM_SWRESET_USB          FIELD(1, 1, 6)
-#define PM_SWRESET_VGADIV       FIELD(1, 1, 26)
-#define PM_SWRESET_GEDIV        FIELD(1, 1, 27)
-
-#define PM_PLLDFCDONE_SYSDFC    FIELD(1, 1, 0)
-#define PM_PLLDFCDONE_DDRDFC    FIELD(1, 1, 1)
-#define PM_PLLDFCDONE_VGADFC    FIELD(1, 1, 2)
diff --git a/arch/unicore32/include/mach/regs-ps2.h b/arch/unicore32/include/mach/regs-ps2.h
deleted file mode 100644
index d539d7482462..000000000000
--- a/arch/unicore32/include/mach/regs-ps2.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity PS2 Controller Registers
- */
-/*
- * the same as I8042_DATA_REG PS2_DATA
- */
-#define PS2_DATA	(PKUNITY_PS2_BASE + 0x0060)
-/*
- * the same as I8042_COMMAND_REG PS2_COMMAND
- */
-#define PS2_COMMAND	(PKUNITY_PS2_BASE + 0x0064)
-/*
- * the same as I8042_STATUS_REG PS2_STATUS
- */
-#define PS2_STATUS	(PKUNITY_PS2_BASE + 0x0064)
-/*
- * counter reg PS2_CNT
- */
-#define PS2_CNT		(PKUNITY_PS2_BASE + 0x0068)
-
diff --git a/arch/unicore32/include/mach/regs-resetc.h b/arch/unicore32/include/mach/regs-resetc.h
deleted file mode 100644
index 5f2b9d77a9ec..000000000000
--- a/arch/unicore32/include/mach/regs-resetc.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity Reset Controller (RC) Registers
- */
-/*
- * Software Reset Register
- */
-#define RESETC_SWRR	(PKUNITY_RESETC_BASE + 0x0000)
-/*
- * Reset Status Register
- */
-#define RESETC_RSSR	(PKUNITY_RESETC_BASE + 0x0004)
-
-/*
- * Software Reset Bit
- */
-#define RESETC_SWRR_SRB		FIELD(1, 1, 0)
-
-/*
- * Hardware Reset
- */
-#define RESETC_RSSR_HWR		FIELD(1, 1, 0)
-/*
- * Software Reset
- */
-#define RESETC_RSSR_SWR		FIELD(1, 1, 1)
-/*
- * Watchdog Reset
- */
-#define RESETC_RSSR_WDR		FIELD(1, 1, 2)
-/*
- * Sleep Mode Reset
- */
-#define RESETC_RSSR_SMR		FIELD(1, 1, 3)
-
diff --git a/arch/unicore32/include/mach/regs-rtc.h b/arch/unicore32/include/mach/regs-rtc.h
deleted file mode 100644
index f2f7f47eb65e..000000000000
--- a/arch/unicore32/include/mach/regs-rtc.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity Real-Time Clock (RTC) control registers
- */
-/*
- * RTC Alarm Reg RTC_RTAR
- */
-#define RTC_RTAR	(PKUNITY_RTC_BASE + 0x0000)
-/*
- * RTC Count Reg RTC_RCNR
- */
-#define RTC_RCNR	(PKUNITY_RTC_BASE + 0x0004)
-/*
- * RTC Trim Reg RTC_RTTR
- */
-#define RTC_RTTR	(PKUNITY_RTC_BASE + 0x0008)
-/*
- * RTC Status Reg RTC_RTSR
- */
-#define RTC_RTSR	(PKUNITY_RTC_BASE + 0x0010)
-
-/*
- * ALarm detected RTC_RTSR_AL
- */
-#define RTC_RTSR_AL		FIELD(1, 1, 0)
-/*
- * 1 Hz clock detected RTC_RTSR_HZ
- */
-#define RTC_RTSR_HZ		FIELD(1, 1, 1)
-/*
- * ALarm interrupt Enable RTC_RTSR_ALE
- */
-#define RTC_RTSR_ALE		FIELD(1, 1, 2)
-/*
- * 1 Hz clock interrupt Enable RTC_RTSR_HZE
- */
-#define RTC_RTSR_HZE		FIELD(1, 1, 3)
-
diff --git a/arch/unicore32/include/mach/regs-sdc.h b/arch/unicore32/include/mach/regs-sdc.h
deleted file mode 100644
index 658bfaf4cb3c..000000000000
--- a/arch/unicore32/include/mach/regs-sdc.h
+++ /dev/null
@@ -1,157 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity Multi-Media Card and Security Digital Card (MMC/SD) Registers
- */
-/*
- * Clock Control Reg SDC_CCR
- */
-#define SDC_CCR		(PKUNITY_SDC_BASE + 0x0000)
-/*
- * Software Reset Reg SDC_SRR
- */
-#define SDC_SRR		(PKUNITY_SDC_BASE + 0x0004)
-/*
- * Argument Reg SDC_ARGUMENT
- */
-#define SDC_ARGUMENT	(PKUNITY_SDC_BASE + 0x0008)
-/*
- * Command Reg SDC_COMMAND
- */
-#define SDC_COMMAND	(PKUNITY_SDC_BASE + 0x000C)
-/*
- * Block Size Reg SDC_BLOCKSIZE
- */
-#define SDC_BLOCKSIZE	(PKUNITY_SDC_BASE + 0x0010)
-/*
- * Block Cound Reg SDC_BLOCKCOUNT
- */
-#define SDC_BLOCKCOUNT	(PKUNITY_SDC_BASE + 0x0014)
-/*
- * Transfer Mode Reg SDC_TMR
- */
-#define SDC_TMR		(PKUNITY_SDC_BASE + 0x0018)
-/*
- * Response Reg. 0 SDC_RES0
- */
-#define SDC_RES0	(PKUNITY_SDC_BASE + 0x001C)
-/*
- * Response Reg. 1 SDC_RES1
- */
-#define SDC_RES1	(PKUNITY_SDC_BASE + 0x0020)
-/*
- * Response Reg. 2 SDC_RES2
- */
-#define SDC_RES2	(PKUNITY_SDC_BASE + 0x0024)
-/*
- * Response Reg. 3 SDC_RES3
- */
-#define SDC_RES3	(PKUNITY_SDC_BASE + 0x0028)
-/*
- * Read Timeout Control Reg SDC_RTCR
- */
-#define SDC_RTCR	(PKUNITY_SDC_BASE + 0x002C)
-/*
- * Interrupt Status Reg SDC_ISR
- */
-#define SDC_ISR		(PKUNITY_SDC_BASE + 0x0030)
-/*
- * Interrupt Status Mask Reg SDC_ISMR
- */
-#define SDC_ISMR	(PKUNITY_SDC_BASE + 0x0034)
-/*
- * RX FIFO SDC_RXFIFO
- */
-#define SDC_RXFIFO	(PKUNITY_SDC_BASE + 0x0038)
-/*
- * TX FIFO SDC_TXFIFO
- */
-#define SDC_TXFIFO	(PKUNITY_SDC_BASE + 0x003C)
-
-/*
- * SD Clock Enable SDC_CCR_CLKEN
- */
-#define SDC_CCR_CLKEN			FIELD(1, 1, 2)
-/*
- * [15:8] SDC_CCR_PDIV(v)
- */
-#define SDC_CCR_PDIV(v)			FIELD((v), 8, 8)
-
-/*
- * Software reset enable SDC_SRR_ENABLE
- */
-#define SDC_SRR_ENABLE			FIELD(0, 1, 0)
-/*
- * Software reset disable SDC_SRR_DISABLE
- */
-#define SDC_SRR_DISABLE			FIELD(1, 1, 0)
-
-/*
- * Response type SDC_COMMAND_RESTYPE_MASK
- */
-#define SDC_COMMAND_RESTYPE_MASK	FMASK(2, 0)
-/*
- * No response SDC_COMMAND_RESTYPE_NONE
- */
-#define SDC_COMMAND_RESTYPE_NONE	FIELD(0, 2, 0)
-/*
- * 136-bit long response SDC_COMMAND_RESTYPE_LONG
- */
-#define SDC_COMMAND_RESTYPE_LONG	FIELD(1, 2, 0)
-/*
- * 48-bit short response SDC_COMMAND_RESTYPE_SHORT
- */
-#define SDC_COMMAND_RESTYPE_SHORT	FIELD(2, 2, 0)
-/*
- * 48-bit short and test if busy response SDC_COMMAND_RESTYPE_SHORTBUSY
- */
-#define SDC_COMMAND_RESTYPE_SHORTBUSY	FIELD(3, 2, 0)
-/*
- * data ready SDC_COMMAND_DATAREADY
- */
-#define SDC_COMMAND_DATAREADY		FIELD(1, 1, 2)
-#define SDC_COMMAND_CMDEN		FIELD(1, 1, 3)
-/*
- * [10:5] SDC_COMMAND_CMDINDEX(v)
- */
-#define SDC_COMMAND_CMDINDEX(v)		FIELD((v), 6, 5)
-
-/*
- * [10:0] SDC_BLOCKSIZE_BSMASK(v)
- */
-#define SDC_BLOCKSIZE_BSMASK(v)		FIELD((v), 11, 0)
-/*
- * [11:0] SDC_BLOCKCOUNT_BCMASK(v)
- */
-#define SDC_BLOCKCOUNT_BCMASK(v)	FIELD((v), 12, 0)
-
-/*
- * Data Width 1bit SDC_TMR_WTH_1BIT
- */
-#define SDC_TMR_WTH_1BIT		FIELD(0, 1, 0)
-/*
- * Data Width 4bit SDC_TMR_WTH_4BIT
- */
-#define SDC_TMR_WTH_4BIT		FIELD(1, 1, 0)
-/*
- * Read SDC_TMR_DIR_READ
- */
-#define SDC_TMR_DIR_READ		FIELD(0, 1, 1)
-/*
- * Write SDC_TMR_DIR_WRITE
- */
-#define SDC_TMR_DIR_WRITE		FIELD(1, 1, 1)
-
-#define SDC_IR_MASK			FMASK(13, 0)
-#define SDC_IR_RESTIMEOUT		FIELD(1, 1, 0)
-#define SDC_IR_WRITECRC			FIELD(1, 1, 1)
-#define SDC_IR_READCRC			FIELD(1, 1, 2)
-#define SDC_IR_TXFIFOREAD		FIELD(1, 1, 3)
-#define SDC_IR_RXFIFOWRITE		FIELD(1, 1, 4)
-#define SDC_IR_READTIMEOUT		FIELD(1, 1, 5)
-#define SDC_IR_DATACOMPLETE		FIELD(1, 1, 6)
-#define SDC_IR_CMDCOMPLETE		FIELD(1, 1, 7)
-#define SDC_IR_RXFIFOFULL		FIELD(1, 1, 8)
-#define SDC_IR_RXFIFOEMPTY		FIELD(1, 1, 9)
-#define SDC_IR_TXFIFOFULL		FIELD(1, 1, 10)
-#define SDC_IR_TXFIFOEMPTY		FIELD(1, 1, 11)
-#define SDC_IR_ENDCMDWITHRES		FIELD(1, 1, 12)
diff --git a/arch/unicore32/include/mach/regs-spi.h b/arch/unicore32/include/mach/regs-spi.h
deleted file mode 100644
index 3460647a9c2a..000000000000
--- a/arch/unicore32/include/mach/regs-spi.h
+++ /dev/null
@@ -1,99 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity Serial Peripheral Interface (SPI) Registers
- */
-/*
- * Control reg. 0 SPI_CR0
- */
-#define SPI_CR0		(PKUNITY_SPI_BASE + 0x0000)
-/*
- * Control reg. 1 SPI_CR1
- */
-#define SPI_CR1		(PKUNITY_SPI_BASE + 0x0004)
-/*
- * Enable reg SPI_SSIENR
- */
-#define SPI_SSIENR	(PKUNITY_SPI_BASE + 0x0008)
-/*
- * Status reg SPI_SR
- */
-#define SPI_SR		(PKUNITY_SPI_BASE + 0x0028)
-/*
- * Interrupt Mask reg SPI_IMR
- */
-#define SPI_IMR		(PKUNITY_SPI_BASE + 0x002C)
-/*
- * Interrupt Status reg SPI_ISR
- */
-#define SPI_ISR		(PKUNITY_SPI_BASE + 0x0030)
-
-/*
- * Enable SPI Controller SPI_SSIENR_EN
- */
-#define SPI_SSIENR_EN		FIELD(1, 1, 0)
-
-/*
- * SPI Busy SPI_SR_BUSY
- */
-#define SPI_SR_BUSY		FIELD(1, 1, 0)
-/*
- * Transmit FIFO Not Full SPI_SR_TFNF
- */
-#define SPI_SR_TFNF		FIELD(1, 1, 1)
-/*
- * Transmit FIFO Empty SPI_SR_TFE
- */
-#define SPI_SR_TFE		FIELD(1, 1, 2)
-/*
- * Receive FIFO Not Empty SPI_SR_RFNE
- */
-#define SPI_SR_RFNE		FIELD(1, 1, 3)
-/*
- * Receive FIFO Full SPI_SR_RFF
- */
-#define SPI_SR_RFF		FIELD(1, 1, 4)
-
-/*
- * Trans. FIFO Empty Interrupt Status SPI_ISR_TXEIS
- */
-#define SPI_ISR_TXEIS		FIELD(1, 1, 0)
-/*
- * Trans. FIFO Overflow Interrupt Status SPI_ISR_TXOIS
- */
-#define SPI_ISR_TXOIS		FIELD(1, 1, 1)
-/*
- * Receiv. FIFO Underflow Interrupt Status SPI_ISR_RXUIS
- */
-#define SPI_ISR_RXUIS		FIELD(1, 1, 2)
-/*
- * Receiv. FIFO Overflow Interrupt Status SPI_ISR_RXOIS
- */
-#define SPI_ISR_RXOIS		FIELD(1, 1, 3)
-/*
- * Receiv. FIFO Full Interrupt Status SPI_ISR_RXFIS
- */
-#define SPI_ISR_RXFIS		FIELD(1, 1, 4)
-#define SPI_ISR_MSTIS		FIELD(1, 1, 5)
-
-/*
- * Trans. FIFO Empty Interrupt Mask SPI_IMR_TXEIM
- */
-#define SPI_IMR_TXEIM		FIELD(1, 1, 0)
-/*
- * Trans. FIFO Overflow Interrupt Mask SPI_IMR_TXOIM
- */
-#define SPI_IMR_TXOIM		FIELD(1, 1, 1)
-/*
- * Receiv. FIFO Underflow Interrupt Mask SPI_IMR_RXUIM
- */
-#define SPI_IMR_RXUIM		FIELD(1, 1, 2)
-/*
- * Receiv. FIFO Overflow Interrupt Mask SPI_IMR_RXOIM
- */
-#define SPI_IMR_RXOIM		FIELD(1, 1, 3)
-/*
- * Receiv. FIFO Full Interrupt Mask SPI_IMR_RXFIM
- */
-#define SPI_IMR_RXFIM		FIELD(1, 1, 4)
-#define SPI_IMR_MSTIM		FIELD(1, 1, 5)
-
diff --git a/arch/unicore32/include/mach/regs-uart.h b/arch/unicore32/include/mach/regs-uart.h
deleted file mode 100644
index 9fa6b1938b77..000000000000
--- a/arch/unicore32/include/mach/regs-uart.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/*
- * PKUnity Universal Asynchronous Receiver/Transmitter (UART) Registers
- */
diff --git a/arch/unicore32/include/mach/regs-umal.h b/arch/unicore32/include/mach/regs-umal.h
deleted file mode 100644
index 7023089c61c6..000000000000
--- a/arch/unicore32/include/mach/regs-umal.h
+++ /dev/null
@@ -1,230 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity Ultra Media Access Layer (UMAL) Ethernet MAC Registers
- */
-
-/* MAC module of UMAL */
-/* UMAL's MAC module includes G/MII interface, several additional PHY
- * interfaces, and MAC control sub-layer, which provides support for control
- * frames (e.g. PAUSE frames).
- */
-/*
- * TX/RX reset and control UMAL_CFG1
- */
-#define UMAL_CFG1		(PKUNITY_UMAL_BASE + 0x0000)
-/*
- * MAC interface mode control UMAL_CFG2
- */
-#define UMAL_CFG2		(PKUNITY_UMAL_BASE + 0x0004)
-/*
- * Inter Packet/Frame Gap UMAL_IPGIFG
- */
-#define UMAL_IPGIFG		(PKUNITY_UMAL_BASE + 0x0008)
-/*
- * Collision retry or backoff UMAL_HALFDUPLEX
- */
-#define UMAL_HALFDUPLEX		(PKUNITY_UMAL_BASE + 0x000c)
-/*
- * Maximum Frame Length UMAL_MAXFRAME
- */
-#define UMAL_MAXFRAME		(PKUNITY_UMAL_BASE + 0x0010)
-/*
- * Test Regsiter UMAL_TESTREG
- */
-#define UMAL_TESTREG		(PKUNITY_UMAL_BASE + 0x001c)
-/*
- * MII Management Configure UMAL_MIICFG
- */
-#define UMAL_MIICFG		(PKUNITY_UMAL_BASE + 0x0020)
-/*
- * MII Management Command UMAL_MIICMD
- */
-#define UMAL_MIICMD		(PKUNITY_UMAL_BASE + 0x0024)
-/*
- * MII Management Address UMAL_MIIADDR
- */
-#define UMAL_MIIADDR		(PKUNITY_UMAL_BASE + 0x0028)
-/*
- * MII Management Control UMAL_MIICTRL
- */
-#define UMAL_MIICTRL		(PKUNITY_UMAL_BASE + 0x002c)
-/*
- * MII Management Status UMAL_MIISTATUS
- */
-#define UMAL_MIISTATUS		(PKUNITY_UMAL_BASE + 0x0030)
-/*
- * MII Management Indicator UMAL_MIIIDCT
- */
-#define UMAL_MIIIDCT		(PKUNITY_UMAL_BASE + 0x0034)
-/*
- * Interface Control UMAL_IFCTRL
- */
-#define UMAL_IFCTRL		(PKUNITY_UMAL_BASE + 0x0038)
-/*
- * Interface Status UMAL_IFSTATUS
- */
-#define UMAL_IFSTATUS		(PKUNITY_UMAL_BASE + 0x003c)
-/*
- * MAC address (high 4 bytes) UMAL_STADDR1
- */
-#define UMAL_STADDR1		(PKUNITY_UMAL_BASE + 0x0040)
-/*
- * MAC address (low 2 bytes) UMAL_STADDR2
- */
-#define UMAL_STADDR2		(PKUNITY_UMAL_BASE + 0x0044)
-
-/* FIFO MODULE OF UMAL */
-/* UMAL's FIFO module provides data queuing for increased system level
- * throughput
- */
-#define UMAL_FIFOCFG0		(PKUNITY_UMAL_BASE + 0x0048)
-#define UMAL_FIFOCFG1		(PKUNITY_UMAL_BASE + 0x004c)
-#define UMAL_FIFOCFG2		(PKUNITY_UMAL_BASE + 0x0050)
-#define UMAL_FIFOCFG3		(PKUNITY_UMAL_BASE + 0x0054)
-#define UMAL_FIFOCFG4		(PKUNITY_UMAL_BASE + 0x0058)
-#define UMAL_FIFOCFG5		(PKUNITY_UMAL_BASE + 0x005c)
-#define UMAL_FIFORAM0		(PKUNITY_UMAL_BASE + 0x0060)
-#define UMAL_FIFORAM1		(PKUNITY_UMAL_BASE + 0x0064)
-#define UMAL_FIFORAM2		(PKUNITY_UMAL_BASE + 0x0068)
-#define UMAL_FIFORAM3		(PKUNITY_UMAL_BASE + 0x006c)
-#define UMAL_FIFORAM4		(PKUNITY_UMAL_BASE + 0x0070)
-#define UMAL_FIFORAM5		(PKUNITY_UMAL_BASE + 0x0074)
-#define UMAL_FIFORAM6		(PKUNITY_UMAL_BASE + 0x0078)
-#define UMAL_FIFORAM7		(PKUNITY_UMAL_BASE + 0x007c)
-
-/* MAHBE MODULE OF UMAL */
-/* UMAL's MAHBE module interfaces to the host system through 32-bit AHB Master
- * and Slave ports.Registers within the M-AHBE provide Control and Status
- * information concerning these transfers.
- */
-/*
- * Transmit Control UMAL_DMATxCtrl
- */
-#define UMAL_DMATxCtrl		(PKUNITY_UMAL_BASE + 0x0180)
-/*
- * Pointer to TX Descripter UMAL_DMATxDescriptor
- */
-#define UMAL_DMATxDescriptor	(PKUNITY_UMAL_BASE + 0x0184)
-/*
- * Status of Tx Packet Transfers UMAL_DMATxStatus
- */
-#define UMAL_DMATxStatus	(PKUNITY_UMAL_BASE + 0x0188)
-/*
- * Receive Control UMAL_DMARxCtrl
- */
-#define UMAL_DMARxCtrl		(PKUNITY_UMAL_BASE + 0x018c)
-/*
- * Pointer to Rx Descriptor UMAL_DMARxDescriptor
- */
-#define UMAL_DMARxDescriptor	(PKUNITY_UMAL_BASE + 0x0190)
-/*
- * Status of Rx Packet Transfers UMAL_DMARxStatus
- */
-#define UMAL_DMARxStatus	(PKUNITY_UMAL_BASE + 0x0194)
-/*
- * Interrupt Mask UMAL_DMAIntrMask
- */
-#define UMAL_DMAIntrMask	(PKUNITY_UMAL_BASE + 0x0198)
-/*
- * Interrupts, read only UMAL_DMAInterrupt
- */
-#define UMAL_DMAInterrupt	(PKUNITY_UMAL_BASE + 0x019c)
-
-/*
- * Commands for UMAL_CFG1 register
- */
-#define UMAL_CFG1_TXENABLE	FIELD(1, 1, 0)
-#define UMAL_CFG1_RXENABLE	FIELD(1, 1, 2)
-#define UMAL_CFG1_TXFLOWCTL	FIELD(1, 1, 4)
-#define UMAL_CFG1_RXFLOWCTL	FIELD(1, 1, 5)
-#define UMAL_CFG1_CONFLPBK	FIELD(1, 1, 8)
-#define UMAL_CFG1_RESET		FIELD(1, 1, 31)
-#define UMAL_CFG1_CONFFLCTL	(MAC_TX_FLOW_CTL | MAC_RX_FLOW_CTL)
-
-/*
- * Commands for UMAL_CFG2 register
- */
-#define UMAL_CFG2_FULLDUPLEX	FIELD(1, 1, 0)
-#define UMAL_CFG2_CRCENABLE	FIELD(1, 1, 1)
-#define UMAL_CFG2_PADCRC	FIELD(1, 1, 2)
-#define UMAL_CFG2_LENGTHCHECK	FIELD(1, 1, 4)
-#define UMAL_CFG2_MODEMASK	FMASK(2, 8)
-#define UMAL_CFG2_NIBBLEMODE	FIELD(1, 2, 8)
-#define UMAL_CFG2_BYTEMODE	FIELD(2, 2, 8)
-#define UMAL_CFG2_PREAMBLENMASK	FMASK(4, 12)
-#define UMAL_CFG2_DEFPREAMBLEN	FIELD(7, 4, 12)
-#define UMAL_CFG2_FD100		(UMAL_CFG2_DEFPREAMBLEN | UMAL_CFG2_NIBBLEMODE \
-				| UMAL_CFG2_LENGTHCHECK | UMAL_CFG2_PADCRC \
-				| UMAL_CFG2_CRCENABLE | UMAL_CFG2_FULLDUPLEX)
-#define UMAL_CFG2_FD1000	(UMAL_CFG2_DEFPREAMBLEN | UMAL_CFG2_BYTEMODE \
-				| UMAL_CFG2_LENGTHCHECK | UMAL_CFG2_PADCRC \
-				| UMAL_CFG2_CRCENABLE | UMAL_CFG2_FULLDUPLEX)
-#define UMAL_CFG2_HD100		(UMAL_CFG2_DEFPREAMBLEN | UMAL_CFG2_NIBBLEMODE \
-				| UMAL_CFG2_LENGTHCHECK | UMAL_CFG2_PADCRC \
-				| UMAL_CFG2_CRCENABLE)
-
-/*
- * Command for UMAL_IFCTRL register
- */
-#define UMAL_IFCTRL_RESET	FIELD(1, 1, 31)
-
-/*
- * Command for UMAL_MIICFG register
- */
-#define UMAL_MIICFG_RESET	FIELD(1, 1, 31)
-
-/*
- * Command for UMAL_MIICMD register
- */
-#define UMAL_MIICMD_READ	FIELD(1, 1, 0)
-
-/*
- * Command for UMAL_MIIIDCT register
- */
-#define UMAL_MIIIDCT_BUSY	FIELD(1, 1, 0)
-#define UMAL_MIIIDCT_NOTVALID	FIELD(1, 1, 2)
-
-/*
- * Commands for DMATxCtrl regesters
- */
-#define UMAL_DMA_Enable		FIELD(1, 1, 0)
-
-/*
- * Commands for DMARxCtrl regesters
- */
-#define UMAL_DMAIntrMask_ENABLEHALFWORD	FIELD(1, 1, 16)
-
-/*
- * Command for DMARxStatus
- */
-#define CLR_RX_BUS_ERR		FIELD(1, 1, 3)
-#define CLR_RX_OVERFLOW		FIELD(1, 1, 2)
-#define CLR_RX_PKT		FIELD(1, 1, 0)
-
-/*
- * Command for DMATxStatus
- */
-#define CLR_TX_BUS_ERR		FIELD(1, 1, 3)
-#define CLR_TX_UNDERRUN		FIELD(1, 1, 1)
-#define CLR_TX_PKT		FIELD(1, 1, 0)
-
-/*
- * Commands for DMAIntrMask and DMAInterrupt register
- */
-#define INT_RX_MASK		FIELD(0xd, 4, 4)
-#define INT_TX_MASK		FIELD(0xb, 4, 0)
-
-#define INT_RX_BUS_ERR		FIELD(1, 1, 7)
-#define INT_RX_OVERFLOW		FIELD(1, 1, 6)
-#define INT_RX_PKT		FIELD(1, 1, 4)
-#define INT_TX_BUS_ERR		FIELD(1, 1, 3)
-#define INT_TX_UNDERRUN		FIELD(1, 1, 1)
-#define INT_TX_PKT		FIELD(1, 1, 0)
-
-/*
- * MARCOS of UMAL's descriptors
- */
-#define UMAL_DESC_PACKETSIZE_EMPTY	FIELD(1, 1, 31)
-#define UMAL_DESC_PACKETSIZE_NONEMPTY	FIELD(0, 1, 31)
-#define UMAL_DESC_PACKETSIZE_SIZEMASK	FMASK(12, 0)
-
diff --git a/arch/unicore32/include/mach/regs-unigfx.h b/arch/unicore32/include/mach/regs-unigfx.h
deleted file mode 100644
index 553d1157c6b2..000000000000
--- a/arch/unicore32/include/mach/regs-unigfx.h
+++ /dev/null
@@ -1,201 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PKUnity UNIGFX Registers
- */
-
-#define UDE_BASE      (PKUNITY_UNIGFX_BASE + 0x1400)
-#define UGE_BASE      (PKUNITY_UNIGFX_BASE + 0x0000)
-
-/*
- * command reg for UNIGFX DE
- */
-/*
- * control reg UDE_CFG
- */
-#define UDE_CFG       (UDE_BASE + 0x0000)
-/*
- * framebuffer start address reg UDE_FSA
- */
-#define UDE_FSA       (UDE_BASE + 0x0004)
-/*
- * line size reg UDE_LS
- */
-#define UDE_LS        (UDE_BASE + 0x0008)
-/*
- * pitch size reg UDE_PS
- */
-#define UDE_PS        (UDE_BASE + 0x000C)
-/*
- * horizontal active time reg UDE_HAT
- */
-#define UDE_HAT       (UDE_BASE + 0x0010)
-/*
- * horizontal blank time reg UDE_HBT
- */
-#define UDE_HBT       (UDE_BASE + 0x0014)
-/*
- * horizontal sync time reg UDE_HST
- */
-#define UDE_HST       (UDE_BASE + 0x0018)
-/*
- * vertival active time reg UDE_VAT
- */
-#define UDE_VAT       (UDE_BASE + 0x001C)
-/*
- * vertival blank time reg UDE_VBT
- */
-#define UDE_VBT       (UDE_BASE + 0x0020)
-/*
- * vertival sync time reg UDE_VST
- */
-#define UDE_VST       (UDE_BASE + 0x0024)
-/*
- * cursor position UDE_CXY
- */
-#define UDE_CXY       (UDE_BASE + 0x0028)
-/*
- * cursor front color UDE_CC0
- */
-#define UDE_CC0       (UDE_BASE + 0x002C)
-/*
- * cursor background color UDE_CC1
- */
-#define UDE_CC1       (UDE_BASE + 0x0030)
-/*
- * video position UDE_VXY
- */
-#define UDE_VXY       (UDE_BASE + 0x0034)
-/*
- * video start address reg UDE_VSA
- */
-#define UDE_VSA       (UDE_BASE + 0x0040)
-/*
- * video size reg UDE_VS
- */
-#define UDE_VS        (UDE_BASE + 0x004C)
-
-/*
- * command reg for UNIGFX GE
- */
-/*
- * src xy reg UGE_SRCXY
- */
-#define UGE_SRCXY     (UGE_BASE + 0x0000)
-/*
- * dst xy reg UGE_DSTXY
- */
-#define UGE_DSTXY     (UGE_BASE + 0x0004)
-/*
- * pitch reg UGE_PITCH
- */
-#define UGE_PITCH     (UGE_BASE + 0x0008)
-/*
- * src start reg UGE_SRCSTART
- */
-#define UGE_SRCSTART  (UGE_BASE + 0x000C)
-/*
- * dst start reg UGE_DSTSTART
- */
-#define UGE_DSTSTART  (UGE_BASE + 0x0010)
-/*
- * width height reg UGE_WIDHEIGHT
- */
-#define UGE_WIDHEIGHT (UGE_BASE + 0x0014)
-/*
- * rop alpah reg UGE_ROPALPHA
- */
-#define UGE_ROPALPHA  (UGE_BASE + 0x0018)
-/*
- * front color UGE_FCOLOR
- */
-#define UGE_FCOLOR    (UGE_BASE + 0x001C)
-/*
- * background color UGE_BCOLOR
- */
-#define UGE_BCOLOR    (UGE_BASE + 0x0020)
-/*
- * src color key for high value UGE_SCH
- */
-#define UGE_SCH       (UGE_BASE + 0x0024)
-/*
- * dst color key for high value UGE_DCH
- */
-#define UGE_DCH       (UGE_BASE + 0x0028)
-/*
- * src color key for low value UGE_SCL
- */
-#define UGE_SCL       (UGE_BASE + 0x002C)
-/*
- * dst color key for low value UGE_DCL
- */
-#define UGE_DCL       (UGE_BASE + 0x0030)
-/*
- * clip 0 reg UGE_CLIP0
- */
-#define UGE_CLIP0     (UGE_BASE + 0x0034)
-/*
- * clip 1 reg UGE_CLIP1
- */
-#define UGE_CLIP1     (UGE_BASE + 0x0038)
-/*
- * command reg UGE_COMMAND
- */
-#define UGE_COMMAND   (UGE_BASE + 0x003C)
-/*
- * pattern 0 UGE_P0
- */
-#define UGE_P0        (UGE_BASE + 0x0040)
-#define UGE_P1        (UGE_BASE + 0x0044)
-#define UGE_P2        (UGE_BASE + 0x0048)
-#define UGE_P3        (UGE_BASE + 0x004C)
-#define UGE_P4        (UGE_BASE + 0x0050)
-#define UGE_P5        (UGE_BASE + 0x0054)
-#define UGE_P6        (UGE_BASE + 0x0058)
-#define UGE_P7        (UGE_BASE + 0x005C)
-#define UGE_P8        (UGE_BASE + 0x0060)
-#define UGE_P9        (UGE_BASE + 0x0064)
-#define UGE_P10       (UGE_BASE + 0x0068)
-#define UGE_P11       (UGE_BASE + 0x006C)
-#define UGE_P12       (UGE_BASE + 0x0070)
-#define UGE_P13       (UGE_BASE + 0x0074)
-#define UGE_P14       (UGE_BASE + 0x0078)
-#define UGE_P15       (UGE_BASE + 0x007C)
-#define UGE_P16       (UGE_BASE + 0x0080)
-#define UGE_P17       (UGE_BASE + 0x0084)
-#define UGE_P18       (UGE_BASE + 0x0088)
-#define UGE_P19       (UGE_BASE + 0x008C)
-#define UGE_P20       (UGE_BASE + 0x0090)
-#define UGE_P21       (UGE_BASE + 0x0094)
-#define UGE_P22       (UGE_BASE + 0x0098)
-#define UGE_P23       (UGE_BASE + 0x009C)
-#define UGE_P24       (UGE_BASE + 0x00A0)
-#define UGE_P25       (UGE_BASE + 0x00A4)
-#define UGE_P26       (UGE_BASE + 0x00A8)
-#define UGE_P27       (UGE_BASE + 0x00AC)
-#define UGE_P28       (UGE_BASE + 0x00B0)
-#define UGE_P29       (UGE_BASE + 0x00B4)
-#define UGE_P30       (UGE_BASE + 0x00B8)
-#define UGE_P31       (UGE_BASE + 0x00BC)
-
-#define UDE_CFG_DST_MASK	FMASK(2, 8)
-#define UDE_CFG_DST8            FIELD(0x0, 2, 8)
-#define UDE_CFG_DST16           FIELD(0x1, 2, 8)
-#define UDE_CFG_DST24           FIELD(0x2, 2, 8)
-#define UDE_CFG_DST32           FIELD(0x3, 2, 8)
-
-/*
- * GDEN enable UDE_CFG_GDEN_ENABLE
- */
-#define UDE_CFG_GDEN_ENABLE     FIELD(1, 1, 3)
-/*
- * VDEN enable UDE_CFG_VDEN_ENABLE
- */
-#define UDE_CFG_VDEN_ENABLE     FIELD(1, 1, 4)
-/*
- * CDEN enable UDE_CFG_CDEN_ENABLE
- */
-#define UDE_CFG_CDEN_ENABLE     FIELD(1, 1, 5)
-/*
- * TIMEUP enable UDE_CFG_TIMEUP_ENABLE
- */
-#define UDE_CFG_TIMEUP_ENABLE   FIELD(1, 1, 6)
diff --git a/arch/unicore32/include/mach/uncompress.h b/arch/unicore32/include/mach/uncompress.h
deleted file mode 100644
index 0c1a56a1913f..000000000000
--- a/arch/unicore32/include/mach/uncompress.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/include/mach/uncompress.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#ifndef __MACH_PUV3_UNCOMPRESS_H__
-#define __MACH_PUV3_UNCOMPRESS_H__
-
-#include <mach/hardware.h>
-#include <mach/ocd.h>
-
-extern char input_data[];
-extern char input_data_end[];
-
-static void arch_decomp_puts(const char *ptr)
-{
-	char c;
-
-	while ((c = *ptr++) != '\0') {
-		if (c == '\n')
-			putc('\r');
-		putc(c);
-	}
-}
-#define ARCH_HAVE_DECOMP_PUTS
-
-#endif /* __MACH_PUV3_UNCOMPRESS_H__ */
diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild
deleted file mode 100644
index e78470141932..000000000000
--- a/arch/unicore32/include/uapi/asm/Kbuild
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-generic-y += ucontext.h
diff --git a/arch/unicore32/include/uapi/asm/byteorder.h b/arch/unicore32/include/uapi/asm/byteorder.h
deleted file mode 100644
index 864fe4814cf4..000000000000
--- a/arch/unicore32/include/uapi/asm/byteorder.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * linux/arch/unicore32/include/asm/byteorder.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * UniCore ONLY support Little Endian mode, the data bus is connected such
- * that byte accesses appear as:
- *  0 = d0...d7, 1 = d8...d15, 2 = d16...d23, 3 = d24...d31
- * and word accesses (data or instruction) appear as:
- *  d0...d31
- */
-#ifndef __UNICORE_BYTEORDER_H__
-#define __UNICORE_BYTEORDER_H__
-
-#include <linux/byteorder/little_endian.h>
-
-#endif
-
diff --git a/arch/unicore32/include/uapi/asm/ptrace.h b/arch/unicore32/include/uapi/asm/ptrace.h
deleted file mode 100644
index 2820de83e37d..000000000000
--- a/arch/unicore32/include/uapi/asm/ptrace.h
+++ /dev/null
@@ -1,91 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * linux/arch/unicore32/include/asm/ptrace.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__UNICORE_PTRACE_H__
-#define _UAPI__UNICORE_PTRACE_H__
-
-#define PTRACE_GET_THREAD_AREA	22
-
-/*
- * PSR bits
- */
-#define USER_MODE	0x00000010
-#define REAL_MODE	0x00000011
-#define INTR_MODE	0x00000012
-#define PRIV_MODE	0x00000013
-#define ABRT_MODE	0x00000017
-#define EXTN_MODE	0x0000001b
-#define SUSR_MODE	0x0000001f
-#define MODE_MASK	0x0000001f
-#define PSR_R_BIT	0x00000040
-#define PSR_I_BIT	0x00000080
-#define PSR_V_BIT	0x10000000
-#define PSR_C_BIT	0x20000000
-#define PSR_Z_BIT	0x40000000
-#define PSR_S_BIT	0x80000000
-
-/*
- * Groups of PSR bits
- */
-#define PSR_f		0xff000000	/* Flags		*/
-#define PSR_c		0x000000ff	/* Control		*/
-
-#ifndef __ASSEMBLY__
-
-/*
- * This struct defines the way the registers are stored on the
- * stack during a system call.  Note that sizeof(struct pt_regs)
- * has to be a multiple of 8.
- */
-struct pt_regs {
-	unsigned long uregs[34];
-};
-
-#define UCreg_asr		uregs[32]
-#define UCreg_pc		uregs[31]
-#define UCreg_lr		uregs[30]
-#define UCreg_sp		uregs[29]
-#define UCreg_ip		uregs[28]
-#define UCreg_fp		uregs[27]
-#define UCreg_26		uregs[26]
-#define UCreg_25		uregs[25]
-#define UCreg_24		uregs[24]
-#define UCreg_23		uregs[23]
-#define UCreg_22		uregs[22]
-#define UCreg_21		uregs[21]
-#define UCreg_20		uregs[20]
-#define UCreg_19		uregs[19]
-#define UCreg_18		uregs[18]
-#define UCreg_17		uregs[17]
-#define UCreg_16		uregs[16]
-#define UCreg_15		uregs[15]
-#define UCreg_14		uregs[14]
-#define UCreg_13		uregs[13]
-#define UCreg_12		uregs[12]
-#define UCreg_11		uregs[11]
-#define UCreg_10		uregs[10]
-#define UCreg_09		uregs[9]
-#define UCreg_08		uregs[8]
-#define UCreg_07		uregs[7]
-#define UCreg_06		uregs[6]
-#define UCreg_05		uregs[5]
-#define UCreg_04		uregs[4]
-#define UCreg_03		uregs[3]
-#define UCreg_02		uregs[2]
-#define UCreg_01		uregs[1]
-#define UCreg_00		uregs[0]
-#define UCreg_ORIG_00		uregs[33]
-
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _UAPI__UNICORE_PTRACE_H__ */
diff --git a/arch/unicore32/include/uapi/asm/sigcontext.h b/arch/unicore32/include/uapi/asm/sigcontext.h
deleted file mode 100644
index 79e56f28e4b5..000000000000
--- a/arch/unicore32/include/uapi/asm/sigcontext.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * linux/arch/unicore32/include/asm/sigcontext.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __UNICORE_SIGCONTEXT_H__
-#define __UNICORE_SIGCONTEXT_H__
-
-#include <asm/ptrace.h>
-/*
- * Signal context structure - contains all info to do with the state
- * before the signal handler was invoked.  Note: only add new entries
- * to the end of the structure.
- */
-struct sigcontext {
-	unsigned long trap_no;
-	unsigned long error_code;
-	unsigned long oldmask;
-	unsigned long fault_address;
-	struct pt_regs regs;
-};
-
-#endif
diff --git a/arch/unicore32/include/uapi/asm/unistd.h b/arch/unicore32/include/uapi/asm/unistd.h
deleted file mode 100644
index 54a7378a70b1..000000000000
--- a/arch/unicore32/include/uapi/asm/unistd.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * linux/arch/unicore32/include/asm/unistd.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#define __ARCH_WANT_RENAMEAT
-#define __ARCH_WANT_SET_GET_RLIMIT
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_TIME32_SYSCALLS
-
-/* Use the standard ABI for syscalls. */
-#include <asm-generic/unistd.h>
-#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/unicore32/kernel/Makefile b/arch/unicore32/kernel/Makefile
deleted file mode 100644
index 2f79aa56735b..000000000000
--- a/arch/unicore32/kernel/Makefile
+++ /dev/null
@@ -1,31 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for the linux kernel.
-#
-
-# Object file lists.
-obj-y				:= dma.o elf.o entry.o process.o ptrace.o
-obj-y				+= setup.o signal.o sys.o stacktrace.o traps.o
-
-obj-$(CONFIG_MODULES)		+= ksyms.o module.o
-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
-
-obj-$(CONFIG_UNICORE_FPU_F64)	+= fpu-ucf64.o
-
-# obj-y for architecture PKUnity v3
-obj-$(CONFIG_ARCH_PUV3)		+= clock.o irq.o time.o
-
-obj-$(CONFIG_PUV3_GPIO)		+= gpio.o
-obj-$(CONFIG_PUV3_PM)		+= pm.o sleep.o
-obj-$(CONFIG_HIBERNATION)	+= hibernate.o hibernate_asm.o
-
-obj-$(CONFIG_PCI)		+= pci.o
-
-# obj-y for specific machines
-obj-$(CONFIG_ARCH_PUV3)		+= puv3-core.o
-obj-$(CONFIG_PUV3_NB0916)	+= puv3-nb0916.o
-
-head-y				:= head.o
-obj-$(CONFIG_DEBUG_LL)		+= debug.o
-
-extra-y				:= $(head-y) vmlinux.lds
diff --git a/arch/unicore32/kernel/asm-offsets.c b/arch/unicore32/kernel/asm-offsets.c
deleted file mode 100644
index f7d672267549..000000000000
--- a/arch/unicore32/kernel/asm-offsets.c
+++ /dev/null
@@ -1,108 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/asm-offsets.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed to extract
- * and format the required data.
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/dma-mapping.h>
-#include <linux/kbuild.h>
-#include <linux/suspend.h>
-#include <linux/thread_info.h>
-#include <asm/memory.h>
-#include <asm/suspend.h>
-
-/*
- * GCC 3.0, 3.1: general bad code generation.
- * GCC 3.2.0: incorrect function argument offset calculation.
- * GCC 3.2.x: miscompiles NEW_AUX_ENT in fs/binfmt_elf.c
- *	(http://gcc.gnu.org/PR8896) and incorrect structure
- *		initialisation in fs/jffs2/erase.c
- */
-#if (__GNUC__ < 4)
-#error Your compiler should upgrade to uc4
-#error	Known good compilers: 4.2.2
-#endif
-
-int main(void)
-{
-	DEFINE(TSK_ACTIVE_MM,	offsetof(struct task_struct, active_mm));
-	BLANK();
-	DEFINE(TI_FLAGS,	offsetof(struct thread_info, flags));
-	DEFINE(TI_PREEMPT,	offsetof(struct thread_info, preempt_count));
-	DEFINE(TI_ADDR_LIMIT,	offsetof(struct thread_info, addr_limit));
-	DEFINE(TI_TASK,		offsetof(struct thread_info, task));
-	DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
-	DEFINE(TI_CPU_SAVE,	offsetof(struct thread_info, cpu_context));
-	DEFINE(TI_USED_CP,	offsetof(struct thread_info, used_cp));
-#ifdef CONFIG_UNICORE_FPU_F64
-	DEFINE(TI_FPSTATE,	offsetof(struct thread_info, fpstate));
-#endif
-	BLANK();
-	DEFINE(S_R0,		offsetof(struct pt_regs, UCreg_00));
-	DEFINE(S_R1,		offsetof(struct pt_regs, UCreg_01));
-	DEFINE(S_R2,		offsetof(struct pt_regs, UCreg_02));
-	DEFINE(S_R3,		offsetof(struct pt_regs, UCreg_03));
-	DEFINE(S_R4,		offsetof(struct pt_regs, UCreg_04));
-	DEFINE(S_R5,		offsetof(struct pt_regs, UCreg_05));
-	DEFINE(S_R6,		offsetof(struct pt_regs, UCreg_06));
-	DEFINE(S_R7,		offsetof(struct pt_regs, UCreg_07));
-	DEFINE(S_R8,		offsetof(struct pt_regs, UCreg_08));
-	DEFINE(S_R9,		offsetof(struct pt_regs, UCreg_09));
-	DEFINE(S_R10,		offsetof(struct pt_regs, UCreg_10));
-	DEFINE(S_R11,		offsetof(struct pt_regs, UCreg_11));
-	DEFINE(S_R12,		offsetof(struct pt_regs, UCreg_12));
-	DEFINE(S_R13,		offsetof(struct pt_regs, UCreg_13));
-	DEFINE(S_R14,		offsetof(struct pt_regs, UCreg_14));
-	DEFINE(S_R15,		offsetof(struct pt_regs, UCreg_15));
-	DEFINE(S_R16,		offsetof(struct pt_regs, UCreg_16));
-	DEFINE(S_R17,		offsetof(struct pt_regs, UCreg_17));
-	DEFINE(S_R18,		offsetof(struct pt_regs, UCreg_18));
-	DEFINE(S_R19,		offsetof(struct pt_regs, UCreg_19));
-	DEFINE(S_R20,		offsetof(struct pt_regs, UCreg_20));
-	DEFINE(S_R21,		offsetof(struct pt_regs, UCreg_21));
-	DEFINE(S_R22,		offsetof(struct pt_regs, UCreg_22));
-	DEFINE(S_R23,		offsetof(struct pt_regs, UCreg_23));
-	DEFINE(S_R24,		offsetof(struct pt_regs, UCreg_24));
-	DEFINE(S_R25,		offsetof(struct pt_regs, UCreg_25));
-	DEFINE(S_R26,		offsetof(struct pt_regs, UCreg_26));
-	DEFINE(S_FP,		offsetof(struct pt_regs, UCreg_fp));
-	DEFINE(S_IP,		offsetof(struct pt_regs, UCreg_ip));
-	DEFINE(S_SP,		offsetof(struct pt_regs, UCreg_sp));
-	DEFINE(S_LR,		offsetof(struct pt_regs, UCreg_lr));
-	DEFINE(S_PC,		offsetof(struct pt_regs, UCreg_pc));
-	DEFINE(S_PSR,		offsetof(struct pt_regs, UCreg_asr));
-	DEFINE(S_OLD_R0,	offsetof(struct pt_regs, UCreg_ORIG_00));
-	DEFINE(S_FRAME_SIZE,	sizeof(struct pt_regs));
-	BLANK();
-	DEFINE(VMA_VM_MM,	offsetof(struct vm_area_struct, vm_mm));
-	DEFINE(VMA_VM_FLAGS,	offsetof(struct vm_area_struct, vm_flags));
-	BLANK();
-	DEFINE(VM_EXEC,		VM_EXEC);
-	BLANK();
-	DEFINE(PAGE_SZ,		PAGE_SIZE);
-	BLANK();
-	DEFINE(SYS_ERROR0,	0x9f0000);
-	BLANK();
-	DEFINE(PBE_ADDRESS,		offsetof(struct pbe, address));
-	DEFINE(PBE_ORIN_ADDRESS,	offsetof(struct pbe, orig_address));
-	DEFINE(PBE_NEXT,		offsetof(struct pbe, next));
-	DEFINE(SWSUSP_CPU,		offsetof(struct swsusp_arch_regs, \
-							cpu_context));
-#ifdef	CONFIG_UNICORE_FPU_F64
-	DEFINE(SWSUSP_FPSTATE,		offsetof(struct swsusp_arch_regs, \
-							fpstate));
-#endif
-	BLANK();
-	DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
-	DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
-	DEFINE(DMA_FROM_DEVICE,		DMA_FROM_DEVICE);
-	return 0;
-}
diff --git a/arch/unicore32/kernel/clock.c b/arch/unicore32/kernel/clock.c
deleted file mode 100644
index 41df6be0a3b2..000000000000
--- a/arch/unicore32/kernel/clock.c
+++ /dev/null
@@ -1,387 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/clock.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/list.h>
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/string.h>
-#include <linux/clk.h>
-#include <linux/mutex.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-
-#include <mach/hardware.h>
-
-/*
- * Very simple clock implementation
- */
-struct clk {
-	struct list_head	node;
-	unsigned long		rate;
-	const char		*name;
-};
-
-static struct clk clk_ost_clk = {
-	.name		= "OST_CLK",
-	.rate		= CLOCK_TICK_RATE,
-};
-
-static struct clk clk_mclk_clk = {
-	.name		= "MAIN_CLK",
-};
-
-static struct clk clk_bclk32_clk = {
-	.name		= "BUS32_CLK",
-};
-
-static struct clk clk_ddr_clk = {
-	.name		= "DDR_CLK",
-};
-
-static struct clk clk_vga_clk = {
-	.name		= "VGA_CLK",
-};
-
-static LIST_HEAD(clocks);
-static DEFINE_MUTEX(clocks_mutex);
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	struct clk *p, *clk = ERR_PTR(-ENOENT);
-
-	mutex_lock(&clocks_mutex);
-	list_for_each_entry(p, &clocks, node) {
-		if (strcmp(id, p->name) == 0) {
-			clk = p;
-			break;
-		}
-	}
-	mutex_unlock(&clocks_mutex);
-
-	return clk;
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_put);
-
-int clk_enable(struct clk *clk)
-{
-	return 0;
-}
-EXPORT_SYMBOL(clk_enable);
-
-void clk_disable(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_disable);
-
-unsigned long clk_get_rate(struct clk *clk)
-{
-	return clk->rate;
-}
-EXPORT_SYMBOL(clk_get_rate);
-
-struct {
-	unsigned long rate;
-	unsigned long cfg;
-	unsigned long div;
-} vga_clk_table[] = {
-	{.rate =  25175000, .cfg = 0x00002001, .div = 0x9},
-	{.rate =  31500000, .cfg = 0x00002001, .div = 0x7},
-	{.rate =  40000000, .cfg = 0x00003801, .div = 0x9},
-	{.rate =  49500000, .cfg = 0x00003801, .div = 0x7},
-	{.rate =  65000000, .cfg = 0x00002c01, .div = 0x4},
-	{.rate =  78750000, .cfg = 0x00002400, .div = 0x7},
-	{.rate = 108000000, .cfg = 0x00002c01, .div = 0x2},
-	{.rate = 106500000, .cfg = 0x00003c01, .div = 0x3},
-	{.rate =  50650000, .cfg = 0x00106400, .div = 0x9},
-	{.rate =  61500000, .cfg = 0x00106400, .div = 0xa},
-	{.rate =  85500000, .cfg = 0x00002800, .div = 0x6},
-};
-
-struct {
-	unsigned long mrate;
-	unsigned long prate;
-} mclk_clk_table[] = {
-	{.mrate = 500000000, .prate = 0x00109801},
-	{.mrate = 525000000, .prate = 0x00104C00},
-	{.mrate = 550000000, .prate = 0x00105000},
-	{.mrate = 575000000, .prate = 0x00105400},
-	{.mrate = 600000000, .prate = 0x00105800},
-	{.mrate = 625000000, .prate = 0x00105C00},
-	{.mrate = 650000000, .prate = 0x00106000},
-	{.mrate = 675000000, .prate = 0x00106400},
-	{.mrate = 700000000, .prate = 0x00106800},
-	{.mrate = 725000000, .prate = 0x00106C00},
-	{.mrate = 750000000, .prate = 0x00107000},
-	{.mrate = 775000000, .prate = 0x00107400},
-	{.mrate = 800000000, .prate = 0x00107800},
-};
-
-int clk_set_rate(struct clk *clk, unsigned long rate)
-{
-	if (clk == &clk_vga_clk) {
-		unsigned long pll_vgacfg, pll_vgadiv;
-		int ret, i;
-
-		/* lookup vga_clk_table */
-		ret = -EINVAL;
-		for (i = 0; i < ARRAY_SIZE(vga_clk_table); i++) {
-			if (rate == vga_clk_table[i].rate) {
-				pll_vgacfg = vga_clk_table[i].cfg;
-				pll_vgadiv = vga_clk_table[i].div;
-				ret = 0;
-				break;
-			}
-		}
-
-		if (ret)
-			return ret;
-
-		if (readl(PM_PLLVGACFG) == pll_vgacfg)
-			return 0;
-
-		/* set pll vga cfg reg. */
-		writel(pll_vgacfg, PM_PLLVGACFG);
-
-		writel(PM_PMCR_CFBVGA, PM_PMCR);
-		while ((readl(PM_PLLDFCDONE) & PM_PLLDFCDONE_VGADFC)
-				!= PM_PLLDFCDONE_VGADFC)
-			udelay(100); /* about 1ms */
-
-		/* set div cfg reg. */
-		writel(readl(PM_PCGR) | PM_PCGR_VGACLK, PM_PCGR);
-
-		writel((readl(PM_DIVCFG) & ~PM_DIVCFG_VGACLK_MASK)
-				| PM_DIVCFG_VGACLK(pll_vgadiv), PM_DIVCFG);
-
-		writel(readl(PM_SWRESET) | PM_SWRESET_VGADIV, PM_SWRESET);
-		while ((readl(PM_SWRESET) & PM_SWRESET_VGADIV)
-				== PM_SWRESET_VGADIV)
-			udelay(100); /* 65536 bclk32, about 320us */
-
-		writel(readl(PM_PCGR) & ~PM_PCGR_VGACLK, PM_PCGR);
-	}
-#ifdef CONFIG_CPU_FREQ
-	if (clk == &clk_mclk_clk) {
-		u32 pll_rate, divstatus = readl(PM_DIVSTATUS);
-		int ret, i;
-
-		/* lookup mclk_clk_table */
-		ret = -EINVAL;
-		for (i = 0; i < ARRAY_SIZE(mclk_clk_table); i++) {
-			if (rate == mclk_clk_table[i].mrate) {
-				pll_rate = mclk_clk_table[i].prate;
-				clk_mclk_clk.rate = mclk_clk_table[i].mrate;
-				ret = 0;
-				break;
-			}
-		}
-
-		if (ret)
-			return ret;
-
-		if (clk_mclk_clk.rate)
-			clk_bclk32_clk.rate = clk_mclk_clk.rate
-				/ (((divstatus & 0x0000f000) >> 12) + 1);
-
-		/* set pll sys cfg reg. */
-		writel(pll_rate, PM_PLLSYSCFG);
-
-		writel(PM_PMCR_CFBSYS, PM_PMCR);
-		while ((readl(PM_PLLDFCDONE) & PM_PLLDFCDONE_SYSDFC)
-				!= PM_PLLDFCDONE_SYSDFC)
-			udelay(100);
-			/* about 1ms */
-	}
-#endif
-	return 0;
-}
-EXPORT_SYMBOL(clk_set_rate);
-
-int clk_register(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_add(&clk->node, &clocks);
-	mutex_unlock(&clocks_mutex);
-	printk(KERN_DEFAULT "PKUnity PM: %s %lu.%02luM\n", clk->name,
-		(clk->rate)/1000000, (clk->rate)/10000 % 100);
-	return 0;
-}
-EXPORT_SYMBOL(clk_register);
-
-void clk_unregister(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_del(&clk->node);
-	mutex_unlock(&clocks_mutex);
-}
-EXPORT_SYMBOL(clk_unregister);
-
-struct {
-	unsigned long prate;
-	unsigned long rate;
-} pllrate_table[] = {
-	{.prate = 0x00002001, .rate = 250000000},
-	{.prate = 0x00104801, .rate = 250000000},
-	{.prate = 0x00104C01, .rate = 262500000},
-	{.prate = 0x00002401, .rate = 275000000},
-	{.prate = 0x00105001, .rate = 275000000},
-	{.prate = 0x00105401, .rate = 287500000},
-	{.prate = 0x00002801, .rate = 300000000},
-	{.prate = 0x00105801, .rate = 300000000},
-	{.prate = 0x00105C01, .rate = 312500000},
-	{.prate = 0x00002C01, .rate = 325000000},
-	{.prate = 0x00106001, .rate = 325000000},
-	{.prate = 0x00106401, .rate = 337500000},
-	{.prate = 0x00003001, .rate = 350000000},
-	{.prate = 0x00106801, .rate = 350000000},
-	{.prate = 0x00106C01, .rate = 362500000},
-	{.prate = 0x00003401, .rate = 375000000},
-	{.prate = 0x00107001, .rate = 375000000},
-	{.prate = 0x00107401, .rate = 387500000},
-	{.prate = 0x00003801, .rate = 400000000},
-	{.prate = 0x00107801, .rate = 400000000},
-	{.prate = 0x00107C01, .rate = 412500000},
-	{.prate = 0x00003C01, .rate = 425000000},
-	{.prate = 0x00108001, .rate = 425000000},
-	{.prate = 0x00108401, .rate = 437500000},
-	{.prate = 0x00004001, .rate = 450000000},
-	{.prate = 0x00108801, .rate = 450000000},
-	{.prate = 0x00108C01, .rate = 462500000},
-	{.prate = 0x00004401, .rate = 475000000},
-	{.prate = 0x00109001, .rate = 475000000},
-	{.prate = 0x00109401, .rate = 487500000},
-	{.prate = 0x00004801, .rate = 500000000},
-	{.prate = 0x00109801, .rate = 500000000},
-	{.prate = 0x00104C00, .rate = 525000000},
-	{.prate = 0x00002400, .rate = 550000000},
-	{.prate = 0x00105000, .rate = 550000000},
-	{.prate = 0x00105400, .rate = 575000000},
-	{.prate = 0x00002800, .rate = 600000000},
-	{.prate = 0x00105800, .rate = 600000000},
-	{.prate = 0x00105C00, .rate = 625000000},
-	{.prate = 0x00002C00, .rate = 650000000},
-	{.prate = 0x00106000, .rate = 650000000},
-	{.prate = 0x00106400, .rate = 675000000},
-	{.prate = 0x00003000, .rate = 700000000},
-	{.prate = 0x00106800, .rate = 700000000},
-	{.prate = 0x00106C00, .rate = 725000000},
-	{.prate = 0x00003400, .rate = 750000000},
-	{.prate = 0x00107000, .rate = 750000000},
-	{.prate = 0x00107400, .rate = 775000000},
-	{.prate = 0x00003800, .rate = 800000000},
-	{.prate = 0x00107800, .rate = 800000000},
-	{.prate = 0x00107C00, .rate = 825000000},
-	{.prate = 0x00003C00, .rate = 850000000},
-	{.prate = 0x00108000, .rate = 850000000},
-	{.prate = 0x00108400, .rate = 875000000},
-	{.prate = 0x00004000, .rate = 900000000},
-	{.prate = 0x00108800, .rate = 900000000},
-	{.prate = 0x00108C00, .rate = 925000000},
-	{.prate = 0x00004400, .rate = 950000000},
-	{.prate = 0x00109000, .rate = 950000000},
-	{.prate = 0x00109400, .rate = 975000000},
-	{.prate = 0x00004800, .rate = 1000000000},
-	{.prate = 0x00109800, .rate = 1000000000},
-};
-
-struct {
-	unsigned long prate;
-	unsigned long drate;
-} pddr_table[] = {
-	{.prate = 0x00100800, .drate = 44236800},
-	{.prate = 0x00100C00, .drate = 66355200},
-	{.prate = 0x00101000, .drate = 88473600},
-	{.prate = 0x00101400, .drate = 110592000},
-	{.prate = 0x00101800, .drate = 132710400},
-	{.prate = 0x00101C01, .drate = 154828800},
-	{.prate = 0x00102001, .drate = 176947200},
-	{.prate = 0x00102401, .drate = 199065600},
-	{.prate = 0x00102801, .drate = 221184000},
-	{.prate = 0x00102C01, .drate = 243302400},
-	{.prate = 0x00103001, .drate = 265420800},
-	{.prate = 0x00103401, .drate = 287539200},
-	{.prate = 0x00103801, .drate = 309657600},
-	{.prate = 0x00103C01, .drate = 331776000},
-	{.prate = 0x00104001, .drate = 353894400},
-};
-
-static int __init clk_init(void)
-{
-#ifdef CONFIG_PUV3_PM
-	u32 pllrate, divstatus = readl(PM_DIVSTATUS);
-	u32 pcgr_val = readl(PM_PCGR);
-	int i;
-
-	pcgr_val |= PM_PCGR_BCLKMME | PM_PCGR_BCLKH264E | PM_PCGR_BCLKH264D
-			| PM_PCGR_HECLK | PM_PCGR_HDCLK;
-	writel(pcgr_val, PM_PCGR);
-
-	pllrate = readl(PM_PLLSYSSTATUS);
-
-	/* lookup pmclk_table */
-	clk_mclk_clk.rate = 0;
-	for (i = 0; i < ARRAY_SIZE(pllrate_table); i++) {
-		if (pllrate == pllrate_table[i].prate) {
-			clk_mclk_clk.rate = pllrate_table[i].rate;
-			break;
-		}
-	}
-
-	if (clk_mclk_clk.rate)
-		clk_bclk32_clk.rate = clk_mclk_clk.rate /
-			(((divstatus & 0x0000f000) >> 12) + 1);
-
-	pllrate = readl(PM_PLLDDRSTATUS);
-
-	/* lookup pddr_table */
-	clk_ddr_clk.rate = 0;
-	for (i = 0; i < ARRAY_SIZE(pddr_table); i++) {
-		if (pllrate == pddr_table[i].prate) {
-			clk_ddr_clk.rate = pddr_table[i].drate;
-			break;
-		}
-	}
-
-	pllrate = readl(PM_PLLVGASTATUS);
-
-	/* lookup pvga_table */
-	clk_vga_clk.rate = 0;
-	for (i = 0; i < ARRAY_SIZE(pllrate_table); i++) {
-		if (pllrate == pllrate_table[i].prate) {
-			clk_vga_clk.rate = pllrate_table[i].rate;
-			break;
-		}
-	}
-
-	if (clk_vga_clk.rate)
-		clk_vga_clk.rate = clk_vga_clk.rate /
-			(((divstatus & 0x00f00000) >> 20) + 1);
-
-	clk_register(&clk_vga_clk);
-#endif
-#ifdef CONFIG_ARCH_FPGA
-	clk_ddr_clk.rate = 33000000;
-	clk_mclk_clk.rate = 33000000;
-	clk_bclk32_clk.rate = 33000000;
-#endif
-	clk_register(&clk_ddr_clk);
-	clk_register(&clk_mclk_clk);
-	clk_register(&clk_bclk32_clk);
-	clk_register(&clk_ost_clk);
-	return 0;
-}
-core_initcall(clk_init);
diff --git a/arch/unicore32/kernel/debug-macro.S b/arch/unicore32/kernel/debug-macro.S
deleted file mode 100644
index 7e2da0de4f71..000000000000
--- a/arch/unicore32/kernel/debug-macro.S
+++ /dev/null
@@ -1,86 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/kernel/debug-macro.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * Debugging macro include header
- */
-#include <generated/asm-offsets.h>
-#include <mach/hardware.h>
-
-		.macro	put_word_ocd, rd, rx=r16
-1001:		movc		\rx, p1.c0, #0
-		cand.a	\rx, #2
-		bne	1001b
-		movc		p1.c1, \rd, #1
-		.endm
-
-#ifdef CONFIG_DEBUG_OCD
-		/* debug using UniCore On-Chip-Debugger */
-		.macro	addruart, rx
-		.endm
-
-		.macro	senduart, rd, rx
-		put_word_ocd	\rd, \rx
-		.endm
-
-		.macro	busyuart, rd, rx
-		.endm
-
-		.macro	waituart, rd, rx
-		.endm
-#else
-#define UART_CLK_DEFAULT        3686400 * 20
-	/* Uartclk = MCLK/ 2, The MCLK on my board is 3686400 * 40  */
-#define BAUD_RATE_DEFAULT	115200
-	/* The baud rate of the serial port */
-
-#define UART_DIVISOR_DEFAULT	(UART_CLK_DEFAULT \
-				/ (16 * BAUD_RATE_DEFAULT) - 1)
-
-		.macro	addruart,rx
-		mrc	p0, #0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0xee000000	@ physical base address
-		movne	\rx, #0x6e000000	@ virtual address
-
-		@ We probe for the active serial port here
-		@ However, now we assume UART0 is active:	epip4d
-		@ We assume r1 and r2 can be clobbered.
-
-		movl 	r2, #UART_DIVISOR_DEFAULT
-		mov 	r1, #0x80
-		str	r1, [\rx, #UART_LCR_OFFSET]
-		and	r1, r2, #0xff00
-		mov	r1, r1, lsr #8
-		str	r1, [\rx, #UART_DLH_OFFSET]
-		and	r1, r2, #0xff
-		str	r1, [\rx, #UART_DLL_OFFSET]
-		mov 	r1, #0x7
-		str	r1, [\rx, #UART_FCR_OFFSET]
-		mov 	r1, #0x3
-		str	r1, [\rx, #UART_LCR_OFFSET]
-		mov 	r1, #0x0
-		str	r1, [\rx, #UART_IER_OFFSET]
-		.endm
-
-		.macro	senduart,rd,rx
-		str	\rd, [\rx, #UART_THR_OFFSET]
-		.endm
-
-		.macro	waituart,rd,rx
-1001:		ldr	\rd, [\rx, #UART_LSR_OFFSET]
-		tst	\rd, #UART_LSR_THRE
-		beq	1001b
-		.endm
-
-		.macro	busyuart,rd,rx
-1001:		ldr	\rd, [\rx, #UART_LSR_OFFSET]
-		tst	\rd, #UART_LSR_TEMT
-		bne	1001b
-		.endm
-#endif
-
diff --git a/arch/unicore32/kernel/debug.S b/arch/unicore32/kernel/debug.S
deleted file mode 100644
index 13bc8c8550e4..000000000000
--- a/arch/unicore32/kernel/debug.S
+++ /dev/null
@@ -1,82 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/kernel/debug.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  32-bit debugging code
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-		.text
-
-/*
- * Some debugging routines (useful if you've got MM problems and
- * printk isn't working).  For DEBUGGING ONLY!!!  Do not leave
- * references to these in a production kernel!
- */
-#include "debug-macro.S"
-
-/*
- * Useful debugging routines
- */
-ENTRY(printhex8)
-		mov	r1, #8
-		b	printhex
-ENDPROC(printhex8)
-
-ENTRY(printhex4)
-		mov	r1, #4
-		b	printhex
-ENDPROC(printhex4)
-
-ENTRY(printhex2)
-		mov	r1, #2
-printhex:	adr	r2, hexbuf
-		add	r3, r2, r1
-		mov	r1, #0
-		stb	r1, [r3]
-1:		and	r1, r0, #15
-		mov	r0, r0 >> #4
-		csub.a	r1, #10
-		beg	2f
-		add	r1, r1, #'0' - 'a' + 10
-2:		add	r1, r1, #'a' - 10
-		stb.w	r1, [r3+], #-1
-		cxor.a	r3, r2
-		bne	1b
-		mov	r0, r2
-		b	printascii
-ENDPROC(printhex2)
-
-		.ltorg
-
-ENTRY(printascii)
-		addruart r3
-		b	2f
-1:		waituart r2, r3
-		senduart r1, r3
-		busyuart r2, r3
-		cxor.a	r1, #'\n'
-		cmoveq	r1, #'\r'
-		beq	1b
-2:		cxor.a	r0, #0
-		beq	3f
-		ldb.w	r1, [r0]+, #1
-		cxor.a	r1, #0
-		bne	1b
-3:		mov	pc, lr
-ENDPROC(printascii)
-
-ENTRY(printch)
-		addruart r3
-		mov	r1, r0
-		mov	r0, #0
-		b	1b
-ENDPROC(printch)
-
-hexbuf:		.space 16
-
diff --git a/arch/unicore32/kernel/dma.c b/arch/unicore32/kernel/dma.c
deleted file mode 100644
index 7a0e2d4d6077..000000000000
--- a/arch/unicore32/kernel/dma.c
+++ /dev/null
@@ -1,179 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/dma.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/errno.h>
-#include <linux/io.h>
-
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <mach/dma.h>
-
-struct dma_channel {
-	char *name;
-	puv3_dma_prio prio;
-	void (*irq_handler)(int, void *);
-	void (*err_handler)(int, void *);
-	void *data;
-};
-
-static struct dma_channel dma_channels[MAX_DMA_CHANNELS];
-
-int puv3_request_dma(char *name, puv3_dma_prio prio,
-			 void (*irq_handler)(int, void *),
-			 void (*err_handler)(int, void *),
-			 void *data)
-{
-	unsigned long flags;
-	int i, found = 0;
-
-	/* basic sanity checks */
-	if (!name)
-		return -EINVAL;
-
-	local_irq_save(flags);
-
-	do {
-		/* try grabbing a DMA channel with the requested priority */
-		for (i = 0; i < MAX_DMA_CHANNELS; i++) {
-			if ((dma_channels[i].prio == prio) &&
-			    !dma_channels[i].name) {
-				found = 1;
-				break;
-			}
-		}
-		/* if requested prio group is full, try a hier priority */
-	} while (!found && prio--);
-
-	if (found) {
-		dma_channels[i].name = name;
-		dma_channels[i].irq_handler = irq_handler;
-		dma_channels[i].err_handler = err_handler;
-		dma_channels[i].data = data;
-	} else {
-		printk(KERN_WARNING "No more available DMA channels for %s\n",
-				name);
-		i = -ENODEV;
-	}
-
-	local_irq_restore(flags);
-	return i;
-}
-EXPORT_SYMBOL(puv3_request_dma);
-
-void puv3_free_dma(int dma_ch)
-{
-	unsigned long flags;
-
-	if (!dma_channels[dma_ch].name) {
-		printk(KERN_CRIT
-			"%s: trying to free channel %d which is already freed\n",
-			__func__, dma_ch);
-		return;
-	}
-
-	local_irq_save(flags);
-	dma_channels[dma_ch].name = NULL;
-	dma_channels[dma_ch].err_handler = NULL;
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(puv3_free_dma);
-
-static irqreturn_t dma_irq_handler(int irq, void *dev_id)
-{
-	int i, dint;
-
-	dint = readl(DMAC_ITCSR);
-	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
-		if (dint & DMAC_CHANNEL(i)) {
-			struct dma_channel *channel = &dma_channels[i];
-
-			/* Clear TC interrupt of channel i */
-			writel(DMAC_CHANNEL(i), DMAC_ITCCR);
-			writel(0, DMAC_ITCCR);
-
-			if (channel->name && channel->irq_handler) {
-				channel->irq_handler(i, channel->data);
-			} else {
-				/*
-				 * IRQ for an unregistered DMA channel:
-				 * let's clear the interrupts and disable it.
-				 */
-				printk(KERN_WARNING "spurious IRQ for"
-						" DMA channel %d\n", i);
-			}
-		}
-	}
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t dma_err_handler(int irq, void *dev_id)
-{
-	int i, dint;
-
-	dint = readl(DMAC_IESR);
-	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
-		if (dint & DMAC_CHANNEL(i)) {
-			struct dma_channel *channel = &dma_channels[i];
-
-			/* Clear Err interrupt of channel i */
-			writel(DMAC_CHANNEL(i), DMAC_IECR);
-			writel(0, DMAC_IECR);
-
-			if (channel->name && channel->err_handler) {
-				channel->err_handler(i, channel->data);
-			} else {
-				/*
-				 * IRQ for an unregistered DMA channel:
-				 * let's clear the interrupts and disable it.
-				 */
-				printk(KERN_WARNING "spurious IRQ for"
-						" DMA channel %d\n", i);
-			}
-		}
-	}
-	return IRQ_HANDLED;
-}
-
-int __init puv3_init_dma(void)
-{
-	int i, ret;
-
-	/* dma channel priorities on v8 processors:
-	 * ch 0 - 1  <--> (0) DMA_PRIO_HIGH
-	 * ch 2 - 3  <--> (1) DMA_PRIO_MEDIUM
-	 * ch 4 - 5  <--> (2) DMA_PRIO_LOW
-	 */
-	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
-		puv3_stop_dma(i);
-		dma_channels[i].name = NULL;
-		dma_channels[i].prio = min((i & 0x7) >> 1, DMA_PRIO_LOW);
-	}
-
-	ret = request_irq(IRQ_DMA, dma_irq_handler, 0, "DMA", NULL);
-	if (ret) {
-		printk(KERN_CRIT "Can't register IRQ for DMA\n");
-		return ret;
-	}
-
-	ret = request_irq(IRQ_DMAERR, dma_err_handler, 0, "DMAERR", NULL);
-	if (ret) {
-		printk(KERN_CRIT "Can't register IRQ for DMAERR\n");
-		free_irq(IRQ_DMA, "DMA");
-		return ret;
-	}
-
-	return 0;
-}
-
-postcore_initcall(puv3_init_dma);
diff --git a/arch/unicore32/kernel/early_printk.c b/arch/unicore32/kernel/early_printk.c
deleted file mode 100644
index c00b6712b8f7..000000000000
--- a/arch/unicore32/kernel/early_printk.c
+++ /dev/null
@@ -1,46 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/early_printk.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/console.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <mach/ocd.h>
-
-/* On-Chip-Debugger functions */
-
-static void early_ocd_write(struct console *con, const char *s, unsigned n)
-{
-	while (*s && n-- > 0) {
-		if (*s == '\n')
-			ocd_putc((int)'\r');
-		ocd_putc((int)*s);
-		s++;
-	}
-}
-
-static struct console early_ocd_console = {
-	.name =		"earlyocd",
-	.write =	early_ocd_write,
-	.flags =	CON_PRINTBUFFER,
-	.index =	-1,
-};
-
-static int __init setup_early_printk(char *buf)
-{
-	if (!buf || early_console)
-		return 0;
-
-	early_console = &early_ocd_console;
-	if (strstr(buf, "keep"))
-		early_console->flags &= ~CON_BOOT;
-	else
-		early_console->flags |= CON_BOOT;
-	register_console(early_console);
-	return 0;
-}
-early_param("earlyprintk", setup_early_printk);
diff --git a/arch/unicore32/kernel/elf.c b/arch/unicore32/kernel/elf.c
deleted file mode 100644
index 22adc65a03e9..000000000000
--- a/arch/unicore32/kernel/elf.c
+++ /dev/null
@@ -1,35 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/elf.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/personality.h>
-#include <linux/binfmts.h>
-#include <linux/elf.h>
-
-int elf_check_arch(const struct elf32_hdr *x)
-{
-	/* Make sure it's an UniCore executable */
-	if (x->e_machine != EM_UNICORE)
-		return 0;
-
-	/* Make sure the entry address is reasonable */
-	if (x->e_entry & 3)
-		return 0;
-
-	return 1;
-}
-EXPORT_SYMBOL(elf_check_arch);
-
-void elf_set_personality(const struct elf32_hdr *x)
-{
-	unsigned int personality = PER_LINUX;
-
-	set_personality(personality);
-}
-EXPORT_SYMBOL(elf_set_personality);
diff --git a/arch/unicore32/kernel/entry.S b/arch/unicore32/kernel/entry.S
deleted file mode 100644
index b35dc83069cb..000000000000
--- a/arch/unicore32/kernel/entry.S
+++ /dev/null
@@ -1,802 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/kernel/entry.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  Low-level vector interface routines
- */
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-#include <asm/thread_info.h>
-#include <asm/memory.h>
-#include <asm/unistd.h>
-#include <generated/asm-offsets.h>
-#include "debug-macro.S"
-
-@
-@ Most of the stack format comes from struct pt_regs, but with
-@ the addition of 8 bytes for storing syscall args 5 and 6.
-@
-#define S_OFF		8
-
-/*
- * The SWI code relies on the fact that R0 is at the bottom of the stack
- * (due to slow/fast restore user regs).
- */
-#if S_R0 != 0
-#error "Please fix"
-#endif
-
-	.macro	zero_fp
-#ifdef CONFIG_FRAME_POINTER
-	mov	fp, #0
-#endif
-	.endm
-
-	.macro	alignment_trap, rtemp
-#ifdef CONFIG_ALIGNMENT_TRAP
-	ldw	\rtemp, .LCcralign
-	ldw	\rtemp, [\rtemp]
-	movc	p0.c1, \rtemp, #0
-#endif
-	.endm
-
-	.macro	load_user_sp_lr, rd, rtemp, offset = 0
-	mov	\rtemp, asr
-	xor	\rtemp, \rtemp, #(PRIV_MODE ^ SUSR_MODE)
-	mov.a	asr, \rtemp			@ switch to the SUSR mode
-
-	ldw	sp, [\rd+], #\offset		@ load sp_user
-	ldw	lr, [\rd+], #\offset + 4	@ load lr_user
-
-	xor	\rtemp, \rtemp, #(PRIV_MODE ^ SUSR_MODE)
-	mov.a	asr, \rtemp			@ switch back to the PRIV mode
-	.endm
-
-	.macro	priv_exit, rpsr
-	mov.a	bsr, \rpsr
-	ldm.w	(r0 - r15), [sp]+
-	ldm.b	(r16 - pc), [sp]+		@ load r0 - pc, asr
-	.endm
-
-	.macro	restore_user_regs, fast = 0, offset = 0
-	ldw	r1, [sp+], #\offset + S_PSR	@ get calling asr
-	ldw	lr, [sp+], #\offset + S_PC	@ get pc
-	mov.a	bsr, r1				@ save in bsr_priv
-	.if	\fast
-	add	sp, sp, #\offset + S_R1		@ r0 is syscall return value
-	ldm.w	(r1 - r15), [sp]+		@ get calling r1 - r15
-	ldur	(r16 - lr), [sp]+		@ get calling r16 - lr
-	.else
-	ldm.w	(r0 - r15), [sp]+		@ get calling r0 - r15
-	ldur	(r16 - lr), [sp]+		@ get calling r16 - lr
-	.endif
-	nop
-	add	sp, sp, #S_FRAME_SIZE - S_R16
-	mov.a	pc, lr				@ return
-						@ and move bsr_priv into asr
-	.endm
-
-	.macro	get_thread_info, rd
-	mov	\rd, sp >> #13
-	mov	\rd, \rd << #13
-	.endm
-
-	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
-	ldw	\base, =(PKUNITY_INTC_BASE)
-	ldw	\irqstat, [\base+], #0xC	@ INTC_ICIP
-	ldw	\tmp,	  [\base+], #0x4	@ INTC_ICMR
-	and.a	\irqstat, \irqstat, \tmp
-	beq	1001f
-	cntlz	\irqnr, \irqstat
-	rsub	\irqnr, \irqnr, #31
-1001:	/* EQ will be set if no irqs pending */
-	.endm
-
-#ifdef CONFIG_DEBUG_LL
-	.macro	printreg, reg, temp
-		adr	\temp, 901f
-		stm	(r0-r3), [\temp]+
-		stw	lr, [\temp+], #0x10
-		mov	r0, \reg
-		b.l	printhex8
-		mov	r0, #':'
-		b.l	printch
-		mov	r0, pc
-		b.l	printhex8
-		adr	r0, 902f
-		b.l	printascii
-		adr	\temp, 901f
-		ldm	(r0-r3), [\temp]+
-		ldw	lr, [\temp+], #0x10
-		b	903f
-901:	.word	0, 0, 0, 0, 0	@ r0-r3, lr
-902:	.asciz	": epip4d\n"
-	.align
-903:
-	.endm
-#endif
-
-/*
- * These are the registers used in the syscall handler, and allow us to
- * have in theory up to 7 arguments to a function - r0 to r6.
- *
- * Note that tbl == why is intentional.
- *
- * We must set at least "tsk" and "why" when calling ret_with_reschedule.
- */
-scno	.req	r21		@ syscall number
-tbl	.req	r22		@ syscall table pointer
-why	.req	r22		@ Linux syscall (!= 0)
-tsk	.req	r23		@ current thread_info
-
-/*
- * Interrupt handling.  Preserves r17, r18, r19
- */
-	.macro	intr_handler
-1:	get_irqnr_and_base r0, r6, r5, lr
-	beq	2f
-	mov	r1, sp
-	@
-	@ routine called with r0 = irq number, r1 = struct pt_regs *
-	@
-	adr	lr, 1b
-	b	asm_do_IRQ
-2:
-	.endm
-
-/*
- * PRIV mode handlers
- */
-	.macro	priv_entry
-	sub	sp, sp, #(S_FRAME_SIZE - 4)
-	stm	(r1 - r15), [sp]+
-	add	r5, sp, #S_R15
-	stm	(r16 - r28), [r5]+
-
-	ldm	(r1 - r3), [r0]+
-	add	r5, sp, #S_SP - 4	@ here for interlock avoidance
-	mov	r4, #-1			@  ""  ""      ""       ""
-	add	r0, sp, #(S_FRAME_SIZE - 4)
-	stw.w	r1, [sp+], #-4		@ save the "real" r0 copied
-					@ from the exception stack
-
-	mov	r1, lr
-
-	@
-	@ We are now ready to fill in the remaining blanks on the stack:
-	@
-	@  r0 - sp_priv
-	@  r1 - lr_priv
-	@  r2 - lr_<exception>, already fixed up for correct return/restart
-	@  r3 - bsr_<exception>
-	@  r4 - orig_r0 (see pt_regs definition in ptrace.h)
-	@
-	stm	(r0 - r4), [r5]+
-	.endm
-
-/*
- * User mode handlers
- *
- */
-	.macro	user_entry
-	sub	sp, sp, #S_FRAME_SIZE
-	stm	(r1 - r15), [sp+]
-	add	r4, sp, #S_R16
-	stm	(r16 - r28), [r4]+
-
-	ldm	(r1 - r3), [r0]+
-	add	r0, sp, #S_PC		@ here for interlock avoidance
-	mov	r4, #-1			@  ""  ""     ""        ""
-
-	stw	r1, [sp]		@ save the "real" r0 copied
-					@ from the exception stack
-
-	@
-	@ We are now ready to fill in the remaining blanks on the stack:
-	@
-	@  r2 - lr_<exception>, already fixed up for correct return/restart
-	@  r3 - bsr_<exception>
-	@  r4 - orig_r0 (see pt_regs definition in ptrace.h)
-	@
-	@ Also, separately save sp_user and lr_user
-	@
-	stm	(r2 - r4), [r0]+
-	stur	(sp, lr), [r0-]
-
-	@
-	@ Enable the alignment trap while in kernel mode
-	@
-	alignment_trap r0
-
-	@
-	@ Clear FP to mark the first stack frame
-	@
-	zero_fp
-	.endm
-
-	.text
-
-@
-@ __invalid - generic code for failed exception
-@			(re-entrant version of handlers)
-@
-__invalid:
-	sub	sp, sp, #S_FRAME_SIZE
-	stm	(r1 - r15), [sp+]
-	add	r1, sp, #S_R16
-	stm	(r16 - r28, sp, lr), [r1]+
-
-	zero_fp
-
-	ldm	(r4 - r6), [r0]+
-	add	r0, sp, #S_PC		@ here for interlock avoidance
-	mov	r7, #-1			@  ""   ""    ""        ""
-	stw	r4, [sp]		@ save preserved r0
-	stm	(r5 - r7), [r0]+	@ lr_<exception>,
-					@ asr_<exception>, "old_r0"
-
-	mov	r0, sp
-	mov	r1, asr
-	b	bad_mode
-ENDPROC(__invalid)
-
-	.align	5
-__dabt_priv:
-	priv_entry
-
-	@
-	@ get ready to re-enable interrupts if appropriate
-	@
-	mov	r17, asr
-	cand.a	r3, #PSR_I_BIT
-	bne	1f
-	andn	r17, r17, #PSR_I_BIT
-1:
-
-	@
-	@ Call the processor-specific abort handler:
-	@
-	@  r2 - aborted context pc
-	@  r3 - aborted context asr
-	@
-	@ The abort handler must return the aborted address in r0, and
-	@ the fault status register in r1.
-	@
-	movc	r1, p0.c3, #0		@ get FSR
-	movc	r0, p0.c4, #0		@ get FAR
-
-	@
-	@ set desired INTR state, then call main handler
-	@
-	mov.a	asr, r17
-	mov	r2, sp
-	b.l	do_DataAbort
-
-	@
-	@ INTRs off again before pulling preserved data off the stack
-	@
-	disable_irq r0
-
-	@
-	@ restore BSR and restart the instruction
-	@
-	ldw	r2, [sp+], #S_PSR
-	priv_exit r2				@ return from exception
-ENDPROC(__dabt_priv)
-
-	.align	5
-__intr_priv:
-	priv_entry
-
-	intr_handler
-
-	mov	r0, #0				@ epip4d
-	movc	p0.c5, r0, #14
-	nop; nop; nop; nop; nop; nop; nop; nop
-
-	ldw	r4, [sp+], #S_PSR		@ irqs are already disabled
-
-	priv_exit r4				@ return from exception
-ENDPROC(__intr_priv)
-
-	.ltorg
-
-	.align	5
-__extn_priv:
-	priv_entry
-
-	mov	r0, sp				@ struct pt_regs *regs
-	mov	r1, asr
-	b	bad_mode			@ not supported
-ENDPROC(__extn_priv)
-
-	.align	5
-__pabt_priv:
-	priv_entry
-
-	@
-	@ re-enable interrupts if appropriate
-	@
-	mov	r17, asr
-	cand.a	r3, #PSR_I_BIT
-	bne	1f
-	andn	r17, r17, #PSR_I_BIT
-1:
-
-	@
-	@ set args, then call main handler
-	@
-	@  r0 - address of faulting instruction
-	@  r1 - pointer to registers on stack
-	@
-	mov	r0, r2			@ pass address of aborted instruction
-	mov	r1, #5
-	mov.a	asr, r17
-	mov	r2, sp			@ regs
-	b.l	do_PrefetchAbort	@ call abort handler
-
-	@
-	@ INTRs off again before pulling preserved data off the stack
-	@
-	disable_irq r0
-
-	@
-	@ restore BSR and restart the instruction
-	@
-	ldw	r2, [sp+], #S_PSR
-	priv_exit r2			@ return from exception
-ENDPROC(__pabt_priv)
-
-	.align	5
-.LCcralign:
-	.word	cr_alignment
-
-	.align	5
-__dabt_user:
-	user_entry
-
-#ifdef CONFIG_UNICORE_FPU_F64
-	cff	ip, s31
-	cand.a	ip, #0x08000000		@ FPU execption traps?
-	beq	209f
-
-	ldw	ip, [sp+], #S_PC
-	add	ip, ip, #4
-	stw	ip, [sp+], #S_PC
-	@
-	@ fall through to the emulation code, which returns using r19 if
-	@ it has emulated the instruction, or the more conventional lr
-	@ if we are to treat this as a real extended instruction
-	@
-	@  r0 - instruction
-	@
-1:	ldw.u	r0, [r2]
-	adr	r19, ret_from_exception
-	adr	lr, 209f
-	@
-	@ fallthrough to call do_uc_f64
-	@
-/*
- * Check whether the instruction is a co-processor instruction.
- * If yes, we need to call the relevant co-processor handler.
- *
- * Note that we don't do a full check here for the co-processor
- * instructions; all instructions with bit 27 set are well
- * defined.  The only instructions that should fault are the
- * co-processor instructions.
- *
- * Emulators may wish to make use of the following registers:
- *  r0  = instruction opcode.
- *  r2  = PC
- *  r19 = normal "successful" return address
- *  r20 = this threads thread_info structure.
- *  lr  = unrecognised instruction return address
- */
-	get_thread_info r20			@ get current thread
-	and	r8, r0, #0x00003c00		@ mask out CP number
-	mov	r7, #1
-	stb	r7, [r20+], #TI_USED_CP + 2	@ set appropriate used_cp[]
-
-	@ F64 hardware support entry point.
-	@  r0  = faulted instruction
-	@  r19 = return address
-	@  r20 = fp_state
-	enable_irq r4
-	add	r20, r20, #TI_FPSTATE	@ r20 = workspace
-	cff	r1, s31			@ get fpu FPSCR
-	andn    r2, r1, #0x08000000
-	ctf     r2, s31			@ clear 27 bit
-	mov	r2, sp			@ nothing stacked - regdump is at TOS
-	mov	lr, r19			@ setup for a return to the user code
-
-	@ Now call the C code to package up the bounce to the support code
-	@   r0 holds the trigger instruction
-	@   r1 holds the FPSCR value
-	@   r2 pointer to register dump
-	b	ucf64_exchandler
-209:
-#endif
-	@
-	@ Call the processor-specific abort handler:
-	@
-	@  r2 - aborted context pc
-	@  r3 - aborted context asr
-	@
-	@ The abort handler must return the aborted address in r0, and
-	@ the fault status register in r1.
-	@
-	movc	r1, p0.c3, #0		@ get FSR
-	movc	r0, p0.c4, #0		@ get FAR
-
-	@
-	@ INTRs on, then call the main handler
-	@
-	enable_irq r2
-	mov	r2, sp
-	adr	lr, ret_from_exception
-	b	do_DataAbort
-ENDPROC(__dabt_user)
-
-	.align	5
-__intr_user:
-	user_entry
-
-	get_thread_info tsk
-
-	intr_handler
-
-	mov	why, #0
-	b	ret_to_user
-ENDPROC(__intr_user)
-
-	.ltorg
-
-	.align	5
-__extn_user:
-	user_entry
-
-	mov	r0, sp
-	mov	r1, asr
-	b	bad_mode
-ENDPROC(__extn_user)
-
-	.align	5
-__pabt_user:
-	user_entry
-
-	mov	r0, r2			@ pass address of aborted instruction.
-	mov	r1, #5
-	enable_irq r1			@ Enable interrupts
-	mov	r2, sp			@ regs
-	b.l	do_PrefetchAbort	@ call abort handler
-	/* fall through */
-/*
- * This is the return code to user mode for abort handlers
- */
-ENTRY(ret_from_exception)
-	get_thread_info tsk
-	mov	why, #0
-	b	ret_to_user
-ENDPROC(__pabt_user)
-ENDPROC(ret_from_exception)
-
-/*
- * Register switch for UniCore V2 processors
- * r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info
- * previous and next are guaranteed not to be the same.
- */
-ENTRY(__switch_to)
-	add	ip, r1, #TI_CPU_SAVE
-	stm.w	(r4 - r15), [ip]+
-	stm.w	(r16 - r27, sp, lr), [ip]+
-
-#ifdef	CONFIG_UNICORE_FPU_F64
-	add	ip, r1, #TI_FPSTATE
-	sfm.w	(f0  - f7 ), [ip]+
-	sfm.w	(f8  - f15), [ip]+
-	sfm.w	(f16 - f23), [ip]+
-	sfm.w	(f24 - f31), [ip]+
-	cff	r4, s31
-	stw	r4, [ip]
-
-	add	ip, r2, #TI_FPSTATE
-	lfm.w	(f0  - f7 ), [ip]+
-	lfm.w	(f8  - f15), [ip]+
-	lfm.w	(f16 - f23), [ip]+
-	lfm.w	(f24 - f31), [ip]+
-	ldw	r4, [ip]
-	ctf	r4, s31
-#endif
-	add	ip, r2, #TI_CPU_SAVE
-	ldm.w	(r4 - r15), [ip]+
-	ldm	(r16 - r27, sp, pc), [ip]+	@ Load all regs saved previously
-ENDPROC(__switch_to)
-
-	.align	5
-/*
- * This is the fast syscall return path.  We do as little as
- * possible here, and this includes saving r0 back into the PRIV
- * stack.
- */
-ret_fast_syscall:
-	disable_irq r1				@ disable interrupts
-	ldw	r1, [tsk+], #TI_FLAGS
-	cand.a	r1, #_TIF_WORK_MASK
-	bne	fast_work_pending
-
-	@ fast_restore_user_regs
-	restore_user_regs fast = 1, offset = S_OFF
-
-/*
- * Ok, we need to do extra processing, enter the slow path.
- */
-fast_work_pending:
-	stw.w	r0, [sp+], #S_R0+S_OFF		@ returned r0
-work_pending:
-	cand.a	r1, #_TIF_NEED_RESCHED
-	bne	work_resched
-	mov	r0, sp				@ 'regs'
-	mov	r2, why				@ 'syscall'
-	cand.a	r1, #_TIF_SIGPENDING		@ delivering a signal?
-	cmovne	why, #0				@ prevent further restarts
-	b.l	do_notify_resume
-	b	ret_slow_syscall		@ Check work again
-
-work_resched:
-	b.l	schedule
-/*
- * "slow" syscall return path.  "why" tells us if this was a real syscall.
- */
-ENTRY(ret_to_user)
-ret_slow_syscall:
-	disable_irq r1				@ disable interrupts
-	get_thread_info tsk			@ epip4d, one path error?!
-	ldw	r1, [tsk+], #TI_FLAGS
-	cand.a	r1, #_TIF_WORK_MASK
-	bne	work_pending
-no_work_pending:
-	@ slow_restore_user_regs
-	restore_user_regs fast = 0, offset = 0
-ENDPROC(ret_to_user)
-
-/*
- * This is how we return from a fork.
- */
-ENTRY(ret_from_fork)
-	b.l	schedule_tail
-	b	ret_slow_syscall
-ENDPROC(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
-	b.l	schedule_tail
-	mov	r0, r5
-	adr	lr, ret_slow_syscall
-	mov	pc, r4
-ENDPROC(ret_from_kernel_thread)
-
-/*=============================================================================
- * SWI handler
- *-----------------------------------------------------------------------------
- */
-	.align	5
-ENTRY(vector_swi)
-	sub	sp, sp, #S_FRAME_SIZE
-	stm	(r0 - r15), [sp]+		@ Calling r0 - r15
-	add	r8, sp, #S_R16
-	stm	(r16 - r28), [r8]+		@ Calling r16 - r28
-	add	r8, sp, #S_PC
-	stur	(sp, lr), [r8-]			@ Calling sp, lr
-	mov	r8, bsr				@ called from non-REAL mode
-	stw	lr, [sp+], #S_PC		@ Save calling PC
-	stw	r8, [sp+], #S_PSR		@ Save ASR
-	stw	r0, [sp+], #S_OLD_R0		@ Save OLD_R0
-	zero_fp
-
-	/*
-	 * Get the system call number.
-	 */
-	sub	ip, lr, #4
-	ldw.u	scno, [ip]			@ get SWI instruction
-
-#ifdef CONFIG_ALIGNMENT_TRAP
-	ldw	ip, __cr_alignment
-	ldw	ip, [ip]
-	movc	p0.c1, ip, #0                   @ update control register
-#endif
-	enable_irq ip
-
-	get_thread_info tsk
-	ldw	tbl, =sys_call_table		@ load syscall table pointer
-
-	andn	scno, scno, #0xff000000		@ mask off SWI op-code
-	andn	scno, scno, #0x00ff0000		@ mask off SWI op-code
-
-	stm.w	(r4, r5), [sp-]			@ push fifth and sixth args
-	ldw	ip, [tsk+], #TI_FLAGS		@ check for syscall tracing
-	cand.a	ip, #_TIF_SYSCALL_TRACE		@ are we tracing syscalls?
-	bne	__sys_trace
-
-	csub.a	scno, #__NR_syscalls		@ check upper syscall limit
-	adr	lr, ret_fast_syscall		@ return address
-	bea	1f
-	ldw	pc, [tbl+], scno << #2		@ call sys_* routine
-1:
-	add	r1, sp, #S_OFF
-2:	mov	why, #0				@ no longer a real syscall
-	b	sys_ni_syscall			@ not private func
-
-	/*
-	 * This is the really slow path.  We're going to be doing
-	 * context switches, and waiting for our parent to respond.
-	 */
-__sys_trace:
-	mov	r2, scno
-	add	r1, sp, #S_OFF
-	mov	r0, #0				@ trace entry [IP = 0]
-	b.l	syscall_trace
-
-	adr	lr, __sys_trace_return		@ return address
-	mov	scno, r0			@ syscall number (possibly new)
-	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	csub.a	scno, #__NR_syscalls		@ check upper syscall limit
-	bea	2b
-	ldm	(r0 - r3), [r1]+		@ have to reload r0 - r3
-	ldw	pc, [tbl+], scno << #2		@ call sys_* routine
-
-__sys_trace_return:
-	stw.w	r0, [sp+], #S_R0 + S_OFF	@ save returned r0
-	mov	r2, scno
-	mov	r1, sp
-	mov	r0, #1				@ trace exit [IP = 1]
-	b.l	syscall_trace
-	b	ret_slow_syscall
-
-	.align	5
-#ifdef CONFIG_ALIGNMENT_TRAP
-	.type	__cr_alignment, #object
-__cr_alignment:
-	.word	cr_alignment
-#endif
-	.ltorg
-
-ENTRY(sys_rt_sigreturn)
-		add	r0, sp, #S_OFF
-		mov	why, #0		@ prevent syscall restart handling
-		b	__sys_rt_sigreturn
-ENDPROC(sys_rt_sigreturn)
-
-	__INIT
-
-/*
- * Vector stubs.
- *
- * This code is copied to 0xffff0200 so we can use branches in the
- * vectors, rather than ldr's.  Note that this code must not
- * exceed 0x300 bytes.
- *
- * Common stub entry macro:
- *   Enter in INTR mode, bsr = PRIV/USER ASR, lr = PRIV/USER PC
- *
- * SP points to a minimal amount of processor-private memory, the address
- * of which is copied into r0 for the mode specific abort handler.
- */
-	.macro	vector_stub, name, mode
-	.align	5
-
-vector_\name:
-	@
-	@ Save r0, lr_<exception> (parent PC) and bsr_<exception>
-	@ (parent ASR)
-	@
-	stw	r0, [sp]
-	stw	lr, [sp+], #4		@ save r0, lr
-	mov	lr, bsr
-	stw	lr, [sp+], #8		@ save bsr
-
-	@
-	@ Prepare for PRIV mode.  INTRs remain disabled.
-	@
-	mov	r0, asr
-	xor	r0, r0, #(\mode ^ PRIV_MODE)
-	mov.a	bsr, r0
-
-	@
-	@ the branch table must immediately follow this code
-	@
-	and	lr, lr, #0x03
-	add	lr, lr, #1
-	mov	r0, sp
-	ldw	lr, [pc+], lr << #2
-	mov.a	pc, lr			@ branch to handler in PRIV mode
-ENDPROC(vector_\name)
-	.align	2
-	@ handler addresses follow this label
-	.endm
-
-	.globl	__stubs_start
-__stubs_start:
-/*
- * Interrupt dispatcher
- */
-	vector_stub	intr, INTR_MODE
-
-	.long	__intr_user			@  0  (USER)
-	.long	__invalid			@  1
-	.long	__invalid			@  2
-	.long	__intr_priv			@  3  (PRIV)
-
-/*
- * Data abort dispatcher
- * Enter in ABT mode, bsr = USER ASR, lr = USER PC
- */
-	vector_stub	dabt, ABRT_MODE
-
-	.long	__dabt_user			@  0  (USER)
-	.long	__invalid			@  1
-	.long	__invalid			@  2  (INTR)
-	.long	__dabt_priv			@  3  (PRIV)
-
-/*
- * Prefetch abort dispatcher
- * Enter in ABT mode, bsr = USER ASR, lr = USER PC
- */
-	vector_stub	pabt, ABRT_MODE
-
-	.long	__pabt_user			@  0 (USER)
-	.long	__invalid			@  1
-	.long	__invalid			@  2 (INTR)
-	.long	__pabt_priv			@  3 (PRIV)
-
-/*
- * Undef instr entry dispatcher
- * Enter in EXTN mode, bsr = PRIV/USER ASR, lr = PRIV/USER PC
- */
-	vector_stub	extn, EXTN_MODE
-
-	.long	__extn_user			@  0 (USER)
-	.long	__invalid			@  1
-	.long	__invalid			@  2 (INTR)
-	.long	__extn_priv			@  3 (PRIV)
-
-/*
- * We group all the following data together to optimise
- * for CPUs with separate I & D caches.
- */
-	.align	5
-
-.LCvswi:
-	.word	vector_swi
-
-	.globl	__stubs_end
-__stubs_end:
-
-	.equ	stubs_offset, __vectors_start + 0x200 - __stubs_start
-
-	.globl	__vectors_start
-__vectors_start:
-	jepriv	SYS_ERROR0
-	b	vector_extn + stubs_offset
-	ldw	pc, .LCvswi + stubs_offset
-	b	vector_pabt + stubs_offset
-	b	vector_dabt + stubs_offset
-	jepriv	SYS_ERROR0
-	b	vector_intr + stubs_offset
-	jepriv	SYS_ERROR0
-
-	.globl	__vectors_end
-__vectors_end:
-
-	.data
-
-	.globl	cr_alignment
-	.globl	cr_no_alignment
-cr_alignment:
-	.space	4
-cr_no_alignment:
-	.space	4
diff --git a/arch/unicore32/kernel/fpu-ucf64.c b/arch/unicore32/kernel/fpu-ucf64.c
deleted file mode 100644
index 85f0af29d29b..000000000000
--- a/arch/unicore32/kernel/fpu-ucf64.c
+++ /dev/null
@@ -1,117 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/fpu-ucf64.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/sched/signal.h>
-#include <linux/init.h>
-
-#include <asm/fpu-ucf64.h>
-
-/*
- * A special flag to tell the normalisation code not to normalise.
- */
-#define F64_NAN_FLAG	0x100
-
-/*
- * A bit pattern used to indicate the initial (unset) value of the
- * exception mask, in case nothing handles an instruction.  This
- * doesn't include the NAN flag, which get masked out before
- * we check for an error.
- */
-#define F64_EXCEPTION_ERROR	((u32)-1 & ~F64_NAN_FLAG)
-
-/*
- * Since we aren't building with -mfpu=f64, we need to code
- * these instructions using their MRC/MCR equivalents.
- */
-#define f64reg(_f64_) #_f64_
-
-#define cff(_f64_) ({			\
-	u32 __v;			\
-	asm("cff %0, " f64reg(_f64_) "@ fmrx	%0, " #_f64_	\
-	    : "=r" (__v) : : "cc");	\
-	__v;				\
-	})
-
-#define ctf(_f64_, _var_)		\
-	asm("ctf %0, " f64reg(_f64_) "@ fmxr	" #_f64_ ", %0"	\
-	   : : "r" (_var_) : "cc")
-
-/*
- * Raise a SIGFPE for the current process.
- * sicode describes the signal being raised.
- */
-void ucf64_raise_sigfpe(struct pt_regs *regs)
-{
-	/*
-	 * This is the same as NWFPE, because it's not clear what
-	 * this is used for
-	 */
-	current->thread.error_code = 0;
-	current->thread.trap_no = 6;
-
-	send_sig_fault(SIGFPE, FPE_FLTUNK,
-		       (void __user *)(instruction_pointer(regs) - 4),
-		       current);
-}
-
-/*
- * Handle exceptions of UniCore-F64.
- */
-void ucf64_exchandler(u32 inst, u32 fpexc, struct pt_regs *regs)
-{
-	u32 tmp = fpexc;
-	u32 exc = F64_EXCEPTION_ERROR & fpexc;
-
-	pr_debug("UniCore-F64: instruction %08x fpscr %08x\n",
-			inst, fpexc);
-
-	if (exc & FPSCR_CMPINSTR_BIT) {
-		if (exc & FPSCR_CON)
-			tmp |= FPSCR_CON;
-		else
-			tmp &= ~(FPSCR_CON);
-		exc &= ~(FPSCR_CMPINSTR_BIT | FPSCR_CON);
-	} else {
-		pr_debug("UniCore-F64 Error: unhandled exceptions\n");
-		pr_debug("UniCore-F64 FPSCR 0x%08x INST 0x%08x\n",
-				cff(FPSCR), inst);
-
-		ucf64_raise_sigfpe(regs);
-		return;
-	}
-
-	/*
-	 * Update the FPSCR with the additional exception flags.
-	 * Comparison instructions always return at least one of
-	 * these flags set.
-	 */
-	tmp &= ~(FPSCR_TRAP | FPSCR_IOS | FPSCR_OFS | FPSCR_UFS |
-			FPSCR_IXS | FPSCR_HIS | FPSCR_IOC | FPSCR_OFC |
-			FPSCR_UFC | FPSCR_IXC | FPSCR_HIC);
-
-	tmp |= exc;
-	ctf(FPSCR, tmp);
-}
-
-/*
- * F64 support code initialisation.
- */
-static int __init ucf64_init(void)
-{
-	ctf(FPSCR, 0x0);     /* FPSCR_UFE | FPSCR_NDE perhaps better */
-
-	printk(KERN_INFO "Enable UniCore-F64 support.\n");
-
-	return 0;
-}
-
-late_initcall(ucf64_init);
diff --git a/arch/unicore32/kernel/gpio.c b/arch/unicore32/kernel/gpio.c
deleted file mode 100644
index 36d395b54b7c..000000000000
--- a/arch/unicore32/kernel/gpio.c
+++ /dev/null
@@ -1,121 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/gpio.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-/* in FPGA, no GPIO support */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/gpio/driver.h>
-/* FIXME: needed for gpio_set_value() - convert to use descriptors or hogs */
-#include <linux/gpio.h>
-#include <mach/hardware.h>
-
-#ifdef CONFIG_LEDS
-#include <linux/leds.h>
-#include <linux/platform_device.h>
-
-static const struct gpio_led puv3_gpio_leds[] = {
-	{ .name = "cpuhealth", .gpio = GPO_CPU_HEALTH, .active_low = 0,
-		.default_trigger = "heartbeat",	},
-	{ .name = "hdd_led", .gpio = GPO_HDD_LED, .active_low = 1,
-		.default_trigger = "disk-activity", },
-};
-
-static const struct gpio_led_platform_data puv3_gpio_led_data = {
-	.num_leds =	ARRAY_SIZE(puv3_gpio_leds),
-	.leds =		(void *) puv3_gpio_leds,
-};
-
-static struct platform_device puv3_gpio_gpio_leds = {
-	.name =		"leds-gpio",
-	.id =		-1,
-	.dev = {
-		.platform_data = (void *) &puv3_gpio_led_data,
-	}
-};
-
-static int __init puv3_gpio_leds_init(void)
-{
-	platform_device_register(&puv3_gpio_gpio_leds);
-	return 0;
-}
-
-device_initcall(puv3_gpio_leds_init);
-#endif
-
-static int puv3_gpio_get(struct gpio_chip *chip, unsigned offset)
-{
-	return !!(readl(GPIO_GPLR) & GPIO_GPIO(offset));
-}
-
-static void puv3_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
-{
-	if (value)
-		writel(GPIO_GPIO(offset), GPIO_GPSR);
-	else
-		writel(GPIO_GPIO(offset), GPIO_GPCR);
-}
-
-static int puv3_direction_input(struct gpio_chip *chip, unsigned offset)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	writel(readl(GPIO_GPDR) & ~GPIO_GPIO(offset), GPIO_GPDR);
-	local_irq_restore(flags);
-	return 0;
-}
-
-static int puv3_direction_output(struct gpio_chip *chip, unsigned offset,
-		int value)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	puv3_gpio_set(chip, offset, value);
-	writel(readl(GPIO_GPDR) | GPIO_GPIO(offset), GPIO_GPDR);
-	local_irq_restore(flags);
-	return 0;
-}
-
-static struct gpio_chip puv3_gpio_chip = {
-	.label			= "gpio",
-	.direction_input	= puv3_direction_input,
-	.direction_output	= puv3_direction_output,
-	.set			= puv3_gpio_set,
-	.get			= puv3_gpio_get,
-	.base			= 0,
-	.ngpio			= GPIO_MAX + 1,
-};
-
-void __init puv3_init_gpio(void)
-{
-	writel(GPIO_DIR, GPIO_GPDR);
-#if	defined(CONFIG_PUV3_NB0916) || defined(CONFIG_PUV3_SMW0919)	\
-	|| defined(CONFIG_PUV3_DB0913)
-	gpio_set_value(GPO_WIFI_EN, 1);
-	gpio_set_value(GPO_HDD_LED, 1);
-	gpio_set_value(GPO_VGA_EN, 1);
-	gpio_set_value(GPO_LCD_EN, 1);
-	gpio_set_value(GPO_CAM_PWR_EN, 0);
-	gpio_set_value(GPO_LCD_VCC_EN, 1);
-	gpio_set_value(GPO_SOFT_OFF, 1);
-	gpio_set_value(GPO_BT_EN, 1);
-	gpio_set_value(GPO_FAN_ON, 0);
-	gpio_set_value(GPO_SPKR, 0);
-	gpio_set_value(GPO_CPU_HEALTH, 1);
-	gpio_set_value(GPO_LAN_SEL, 1);
-/*
- * DO NOT modify the GPO_SET_V1 and GPO_SET_V2 in kernel
- *	gpio_set_value(GPO_SET_V1, 1);
- *	gpio_set_value(GPO_SET_V2, 1);
- */
-#endif
-	gpiochip_add_data(&puv3_gpio_chip, NULL);
-}
diff --git a/arch/unicore32/kernel/head.S b/arch/unicore32/kernel/head.S
deleted file mode 100644
index 9bbb8668f9f7..000000000000
--- a/arch/unicore32/kernel/head.S
+++ /dev/null
@@ -1,249 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/kernel/head.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-
-#include <asm/assembler.h>
-#include <asm/ptrace.h>
-#include <generated/asm-offsets.h>
-#include <asm/memory.h>
-#include <asm/thread_info.h>
-#include <asm/hwdef-copro.h>
-#include <asm/pgtable-hwdef.h>
-
-#if (PHYS_OFFSET & 0x003fffff)
-#error "PHYS_OFFSET must be at an even 4MiB boundary!"
-#endif
-
-#define KERNEL_RAM_VADDR	(PAGE_OFFSET + KERNEL_IMAGE_START)
-#define KERNEL_RAM_PADDR	(PHYS_OFFSET + KERNEL_IMAGE_START)
-
-#define KERNEL_PGD_PADDR	(KERNEL_RAM_PADDR - 0x1000)
-#define KERNEL_PGD_VADDR	(KERNEL_RAM_VADDR - 0x1000)
-
-#define KERNEL_START		KERNEL_RAM_VADDR
-#define KERNEL_END		_end
-
-/*
- * swapper_pg_dir is the virtual address of the initial page table.
- * We place the page tables 4K below KERNEL_RAM_VADDR.  Therefore, we must
- * make sure that KERNEL_RAM_VADDR is correctly set.  Currently, we expect
- * the least significant 16 bits to be 0x8000, but we could probably
- * relax this restriction to KERNEL_RAM_VADDR >= PAGE_OFFSET + 0x1000.
- */
-#if (KERNEL_RAM_VADDR & 0xffff) != 0x8000
-#error KERNEL_RAM_VADDR must start at 0xXXXX8000
-#endif
-
-	.globl	swapper_pg_dir
-	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - 0x1000
-
-/*
- * Kernel startup entry point.
- * ---------------------------
- *
- * This is normally called from the decompressor code.  The requirements
- * are: MMU = off, D-cache = off, I-cache = dont care
- *
- * This code is mostly position independent, so if you link the kernel at
- * 0xc0008000, you call this at __pa(0xc0008000).
- */
-	__HEAD
-ENTRY(stext)
-	@ set asr
-	mov	r0, #PRIV_MODE			@ ensure priv mode
-	or	r0, #PSR_R_BIT | PSR_I_BIT	@ disable irqs
-	mov.a	asr, r0
-
-	@ process identify
-	movc	r0, p0.c0, #0			@ cpuid
-	movl	r1, 0xff00ffff			@ mask
-	movl	r2, 0x4d000863			@ value
-	and	r0, r1, r0
-	cxor.a	r0, r2
-	bne	__error_p			@ invalid processor id
-
-	/*
-	 * Clear the 4K level 1 swapper page table
-	 */
-	movl	r0, #KERNEL_PGD_PADDR		@ page table address
-	mov	r1, #0
-	add	r2, r0, #0x1000
-101:	stw.w	r1, [r0]+, #4
-	stw.w	r1, [r0]+, #4
-	stw.w	r1, [r0]+, #4
-	stw.w	r1, [r0]+, #4
-	cxor.a	r0, r2
-	bne	101b
-
-	movl	r4, #KERNEL_PGD_PADDR		@ page table address
-	mov	r7, #PMD_TYPE_SECT | PMD_PRESENT	@ page size: section
-	or	r7, r7, #PMD_SECT_CACHEABLE		@ cacheable
-	or	r7, r7, #PMD_SECT_READ | PMD_SECT_WRITE | PMD_SECT_EXEC
-
-	/*
-	 * Create identity mapping for first 4MB of kernel to
-	 * cater for the MMU enable.  This identity mapping
-	 * will be removed by paging_init().  We use our current program
-	 * counter to determine corresponding section base address.
-	 */
-	mov	r6, pc
-	mov	r6, r6 >> #22			@ start of kernel section
-	or	r1, r7, r6 << #22		@ flags + kernel base
-	stw	r1, [r4+], r6 << #2		@ identity mapping
-
-	/*
-	 * Now setup the pagetables for our kernel direct
-	 * mapped region.
-	 */
-	add	r0, r4,  #(KERNEL_START & 0xff000000) >> 20
-	stw.w	r1, [r0+], #(KERNEL_START & 0x00c00000) >> 20
-	movl	r6, #(KERNEL_END - 1)
-	add	r0, r0, #4
-	add	r6, r4, r6 >> #20
-102:	csub.a	r0, r6
-	add	r1, r1, #1 << 22
-	bua	103f
-	stw.w	r1, [r0]+, #4
-	b	102b
-103:
-	/*
-	 * Then map first 4MB of ram in case it contains our boot params.
-	 */
-	add	r0, r4, #PAGE_OFFSET >> 20
-	or	r6, r7, #(PHYS_OFFSET & 0xffc00000)
-	stw	r6, [r0]
-
-	ldw	r15, __switch_data		@ address to jump to after
-
-	/*
-	 * Initialise TLB, Caches, and MMU state ready to switch the MMU
-	 * on.
-	 */
-	mov	r0, #0
-	movc	p0.c5, r0, #28			@ cache invalidate all
-	nop8
-	movc	p0.c6, r0, #6			@ TLB invalidate all
-	nop8
-
-	/*
-	 * ..V. .... ..TB IDAM
-	 * ..1. .... ..01 1111
-	 */
-	movl	r0, #0x201f			@ control register setting
-
-	/*
-	 * Setup common bits before finally enabling the MMU.  Essentially
-	 * this is just loading the page table pointer and domain access
-	 * registers.
-	 */
-	#ifndef CONFIG_ALIGNMENT_TRAP
-		andn	r0, r0, #CR_A
-	#endif
-	#ifdef CONFIG_CPU_DCACHE_DISABLE
-		andn	r0, r0, #CR_D
-	#endif
-	#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
-		andn	r0, r0, #CR_B
-	#endif
-	#ifdef CONFIG_CPU_ICACHE_DISABLE
-		andn	r0, r0, #CR_I
-	#endif
-
-	movc	p0.c2, r4, #0			@ set pgd
-	b	__turn_mmu_on
-ENDPROC(stext)
-
-/*
- * Enable the MMU.  This completely changes the structure of the visible
- * memory space.  You will not be able to trace execution through this.
- *
- *  r0  = cp#0 control register
- *  r15 = *virtual* address to jump to upon completion
- */
-	.align	5
-__turn_mmu_on:
-	mov	r0, r0
-	movc	p0.c1, r0, #0			@ write control reg
-	nop					@ fetch inst by phys addr
-	mov	pc, r15
-	nop8					@ fetch inst by phys addr
-ENDPROC(__turn_mmu_on)
-
-/*
- * Setup the initial page tables.  We only setup the barest
- * amount which are required to get the kernel running, which
- * generally means mapping in the kernel code.
- *
- * r9  = cpuid
- * r10 = procinfo
- *
- * Returns:
- *  r0, r3, r6, r7 corrupted
- *  r4 = physical page table address
- */
-	.ltorg
-
-	.align	2
-	.type	__switch_data, %object
-__switch_data:
-	.long	__mmap_switched
-	.long	__bss_start			@ r6
-	.long	_end				@ r7
-	.long	cr_alignment			@ r8
-	.long	init_thread_union + THREAD_START_SP @ sp
-
-/*
- * The following fragment of code is executed with the MMU on in MMU mode,
- * and uses absolute addresses; this is not position independent.
- *
- *  r0  = cp#0 control register
- */
-__mmap_switched:
-	adr	r3, __switch_data + 4
-
-	ldm.w	(r6, r7, r8), [r3]+
-	ldw	sp, [r3]
-
-	mov	fp, #0				@ Clear BSS (and zero fp)
-203:	csub.a	r6, r7
-	bea	204f
-	stw.w	fp, [r6]+,#4
-	b	203b
-204:
-	andn	r1, r0, #CR_A			@ Clear 'A' bit
-	stm	(r0, r1), [r8]+			@ Save control register values
-	b	start_kernel
-ENDPROC(__mmap_switched)
-
-/*
- * Exception handling.  Something went wrong and we can't proceed.  We
- * ought to tell the user, but since we don't have any guarantee that
- * we're even running on the right architecture, we do virtually nothing.
- *
- * If CONFIG_DEBUG_LL is set we try to print out something about the error
- * and hope for the best (useful if bootloader fails to pass a proper
- * machine ID for example).
- */
-__error_p:
-#ifdef CONFIG_DEBUG_LL
-	adr	r0, str_p1
-	b.l	printascii
-	mov	r0, r9
-	b.l	printhex8
-	adr	r0, str_p2
-	b.l	printascii
-901:	nop8
-	b	901b
-str_p1:	.asciz	"\nError: unrecognized processor variant (0x"
-str_p2:	.asciz	").\n"
-	.align
-#endif
-ENDPROC(__error_p)
-
diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c
deleted file mode 100644
index 4cdf3c846a2d..000000000000
--- a/arch/unicore32/kernel/hibernate.c
+++ /dev/null
@@ -1,159 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  linux/arch/unicore32/kernel/hibernate.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-
-#include <linux/gfp.h>
-#include <linux/suspend.h>
-#include <linux/memblock.h>
-#include <linux/pgtable.h>
-
-#include <asm/page.h>
-#include <asm/pgalloc.h>
-#include <asm/sections.h>
-#include <asm/suspend.h>
-
-#include "mach/pm.h"
-
-/* Pointer to the temporary resume page tables */
-pgd_t *resume_pg_dir;
-
-struct swsusp_arch_regs swsusp_arch_regs_cpu0;
-
-/*
- * Create a middle page table on a resume-safe page and put a pointer to it in
- * the given global directory entry.  This only returns the gd entry
- * in non-PAE compilation mode, since the middle layer is folded.
- */
-static pmd_t *resume_one_md_table_init(pgd_t *pgd)
-{
-	pud_t *pud;
-	p4d_t *p4d;
-	pmd_t *pmd_table;
-
-	p4d = p4d_offset(pgd, 0);
-	pud = pud_offset(p4d, 0);
-	pmd_table = pmd_offset(pud, 0);
-
-	return pmd_table;
-}
-
-/*
- * Create a page table on a resume-safe page and place a pointer to it in
- * a middle page directory entry.
- */
-static pte_t *resume_one_page_table_init(pmd_t *pmd)
-{
-	if (pmd_none(*pmd)) {
-		pte_t *page_table = (pte_t *)get_safe_page(GFP_ATOMIC);
-		if (!page_table)
-			return NULL;
-
-		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_KERNEL_TABLE));
-
-		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
-
-		return page_table;
-	}
-
-	return pte_offset_kernel(pmd, 0);
-}
-
-/*
- * This maps the physical memory to kernel virtual address space, a total
- * of max_low_pfn pages, by creating page tables starting from address
- * PAGE_OFFSET.  The page tables are allocated out of resume-safe pages.
- */
-static int resume_physical_mapping_init(pgd_t *pgd_base)
-{
-	unsigned long pfn;
-	pgd_t *pgd;
-	pmd_t *pmd;
-	pte_t *pte;
-	int pgd_idx, pmd_idx;
-
-	pgd_idx = pgd_index(PAGE_OFFSET);
-	pgd = pgd_base + pgd_idx;
-	pfn = 0;
-
-	for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) {
-		pmd = resume_one_md_table_init(pgd);
-		if (!pmd)
-			return -ENOMEM;
-
-		if (pfn >= max_low_pfn)
-			continue;
-
-		for (pmd_idx = 0; pmd_idx < PTRS_PER_PMD; pmd++, pmd_idx++) {
-			pte_t *max_pte;
-
-			if (pfn >= max_low_pfn)
-				break;
-
-			/* Map with normal page tables.
-			 * NOTE: We can mark everything as executable here
-			 */
-			pte = resume_one_page_table_init(pmd);
-			if (!pte)
-				return -ENOMEM;
-
-			max_pte = pte + PTRS_PER_PTE;
-			for (; pte < max_pte; pte++, pfn++) {
-				if (pfn >= max_low_pfn)
-					break;
-
-				set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
-			}
-		}
-	}
-
-	return 0;
-}
-
-static inline void resume_init_first_level_page_table(pgd_t *pg_dir)
-{
-}
-
-int swsusp_arch_resume(void)
-{
-	int error;
-
-	resume_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
-	if (!resume_pg_dir)
-		return -ENOMEM;
-
-	resume_init_first_level_page_table(resume_pg_dir);
-	error = resume_physical_mapping_init(resume_pg_dir);
-	if (error)
-		return error;
-
-	/* We have got enough memory and from now on we cannot recover */
-	restore_image(resume_pg_dir, restore_pblist);
-	return 0;
-}
-
-/*
- *	pfn_is_nosave - check if given pfn is in the 'nosave' section
- */
-
-int pfn_is_nosave(unsigned long pfn)
-{
-	unsigned long begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
-	unsigned long end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
-
-	return (pfn >= begin_pfn) && (pfn < end_pfn);
-}
-
-void save_processor_state(void)
-{
-}
-
-void restore_processor_state(void)
-{
-	local_flush_tlb_all();
-}
diff --git a/arch/unicore32/kernel/hibernate_asm.S b/arch/unicore32/kernel/hibernate_asm.S
deleted file mode 100644
index a589bc189e24..000000000000
--- a/arch/unicore32/kernel/hibernate_asm.S
+++ /dev/null
@@ -1,114 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/kernel/hibernate_asm.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-
-#include <linux/sys.h>
-#include <linux/errno.h>
-#include <linux/linkage.h>
-#include <linux/pgtable.h>
-#include <generated/asm-offsets.h>
-#include <asm/page.h>
-#include <asm/assembler.h>
-
-@ restore_image(pgd_t *resume_pg_dir, struct pbe *restore_pblist)
-@ r0: resume_pg_dir
-@ r1: restore_pblist
-@ copy restore_pblist pages
-@ restore registers from swsusp_arch_regs_cpu0
-@
-ENTRY(restore_image)
-	sub	r0, r0, #PAGE_OFFSET
-	mov	r5, #0
-	movc	p0.c6, r5, #6	@invalidate ITLB & DTLB
-	movc	p0.c2, r0, #0
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-
-	.p2align 4,,7
-101:
-	csub.a	r1, #0
-	beq	109f
-
-	ldw	r6, [r1+], #PBE_ADDRESS
-	ldw	r7, [r1+], #PBE_ORIN_ADDRESS
-
-	movl	ip, #128
-102:	ldm.w	(r8 - r15), [r6]+
-	stm.w	(r8 - r15), [r7]+
-	sub.a	ip, ip, #1
-	bne	102b
-
-	ldw	r1, [r1+], #PBE_NEXT
-	b	101b
-
-	.p2align 4,,7
-109:
-	/* go back to the original page tables */
-	ldw	r0, =swapper_pg_dir
-	sub	r0, r0, #PAGE_OFFSET
-	mov	r5, #0
-	movc	p0.c6, r5, #6
-	movc	p0.c2, r0, #0
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-
-#ifdef	CONFIG_UNICORE_FPU_F64
-	ldw	ip, 1f
-	add	ip, ip, #SWSUSP_FPSTATE
-	lfm.w	(f0  - f7 ), [ip]+
-	lfm.w	(f8  - f15), [ip]+
-	lfm.w	(f16 - f23), [ip]+
-	lfm.w	(f24 - f31), [ip]+
-	ldw	r4, [ip]
-	ctf	r4, s31
-#endif
-	mov	r0, #0x0
-	ldw	ip, 1f
-	add	ip, ip, #SWSUSP_CPU
-	ldm.w	(r4 - r15), [ip]+
-	ldm	(r16 - r27, sp, pc), [ip]+	@ Load all regs saved previously
-
-	.align	2
-1:	.long	swsusp_arch_regs_cpu0
-
-
-@ swsusp_arch_suspend()
-@ - prepare pc for resume, return from function without swsusp_save on resume
-@ - save registers in swsusp_arch_regs_cpu0
-@ - call swsusp_save write suspend image
-
-ENTRY(swsusp_arch_suspend)
-	ldw	ip, 1f
-	add	ip, ip, #SWSUSP_CPU
-	stm.w	(r4 - r15), [ip]+
-	stm.w	(r16 - r27, sp, lr), [ip]+
-
-#ifdef	CONFIG_UNICORE_FPU_F64
-	ldw	ip, 1f
-	add	ip, ip, #SWSUSP_FPSTATE
-	sfm.w	(f0  - f7 ), [ip]+
-	sfm.w	(f8  - f15), [ip]+
-	sfm.w	(f16 - f23), [ip]+
-	sfm.w	(f24 - f31), [ip]+
-	cff	r4, s31
-	stw	r4, [ip]
-#endif
-	b	swsusp_save			@ no return
-
-1:	.long	swsusp_arch_regs_cpu0
diff --git a/arch/unicore32/kernel/irq.c b/arch/unicore32/kernel/irq.c
deleted file mode 100644
index c014ae3c3e48..000000000000
--- a/arch/unicore32/kernel/irq.c
+++ /dev/null
@@ -1,371 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/irq.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/random.h>
-#include <linux/smp.h>
-#include <linux/init.h>
-#include <linux/seq_file.h>
-#include <linux/errno.h>
-#include <linux/list.h>
-#include <linux/kallsyms.h>
-#include <linux/proc_fs.h>
-#include <linux/syscore_ops.h>
-
-#include <mach/hardware.h>
-
-#include "setup.h"
-
-/*
- * PKUnity GPIO edge detection for IRQs:
- * IRQs are generated on Falling-Edge, Rising-Edge, or both.
- * Use this instead of directly setting GRER/GFER.
- */
-static int GPIO_IRQ_rising_edge;
-static int GPIO_IRQ_falling_edge;
-static int GPIO_IRQ_mask = 0;
-
-#define GPIO_MASK(irq)		(1 << (irq - IRQ_GPIO0))
-
-static int puv3_gpio_type(struct irq_data *d, unsigned int type)
-{
-	unsigned int mask;
-
-	if (d->irq < IRQ_GPIOHIGH)
-		mask = 1 << d->irq;
-	else
-		mask = GPIO_MASK(d->irq);
-
-	if (type == IRQ_TYPE_PROBE) {
-		if ((GPIO_IRQ_rising_edge | GPIO_IRQ_falling_edge) & mask)
-			return 0;
-		type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING;
-	}
-
-	if (type & IRQ_TYPE_EDGE_RISING)
-		GPIO_IRQ_rising_edge |= mask;
-	else
-		GPIO_IRQ_rising_edge &= ~mask;
-	if (type & IRQ_TYPE_EDGE_FALLING)
-		GPIO_IRQ_falling_edge |= mask;
-	else
-		GPIO_IRQ_falling_edge &= ~mask;
-
-	writel(GPIO_IRQ_rising_edge & GPIO_IRQ_mask, GPIO_GRER);
-	writel(GPIO_IRQ_falling_edge & GPIO_IRQ_mask, GPIO_GFER);
-
-	return 0;
-}
-
-/*
- * GPIO IRQs must be acknowledged.  This is for IRQs from 0 to 7.
- */
-static void puv3_low_gpio_ack(struct irq_data *d)
-{
-	writel((1 << d->irq), GPIO_GEDR);
-}
-
-static void puv3_low_gpio_mask(struct irq_data *d)
-{
-	writel(readl(INTC_ICMR) & ~(1 << d->irq), INTC_ICMR);
-}
-
-static void puv3_low_gpio_unmask(struct irq_data *d)
-{
-	writel(readl(INTC_ICMR) | (1 << d->irq), INTC_ICMR);
-}
-
-static int puv3_low_gpio_wake(struct irq_data *d, unsigned int on)
-{
-	if (on)
-		writel(readl(PM_PWER) | (1 << d->irq), PM_PWER);
-	else
-		writel(readl(PM_PWER) & ~(1 << d->irq), PM_PWER);
-	return 0;
-}
-
-static struct irq_chip puv3_low_gpio_chip = {
-	.name		= "GPIO-low",
-	.irq_ack	= puv3_low_gpio_ack,
-	.irq_mask	= puv3_low_gpio_mask,
-	.irq_unmask	= puv3_low_gpio_unmask,
-	.irq_set_type	= puv3_gpio_type,
-	.irq_set_wake	= puv3_low_gpio_wake,
-};
-
-/*
- * IRQ8 (GPIO0 through 27) handler.  We enter here with the
- * irq_controller_lock held, and IRQs disabled.  Decode the IRQ
- * and call the handler.
- */
-static void puv3_gpio_handler(struct irq_desc *desc)
-{
-	unsigned int mask, irq;
-
-	mask = readl(GPIO_GEDR);
-	do {
-		/*
-		 * clear down all currently active IRQ sources.
-		 * We will be processing them all.
-		 */
-		writel(mask, GPIO_GEDR);
-
-		irq = IRQ_GPIO0;
-		do {
-			if (mask & 1)
-				generic_handle_irq(irq);
-			mask >>= 1;
-			irq++;
-		} while (mask);
-		mask = readl(GPIO_GEDR);
-	} while (mask);
-}
-
-/*
- * GPIO0-27 edge IRQs need to be handled specially.
- * In addition, the IRQs are all collected up into one bit in the
- * interrupt controller registers.
- */
-static void puv3_high_gpio_ack(struct irq_data *d)
-{
-	unsigned int mask = GPIO_MASK(d->irq);
-
-	writel(mask, GPIO_GEDR);
-}
-
-static void puv3_high_gpio_mask(struct irq_data *d)
-{
-	unsigned int mask = GPIO_MASK(d->irq);
-
-	GPIO_IRQ_mask &= ~mask;
-
-	writel(readl(GPIO_GRER) & ~mask, GPIO_GRER);
-	writel(readl(GPIO_GFER) & ~mask, GPIO_GFER);
-}
-
-static void puv3_high_gpio_unmask(struct irq_data *d)
-{
-	unsigned int mask = GPIO_MASK(d->irq);
-
-	GPIO_IRQ_mask |= mask;
-
-	writel(GPIO_IRQ_rising_edge & GPIO_IRQ_mask, GPIO_GRER);
-	writel(GPIO_IRQ_falling_edge & GPIO_IRQ_mask, GPIO_GFER);
-}
-
-static int puv3_high_gpio_wake(struct irq_data *d, unsigned int on)
-{
-	if (on)
-		writel(readl(PM_PWER) | PM_PWER_GPIOHIGH, PM_PWER);
-	else
-		writel(readl(PM_PWER) & ~PM_PWER_GPIOHIGH, PM_PWER);
-	return 0;
-}
-
-static struct irq_chip puv3_high_gpio_chip = {
-	.name		= "GPIO-high",
-	.irq_ack	= puv3_high_gpio_ack,
-	.irq_mask	= puv3_high_gpio_mask,
-	.irq_unmask	= puv3_high_gpio_unmask,
-	.irq_set_type	= puv3_gpio_type,
-	.irq_set_wake	= puv3_high_gpio_wake,
-};
-
-/*
- * We don't need to ACK IRQs on the PKUnity unless they're GPIOs
- * this is for internal IRQs i.e. from 8 to 31.
- */
-static void puv3_mask_irq(struct irq_data *d)
-{
-	writel(readl(INTC_ICMR) & ~(1 << d->irq), INTC_ICMR);
-}
-
-static void puv3_unmask_irq(struct irq_data *d)
-{
-	writel(readl(INTC_ICMR) | (1 << d->irq), INTC_ICMR);
-}
-
-/*
- * Apart form GPIOs, only the RTC alarm can be a wakeup event.
- */
-static int puv3_set_wake(struct irq_data *d, unsigned int on)
-{
-	if (d->irq == IRQ_RTCAlarm) {
-		if (on)
-			writel(readl(PM_PWER) | PM_PWER_RTC, PM_PWER);
-		else
-			writel(readl(PM_PWER) & ~PM_PWER_RTC, PM_PWER);
-		return 0;
-	}
-	return -EINVAL;
-}
-
-static struct irq_chip puv3_normal_chip = {
-	.name		= "PKUnity-v3",
-	.irq_ack	= puv3_mask_irq,
-	.irq_mask	= puv3_mask_irq,
-	.irq_unmask	= puv3_unmask_irq,
-	.irq_set_wake	= puv3_set_wake,
-};
-
-static struct resource irq_resource = {
-	.name	= "irqs",
-	.start	= io_v2p(PKUNITY_INTC_BASE),
-	.end	= io_v2p(PKUNITY_INTC_BASE) + 0xFFFFF,
-};
-
-static struct puv3_irq_state {
-	unsigned int	saved;
-	unsigned int	icmr;
-	unsigned int	iclr;
-	unsigned int	iccr;
-} puv3_irq_state;
-
-static int puv3_irq_suspend(void)
-{
-	struct puv3_irq_state *st = &puv3_irq_state;
-
-	st->saved = 1;
-	st->icmr = readl(INTC_ICMR);
-	st->iclr = readl(INTC_ICLR);
-	st->iccr = readl(INTC_ICCR);
-
-	/*
-	 * Disable all GPIO-based interrupts.
-	 */
-	writel(readl(INTC_ICMR) & ~(0x1ff), INTC_ICMR);
-
-	/*
-	 * Set the appropriate edges for wakeup.
-	 */
-	writel(readl(PM_PWER) & GPIO_IRQ_rising_edge, GPIO_GRER);
-	writel(readl(PM_PWER) & GPIO_IRQ_falling_edge, GPIO_GFER);
-
-	/*
-	 * Clear any pending GPIO interrupts.
-	 */
-	writel(readl(GPIO_GEDR), GPIO_GEDR);
-
-	return 0;
-}
-
-static void puv3_irq_resume(void)
-{
-	struct puv3_irq_state *st = &puv3_irq_state;
-
-	if (st->saved) {
-		writel(st->iccr, INTC_ICCR);
-		writel(st->iclr, INTC_ICLR);
-
-		writel(GPIO_IRQ_rising_edge & GPIO_IRQ_mask, GPIO_GRER);
-		writel(GPIO_IRQ_falling_edge & GPIO_IRQ_mask, GPIO_GFER);
-
-		writel(st->icmr, INTC_ICMR);
-	}
-}
-
-static struct syscore_ops puv3_irq_syscore_ops = {
-	.suspend	= puv3_irq_suspend,
-	.resume		= puv3_irq_resume,
-};
-
-static int __init puv3_irq_init_syscore(void)
-{
-	register_syscore_ops(&puv3_irq_syscore_ops);
-	return 0;
-}
-
-device_initcall(puv3_irq_init_syscore);
-
-void __init init_IRQ(void)
-{
-	unsigned int irq;
-
-	request_resource(&iomem_resource, &irq_resource);
-
-	/* disable all IRQs */
-	writel(0, INTC_ICMR);
-
-	/* all IRQs are IRQ, not REAL */
-	writel(0, INTC_ICLR);
-
-	/* clear all GPIO edge detects */
-	writel(FMASK(8, 0) & ~FIELD(1, 1, GPI_SOFF_REQ), GPIO_GPIR);
-	writel(0, GPIO_GFER);
-	writel(0, GPIO_GRER);
-	writel(0x0FFFFFFF, GPIO_GEDR);
-
-	writel(1, INTC_ICCR);
-
-	for (irq = 0; irq < IRQ_GPIOHIGH; irq++) {
-		irq_set_chip(irq, &puv3_low_gpio_chip);
-		irq_set_handler(irq, handle_edge_irq);
-		irq_modify_status(irq,
-			IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN,
-			0);
-	}
-
-	for (irq = IRQ_GPIOHIGH + 1; irq < IRQ_GPIO0; irq++) {
-		irq_set_chip(irq, &puv3_normal_chip);
-		irq_set_handler(irq, handle_level_irq);
-		irq_modify_status(irq,
-			IRQ_NOREQUEST | IRQ_NOAUTOEN,
-			IRQ_NOPROBE);
-	}
-
-	for (irq = IRQ_GPIO0; irq <= IRQ_GPIO27; irq++) {
-		irq_set_chip(irq, &puv3_high_gpio_chip);
-		irq_set_handler(irq, handle_edge_irq);
-		irq_modify_status(irq,
-			IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN,
-			0);
-	}
-
-	/*
-	 * Install handler for GPIO 0-27 edge detect interrupts
-	 */
-	irq_set_chip(IRQ_GPIOHIGH, &puv3_normal_chip);
-	irq_set_chained_handler(IRQ_GPIOHIGH, puv3_gpio_handler);
-
-#ifdef CONFIG_PUV3_GPIO
-	puv3_init_gpio();
-#endif
-}
-
-/*
- * do_IRQ handles all hardware IRQ's.  Decoded IRQs should not
- * come via this function.  Instead, they should provide their
- * own 'handler'
- */
-asmlinkage void asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	irq_enter();
-
-	/*
-	 * Some hardware gives randomly wrong interrupts.  Rather
-	 * than crashing, do something sensible.
-	 */
-	if (unlikely(irq >= nr_irqs)) {
-		if (printk_ratelimit())
-			printk(KERN_WARNING "Bad IRQ%u\n", irq);
-		ack_bad_irq(irq);
-	} else {
-		generic_handle_irq(irq);
-	}
-
-	irq_exit();
-	set_irq_regs(old_regs);
-}
-
diff --git a/arch/unicore32/kernel/ksyms.c b/arch/unicore32/kernel/ksyms.c
deleted file mode 100644
index 731445008932..000000000000
--- a/arch/unicore32/kernel/ksyms.c
+++ /dev/null
@@ -1,57 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/ksyms.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/delay.h>
-#include <linux/in6.h>
-#include <linux/syscalls.h>
-#include <linux/uaccess.h>
-#include <linux/io.h>
-
-#include <asm/checksum.h>
-
-#include "ksyms.h"
-
-EXPORT_SYMBOL(find_first_bit);
-EXPORT_SYMBOL(find_first_zero_bit);
-EXPORT_SYMBOL(find_next_zero_bit);
-EXPORT_SYMBOL(find_next_bit);
-
-	/* platform dependent support */
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__const_udelay);
-
-	/* string / mem functions */
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(memchr);
-
-	/* user mem (segment) */
-EXPORT_SYMBOL(__strnlen_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-
-EXPORT_SYMBOL(copy_page);
-
-EXPORT_SYMBOL(raw_copy_from_user);
-EXPORT_SYMBOL(raw_copy_to_user);
-EXPORT_SYMBOL(__clear_user);
-
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__divsi3);
-EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(__modsi3);
-EXPORT_SYMBOL(__ucmpdi2);
-EXPORT_SYMBOL(__udivsi3);
-EXPORT_SYMBOL(__umodsi3);
-
diff --git a/arch/unicore32/kernel/ksyms.h b/arch/unicore32/kernel/ksyms.h
deleted file mode 100644
index 5d2d5ba324ac..000000000000
--- a/arch/unicore32/kernel/ksyms.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * libgcc functions - functions that are used internally by the
- * compiler...  (prototypes are not correct though, but that
- * doesn't really matter since they're not versioned).
- */
-extern void __ashldi3(void);
-extern void __ashrdi3(void);
-extern void __divsi3(void);
-extern void __lshrdi3(void);
-extern void __modsi3(void);
-extern void __ucmpdi2(void);
-extern void __udivsi3(void);
-extern void __umodsi3(void);
diff --git a/arch/unicore32/kernel/module.c b/arch/unicore32/kernel/module.c
deleted file mode 100644
index 67c89ef2d6ee..000000000000
--- a/arch/unicore32/kernel/module.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/module.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/moduleloader.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/elf.h>
-#include <linux/vmalloc.h>
-#include <linux/fs.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-
-#include <asm/sections.h>
-
-void *module_alloc(unsigned long size)
-{
-	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
-				GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
-				__builtin_return_address(0));
-}
-
-int
-apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
-	       unsigned int relindex, struct module *module)
-{
-	Elf32_Shdr *symsec = sechdrs + symindex;
-	Elf32_Shdr *relsec = sechdrs + relindex;
-	Elf32_Shdr *dstsec = sechdrs + relsec->sh_info;
-	Elf32_Rel *rel = (void *)relsec->sh_addr;
-	unsigned int i;
-
-	for (i = 0; i < relsec->sh_size / sizeof(Elf32_Rel); i++, rel++) {
-		unsigned long loc;
-		Elf32_Sym *sym;
-		s32 offset;
-
-		offset = ELF32_R_SYM(rel->r_info);
-		if (offset < 0 || offset >
-				(symsec->sh_size / sizeof(Elf32_Sym))) {
-			printk(KERN_ERR "%s: bad relocation, "
-					"section %d reloc %d\n",
-					module->name, relindex, i);
-			return -ENOEXEC;
-		}
-
-		sym = ((Elf32_Sym *)symsec->sh_addr) + offset;
-
-		if (rel->r_offset < 0 || rel->r_offset >
-				dstsec->sh_size - sizeof(u32)) {
-			printk(KERN_ERR "%s: out of bounds relocation, "
-				"section %d reloc %d offset %d size %d\n",
-				module->name, relindex, i, rel->r_offset,
-				dstsec->sh_size);
-			return -ENOEXEC;
-		}
-
-		loc = dstsec->sh_addr + rel->r_offset;
-
-		switch (ELF32_R_TYPE(rel->r_info)) {
-		case R_UNICORE_NONE:
-			/* ignore */
-			break;
-
-		case R_UNICORE_ABS32:
-			*(u32 *)loc += sym->st_value;
-			break;
-
-		case R_UNICORE_PC24:
-		case R_UNICORE_CALL:
-		case R_UNICORE_JUMP24:
-			offset = (*(u32 *)loc & 0x00ffffff) << 2;
-			if (offset & 0x02000000)
-				offset -= 0x04000000;
-
-			offset += sym->st_value - loc;
-			if (offset & 3 ||
-			    offset <= (s32)0xfe000000 ||
-			    offset >= (s32)0x02000000) {
-				printk(KERN_ERR
-				       "%s: relocation out of range, section "
-				       "%d reloc %d sym '%s'\n", module->name,
-				       relindex, i, strtab + sym->st_name);
-				return -ENOEXEC;
-			}
-
-			offset >>= 2;
-
-			*(u32 *)loc &= 0xff000000;
-			*(u32 *)loc |= offset & 0x00ffffff;
-			break;
-
-		default:
-			printk(KERN_ERR "%s: unknown relocation: %u\n",
-			       module->name, ELF32_R_TYPE(rel->r_info));
-			return -ENOEXEC;
-		}
-	}
-	return 0;
-}
diff --git a/arch/unicore32/kernel/pci.c b/arch/unicore32/kernel/pci.c
deleted file mode 100644
index 0d098aa05b47..000000000000
--- a/arch/unicore32/kernel/pci.c
+++ /dev/null
@@ -1,371 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/pci.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  PCI bios-type initialisation for PCI machines
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/pci.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/io.h>
-
-static int debug_pci;
-
-#define CONFIG_CMD(bus, devfn, where)	\
-	(0x80000000 | (bus->number << 16) | (devfn << 8) | (where & ~3))
-
-static int
-puv3_read_config(struct pci_bus *bus, unsigned int devfn, int where,
-			int size, u32 *value)
-{
-	writel(CONFIG_CMD(bus, devfn, where), PCICFG_ADDR);
-	switch (size) {
-	case 1:
-		*value = (readl(PCICFG_DATA) >> ((where & 3) * 8)) & 0xFF;
-		break;
-	case 2:
-		*value = (readl(PCICFG_DATA) >> ((where & 2) * 8)) & 0xFFFF;
-		break;
-	case 4:
-		*value = readl(PCICFG_DATA);
-		break;
-	}
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static int
-puv3_write_config(struct pci_bus *bus, unsigned int devfn, int where,
-			int size, u32 value)
-{
-	writel(CONFIG_CMD(bus, devfn, where), PCICFG_ADDR);
-	switch (size) {
-	case 1:
-		writel((readl(PCICFG_DATA) & ~FMASK(8, (where&3)*8))
-			| FIELD(value, 8, (where&3)*8), PCICFG_DATA);
-		break;
-	case 2:
-		writel((readl(PCICFG_DATA) & ~FMASK(16, (where&2)*8))
-			| FIELD(value, 16, (where&2)*8), PCICFG_DATA);
-		break;
-	case 4:
-		writel(value, PCICFG_DATA);
-		break;
-	}
-	return PCIBIOS_SUCCESSFUL;
-}
-
-struct pci_ops pci_puv3_ops = {
-	.read  = puv3_read_config,
-	.write = puv3_write_config,
-};
-
-void pci_puv3_preinit(void)
-{
-	printk(KERN_DEBUG "PCI: PKUnity PCI Controller Initializing ...\n");
-	/* config PCI bridge base */
-	writel(io_v2p(PKUNITY_PCIBRI_BASE), PCICFG_BRIBASE);
-
-	writel(0, PCIBRI_AHBCTL0);
-	writel(io_v2p(PKUNITY_PCIBRI_BASE) | PCIBRI_BARx_MEM, PCIBRI_AHBBAR0);
-	writel(0xFFFF0000, PCIBRI_AHBAMR0);
-	writel(0, PCIBRI_AHBTAR0);
-
-	writel(PCIBRI_CTLx_AT, PCIBRI_AHBCTL1);
-	writel(io_v2p(PKUNITY_PCILIO_BASE) | PCIBRI_BARx_IO, PCIBRI_AHBBAR1);
-	writel(0xFFFF0000, PCIBRI_AHBAMR1);
-	writel(0x00000000, PCIBRI_AHBTAR1);
-
-	writel(PCIBRI_CTLx_PREF, PCIBRI_AHBCTL2);
-	writel(io_v2p(PKUNITY_PCIMEM_BASE) | PCIBRI_BARx_MEM, PCIBRI_AHBBAR2);
-	writel(0xF8000000, PCIBRI_AHBAMR2);
-	writel(0, PCIBRI_AHBTAR2);
-
-	writel(io_v2p(PKUNITY_PCIAHB_BASE) | PCIBRI_BARx_MEM, PCIBRI_BAR1);
-
-	writel(PCIBRI_CTLx_AT | PCIBRI_CTLx_PREF, PCIBRI_PCICTL0);
-	writel(io_v2p(PKUNITY_PCIAHB_BASE) | PCIBRI_BARx_MEM, PCIBRI_PCIBAR0);
-	writel(0xF8000000, PCIBRI_PCIAMR0);
-	writel(PKUNITY_SDRAM_BASE, PCIBRI_PCITAR0);
-
-	writel(readl(PCIBRI_CMD) | PCIBRI_CMD_IO | PCIBRI_CMD_MEM, PCIBRI_CMD);
-}
-
-static int pci_puv3_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
-{
-	if (dev->bus->number == 0) {
-#ifdef CONFIG_ARCH_FPGA /* 4 pci slots */
-		if      (dev->devfn == 0x00)
-			return IRQ_PCIINTA;
-		else if (dev->devfn == 0x08)
-			return IRQ_PCIINTB;
-		else if (dev->devfn == 0x10)
-			return IRQ_PCIINTC;
-		else if (dev->devfn == 0x18)
-			return IRQ_PCIINTD;
-#endif
-#ifdef CONFIG_PUV3_DB0913 /* 3 pci slots */
-		if      (dev->devfn == 0x30)
-			return IRQ_PCIINTB;
-		else if (dev->devfn == 0x60)
-			return IRQ_PCIINTC;
-		else if (dev->devfn == 0x58)
-			return IRQ_PCIINTD;
-#endif
-#if	defined(CONFIG_PUV3_NB0916) || defined(CONFIG_PUV3_SMW0919)
-		/* only support 2 pci devices */
-		if      (dev->devfn == 0x00)
-			return IRQ_PCIINTC; /* sata */
-#endif
-	}
-	return -1;
-}
-
-/*
- * Only first 128MB of memory can be accessed via PCI.
- * We use GFP_DMA to allocate safe buffers to do map/unmap.
- * This is really ugly and we need a better way of specifying
- * DMA-capable regions of memory.
- */
-void __init puv3_pci_adjust_zones(unsigned long max_zone_pfn)
-{
-	unsigned int sz = SZ_128M >> PAGE_SHIFT;
-
-	max_zone_pfn[ZONE_DMA] = sz;
-}
-
-/*
- * If the bus contains any of these devices, then we must not turn on
- * parity checking of any kind.
- */
-static inline int pdev_bad_for_parity(struct pci_dev *dev)
-{
-	return 0;
-}
-
-/*
- * pcibios_fixup_bus - Called after each bus is probed,
- * but before its children are examined.
- */
-void pcibios_fixup_bus(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-	u16 features = PCI_COMMAND_SERR
-		| PCI_COMMAND_PARITY
-		| PCI_COMMAND_FAST_BACK;
-
-	bus->resource[0] = &ioport_resource;
-	bus->resource[1] = &iomem_resource;
-
-	/*
-	 * Walk the devices on this bus, working out what we can
-	 * and can't support.
-	 */
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		u16 status;
-
-		pci_read_config_word(dev, PCI_STATUS, &status);
-
-		/*
-		 * If any device on this bus does not support fast back
-		 * to back transfers, then the bus as a whole is not able
-		 * to support them.  Having fast back to back transfers
-		 * on saves us one PCI cycle per transaction.
-		 */
-		if (!(status & PCI_STATUS_FAST_BACK))
-			features &= ~PCI_COMMAND_FAST_BACK;
-
-		if (pdev_bad_for_parity(dev))
-			features &= ~(PCI_COMMAND_SERR
-					| PCI_COMMAND_PARITY);
-
-		switch (dev->class >> 8) {
-		case PCI_CLASS_BRIDGE_PCI:
-			pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &status);
-			status |= PCI_BRIDGE_CTL_PARITY
-				| PCI_BRIDGE_CTL_MASTER_ABORT;
-			status &= ~(PCI_BRIDGE_CTL_BUS_RESET
-				| PCI_BRIDGE_CTL_FAST_BACK);
-			pci_write_config_word(dev, PCI_BRIDGE_CONTROL, status);
-			break;
-
-		case PCI_CLASS_BRIDGE_CARDBUS:
-			pci_read_config_word(dev, PCI_CB_BRIDGE_CONTROL,
-					&status);
-			status |= PCI_CB_BRIDGE_CTL_PARITY
-				| PCI_CB_BRIDGE_CTL_MASTER_ABORT;
-			pci_write_config_word(dev, PCI_CB_BRIDGE_CONTROL,
-					status);
-			break;
-		}
-	}
-
-	/*
-	 * Now walk the devices again, this time setting them up.
-	 */
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		u16 cmd;
-
-		pci_read_config_word(dev, PCI_COMMAND, &cmd);
-		cmd |= features;
-		pci_write_config_word(dev, PCI_COMMAND, cmd);
-
-		pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE,
-				      L1_CACHE_BYTES >> 2);
-	}
-
-	/*
-	 * Propagate the flags to the PCI bridge.
-	 */
-	if (bus->self && bus->self->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		if (features & PCI_COMMAND_FAST_BACK)
-			bus->bridge_ctl |= PCI_BRIDGE_CTL_FAST_BACK;
-		if (features & PCI_COMMAND_PARITY)
-			bus->bridge_ctl |= PCI_BRIDGE_CTL_PARITY;
-	}
-
-	/*
-	 * Report what we did for this bus
-	 */
-	printk(KERN_INFO "PCI: bus%d: Fast back to back transfers %sabled\n",
-		bus->number, (features & PCI_COMMAND_FAST_BACK) ? "en" : "dis");
-}
-EXPORT_SYMBOL(pcibios_fixup_bus);
-
-static struct resource busn_resource = {
-	.name	= "PCI busn",
-	.start	= 0,
-	.end	= 255,
-	.flags	= IORESOURCE_BUS,
-};
-
-static int __init pci_common_init(void)
-{
-	struct pci_bus *puv3_bus;
-	struct pci_host_bridge *bridge;
-	int ret;
-
-	bridge = pci_alloc_host_bridge(0);
-	if (!bridge)
-		return -ENOMEM;
-
-	pci_puv3_preinit();
-
-	pci_add_resource(&bridge->windows, &ioport_resource);
-	pci_add_resource(&bridge->windows, &iomem_resource);
-	pci_add_resource(&bridge->windows, &busn_resource);
-	bridge->sysdata = NULL;
-	bridge->busnr = 0;
-	bridge->ops = &pci_puv3_ops;
-	bridge->swizzle_irq = pci_common_swizzle;
-	bridge->map_irq = pci_puv3_map_irq;
-
-	/* Scan our single hose.  */
-	ret = pci_scan_root_bus_bridge(bridge);
-	if (ret) {
-		pci_free_host_bridge(bridge);
-		return;
-	}
-
-	puv3_bus = bridge->bus;
-
-	if (!puv3_bus)
-		panic("PCI: unable to scan bus!");
-
-	pci_bus_size_bridges(puv3_bus);
-	pci_bus_assign_resources(puv3_bus);
-	pci_bus_add_devices(puv3_bus);
-	return 0;
-}
-subsys_initcall(pci_common_init);
-
-char * __init pcibios_setup(char *str)
-{
-	if (!strcmp(str, "debug")) {
-		debug_pci = 1;
-		return NULL;
-	}
-	return str;
-}
-
-void pcibios_set_master(struct pci_dev *dev)
-{
-	/* No special bus mastering setup handling */
-}
-
-/*
- * From arch/i386/kernel/pci-i386.c:
- *
- * We need to avoid collisions with `mirrored' VGA ports
- * and other strange ISA hardware, so we always want the
- * addresses to be allocated in the 0x000-0x0ff region
- * modulo 0x400.
- *
- * Why? Because some silly external IO cards only decode
- * the low 10 bits of the IO address. The 0x00-0xff region
- * is reserved for motherboard devices that decode all 16
- * bits, so it's ok to allocate at, say, 0x2800-0x28ff,
- * but we want to try to avoid allocating at 0x2900-0x2bff
- * which might be mirrored at 0x0100-0x03ff..
- */
-resource_size_t pcibios_align_resource(void *data, const struct resource *res,
-				resource_size_t size, resource_size_t align)
-{
-	resource_size_t start = res->start;
-
-	if (res->flags & IORESOURCE_IO && start & 0x300)
-		start = (start + 0x3ff) & ~0x3ff;
-
-	start = (start + align - 1) & ~(align - 1);
-
-	return start;
-}
-
-/**
- * pcibios_enable_device - Enable I/O and memory.
- * @dev: PCI device to be enabled
- */
-int pcibios_enable_device(struct pci_dev *dev, int mask)
-{
-	u16 cmd, old_cmd;
-	int idx;
-	struct resource *r;
-
-	pci_read_config_word(dev, PCI_COMMAND, &cmd);
-	old_cmd = cmd;
-	for (idx = 0; idx < 6; idx++) {
-		/* Only set up the requested stuff */
-		if (!(mask & (1 << idx)))
-			continue;
-
-		r = dev->resource + idx;
-		if (!r->start && r->end) {
-			printk(KERN_ERR "PCI: Device %s not available because"
-			       " of resource collisions\n", pci_name(dev));
-			return -EINVAL;
-		}
-		if (r->flags & IORESOURCE_IO)
-			cmd |= PCI_COMMAND_IO;
-		if (r->flags & IORESOURCE_MEM)
-			cmd |= PCI_COMMAND_MEMORY;
-	}
-
-	/*
-	 * Bridges (eg, cardbus bridges) need to be fully enabled
-	 */
-	if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE)
-		cmd |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY;
-
-	if (cmd != old_cmd) {
-		printk("PCI: enabling device %s (%04x -> %04x)\n",
-		       pci_name(dev), old_cmd, cmd);
-		pci_write_config_word(dev, PCI_COMMAND, cmd);
-	}
-	return 0;
-}
diff --git a/arch/unicore32/kernel/pm.c b/arch/unicore32/kernel/pm.c
deleted file mode 100644
index 94b7f9df6c1a..000000000000
--- a/arch/unicore32/kernel/pm.c
+++ /dev/null
@@ -1,121 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/pm.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/suspend.h>
-#include <linux/errno.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-
-#include <mach/hardware.h>
-#include <mach/pm.h>
-
-#include "setup.h"
-
-struct puv3_cpu_pm_fns *puv3_cpu_pm_fns;
-static unsigned long *sleep_save;
-
-int puv3_pm_enter(suspend_state_t state)
-{
-	unsigned long sleep_save_checksum = 0, checksum = 0;
-	int i;
-
-	/* skip registers saving for standby */
-	if (state != PM_SUSPEND_STANDBY) {
-		puv3_cpu_pm_fns->save(sleep_save);
-		/* before sleeping, calculate and save a checksum */
-		for (i = 0; i < puv3_cpu_pm_fns->save_count - 1; i++)
-			sleep_save_checksum += sleep_save[i];
-	}
-
-	/* *** go zzz *** */
-	puv3_cpu_pm_fns->enter(state);
-	cpu_init();
-#ifdef CONFIG_INPUT_KEYBOARD
-	puv3_ps2_init();
-#endif
-#ifdef CONFIG_PCI
-	pci_puv3_preinit();
-#endif
-	if (state != PM_SUSPEND_STANDBY) {
-		/* after sleeping, validate the checksum */
-		for (i = 0; i < puv3_cpu_pm_fns->save_count - 1; i++)
-			checksum += sleep_save[i];
-
-		/* if invalid, display message and wait for a hardware reset */
-		if (checksum != sleep_save_checksum) {
-			while (1)
-				puv3_cpu_pm_fns->enter(state);
-		}
-		puv3_cpu_pm_fns->restore(sleep_save);
-	}
-
-	pr_debug("*** made it back from resume\n");
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(puv3_pm_enter);
-
-unsigned long sleep_phys_sp(void *sp)
-{
-	return virt_to_phys(sp);
-}
-
-static int puv3_pm_valid(suspend_state_t state)
-{
-	if (puv3_cpu_pm_fns)
-		return puv3_cpu_pm_fns->valid(state);
-
-	return -EINVAL;
-}
-
-static int puv3_pm_prepare(void)
-{
-	int ret = 0;
-
-	if (puv3_cpu_pm_fns && puv3_cpu_pm_fns->prepare)
-		ret = puv3_cpu_pm_fns->prepare();
-
-	return ret;
-}
-
-static void puv3_pm_finish(void)
-{
-	if (puv3_cpu_pm_fns && puv3_cpu_pm_fns->finish)
-		puv3_cpu_pm_fns->finish();
-}
-
-static struct platform_suspend_ops puv3_pm_ops = {
-	.valid		= puv3_pm_valid,
-	.enter		= puv3_pm_enter,
-	.prepare	= puv3_pm_prepare,
-	.finish		= puv3_pm_finish,
-};
-
-static int __init puv3_pm_init(void)
-{
-	if (!puv3_cpu_pm_fns) {
-		printk(KERN_ERR "no valid puv3_cpu_pm_fns defined\n");
-		return -EINVAL;
-	}
-
-	sleep_save = kmalloc_array(puv3_cpu_pm_fns->save_count,
-				   sizeof(unsigned long),
-				   GFP_KERNEL);
-	if (!sleep_save) {
-		printk(KERN_ERR "failed to alloc memory for pm save\n");
-		return -ENOMEM;
-	}
-
-	suspend_set_ops(&puv3_pm_ops);
-	return 0;
-}
-
-device_initcall(puv3_pm_init);
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
deleted file mode 100644
index b4fd3a604a18..000000000000
--- a/arch/unicore32/kernel/process.c
+++ /dev/null
@@ -1,319 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/process.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <stdarg.h>
-
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
-#include <linux/sched/task.h>
-#include <linux/sched/task_stack.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/cpu.h>
-#include <linux/elfcore.h>
-#include <linux/pm.h>
-#include <linux/tick.h>
-#include <linux/utsname.h>
-#include <linux/uaccess.h>
-#include <linux/random.h>
-#include <linux/gpio.h>
-#include <linux/stacktrace.h>
-
-#include <asm/cacheflush.h>
-#include <asm/processor.h>
-#include <asm/stacktrace.h>
-
-#include "setup.h"
-
-static const char * const processor_modes[] = {
-	"UK00", "UK01", "UK02", "UK03", "UK04", "UK05", "UK06", "UK07",
-	"UK08", "UK09", "UK0A", "UK0B", "UK0C", "UK0D", "UK0E", "UK0F",
-	"USER", "REAL", "INTR", "PRIV", "UK14", "UK15", "UK16", "ABRT",
-	"UK18", "UK19", "UK1A", "EXTN", "UK1C", "UK1D", "UK1E", "SUSR"
-};
-
-void arch_cpu_idle(void)
-{
-	cpu_do_idle();
-	local_irq_enable();
-}
-
-void machine_halt(void)
-{
-	gpio_set_value(GPO_SOFT_OFF, 0);
-}
-
-/*
- * Function pointers to optional machine specific functions
- */
-void (*pm_power_off)(void) = NULL;
-EXPORT_SYMBOL(pm_power_off);
-
-void machine_power_off(void)
-{
-	if (pm_power_off)
-		pm_power_off();
-	machine_halt();
-}
-
-void machine_restart(char *cmd)
-{
-	/* Disable interrupts first */
-	local_irq_disable();
-
-	/*
-	 * Tell the mm system that we are going to reboot -
-	 * we may need it to insert some 1:1 mappings so that
-	 * soft boot works.
-	 */
-	setup_mm_for_reboot();
-
-	/* Clean and invalidate caches */
-	flush_cache_all();
-
-	/* Turn off caching */
-	cpu_proc_fin();
-
-	/* Push out any further dirty data, and ensure cache is empty */
-	flush_cache_all();
-
-	/*
-	 * Now handle reboot code.
-	 */
-	if (reboot_mode == REBOOT_SOFT) {
-		/* Jump into ROM at address 0xffff0000 */
-		cpu_reset(VECTORS_BASE);
-	} else {
-		writel(0x00002001, PM_PLLSYSCFG); /* cpu clk = 250M */
-		writel(0x00100800, PM_PLLDDRCFG); /* ddr clk =  44M */
-		writel(0x00002001, PM_PLLVGACFG); /* vga clk = 250M */
-
-		/* Use on-chip reset capability */
-		/* following instructions must be in one icache line */
-		__asm__ __volatile__(
-			"	.align 5\n\t"
-			"	stw	%1, [%0]\n\t"
-			"201:	ldw	r0, [%0]\n\t"
-			"	cmpsub.a	r0, #0\n\t"
-			"	bne	201b\n\t"
-			"	stw	%3, [%2]\n\t"
-			"	nop; nop; nop\n\t"
-			/* prefetch 3 instructions at most */
-			:
-			: "r" (PM_PMCR),
-			  "r" (PM_PMCR_CFBSYS | PM_PMCR_CFBDDR
-				| PM_PMCR_CFBVGA),
-			  "r" (RESETC_SWRR),
-			  "r" (RESETC_SWRR_SRB)
-			: "r0", "memory");
-	}
-
-	/*
-	 * Whoops - the architecture was unable to reboot.
-	 * Tell the user!
-	 */
-	mdelay(1000);
-	printk(KERN_EMERG "Reboot failed -- System halted\n");
-	do { } while (1);
-}
-
-void __show_regs(struct pt_regs *regs)
-{
-	unsigned long flags;
-	char buf[64];
-
-	show_regs_print_info(KERN_DEFAULT);
-	printk("PC is at %pS\n", (void *)instruction_pointer(regs));
-	printk("LR is at %pS\n", (void *)regs->UCreg_lr);
-	printk(KERN_DEFAULT "pc : [<%08lx>]    lr : [<%08lx>]    psr: %08lx\n"
-	       "sp : %08lx  ip : %08lx  fp : %08lx\n",
-		regs->UCreg_pc, regs->UCreg_lr, regs->UCreg_asr,
-		regs->UCreg_sp, regs->UCreg_ip, regs->UCreg_fp);
-	printk(KERN_DEFAULT "r26: %08lx  r25: %08lx  r24: %08lx\n",
-		regs->UCreg_26, regs->UCreg_25,
-		regs->UCreg_24);
-	printk(KERN_DEFAULT "r23: %08lx  r22: %08lx  r21: %08lx  r20: %08lx\n",
-		regs->UCreg_23, regs->UCreg_22,
-		regs->UCreg_21, regs->UCreg_20);
-	printk(KERN_DEFAULT "r19: %08lx  r18: %08lx  r17: %08lx  r16: %08lx\n",
-		regs->UCreg_19, regs->UCreg_18,
-		regs->UCreg_17, regs->UCreg_16);
-	printk(KERN_DEFAULT "r15: %08lx  r14: %08lx  r13: %08lx  r12: %08lx\n",
-		regs->UCreg_15, regs->UCreg_14,
-		regs->UCreg_13, regs->UCreg_12);
-	printk(KERN_DEFAULT "r11: %08lx  r10: %08lx  r9 : %08lx  r8 : %08lx\n",
-		regs->UCreg_11, regs->UCreg_10,
-		regs->UCreg_09, regs->UCreg_08);
-	printk(KERN_DEFAULT "r7 : %08lx  r6 : %08lx  r5 : %08lx  r4 : %08lx\n",
-		regs->UCreg_07, regs->UCreg_06,
-		regs->UCreg_05, regs->UCreg_04);
-	printk(KERN_DEFAULT "r3 : %08lx  r2 : %08lx  r1 : %08lx  r0 : %08lx\n",
-		regs->UCreg_03, regs->UCreg_02,
-		regs->UCreg_01, regs->UCreg_00);
-
-	flags = regs->UCreg_asr;
-	buf[0] = flags & PSR_S_BIT ? 'S' : 's';
-	buf[1] = flags & PSR_Z_BIT ? 'Z' : 'z';
-	buf[2] = flags & PSR_C_BIT ? 'C' : 'c';
-	buf[3] = flags & PSR_V_BIT ? 'V' : 'v';
-	buf[4] = '\0';
-
-	printk(KERN_DEFAULT "Flags: %s  INTR o%s  REAL o%s  Mode %s  Segment %s\n",
-		buf, interrupts_enabled(regs) ? "n" : "ff",
-		fast_interrupts_enabled(regs) ? "n" : "ff",
-		processor_modes[processor_mode(regs)],
-		uaccess_kernel() ? "kernel" : "user");
-	{
-		unsigned int ctrl;
-
-		buf[0] = '\0';
-		{
-			unsigned int transbase;
-			asm("movc %0, p0.c2, #0\n"
-			    : "=r" (transbase));
-			snprintf(buf, sizeof(buf), "  Table: %08x", transbase);
-		}
-		asm("movc %0, p0.c1, #0\n" : "=r" (ctrl));
-
-		printk(KERN_DEFAULT "Control: %08x%s\n", ctrl, buf);
-	}
-}
-
-void show_regs(struct pt_regs *regs)
-{
-	printk(KERN_DEFAULT "\n");
-	printk(KERN_DEFAULT "Pid: %d, comm: %20s\n",
-			task_pid_nr(current), current->comm);
-	__show_regs(regs);
-	__backtrace();
-}
-
-void flush_thread(void)
-{
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = current;
-
-	memset(thread->used_cp, 0, sizeof(thread->used_cp));
-	memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
-#ifdef CONFIG_UNICORE_FPU_F64
-	memset(&thread->fpstate, 0, sizeof(struct fp_state));
-#endif
-}
-
-void release_thread(struct task_struct *dead_task)
-{
-}
-
-asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
-
-int
-copy_thread(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p)
-{
-	struct thread_info *thread = task_thread_info(p);
-	struct pt_regs *childregs = task_pt_regs(p);
-
-	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
-	thread->cpu_context.sp = (unsigned long)childregs;
-	if (unlikely(p->flags & PF_KTHREAD)) {
-		thread->cpu_context.pc = (unsigned long)ret_from_kernel_thread;
-		thread->cpu_context.r4 = stack_start;
-		thread->cpu_context.r5 = stk_sz;
-		memset(childregs, 0, sizeof(struct pt_regs));
-	} else {
-		thread->cpu_context.pc = (unsigned long)ret_from_fork;
-		*childregs = *current_pt_regs();
-		childregs->UCreg_00 = 0;
-		if (stack_start)
-			childregs->UCreg_sp = stack_start;
-
-		if (clone_flags & CLONE_SETTLS)
-			childregs->UCreg_16 = childregs->UCreg_03;
-	}
-	return 0;
-}
-
-/*
- * Fill in the task's elfregs structure for a core dump.
- */
-int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs)
-{
-	elf_core_copy_regs(elfregs, task_pt_regs(t));
-	return 1;
-}
-
-/*
- * fill in the fpe structure for a core dump...
- */
-int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fp)
-{
-	struct thread_info *thread = current_thread_info();
-	int used_math = thread->used_cp[1] | thread->used_cp[2];
-
-#ifdef CONFIG_UNICORE_FPU_F64
-	if (used_math)
-		memcpy(fp, &thread->fpstate, sizeof(*fp));
-#endif
-	return used_math != 0;
-}
-EXPORT_SYMBOL(dump_fpu);
-
-unsigned long get_wchan(struct task_struct *p)
-{
-	struct stackframe frame;
-	int count = 0;
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-
-	frame.fp = thread_saved_fp(p);
-	frame.sp = thread_saved_sp(p);
-	frame.lr = 0;			/* recovered from the stack */
-	frame.pc = thread_saved_pc(p);
-	do {
-		int ret = unwind_frame(&frame);
-		if (ret < 0)
-			return 0;
-		if (!in_sched_functions(frame.pc))
-			return frame.pc;
-	} while ((count++) < 16);
-	return 0;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	return randomize_page(mm->brk, 0x02000000);
-}
-
-/*
- * The vectors page is always readable from user space for the
- * atomic helpers and the signal restart code.  Let's declare a mapping
- * for it so it is visible through ptrace and /proc/<pid>/mem.
- */
-
-int vectors_user_mapping(void)
-{
-	struct mm_struct *mm = current->mm;
-	return install_special_mapping(mm, 0xffff0000, PAGE_SIZE,
-				       VM_READ | VM_EXEC |
-				       VM_MAYREAD | VM_MAYEXEC |
-				       VM_DONTEXPAND | VM_DONTDUMP,
-				       NULL);
-}
-
-const char *arch_vma_name(struct vm_area_struct *vma)
-{
-	return (vma->vm_start == 0xffff0000) ? "[vectors]" : NULL;
-}
diff --git a/arch/unicore32/kernel/ptrace.c b/arch/unicore32/kernel/ptrace.c
deleted file mode 100644
index 0f216567b90a..000000000000
--- a/arch/unicore32/kernel/ptrace.c
+++ /dev/null
@@ -1,147 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/ptrace.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * By Ross Biro 1/23/92
- */
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/signal.h>
-#include <linux/uaccess.h>
-#include <linux/sched/task_stack.h>
-
-/*
- * this routine will get a word off of the processes privileged stack.
- * the offset is how far from the base addr as stored in the THREAD.
- * this routine assumes that all the privileged stacks are in our
- * data space.
- */
-static inline long get_user_reg(struct task_struct *task, int offset)
-{
-	return task_pt_regs(task)->uregs[offset];
-}
-
-/*
- * this routine will put a word on the processes privileged stack.
- * the offset is how far from the base addr as stored in the THREAD.
- * this routine assumes that all the privileged stacks are in our
- * data space.
- */
-static inline int
-put_user_reg(struct task_struct *task, int offset, long data)
-{
-	struct pt_regs newregs, *regs = task_pt_regs(task);
-	int ret = -EINVAL;
-
-	newregs = *regs;
-	newregs.uregs[offset] = data;
-
-	if (valid_user_regs(&newregs)) {
-		regs->uregs[offset] = data;
-		ret = 0;
-	}
-
-	return ret;
-}
-
-/*
- * Called by kernel/ptrace.c when detaching..
- */
-void ptrace_disable(struct task_struct *child)
-{
-}
-
-/*
- * We actually access the pt_regs stored on the kernel stack.
- */
-static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
-			    unsigned long __user *ret)
-{
-	unsigned long tmp;
-
-	tmp = 0;
-	if (off < sizeof(struct pt_regs))
-		tmp = get_user_reg(tsk, off >> 2);
-
-	return put_user(tmp, ret);
-}
-
-/*
- * We actually access the pt_regs stored on the kernel stack.
- */
-static int ptrace_write_user(struct task_struct *tsk, unsigned long off,
-			     unsigned long val)
-{
-	if (off >= sizeof(struct pt_regs))
-		return 0;
-
-	return put_user_reg(tsk, off >> 2, val);
-}
-
-long arch_ptrace(struct task_struct *child, long request,
-		 unsigned long addr, unsigned long data)
-{
-	int ret;
-	unsigned long __user *datap = (unsigned long __user *) data;
-
-	switch (request) {
-	case PTRACE_PEEKUSR:
-		ret = ptrace_read_user(child, addr, datap);
-		break;
-
-	case PTRACE_POKEUSR:
-		ret = ptrace_write_user(child, addr, data);
-		break;
-
-	case PTRACE_GET_THREAD_AREA:
-		ret = put_user(task_pt_regs(child)->UCreg_16,
-			       datap);
-		break;
-
-	default:
-		ret = ptrace_request(child, request, addr, data);
-		break;
-	}
-
-	return ret;
-}
-
-asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
-{
-	unsigned long ip;
-
-	if (!test_thread_flag(TIF_SYSCALL_TRACE))
-		return scno;
-	if (!(current->ptrace & PT_PTRACED))
-		return scno;
-
-	/*
-	 * Save IP.  IP is used to denote syscall entry/exit:
-	 *  IP = 0 -> entry, = 1 -> exit
-	 */
-	ip = regs->UCreg_ip;
-	regs->UCreg_ip = why;
-
-	current_thread_info()->syscall = scno;
-
-	/* the 0x80 provides a way for the tracing parent to distinguish
-	   between a syscall stop and SIGTRAP delivery */
-	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
-				 ? 0x80 : 0));
-	/*
-	 * this isn't the same as continuing with a signal, but it will do
-	 * for normal use.  strace only continues with a signal if the
-	 * stopping signal is not SIGTRAP.  -brl
-	 */
-	if (current->exit_code) {
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
-	regs->UCreg_ip = ip;
-
-	return current_thread_info()->syscall;
-}
diff --git a/arch/unicore32/kernel/puv3-core.c b/arch/unicore32/kernel/puv3-core.c
deleted file mode 100644
index 78f12e627365..000000000000
--- a/arch/unicore32/kernel/puv3-core.c
+++ /dev/null
@@ -1,276 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  linux/arch/unicore32/kernel/puv3-core.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/amba/bus.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
-#include <linux/cnt32_to_63.h>
-#include <linux/usb/musb.h>
-
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <mach/pm.h>
-
-/*
- * This is the PKUnity sched_clock implementation.  This has
- * a resolution of 271ns, and a maximum value of 32025597s (370 days).
- *
- * The return value is guaranteed to be monotonic in that range as
- * long as there is always less than 582 seconds between successive
- * calls to this function.
- *
- *  ( * 1E9 / CLOCK_TICK_RATE ) -> about 2235/32
- */
-unsigned long long sched_clock(void)
-{
-	unsigned long long v = cnt32_to_63(readl(OST_OSCR));
-
-	/* original conservative method, but overflow frequently
-	 * v *= NSEC_PER_SEC >> 12;
-	 * do_div(v, CLOCK_TICK_RATE >> 12);
-	 */
-	v = ((v & 0x7fffffffffffffffULL) * 2235) >> 5;
-
-	return v;
-}
-
-static struct resource puv3_usb_resources[] = {
-	/* order is significant! */
-	{
-		.start		= io_v2p(PKUNITY_USB_BASE),
-		.end		= io_v2p(PKUNITY_USB_BASE) + 0x3ff,
-		.flags		= IORESOURCE_MEM,
-	}, {
-		.start		= IRQ_USB,
-		.flags		= IORESOURCE_IRQ,
-	}, {
-		.start		= IRQ_USB,
-		.flags		= IORESOURCE_IRQ,
-	},
-};
-
-static struct musb_hdrc_config	puv3_usb_config[] = {
-	{
-		.num_eps = 16,
-		.multipoint = 1,
-#ifdef CONFIG_USB_INVENTRA_DMA
-		.dma = 1,
-		.dma_channels = 8,
-#endif
-	},
-};
-
-static struct musb_hdrc_platform_data puv3_usb_plat = {
-	.mode		= MUSB_HOST,
-	.min_power	= 100,
-	.clock		= 0,
-	.config		= puv3_usb_config,
-};
-
-static struct resource puv3_mmc_resources[] = {
-	[0] = {
-		.start	= io_v2p(PKUNITY_SDC_BASE),
-		.end	= io_v2p(PKUNITY_SDC_BASE) + 0xfff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_SDC,
-		.end	= IRQ_SDC,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource puv3_unigfx_resources[] = {
-	[0] = {
-		.start	= io_v2p(PKUNITY_UNIGFX_BASE),
-		.end	= io_v2p(PKUNITY_UNIGFX_BASE) + 0xfff,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct resource puv3_rtc_resources[] = {
-	[0] = {
-		.start = io_v2p(PKUNITY_RTC_BASE),
-		.end   = io_v2p(PKUNITY_RTC_BASE) + 0xff,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = IRQ_RTCAlarm,
-		.end   = IRQ_RTCAlarm,
-		.flags = IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start = IRQ_RTC,
-		.end   = IRQ_RTC,
-		.flags = IORESOURCE_IRQ
-	}
-};
-
-static struct resource puv3_pwm_resources[] = {
-	[0] = {
-		.start	= io_v2p(PKUNITY_OST_BASE) + 0x80,
-		.end	= io_v2p(PKUNITY_OST_BASE) + 0xff,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct resource puv3_uart0_resources[] = {
-	[0] = {
-		.start = io_v2p(PKUNITY_UART0_BASE),
-		.end   = io_v2p(PKUNITY_UART0_BASE) + 0xff,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = IRQ_UART0,
-		.end   = IRQ_UART0,
-		.flags = IORESOURCE_IRQ
-	}
-};
-
-static struct resource puv3_uart1_resources[] = {
-	[0] = {
-		.start = io_v2p(PKUNITY_UART1_BASE),
-		.end   = io_v2p(PKUNITY_UART1_BASE) + 0xff,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = IRQ_UART1,
-		.end   = IRQ_UART1,
-		.flags = IORESOURCE_IRQ
-	}
-};
-
-static struct resource puv3_umal_resources[] = {
-	[0] = {
-		.start = io_v2p(PKUNITY_UMAL_BASE),
-		.end   = io_v2p(PKUNITY_UMAL_BASE) + 0x1fff,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = IRQ_UMAL,
-		.end   = IRQ_UMAL,
-		.flags = IORESOURCE_IRQ
-	}
-};
-
-#ifdef CONFIG_PUV3_PM
-
-#define SAVE(x)		sleep_save[SLEEP_SAVE_##x] = x
-#define RESTORE(x)	x = sleep_save[SLEEP_SAVE_##x]
-
-/*
- * List of global PXA peripheral registers to preserve.
- * More ones like CP and general purpose register values are preserved
- * with the stack pointer in sleep.S.
- */
-enum {
-	SLEEP_SAVE_PM_PLLDDRCFG,
-	SLEEP_SAVE_COUNT
-};
-
-
-static void puv3_cpu_pm_save(unsigned long *sleep_save)
-{
-/*	SAVE(PM_PLLDDRCFG); */
-}
-
-static void puv3_cpu_pm_restore(unsigned long *sleep_save)
-{
-/*	RESTORE(PM_PLLDDRCFG); */
-}
-
-static int puv3_cpu_pm_prepare(void)
-{
-	/* set resume return address */
-	writel(virt_to_phys(puv3_cpu_resume), PM_DIVCFG);
-	return 0;
-}
-
-static void puv3_cpu_pm_enter(suspend_state_t state)
-{
-	/* Clear reset status */
-	writel(RESETC_RSSR_HWR | RESETC_RSSR_WDR
-			| RESETC_RSSR_SMR | RESETC_RSSR_SWR, RESETC_RSSR);
-
-	switch (state) {
-/*	case PM_SUSPEND_ON:
-		puv3_cpu_idle();
-		break; */
-	case PM_SUSPEND_MEM:
-		puv3_cpu_pm_prepare();
-		puv3_cpu_suspend(PM_PMCR_SFB);
-		break;
-	}
-}
-
-static int puv3_cpu_pm_valid(suspend_state_t state)
-{
-	return state == PM_SUSPEND_MEM;
-}
-
-static void puv3_cpu_pm_finish(void)
-{
-	/* ensure not to come back here if it wasn't intended */
-	/* PSPR = 0; */
-}
-
-static struct puv3_cpu_pm_fns puv3_cpu_pm_fnss = {
-	.save_count	= SLEEP_SAVE_COUNT,
-	.valid		= puv3_cpu_pm_valid,
-	.save		= puv3_cpu_pm_save,
-	.restore	= puv3_cpu_pm_restore,
-	.enter		= puv3_cpu_pm_enter,
-	.prepare	= puv3_cpu_pm_prepare,
-	.finish		= puv3_cpu_pm_finish,
-};
-
-static void __init puv3_init_pm(void)
-{
-	puv3_cpu_pm_fns = &puv3_cpu_pm_fnss;
-}
-#else
-static inline void puv3_init_pm(void) {}
-#endif
-
-void puv3_ps2_init(void)
-{
-	struct clk *bclk32;
-
-	bclk32 = clk_get(NULL, "BUS32_CLK");
-	writel(clk_get_rate(bclk32) / 200000, PS2_CNT); /* should > 5us */
-}
-
-void __init puv3_core_init(void)
-{
-	puv3_init_pm();
-	puv3_ps2_init();
-
-	platform_device_register_simple("PKUnity-v3-RTC", -1,
-			puv3_rtc_resources, ARRAY_SIZE(puv3_rtc_resources));
-	platform_device_register_simple("PKUnity-v3-UMAL", -1,
-			puv3_umal_resources, ARRAY_SIZE(puv3_umal_resources));
-	platform_device_register_simple("PKUnity-v3-MMC", -1,
-			puv3_mmc_resources, ARRAY_SIZE(puv3_mmc_resources));
-	platform_device_register_simple("PKUnity-v3-UNIGFX", -1,
-			puv3_unigfx_resources, ARRAY_SIZE(puv3_unigfx_resources));
-	platform_device_register_simple("PKUnity-v3-PWM", -1,
-			puv3_pwm_resources, ARRAY_SIZE(puv3_pwm_resources));
-	platform_device_register_simple("PKUnity-v3-UART", 0,
-			puv3_uart0_resources, ARRAY_SIZE(puv3_uart0_resources));
-	platform_device_register_simple("PKUnity-v3-UART", 1,
-			puv3_uart1_resources, ARRAY_SIZE(puv3_uart1_resources));
-	platform_device_register_simple("PKUnity-v3-AC97", -1, NULL, 0);
-	platform_device_register_resndata(NULL, "musb_hdrc", -1,
-			puv3_usb_resources, ARRAY_SIZE(puv3_usb_resources),
-			&puv3_usb_plat, sizeof(puv3_usb_plat));
-}
-
diff --git a/arch/unicore32/kernel/puv3-nb0916.c b/arch/unicore32/kernel/puv3-nb0916.c
deleted file mode 100644
index e251f5028396..000000000000
--- a/arch/unicore32/kernel/puv3-nb0916.c
+++ /dev/null
@@ -1,147 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/puv3-nb0916.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/physmap.h>
-#include <linux/io.h>
-#include <linux/reboot.h>
-#include <linux/interrupt.h>
-#include <linux/i2c.h>
-#include <linux/pwm.h>
-#include <linux/pwm_backlight.h>
-#include <linux/gpio.h>
-#include <linux/gpio_keys.h>
-#include <linux/input.h>
-
-#include <mach/hardware.h>
-
-static struct physmap_flash_data physmap_flash_data = {
-	.width		= 1,
-};
-
-static struct resource physmap_flash_resource = {
-	.start		= 0xFFF80000,
-	.end		= 0xFFFFFFFF,
-	.flags		= IORESOURCE_MEM,
-};
-
-static struct resource puv3_i2c_resources[] = {
-	[0] = {
-		.start = io_v2p(PKUNITY_I2C_BASE),
-		.end   = io_v2p(PKUNITY_I2C_BASE) + 0xff,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = IRQ_I2C,
-		.end   = IRQ_I2C,
-		.flags = IORESOURCE_IRQ,
-	}
-};
-
-static struct pwm_lookup nb0916_pwm_lookup[] = {
-	PWM_LOOKUP("PKUnity-v3-PWM", 0, "pwm-backlight", NULL, 70 * 1024,
-		   PWM_POLARITY_NORMAL),
-};
-
-static struct platform_pwm_backlight_data nb0916_backlight_data = {
-	.max_brightness	= 100,
-	.dft_brightness	= 100,
-};
-
-static struct gpio_keys_button nb0916_gpio_keys[] = {
-	{
-		.type	= EV_KEY,
-		.code	= KEY_POWER,
-		.gpio	= GPI_SOFF_REQ,
-		.desc	= "Power Button",
-		.wakeup = 1,
-		.active_low = 1,
-	},
-	{
-		.type	= EV_KEY,
-		.code	= BTN_TOUCH,
-		.gpio	= GPI_BTN_TOUCH,
-		.desc	= "Touchpad Button",
-		.wakeup = 1,
-		.active_low = 1,
-	},
-};
-
-static struct gpio_keys_platform_data nb0916_gpio_button_data = {
-	.buttons	= nb0916_gpio_keys,
-	.nbuttons	= ARRAY_SIZE(nb0916_gpio_keys),
-};
-
-static irqreturn_t nb0916_lcdcaseoff_handler(int irq, void *dev_id)
-{
-	if (gpio_get_value(GPI_LCD_CASE_OFF))
-		gpio_set_value(GPO_LCD_EN, 1);
-	else
-		gpio_set_value(GPO_LCD_EN, 0);
-
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t nb0916_overheat_handler(int irq, void *dev_id)
-{
-	machine_halt();
-	/* SYSTEM HALT, NO RETURN */
-	return IRQ_HANDLED;
-}
-
-static struct i2c_board_info __initdata puv3_i2c_devices[] = {
-	{	I2C_BOARD_INFO("lm75",		I2C_TAR_THERMAL),	},
-	{	I2C_BOARD_INFO("bq27200",	I2C_TAR_PWIC),		},
-	{	I2C_BOARD_INFO("24c02",		I2C_TAR_EEPROM),	},
-};
-
-int __init mach_nb0916_init(void)
-{
-	i2c_register_board_info(0, puv3_i2c_devices,
-			ARRAY_SIZE(puv3_i2c_devices));
-
-	platform_device_register_simple("PKUnity-v3-I2C", -1,
-			puv3_i2c_resources, ARRAY_SIZE(puv3_i2c_resources));
-
-	pwm_add_table(nb0916_pwm_lookup, ARRAY_SIZE(nb0916_pwm_lookup));
-
-	platform_device_register_data(NULL, "pwm-backlight", -1,
-			&nb0916_backlight_data, sizeof(nb0916_backlight_data));
-
-	platform_device_register_data(NULL, "gpio-keys", -1,
-			&nb0916_gpio_button_data, sizeof(nb0916_gpio_button_data));
-
-	platform_device_register_resndata(NULL, "physmap-flash", -1,
-			&physmap_flash_resource, 1,
-			&physmap_flash_data, sizeof(physmap_flash_data));
-
-	if (request_irq(gpio_to_irq(GPI_LCD_CASE_OFF),
-		&nb0916_lcdcaseoff_handler,
-		IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-		"NB0916 lcd case off", NULL) < 0) {
-
-		printk(KERN_DEBUG "LCD-Case-OFF IRQ %d not available\n",
-			gpio_to_irq(GPI_LCD_CASE_OFF));
-	}
-
-	if (request_irq(gpio_to_irq(GPI_OTP_INT), &nb0916_overheat_handler,
-		IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-		"NB0916 overheating protection", NULL) < 0) {
-
-		printk(KERN_DEBUG "Overheating Protection IRQ %d not available\n",
-			gpio_to_irq(GPI_OTP_INT));
-	}
-
-	return 0;
-}
-
-subsys_initcall_sync(mach_nb0916_init);
diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c
deleted file mode 100644
index 0c4242a5ee1d..000000000000
--- a/arch/unicore32/kernel/setup.c
+++ /dev/null
@@ -1,352 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/setup.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/stddef.h>
-#include <linux/ioport.h>
-#include <linux/delay.h>
-#include <linux/utsname.h>
-#include <linux/initrd.h>
-#include <linux/console.h>
-#include <linux/memblock.h>
-#include <linux/seq_file.h>
-#include <linux/screen_info.h>
-#include <linux/init.h>
-#include <linux/root_dev.h>
-#include <linux/cpu.h>
-#include <linux/interrupt.h>
-#include <linux/smp.h>
-#include <linux/fs.h>
-#include <linux/proc_fs.h>
-#include <linux/elf.h>
-#include <linux/io.h>
-
-#include <asm/cputype.h>
-#include <asm/sections.h>
-#include <asm/setup.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-#include <asm/traps.h>
-#include <asm/memblock.h>
-
-#include "setup.h"
-
-#ifndef MEM_SIZE
-#define MEM_SIZE	(16*1024*1024)
-#endif
-
-struct stack {
-	u32 irq[3];
-	u32 abt[3];
-	u32 und[3];
-} ____cacheline_aligned;
-
-static struct stack stacks[NR_CPUS];
-
-#ifdef CONFIG_VGA_CONSOLE
-struct screen_info screen_info;
-#endif
-
-char elf_platform[ELF_PLATFORM_SIZE];
-EXPORT_SYMBOL(elf_platform);
-
-static char __initdata cmd_line[COMMAND_LINE_SIZE];
-
-static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE;
-
-/*
- * Standard memory resources
- */
-static struct resource mem_res[] = {
-	{
-		.name = "Kernel code",
-		.start = 0,
-		.end = 0,
-		.flags = IORESOURCE_SYSTEM_RAM
-	},
-	{
-		.name = "Kernel data",
-		.start = 0,
-		.end = 0,
-		.flags = IORESOURCE_SYSTEM_RAM
-	}
-};
-
-#define kernel_code mem_res[0]
-#define kernel_data mem_res[1]
-
-/*
- * These functions re-use the assembly code in head.S, which
- * already provide the required functionality.
- */
-static void __init setup_processor(void)
-{
-	printk(KERN_DEFAULT "CPU: UniCore-II [%08x] revision %d, cr=%08lx\n",
-	       uc32_cpuid, (int)(uc32_cpuid >> 16) & 15, cr_alignment);
-
-	sprintf(init_utsname()->machine, "puv3");
-	sprintf(elf_platform, "ucv2");
-}
-
-/*
- * cpu_init - initialise one CPU.
- *
- * cpu_init sets up the per-CPU stacks.
- */
-void cpu_init(void)
-{
-	unsigned int cpu = smp_processor_id();
-	struct stack *stk = &stacks[cpu];
-
-	/*
-	 * setup stacks for re-entrant exception handlers
-	 */
-	__asm__ (
-	"mov.a	asr, %1\n\t"
-	"add	sp, %0, %2\n\t"
-	"mov.a	asr, %3\n\t"
-	"add	sp, %0, %4\n\t"
-	"mov.a	asr, %5\n\t"
-	"add	sp, %0, %6\n\t"
-	"mov.a	asr, %7"
-	    :
-	    : "r" (stk),
-	      "r" (PSR_R_BIT | PSR_I_BIT | INTR_MODE),
-	      "I" (offsetof(struct stack, irq[0])),
-	      "r" (PSR_R_BIT | PSR_I_BIT | ABRT_MODE),
-	      "I" (offsetof(struct stack, abt[0])),
-	      "r" (PSR_R_BIT | PSR_I_BIT | EXTN_MODE),
-	      "I" (offsetof(struct stack, und[0])),
-	      "r" (PSR_R_BIT | PSR_I_BIT | PRIV_MODE)
-	: "r30", "cc");
-}
-
-static int __init uc32_add_memory(unsigned long start, unsigned long size)
-{
-	struct membank *bank = &meminfo.bank[meminfo.nr_banks];
-
-	if (meminfo.nr_banks >= NR_BANKS) {
-		printk(KERN_CRIT "NR_BANKS too low, "
-			"ignoring memory at %#lx\n", start);
-		return -EINVAL;
-	}
-
-	/*
-	 * Ensure that start/size are aligned to a page boundary.
-	 * Size is appropriately rounded down, start is rounded up.
-	 */
-	size -= start & ~PAGE_MASK;
-
-	bank->start = PAGE_ALIGN(start);
-	bank->size  = size & PAGE_MASK;
-
-	/*
-	 * Check whether this memory region has non-zero size or
-	 * invalid node number.
-	 */
-	if (bank->size == 0)
-		return -EINVAL;
-
-	meminfo.nr_banks++;
-	return 0;
-}
-
-/*
- * Pick out the memory size.  We look for mem=size@start,
- * where start and size are "size[KkMm]"
- */
-static int __init early_mem(char *p)
-{
-	static int usermem __initdata = 1;
-	unsigned long size, start;
-	char *endp;
-
-	/*
-	 * If the user specifies memory size, we
-	 * blow away any automatically generated
-	 * size.
-	 */
-	if (usermem) {
-		usermem = 0;
-		meminfo.nr_banks = 0;
-	}
-
-	start = PHYS_OFFSET;
-	size  = memparse(p, &endp);
-	if (*endp == '@')
-		start = memparse(endp + 1, NULL);
-
-	uc32_add_memory(start, size);
-
-	return 0;
-}
-early_param("mem", early_mem);
-
-static void __init
-request_standard_resources(struct meminfo *mi)
-{
-	struct resource *res;
-	int i;
-
-	kernel_code.start   = virt_to_phys(_stext);
-	kernel_code.end     = virt_to_phys(_etext - 1);
-	kernel_data.start   = virt_to_phys(_sdata);
-	kernel_data.end     = virt_to_phys(_end - 1);
-
-	for (i = 0; i < mi->nr_banks; i++) {
-		if (mi->bank[i].size == 0)
-			continue;
-
-		res = memblock_alloc_low(sizeof(*res), SMP_CACHE_BYTES);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes align=%x\n",
-			      __func__, sizeof(*res), SMP_CACHE_BYTES);
-
-		res->name  = "System RAM";
-		res->start = mi->bank[i].start;
-		res->end   = mi->bank[i].start + mi->bank[i].size - 1;
-		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-
-		request_resource(&iomem_resource, res);
-
-		if (kernel_code.start >= res->start &&
-		    kernel_code.end <= res->end)
-			request_resource(res, &kernel_code);
-		if (kernel_data.start >= res->start &&
-		    kernel_data.end <= res->end)
-			request_resource(res, &kernel_data);
-	}
-}
-
-static void (*init_machine)(void) __initdata;
-
-static int __init customize_machine(void)
-{
-	/* customizes platform devices, or adds new ones */
-	if (init_machine)
-		init_machine();
-	return 0;
-}
-arch_initcall(customize_machine);
-
-void __init setup_arch(char **cmdline_p)
-{
-	char *from = default_command_line;
-
-	setup_processor();
-
-	init_mm.start_code = (unsigned long) _stext;
-	init_mm.end_code   = (unsigned long) _etext;
-	init_mm.end_data   = (unsigned long) _edata;
-	init_mm.brk	   = (unsigned long) _end;
-
-	/* parse_early_param needs a boot_command_line */
-	strlcpy(boot_command_line, from, COMMAND_LINE_SIZE);
-
-	/* populate cmd_line too for later use, preserving boot_command_line */
-	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
-	*cmdline_p = cmd_line;
-
-	parse_early_param();
-
-	uc32_memblock_init(&meminfo);
-
-	paging_init();
-	request_standard_resources(&meminfo);
-
-	cpu_init();
-
-	/*
-	 * Set up various architecture-specific pointers
-	 */
-	init_machine = puv3_core_init;
-
-#ifdef CONFIG_VT
-#if defined(CONFIG_VGA_CONSOLE)
-	conswitchp = &vga_con;
-#endif
-#endif
-	early_trap_init();
-}
-
-static struct cpu cpuinfo_unicore;
-
-static int __init topology_init(void)
-{
-	int i;
-
-	for_each_possible_cpu(i)
-		register_cpu(&cpuinfo_unicore, i);
-
-	return 0;
-}
-subsys_initcall(topology_init);
-
-#ifdef CONFIG_HAVE_PROC_CPU
-static int __init proc_cpu_init(void)
-{
-	struct proc_dir_entry *res;
-
-	res = proc_mkdir("cpu", NULL);
-	if (!res)
-		return -ENOMEM;
-	return 0;
-}
-fs_initcall(proc_cpu_init);
-#endif
-
-static int c_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "Processor\t: UniCore-II rev %d (%s)\n",
-		   (int)(uc32_cpuid >> 16) & 15, elf_platform);
-
-	seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
-		   loops_per_jiffy / (500000/HZ),
-		   (loops_per_jiffy / (5000/HZ)) % 100);
-
-	/* dump out the processor features */
-	seq_puts(m, "Features\t: CMOV UC-F64");
-
-	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", uc32_cpuid >> 24);
-	seq_printf(m, "CPU architecture: 2\n");
-	seq_printf(m, "CPU revision\t: %d\n", (uc32_cpuid >> 16) & 15);
-
-	seq_printf(m, "Cache type\t: write-back\n"
-			"Cache clean\t: cp0 c5 ops\n"
-			"Cache lockdown\t: not support\n"
-			"Cache format\t: Harvard\n");
-
-	seq_puts(m, "\n");
-
-	seq_printf(m, "Hardware\t: PKUnity v3\n");
-
-	return 0;
-}
-
-static void *c_start(struct seq_file *m, loff_t *pos)
-{
-	return *pos < 1 ? (void *)1 : NULL;
-}
-
-static void *c_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	++*pos;
-	return NULL;
-}
-
-static void c_stop(struct seq_file *m, void *v)
-{
-}
-
-const struct seq_operations cpuinfo_op = {
-	.start	= c_start,
-	.next	= c_next,
-	.stop	= c_stop,
-	.show	= c_show
-};
diff --git a/arch/unicore32/kernel/setup.h b/arch/unicore32/kernel/setup.h
deleted file mode 100644
index 967352323185..000000000000
--- a/arch/unicore32/kernel/setup.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/kernel/setup.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#ifndef __UNICORE_KERNEL_SETUP_H__
-#define __UNICORE_KERNEL_SETUP_H__
-
-#include <asm/hwdef-copro.h>
-
-extern void paging_init(void);
-extern void puv3_core_init(void);
-extern void cpu_init(void);
-
-extern void puv3_ps2_init(void);
-extern void pci_puv3_preinit(void);
-extern void __init puv3_init_gpio(void);
-
-extern void setup_mm_for_reboot(void);
-
-extern char __stubs_start[], __stubs_end[];
-extern char __vectors_start[], __vectors_end[];
-
-extern void kernel_thread_helper(void);
-
-extern void __init early_signal_init(void);
-
-extern asmlinkage void __backtrace(void);
-extern asmlinkage void c_backtrace(unsigned long fp, const char *loglvl);
-
-extern void __show_regs(struct pt_regs *);
-
-#endif
diff --git a/arch/unicore32/kernel/signal.c b/arch/unicore32/kernel/signal.c
deleted file mode 100644
index 3946182a835d..000000000000
--- a/arch/unicore32/kernel/signal.c
+++ /dev/null
@@ -1,424 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/signal.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/personality.h>
-#include <linux/uaccess.h>
-#include <linux/tracehook.h>
-#include <linux/elf.h>
-#include <linux/unistd.h>
-
-#include <asm/cacheflush.h>
-#include <asm/ucontext.h>
-
-/*
- * For UniCore syscalls, we encode the syscall number into the instruction.
- */
-#define SWI_SYS_SIGRETURN	(0xff000000) /* error number for new abi */
-#define SWI_SYS_RT_SIGRETURN	(0xff000000 | (__NR_rt_sigreturn))
-#define SWI_SYS_RESTART		(0xff000000 | (__NR_restart_syscall))
-
-#define KERN_SIGRETURN_CODE	(KUSER_VECPAGE_BASE + 0x00000500)
-#define KERN_RESTART_CODE	(KERN_SIGRETURN_CODE + sizeof(sigreturn_codes))
-
-const unsigned long sigreturn_codes[3] = {
-	SWI_SYS_SIGRETURN, SWI_SYS_RT_SIGRETURN,
-};
-
-const unsigned long syscall_restart_code[2] = {
-	SWI_SYS_RESTART,	/* swi	__NR_restart_syscall */
-	0x69efc004,		/* ldr	pc, [sp], #4 */
-};
-
-/*
- * Do a signal return; undo the signal stack.  These are aligned to 64-bit.
- */
-struct sigframe {
-	struct ucontext uc;
-	unsigned long retcode[2];
-};
-
-struct rt_sigframe {
-	struct siginfo info;
-	struct sigframe sig;
-};
-
-static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
-{
-	sigset_t set;
-	int err;
-
-	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
-	if (err == 0)
-		set_current_blocked(&set);
-
-	err |= __get_user(regs->UCreg_00, &sf->uc.uc_mcontext.regs.UCreg_00);
-	err |= __get_user(regs->UCreg_01, &sf->uc.uc_mcontext.regs.UCreg_01);
-	err |= __get_user(regs->UCreg_02, &sf->uc.uc_mcontext.regs.UCreg_02);
-	err |= __get_user(regs->UCreg_03, &sf->uc.uc_mcontext.regs.UCreg_03);
-	err |= __get_user(regs->UCreg_04, &sf->uc.uc_mcontext.regs.UCreg_04);
-	err |= __get_user(regs->UCreg_05, &sf->uc.uc_mcontext.regs.UCreg_05);
-	err |= __get_user(regs->UCreg_06, &sf->uc.uc_mcontext.regs.UCreg_06);
-	err |= __get_user(regs->UCreg_07, &sf->uc.uc_mcontext.regs.UCreg_07);
-	err |= __get_user(regs->UCreg_08, &sf->uc.uc_mcontext.regs.UCreg_08);
-	err |= __get_user(regs->UCreg_09, &sf->uc.uc_mcontext.regs.UCreg_09);
-	err |= __get_user(regs->UCreg_10, &sf->uc.uc_mcontext.regs.UCreg_10);
-	err |= __get_user(regs->UCreg_11, &sf->uc.uc_mcontext.regs.UCreg_11);
-	err |= __get_user(regs->UCreg_12, &sf->uc.uc_mcontext.regs.UCreg_12);
-	err |= __get_user(regs->UCreg_13, &sf->uc.uc_mcontext.regs.UCreg_13);
-	err |= __get_user(regs->UCreg_14, &sf->uc.uc_mcontext.regs.UCreg_14);
-	err |= __get_user(regs->UCreg_15, &sf->uc.uc_mcontext.regs.UCreg_15);
-	err |= __get_user(regs->UCreg_16, &sf->uc.uc_mcontext.regs.UCreg_16);
-	err |= __get_user(regs->UCreg_17, &sf->uc.uc_mcontext.regs.UCreg_17);
-	err |= __get_user(regs->UCreg_18, &sf->uc.uc_mcontext.regs.UCreg_18);
-	err |= __get_user(regs->UCreg_19, &sf->uc.uc_mcontext.regs.UCreg_19);
-	err |= __get_user(regs->UCreg_20, &sf->uc.uc_mcontext.regs.UCreg_20);
-	err |= __get_user(regs->UCreg_21, &sf->uc.uc_mcontext.regs.UCreg_21);
-	err |= __get_user(regs->UCreg_22, &sf->uc.uc_mcontext.regs.UCreg_22);
-	err |= __get_user(regs->UCreg_23, &sf->uc.uc_mcontext.regs.UCreg_23);
-	err |= __get_user(regs->UCreg_24, &sf->uc.uc_mcontext.regs.UCreg_24);
-	err |= __get_user(regs->UCreg_25, &sf->uc.uc_mcontext.regs.UCreg_25);
-	err |= __get_user(regs->UCreg_26, &sf->uc.uc_mcontext.regs.UCreg_26);
-	err |= __get_user(regs->UCreg_fp, &sf->uc.uc_mcontext.regs.UCreg_fp);
-	err |= __get_user(regs->UCreg_ip, &sf->uc.uc_mcontext.regs.UCreg_ip);
-	err |= __get_user(regs->UCreg_sp, &sf->uc.uc_mcontext.regs.UCreg_sp);
-	err |= __get_user(regs->UCreg_lr, &sf->uc.uc_mcontext.regs.UCreg_lr);
-	err |= __get_user(regs->UCreg_pc, &sf->uc.uc_mcontext.regs.UCreg_pc);
-	err |= __get_user(regs->UCreg_asr, &sf->uc.uc_mcontext.regs.UCreg_asr);
-
-	err |= !valid_user_regs(regs);
-
-	return err;
-}
-
-asmlinkage int __sys_rt_sigreturn(struct pt_regs *regs)
-{
-	struct rt_sigframe __user *frame;
-
-	/* Always make any pending restarted system calls return -EINTR */
-	current->restart_block.fn = do_no_restart_syscall;
-
-	/*
-	 * Since we stacked the signal on a 64-bit boundary,
-	 * then 'sp' should be word aligned here.  If it's
-	 * not, then the user is trying to mess with us.
-	 */
-	if (regs->UCreg_sp & 7)
-		goto badframe;
-
-	frame = (struct rt_sigframe __user *)regs->UCreg_sp;
-
-	if (!access_ok(frame, sizeof(*frame)))
-		goto badframe;
-
-	if (restore_sigframe(regs, &frame->sig))
-		goto badframe;
-
-	if (restore_altstack(&frame->sig.uc.uc_stack))
-		goto badframe;
-
-	return regs->UCreg_00;
-
-badframe:
-	force_sig(SIGSEGV);
-	return 0;
-}
-
-static int setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs,
-		sigset_t *set)
-{
-	int err = 0;
-
-	err |= __put_user(regs->UCreg_00, &sf->uc.uc_mcontext.regs.UCreg_00);
-	err |= __put_user(regs->UCreg_01, &sf->uc.uc_mcontext.regs.UCreg_01);
-	err |= __put_user(regs->UCreg_02, &sf->uc.uc_mcontext.regs.UCreg_02);
-	err |= __put_user(regs->UCreg_03, &sf->uc.uc_mcontext.regs.UCreg_03);
-	err |= __put_user(regs->UCreg_04, &sf->uc.uc_mcontext.regs.UCreg_04);
-	err |= __put_user(regs->UCreg_05, &sf->uc.uc_mcontext.regs.UCreg_05);
-	err |= __put_user(regs->UCreg_06, &sf->uc.uc_mcontext.regs.UCreg_06);
-	err |= __put_user(regs->UCreg_07, &sf->uc.uc_mcontext.regs.UCreg_07);
-	err |= __put_user(regs->UCreg_08, &sf->uc.uc_mcontext.regs.UCreg_08);
-	err |= __put_user(regs->UCreg_09, &sf->uc.uc_mcontext.regs.UCreg_09);
-	err |= __put_user(regs->UCreg_10, &sf->uc.uc_mcontext.regs.UCreg_10);
-	err |= __put_user(regs->UCreg_11, &sf->uc.uc_mcontext.regs.UCreg_11);
-	err |= __put_user(regs->UCreg_12, &sf->uc.uc_mcontext.regs.UCreg_12);
-	err |= __put_user(regs->UCreg_13, &sf->uc.uc_mcontext.regs.UCreg_13);
-	err |= __put_user(regs->UCreg_14, &sf->uc.uc_mcontext.regs.UCreg_14);
-	err |= __put_user(regs->UCreg_15, &sf->uc.uc_mcontext.regs.UCreg_15);
-	err |= __put_user(regs->UCreg_16, &sf->uc.uc_mcontext.regs.UCreg_16);
-	err |= __put_user(regs->UCreg_17, &sf->uc.uc_mcontext.regs.UCreg_17);
-	err |= __put_user(regs->UCreg_18, &sf->uc.uc_mcontext.regs.UCreg_18);
-	err |= __put_user(regs->UCreg_19, &sf->uc.uc_mcontext.regs.UCreg_19);
-	err |= __put_user(regs->UCreg_20, &sf->uc.uc_mcontext.regs.UCreg_20);
-	err |= __put_user(regs->UCreg_21, &sf->uc.uc_mcontext.regs.UCreg_21);
-	err |= __put_user(regs->UCreg_22, &sf->uc.uc_mcontext.regs.UCreg_22);
-	err |= __put_user(regs->UCreg_23, &sf->uc.uc_mcontext.regs.UCreg_23);
-	err |= __put_user(regs->UCreg_24, &sf->uc.uc_mcontext.regs.UCreg_24);
-	err |= __put_user(regs->UCreg_25, &sf->uc.uc_mcontext.regs.UCreg_25);
-	err |= __put_user(regs->UCreg_26, &sf->uc.uc_mcontext.regs.UCreg_26);
-	err |= __put_user(regs->UCreg_fp, &sf->uc.uc_mcontext.regs.UCreg_fp);
-	err |= __put_user(regs->UCreg_ip, &sf->uc.uc_mcontext.regs.UCreg_ip);
-	err |= __put_user(regs->UCreg_sp, &sf->uc.uc_mcontext.regs.UCreg_sp);
-	err |= __put_user(regs->UCreg_lr, &sf->uc.uc_mcontext.regs.UCreg_lr);
-	err |= __put_user(regs->UCreg_pc, &sf->uc.uc_mcontext.regs.UCreg_pc);
-	err |= __put_user(regs->UCreg_asr, &sf->uc.uc_mcontext.regs.UCreg_asr);
-
-	err |= __put_user(current->thread.trap_no,
-			&sf->uc.uc_mcontext.trap_no);
-	err |= __put_user(current->thread.error_code,
-			&sf->uc.uc_mcontext.error_code);
-	err |= __put_user(current->thread.address,
-			&sf->uc.uc_mcontext.fault_address);
-	err |= __put_user(set->sig[0], &sf->uc.uc_mcontext.oldmask);
-
-	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
-
-	return err;
-}
-
-static inline void __user *get_sigframe(struct k_sigaction *ka,
-		struct pt_regs *regs, int framesize)
-{
-	unsigned long sp = regs->UCreg_sp;
-	void __user *frame;
-
-	/*
-	 * This is the X/Open sanctioned signal stack switching.
-	 */
-	if ((ka->sa.sa_flags & SA_ONSTACK) && !sas_ss_flags(sp))
-		sp = current->sas_ss_sp + current->sas_ss_size;
-
-	/*
-	 * ATPCS B01 mandates 8-byte alignment
-	 */
-	frame = (void __user *)((sp - framesize) & ~7);
-
-	/*
-	 * Check that we can actually write to the signal frame.
-	 */
-	if (!access_ok(frame, framesize))
-		frame = NULL;
-
-	return frame;
-}
-
-static int setup_return(struct pt_regs *regs, struct k_sigaction *ka,
-	     unsigned long __user *rc, void __user *frame, int usig)
-{
-	unsigned long handler = (unsigned long)ka->sa.sa_handler;
-	unsigned long retcode;
-	unsigned long asr = regs->UCreg_asr & ~PSR_f;
-
-	unsigned int idx = 0;
-
-	if (ka->sa.sa_flags & SA_SIGINFO)
-		idx += 1;
-
-	if (__put_user(sigreturn_codes[idx],   rc) ||
-	    __put_user(sigreturn_codes[idx+1], rc+1))
-		return 1;
-
-	retcode = KERN_SIGRETURN_CODE + (idx << 2);
-
-	regs->UCreg_00 = usig;
-	regs->UCreg_sp = (unsigned long)frame;
-	regs->UCreg_lr = retcode;
-	regs->UCreg_pc = handler;
-	regs->UCreg_asr = asr;
-
-	return 0;
-}
-
-static int setup_frame(struct ksignal *ksig, sigset_t *set,
-		       struct pt_regs *regs)
-{
-	struct sigframe __user *frame = get_sigframe(&ksig->ka, regs, sizeof(*frame));
-	int err = 0;
-
-	if (!frame)
-		return 1;
-
-	/*
-	 * Set uc.uc_flags to a value which sc.trap_no would never have.
-	 */
-	err |= __put_user(0x5ac3c35a, &frame->uc.uc_flags);
-
-	err |= setup_sigframe(frame, regs, set);
-	if (err == 0)
-		err |= setup_return(regs, &ksig->ka, frame->retcode, frame,
-				    ksig->sig);
-
-	return err;
-}
-
-static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
-			  struct pt_regs *regs)
-{
-	struct rt_sigframe __user *frame =
-			get_sigframe(&ksig->ka, regs, sizeof(*frame));
-	int err = 0;
-
-	if (!frame)
-		return 1;
-
-	err |= copy_siginfo_to_user(&frame->info, &ksig->info);
-
-	err |= __put_user(0, &frame->sig.uc.uc_flags);
-	err |= __put_user(NULL, &frame->sig.uc.uc_link);
-	err |= __save_altstack(&frame->sig.uc.uc_stack, regs->UCreg_sp);
-	err |= setup_sigframe(&frame->sig, regs, set);
-	if (err == 0)
-		err |= setup_return(regs, &ksig->ka, frame->sig.retcode, frame,
-				    ksig->sig);
-
-	if (err == 0) {
-		/*
-		 * For realtime signals we must also set the second and third
-		 * arguments for the signal handler.
-		 */
-		regs->UCreg_01 = (unsigned long)&frame->info;
-		regs->UCreg_02 = (unsigned long)&frame->sig.uc;
-	}
-
-	return err;
-}
-
-static inline void setup_syscall_restart(struct pt_regs *regs)
-{
-	regs->UCreg_00 = regs->UCreg_ORIG_00;
-	regs->UCreg_pc -= 4;
-}
-
-/*
- * OK, we're invoking a handler
- */
-static void handle_signal(struct ksignal *ksig, struct pt_regs *regs,
-			  int syscall)
-{
-	struct thread_info *thread = current_thread_info();
-	sigset_t *oldset = sigmask_to_save();
-	int usig = ksig->sig;
-	int ret;
-
-	/*
-	 * If we were from a system call, check for system call restarting...
-	 */
-	if (syscall) {
-		switch (regs->UCreg_00) {
-		case -ERESTART_RESTARTBLOCK:
-		case -ERESTARTNOHAND:
-			regs->UCreg_00 = -EINTR;
-			break;
-		case -ERESTARTSYS:
-			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
-				regs->UCreg_00 = -EINTR;
-				break;
-			}
-			/* fallthrough */
-		case -ERESTARTNOINTR:
-			setup_syscall_restart(regs);
-		}
-	}
-
-	/*
-	 * Set up the stack frame
-	 */
-	if (ksig->ka.sa.sa_flags & SA_SIGINFO)
-		ret = setup_rt_frame(ksig, oldset, regs);
-	else
-		ret = setup_frame(ksig, oldset, regs);
-
-	/*
-	 * Check that the resulting registers are actually sane.
-	 */
-	ret |= !valid_user_regs(regs);
-
-	signal_setup_done(ret, ksig, 0);
-}
-
-/*
- * Note that 'init' is a special process: it doesn't get signals it doesn't
- * want to handle. Thus you cannot kill init even with a SIGKILL even by
- * mistake.
- *
- * Note that we go through the signals twice: once to check the signals that
- * the kernel can handle, and then we build all the user-level signal handling
- * stack-frames in one go after that.
- */
-static void do_signal(struct pt_regs *regs, int syscall)
-{
-	struct ksignal ksig;
-
-	/*
-	 * We want the common case to go fast, which
-	 * is why we may in certain cases get here from
-	 * kernel mode. Just return without doing anything
-	 * if so.
-	 */
-	if (!user_mode(regs))
-		return;
-
-	if (get_signal(&ksig)) {
-		handle_signal(&ksig, regs, syscall);
-		return;
-	}
-
-	/*
-	 * No signal to deliver to the process - restart the syscall.
-	 */
-	if (syscall) {
-		if (regs->UCreg_00 == -ERESTART_RESTARTBLOCK) {
-				u32 __user *usp;
-
-				regs->UCreg_sp -= 4;
-				usp = (u32 __user *)regs->UCreg_sp;
-
-				if (put_user(regs->UCreg_pc, usp) == 0) {
-					regs->UCreg_pc = KERN_RESTART_CODE;
-				} else {
-					regs->UCreg_sp += 4;
-					force_sigsegv(0);
-				}
-		}
-		if (regs->UCreg_00 == -ERESTARTNOHAND ||
-		    regs->UCreg_00 == -ERESTARTSYS ||
-		    regs->UCreg_00 == -ERESTARTNOINTR) {
-			setup_syscall_restart(regs);
-		}
-	}
-	/* If there's no signal to deliver, we just put the saved
-	 * sigmask back.
-	 */
-	restore_saved_sigmask();
-}
-
-asmlinkage void do_notify_resume(struct pt_regs *regs,
-		unsigned int thread_flags, int syscall)
-{
-	if (thread_flags & _TIF_SIGPENDING)
-		do_signal(regs, syscall);
-
-	if (thread_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-	}
-}
-
-/*
- * Copy signal return handlers into the vector page, and
- * set sigreturn to be a pointer to these.
- */
-void __init early_signal_init(void)
-{
-	memcpy((void *)kuser_vecpage_to_vectors(KERN_SIGRETURN_CODE),
-			sigreturn_codes, sizeof(sigreturn_codes));
-	memcpy((void *)kuser_vecpage_to_vectors(KERN_RESTART_CODE),
-			syscall_restart_code, sizeof(syscall_restart_code));
-	/* Need not to flush icache, since early_trap_init will do it last. */
-}
diff --git a/arch/unicore32/kernel/sleep.S b/arch/unicore32/kernel/sleep.S
deleted file mode 100644
index 23151abe53c6..000000000000
--- a/arch/unicore32/kernel/sleep.S
+++ /dev/null
@@ -1,199 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/kernel/sleep.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <mach/hardware.h>
-
-		.text
-
-pkunity_cpu_save_cp:
-
-	@ get coprocessor registers
-
-	movc	r3, p0.c7, #0			@ PID
-	movc	r4, p0.c2, #0			@ translation table base addr
-	movc	r5, p0.c1, #0			@ control reg
-
-
-	@ store them plus current virtual stack ptr on stack
-	mov	r6, sp
-	stm.w	(r3 - r6), [sp-]
-
-	mov	pc, lr
-
-pkunity_cpu_save_sp:
-	@ preserve phys address of stack
-	mov	r0, sp
-	stw.w	lr, [sp+], #-4
-	b.l	sleep_phys_sp
-	ldw	r1, =sleep_save_sp
-	stw	r0, [r1]
-	ldw.w	pc, [sp]+, #4
-
-/*
- * puv3_cpu_suspend()
- *
- * Forces CPU into sleep state.
- *
- * r0 = value for PWRMODE M field for desired sleep state
- */
-
-ENTRY(puv3_cpu_suspend)
-	stm.w	(r16 - r27, lr), [sp-]		@ save registers on stack
-	stm.w	(r4 - r15), [sp-]		@ save registers on stack
-
-#ifdef	CONFIG_UNICORE_FPU_F64
-	sfm.w	(f0  - f7 ), [sp-]
-	sfm.w	(f8  - f15), [sp-]
-	sfm.w	(f16 - f23), [sp-]
-	sfm.w	(f24 - f31), [sp-]
-	cff	r4, s31
-	stm.w	(r4), [sp-]
-#endif
-	b.l	pkunity_cpu_save_cp
-
-	b.l	pkunity_cpu_save_sp
-
-	@ clean data cache
-	mov	r1, #0
-	movc	p0.c5, r1, #14
-	nop
-	nop
-	nop
-	nop
-
-
-
-	@ DDR2 BaseAddr
-	ldw	r0, =(PKUNITY_DDR2CTRL_BASE)
-
-	@ PM BaseAddr
-	ldw	r1, =(PKUNITY_PM_BASE)
-
-	@ set PLL_SYS_CFG reg, 275
-	movl	r6, #0x00002401
-	stw	r6, [r1+], #0x18
-	@ set PLL_DDR_CFG reg, 66MHz
-	movl	r6, #0x00100c00
-	stw	r6, [r1+], #0x1c
-
-	@ set wake up source
-	movl	r8, #0x800001ff		@ epip4d
-	stw	r8, [r1+], #0xc
-
-	@ set PGSR
-	movl	r5, #0x40000
-	stw	r5, [r1+], #0x10
-
-	@ prepare DDR2 refresh settings
-	ldw	r5, [r0+], #0x24
-	or	r5, r5, #0x00000001
-
-	@ prepare PMCR for PLL changing
-	movl	r6, #0xc
-
-	@ prepare for closing PLL
-	movl	r7, #0x1
-
-	@ prepare sleep mode
-	mov	r8, #0x1
-
-@	movl	r0, 0x11111111
-@	put_word_ocd r0
-	b	pkunity_cpu_do_suspend
-
-	.ltorg
-	.align	5
-pkunity_cpu_do_suspend:
-	b	101f
-	@ put DDR2 into self-refresh
-100:	stw	r5, [r0+], #0x24
-	@ change PLL
-	stw	r6, [r1]
-	b	1f
-
-	.ltorg
-	.align	5
-101:	b	102f
-	@ wait for PLL changing complete
-1:	ldw	r6, [r1+], #0x44
-	csub.a	r6, #0x1
-	bne	1b
-	b	2f
-
-	.ltorg
-	.align	5
-102:	b	100b
-	@ close PLL
-2:	stw	r7, [r1+], #0x4
-	@ enter sleep mode
-	stw	r8, [r1]
-3:	b	3b
-
-
-
-
-/*
- * puv3_cpu_resume()
- *
- * entry point from bootloader into kernel during resume
- *
- * Note: Yes, part of the following code is located into the .data section.
- *       This is to allow sleep_save_sp to be accessed with a relative load
- *       while we can't rely on any MMU translation.  We could have put
- *       sleep_save_sp in the .text section as well, but some setups might
- *       insist on it to be truly read-only.
- */
-
-	.data
-	.align 5
-ENTRY(puv3_cpu_resume)
-@	movl	r0, 0x20202020
-@	put_word_ocd r0
-
-	ldw	r0, sleep_save_sp		@ stack phys addr
-	ldw	r2, =resume_after_mmu		@ its absolute virtual address
-	ldm	(r3 - r6), [r0]+		@ CP regs + virt stack ptr
-	mov	sp, r6				@ CP regs + virt stack ptr
-
-	mov	r1, #0
-	movc	p0.c6, r1, #6			@ invalidate I & D TLBs
-	movc	p0.c5, r1, #28			@ invalidate I & D caches, BTB
-
-	movc	p0.c7, r3, #0			@ PID
-	movc	p0.c2, r4, #0			@ translation table base addr
-	movc	p0.c1, r5, #0			@ control reg, turn on mmu
-	nop
-	jump	r2
-	nop
-	nop
-	nop
-	nop
-	nop
-
-sleep_save_sp:
-	.word	0				@ preserve stack phys ptr here
-
-	.text
-resume_after_mmu:
-@	movl	r0, 0x30303030
-@	put_word_ocd r0
-
-#ifdef	CONFIG_UNICORE_FPU_F64
-	lfm.w	(f0  - f7 ), [sp]+
-	lfm.w	(f8  - f15), [sp]+
-	lfm.w	(f16 - f23), [sp]+
-	lfm.w	(f24 - f31), [sp]+
-	ldm.w	(r4), [sp]+
-	ctf	r4, s31
-#endif
-	ldm.w	(r4 - r15), [sp]+		@ restore registers from stack
-	ldm.w	(r16 - r27, pc), [sp]+		@ return to caller
diff --git a/arch/unicore32/kernel/stacktrace.c b/arch/unicore32/kernel/stacktrace.c
deleted file mode 100644
index c9d8650e9d78..000000000000
--- a/arch/unicore32/kernel/stacktrace.c
+++ /dev/null
@@ -1,127 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/stacktrace.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
-#include <linux/stacktrace.h>
-
-#include <asm/stacktrace.h>
-
-#if defined(CONFIG_FRAME_POINTER)
-/*
- * Unwind the current stack frame and store the new register values in the
- * structure passed as argument. Unwinding is equivalent to a function return,
- * hence the new PC value rather than LR should be used for backtrace.
- *
- * With framepointer enabled, a simple function prologue looks like this:
- *	mov	ip, sp
- *	stmdb	sp!, {fp, ip, lr, pc}
- *	sub	fp, ip, #4
- *
- * A simple function epilogue looks like this:
- *	ldm	sp, {fp, sp, pc}
- *
- * Note that with framepointer enabled, even the leaf functions have the same
- * prologue and epilogue, therefore we can ignore the LR value in this case.
- */
-int notrace unwind_frame(struct stackframe *frame)
-{
-	unsigned long high, low;
-	unsigned long fp = frame->fp;
-
-	/* only go to a higher address on the stack */
-	low = frame->sp;
-	high = ALIGN(low, THREAD_SIZE);
-
-	/* check current frame pointer is within bounds */
-	if (fp < (low + 12) || fp + 4 >= high)
-		return -EINVAL;
-
-	/* restore the registers from the stack frame */
-	frame->fp = *(unsigned long *)(fp - 12);
-	frame->sp = *(unsigned long *)(fp - 8);
-	frame->pc = *(unsigned long *)(fp - 4);
-
-	return 0;
-}
-#endif
-
-void notrace walk_stackframe(struct stackframe *frame,
-		     int (*fn)(struct stackframe *, void *), void *data)
-{
-	while (1) {
-		int ret;
-
-		if (fn(frame, data))
-			break;
-		ret = unwind_frame(frame);
-		if (ret < 0)
-			break;
-	}
-}
-EXPORT_SYMBOL(walk_stackframe);
-
-#ifdef CONFIG_STACKTRACE
-struct stack_trace_data {
-	struct stack_trace *trace;
-	unsigned int no_sched_functions;
-	unsigned int skip;
-};
-
-static int save_trace(struct stackframe *frame, void *d)
-{
-	struct stack_trace_data *data = d;
-	struct stack_trace *trace = data->trace;
-	unsigned long addr = frame->pc;
-
-	if (data->no_sched_functions && in_sched_functions(addr))
-		return 0;
-	if (data->skip) {
-		data->skip--;
-		return 0;
-	}
-
-	trace->entries[trace->nr_entries++] = addr;
-
-	return trace->nr_entries >= trace->max_entries;
-}
-
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
-{
-	struct stack_trace_data data;
-	struct stackframe frame;
-
-	data.trace = trace;
-	data.skip = trace->skip;
-
-	if (tsk != current) {
-		data.no_sched_functions = 1;
-		frame.fp = thread_saved_fp(tsk);
-		frame.sp = thread_saved_sp(tsk);
-		frame.lr = 0;		/* recovered from the stack */
-		frame.pc = thread_saved_pc(tsk);
-	} else {
-		register unsigned long current_sp asm("sp");
-
-		data.no_sched_functions = 0;
-		frame.fp = (unsigned long)__builtin_frame_address(0);
-		frame.sp = current_sp;
-		frame.lr = (unsigned long)__builtin_return_address(0);
-		frame.pc = (unsigned long)save_stack_trace_tsk;
-	}
-
-	walk_stackframe(&frame, save_trace, &data);
-}
-
-void save_stack_trace(struct stack_trace *trace)
-{
-	save_stack_trace_tsk(current, trace);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
-#endif
diff --git a/arch/unicore32/kernel/sys.c b/arch/unicore32/kernel/sys.c
deleted file mode 100644
index 256fb4082296..000000000000
--- a/arch/unicore32/kernel/sys.c
+++ /dev/null
@@ -1,37 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/sys.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/mm.h>
-#include <linux/sem.h>
-#include <linux/msg.h>
-#include <linux/shm.h>
-#include <linux/stat.h>
-#include <linux/syscalls.h>
-#include <linux/mman.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/ipc.h>
-#include <linux/uaccess.h>
-
-#include <asm/syscalls.h>
-#include <asm/cacheflush.h>
-
-/* Provide the actual syscall number to call mapping. */
-#undef __SYSCALL
-#define __SYSCALL(nr, call)	[nr] = (call),
-
-#define sys_mmap2 sys_mmap_pgoff
-/* Note that we don't include <linux/unistd.h> but <asm/unistd.h> */
-void *sys_call_table[__NR_syscalls] = {
-	[0 ... __NR_syscalls-1] = sys_ni_syscall,
-#include <asm/unistd.h>
-};
diff --git a/arch/unicore32/kernel/time.c b/arch/unicore32/kernel/time.c
deleted file mode 100644
index c3a37edf4d40..000000000000
--- a/arch/unicore32/kernel/time.c
+++ /dev/null
@@ -1,128 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/time.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- *	Maintained by GUAN Xue-tao <gxt@mprc.pku.edu.cn>
- *	Copyright (C) 2001-2010 Guan Xuetao
- */
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/timex.h>
-#include <linux/clockchips.h>
-
-#include <mach/hardware.h>
-
-#define MIN_OSCR_DELTA 2
-
-static irqreturn_t puv3_ost0_interrupt(int irq, void *dev_id)
-{
-	struct clock_event_device *c = dev_id;
-
-	/* Disarm the compare/match, signal the event. */
-	writel(readl(OST_OIER) & ~OST_OIER_E0, OST_OIER);
-	writel(readl(OST_OSSR) & ~OST_OSSR_M0, OST_OSSR);
-	c->event_handler(c);
-
-	return IRQ_HANDLED;
-}
-
-static int
-puv3_osmr0_set_next_event(unsigned long delta, struct clock_event_device *c)
-{
-	unsigned long next, oscr;
-
-	writel(readl(OST_OIER) | OST_OIER_E0, OST_OIER);
-	next = readl(OST_OSCR) + delta;
-	writel(next, OST_OSMR0);
-	oscr = readl(OST_OSCR);
-
-	return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0;
-}
-
-static int puv3_osmr0_shutdown(struct clock_event_device *evt)
-{
-	writel(readl(OST_OIER) & ~OST_OIER_E0, OST_OIER);
-	writel(readl(OST_OSSR) & ~OST_OSSR_M0, OST_OSSR);
-	return 0;
-}
-
-static struct clock_event_device ckevt_puv3_osmr0 = {
-	.name			= "osmr0",
-	.features		= CLOCK_EVT_FEAT_ONESHOT,
-	.rating			= 200,
-	.set_next_event		= puv3_osmr0_set_next_event,
-	.set_state_shutdown	= puv3_osmr0_shutdown,
-	.set_state_oneshot	= puv3_osmr0_shutdown,
-};
-
-static u64 puv3_read_oscr(struct clocksource *cs)
-{
-	return readl(OST_OSCR);
-}
-
-static struct clocksource cksrc_puv3_oscr = {
-	.name		= "oscr",
-	.rating		= 200,
-	.read		= puv3_read_oscr,
-	.mask		= CLOCKSOURCE_MASK(32),
-	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-void __init time_init(void)
-{
-	writel(0, OST_OIER);		/* disable any timer interrupts */
-	writel(0, OST_OSSR);		/* clear status on all timers */
-
-	clockevents_calc_mult_shift(&ckevt_puv3_osmr0, CLOCK_TICK_RATE, 5);
-
-	ckevt_puv3_osmr0.max_delta_ns =
-		clockevent_delta2ns(0x7fffffff, &ckevt_puv3_osmr0);
-	ckevt_puv3_osmr0.max_delta_ticks = 0x7fffffff;
-	ckevt_puv3_osmr0.min_delta_ns =
-		clockevent_delta2ns(MIN_OSCR_DELTA * 2, &ckevt_puv3_osmr0) + 1;
-	ckevt_puv3_osmr0.min_delta_ticks = MIN_OSCR_DELTA * 2;
-	ckevt_puv3_osmr0.cpumask = cpumask_of(0);
-
-	if (request_irq(IRQ_TIMER0, puv3_ost0_interrupt,
-			IRQF_TIMER | IRQF_IRQPOLL, "ost0", &ckevt_puv3_osmr0))
-		pr_err("Failed to register ost0 interrupt\n");
-
-	clocksource_register_hz(&cksrc_puv3_oscr, CLOCK_TICK_RATE);
-	clockevents_register_device(&ckevt_puv3_osmr0);
-}
-
-#ifdef CONFIG_PM
-unsigned long osmr[4], oier;
-
-void puv3_timer_suspend(void)
-{
-	osmr[0] = readl(OST_OSMR0);
-	osmr[1] = readl(OST_OSMR1);
-	osmr[2] = readl(OST_OSMR2);
-	osmr[3] = readl(OST_OSMR3);
-	oier = readl(OST_OIER);
-}
-
-void puv3_timer_resume(void)
-{
-	writel(0, OST_OSSR);
-	writel(osmr[0], OST_OSMR0);
-	writel(osmr[1], OST_OSMR1);
-	writel(osmr[2], OST_OSMR2);
-	writel(osmr[3], OST_OSMR3);
-	writel(oier, OST_OIER);
-
-	/*
-	 * OSMR0 is the system timer: make sure OSCR is sufficiently behind
-	 */
-	writel(readl(OST_OSMR0) - LATCH, OST_OSCR);
-}
-#else
-void puv3_timer_suspend(void) { };
-void puv3_timer_resume(void) { };
-#endif
-
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
deleted file mode 100644
index a3ac01df1a2e..000000000000
--- a/arch/unicore32/kernel/traps.c
+++ /dev/null
@@ -1,322 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/kernel/traps.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  'traps.c' handles hardware exceptions after we have saved some state.
- *  Mostly a debugging aid, but will probably kill the offending process.
- */
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/debug.h>
-#include <linux/sched/task_stack.h>
-#include <linux/spinlock.h>
-#include <linux/personality.h>
-#include <linux/kallsyms.h>
-#include <linux/kdebug.h>
-#include <linux/uaccess.h>
-#include <linux/delay.h>
-#include <linux/hardirq.h>
-#include <linux/init.h>
-#include <linux/atomic.h>
-#include <linux/unistd.h>
-
-#include <asm/cacheflush.h>
-#include <asm/traps.h>
-
-#include "setup.h"
-
-static void dump_mem(const char *, const char *, unsigned long, unsigned long);
-
-void dump_backtrace_entry(unsigned long where,
-		unsigned long from, unsigned long frame)
-{
-#ifdef CONFIG_KALLSYMS
-	printk(KERN_DEFAULT "[<%08lx>] (%pS) from [<%08lx>] (%pS)\n",
-			where, (void *)where, from, (void *)from);
-#else
-	printk(KERN_DEFAULT "Function entered at [<%08lx>] from [<%08lx>]\n",
-			where, from);
-#endif
-}
-
-/*
- * Stack pointers should always be within the kernels view of
- * physical memory.  If it is not there, then we can't dump
- * out any information relating to the stack.
- */
-static int verify_stack(unsigned long sp)
-{
-	if (sp < PAGE_OFFSET ||
-	    (sp > (unsigned long)high_memory && high_memory != NULL))
-		return -EFAULT;
-
-	return 0;
-}
-
-/*
- * Dump out the contents of some memory nicely...
- */
-static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
-		     unsigned long top)
-{
-	unsigned long first;
-	mm_segment_t fs;
-	int i;
-
-	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
-	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-
-	printk(KERN_DEFAULT "%s%s(0x%08lx to 0x%08lx)\n",
-			lvl, str, bottom, top);
-
-	for (first = bottom & ~31; first < top; first += 32) {
-		unsigned long p;
-		char str[sizeof(" 12345678") * 8 + 1];
-
-		memset(str, ' ', sizeof(str));
-		str[sizeof(str) - 1] = '\0';
-
-		for (p = first, i = 0; i < 8 && p < top; i++, p += 4) {
-			if (p >= bottom && p < top) {
-				unsigned long val;
-				if (__get_user(val, (unsigned long *)p) == 0)
-					sprintf(str + i * 9, " %08lx", val);
-				else
-					sprintf(str + i * 9, " ????????");
-			}
-		}
-		printk(KERN_DEFAULT "%s%04lx:%s\n", lvl, first & 0xffff, str);
-	}
-
-	set_fs(fs);
-}
-
-static void dump_instr(const char *lvl, struct pt_regs *regs)
-{
-	unsigned long addr = instruction_pointer(regs);
-	const int width = 8;
-	mm_segment_t fs;
-	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
-	int i;
-
-	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
-	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-
-	for (i = -4; i < 1; i++) {
-		unsigned int val, bad;
-
-		bad = __get_user(val, &((u32 *)addr)[i]);
-
-		if (!bad)
-			p += sprintf(p, i == 0 ? "(%0*x) " : "%0*x ",
-					width, val);
-		else {
-			p += sprintf(p, "bad PC value");
-			break;
-		}
-	}
-	printk(KERN_DEFAULT "%sCode: %s\n", lvl, str);
-
-	set_fs(fs);
-}
-
-static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
-			   const char *loglvl)
-{
-	unsigned int fp;
-	int ok = 1;
-
-	printk("%sBacktrace: ", loglvl);
-
-	if (!tsk)
-		tsk = current;
-
-	if (regs)
-		fp = regs->UCreg_fp;
-	else if (tsk != current)
-		fp = thread_saved_fp(tsk);
-	else
-		asm("mov %0, fp" : "=r" (fp) : : "cc");
-
-	if (!fp) {
-		printk("%sno frame pointer", loglvl);
-		ok = 0;
-	} else if (verify_stack(fp)) {
-		printk("%sinvalid frame pointer 0x%08x", loglvl, fp);
-		ok = 0;
-	} else if (fp < (unsigned long)end_of_stack(tsk))
-		printk("%sframe pointer underflow", loglvl);
-	printk("%s\n", loglvl);
-
-	if (ok)
-		c_backtrace(fp, loglvl);
-}
-
-void show_stack(struct task_struct *tsk, unsigned long *sp,
-		       const char *loglvl)
-{
-	dump_backtrace(NULL, tsk, loglvl);
-	barrier();
-}
-
-static int __die(const char *str, int err, struct thread_info *thread,
-		struct pt_regs *regs)
-{
-	struct task_struct *tsk = thread->task;
-	static int die_counter;
-	int ret;
-
-	printk(KERN_EMERG "Internal error: %s: %x [#%d]\n",
-	       str, err, ++die_counter);
-
-	/* trap and error numbers are mostly meaningless on UniCore */
-	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, \
-			SIGSEGV);
-	if (ret == NOTIFY_STOP)
-		return ret;
-
-	print_modules();
-	__show_regs(regs);
-	printk(KERN_EMERG "Process %.*s (pid: %d, stack limit = 0x%p)\n",
-		TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1);
-
-	if (!user_mode(regs) || in_interrupt()) {
-		dump_mem(KERN_EMERG, "Stack: ", regs->UCreg_sp,
-			 THREAD_SIZE + (unsigned long)task_stack_page(tsk));
-		dump_backtrace(regs, tsk, KERN_EMERG);
-		dump_instr(KERN_EMERG, regs);
-	}
-
-	return ret;
-}
-
-DEFINE_SPINLOCK(die_lock);
-
-/*
- * This function is protected against re-entrancy.
- */
-void die(const char *str, struct pt_regs *regs, int err)
-{
-	struct thread_info *thread = current_thread_info();
-	int ret;
-
-	oops_enter();
-
-	spin_lock_irq(&die_lock);
-	console_verbose();
-	bust_spinlocks(1);
-	ret = __die(str, err, thread, regs);
-
-	bust_spinlocks(0);
-	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
-	spin_unlock_irq(&die_lock);
-	oops_exit();
-
-	if (in_interrupt())
-		panic("Fatal exception in interrupt");
-	if (panic_on_oops)
-		panic("Fatal exception");
-	if (ret != NOTIFY_STOP)
-		do_exit(SIGSEGV);
-}
-
-void uc32_notify_die(const char *str, struct pt_regs *regs,
-		int sig, int code, void __user *addr,
-		unsigned long err, unsigned long trap)
-{
-	if (user_mode(regs)) {
-		current->thread.error_code = err;
-		current->thread.trap_no = trap;
-
-		force_sig_fault(sig, code, addr);
-	} else
-		die(str, regs, err);
-}
-
-/*
- * bad_mode handles the impossible case in the vectors.  If you see one of
- * these, then it's extremely serious, and could mean you have buggy hardware.
- * It never returns, and never tries to sync.  We hope that we can at least
- * dump out some state information...
- */
-asmlinkage void bad_mode(struct pt_regs *regs, unsigned int reason)
-{
-	console_verbose();
-
-	printk(KERN_CRIT "Bad mode detected with reason 0x%x\n", reason);
-
-	die("Oops - bad mode", regs, 0);
-	local_irq_disable();
-	panic("bad mode");
-}
-
-void __pte_error(const char *file, int line, unsigned long val)
-{
-	printk(KERN_DEFAULT "%s:%d: bad pte %08lx.\n", file, line, val);
-}
-
-void __pmd_error(const char *file, int line, unsigned long val)
-{
-	printk(KERN_DEFAULT "%s:%d: bad pmd %08lx.\n", file, line, val);
-}
-
-void __pgd_error(const char *file, int line, unsigned long val)
-{
-	printk(KERN_DEFAULT "%s:%d: bad pgd %08lx.\n", file, line, val);
-}
-
-asmlinkage void __div0(void)
-{
-	printk(KERN_DEFAULT "Division by zero in kernel.\n");
-	dump_stack();
-}
-EXPORT_SYMBOL(__div0);
-
-void abort(void)
-{
-	BUG();
-
-	/* if that doesn't kill us, halt */
-	panic("Oops failed to kill thread");
-}
-
-void __init trap_init(void)
-{
-	return;
-}
-
-void __init early_trap_init(void)
-{
-	unsigned long vectors = VECTORS_BASE;
-
-	/*
-	 * Copy the vectors, stubs (in entry-unicore.S)
-	 * into the vector page, mapped at 0xffff0000, and ensure these
-	 * are visible to the instruction stream.
-	 */
-	memcpy((void *)vectors,
-			__vectors_start,
-			__vectors_end - __vectors_start);
-	memcpy((void *)vectors + 0x200,
-			__stubs_start,
-			__stubs_end - __stubs_start);
-
-	early_signal_init();
-
-	flush_icache_range(vectors, vectors + PAGE_SIZE);
-}
diff --git a/arch/unicore32/kernel/vmlinux.lds.S b/arch/unicore32/kernel/vmlinux.lds.S
deleted file mode 100644
index 6fb320b337ef..000000000000
--- a/arch/unicore32/kernel/vmlinux.lds.S
+++ /dev/null
@@ -1,59 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/kernel/vmlinux.lds.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/thread_info.h>
-#include <asm/memory.h>
-#include <asm/page.h>
-#include <asm/cache.h>
-
-OUTPUT_ARCH(unicore32)
-ENTRY(stext)
-
-jiffies = jiffies_64;
-
-SECTIONS
-{
-	. = PAGE_OFFSET + KERNEL_IMAGE_START;
-
-	_text = .;
-	__init_begin = .;
-	HEAD_TEXT_SECTION
-	INIT_TEXT_SECTION(PAGE_SIZE)
-	INIT_DATA_SECTION(16)
-	PERCPU_SECTION(L1_CACHE_BYTES)
-	__init_end = .;
-
-	_stext = .;
-	.text : {		/* Real text segment */
-		TEXT_TEXT
-		SCHED_TEXT
-		CPUIDLE_TEXT
-		LOCK_TEXT
-
-		*(.fixup)
-		*(.gnu.warning)
-	}
-	_etext = .;
-
-	_sdata = .;
-	RO_DATA(PAGE_SIZE)
-	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
-	_edata = .;
-
-	EXCEPTION_TABLE(L1_CACHE_BYTES)
-
-	BSS_SECTION(0, 0, 0)
-	_end = .;
-
-	STABS_DEBUG
-	DWARF_DEBUG
-
-	DISCARDS		/* Exit code and data */
-}
diff --git a/arch/unicore32/lib/Makefile b/arch/unicore32/lib/Makefile
deleted file mode 100644
index 5af06645b8f0..000000000000
--- a/arch/unicore32/lib/Makefile
+++ /dev/null
@@ -1,28 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# linux/arch/unicore32/lib/Makefile
-#
-# Copyright (C) 2001-2010 GUAN Xue-tao
-#
-
-lib-y	:= backtrace.o delay.o findbit.o
-lib-y	+= strncpy_from_user.o strnlen_user.o
-lib-y	+= clear_user.o copy_page.o
-lib-y	+= copy_from_user.o copy_to_user.o
-
-GNU_LIBC_A		= $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libc.a)
-GNU_LIBC_A_OBJS		:= memchr.o memcpy.o memmove.o memset.o
-GNU_LIBC_A_OBJS		+= strchr.o strrchr.o
-GNU_LIBC_A_OBJS		+= rawmemchr.o			# needed by strrchr.o
-
-GNU_LIBGCC_A		= $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libgcc.a)
-GNU_LIBGCC_A_OBJS	:= _ashldi3.o _ashrdi3.o _lshrdi3.o
-GNU_LIBGCC_A_OBJS	+= _divsi3.o _modsi3.o _ucmpdi2.o _umodsi3.o _udivsi3.o
-
-lib-y	+= $(GNU_LIBC_A_OBJS) $(GNU_LIBGCC_A_OBJS)
-
-$(addprefix $(obj)/, $(GNU_LIBC_A_OBJS)):
-	$(Q)$(AR) p $(GNU_LIBC_A) $(notdir $@) > $@
-
-$(addprefix $(obj)/, $(GNU_LIBGCC_A_OBJS)):
-	$(Q)$(AR) p $(GNU_LIBGCC_A) $(notdir $@) > $@
diff --git a/arch/unicore32/lib/backtrace.S b/arch/unicore32/lib/backtrace.S
deleted file mode 100644
index 6221944b81f3..000000000000
--- a/arch/unicore32/lib/backtrace.S
+++ /dev/null
@@ -1,168 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/backtrace.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-		.text
-
-@ fp is 0 or stack frame
-
-#define frame	v4
-#define sv_fp	v5
-#define sv_pc	v6
-#define offset	v8
-#define loglvl	v9
-
-ENTRY(__backtrace)
-		mov	r0, fp
-
-ENTRY(c_backtrace)
-
-#if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK)
-		mov	pc, lr
-ENDPROC(__backtrace)
-ENDPROC(c_backtrace)
-#else
-		stm.w	(v4 - v10, lr), [sp-]	@ Save an extra register
-						@ so we have a location...
-		mov.a	frame, r0		@ if frame pointer is zero
-		beq	no_frame		@ we have no stack frames
-		mov	loglvl, r1
-
-1:		stm.w	(pc), [sp-]		@ calculate offset of PC stored
-		ldw.w	r0, [sp]+, #4		@ by stmfd for this CPU
-		adr	r1, 1b
-		sub	offset, r0, r1
-
-/*
- * Stack frame layout:
- *             optionally saved caller registers (r4 - r10)
- *             saved fp
- *             saved sp
- *             saved lr
- *    frame => saved pc
- *             optionally saved arguments (r0 - r3)
- * saved sp => <next word>
- *
- * Functions start with the following code sequence:
- *                  mov   ip, sp
- *                  stm.w (r0 - r3), [sp-] (optional)
- * corrected pc =>  stm.w sp, (..., fp, ip, lr, pc)
- */
-for_each_frame:
-
-1001:		ldw	sv_pc, [frame+], #0	@ get saved pc
-1002:		ldw	sv_fp, [frame+], #-12	@ get saved fp
-
-		sub	sv_pc, sv_pc, offset	@ Correct PC for prefetching
-
-1003:		ldw	r2, [sv_pc+], #-4	@ if stmfd sp, {args} exists,
-		ldw	r3, .Ldsi+4		@ adjust saved 'pc' back one
-		cxor.a	r3, r2 >> #14		@ instruction
-		beq	201f
-		sub	r0, sv_pc, #4		@ allow for mov
-		b	202f
-201:
-		sub	r0, sv_pc, #8		@ allow for mov + stmia
-202:
-		ldw	r1, [frame+], #-4	@ get saved lr
-		mov	r2, frame
-		b.l	dump_backtrace_entry
-
-		ldw	r1, [sv_pc+], #-4	@ if stmfd sp, {args} exists,
-		ldw	r3, .Ldsi+4
-		cxor.a	r3, r1 >> #14
-		bne	1004f
-		ldw	r0, [frame+], #-8	@ get sp
-		sub	r0, r0, #4		@ point at the last arg
-		b.l	.Ldumpstm		@ dump saved registers
-
-1004:		ldw	r1, [sv_pc+], #0	@ if stmfd {, fp, ip, lr, pc}
-		ldw	r3, .Ldsi		@ instruction exists,
-		cxor.a	r3, r1 >> #14
-		bne	201f
-		sub	r0, frame, #16
-		b.l	.Ldumpstm		@ dump saved registers
-201:
-		cxor.a	sv_fp, #0		@ zero saved fp means
-		beq	no_frame		@ no further frames
-
-		csub.a	sv_fp, frame		@ next frame must be
-		mov	frame, sv_fp		@ above the current frame
-		bua	for_each_frame
-
-1006:		adr	r0, .Lbad
-		mov	r1, loglvl
-		mov	r2, frame
-		b.l	printk
-no_frame:	ldm.w	(v4 - v10, pc), [sp]+
-ENDPROC(__backtrace)
-ENDPROC(c_backtrace)
-
-		.pushsection __ex_table,"a"
-		.align	3
-		.long	1001b, 1006b
-		.long	1002b, 1006b
-		.long	1003b, 1006b
-		.long	1004b, 1006b
-		.popsection
-
-#define instr v4
-#define reg   v5
-#define stack v6
-
-.Ldumpstm:	stm.w	(instr, reg, stack, v7, lr), [sp-]
-		mov	stack, r0
-		mov	instr, r1
-		mov	reg, #14
-		mov	v7, #0
-1:		mov	r3, #1
-		csub.a	reg, #8
-		bne	201f
-		sub	reg, reg, #3
-201:
-		cand.a	instr, r3 << reg
-		beq	2f
-		add	v7, v7, #1
-		cxor.a	v7, #6
-		cmoveq	v7, #1
-		bne	201f
-		adr	r0, .Lcr
-		mov	r1, loglvl
-		b.l	printk
-201:
-		ldw.w	r3, [stack]+, #-4
-		mov	r2, reg
-		csub.a	r2, #8
-		bsl	201f
-		sub	r2, r2, #3
-201:
-		cand.a	instr, #0x40		@ if H is 1, high 16 regs
-		beq	201f
-		add	r2, r2, #0x10		@ so r2 need add 16
-201:
-		adr	r0, .Lfp
-		mov	r1, loglvl
-		b.l	printk
-2:		sub.a	reg, reg, #1
-		bns	1b
-		cxor.a	v7, #0
-		beq	201f
-		adr	r0, .Lcr
-		mov	r1, loglvl
-		b.l	printk
-201:		ldm.w	(instr, reg, stack, v7, pc), [sp]+
-
-.Lfp:		.asciz	"%sr%d:%08x "
-.Lcr:		.asciz	"%s\n"
-.Lbad:		.asciz	"%sBacktrace aborted due to bad frame pointer <%p>\n"
-		.align
-.Ldsi:		.word	0x92eec000 >> 14	@ stm.w sp, (... fp, ip, lr, pc)
-		.word	0x92e10000 >> 14	@ stm.w sp, ()
-
-#endif
diff --git a/arch/unicore32/lib/clear_user.S b/arch/unicore32/lib/clear_user.S
deleted file mode 100644
index c6ca431b1090..000000000000
--- a/arch/unicore32/lib/clear_user.S
+++ /dev/null
@@ -1,54 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/clear_user.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-		.text
-
-/* Prototype: int __clear_user(void *addr, size_t sz)
- * Purpose  : clear some user memory
- * Params   : addr - user memory address to clear
- *          : sz   - number of bytes to clear
- * Returns  : number of bytes NOT cleared
- */
-WEAK(__clear_user)
-		stm.w	(lr), [sp-]
-		stm.w	(r1), [sp-]
-		mov	r2, #0
-		csub.a	r1, #4
-		bsl	2f
-		and.a	ip, r0, #3
-		beq	1f
-		csub.a	ip, #2
-		strusr	r2, r0, 1
-		strusr	r2, r0, 1, el
-		strusr	r2, r0, 1, sl
-		rsub	ip, ip, #4
-		sub	r1, r1, ip		@  7  6  5  4  3  2  1
-1:		sub.a	r1, r1, #8		@ -1 -2 -3 -4 -5 -6 -7
-		strusr	r2, r0, 4, ns, rept=2
-		bns	1b
-		add.a	r1, r1, #4		@  3  2  1  0 -1 -2 -3
-		strusr	r2, r0, 4, ns
-2:		cand.a	r1, #2			@ 1x 1x 0x 0x 1x 1x 0x
-		strusr	r2, r0, 1, ne, rept=2
-		cand.a	r1, #1			@ x1 x0 x1 x0 x1 x0 x1
-		beq	3f
-USER(		stb.u	r2, [r0])
-3:		mov	r0, #0
-		ldm.w	(r1), [sp]+
-		ldm.w	(pc), [sp]+
-ENDPROC(__clear_user)
-
-		.pushsection .fixup,"ax"
-		.align	0
-9001:		ldm.w	(r0), [sp]+
-		ldm.w	(pc), [sp]+
-		.popsection
-
diff --git a/arch/unicore32/lib/copy_from_user.S b/arch/unicore32/lib/copy_from_user.S
deleted file mode 100644
index affb43920ac0..000000000000
--- a/arch/unicore32/lib/copy_from_user.S
+++ /dev/null
@@ -1,101 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/copy_from_user.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-/*
- * Prototype:
- *
- *	size_t raw_copy_from_user(void *to, const void *from, size_t n)
- *
- * Purpose:
- *
- *	copy a block to kernel memory from user memory
- *
- * Params:
- *
- *	to = kernel memory
- *	from = user memory
- *	n = number of bytes to copy
- *
- * Return value:
- *
- *	Number of bytes NOT copied.
- */
-
-	.macro ldr1w ptr reg abort
-	ldrusr	\reg, \ptr, 4, abort=\abort
-	.endm
-
-	.macro ldr4w ptr reg1 reg2 reg3 reg4 abort
-100:	ldm.w	(\reg1, \reg2, \reg3, \reg4), [\ptr]+
-	.pushsection __ex_table, "a"
-	.align	3
-	.long 100b, \abort
-	.popsection
-	.endm
-
-	.macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
-100:	ldm.w (\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8), [\ptr]+
-	.pushsection __ex_table, "a"
-	.align	3
-	.long 100b, \abort
-	.popsection
-	.endm
-
-	.macro ldr1b ptr reg cond=al abort
-	ldrusr	\reg, \ptr, 1, \cond, abort=\abort
-	.endm
-
-	.macro str1w ptr reg abort
-	stw.w \reg, [\ptr]+, #4
-	.endm
-
-	.macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
-	stm.w (\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8), [\ptr]+
-	.endm
-
-	.macro str1b ptr reg cond=al abort
-	.ifnc	\cond, al
-	b\cond	201f
-	b	202f
-	.endif
-201:	stb.w \reg, [\ptr]+, #1
-202:
-	.endm
-
-	.macro enter
-	mov	r3, #0
-	stm.w	(r0, r2, r3), [sp-]
-	.endm
-
-	.macro exit
-	add	sp, sp, #8
-	ldm.w	(r0), [sp]+
-	mov	pc, lr
-	.endm
-
-	.text
-
-ENTRY(raw_copy_from_user)
-
-#include "copy_template.S"
-
-ENDPROC(raw_copy_from_user)
-
-	.pushsection .fixup,"ax"
-	.align 0
-	copy_abort_preamble
-	ldm.w	(r1, r2, r3), [sp]+
-	sub	r0, r0, r1
-	rsub	r0, r0, r2
-	copy_abort_end
-	.popsection
-
diff --git a/arch/unicore32/lib/copy_page.S b/arch/unicore32/lib/copy_page.S
deleted file mode 100644
index dc163f2d1af0..000000000000
--- a/arch/unicore32/lib/copy_page.S
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/copy_page.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  ASM optimised string functions
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <generated/asm-offsets.h>
-#include <asm/cache.h>
-
-#define COPY_COUNT (PAGE_SZ/256)
-
-		.text
-		.align	5
-/*
- * UniCore optimised copy_page routine
- */
-ENTRY(copy_page)
-		stm.w	(r17 - r19, lr), [sp-]
-		mov	r17, r0
-		mov	r18, r1
-		mov	r19, #COPY_COUNT
-1:
-	.rept	4
-		ldm.w	(r0 - r15), [r18]+
-		stm.w	(r0 - r15), [r17]+
-	.endr
-		sub.a	r19, r19, #1
-		bne	1b
-		ldm.w	(r17 - r19, pc), [sp]+
-ENDPROC(copy_page)
diff --git a/arch/unicore32/lib/copy_template.S b/arch/unicore32/lib/copy_template.S
deleted file mode 100644
index 02a7aef83fbf..000000000000
--- a/arch/unicore32/lib/copy_template.S
+++ /dev/null
@@ -1,211 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/copy_template.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-/*
- * Theory of operation
- * -------------------
- *
- * This file provides the core code for a forward memory copy used in
- * the implementation of memcopy(), copy_to_user() and copy_from_user().
- *
- * The including file must define the following accessor macros
- * according to the need of the given function:
- *
- * ldr1w ptr reg abort
- *
- *	This loads one word from 'ptr', stores it in 'reg' and increments
- *	'ptr' to the next word. The 'abort' argument is used for fixup tables.
- *
- * ldr4w ptr reg1 reg2 reg3 reg4 abort
- * ldr8w ptr, reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
- *
- *	This loads four or eight words starting from 'ptr', stores them
- *	in provided registers and increments 'ptr' past those words.
- *	The'abort' argument is used for fixup tables.
- *
- * ldr1b ptr reg cond abort
- *
- *	Similar to ldr1w, but it loads a byte and increments 'ptr' one byte.
- *	It also must apply the condition code if provided, otherwise the
- *	"al" condition is assumed by default.
- *
- * str1w ptr reg abort
- * str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
- * str1b ptr reg cond abort
- *
- *	Same as their ldr* counterparts, but data is stored to 'ptr' location
- *	rather than being loaded.
- *
- * enter
- *
- *	Preserve the provided registers on the stack plus any additional
- *	data as needed by the implementation including this code. Called
- *	upon code entry.
- *
- * exit
- *
- *	Restore registers with the values previously saved with the
- *	'preserv' macro. Called upon code termination.
- */
-
-
-		enter
-
-		sub.a	r2, r2, #4
-		bsl	8f
-		and.a	ip, r0, #3
-		bne	9f
-		and.a	ip, r1, #3
-		bne	10f
-
-1:		sub.a	r2, r2, #(28)
-		stm.w	(r5 - r8), [sp-]
-		bsl	5f
-
-3:
-4:		ldr8w	r1, r3, r4, r5, r6, r7, r8, r10, r11, abort=20f
-		sub.a	r2, r2, #32
-		str8w	r0, r3, r4, r5, r6, r7, r8, r10, r11, abort=20f
-		beg	3b
-
-5:		and.a	ip, r2, #28
-		rsub	ip, ip, #32
-		beq	7f
-		add	pc, pc, ip		@ C is always clear here
-		nop
-
-		ldr1w	r1, r3, abort=20f
-		ldr1w	r1, r4, abort=20f
-		ldr1w	r1, r5, abort=20f
-		ldr1w	r1, r6, abort=20f
-		ldr1w	r1, r7, abort=20f
-		ldr1w	r1, r8, abort=20f
-		ldr1w	r1, r11, abort=20f
-
-		add	pc, pc, ip
-		nop
-
-		str1w	r0, r3, abort=20f
-		str1w	r0, r4, abort=20f
-		str1w	r0, r5, abort=20f
-		str1w	r0, r6, abort=20f
-		str1w	r0, r7, abort=20f
-		str1w	r0, r8, abort=20f
-		str1w	r0, r11, abort=20f
-
-7:		ldm.w	(r5 - r8), [sp]+
-
-8:		mov.a	r2, r2 << #31
-		ldr1b	r1, r3, ne, abort=21f
-		ldr1b	r1, r4, ea, abort=21f
-		ldr1b	r1, r10, ea, abort=21f
-		str1b	r0, r3, ne, abort=21f
-		str1b	r0, r4, ea, abort=21f
-		str1b	r0, r10, ea, abort=21f
-
-		exit
-
-9:		rsub	ip, ip, #4
-		csub.a	ip, #2
-		ldr1b	r1, r3, sg, abort=21f
-		ldr1b	r1, r4, eg, abort=21f
-		ldr1b	r1, r11, abort=21f
-		str1b	r0, r3, sg, abort=21f
-		str1b	r0, r4, eg, abort=21f
-		sub.a	r2, r2, ip
-		str1b	r0, r11, abort=21f
-		bsl	8b
-		and.a	ip, r1, #3
-		beq	1b
-
-10:		andn	r1, r1, #3
-		csub.a	ip, #2
-		ldr1w	r1, r11, abort=21f
-		beq	17f
-		bsg	18f
-
-
-		.macro	forward_copy_shift a b
-
-		sub.a	r2, r2, #28
-		bsl	14f
-
-11:		stm.w	(r5 - r9), [sp-]
-
-12:
-		ldr4w	r1, r4, r5, r6, r7, abort=19f
-		mov	r3, r11 pull #\a
-		sub.a	r2, r2, #32
-		ldr4w	r1, r8, r9, r10, r11, abort=19f
-		or	r3, r3, r4 push #\b
-		mov	r4, r4 pull #\a
-		or	r4, r4, r5 push #\b
-		mov	r5, r5 pull #\a
-		or	r5, r5, r6 push #\b
-		mov	r6, r6 pull #\a
-		or	r6, r6, r7 push #\b
-		mov	r7, r7 pull #\a
-		or	r7, r7, r8 push #\b
-		mov	r8, r8 pull #\a
-		or	r8, r8, r9 push #\b
-		mov	r9, r9 pull #\a
-		or	r9, r9, r10 push #\b
-		mov	r10, r10 pull #\a
-		or	r10, r10, r11 push #\b
-		str8w	r0, r3, r4, r5, r6, r7, r8, r9, r10, , abort=19f
-		beg	12b
-
-		ldm.w	(r5 - r9), [sp]+
-
-14:		and.a	ip, r2, #28
-		beq	16f
-
-15:		mov	r3, r11 pull #\a
-		ldr1w	r1, r11, abort=21f
-		sub.a	ip, ip, #4
-		or	r3, r3, r11 push #\b
-		str1w	r0, r3, abort=21f
-		bsg	15b
-
-16:		sub	r1, r1, #(\b / 8)
-		b	8b
-
-		.endm
-
-
-		forward_copy_shift	a=8	b=24
-
-17:		forward_copy_shift	a=16	b=16
-
-18:		forward_copy_shift	a=24	b=8
-
-
-/*
- * Abort preamble and completion macros.
- * If a fixup handler is required then those macros must surround it.
- * It is assumed that the fixup code will handle the private part of
- * the exit macro.
- */
-
-	.macro	copy_abort_preamble
-19:	ldm.w	(r5 - r9), [sp]+
-	b	21f
-299:	.word	0			@ store lr
-					@ to avoid function call in fixup
-20:	ldm.w	(r5 - r8), [sp]+
-21:
-	adr	r1, 299b
-	stw	lr, [r1]
-	.endm
-
-	.macro	copy_abort_end
-	adr	lr, 299b
-	ldw	pc, [lr]
-	.endm
-
diff --git a/arch/unicore32/lib/copy_to_user.S b/arch/unicore32/lib/copy_to_user.S
deleted file mode 100644
index c867f08f89ce..000000000000
--- a/arch/unicore32/lib/copy_to_user.S
+++ /dev/null
@@ -1,93 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/copy_to_user.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-/*
- * Prototype:
- *
- *	size_t raw_copy_to_user(void *to, const void *from, size_t n)
- *
- * Purpose:
- *
- *	copy a block to user memory from kernel memory
- *
- * Params:
- *
- *	to = user memory
- *	from = kernel memory
- *	n = number of bytes to copy
- *
- * Return value:
- *
- *	Number of bytes NOT copied.
- */
-
-	.macro ldr1w ptr reg abort
-	ldw.w \reg, [\ptr]+, #4
-	.endm
-
-	.macro ldr4w ptr reg1 reg2 reg3 reg4 abort
-	ldm.w	(\reg1, \reg2, \reg3, \reg4), [\ptr]+
-	.endm
-
-	.macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
-	ldm.w (\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8), [\ptr]+
-	.endm
-
-	.macro ldr1b ptr reg cond=al abort
-	notcond	\cond, .+8
-	ldb.w \reg, [\ptr]+, #1
-	.endm
-
-	.macro str1w ptr reg abort
-	strusr	\reg, \ptr, 4, abort=\abort
-	.endm
-
-	.macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
-100:	stm.w (\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8), [\ptr]+
-
-	.pushsection __ex_table, "a"
-	.long 100b, \abort
-	.popsection
-	.endm
-
-	.macro str1b ptr reg cond=al abort
-	strusr	\reg, \ptr, 1, \cond, abort=\abort
-	.endm
-
-	.macro enter
-	mov	r3, #0
-	stm.w	(r0, r2, r3), [sp-]
-	.endm
-
-	.macro exit
-	add	sp, sp, #8
-	ldm.w	(r0), [sp]+
-	mov	pc, lr
-	.endm
-
-	.text
-
-WEAK(raw_copy_to_user)
-
-#include "copy_template.S"
-
-ENDPROC(raw_copy_to_user)
-
-	.pushsection .fixup,"ax"
-	.align 0
-	copy_abort_preamble
-	ldm.w	(r1, r2, r3), [sp]+
-	sub	r0, r0, r1
-	rsub	r0, r0, r2
-	copy_abort_end
-	.popsection
-
diff --git a/arch/unicore32/lib/delay.S b/arch/unicore32/lib/delay.S
deleted file mode 100644
index 6a359dd034e5..000000000000
--- a/arch/unicore32/lib/delay.S
+++ /dev/null
@@ -1,48 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/delay.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/param.h>
-		.text
-
-.LC0:		.word	loops_per_jiffy
-.LC1:		.word	(2199023*HZ)>>11
-
-/*
- * r0  <= 2000
- * lpj <= 0x01ffffff (max. 3355 bogomips)
- * HZ  <= 1000
- */
-
-ENTRY(__udelay)
-		ldw	r2, .LC1
-		mul	r0, r2, r0
-ENTRY(__const_udelay)				@ 0 <= r0 <= 0x7fffff06
-		ldw	r2, .LC0
-		ldw	r2, [r2]		@ max = 0x01ffffff
-		mov	r0, r0 >> #14		@ max = 0x0001ffff
-		mov	r2, r2 >> #10		@ max = 0x00007fff
-		mul	r0, r2, r0		@ max = 2^32-1
-		mov.a	r0, r0 >> #6
-		cmoveq	pc, lr
-
-/*
- * loops = r0 * HZ * loops_per_jiffy / 1000000
- *
- * Oh, if only we had a cycle counter...
- */
-
-@ Delay routine
-ENTRY(__delay)
-		sub.a	r0, r0, #2
-		bua	__delay
-		mov	pc, lr
-ENDPROC(__udelay)
-ENDPROC(__const_udelay)
-ENDPROC(__delay)
diff --git a/arch/unicore32/lib/findbit.S b/arch/unicore32/lib/findbit.S
deleted file mode 100644
index 42f1282670d2..000000000000
--- a/arch/unicore32/lib/findbit.S
+++ /dev/null
@@ -1,97 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/findbit.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-                .text
-
-/*
- * Purpose  : Find a 'zero' bit
- * Prototype: int find_first_zero_bit(void *addr, unsigned int maxbit);
- */
-ENTRY(find_first_zero_bit)
-		cxor.a	r1, #0
-		beq	3f
-		mov	r2, #0
-1:		ldb	r3, [r0+], r2 >> #3
-		xor.a	r3, r3, #0xff		@ invert bits
-		bne	.L_found		@ any now set - found zero bit
-		add	r2, r2, #8		@ next bit pointer
-2:		csub.a	r2, r1			@ any more?
-		bub	1b
-3:		mov	r0, r1			@ no free bits
-		mov	pc, lr
-ENDPROC(find_first_zero_bit)
-
-/*
- * Purpose  : Find next 'zero' bit
- * Prototype: int find_next_zero_bit
- *		(void *addr, unsigned int maxbit, int offset)
- */
-ENTRY(find_next_zero_bit)
-		cxor.a	r1, #0
-		beq	3b
-		and.a	ip, r2, #7
-		beq	1b			@ If new byte, goto old routine
-		ldb	r3, [r0+], r2 >> #3
-		xor	r3, r3, #0xff		@ now looking for a 1 bit
-		mov.a	r3, r3 >> ip		@ shift off unused bits
-		bne	.L_found
-		or	r2, r2, #7		@ if zero, then no bits here
-		add	r2, r2, #1		@ align bit pointer
-		b	2b			@ loop for next bit
-ENDPROC(find_next_zero_bit)
-
-/*
- * Purpose  : Find a 'one' bit
- * Prototype: int find_first_bit
- *		(const unsigned long *addr, unsigned int maxbit);
- */
-ENTRY(find_first_bit)
-		cxor.a	r1, #0
-		beq	3f
-		mov	r2, #0
-1:		ldb	r3, [r0+], r2 >> #3
-		mov.a	r3, r3
-		bne	.L_found		@ any now set - found zero bit
-		add	r2, r2, #8		@ next bit pointer
-2:		csub.a	r2, r1			@ any more?
-		bub	1b
-3:		mov	r0, r1			@ no free bits
-		mov	pc, lr
-ENDPROC(find_first_bit)
-
-/*
- * Purpose  : Find next 'one' bit
- * Prototype: int find_next_zero_bit
- *		(void *addr, unsigned int maxbit, int offset)
- */
-ENTRY(find_next_bit)
-		cxor.a	r1, #0
-		beq	3b
-		and.a	ip, r2, #7
-		beq	1b			@ If new byte, goto old routine
-		ldb	r3, [r0+], r2 >> #3
-		mov.a	r3, r3 >> ip		@ shift off unused bits
-		bne	.L_found
-		or	r2, r2, #7		@ if zero, then no bits here
-		add	r2, r2, #1		@ align bit pointer
-		b	2b			@ loop for next bit
-ENDPROC(find_next_bit)
-
-/*
- * One or more bits in the LSB of r3 are assumed to be set.
- */
-.L_found:
-		rsub	r1, r3, #0
-		and	r3, r3, r1
-		cntlz	r3, r3
-		rsub	r3, r3, #31
-		add	r0, r2, r3
-		mov	pc, lr
-
diff --git a/arch/unicore32/lib/strncpy_from_user.S b/arch/unicore32/lib/strncpy_from_user.S
deleted file mode 100644
index f227b8227a4c..000000000000
--- a/arch/unicore32/lib/strncpy_from_user.S
+++ /dev/null
@@ -1,42 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/strncpy_from_user.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-
-	.text
-	.align	5
-
-/*
- * Copy a string from user space to kernel space.
- *  r0 = dst, r1 = src, r2 = byte length
- * returns the number of characters copied (strlen of copied string),
- *  -EFAULT on exception, or "len" if we fill the whole buffer
- */
-ENTRY(__strncpy_from_user)
-	mov	ip, r1
-1:	sub.a	r2, r2, #1
-	ldrusr	r3, r1, 1, ns
-	bfs	2f
-	stb.w	r3, [r0]+, #1
-	cxor.a	r3, #0
-	bne	1b
-	sub	r1, r1, #1	@ take NUL character out of count
-2:	sub	r0, r1, ip
-	mov	pc, lr
-ENDPROC(__strncpy_from_user)
-
-	.pushsection .fixup,"ax"
-	.align	0
-9001:	mov	r3, #0
-	stb	r3, [r0+], #0	@ null terminate
-	mov	r0, #-EFAULT
-	mov	pc, lr
-	.popsection
-
diff --git a/arch/unicore32/lib/strnlen_user.S b/arch/unicore32/lib/strnlen_user.S
deleted file mode 100644
index c836b12776fe..000000000000
--- a/arch/unicore32/lib/strnlen_user.S
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/lib/strnlen_user.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-
-	.text
-	.align	5
-
-/* Prototype: unsigned long __strnlen_user(const char *str, long n)
- * Purpose  : get length of a string in user memory
- * Params   : str - address of string in user memory
- * Returns  : length of string *including terminator*
- *	      or zero on exception, or n + 1 if too long
- */
-ENTRY(__strnlen_user)
-	mov	r2, r0
-1:
-	ldrusr	r3, r0, 1
-	cxor.a	r3, #0
-	beq	2f
-	sub.a	r1, r1, #1
-	bne	1b
-	add	r0, r0, #1
-2:	sub	r0, r0, r2
-	mov	pc, lr
-ENDPROC(__strnlen_user)
-
-	.pushsection .fixup,"ax"
-	.align	0
-9001:	mov	r0, #0
-	mov	pc, lr
-	.popsection
diff --git a/arch/unicore32/mm/Kconfig b/arch/unicore32/mm/Kconfig
deleted file mode 100644
index 82759b6aba67..000000000000
--- a/arch/unicore32/mm/Kconfig
+++ /dev/null
@@ -1,41 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-comment "Processor Type"
-
-# Select CPU types depending on the architecture selected.  This selects
-# which CPUs we support in the kernel image, and the compiler instruction
-# optimiser behaviour.
-
-config CPU_UCV2
-	def_bool y
-
-comment "Processor Features"
-
-config CPU_ICACHE_DISABLE
-	bool "Disable I-Cache (I-bit)"
-	help
-	  Say Y here to disable the processor instruction cache. Unless
-	  you have a reason not to or are unsure, say N.
-
-config CPU_DCACHE_DISABLE
-	bool "Disable D-Cache (D-bit)"
-	help
-	  Say Y here to disable the processor data cache. Unless
-	  you have a reason not to or are unsure, say N.
-
-config CPU_DCACHE_WRITETHROUGH
-	bool "Force write through D-cache"
-	help
-	  Say Y here to use the data cache in writethrough mode. Unless you
-	  specifically require this or are unsure, say N.
-
-config CPU_DCACHE_LINE_DISABLE
-	bool "Disable D-cache line ops"
-	default y
-	help
-	  Say Y here to disable the data cache line operations.
-
-config CPU_TLB_SINGLE_ENTRY_DISABLE
-	bool "Disable TLB single entry ops"
-	default y
-	help
-	  Say Y here to disable the TLB single entry operations.
diff --git a/arch/unicore32/mm/Makefile b/arch/unicore32/mm/Makefile
deleted file mode 100644
index 8106260583ab..000000000000
--- a/arch/unicore32/mm/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for the linux unicore-specific parts of the memory manager.
-#
-
-obj-y				:= extable.o fault.o init.o pgd.o mmu.o
-obj-y				+= flush.o ioremap.o
-
-obj-$(CONFIG_MODULES)		+= proc-syms.o
-
-obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
-
-obj-$(CONFIG_CPU_UCV2)		+= cache-ucv2.o tlb-ucv2.o proc-ucv2.o
-
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
deleted file mode 100644
index 2ea98f7a4156..000000000000
--- a/arch/unicore32/mm/alignment.c
+++ /dev/null
@@ -1,524 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/mm/alignment.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-/*
- * TODO:
- *  FPU ldm/stm not handling
- */
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/sched/debug.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/uaccess.h>
-#include <linux/pgtable.h>
-
-#include <asm/tlbflush.h>
-#include <asm/unaligned.h>
-
-#include "mm.h"
-
-#define CODING_BITS(i)	(i & 0xe0000120)
-
-#define LDST_P_BIT(i)	(i & (1 << 28))	/* Preindex             */
-#define LDST_U_BIT(i)	(i & (1 << 27))	/* Add offset           */
-#define LDST_W_BIT(i)	(i & (1 << 25))	/* Writeback            */
-#define LDST_L_BIT(i)	(i & (1 << 24))	/* Load                 */
-
-#define LDST_P_EQ_U(i)	((((i) ^ ((i) >> 1)) & (1 << 27)) == 0)
-
-#define LDSTH_I_BIT(i)	(i & (1 << 26))	/* half-word immed      */
-#define LDM_S_BIT(i)	(i & (1 << 26))	/* write ASR from BSR */
-#define LDM_H_BIT(i)	(i & (1 << 6))	/* select r0-r15 or r16-r31 */
-
-#define RN_BITS(i)	((i >> 19) & 31)	/* Rn                   */
-#define RD_BITS(i)	((i >> 14) & 31)	/* Rd                   */
-#define RM_BITS(i)	(i & 31)	/* Rm                   */
-
-#define REGMASK_BITS(i)	(((i & 0x7fe00) >> 3) | (i & 0x3f))
-#define OFFSET_BITS(i)	(i & 0x03fff)
-
-#define SHIFT_BITS(i)	((i >> 9) & 0x1f)
-#define SHIFT_TYPE(i)	(i & 0xc0)
-#define SHIFT_LSL	0x00
-#define SHIFT_LSR	0x40
-#define SHIFT_ASR	0x80
-#define SHIFT_RORRRX	0xc0
-
-union offset_union {
-	unsigned long un;
-	signed long sn;
-};
-
-#define TYPE_ERROR	0
-#define TYPE_FAULT	1
-#define TYPE_LDST	2
-#define TYPE_DONE	3
-#define TYPE_SWAP  4
-#define TYPE_COLS  5		/* Coprocessor load/store */
-
-#define get8_unaligned_check(val, addr, err)		\
-	__asm__(					\
-	"1:	ldb.u	%1, [%2], #1\n"			\
-	"2:\n"						\
-	"	.pushsection .fixup,\"ax\"\n"		\
-	"	.align	2\n"				\
-	"3:	mov	%0, #1\n"			\
-	"	b	2b\n"				\
-	"	.popsection\n"				\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"				\
-	"	.long	1b, 3b\n"			\
-	"	.popsection\n"				\
-	: "=r" (err), "=&r" (val), "=r" (addr)		\
-	: "0" (err), "2" (addr))
-
-#define get8t_unaligned_check(val, addr, err)		\
-	__asm__(					\
-	"1:	ldb.u	%1, [%2], #1\n"			\
-	"2:\n"						\
-	"	.pushsection .fixup,\"ax\"\n"		\
-	"	.align	2\n"				\
-	"3:	mov	%0, #1\n"			\
-	"	b	2b\n"				\
-	"	.popsection\n"				\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"				\
-	"	.long	1b, 3b\n"			\
-	"	.popsection\n"				\
-	: "=r" (err), "=&r" (val), "=r" (addr)		\
-	: "0" (err), "2" (addr))
-
-#define get16_unaligned_check(val, addr)			\
-	do {							\
-		unsigned int err = 0, v, a = addr;		\
-		get8_unaligned_check(val, a, err);		\
-		get8_unaligned_check(v, a, err);		\
-		val |= v << 8;					\
-		if (err)					\
-			goto fault;				\
-	} while (0)
-
-#define put16_unaligned_check(val, addr)			\
-	do {							\
-		unsigned int err = 0, v = val, a = addr;	\
-		__asm__(					\
-		"1:	stb.u	%1, [%2], #1\n"			\
-		"	mov	%1, %1 >> #8\n"			\
-		"2:	stb.u	%1, [%2]\n"			\
-		"3:\n"						\
-		"	.pushsection .fixup,\"ax\"\n"		\
-		"	.align	2\n"				\
-		"4:	mov	%0, #1\n"			\
-		"	b	3b\n"				\
-		"	.popsection\n"				\
-		"	.pushsection __ex_table,\"a\"\n"		\
-		"	.align	3\n"				\
-		"	.long	1b, 4b\n"			\
-		"	.long	2b, 4b\n"			\
-		"	.popsection\n"				\
-		: "=r" (err), "=&r" (v), "=&r" (a)		\
-		: "0" (err), "1" (v), "2" (a));			\
-		if (err)					\
-			goto fault;				\
-	} while (0)
-
-#define __put32_unaligned_check(ins, val, addr)			\
-	do {							\
-		unsigned int err = 0, v = val, a = addr;	\
-		__asm__(					\
-		"1:	"ins"	%1, [%2], #1\n"			\
-		"	mov	%1, %1 >> #8\n"			\
-		"2:	"ins"	%1, [%2], #1\n"			\
-		"	mov	%1, %1 >> #8\n"			\
-		"3:	"ins"	%1, [%2], #1\n"			\
-		"	mov	%1, %1 >> #8\n"			\
-		"4:	"ins"	%1, [%2]\n"			\
-		"5:\n"						\
-		"	.pushsection .fixup,\"ax\"\n"		\
-		"	.align	2\n"				\
-		"6:	mov	%0, #1\n"			\
-		"	b	5b\n"				\
-		"	.popsection\n"				\
-		"	.pushsection __ex_table,\"a\"\n"		\
-		"	.align	3\n"				\
-		"	.long	1b, 6b\n"			\
-		"	.long	2b, 6b\n"			\
-		"	.long	3b, 6b\n"			\
-		"	.long	4b, 6b\n"			\
-		"	.popsection\n"				\
-		: "=r" (err), "=&r" (v), "=&r" (a)		\
-		: "0" (err), "1" (v), "2" (a));			\
-		if (err)					\
-			goto fault;				\
-	} while (0)
-
-#define get32_unaligned_check(val, addr)			\
-	do {							\
-		unsigned int err = 0, v, a = addr;		\
-		get8_unaligned_check(val, a, err);		\
-		get8_unaligned_check(v, a, err);		\
-		val |= v << 8;					\
-		get8_unaligned_check(v, a, err);		\
-		val |= v << 16;					\
-		get8_unaligned_check(v, a, err);		\
-		val |= v << 24;					\
-		if (err)					\
-			goto fault;				\
-	} while (0)
-
-#define put32_unaligned_check(val, addr)			\
-	__put32_unaligned_check("stb.u", val, addr)
-
-#define get32t_unaligned_check(val, addr)			\
-	do {							\
-		unsigned int err = 0, v, a = addr;		\
-		get8t_unaligned_check(val, a, err);		\
-		get8t_unaligned_check(v, a, err);		\
-		val |= v << 8;					\
-		get8t_unaligned_check(v, a, err);		\
-		val |= v << 16;					\
-		get8t_unaligned_check(v, a, err);		\
-		val |= v << 24;					\
-		if (err)					\
-			goto fault;				\
-	} while (0)
-
-#define put32t_unaligned_check(val, addr)			\
-	__put32_unaligned_check("stb.u", val, addr)
-
-static void
-do_alignment_finish_ldst(unsigned long addr, unsigned long instr,
-			 struct pt_regs *regs, union offset_union offset)
-{
-	if (!LDST_U_BIT(instr))
-		offset.un = -offset.un;
-
-	if (!LDST_P_BIT(instr))
-		addr += offset.un;
-
-	if (!LDST_P_BIT(instr) || LDST_W_BIT(instr))
-		regs->uregs[RN_BITS(instr)] = addr;
-}
-
-static int
-do_alignment_ldrhstrh(unsigned long addr, unsigned long instr,
-		      struct pt_regs *regs)
-{
-	unsigned int rd = RD_BITS(instr);
-
-	/* old value 0x40002120, can't judge swap instr correctly */
-	if ((instr & 0x4b003fe0) == 0x40000120)
-		goto swp;
-
-	if (LDST_L_BIT(instr)) {
-		unsigned long val;
-		get16_unaligned_check(val, addr);
-
-		/* signed half-word? */
-		if (instr & 0x80)
-			val = (signed long)((signed short)val);
-
-		regs->uregs[rd] = val;
-	} else
-		put16_unaligned_check(regs->uregs[rd], addr);
-
-	return TYPE_LDST;
-
-swp:
-	/* only handle swap word
-	 * for swap byte should not active this alignment exception */
-	get32_unaligned_check(regs->uregs[RD_BITS(instr)], addr);
-	put32_unaligned_check(regs->uregs[RM_BITS(instr)], addr);
-	return TYPE_SWAP;
-
-fault:
-	return TYPE_FAULT;
-}
-
-static int
-do_alignment_ldrstr(unsigned long addr, unsigned long instr,
-		    struct pt_regs *regs)
-{
-	unsigned int rd = RD_BITS(instr);
-
-	if (!LDST_P_BIT(instr) && LDST_W_BIT(instr))
-		goto trans;
-
-	if (LDST_L_BIT(instr))
-		get32_unaligned_check(regs->uregs[rd], addr);
-	else
-		put32_unaligned_check(regs->uregs[rd], addr);
-	return TYPE_LDST;
-
-trans:
-	if (LDST_L_BIT(instr))
-		get32t_unaligned_check(regs->uregs[rd], addr);
-	else
-		put32t_unaligned_check(regs->uregs[rd], addr);
-	return TYPE_LDST;
-
-fault:
-	return TYPE_FAULT;
-}
-
-/*
- * LDM/STM alignment handler.
- *
- * There are 4 variants of this instruction:
- *
- * B = rn pointer before instruction, A = rn pointer after instruction
- *              ------ increasing address ----->
- *	        |    | r0 | r1 | ... | rx |    |
- * PU = 01             B                    A
- * PU = 11        B                    A
- * PU = 00        A                    B
- * PU = 10             A                    B
- */
-static int
-do_alignment_ldmstm(unsigned long addr, unsigned long instr,
-		    struct pt_regs *regs)
-{
-	unsigned int rd, rn, pc_correction, reg_correction, nr_regs, regbits;
-	unsigned long eaddr, newaddr;
-
-	if (LDM_S_BIT(instr))
-		goto bad;
-
-	pc_correction = 4;	/* processor implementation defined */
-
-	/* count the number of registers in the mask to be transferred */
-	nr_regs = hweight16(REGMASK_BITS(instr)) * 4;
-
-	rn = RN_BITS(instr);
-	newaddr = eaddr = regs->uregs[rn];
-
-	if (!LDST_U_BIT(instr))
-		nr_regs = -nr_regs;
-	newaddr += nr_regs;
-	if (!LDST_U_BIT(instr))
-		eaddr = newaddr;
-
-	if (LDST_P_EQ_U(instr))	/* U = P */
-		eaddr += 4;
-
-	/*
-	 * This is a "hint" - we already have eaddr worked out by the
-	 * processor for us.
-	 */
-	if (addr != eaddr) {
-		printk(KERN_ERR "LDMSTM: PC = %08lx, instr = %08lx, "
-		       "addr = %08lx, eaddr = %08lx\n",
-		       instruction_pointer(regs), instr, addr, eaddr);
-		show_regs(regs);
-	}
-
-	if (LDM_H_BIT(instr))
-		reg_correction = 0x10;
-	else
-		reg_correction = 0x00;
-
-	for (regbits = REGMASK_BITS(instr), rd = 0; regbits;
-	     regbits >>= 1, rd += 1)
-		if (regbits & 1) {
-			if (LDST_L_BIT(instr))
-				get32_unaligned_check(regs->
-					uregs[rd + reg_correction], eaddr);
-			else
-				put32_unaligned_check(regs->
-					uregs[rd + reg_correction], eaddr);
-			eaddr += 4;
-		}
-
-	if (LDST_W_BIT(instr))
-		regs->uregs[rn] = newaddr;
-	return TYPE_DONE;
-
-fault:
-	regs->UCreg_pc -= pc_correction;
-	return TYPE_FAULT;
-
-bad:
-	printk(KERN_ERR "Alignment trap: not handling ldm with s-bit set\n");
-	return TYPE_ERROR;
-}
-
-static int
-do_alignment(unsigned long addr, unsigned int error_code, struct pt_regs *regs)
-{
-	union offset_union offset;
-	unsigned long instr, instrptr;
-	int (*handler) (unsigned long addr, unsigned long instr,
-			struct pt_regs *regs);
-	unsigned int type;
-
-	instrptr = instruction_pointer(regs);
-	if (instrptr >= PAGE_OFFSET)
-		instr = *(unsigned long *)instrptr;
-	else {
-		__asm__ __volatile__(
-				"ldw.u	%0, [%1]\n"
-				: "=&r"(instr)
-				: "r"(instrptr));
-	}
-
-	regs->UCreg_pc += 4;
-
-	switch (CODING_BITS(instr)) {
-	case 0x40000120:	/* ldrh or strh */
-		if (LDSTH_I_BIT(instr))
-			offset.un = (instr & 0x3e00) >> 4 | (instr & 31);
-		else
-			offset.un = regs->uregs[RM_BITS(instr)];
-		handler = do_alignment_ldrhstrh;
-		break;
-
-	case 0x60000000:	/* ldr or str immediate */
-	case 0x60000100:	/* ldr or str immediate */
-	case 0x60000020:	/* ldr or str immediate */
-	case 0x60000120:	/* ldr or str immediate */
-		offset.un = OFFSET_BITS(instr);
-		handler = do_alignment_ldrstr;
-		break;
-
-	case 0x40000000:	/* ldr or str register */
-		offset.un = regs->uregs[RM_BITS(instr)];
-		{
-			unsigned int shiftval = SHIFT_BITS(instr);
-
-			switch (SHIFT_TYPE(instr)) {
-			case SHIFT_LSL:
-				offset.un <<= shiftval;
-				break;
-
-			case SHIFT_LSR:
-				offset.un >>= shiftval;
-				break;
-
-			case SHIFT_ASR:
-				offset.sn >>= shiftval;
-				break;
-
-			case SHIFT_RORRRX:
-				if (shiftval == 0) {
-					offset.un >>= 1;
-					if (regs->UCreg_asr & PSR_C_BIT)
-						offset.un |= 1 << 31;
-				} else
-					offset.un = offset.un >> shiftval |
-					    offset.un << (32 - shiftval);
-				break;
-			}
-		}
-		handler = do_alignment_ldrstr;
-		break;
-
-	case 0x80000000:	/* ldm or stm */
-	case 0x80000020:	/* ldm or stm */
-		handler = do_alignment_ldmstm;
-		break;
-
-	default:
-		goto bad;
-	}
-
-	type = handler(addr, instr, regs);
-
-	if (type == TYPE_ERROR || type == TYPE_FAULT)
-		goto bad_or_fault;
-
-	if (type == TYPE_LDST)
-		do_alignment_finish_ldst(addr, instr, regs, offset);
-
-	return 0;
-
-bad_or_fault:
-	if (type == TYPE_ERROR)
-		goto bad;
-	regs->UCreg_pc -= 4;
-	/*
-	 * We got a fault - fix it up, or die.
-	 */
-	do_bad_area(addr, error_code, regs);
-	return 0;
-
-bad:
-	/*
-	 * Oops, we didn't handle the instruction.
-	 * However, we must handle fpu instr firstly.
-	 */
-#ifdef CONFIG_UNICORE_FPU_F64
-	/* handle co.load/store */
-#define CODING_COLS                0xc0000000
-#define COLS_OFFSET_BITS(i)	(i & 0x1FF)
-#define COLS_L_BITS(i)		(i & (1<<24))
-#define COLS_FN_BITS(i)		((i>>14) & 31)
-	if ((instr & 0xe0000000) == CODING_COLS) {
-		unsigned int fn = COLS_FN_BITS(instr);
-		unsigned long val = 0;
-		if (COLS_L_BITS(instr)) {
-			get32t_unaligned_check(val, addr);
-			switch (fn) {
-#define ASM_MTF(n)	case n:						\
-			__asm__ __volatile__("MTF %0, F" __stringify(n)	\
-				: : "r"(val));				\
-			break;
-			ASM_MTF(0); ASM_MTF(1); ASM_MTF(2); ASM_MTF(3);
-			ASM_MTF(4); ASM_MTF(5); ASM_MTF(6); ASM_MTF(7);
-			ASM_MTF(8); ASM_MTF(9); ASM_MTF(10); ASM_MTF(11);
-			ASM_MTF(12); ASM_MTF(13); ASM_MTF(14); ASM_MTF(15);
-			ASM_MTF(16); ASM_MTF(17); ASM_MTF(18); ASM_MTF(19);
-			ASM_MTF(20); ASM_MTF(21); ASM_MTF(22); ASM_MTF(23);
-			ASM_MTF(24); ASM_MTF(25); ASM_MTF(26); ASM_MTF(27);
-			ASM_MTF(28); ASM_MTF(29); ASM_MTF(30); ASM_MTF(31);
-#undef ASM_MTF
-			}
-		} else {
-			switch (fn) {
-#define ASM_MFF(n)	case n:						\
-			__asm__ __volatile__("MFF %0, F" __stringify(n)	\
-				: : "r"(val));				\
-			break;
-			ASM_MFF(0); ASM_MFF(1); ASM_MFF(2); ASM_MFF(3);
-			ASM_MFF(4); ASM_MFF(5); ASM_MFF(6); ASM_MFF(7);
-			ASM_MFF(8); ASM_MFF(9); ASM_MFF(10); ASM_MFF(11);
-			ASM_MFF(12); ASM_MFF(13); ASM_MFF(14); ASM_MFF(15);
-			ASM_MFF(16); ASM_MFF(17); ASM_MFF(18); ASM_MFF(19);
-			ASM_MFF(20); ASM_MFF(21); ASM_MFF(22); ASM_MFF(23);
-			ASM_MFF(24); ASM_MFF(25); ASM_MFF(26); ASM_MFF(27);
-			ASM_MFF(28); ASM_MFF(29); ASM_MFF(30); ASM_MFF(31);
-#undef ASM_MFF
-			}
-			put32t_unaligned_check(val, addr);
-		}
-		return TYPE_COLS;
-	}
-fault:
-	return TYPE_FAULT;
-#endif
-	printk(KERN_ERR "Alignment trap: not handling instruction "
-	       "%08lx at [<%08lx>]\n", instr, instrptr);
-	return 1;
-}
-
-/*
- * This needs to be done after sysctl_init, otherwise sys/ will be
- * overwritten.  Actually, this shouldn't be in sys/ at all since
- * it isn't a sysctl, and it doesn't contain sysctl information.
- */
-static int __init alignment_init(void)
-{
-	hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,
-			"alignment exception");
-
-	return 0;
-}
-
-fs_initcall(alignment_init);
diff --git a/arch/unicore32/mm/cache-ucv2.S b/arch/unicore32/mm/cache-ucv2.S
deleted file mode 100644
index 2108837d6f4f..000000000000
--- a/arch/unicore32/mm/cache-ucv2.S
+++ /dev/null
@@ -1,209 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/mm/cache-ucv2.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- *  This is the "shell" of the UniCore-v2 processor support.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/assembler.h>
-#include <asm/page.h>
-
-#include "proc-macros.S"
-
-/*
- *	__cpuc_flush_icache_all()
- *	__cpuc_flush_kern_all()
- *	__cpuc_flush_user_all()
- *
- *	Flush the entire cache.
- */
-ENTRY(__cpuc_flush_icache_all)
-	/*FALLTHROUGH*/
-ENTRY(__cpuc_flush_kern_all)
-	/*FALLTHROUGH*/
-ENTRY(__cpuc_flush_user_all)
-	mov	r0, #0
-	movc	p0.c5, r0, #14			@ Dcache flush all
-	nop8
-
-	mov	r0, #0
-	movc	p0.c5, r0, #20			@ Icache invalidate all
-	nop8
-
-	mov	pc, lr
-
-/*
- *	__cpuc_flush_user_range(start, end, flags)
- *
- *	Flush a range of TLB entries in the specified address space.
- *
- *	- start - start address (may not be aligned)
- *	- end   - end address (exclusive, may not be aligned)
- *	- flags	- vm_area_struct flags describing address space
- */
-ENTRY(__cpuc_flush_user_range)
-	cxor.a	r2, #0
-	beq	__cpuc_dma_flush_range
-
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-	andn	r0, r0, #CACHE_LINESIZE - 1	@ Safety check
-	sub	r1, r1, r0
-	csub.a	r1, #MAX_AREA_SIZE
-	bsg	2f
-
-	andn	r1, r1, #CACHE_LINESIZE - 1
-	add	r1, r1, #CACHE_LINESIZE
-
-101:	dcacheline_flush	r0, r11, r12
-
-	add	r0, r0, #CACHE_LINESIZE
-	sub.a	r1, r1, #CACHE_LINESIZE
-	bns	101b
-	b	3f
-#endif
-2:	mov	ip, #0
-	movc	p0.c5, ip, #14			@ Dcache flush all
-	nop8
-
-3:	mov	ip, #0
-	movc	p0.c5, ip, #20			@ Icache invalidate all
-	nop8
-
-	mov	pc, lr
-
-/*
- *	__cpuc_coherent_kern_range(start,end)
- *	__cpuc_coherent_user_range(start,end)
- *
- *	Ensure that the I and D caches are coherent within specified
- *	region.  This is typically used when code has been written to
- *	a memory region, and will be executed.
- *
- *	- start   - virtual start address of region
- *	- end     - virtual end address of region
- */
-ENTRY(__cpuc_coherent_kern_range)
-	/* FALLTHROUGH */
-ENTRY(__cpuc_coherent_user_range)
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-	andn	r0, r0, #CACHE_LINESIZE - 1	@ Safety check
-	sub	r1, r1, r0
-	csub.a	r1, #MAX_AREA_SIZE
-	bsg	2f
-
-	andn	r1, r1, #CACHE_LINESIZE - 1
-	add	r1, r1, #CACHE_LINESIZE
-
-	@ r0 va2pa r10
-	mov	r9, #PAGE_SZ
-	sub	r9, r9, #1			@ PAGE_MASK
-101:	va2pa	r0, r10, r11, r12, r13, 2f	@ r10 is PA
-	b	103f
-102:	cand.a	r0, r9
-	beq	101b
-
-103:	movc	p0.c5, r10, #11			@ Dcache clean line of R10
-	nop8
-
-	add	r0, r0, #CACHE_LINESIZE
-	add	r10, r10, #CACHE_LINESIZE
-	sub.a	r1, r1, #CACHE_LINESIZE
-	bns	102b
-	b	3f
-#endif
-2:	mov	ip, #0
-	movc	p0.c5, ip, #10			@ Dcache clean all
-	nop8
-
-3:	mov	ip, #0
-	movc	p0.c5, ip, #20			@ Icache invalidate all
-	nop8
-
-	mov	pc, lr
-
-/*
- *	__cpuc_flush_kern_dcache_area(void *addr, size_t size)
- *
- *	- addr	- kernel address
- *	- size	- region size
- */
-ENTRY(__cpuc_flush_kern_dcache_area)
-	mov	ip, #0
-	movc	p0.c5, ip, #14			@ Dcache flush all
-	nop8
-	mov	pc, lr
-
-/*
- *	__cpuc_dma_clean_range(start,end)
- *	- start   - virtual start address of region
- *	- end     - virtual end address of region
- */
-ENTRY(__cpuc_dma_clean_range)
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-	andn	r0, r0, #CACHE_LINESIZE - 1
-	sub	r1, r1, r0
-	andn	r1, r1, #CACHE_LINESIZE - 1
-	add	r1, r1, #CACHE_LINESIZE
-
-	csub.a	r1, #MAX_AREA_SIZE
-	bsg	2f
-
-	@ r0 va2pa r10
-	mov	r9, #PAGE_SZ
-	sub	r9, r9, #1			@ PAGE_MASK
-101:	va2pa	r0, r10, r11, r12, r13, 2f	@ r10 is PA
-	b	1f
-102:	cand.a	r0, r9
-	beq	101b
-
-1:	movc	p0.c5, r10, #11			@ Dcache clean line of R10
-	nop8
-	add	r0, r0, #CACHE_LINESIZE
-	add	r10, r10, #CACHE_LINESIZE
-	sub.a	r1, r1, #CACHE_LINESIZE
-	bns	102b
-	mov	pc, lr
-#endif
-2:	mov	ip, #0
-	movc	p0.c5, ip, #10			@ Dcache clean all
-	nop8
-
-	mov	pc, lr
-
-/*
- *	__cpuc_dma_inv_range(start,end)
- *	__cpuc_dma_flush_range(start,end)
- *	- start   - virtual start address of region
- *	- end     - virtual end address of region
- */
-__cpuc_dma_inv_range:
-	/* FALLTHROUGH */
-ENTRY(__cpuc_dma_flush_range)
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-	andn	r0, r0, #CACHE_LINESIZE - 1
-	sub	r1, r1, r0
-	andn	r1, r1, #CACHE_LINESIZE - 1
-	add	r1, r1, #CACHE_LINESIZE
-
-	csub.a	r1, #MAX_AREA_SIZE
-	bsg	2f
-
-	@ r0 va2pa r10
-101:	dcacheline_flush	r0, r11, r12
-
-	add	r0, r0, #CACHE_LINESIZE
-	sub.a	r1, r1, #CACHE_LINESIZE
-	bns	101b
-	mov	pc, lr
-#endif
-2:	mov	ip, #0
-	movc	p0.c5, ip, #14			@ Dcache flush all
-	nop8
-
-	mov	pc, lr
-
diff --git a/arch/unicore32/mm/extable.c b/arch/unicore32/mm/extable.c
deleted file mode 100644
index e53352b41c4a..000000000000
--- a/arch/unicore32/mm/extable.c
+++ /dev/null
@@ -1,21 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/mm/extable.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/extable.h>
-#include <linux/uaccess.h>
-
-int fixup_exception(struct pt_regs *regs)
-{
-	const struct exception_table_entry *fixup;
-
-	fixup = search_exception_tables(instruction_pointer(regs));
-	if (fixup)
-		regs->UCreg_pc = fixup->fixup;
-
-	return fixup != NULL;
-}
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
deleted file mode 100644
index 7654bddde133..000000000000
--- a/arch/unicore32/mm/fault.c
+++ /dev/null
@@ -1,481 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/mm/fault.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/extable.h>
-#include <linux/signal.h>
-#include <linux/mm.h>
-#include <linux/hardirq.h>
-#include <linux/init.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/page-flags.h>
-#include <linux/sched/signal.h>
-#include <linux/io.h>
-
-#include <asm/tlbflush.h>
-
-/*
- * Fault status register encodings.  We steal bit 31 for our own purposes.
- */
-#define FSR_LNX_PF		(1 << 31)
-
-static inline int fsr_fs(unsigned int fsr)
-{
-	/* xyabcde will be abcde+xy */
-	return (fsr & 31) + ((fsr & (3 << 5)) >> 5);
-}
-
-/*
- * This is useful to dump out the page tables associated with
- * 'addr' in mm 'mm'.
- */
-void show_pte(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pgd;
-
-	if (!mm)
-		mm = &init_mm;
-
-	printk(KERN_ALERT "pgd = %p\n", mm->pgd);
-	pgd = pgd_offset(mm, addr);
-	printk(KERN_ALERT "[%08lx] *pgd=%08lx", addr, pgd_val(*pgd));
-
-	do {
-		pmd_t *pmd;
-		pte_t *pte;
-
-		if (pgd_none(*pgd))
-			break;
-
-		if (pgd_bad(*pgd)) {
-			printk("(bad)");
-			break;
-		}
-
-		pmd = pmd_offset((pud_t *) pgd, addr);
-		if (PTRS_PER_PMD != 1)
-			printk(", *pmd=%08lx", pmd_val(*pmd));
-
-		if (pmd_none(*pmd))
-			break;
-
-		if (pmd_bad(*pmd)) {
-			printk("(bad)");
-			break;
-		}
-
-		/* We must not map this if we have highmem enabled */
-		if (PageHighMem(pfn_to_page(pmd_val(*pmd) >> PAGE_SHIFT)))
-			break;
-
-		pte = pte_offset_map(pmd, addr);
-		printk(", *pte=%08lx", pte_val(*pte));
-		pte_unmap(pte);
-	} while (0);
-
-	printk("\n");
-}
-
-/*
- * Oops.  The kernel tried to access some page that wasn't present.
- */
-static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
-		unsigned int fsr, struct pt_regs *regs)
-{
-	/*
-	 * Are we prepared to handle this kernel fault?
-	 */
-	if (fixup_exception(regs))
-		return;
-
-	/*
-	 * No handler, we'll have to terminate things with extreme prejudice.
-	 */
-	bust_spinlocks(1);
-	printk(KERN_ALERT
-	       "Unable to handle kernel %s at virtual address %08lx\n",
-	       (addr < PAGE_SIZE) ? "NULL pointer dereference" :
-	       "paging request", addr);
-
-	show_pte(mm, addr);
-	die("Oops", regs, fsr);
-	bust_spinlocks(0);
-	do_exit(SIGKILL);
-}
-
-/*
- * Something tried to access memory that isn't in our memory map..
- * User mode accesses just cause a SIGSEGV
- */
-static void __do_user_fault(unsigned long addr, unsigned int fsr,
-			    unsigned int sig, int code,	struct pt_regs *regs)
-{
-	struct task_struct *tsk = current;
-
-	tsk->thread.address = addr;
-	tsk->thread.error_code = fsr;
-	tsk->thread.trap_no = 14;
-	force_sig_fault(sig, code, (void __user *)addr);
-}
-
-void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
-{
-	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->active_mm;
-
-	/*
-	 * If we are in kernel mode at this point, we
-	 * have no context to handle this fault with.
-	 */
-	if (user_mode(regs))
-		__do_user_fault(addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
-	else
-		__do_kernel_fault(mm, addr, fsr, regs);
-}
-
-#define VM_FAULT_BADMAP		0x010000
-#define VM_FAULT_BADACCESS	0x020000
-
-/*
- * Check that the permissions on the VMA allow for the fault which occurred.
- * If we encountered a write fault, we must have write permission, otherwise
- * we allow any permission.
- */
-static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
-{
-	unsigned int mask = VM_ACCESS_FLAGS;
-
-	if (!(fsr ^ 0x12))	/* write? */
-		mask = VM_WRITE;
-	if (fsr & FSR_LNX_PF)
-		mask = VM_EXEC;
-
-	return vma->vm_flags & mask ? false : true;
-}
-
-static vm_fault_t __do_pf(struct mm_struct *mm, unsigned long addr,
-		unsigned int fsr, unsigned int flags, struct task_struct *tsk)
-{
-	struct vm_area_struct *vma;
-	vm_fault_t fault;
-
-	vma = find_vma(mm, addr);
-	fault = VM_FAULT_BADMAP;
-	if (unlikely(!vma))
-		goto out;
-	if (unlikely(vma->vm_start > addr))
-		goto check_stack;
-
-	/*
-	 * Ok, we have a good vm_area for this
-	 * memory access, so we can handle it.
-	 */
-good_area:
-	if (access_error(fsr, vma)) {
-		fault = VM_FAULT_BADACCESS;
-		goto out;
-	}
-
-	/*
-	 * If for any reason at all we couldn't handle the fault, make
-	 * sure we exit gracefully rather than endlessly redo the fault.
-	 */
-	fault = handle_mm_fault(vma, addr & PAGE_MASK, flags);
-	return fault;
-
-check_stack:
-	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
-		goto good_area;
-out:
-	return fault;
-}
-
-static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
-{
-	struct task_struct *tsk;
-	struct mm_struct *mm;
-	int sig, code;
-	vm_fault_t fault;
-	unsigned int flags = FAULT_FLAG_DEFAULT;
-
-	tsk = current;
-	mm = tsk->mm;
-
-	/*
-	 * If we're in an interrupt or have no user
-	 * context, we must not take the fault..
-	 */
-	if (faulthandler_disabled() || !mm)
-		goto no_context;
-
-	if (user_mode(regs))
-		flags |= FAULT_FLAG_USER;
-	if (!(fsr ^ 0x12))
-		flags |= FAULT_FLAG_WRITE;
-
-	/*
-	 * As per x86, we may deadlock here.  However, since the kernel only
-	 * validly references user space from well defined areas of the code,
-	 * we can bug out early if this is from code which shouldn't.
-	 */
-	if (!mmap_read_trylock(mm)) {
-		if (!user_mode(regs)
-		    && !search_exception_tables(regs->UCreg_pc))
-			goto no_context;
-retry:
-		mmap_read_lock(mm);
-	} else {
-		/*
-		 * The above down_read_trylock() might have succeeded in
-		 * which case, we'll have missed the might_sleep() from
-		 * down_read()
-		 */
-		might_sleep();
-#ifdef CONFIG_DEBUG_VM
-		if (!user_mode(regs) &&
-		    !search_exception_tables(regs->UCreg_pc))
-			goto no_context;
-#endif
-	}
-
-	fault = __do_pf(mm, addr, fsr, flags, tsk);
-
-	/* If we need to retry but a fatal signal is pending, handle the
-	 * signal first. We do not need to release the mmap_lock because
-	 * it would already be released in __lock_page_or_retry in
-	 * mm/filemap.c. */
-	if (fault_signal_pending(fault, regs))
-		return 0;
-
-	if (!(fault & VM_FAULT_ERROR) && (flags & FAULT_FLAG_ALLOW_RETRY)) {
-		if (fault & VM_FAULT_MAJOR)
-			tsk->maj_flt++;
-		else
-			tsk->min_flt++;
-		if (fault & VM_FAULT_RETRY) {
-			flags |= FAULT_FLAG_TRIED;
-			goto retry;
-		}
-	}
-
-	mmap_read_unlock(mm);
-
-	/*
-	 * Handle the "normal" case first - VM_FAULT_MAJOR
-	 */
-	if (likely(!(fault &
-	       (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
-		return 0;
-
-	/*
-	 * If we are in kernel mode at this point, we
-	 * have no context to handle this fault with.
-	 */
-	if (!user_mode(regs))
-		goto no_context;
-
-	if (fault & VM_FAULT_OOM) {
-		/*
-		 * We ran out of memory, call the OOM killer, and return to
-		 * userspace (which will retry the fault, or kill us if we
-		 * got oom-killed)
-		 */
-		pagefault_out_of_memory();
-		return 0;
-	}
-
-	if (fault & VM_FAULT_SIGBUS) {
-		/*
-		 * We had some memory, but were unable to
-		 * successfully fix up this page fault.
-		 */
-		sig = SIGBUS;
-		code = BUS_ADRERR;
-	} else {
-		/*
-		 * Something tried to access memory that
-		 * isn't in our memory map..
-		 */
-		sig = SIGSEGV;
-		code = fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR;
-	}
-
-	__do_user_fault(addr, fsr, sig, code, regs);
-	return 0;
-
-no_context:
-	__do_kernel_fault(mm, addr, fsr, regs);
-	return 0;
-}
-
-/*
- * First Level Translation Fault Handler
- *
- * We enter here because the first level page table doesn't contain
- * a valid entry for the address.
- *
- * If the address is in kernel space (>= TASK_SIZE), then we are
- * probably faulting in the vmalloc() area.
- *
- * If the init_task's first level page tables contains the relevant
- * entry, we copy the it to this task.  If not, we send the process
- * a signal, fixup the exception, or oops the kernel.
- *
- * NOTE! We MUST NOT take any locks for this case. We may be in an
- * interrupt or a critical region, and should only copy the information
- * from the master page table, nothing more.
- */
-static int do_ifault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
-{
-	unsigned int index;
-	pgd_t *pgd, *pgd_k;
-	pmd_t *pmd, *pmd_k;
-
-	if (addr < TASK_SIZE)
-		return do_pf(addr, fsr, regs);
-
-	if (user_mode(regs))
-		goto bad_area;
-
-	index = pgd_index(addr);
-
-	pgd = cpu_get_pgd() + index;
-	pgd_k = init_mm.pgd + index;
-
-	if (pgd_none(*pgd_k))
-		goto bad_area;
-
-	pmd_k = pmd_offset((pud_t *) pgd_k, addr);
-	pmd = pmd_offset((pud_t *) pgd, addr);
-
-	if (pmd_none(*pmd_k))
-		goto bad_area;
-
-	set_pmd(pmd, *pmd_k);
-	flush_pmd_entry(pmd);
-	return 0;
-
-bad_area:
-	do_bad_area(addr, fsr, regs);
-	return 0;
-}
-
-/*
- * This abort handler always returns "fault".
- */
-static int do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
-{
-	return 1;
-}
-
-static int do_good(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
-{
-	unsigned int res1, res2;
-
-	printk("dabt exception but no error!\n");
-
-	__asm__ __volatile__(
-			"mff %0,f0\n"
-			"mff %1,f1\n"
-			: "=r"(res1), "=r"(res2)
-			:
-			: "memory");
-
-	printk(KERN_EMERG "r0 :%08x  r1 :%08x\n", res1, res2);
-	panic("shut up\n");
-	return 0;
-}
-
-static struct fsr_info {
-	int (*fn) (unsigned long addr, unsigned int fsr, struct pt_regs *regs);
-	int sig;
-	int code;
-	const char *name;
-} fsr_info[] = {
-	/*
-	 * The following are the standard Unicore-I and UniCore-II aborts.
-	 */
-	{ do_good,	SIGBUS,  0,		"no error"		},
-	{ do_bad,	SIGBUS,  BUS_ADRALN,	"alignment exception"	},
-	{ do_bad,	SIGBUS,  BUS_OBJERR,	"external exception"	},
-	{ do_bad,	SIGBUS,  0,		"burst operation"	},
-	{ do_bad,	SIGBUS,  0,		"unknown 00100"		},
-	{ do_ifault,	SIGSEGV, SEGV_MAPERR,	"2nd level pt non-exist"},
-	{ do_bad,	SIGBUS,  0,		"2nd lvl large pt non-exist" },
-	{ do_bad,	SIGBUS,  0,		"invalid pte"		},
-	{ do_pf,	SIGSEGV, SEGV_MAPERR,	"page miss"		},
-	{ do_bad,	SIGBUS,  0,		"middle page miss"	},
-	{ do_bad,	SIGBUS,	 0,		"large page miss"	},
-	{ do_pf,	SIGSEGV, SEGV_MAPERR,	"super page (section) miss" },
-	{ do_bad,	SIGBUS,  0,		"unknown 01100"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 01101"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 01110"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 01111"		},
-	{ do_bad,	SIGBUS,  0,		"addr: up 3G or IO"	},
-	{ do_pf,	SIGSEGV, SEGV_ACCERR,	"read unreadable addr"	},
-	{ do_pf,	SIGSEGV, SEGV_ACCERR,	"write unwriteable addr"},
-	{ do_pf,	SIGSEGV, SEGV_ACCERR,	"exec unexecutable addr"},
-	{ do_bad,	SIGBUS,  0,		"unknown 10100"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 10101"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 10110"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 10111"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 11000"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 11001"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 11010"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 11011"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 11100"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 11101"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 11110"		},
-	{ do_bad,	SIGBUS,  0,		"unknown 11111"		}
-};
-
-void __init hook_fault_code(int nr,
-		int (*fn) (unsigned long, unsigned int, struct pt_regs *),
-		int sig, int code, const char *name)
-{
-	if (nr < 0 || nr >= ARRAY_SIZE(fsr_info))
-		BUG();
-
-	fsr_info[nr].fn   = fn;
-	fsr_info[nr].sig  = sig;
-	fsr_info[nr].code = code;
-	fsr_info[nr].name = name;
-}
-
-/*
- * Dispatch a data abort to the relevant handler.
- */
-asmlinkage void do_DataAbort(unsigned long addr, unsigned int fsr,
-			struct pt_regs *regs)
-{
-	const struct fsr_info *inf = fsr_info + fsr_fs(fsr);
-
-	if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs))
-		return;
-
-	printk(KERN_ALERT "Unhandled fault: %s (0x%03x) at 0x%08lx\n",
-	       inf->name, fsr, addr);
-
-	uc32_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
-			fsr, 0);
-}
-
-asmlinkage void do_PrefetchAbort(unsigned long addr,
-			unsigned int ifsr, struct pt_regs *regs)
-{
-	const struct fsr_info *inf = fsr_info + fsr_fs(ifsr);
-
-	if (!inf->fn(addr, ifsr | FSR_LNX_PF, regs))
-		return;
-
-	printk(KERN_ALERT "Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
-	       inf->name, ifsr, addr);
-
-	uc32_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
-			ifsr, 0);
-}
diff --git a/arch/unicore32/mm/flush.c b/arch/unicore32/mm/flush.c
deleted file mode 100644
index 65954f8d89a2..000000000000
--- a/arch/unicore32/mm/flush.c
+++ /dev/null
@@ -1,94 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/mm/flush.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-void flush_cache_mm(struct mm_struct *mm)
-{
-}
-
-void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
-		unsigned long end)
-{
-	if (vma->vm_flags & VM_EXEC)
-		__flush_icache_all();
-}
-
-void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr,
-		unsigned long pfn)
-{
-}
-
-static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
-			 unsigned long uaddr, void *kaddr, unsigned long len)
-{
-	/* VIPT non-aliasing D-cache */
-	if (vma->vm_flags & VM_EXEC) {
-		unsigned long addr = (unsigned long)kaddr;
-
-		__cpuc_coherent_kern_range(addr, addr + len);
-	}
-}
-
-/*
- * Copy user data from/to a page which is mapped into a different
- * processes address space.  Really, we want to allow our "user
- * space" model to handle this.
- *
- * Note that this code needs to run on the current CPU.
- */
-void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
-		       unsigned long uaddr, void *dst, const void *src,
-		       unsigned long len)
-{
-	memcpy(dst, src, len);
-	flush_ptrace_access(vma, page, uaddr, dst, len);
-}
-
-void __flush_dcache_page(struct address_space *mapping, struct page *page)
-{
-	/*
-	 * Writeback any data associated with the kernel mapping of this
-	 * page.  This ensures that data in the physical page is mutually
-	 * coherent with the kernels mapping.
-	 */
-	__cpuc_flush_kern_dcache_area(page_address(page), PAGE_SIZE);
-}
-
-/*
- * Ensure cache coherency between kernel mapping and userspace mapping
- * of this page.
- */
-void flush_dcache_page(struct page *page)
-{
-	struct address_space *mapping;
-
-	/*
-	 * The zero page is never written to, so never has any dirty
-	 * cache lines, and therefore never needs to be flushed.
-	 */
-	if (page == ZERO_PAGE(0))
-		return;
-
-	mapping = page_mapping_file(page);
-
-	if (mapping && !mapping_mapped(mapping))
-		clear_bit(PG_dcache_clean, &page->flags);
-	else {
-		__flush_dcache_page(mapping, page);
-		if (mapping)
-			__flush_icache_all();
-		set_bit(PG_dcache_clean, &page->flags);
-	}
-}
-EXPORT_SYMBOL(flush_dcache_page);
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
deleted file mode 100644
index 52425d383cea..000000000000
--- a/arch/unicore32/mm/init.c
+++ /dev/null
@@ -1,261 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  linux/arch/unicore32/mm/init.c
- *
- *  Copyright (C) 2010 GUAN Xue-tao
- */
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/swap.h>
-#include <linux/init.h>
-#include <linux/memblock.h>
-#include <linux/mman.h>
-#include <linux/nodemask.h>
-#include <linux/initrd.h>
-#include <linux/highmem.h>
-#include <linux/gfp.h>
-#include <linux/sort.h>
-#include <linux/dma-mapping.h>
-#include <linux/export.h>
-
-#include <asm/sections.h>
-#include <asm/setup.h>
-#include <linux/sizes.h>
-#include <asm/tlb.h>
-#include <asm/memblock.h>
-#include <mach/map.h>
-
-#include "mm.h"
-
-/*
- * This keeps memory configuration data used by a couple memory
- * initialization functions, as well as show_mem() for the skipping
- * of holes in the memory map.  It is populated by uc32_add_memory().
- */
-struct meminfo meminfo;
-
-static void __init find_limits(unsigned long *min, unsigned long *max_low,
-	unsigned long *max_high)
-{
-	struct meminfo *mi = &meminfo;
-	int i;
-
-	*min = -1UL;
-	*max_low = *max_high = 0;
-
-	for_each_bank(i, mi) {
-		struct membank *bank = &mi->bank[i];
-		unsigned long start, end;
-
-		start = bank_pfn_start(bank);
-		end = bank_pfn_end(bank);
-
-		if (*min > start)
-			*min = start;
-		if (*max_high < end)
-			*max_high = end;
-		if (bank->highmem)
-			continue;
-		if (*max_low < end)
-			*max_low = end;
-	}
-}
-
-static void __init uc32_bootmem_free(unsigned long max_low)
-{
-	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
-
-	max_zone_pfn[ZONE_DMA] = max_low;
-	max_zone_pfn[ZONE_NORMAL] = max_low;
-
-	/*
-	 * Adjust the sizes according to any special requirements for
-	 * this machine type.
-	 * This might lower ZONE_DMA limit.
-	 */
-	arch_adjust_zones(max_zone_pfn);
-
-	free_area_init(max_zone_pfn);
-}
-
-int pfn_valid(unsigned long pfn)
-{
-	return memblock_is_memory(pfn << PAGE_SHIFT);
-}
-EXPORT_SYMBOL(pfn_valid);
-
-static void uc32_memory_present(void)
-{
-}
-
-static int __init meminfo_cmp(const void *_a, const void *_b)
-{
-	const struct membank *a = _a, *b = _b;
-	long cmp = bank_pfn_start(a) - bank_pfn_start(b);
-	return cmp < 0 ? -1 : cmp > 0 ? 1 : 0;
-}
-
-void __init uc32_memblock_init(struct meminfo *mi)
-{
-	int i;
-
-	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]),
-		meminfo_cmp, NULL);
-
-	for (i = 0; i < mi->nr_banks; i++)
-		memblock_add(mi->bank[i].start, mi->bank[i].size);
-
-	/* Register the kernel text, kernel data and initrd with memblock. */
-	memblock_reserve(__pa(_text), _end - _text);
-
-#ifdef CONFIG_BLK_DEV_INITRD
-	if (!phys_initrd_size) {
-		phys_initrd_start = 0x01000000;
-		phys_initrd_size = SZ_8M;
-	}
-
-	if (phys_initrd_size) {
-		memblock_reserve(phys_initrd_start, phys_initrd_size);
-
-		/* Now convert initrd to virtual addresses */
-		initrd_start = __phys_to_virt(phys_initrd_start);
-		initrd_end = initrd_start + phys_initrd_size;
-	}
-#endif
-
-	uc32_mm_memblock_reserve();
-
-	memblock_allow_resize();
-	memblock_dump_all();
-}
-
-void __init bootmem_init(void)
-{
-	unsigned long min, max_low, max_high;
-
-	max_low = max_high = 0;
-
-	find_limits(&min, &max_low, &max_high);
-
-	node_set_online(0);
-
-	/*
-	 * Sparsemem tries to allocate bootmem in memory_present(),
-	 * so must be done after the fixed reservations
-	 */
-	uc32_memory_present();
-
-	/*
-	 * sparse_init() needs the bootmem allocator up and running.
-	 */
-	sparse_init();
-
-	/*
-	 * Now free the memory - free_area_init needs
-	 * the sparse mem_map arrays initialized by sparse_init()
-	 * for memmap_init_zone(), otherwise all PFNs are invalid.
-	 */
-	uc32_bootmem_free(max_low);
-
-	high_memory = __va((max_low << PAGE_SHIFT) - 1) + 1;
-
-	/*
-	 * This doesn't seem to be used by the Linux memory manager any
-	 * more, but is used by ll_rw_block.  If we can get rid of it, we
-	 * also get rid of some of the stuff above as well.
-	 *
-	 * Note: max_low_pfn and max_pfn reflect the number of _pages_ in
-	 * the system, not the maximum PFN.
-	 */
-	max_low_pfn = max_low - PHYS_PFN_OFFSET;
-	max_pfn = max_high - PHYS_PFN_OFFSET;
-}
-
-static inline void
-free_memmap(unsigned long start_pfn, unsigned long end_pfn)
-{
-	struct page *start_pg, *end_pg;
-	unsigned long pg, pgend;
-
-	/*
-	 * Convert start_pfn/end_pfn to a struct page pointer.
-	 */
-	start_pg = pfn_to_page(start_pfn - 1) + 1;
-	end_pg = pfn_to_page(end_pfn);
-
-	/*
-	 * Convert to physical addresses, and
-	 * round start upwards and end downwards.
-	 */
-	pg = PAGE_ALIGN(__pa(start_pg));
-	pgend = __pa(end_pg) & PAGE_MASK;
-
-	/*
-	 * If there are free pages between these,
-	 * free the section of the memmap array.
-	 */
-	if (pg < pgend)
-		memblock_free(pg, pgend - pg);
-}
-
-/*
- * The mem_map array can get very big.  Free the unused area of the memory map.
- */
-static void __init free_unused_memmap(struct meminfo *mi)
-{
-	unsigned long bank_start, prev_bank_end = 0;
-	unsigned int i;
-
-	/*
-	 * This relies on each bank being in address order.
-	 * The banks are sorted previously in bootmem_init().
-	 */
-	for_each_bank(i, mi) {
-		struct membank *bank = &mi->bank[i];
-
-		bank_start = bank_pfn_start(bank);
-
-		/*
-		 * If we had a previous bank, and there is a space
-		 * between the current bank and the previous, free it.
-		 */
-		if (prev_bank_end && prev_bank_end < bank_start)
-			free_memmap(prev_bank_end, bank_start);
-
-		/*
-		 * Align up here since the VM subsystem insists that the
-		 * memmap entries are valid from the bank end aligned to
-		 * MAX_ORDER_NR_PAGES.
-		 */
-		prev_bank_end = ALIGN(bank_pfn_end(bank), MAX_ORDER_NR_PAGES);
-	}
-}
-
-/*
- * mem_init() marks the free areas in the mem_map and tells us how much
- * memory is free.  This is done after various parts of the system have
- * claimed their memory after the kernel image.
- */
-void __init mem_init(void)
-{
-	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
-
-	free_unused_memmap(&meminfo);
-
-	/* this will put all unused low memory onto the freelists */
-	memblock_free_all();
-
-	mem_init_print_info(NULL);
-
-	BUILD_BUG_ON(TASK_SIZE				> MODULES_VADDR);
-	BUG_ON(TASK_SIZE				> MODULES_VADDR);
-
-	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
-		/*
-		 * On a machine this small we won't get
-		 * anywhere without overcommit, so turn
-		 * it on by default.
-		 */
-		sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
-	}
-}
diff --git a/arch/unicore32/mm/ioremap.c b/arch/unicore32/mm/ioremap.c
deleted file mode 100644
index 46a64bd6156a..000000000000
--- a/arch/unicore32/mm/ioremap.c
+++ /dev/null
@@ -1,242 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/mm/ioremap.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * Re-map IO memory to kernel address space so that we can access it.
- *
- * This allows a driver to remap an arbitrary region of bus memory into
- * virtual space.  One should *only* use readl, writel, memcpy_toio and
- * so on with such remapped areas.
- *
- * Because UniCore only has a 32-bit address space we can't address the
- * whole of the (physical) PCI space at once.  PCI huge-mode addressing
- * allows us to circumvent this restriction by splitting PCI space into
- * two 2GB chunks and mapping only one at a time into processor memory.
- * We use MMU protection domains to trap any attempt to access the bank
- * that is not currently mapped.  (This isn't fully implemented yet.)
- */
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/mm.h>
-#include <linux/vmalloc.h>
-#include <linux/io.h>
-
-#include <asm/cputype.h>
-#include <asm/cacheflush.h>
-#include <asm/mmu_context.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <linux/sizes.h>
-
-#include <mach/map.h>
-#include "mm.h"
-
-/*
- * Used by ioremap() and iounmap() code to mark (super)section-mapped
- * I/O regions in vm_struct->flags field.
- */
-#define VM_UNICORE_SECTION_MAPPING	0x80000000
-
-int ioremap_page(unsigned long virt, unsigned long phys,
-		 const struct mem_type *mtype)
-{
-	return ioremap_page_range(virt, virt + PAGE_SIZE, phys,
-				  __pgprot(mtype->prot_pte));
-}
-EXPORT_SYMBOL(ioremap_page);
-
-/*
- * Section support is unsafe on SMP - If you iounmap and ioremap a region,
- * the other CPUs will not see this change until their next context switch.
- * Meanwhile, (eg) if an interrupt comes in on one of those other CPUs
- * which requires the new ioremap'd region to be referenced, the CPU will
- * reference the _old_ region.
- *
- * Note that get_vm_area_caller() allocates a guard 4K page, so we need to
- * mask the size back to 4MB aligned or we will overflow in the loop below.
- */
-static void unmap_area_sections(unsigned long virt, unsigned long size)
-{
-	unsigned long addr = virt, end = virt + (size & ~(SZ_4M - 1));
-	pgd_t *pgd;
-
-	flush_cache_vunmap(addr, end);
-	pgd = pgd_offset_k(addr);
-	do {
-		pmd_t pmd, *pmdp = pmd_offset((pud_t *)pgd, addr);
-
-		pmd = *pmdp;
-		if (!pmd_none(pmd)) {
-			/*
-			 * Clear the PMD from the page table, and
-			 * increment the kvm sequence so others
-			 * notice this change.
-			 *
-			 * Note: this is still racy on SMP machines.
-			 */
-			pmd_clear(pmdp);
-
-			/*
-			 * Free the page table, if there was one.
-			 */
-			if ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_TABLE)
-				pte_free_kernel(&init_mm, pmd_page_vaddr(pmd));
-		}
-
-		addr += PGDIR_SIZE;
-		pgd++;
-	} while (addr < end);
-
-	flush_tlb_kernel_range(virt, end);
-}
-
-static int
-remap_area_sections(unsigned long virt, unsigned long pfn,
-		    size_t size, const struct mem_type *type)
-{
-	unsigned long addr = virt, end = virt + size;
-	pgd_t *pgd;
-
-	/*
-	 * Remove and free any PTE-based mapping, and
-	 * sync the current kernel mapping.
-	 */
-	unmap_area_sections(virt, size);
-
-	pgd = pgd_offset_k(addr);
-	do {
-		pmd_t *pmd = pmd_offset((pud_t *)pgd, addr);
-
-		set_pmd(pmd, __pmd(__pfn_to_phys(pfn) | type->prot_sect));
-		pfn += SZ_4M >> PAGE_SHIFT;
-		flush_pmd_entry(pmd);
-
-		addr += PGDIR_SIZE;
-		pgd++;
-	} while (addr < end);
-
-	return 0;
-}
-
-void __iomem *__uc32_ioremap_pfn_caller(unsigned long pfn,
-	unsigned long offset, size_t size, unsigned int mtype, void *caller)
-{
-	const struct mem_type *type;
-	int err;
-	unsigned long addr;
-	struct vm_struct *area;
-
-	/*
-	 * High mappings must be section aligned
-	 */
-	if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SECTION_MASK))
-		return NULL;
-
-	/*
-	 * Don't allow RAM to be mapped
-	 */
-	if (pfn_valid(pfn)) {
-		WARN(1, "BUG: Your driver calls ioremap() on\n"
-			"system memory.  This leads to architecturally\n"
-			"unpredictable behaviour, and ioremap() will fail in\n"
-			"the next kernel release. Please fix your driver.\n");
-		return NULL;
-	}
-
-	type = get_mem_type(mtype);
-	if (!type)
-		return NULL;
-
-	/*
-	 * Page align the mapping size, taking account of any offset.
-	 */
-	size = PAGE_ALIGN(offset + size);
-
-	area = get_vm_area_caller(size, VM_IOREMAP, caller);
-	if (!area)
-		return NULL;
-	addr = (unsigned long)area->addr;
-
-	if (!((__pfn_to_phys(pfn) | size | addr) & ~PMD_MASK)) {
-		area->flags |= VM_UNICORE_SECTION_MAPPING;
-		err = remap_area_sections(addr, pfn, size, type);
-	} else
-		err = ioremap_page_range(addr, addr + size, __pfn_to_phys(pfn),
-					 __pgprot(type->prot_pte));
-
-	if (err) {
-		vunmap((void *)addr);
-		return NULL;
-	}
-
-	flush_cache_vmap(addr, addr + size);
-	return (void __iomem *) (offset + addr);
-}
-
-void __iomem *__uc32_ioremap_caller(unsigned long phys_addr, size_t size,
-	unsigned int mtype, void *caller)
-{
-	unsigned long last_addr;
-	unsigned long offset = phys_addr & ~PAGE_MASK;
-	unsigned long pfn = __phys_to_pfn(phys_addr);
-
-	/*
-	 * Don't allow wraparound or zero size
-	 */
-	last_addr = phys_addr + size - 1;
-	if (!size || last_addr < phys_addr)
-		return NULL;
-
-	return __uc32_ioremap_pfn_caller(pfn, offset, size, mtype, caller);
-}
-
-/*
- * Remap an arbitrary physical address space into the kernel virtual
- * address space. Needed when the kernel wants to access high addresses
- * directly.
- *
- * NOTE! We need to allow non-page-aligned mappings too: we will obviously
- * have to convert them into an offset in a page-aligned mapping, but the
- * caller shouldn't need to know that small detail.
- */
-void __iomem *
-__uc32_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
-		  unsigned int mtype)
-{
-	return __uc32_ioremap_pfn_caller(pfn, offset, size, mtype,
-			__builtin_return_address(0));
-}
-EXPORT_SYMBOL(__uc32_ioremap_pfn);
-
-void __iomem *
-__uc32_ioremap(unsigned long phys_addr, size_t size)
-{
-	return __uc32_ioremap_caller(phys_addr, size, MT_DEVICE,
-			__builtin_return_address(0));
-}
-EXPORT_SYMBOL(__uc32_ioremap);
-
-void __uc32_iounmap(volatile void __iomem *io_addr)
-{
-	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-	struct vm_struct *vm;
-
-	/*
-	 * If this is a section based mapping we need to handle it
-	 * specially as the VM subsystem does not know how to handle
-	 * such a beast. We need the lock here b/c we need to clear
-	 * all the mappings before the area can be reclaimed
-	 * by someone else.
-	 */
-	vm = find_vm_area(addr);
-	if (vm && (vm->flags & VM_IOREMAP) &&
-		(vm->flags & VM_UNICORE_SECTION_MAPPING))
-		unmap_area_sections((unsigned long)vm->addr, vm->size);
-
-	vunmap(addr);
-}
-EXPORT_SYMBOL(__uc32_iounmap);
diff --git a/arch/unicore32/mm/mm.h b/arch/unicore32/mm/mm.h
deleted file mode 100644
index f157f5d249ab..000000000000
--- a/arch/unicore32/mm/mm.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/mm/mm.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <asm/hwdef-copro.h>
-
-/* the upper-most page table pointer */
-extern pmd_t *top_pmd;
-extern int sysctl_overcommit_memory;
-
-#define TOP_PTE(x)	pte_offset_kernel(top_pmd, x)
-
-struct mem_type {
-	unsigned int prot_pte;
-	unsigned int prot_l1;
-	unsigned int prot_sect;
-};
-
-const struct mem_type *get_mem_type(unsigned int type);
-
-extern void __flush_dcache_page(struct address_space *, struct page *);
-extern void hook_fault_code(int nr, int (*fn)
-		(unsigned long, unsigned int, struct pt_regs *),
-		int sig, int code, const char *name);
-
-void __init bootmem_init(void);
-void uc32_mm_memblock_reserve(void);
diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c
deleted file mode 100644
index 183d5b056814..000000000000
--- a/arch/unicore32/mm/mmu.c
+++ /dev/null
@@ -1,513 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/mm/mmu.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/mman.h>
-#include <linux/nodemask.h>
-#include <linux/memblock.h>
-#include <linux/fs.h>
-#include <linux/io.h>
-
-#include <asm/cputype.h>
-#include <asm/sections.h>
-#include <asm/setup.h>
-#include <linux/sizes.h>
-#include <asm/tlb.h>
-#include <asm/memblock.h>
-
-#include <mach/map.h>
-
-#include "mm.h"
-
-/*
- * empty_zero_page is a special page that is used for
- * zero-initialized data and COW.
- */
-struct page *empty_zero_page;
-EXPORT_SYMBOL(empty_zero_page);
-
-/*
- * The pmd table for the upper-most set of pages.
- */
-pmd_t *top_pmd;
-
-pgprot_t pgprot_user;
-EXPORT_SYMBOL(pgprot_user);
-
-pgprot_t pgprot_kernel;
-EXPORT_SYMBOL(pgprot_kernel);
-
-static int __init noalign_setup(char *__unused)
-{
-	cr_alignment &= ~CR_A;
-	cr_no_alignment &= ~CR_A;
-	set_cr(cr_alignment);
-	return 1;
-}
-__setup("noalign", noalign_setup);
-
-void adjust_cr(unsigned long mask, unsigned long set)
-{
-	unsigned long flags;
-
-	mask &= ~CR_A;
-
-	set &= mask;
-
-	local_irq_save(flags);
-
-	cr_no_alignment = (cr_no_alignment & ~mask) | set;
-	cr_alignment = (cr_alignment & ~mask) | set;
-
-	set_cr((get_cr() & ~mask) | set);
-
-	local_irq_restore(flags);
-}
-
-struct map_desc {
-	unsigned long virtual;
-	unsigned long pfn;
-	unsigned long length;
-	unsigned int type;
-};
-
-#define PROT_PTE_DEVICE		(PTE_PRESENT | PTE_YOUNG |	\
-				PTE_DIRTY | PTE_READ | PTE_WRITE)
-#define PROT_SECT_DEVICE	(PMD_TYPE_SECT | PMD_PRESENT |	\
-				PMD_SECT_READ | PMD_SECT_WRITE)
-
-static struct mem_type mem_types[] = {
-	[MT_DEVICE] = {		  /* Strongly ordered */
-		.prot_pte	= PROT_PTE_DEVICE,
-		.prot_l1	= PMD_TYPE_TABLE | PMD_PRESENT,
-		.prot_sect	= PROT_SECT_DEVICE,
-	},
-	/*
-	 * MT_KUSER: pte for vecpage -- cacheable,
-	 *       and sect for unigfx mmap -- noncacheable
-	 */
-	[MT_KUSER] = {
-		.prot_pte  = PTE_PRESENT | PTE_YOUNG | PTE_DIRTY |
-				PTE_CACHEABLE | PTE_READ | PTE_EXEC,
-		.prot_l1   = PMD_TYPE_TABLE | PMD_PRESENT,
-		.prot_sect = PROT_SECT_DEVICE,
-	},
-	[MT_HIGH_VECTORS] = {
-		.prot_pte  = PTE_PRESENT | PTE_YOUNG | PTE_DIRTY |
-				PTE_CACHEABLE | PTE_READ | PTE_WRITE |
-				PTE_EXEC,
-		.prot_l1   = PMD_TYPE_TABLE | PMD_PRESENT,
-	},
-	[MT_MEMORY] = {
-		.prot_pte  = PTE_PRESENT | PTE_YOUNG | PTE_DIRTY |
-				PTE_WRITE | PTE_EXEC,
-		.prot_l1   = PMD_TYPE_TABLE | PMD_PRESENT,
-		.prot_sect = PMD_TYPE_SECT | PMD_PRESENT | PMD_SECT_CACHEABLE |
-				PMD_SECT_READ | PMD_SECT_WRITE | PMD_SECT_EXEC,
-	},
-	[MT_ROM] = {
-		.prot_sect = PMD_TYPE_SECT | PMD_PRESENT | PMD_SECT_CACHEABLE |
-				PMD_SECT_READ,
-	},
-};
-
-const struct mem_type *get_mem_type(unsigned int type)
-{
-	return type < ARRAY_SIZE(mem_types) ? &mem_types[type] : NULL;
-}
-EXPORT_SYMBOL(get_mem_type);
-
-/*
- * Adjust the PMD section entries according to the CPU in use.
- */
-static void __init build_mem_type_table(void)
-{
-	pgprot_user   = __pgprot(PTE_PRESENT | PTE_YOUNG | PTE_CACHEABLE);
-	pgprot_kernel = __pgprot(PTE_PRESENT | PTE_YOUNG |
-				 PTE_DIRTY | PTE_READ | PTE_WRITE |
-				 PTE_EXEC | PTE_CACHEABLE);
-}
-
-#define vectors_base()	(vectors_high() ? 0xffff0000 : 0)
-
-static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr,
-		unsigned long prot)
-{
-	if (pmd_none(*pmd)) {
-		size_t size = PTRS_PER_PTE * sizeof(pte_t);
-		pte_t *pte = memblock_alloc(size, size);
-
-		if (!pte)
-			panic("%s: Failed to allocate %zu bytes align=%zx\n",
-			      __func__, size, size);
-
-		__pmd_populate(pmd, __pa(pte) | prot);
-	}
-	BUG_ON(pmd_bad(*pmd));
-	return pte_offset_kernel(pmd, addr);
-}
-
-static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
-				  unsigned long end, unsigned long pfn,
-				  const struct mem_type *type)
-{
-	pte_t *pte = early_pte_alloc(pmd, addr, type->prot_l1);
-	do {
-		set_pte(pte, pfn_pte(pfn, __pgprot(type->prot_pte)));
-		pfn++;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-}
-
-static void __init alloc_init_section(pgd_t *pgd, unsigned long addr,
-				      unsigned long end, unsigned long phys,
-				      const struct mem_type *type)
-{
-	pmd_t *pmd = pmd_offset((pud_t *)pgd, addr);
-
-	/*
-	 * Try a section mapping - end, addr and phys must all be aligned
-	 * to a section boundary.
-	 */
-	if (((addr | end | phys) & ~SECTION_MASK) == 0) {
-		pmd_t *p = pmd;
-
-		do {
-			set_pmd(pmd, __pmd(phys | type->prot_sect));
-			phys += SECTION_SIZE;
-		} while (pmd++, addr += SECTION_SIZE, addr != end);
-
-		flush_pmd_entry(p);
-	} else {
-		/*
-		 * No need to loop; pte's aren't interested in the
-		 * individual L1 entries.
-		 */
-		alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type);
-	}
-}
-
-/*
- * Create the page directory entries and any necessary
- * page tables for the mapping specified by `md'.  We
- * are able to cope here with varying sizes and address
- * offsets, and we take full advantage of sections.
- */
-static void __init create_mapping(struct map_desc *md)
-{
-	unsigned long phys, addr, length, end;
-	const struct mem_type *type;
-	pgd_t *pgd;
-
-	if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) {
-		printk(KERN_WARNING "BUG: not creating mapping for "
-		       "0x%08llx at 0x%08lx in user region\n",
-		       __pfn_to_phys((u64)md->pfn), md->virtual);
-		return;
-	}
-
-	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
-	    md->virtual >= PAGE_OFFSET && md->virtual < VMALLOC_END) {
-		printk(KERN_WARNING "BUG: mapping for 0x%08llx at 0x%08lx "
-		       "overlaps vmalloc space\n",
-		       __pfn_to_phys((u64)md->pfn), md->virtual);
-	}
-
-	type = &mem_types[md->type];
-
-	addr = md->virtual & PAGE_MASK;
-	phys = (unsigned long)__pfn_to_phys(md->pfn);
-	length = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));
-
-	if (type->prot_l1 == 0 && ((addr | phys | length) & ~SECTION_MASK)) {
-		printk(KERN_WARNING "BUG: map for 0x%08lx at 0x%08lx can not "
-		       "be mapped using pages, ignoring.\n",
-		       __pfn_to_phys(md->pfn), addr);
-		return;
-	}
-
-	pgd = pgd_offset_k(addr);
-	end = addr + length;
-	do {
-		unsigned long next = pgd_addr_end(addr, end);
-
-		alloc_init_section(pgd, addr, next, phys, type);
-
-		phys += next - addr;
-		addr = next;
-	} while (pgd++, addr != end);
-}
-
-static void * __initdata vmalloc_min = (void *)(VMALLOC_END - SZ_128M);
-
-/*
- * vmalloc=size forces the vmalloc area to be exactly 'size'
- * bytes. This can be used to increase (or decrease) the vmalloc
- * area - the default is 128m.
- */
-static int __init early_vmalloc(char *arg)
-{
-	unsigned long vmalloc_reserve = memparse(arg, NULL);
-
-	if (vmalloc_reserve < SZ_16M) {
-		vmalloc_reserve = SZ_16M;
-		printk(KERN_WARNING
-			"vmalloc area too small, limiting to %luMB\n",
-			vmalloc_reserve >> 20);
-	}
-
-	if (vmalloc_reserve > VMALLOC_END - (PAGE_OFFSET + SZ_32M)) {
-		vmalloc_reserve = VMALLOC_END - (PAGE_OFFSET + SZ_32M);
-		printk(KERN_WARNING
-			"vmalloc area is too big, limiting to %luMB\n",
-			vmalloc_reserve >> 20);
-	}
-
-	vmalloc_min = (void *)(VMALLOC_END - vmalloc_reserve);
-	return 0;
-}
-early_param("vmalloc", early_vmalloc);
-
-static phys_addr_t lowmem_limit __initdata = SZ_1G;
-
-static void __init sanity_check_meminfo(void)
-{
-	int i, j;
-
-	lowmem_limit = __pa(vmalloc_min - 1) + 1;
-	memblock_set_current_limit(lowmem_limit);
-
-	for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
-		struct membank *bank = &meminfo.bank[j];
-		*bank = meminfo.bank[i];
-		j++;
-	}
-	meminfo.nr_banks = j;
-}
-
-static inline void prepare_page_table(void)
-{
-	unsigned long addr;
-	phys_addr_t end;
-
-	/*
-	 * Clear out all the mappings below the kernel image.
-	 */
-	for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
-		pmd_clear(pmd_off_k(addr));
-
-	for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
-		pmd_clear(pmd_off_k(addr));
-
-	/*
-	 * Find the end of the first block of lowmem.
-	 */
-	end = memblock.memory.regions[0].base + memblock.memory.regions[0].size;
-	if (end >= lowmem_limit)
-		end = lowmem_limit;
-
-	/*
-	 * Clear out all the kernel space mappings, except for the first
-	 * memory bank, up to the end of the vmalloc region.
-	 */
-	for (addr = __phys_to_virt(end);
-	     addr < VMALLOC_END; addr += PGDIR_SIZE)
-		pmd_clear(pmd_off_k(addr));
-}
-
-/*
- * Reserve the special regions of memory
- */
-void __init uc32_mm_memblock_reserve(void)
-{
-	/*
-	 * Reserve the page tables.  These are already in use,
-	 * and can only be in node 0.
-	 */
-	memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
-}
-
-/*
- * Set up device the mappings.  Since we clear out the page tables for all
- * mappings above VMALLOC_END, we will remove any debug device mappings.
- * This means you have to be careful how you debug this function, or any
- * called function.  This means you can't use any function or debugging
- * method which may touch any device, otherwise the kernel _will_ crash.
- */
-static void __init devicemaps_init(void)
-{
-	struct map_desc map;
-	unsigned long addr;
-	void *vectors;
-
-	/*
-	 * Allocate the vector page early.
-	 */
-	vectors = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!vectors)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
-
-	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
-		pmd_clear(pmd_off_k(addr));
-
-	/*
-	 * Create a mapping for the machine vectors at the high-vectors
-	 * location (0xffff0000).  If we aren't using high-vectors, also
-	 * create a mapping at the low-vectors virtual address.
-	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
-	map.virtual = VECTORS_BASE;
-	map.length = PAGE_SIZE;
-	map.type = MT_HIGH_VECTORS;
-	create_mapping(&map);
-
-	/*
-	 * Create a mapping for the kuser page at the special
-	 * location (0xbfff0000) to the same vectors location.
-	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
-	map.virtual = KUSER_VECPAGE_BASE;
-	map.length = PAGE_SIZE;
-	map.type = MT_KUSER;
-	create_mapping(&map);
-
-	/*
-	 * Finally flush the caches and tlb to ensure that we're in a
-	 * consistent state wrt the writebuffer.  This also ensures that
-	 * any write-allocated cache lines in the vector page are written
-	 * back.  After this point, we can start to touch devices again.
-	 */
-	local_flush_tlb_all();
-	flush_cache_all();
-}
-
-static void __init map_lowmem(void)
-{
-	struct memblock_region *reg;
-
-	/* Map all the lowmem memory banks. */
-	for_each_memblock(memory, reg) {
-		phys_addr_t start = reg->base;
-		phys_addr_t end = start + reg->size;
-		struct map_desc map;
-
-		if (end > lowmem_limit)
-			end = lowmem_limit;
-		if (start >= end)
-			break;
-
-		map.pfn = __phys_to_pfn(start);
-		map.virtual = __phys_to_virt(start);
-		map.length = end - start;
-		map.type = MT_MEMORY;
-
-		create_mapping(&map);
-	}
-}
-
-/*
- * paging_init() sets up the page tables, initialises the zone memory
- * maps, and sets up the zero page, bad page and bad page tables.
- */
-void __init paging_init(void)
-{
-	void *zero_page;
-
-	build_mem_type_table();
-	sanity_check_meminfo();
-	prepare_page_table();
-	map_lowmem();
-	devicemaps_init();
-
-	top_pmd = pmd_off_k(0xffff0000);
-
-	/* allocate the zero page. */
-	zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!zero_page)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
-
-	bootmem_init();
-
-	empty_zero_page = virt_to_page(zero_page);
-	__flush_dcache_page(NULL, empty_zero_page);
-}
-
-/*
- * In order to soft-boot, we need to insert a 1:1 mapping in place of
- * the user-mode pages.  This will then ensure that we have predictable
- * results when turning the mmu off
- */
-void setup_mm_for_reboot(void)
-{
-	unsigned long base_pmdval;
-	pgd_t *pgd;
-	int i;
-
-	/*
-	 * We need to access to user-mode page tables here. For kernel threads
-	 * we don't have any user-mode mappings so we use the context that we
-	 * "borrowed".
-	 */
-	pgd = current->active_mm->pgd;
-
-	base_pmdval = PMD_SECT_WRITE | PMD_SECT_READ | PMD_TYPE_SECT;
-
-	for (i = 0; i < FIRST_USER_PGD_NR + USER_PTRS_PER_PGD; i++, pgd++) {
-		unsigned long pmdval = (i << PGDIR_SHIFT) | base_pmdval;
-		pmd_t *pmd;
-
-		pmd = pmd_off(pgd, i << PGDIR_SHIFT);
-		set_pmd(pmd, __pmd(pmdval));
-		flush_pmd_entry(pmd);
-	}
-
-	local_flush_tlb_all();
-}
-
-/*
- * Take care of architecture specific things when placing a new PTE into
- * a page table, or changing an existing PTE.  Basically, there are two
- * things that we need to take care of:
- *
- *  1. If PG_dcache_clean is not set for the page, we need to ensure
- *     that any cache entries for the kernels virtual memory
- *     range are written back to the page.
- *  2. If we have multiple shared mappings of the same space in
- *     an object, we need to deal with the cache aliasing issues.
- *
- * Note that the pte lock will be held.
- */
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
-	pte_t *ptep)
-{
-	unsigned long pfn = pte_pfn(*ptep);
-	struct address_space *mapping;
-	struct page *page;
-
-	if (!pfn_valid(pfn))
-		return;
-
-	/*
-	 * The zero page is never written to, so never has any dirty
-	 * cache lines, and therefore never needs to be flushed.
-	 */
-	page = pfn_to_page(pfn);
-	if (page == ZERO_PAGE(0))
-		return;
-
-	mapping = page_mapping_file(page);
-	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
-		__flush_dcache_page(mapping, page);
-	if (mapping)
-		if (vma->vm_flags & VM_EXEC)
-			__flush_icache_all();
-}
diff --git a/arch/unicore32/mm/pgd.c b/arch/unicore32/mm/pgd.c
deleted file mode 100644
index f01c73e04836..000000000000
--- a/arch/unicore32/mm/pgd.c
+++ /dev/null
@@ -1,102 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/mm/pgd.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/mm.h>
-#include <linux/gfp.h>
-#include <linux/highmem.h>
-
-#include <asm/pgalloc.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-
-#include "mm.h"
-
-#define FIRST_KERNEL_PGD_NR	(FIRST_USER_PGD_NR + USER_PTRS_PER_PGD)
-
-/*
- * need to get a 4k page for level 1
- */
-pgd_t *get_pgd_slow(struct mm_struct *mm)
-{
-	pgd_t *new_pgd, *init_pgd;
-	pmd_t *new_pmd, *init_pmd;
-	pte_t *new_pte, *init_pte;
-
-	new_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, 0);
-	if (!new_pgd)
-		goto no_pgd;
-
-	memset(new_pgd, 0, FIRST_KERNEL_PGD_NR * sizeof(pgd_t));
-
-	/*
-	 * Copy over the kernel and IO PGD entries
-	 */
-	init_pgd = pgd_offset_k(0);
-	memcpy(new_pgd + FIRST_KERNEL_PGD_NR, init_pgd + FIRST_KERNEL_PGD_NR,
-		       (PTRS_PER_PGD - FIRST_KERNEL_PGD_NR) * sizeof(pgd_t));
-
-	clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
-
-	if (!vectors_high()) {
-		/*
-		 * On UniCore, first page must always be allocated since it
-		 * contains the machine vectors.
-		 */
-		new_pmd = pmd_alloc(mm, (pud_t *)new_pgd, 0);
-		if (!new_pmd)
-			goto no_pmd;
-
-		new_pte = pte_alloc_map(mm, new_pmd, 0);
-		if (!new_pte)
-			goto no_pte;
-
-		init_pmd = pmd_offset((pud_t *)init_pgd, 0);
-		init_pte = pte_offset_map(init_pmd, 0);
-		set_pte(new_pte, *init_pte);
-		pte_unmap(init_pte);
-		pte_unmap(new_pte);
-	}
-
-	return new_pgd;
-
-no_pte:
-	pmd_free(mm, new_pmd);
-	mm_dec_nr_pmds(mm);
-no_pmd:
-	free_pages((unsigned long)new_pgd, 0);
-no_pgd:
-	return NULL;
-}
-
-void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd)
-{
-	pmd_t *pmd;
-	pgtable_t pte;
-
-	if (!pgd)
-		return;
-
-	/* pgd is always present and good */
-	pmd = pmd_off(pgd, 0);
-	if (pmd_none(*pmd))
-		goto free;
-	if (pmd_bad(*pmd)) {
-		pmd_ERROR(*pmd);
-		pmd_clear(pmd);
-		goto free;
-	}
-
-	pte = pmd_pgtable(*pmd);
-	pmd_clear(pmd);
-	pte_free(mm, pte);
-	mm_dec_nr_ptes(mm);
-	pmd_free(mm, pmd);
-	mm_dec_nr_pmds(mm);
-free:
-	free_pages((unsigned long) pgd, 0);
-}
diff --git a/arch/unicore32/mm/proc-macros.S b/arch/unicore32/mm/proc-macros.S
deleted file mode 100644
index 3b0ae7d5bd80..000000000000
--- a/arch/unicore32/mm/proc-macros.S
+++ /dev/null
@@ -1,142 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/mm/proc-macros.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * We need constants.h for:
- *  VMA_VM_MM
- *  VMA_VM_FLAGS
- *  VM_EXEC
- */
-#include <generated/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/memory.h>
-
-/*
- * the cache line sizes of the I and D cache are the same
- */
-#define CACHE_LINESIZE	32
-
-/*
- * This is the maximum size of an area which will be invalidated
- * using the single invalidate entry instructions.  Anything larger
- * than this, and we go for the whole cache.
- *
- * This value should be chosen such that we choose the cheapest
- * alternative.
- */
-#ifdef CONFIG_CPU_UCV2
-#define MAX_AREA_SIZE	0x800		/* 64 cache line */
-#endif
-
-/*
- * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
- */
-	.macro	vma_vm_mm, rd, rn
-	ldw	\rd, [\rn+], #VMA_VM_MM
-	.endm
-
-/*
- * vma_vm_flags - get vma->vm_flags
- */
-	.macro	vma_vm_flags, rd, rn
-	ldw	\rd, [\rn+], #VMA_VM_FLAGS
-	.endm
-
-	.macro	tsk_mm, rd, rn
-	ldw	\rd, [\rn+], #TI_TASK
-	ldw	\rd, [\rd+], #TSK_ACTIVE_MM
-	.endm
-
-/*
- * act_mm - get current->active_mm
- */
-	.macro	act_mm, rd
-	andn	\rd, sp, #8128
-	andn	\rd, \rd, #63
-	ldw	\rd, [\rd+], #TI_TASK
-	ldw	\rd, [\rd+], #TSK_ACTIVE_MM
-	.endm
-
-/*
- * mmid - get context id from mm pointer (mm->context.id)
- */
-	.macro	mmid, rd, rn
-	ldw	\rd, [\rn+], #MM_CONTEXT_ID
-	.endm
-
-/*
- * mask_asid - mask the ASID from the context ID
- */
-	.macro	asid, rd, rn
-	and	\rd, \rn, #255
-	.endm
-
-	.macro	crval, clear, mmuset, ucset
-	.word	\clear
-	.word	\mmuset
-	.endm
-
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-/*
- * va2pa va, pa, tbl, msk, off, err
- *	This macro is used to translate virtual address to its physical address.
- *
- *	va: virtual address
- *	pa: physical address, result is stored in this register
- *	tbl, msk, off:	temp registers, will be destroyed
- *	err: jump to error label if the physical address not exist
- * NOTE: all regs must be different
- */
-	.macro	va2pa, va, pa, tbl, msk, off, err=990f
-	movc	\pa, p0.c2, #0
-	mov	\off, \va >> #22		@ off <- index of 1st page table
-	adr	\tbl, 910f			@ tbl <- table of 1st page table
-900:						@ ---- handle 1, 2 page table
-	add	\pa, \pa, #PAGE_OFFSET		@ pa <- virt addr of page table
-	ldw	\pa, [\pa+], \off << #2		@ pa <- the content of pt
-	cand.a	\pa, #4				@ test exist bit
-	beq	\err				@ if not exist
-	and	\off, \pa, #3			@ off <- the last 2 bits
-	add	\tbl, \tbl, \off << #3		@ cmove table pointer
-	ldw	\msk, [\tbl+], #0		@ get the mask
-	ldw	pc, [\tbl+], #4
-930:						@ ---- handle 2nd page table
-	and	\pa, \pa, \msk			@ pa <- phys addr of 2nd pt
-	mov	\off, \va << #10
-	cntlo	\tbl, \msk			@ use tbl as temp reg
-	mov	\off, \off >> \tbl
-	mov	\off, \off >> #2		@ off <- index of 2nd pt
-	adr	\tbl, 920f			@ tbl <- table of 2nd pt
-	b	900b
-910:						@ 1st level page table
-	.word	0xfffff000, 930b		@ second level page table
-	.word	0xfffffc00, 930b		@ second level large page table
-	.word	0x00000000, \err		@ invalid
-	.word	0xffc00000, 980f		@ super page
-
-920:						@ 2nd level page table
-	.word	0xfffff000, 980f		@ page
-	.word	0xffffc000, 980f		@ middle page
-	.word	0xffff0000, 980f		@ large page
-	.word	0x00000000, \err		@ invalid
-980:
-	andn	\tbl, \va, \msk
-	and	\pa, \pa, \msk
-	or	\pa, \pa, \tbl
-990:
-	.endm
-#endif
-
-	.macro dcacheline_flush, addr, t1, t2
-	mov	\t1, \addr << #20
-	ldw	\t2, =_stext			@ _stext must ALIGN(4096)
-	add	\t2, \t2, \t1 >> #20
-	ldw	\t1, [\t2+], #0x0000
-	ldw	\t1, [\t2+], #0x1000
-	ldw	\t1, [\t2+], #0x2000
-	ldw	\t1, [\t2+], #0x3000
-	.endm
diff --git a/arch/unicore32/mm/proc-syms.c b/arch/unicore32/mm/proc-syms.c
deleted file mode 100644
index 6c081616fc3c..000000000000
--- a/arch/unicore32/mm/proc-syms.c
+++ /dev/null
@@ -1,19 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/unicore32/mm/proc-syms.c
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/module.h>
-#include <linux/mm.h>
-
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-#include <asm/page.h>
-
-EXPORT_SYMBOL(cpu_dcache_clean_area);
-EXPORT_SYMBOL(cpu_set_pte);
-
-EXPORT_SYMBOL(__cpuc_coherent_kern_range);
diff --git a/arch/unicore32/mm/proc-ucv2.S b/arch/unicore32/mm/proc-ucv2.S
deleted file mode 100644
index 18f8c4fb21a0..000000000000
--- a/arch/unicore32/mm/proc-ucv2.S
+++ /dev/null
@@ -1,131 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/mm/proc-ucv2.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/pgtable.h>
-#include <asm/assembler.h>
-#include <asm/hwcap.h>
-#include <asm/pgtable-hwdef.h>
-
-#include "proc-macros.S"
-
-ENTRY(cpu_proc_fin)
-	stm.w	(lr), [sp-]
-	mov	ip, #PSR_R_BIT | PSR_I_BIT | PRIV_MODE
-	mov.a	asr, ip
-	b.l	__cpuc_flush_kern_all
-	ldm.w	(pc), [sp]+
-
-/*
- *	cpu_reset(loc)
- *
- *	Perform a soft reset of the system.  Put the CPU into the
- *	same state as it would be if it had been reset, and branch
- *	to what would be the reset vector.
- *
- *	- loc   - location to jump to for soft reset
- */
-	.align	5
-ENTRY(cpu_reset)
-	mov	ip, #0
-	movc	p0.c5, ip, #28			@ Cache invalidate all
-	nop8
-
-	movc	p0.c6, ip, #6			@ TLB invalidate all
-	nop8
-
-	movc	ip, p0.c1, #0			@ ctrl register
-	or	ip, ip, #0x2000			@ vector base address
-	andn	ip, ip, #0x000f			@ ............idam
-	movc	p0.c1, ip, #0			@ disable caches and mmu
-	nop
-	mov	pc, r0				@ jump to loc
-	nop8
-
-/*
- *	cpu_do_idle()
- *
- *	Idle the processor (eg, wait for interrupt).
- *
- *	IRQs are already disabled.
- */
-ENTRY(cpu_do_idle)
-	mov	r0, #0				@ PCI address
-	.rept	8
-	ldw	r1, [r0]
-	.endr
-	mov	pc, lr
-
-ENTRY(cpu_dcache_clean_area)
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-	csub.a	r1, #MAX_AREA_SIZE
-	bsg	101f
-	mov	r9, #PAGE_SZ
-	sub	r9, r9, #1			@ PAGE_MASK
-1:	va2pa	r0, r10, r11, r12, r13		@ r10 is PA
-	b	3f
-2:	cand.a	r0, r9
-	beq	1b
-3:	movc	p0.c5, r10, #11			@ clean D entry
-	nop8
-	add	r0, r0, #CACHE_LINESIZE
-	add	r10, r10, #CACHE_LINESIZE
-	sub.a	r1, r1, #CACHE_LINESIZE
-	bua	2b
-	mov	pc, lr
-#endif
-101:	mov	ip, #0
-	movc	p0.c5, ip, #10			@ Dcache clean all
-	nop8
-
-	mov	pc, lr
-
-/*
- *	cpu_do_switch_mm(pgd_phys)
- *
- *	Set the translation table base pointer to be pgd_phys
- *
- *	- pgd_phys - physical address of new pgd
- *
- *	It is assumed that:
- *	- we are not using split page tables
- */
-	.align	5
-ENTRY(cpu_do_switch_mm)
-	movc	p0.c2, r0, #0			@ update page table ptr
-	nop8
-
-	movc	p0.c6, ip, #6			@ TLB invalidate all
-	nop8
-
-	mov	pc, lr
-
-/*
- *	cpu_set_pte(ptep, pte)
- *
- *	Set a level 2 translation table entry.
- *
- *	- ptep  - pointer to level 2 translation table entry
- *	- pte   - PTE value to store
- */
-	.align	5
-ENTRY(cpu_set_pte)
-	stw	r1, [r0]
-#ifndef CONFIG_CPU_DCACHE_LINE_DISABLE
-	sub	r2, r0, #PAGE_OFFSET
-	movc	p0.c5, r2, #11				@ Dcache clean line
-	nop8
-#else
-	mov	ip, #0
-	movc	p0.c5, ip, #10				@ Dcache clean all
-	nop8
-	@dcacheline_flush	r0, r2, ip
-#endif
-	mov	pc, lr
-
diff --git a/arch/unicore32/mm/tlb-ucv2.S b/arch/unicore32/mm/tlb-ucv2.S
deleted file mode 100644
index 0ce9c6b6f1db..000000000000
--- a/arch/unicore32/mm/tlb-ucv2.S
+++ /dev/null
@@ -1,86 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/arch/unicore32/mm/tlb-ucv2.S
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- */
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-#include "proc-macros.S"
-
-/*
- *	__cpu_flush_user_tlb_range(start, end, vma)
- *
- *	Invalidate a range of TLB entries in the specified address space.
- *
- *	- start - start address (may not be aligned)
- *	- end   - end address (exclusive, may not be aligned)
- *	- vma   - vma_struct describing address range
- */
-ENTRY(__cpu_flush_user_tlb_range)
-#ifndef	CONFIG_CPU_TLB_SINGLE_ENTRY_DISABLE
-	mov	r0, r0 >> #PAGE_SHIFT		@ align address
-	mov	r0, r0 << #PAGE_SHIFT
-	vma_vm_flags r2, r2			@ get vma->vm_flags
-1:
-	movc	p0.c6, r0, #3
-	nop8
-
-	cand.a	r2, #VM_EXEC			@ Executable area ?
-	beq	2f
-
-	movc	p0.c6, r0, #5
-	nop8
-2:
-	add	r0, r0, #PAGE_SZ
-	csub.a	r0, r1
-	beb	1b
-#else
-	movc	p0.c6, r0, #2
-	nop8
-
-	cand.a	r2, #VM_EXEC			@ Executable area ?
-	beq	2f
-
-	movc	p0.c6, r0, #4
-	nop8
-2:
-#endif
-	mov	pc, lr
-
-/*
- *	__cpu_flush_kern_tlb_range(start,end)
- *
- *	Invalidate a range of kernel TLB entries
- *
- *	- start - start address (may not be aligned)
- *	- end   - end address (exclusive, may not be aligned)
- */
-ENTRY(__cpu_flush_kern_tlb_range)
-#ifndef	CONFIG_CPU_TLB_SINGLE_ENTRY_DISABLE
-	mov	r0, r0 >> #PAGE_SHIFT		@ align address
-	mov	r0, r0 << #PAGE_SHIFT
-1:
-	movc	p0.c6, r0, #3
-	nop8
-
-	movc	p0.c6, r0, #5
-	nop8
-
-	add	r0, r0, #PAGE_SZ
-	csub.a	r0, r1
-	beb	1b
-#else
-	movc	p0.c6, r0, #2
-	nop8
-
-	movc	p0.c6, r0, #4
-	nop8
-#endif
-	mov	pc, lr
-
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a0cc524882d..883da0abf779 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -67,7 +67,7 @@ config X86
 	select ARCH_HAS_FILTER_PGPROT
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_KCOV			if X86_64
+	select ARCH_HAS_KCOV			if X86_64 && STACK_VALIDATION
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 0dd319e6e5b4..ee1d3c5834c6 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -3,6 +3,9 @@
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
+config TRACE_IRQFLAGS_NMI_SUPPORT
+	def_bool y
+
 config EARLY_PRINTK_USB
 	bool
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 7619742f91c9..5a828fde7a42 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -90,8 +90,8 @@ endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
 
-vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
+efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a
 
 # The compressed kernel is built with -fPIC/-fPIE so that a boot loader
 # can place it anywhere in memory and it will still run. However, since
@@ -115,7 +115,7 @@ endef
 quiet_cmd_check-and-link-vmlinux = LD      $@
       cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
 
-$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
+$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE
 	$(call if_changed,check-and-link-vmlinux)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index e821a7d7d5c4..97d37f0a34f5 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -213,7 +213,6 @@ SYM_FUNC_START(startup_32)
 	 * We place all of the values on our mini stack so lret can
 	 * used to perform that far jump.
 	 */
-	pushl	$__KERNEL_CS
 	leal	startup_64(%ebp), %eax
 #ifdef CONFIG_EFI_MIXED
 	movl	efi32_boot_args(%ebp), %edi
@@ -224,11 +223,20 @@ SYM_FUNC_START(startup_32)
 	movl	efi32_boot_args+8(%ebp), %edx	// saved bootparams pointer
 	cmpl	$0, %edx
 	jnz	1f
+	/*
+	 * efi_pe_entry uses MS calling convention, which requires 32 bytes of
+	 * shadow space on the stack even if all arguments are passed in
+	 * registers. We also need an additional 8 bytes for the space that
+	 * would be occupied by the return address, and this also results in
+	 * the correct stack alignment for entry.
+	 */
+	subl	$40, %esp
 	leal	efi_pe_entry(%ebp), %eax
 	movl	%edi, %ecx			// MS calling convention
 	movl	%esi, %edx
 1:
 #endif
+	pushl	$__KERNEL_CS
 	pushl	%eax
 
 	/* Enter paged protected Mode, activating Long Mode */
@@ -784,6 +792,7 @@ SYM_DATA_LOCAL(boot_heap,	.fill BOOT_HEAP_SIZE, 1, 0)
 
 SYM_DATA_START_LOCAL(boot_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
+	.balign 16
 SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end)
 
 /*
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index ec437db1fa54..3f0fc7dd87d7 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -63,7 +63,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 
 #define VMOVDQ		vmovdqu
 
@@ -127,10 +126,6 @@ ddq_add_8:
 
 /* generate a unique variable for ddq_add_x */
 
-.macro setddq n
-	var_ddq_add = ddq_add_\n
-.endm
-
 /* generate a unique variable for xmm register */
 .macro setxdata n
 	var_xdata = %xmm\n
@@ -140,9 +135,7 @@ ddq_add_8:
 
 .macro club name, id
 .altmacro
-	.if \name == DDQ_DATA
-		setddq %\id
-	.elseif \name == XDATA
+	.if \name == XDATA
 		setxdata %\id
 	.endif
 .noaltmacro
@@ -165,9 +158,8 @@ ddq_add_8:
 
 	.set i, 1
 	.rept (by - 1)
-		club DDQ_DATA, i
 		club XDATA, i
-		vpaddq	var_ddq_add(%rip), xcounter, var_xdata
+		vpaddq	(ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata
 		vptest	ddq_low_msk(%rip), var_xdata
 		jnz 1f
 		vpaddq	ddq_high_add_1(%rip), var_xdata, var_xdata
@@ -180,8 +172,7 @@ ddq_add_8:
 	vmovdqa	1*16(p_keys), xkeyA
 
 	vpxor	xkey0, xdata0, xdata0
-	club DDQ_DATA, by
-	vpaddq	var_ddq_add(%rip), xcounter, xcounter
+	vpaddq	(ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter
 	vptest	ddq_low_msk(%rip), xcounter
 	jnz	1f
 	vpaddq	ddq_high_add_1(%rip), xcounter, xcounter
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 54e7d15dbd0d..1852b19a73a0 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -26,7 +26,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 #include <asm/frame.h>
 #include <asm/nospec-branch.h>
 
@@ -201,7 +200,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	mov	\SUBKEY, %r12
 	movdqu	(%r12), \TMP3
 	movdqa	SHUF_MASK(%rip), \TMP2
-	PSHUFB_XMM \TMP2, \TMP3
+	pshufb	\TMP2, \TMP3
 
 	# precompute HashKey<<1 mod poly from the HashKey (required for GHASH)
 
@@ -263,10 +262,10 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	movdqu %xmm0, OrigIV(%arg2) # ctx_data.orig_IV = iv
 
 	movdqa  SHUF_MASK(%rip), %xmm2
-	PSHUFB_XMM %xmm2, %xmm0
+	pshufb %xmm2, %xmm0
 	movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
 
-	PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
+	PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7
 	movdqu HashKey(%arg2), %xmm13
 
 	CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \
@@ -347,7 +346,7 @@ _zero_cipher_left_\@:
 	paddd ONE(%rip), %xmm0                # INCR CNT to get Yn
 	movdqu %xmm0, CurCount(%arg2)
 	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm0
+	pshufb %xmm10, %xmm0
 
 	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm1        # Encrypt(K, Yn)
 	movdqu %xmm0, PBlockEncKey(%arg2)
@@ -377,7 +376,7 @@ _large_enough_update_\@:
 	# get the appropriate shuffle mask
 	movdqu	(%r12), %xmm2
 	# shift right 16-r13 bytes
-	PSHUFB_XMM  %xmm2, %xmm1
+	pshufb  %xmm2, %xmm1
 
 _data_read_\@:
 	lea ALL_F+16(%rip), %r12
@@ -393,12 +392,12 @@ _data_read_\@:
 .ifc \operation, dec
 	pand    %xmm1, %xmm2
 	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10 ,%xmm2
+	pshufb %xmm10 ,%xmm2
 
 	pxor %xmm2, %xmm8
 .else
 	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10,%xmm0
+	pshufb %xmm10,%xmm0
 
 	pxor	%xmm0, %xmm8
 .endif
@@ -408,17 +407,17 @@ _data_read_\@:
 	# GHASH computation for the last <16 byte block
 	movdqa SHUF_MASK(%rip), %xmm10
 	# shuffle xmm0 back to output as ciphertext
-	PSHUFB_XMM %xmm10, %xmm0
+	pshufb %xmm10, %xmm0
 .endif
 
 	# Output %r13 bytes
-	MOVQ_R64_XMM %xmm0, %rax
+	movq %xmm0, %rax
 	cmp $8, %r13
 	jle _less_than_8_bytes_left_\@
 	mov %rax, (%arg3 , %r11, 1)
 	add $8, %r11
 	psrldq $8, %xmm0
-	MOVQ_R64_XMM %xmm0, %rax
+	movq %xmm0, %rax
 	sub $8, %r13
 _less_than_8_bytes_left_\@:
 	mov %al,  (%arg3, %r11, 1)
@@ -449,7 +448,7 @@ _partial_done\@:
 	movd	%r12d, %xmm15		  # len(A) in %xmm15
 	mov InLen(%arg2), %r12
 	shl     $3, %r12                  # len(C) in bits (*128)
-	MOVQ_R64_XMM    %r12, %xmm1
+	movq    %r12, %xmm1
 
 	pslldq	$8, %xmm15		  # %xmm15 = len(A)||0x0000000000000000
 	pxor	%xmm1, %xmm15		  # %xmm15 = len(A)||len(C)
@@ -457,7 +456,7 @@ _partial_done\@:
 	GHASH_MUL	%xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
 	# final GHASH computation
 	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm8
+	pshufb %xmm10, %xmm8
 
 	movdqu OrigIV(%arg2), %xmm0       # %xmm0 = Y0
 	ENCRYPT_SINGLE_BLOCK	%xmm0,  %xmm1	  # E(K, Y0)
@@ -470,7 +469,7 @@ _return_T_\@:
 	cmp	$8, %r11
 	jl	_T_4_\@
 _T_8_\@:
-	MOVQ_R64_XMM	%xmm0, %rax
+	movq	%xmm0, %rax
 	mov	%rax, (%r10)
 	add	$8, %r10
 	sub	$8, %r11
@@ -518,9 +517,9 @@ _return_T_done_\@:
 	pshufd	  $78, \HK, \TMP3
 	pxor	  \GH, \TMP2            # TMP2 = a1+a0
 	pxor	  \HK, \TMP3            # TMP3 = b1+b0
-	PCLMULQDQ 0x11, \HK, \TMP1     # TMP1 = a1*b1
-	PCLMULQDQ 0x00, \HK, \GH       # GH = a0*b0
-	PCLMULQDQ 0x00, \TMP3, \TMP2   # TMP2 = (a0+a1)*(b1+b0)
+	pclmulqdq $0x11, \HK, \TMP1     # TMP1 = a1*b1
+	pclmulqdq $0x00, \HK, \GH       # GH = a0*b0
+	pclmulqdq $0x00, \TMP3, \TMP2   # TMP2 = (a0+a1)*(b1+b0)
 	pxor	  \GH, \TMP2
 	pxor	  \TMP1, \TMP2          # TMP2 = (a0*b0)+(a1*b0)
 	movdqa	  \TMP2, \TMP3
@@ -570,7 +569,7 @@ _return_T_done_\@:
         cmp $8, \DLEN
         jl _read_lt8_\@
         mov (\DPTR), %rax
-        MOVQ_R64_XMM %rax, \XMMDst
+        movq %rax, \XMMDst
         sub $8, \DLEN
         jz _done_read_partial_block_\@
 	xor %eax, %eax
@@ -579,7 +578,7 @@ _read_next_byte_\@:
         mov 7(\DPTR, \DLEN, 1), %al
         dec \DLEN
         jnz _read_next_byte_\@
-        MOVQ_R64_XMM %rax, \XMM1
+        movq %rax, \XMM1
 	pslldq $8, \XMM1
         por \XMM1, \XMMDst
 	jmp _done_read_partial_block_\@
@@ -590,7 +589,7 @@ _read_next_byte_lt8_\@:
         mov -1(\DPTR, \DLEN, 1), %al
         dec \DLEN
         jnz _read_next_byte_lt8_\@
-        MOVQ_R64_XMM %rax, \XMMDst
+        movq %rax, \XMMDst
 _done_read_partial_block_\@:
 .endm
 
@@ -608,7 +607,7 @@ _done_read_partial_block_\@:
 	jl	   _get_AAD_rest\@
 _get_AAD_blocks\@:
 	movdqu	   (%r10), \TMP7
-	PSHUFB_XMM   %xmm14, \TMP7 # byte-reflect the AAD data
+	pshufb	   %xmm14, \TMP7 # byte-reflect the AAD data
 	pxor	   \TMP7, \TMP6
 	GHASH_MUL  \TMP6, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5
 	add	   $16, %r10
@@ -624,7 +623,7 @@ _get_AAD_rest\@:
 	je	   _get_AAD_done\@
 
 	READ_PARTIAL_BLOCK %r10, %r11, \TMP1, \TMP7
-	PSHUFB_XMM   %xmm14, \TMP7 # byte-reflect the AAD data
+	pshufb	   %xmm14, \TMP7 # byte-reflect the AAD data
 	pxor	   \TMP6, \TMP7
 	GHASH_MUL  \TMP7, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5
 	movdqu \TMP7, \TMP6
@@ -667,7 +666,7 @@ _data_read_\@:				# Finished reading in data
 	# r16-r13 is the number of bytes in plaintext mod 16)
 	add	%r13, %r12
 	movdqu	(%r12), %xmm2		# get the appropriate shuffle mask
-	PSHUFB_XMM %xmm2, %xmm9		# shift right r13 bytes
+	pshufb	%xmm2, %xmm9		# shift right r13 bytes
 
 .ifc \operation, dec
 	movdqa	%xmm1, %xmm3
@@ -689,8 +688,8 @@ _no_extra_mask_1_\@:
 
 	pand	%xmm1, %xmm3
 	movdqa	SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM	%xmm10, %xmm3
-	PSHUFB_XMM	%xmm2, %xmm3
+	pshufb	%xmm10, %xmm3
+	pshufb	%xmm2, %xmm3
 	pxor	%xmm3, \AAD_HASH
 
 	cmp	$0, %r10
@@ -724,8 +723,8 @@ _no_extra_mask_2_\@:
 	pand	%xmm1, %xmm9
 
 	movdqa	SHUF_MASK(%rip), %xmm1
-	PSHUFB_XMM %xmm1, %xmm9
-	PSHUFB_XMM %xmm2, %xmm9
+	pshufb	%xmm1, %xmm9
+	pshufb	%xmm2, %xmm9
 	pxor	%xmm9, \AAD_HASH
 
 	cmp	$0, %r10
@@ -744,8 +743,8 @@ _encode_done_\@:
 
 	movdqa	SHUF_MASK(%rip), %xmm10
 	# shuffle xmm9 back to output as ciphertext
-	PSHUFB_XMM	%xmm10, %xmm9
-	PSHUFB_XMM	%xmm2, %xmm9
+	pshufb	%xmm10, %xmm9
+	pshufb	%xmm2, %xmm9
 .endif
 	# output encrypted Bytes
 	cmp	$0, %r10
@@ -759,14 +758,14 @@ _partial_fill_\@:
 	mov	\PLAIN_CYPH_LEN, %r13
 _count_set_\@:
 	movdqa	%xmm9, %xmm0
-	MOVQ_R64_XMM	%xmm0, %rax
+	movq	%xmm0, %rax
 	cmp	$8, %r13
 	jle	_less_than_8_bytes_left_\@
 
 	mov	%rax, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
 	add	$8, \DATA_OFFSET
 	psrldq	$8, %xmm0
-	MOVQ_R64_XMM	%xmm0, %rax
+	movq	%xmm0, %rax
 	sub	$8, %r13
 _less_than_8_bytes_left_\@:
 	movb	%al, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
@@ -810,7 +809,7 @@ _partial_block_done_\@:
 .else
 	MOVADQ		\XMM0, %xmm\index
 .endif
-	PSHUFB_XMM	%xmm14, %xmm\index      # perform a 16 byte swap
+	pshufb	%xmm14, %xmm\index      # perform a 16 byte swap
 	pxor		\TMP2, %xmm\index
 .endr
 	lea	0x10(%arg1),%r10
@@ -821,7 +820,7 @@ _partial_block_done_\@:
 aes_loop_initial_\@:
 	MOVADQ	(%r10),\TMP1
 .irpc	index, \i_seq
-	AESENC	\TMP1, %xmm\index
+	aesenc	\TMP1, %xmm\index
 .endr
 	add	$16,%r10
 	sub	$1,%eax
@@ -829,7 +828,7 @@ aes_loop_initial_\@:
 
 	MOVADQ	(%r10), \TMP1
 .irpc index, \i_seq
-	AESENCLAST \TMP1, %xmm\index         # Last Round
+	aesenclast \TMP1, %xmm\index         # Last Round
 .endr
 .irpc index, \i_seq
 	movdqu	   (%arg4 , %r11, 1), \TMP1
@@ -841,7 +840,7 @@ aes_loop_initial_\@:
 .ifc \operation, dec
 	movdqa     \TMP1, %xmm\index
 .endif
-	PSHUFB_XMM	   %xmm14, %xmm\index
+	pshufb	   %xmm14, %xmm\index
 
 		# prepare plaintext/ciphertext for GHASH computation
 .endr
@@ -876,19 +875,19 @@ aes_loop_initial_\@:
 	MOVADQ	   ONE(%RIP),\TMP1
 	paddd	   \TMP1, \XMM0              # INCR Y0
 	MOVADQ	   \XMM0, \XMM1
-	PSHUFB_XMM  %xmm14, \XMM1        # perform a 16 byte swap
+	pshufb  %xmm14, \XMM1        # perform a 16 byte swap
 
 	paddd	   \TMP1, \XMM0              # INCR Y0
 	MOVADQ	   \XMM0, \XMM2
-	PSHUFB_XMM  %xmm14, \XMM2        # perform a 16 byte swap
+	pshufb  %xmm14, \XMM2        # perform a 16 byte swap
 
 	paddd	   \TMP1, \XMM0              # INCR Y0
 	MOVADQ	   \XMM0, \XMM3
-	PSHUFB_XMM %xmm14, \XMM3        # perform a 16 byte swap
+	pshufb %xmm14, \XMM3        # perform a 16 byte swap
 
 	paddd	   \TMP1, \XMM0              # INCR Y0
 	MOVADQ	   \XMM0, \XMM4
-	PSHUFB_XMM %xmm14, \XMM4        # perform a 16 byte swap
+	pshufb %xmm14, \XMM4        # perform a 16 byte swap
 
 	MOVADQ	   0(%arg1),\TMP1
 	pxor	   \TMP1, \XMM1
@@ -897,17 +896,17 @@ aes_loop_initial_\@:
 	pxor	   \TMP1, \XMM4
 .irpc index, 1234 # do 4 rounds
 	movaps 0x10*\index(%arg1), \TMP1
-	AESENC	   \TMP1, \XMM1
-	AESENC	   \TMP1, \XMM2
-	AESENC	   \TMP1, \XMM3
-	AESENC	   \TMP1, \XMM4
+	aesenc	   \TMP1, \XMM1
+	aesenc	   \TMP1, \XMM2
+	aesenc	   \TMP1, \XMM3
+	aesenc	   \TMP1, \XMM4
 .endr
 .irpc index, 56789 # do next 5 rounds
 	movaps 0x10*\index(%arg1), \TMP1
-	AESENC	   \TMP1, \XMM1
-	AESENC	   \TMP1, \XMM2
-	AESENC	   \TMP1, \XMM3
-	AESENC	   \TMP1, \XMM4
+	aesenc	   \TMP1, \XMM1
+	aesenc	   \TMP1, \XMM2
+	aesenc	   \TMP1, \XMM3
+	aesenc	   \TMP1, \XMM4
 .endr
 	lea	   0xa0(%arg1),%r10
 	mov	   keysize,%eax
@@ -918,7 +917,7 @@ aes_loop_initial_\@:
 aes_loop_pre_\@:
 	MOVADQ	   (%r10),\TMP2
 .irpc	index, 1234
-	AESENC	   \TMP2, %xmm\index
+	aesenc	   \TMP2, %xmm\index
 .endr
 	add	   $16,%r10
 	sub	   $1,%eax
@@ -926,10 +925,10 @@ aes_loop_pre_\@:
 
 aes_loop_pre_done\@:
 	MOVADQ	   (%r10), \TMP2
-	AESENCLAST \TMP2, \XMM1
-	AESENCLAST \TMP2, \XMM2
-	AESENCLAST \TMP2, \XMM3
-	AESENCLAST \TMP2, \XMM4
+	aesenclast \TMP2, \XMM1
+	aesenclast \TMP2, \XMM2
+	aesenclast \TMP2, \XMM3
+	aesenclast \TMP2, \XMM4
 	movdqu	   16*0(%arg4 , %r11 , 1), \TMP1
 	pxor	   \TMP1, \XMM1
 .ifc \operation, dec
@@ -961,12 +960,12 @@ aes_loop_pre_done\@:
 .endif
 
 	add	   $64, %r11
-	PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
+	pshufb %xmm14, \XMM1 # perform a 16 byte swap
 	pxor	   \XMMDst, \XMM1
 # combine GHASHed value with the corresponding ciphertext
-	PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap
-	PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
-	PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
+	pshufb %xmm14, \XMM2 # perform a 16 byte swap
+	pshufb %xmm14, \XMM3 # perform a 16 byte swap
+	pshufb %xmm14, \XMM4 # perform a 16 byte swap
 
 _initial_blocks_done\@:
 
@@ -978,7 +977,7 @@ _initial_blocks_done\@:
 * arg1, %arg3, %arg4 are used as pointers only, not modified
 * %r11 is the data offset value
 */
-.macro GHASH_4_ENCRYPT_4_PARALLEL_ENC TMP1 TMP2 TMP3 TMP4 TMP5 \
+.macro GHASH_4_ENCRYPT_4_PARALLEL_enc TMP1 TMP2 TMP3 TMP4 TMP5 \
 TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 
 	movdqa	  \XMM1, \XMM5
@@ -994,7 +993,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pxor	  \XMM5, \TMP6
 	paddd     ONE(%rip), \XMM0		# INCR CNT
 	movdqu	  HashKey_4(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
+	pclmulqdq $0x11, \TMP5, \TMP4           # TMP4 = a1*b1
 	movdqa    \XMM0, \XMM1
 	paddd     ONE(%rip), \XMM0		# INCR CNT
 	movdqa    \XMM0, \XMM2
@@ -1002,51 +1001,51 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa    \XMM0, \XMM3
 	paddd     ONE(%rip), \XMM0		# INCR CNT
 	movdqa    \XMM0, \XMM4
-	PSHUFB_XMM %xmm15, \XMM1	# perform a 16 byte swap
-	PCLMULQDQ 0x00, \TMP5, \XMM5           # XMM5 = a0*b0
-	PSHUFB_XMM %xmm15, \XMM2	# perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM3	# perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM4	# perform a 16 byte swap
+	pshufb %xmm15, \XMM1	# perform a 16 byte swap
+	pclmulqdq $0x00, \TMP5, \XMM5           # XMM5 = a0*b0
+	pshufb %xmm15, \XMM2	# perform a 16 byte swap
+	pshufb %xmm15, \XMM3	# perform a 16 byte swap
+	pshufb %xmm15, \XMM4	# perform a 16 byte swap
 
 	pxor	  (%arg1), \XMM1
 	pxor	  (%arg1), \XMM2
 	pxor	  (%arg1), \XMM3
 	pxor	  (%arg1), \XMM4
 	movdqu	  HashKey_4_k(%arg2), \TMP5
-	PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP5, \TMP6       # TMP6 = (a1+a0)*(b1+b0)
 	movaps 0x10(%arg1), \TMP1
-	AESENC	  \TMP1, \XMM1              # Round 1
-	AESENC	  \TMP1, \XMM2
-	AESENC	  \TMP1, \XMM3
-	AESENC	  \TMP1, \XMM4
+	aesenc	  \TMP1, \XMM1              # Round 1
+	aesenc	  \TMP1, \XMM2
+	aesenc	  \TMP1, \XMM3
+	aesenc	  \TMP1, \XMM4
 	movaps 0x20(%arg1), \TMP1
-	AESENC	  \TMP1, \XMM1              # Round 2
-	AESENC	  \TMP1, \XMM2
-	AESENC	  \TMP1, \XMM3
-	AESENC	  \TMP1, \XMM4
+	aesenc	  \TMP1, \XMM1              # Round 2
+	aesenc	  \TMP1, \XMM2
+	aesenc	  \TMP1, \XMM3
+	aesenc	  \TMP1, \XMM4
 	movdqa	  \XMM6, \TMP1
 	pshufd	  $78, \XMM6, \TMP2
 	pxor	  \XMM6, \TMP2
 	movdqu	  HashKey_3(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
+	pclmulqdq $0x11, \TMP5, \TMP1       # TMP1 = a1 * b1
 	movaps 0x30(%arg1), \TMP3
-	AESENC    \TMP3, \XMM1              # Round 3
-	AESENC    \TMP3, \XMM2
-	AESENC    \TMP3, \XMM3
-	AESENC    \TMP3, \XMM4
-	PCLMULQDQ 0x00, \TMP5, \XMM6           # XMM6 = a0*b0
+	aesenc    \TMP3, \XMM1              # Round 3
+	aesenc    \TMP3, \XMM2
+	aesenc    \TMP3, \XMM3
+	aesenc    \TMP3, \XMM4
+	pclmulqdq $0x00, \TMP5, \XMM6       # XMM6 = a0*b0
 	movaps 0x40(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1              # Round 4
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
+	aesenc	  \TMP3, \XMM1              # Round 4
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
 	movdqu	  HashKey_3_k(%arg2), \TMP5
-	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP5, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x50(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1              # Round 5
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
+	aesenc	  \TMP3, \XMM1              # Round 5
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
 	pxor	  \TMP1, \TMP4
 # accumulate the results in TMP4:XMM5, TMP6 holds the middle part
 	pxor	  \XMM6, \XMM5
@@ -1058,25 +1057,25 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 
         # Multiply TMP5 * HashKey using karatsuba
 
-	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1*b1
+	pclmulqdq $0x11, \TMP5, \TMP1       # TMP1 = a1*b1
 	movaps 0x60(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1              # Round 6
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
-	PCLMULQDQ 0x00, \TMP5, \XMM7           # XMM7 = a0*b0
+	aesenc	  \TMP3, \XMM1              # Round 6
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
+	pclmulqdq $0x00, \TMP5, \XMM7       # XMM7 = a0*b0
 	movaps 0x70(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1             # Round 7
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
+	aesenc	  \TMP3, \XMM1              # Round 7
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
 	movdqu	  HashKey_2_k(%arg2), \TMP5
-	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP5, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x80(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1             # Round 8
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
+	aesenc	  \TMP3, \XMM1              # Round 8
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
 	pxor	  \TMP1, \TMP4
 # accumulate the results in TMP4:XMM5, TMP6 holds the middle part
 	pxor	  \XMM7, \XMM5
@@ -1089,13 +1088,13 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pshufd	  $78, \XMM8, \TMP2
 	pxor	  \XMM8, \TMP2
 	movdqu	  HashKey(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
+	pclmulqdq $0x11, \TMP5, \TMP1      # TMP1 = a1*b1
 	movaps 0x90(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1            # Round 9
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
-	PCLMULQDQ 0x00, \TMP5, \XMM8          # XMM8 = a0*b0
+	aesenc	  \TMP3, \XMM1             # Round 9
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
+	pclmulqdq $0x00, \TMP5, \XMM8      # XMM8 = a0*b0
 	lea	  0xa0(%arg1),%r10
 	mov	  keysize,%eax
 	shr	  $2,%eax			# 128->4, 192->6, 256->8
@@ -1105,7 +1104,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 aes_loop_par_enc\@:
 	MOVADQ	  (%r10),\TMP3
 .irpc	index, 1234
-	AESENC	  \TMP3, %xmm\index
+	aesenc	  \TMP3, %xmm\index
 .endr
 	add	  $16,%r10
 	sub	  $1,%eax
@@ -1113,12 +1112,12 @@ aes_loop_par_enc\@:
 
 aes_loop_par_enc_done\@:
 	MOVADQ	  (%r10), \TMP3
-	AESENCLAST \TMP3, \XMM1           # Round 10
-	AESENCLAST \TMP3, \XMM2
-	AESENCLAST \TMP3, \XMM3
-	AESENCLAST \TMP3, \XMM4
+	aesenclast \TMP3, \XMM1           # Round 10
+	aesenclast \TMP3, \XMM2
+	aesenclast \TMP3, \XMM3
+	aesenclast \TMP3, \XMM4
 	movdqu    HashKey_k(%arg2), \TMP5
-	PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
 	movdqu	  (%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
 	movdqu	  16(%arg4,%r11,1), \TMP3
@@ -1131,10 +1130,10 @@ aes_loop_par_enc_done\@:
         movdqu    \XMM2, 16(%arg3,%r11,1)      # Write to the ciphertext buffer
         movdqu    \XMM3, 32(%arg3,%r11,1)      # Write to the ciphertext buffer
         movdqu    \XMM4, 48(%arg3,%r11,1)      # Write to the ciphertext buffer
-	PSHUFB_XMM %xmm15, \XMM1        # perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM2	# perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM3	# perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM4	# perform a 16 byte swap
+	pshufb %xmm15, \XMM1        # perform a 16 byte swap
+	pshufb %xmm15, \XMM2	# perform a 16 byte swap
+	pshufb %xmm15, \XMM3	# perform a 16 byte swap
+	pshufb %xmm15, \XMM4	# perform a 16 byte swap
 
 	pxor	  \TMP4, \TMP1
 	pxor	  \XMM8, \XMM5
@@ -1186,7 +1185,7 @@ aes_loop_par_enc_done\@:
 * arg1, %arg3, %arg4 are used as pointers only, not modified
 * %r11 is the data offset value
 */
-.macro GHASH_4_ENCRYPT_4_PARALLEL_DEC TMP1 TMP2 TMP3 TMP4 TMP5 \
+.macro GHASH_4_ENCRYPT_4_PARALLEL_dec TMP1 TMP2 TMP3 TMP4 TMP5 \
 TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 
 	movdqa	  \XMM1, \XMM5
@@ -1202,7 +1201,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pxor	  \XMM5, \TMP6
 	paddd     ONE(%rip), \XMM0		# INCR CNT
 	movdqu	  HashKey_4(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
+	pclmulqdq $0x11, \TMP5, \TMP4           # TMP4 = a1*b1
 	movdqa    \XMM0, \XMM1
 	paddd     ONE(%rip), \XMM0		# INCR CNT
 	movdqa    \XMM0, \XMM2
@@ -1210,51 +1209,51 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa    \XMM0, \XMM3
 	paddd     ONE(%rip), \XMM0		# INCR CNT
 	movdqa    \XMM0, \XMM4
-	PSHUFB_XMM %xmm15, \XMM1	# perform a 16 byte swap
-	PCLMULQDQ 0x00, \TMP5, \XMM5           # XMM5 = a0*b0
-	PSHUFB_XMM %xmm15, \XMM2	# perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM3	# perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM4	# perform a 16 byte swap
+	pshufb %xmm15, \XMM1	# perform a 16 byte swap
+	pclmulqdq $0x00, \TMP5, \XMM5           # XMM5 = a0*b0
+	pshufb %xmm15, \XMM2	# perform a 16 byte swap
+	pshufb %xmm15, \XMM3	# perform a 16 byte swap
+	pshufb %xmm15, \XMM4	# perform a 16 byte swap
 
 	pxor	  (%arg1), \XMM1
 	pxor	  (%arg1), \XMM2
 	pxor	  (%arg1), \XMM3
 	pxor	  (%arg1), \XMM4
 	movdqu	  HashKey_4_k(%arg2), \TMP5
-	PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP5, \TMP6       # TMP6 = (a1+a0)*(b1+b0)
 	movaps 0x10(%arg1), \TMP1
-	AESENC	  \TMP1, \XMM1              # Round 1
-	AESENC	  \TMP1, \XMM2
-	AESENC	  \TMP1, \XMM3
-	AESENC	  \TMP1, \XMM4
+	aesenc	  \TMP1, \XMM1              # Round 1
+	aesenc	  \TMP1, \XMM2
+	aesenc	  \TMP1, \XMM3
+	aesenc	  \TMP1, \XMM4
 	movaps 0x20(%arg1), \TMP1
-	AESENC	  \TMP1, \XMM1              # Round 2
-	AESENC	  \TMP1, \XMM2
-	AESENC	  \TMP1, \XMM3
-	AESENC	  \TMP1, \XMM4
+	aesenc	  \TMP1, \XMM1              # Round 2
+	aesenc	  \TMP1, \XMM2
+	aesenc	  \TMP1, \XMM3
+	aesenc	  \TMP1, \XMM4
 	movdqa	  \XMM6, \TMP1
 	pshufd	  $78, \XMM6, \TMP2
 	pxor	  \XMM6, \TMP2
 	movdqu	  HashKey_3(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
+	pclmulqdq $0x11, \TMP5, \TMP1       # TMP1 = a1 * b1
 	movaps 0x30(%arg1), \TMP3
-	AESENC    \TMP3, \XMM1              # Round 3
-	AESENC    \TMP3, \XMM2
-	AESENC    \TMP3, \XMM3
-	AESENC    \TMP3, \XMM4
-	PCLMULQDQ 0x00, \TMP5, \XMM6           # XMM6 = a0*b0
+	aesenc    \TMP3, \XMM1              # Round 3
+	aesenc    \TMP3, \XMM2
+	aesenc    \TMP3, \XMM3
+	aesenc    \TMP3, \XMM4
+	pclmulqdq $0x00, \TMP5, \XMM6       # XMM6 = a0*b0
 	movaps 0x40(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1              # Round 4
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
+	aesenc	  \TMP3, \XMM1              # Round 4
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
 	movdqu	  HashKey_3_k(%arg2), \TMP5
-	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP5, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x50(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1              # Round 5
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
+	aesenc	  \TMP3, \XMM1              # Round 5
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
 	pxor	  \TMP1, \TMP4
 # accumulate the results in TMP4:XMM5, TMP6 holds the middle part
 	pxor	  \XMM6, \XMM5
@@ -1266,25 +1265,25 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 
         # Multiply TMP5 * HashKey using karatsuba
 
-	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1*b1
+	pclmulqdq $0x11, \TMP5, \TMP1       # TMP1 = a1*b1
 	movaps 0x60(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1              # Round 6
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
-	PCLMULQDQ 0x00, \TMP5, \XMM7           # XMM7 = a0*b0
+	aesenc	  \TMP3, \XMM1              # Round 6
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
+	pclmulqdq $0x00, \TMP5, \XMM7       # XMM7 = a0*b0
 	movaps 0x70(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1             # Round 7
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
+	aesenc	  \TMP3, \XMM1              # Round 7
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
 	movdqu	  HashKey_2_k(%arg2), \TMP5
-	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP5, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x80(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1             # Round 8
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
+	aesenc	  \TMP3, \XMM1              # Round 8
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
 	pxor	  \TMP1, \TMP4
 # accumulate the results in TMP4:XMM5, TMP6 holds the middle part
 	pxor	  \XMM7, \XMM5
@@ -1297,13 +1296,13 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pshufd	  $78, \XMM8, \TMP2
 	pxor	  \XMM8, \TMP2
 	movdqu	  HashKey(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
+	pclmulqdq $0x11, \TMP5, \TMP1      # TMP1 = a1*b1
 	movaps 0x90(%arg1), \TMP3
-	AESENC	  \TMP3, \XMM1            # Round 9
-	AESENC	  \TMP3, \XMM2
-	AESENC	  \TMP3, \XMM3
-	AESENC	  \TMP3, \XMM4
-	PCLMULQDQ 0x00, \TMP5, \XMM8          # XMM8 = a0*b0
+	aesenc	  \TMP3, \XMM1             # Round 9
+	aesenc	  \TMP3, \XMM2
+	aesenc	  \TMP3, \XMM3
+	aesenc	  \TMP3, \XMM4
+	pclmulqdq $0x00, \TMP5, \XMM8      # XMM8 = a0*b0
 	lea	  0xa0(%arg1),%r10
 	mov	  keysize,%eax
 	shr	  $2,%eax		        # 128->4, 192->6, 256->8
@@ -1313,7 +1312,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 aes_loop_par_dec\@:
 	MOVADQ	  (%r10),\TMP3
 .irpc	index, 1234
-	AESENC	  \TMP3, %xmm\index
+	aesenc	  \TMP3, %xmm\index
 .endr
 	add	  $16,%r10
 	sub	  $1,%eax
@@ -1321,12 +1320,12 @@ aes_loop_par_dec\@:
 
 aes_loop_par_dec_done\@:
 	MOVADQ	  (%r10), \TMP3
-	AESENCLAST \TMP3, \XMM1           # last round
-	AESENCLAST \TMP3, \XMM2
-	AESENCLAST \TMP3, \XMM3
-	AESENCLAST \TMP3, \XMM4
+	aesenclast \TMP3, \XMM1           # last round
+	aesenclast \TMP3, \XMM2
+	aesenclast \TMP3, \XMM3
+	aesenclast \TMP3, \XMM4
 	movdqu    HashKey_k(%arg2), \TMP5
-	PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
 	movdqu	  (%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
 	movdqu	  \XMM1, (%arg3,%r11,1)        # Write to plaintext buffer
@@ -1343,10 +1342,10 @@ aes_loop_par_dec_done\@:
 	pxor	  \TMP3, \XMM4                 # Ciphertext/Plaintext XOR EK
 	movdqu	  \XMM4, 48(%arg3,%r11,1)      # Write to plaintext buffer
 	movdqa    \TMP3, \XMM4
-	PSHUFB_XMM %xmm15, \XMM1        # perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM2	# perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM3	# perform a 16 byte swap
-	PSHUFB_XMM %xmm15, \XMM4	# perform a 16 byte swap
+	pshufb %xmm15, \XMM1        # perform a 16 byte swap
+	pshufb %xmm15, \XMM2	# perform a 16 byte swap
+	pshufb %xmm15, \XMM3	# perform a 16 byte swap
+	pshufb %xmm15, \XMM4	# perform a 16 byte swap
 
 	pxor	  \TMP4, \TMP1
 	pxor	  \XMM8, \XMM5
@@ -1402,10 +1401,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	pshufd	  $78, \XMM1, \TMP2
 	pxor	  \XMM1, \TMP2
 	movdqu	  HashKey_4(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP6       # TMP6 = a1*b1
-	PCLMULQDQ 0x00, \TMP5, \XMM1       # XMM1 = a0*b0
+	pclmulqdq $0x11, \TMP5, \TMP6       # TMP6 = a1*b1
+	pclmulqdq $0x00, \TMP5, \XMM1       # XMM1 = a0*b0
 	movdqu	  HashKey_4_k(%arg2), \TMP4
-	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	movdqa	  \XMM1, \XMMDst
 	movdqa	  \TMP2, \XMM1              # result in TMP6, XMMDst, XMM1
 
@@ -1415,10 +1414,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	pshufd	  $78, \XMM2, \TMP2
 	pxor	  \XMM2, \TMP2
 	movdqu	  HashKey_3(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
-	PCLMULQDQ 0x00, \TMP5, \XMM2       # XMM2 = a0*b0
+	pclmulqdq $0x11, \TMP5, \TMP1       # TMP1 = a1*b1
+	pclmulqdq $0x00, \TMP5, \XMM2       # XMM2 = a0*b0
 	movdqu	  HashKey_3_k(%arg2), \TMP4
-	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM2, \XMMDst
 	pxor	  \TMP2, \XMM1
@@ -1430,10 +1429,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	pshufd	  $78, \XMM3, \TMP2
 	pxor	  \XMM3, \TMP2
 	movdqu	  HashKey_2(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
-	PCLMULQDQ 0x00, \TMP5, \XMM3       # XMM3 = a0*b0
+	pclmulqdq $0x11, \TMP5, \TMP1       # TMP1 = a1*b1
+	pclmulqdq $0x00, \TMP5, \XMM3       # XMM3 = a0*b0
 	movdqu	  HashKey_2_k(%arg2), \TMP4
-	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM3, \XMMDst
 	pxor	  \TMP2, \XMM1   # results accumulated in TMP6, XMMDst, XMM1
@@ -1443,10 +1442,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	pshufd	  $78, \XMM4, \TMP2
 	pxor	  \XMM4, \TMP2
 	movdqu	  HashKey(%arg2), \TMP5
-	PCLMULQDQ 0x11, \TMP5, \TMP1	    # TMP1 = a1*b1
-	PCLMULQDQ 0x00, \TMP5, \XMM4       # XMM4 = a0*b0
+	pclmulqdq $0x11, \TMP5, \TMP1	    # TMP1 = a1*b1
+	pclmulqdq $0x00, \TMP5, \XMM4       # XMM4 = a0*b0
 	movdqu	  HashKey_k(%arg2), \TMP4
-	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
+	pclmulqdq $0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM4, \XMMDst
 	pxor	  \XMM1, \TMP2
@@ -1504,13 +1503,13 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 
 _esb_loop_\@:
 	MOVADQ		(%r10),\TMP1
-	AESENC		\TMP1,\XMM0
+	aesenc		\TMP1,\XMM0
 	add		$16,%r10
 	sub		$1,%eax
 	jnz		_esb_loop_\@
 
 	MOVADQ		(%r10),\TMP1
-	AESENCLAST	\TMP1,\XMM0
+	aesenclast	\TMP1,\XMM0
 .endm
 /*****************************************************************************
 * void aesni_gcm_dec(void *aes_ctx,    // AES Key schedule. Starts on a 16 byte boundary.
@@ -1849,72 +1848,72 @@ SYM_FUNC_START(aesni_set_key)
 	movups 0x10(UKEYP), %xmm2	# other user key
 	movaps %xmm2, (TKEYP)
 	add $0x10, TKEYP
-	AESKEYGENASSIST 0x1 %xmm2 %xmm1		# round 1
+	aeskeygenassist $0x1, %xmm2, %xmm1	# round 1
 	call _key_expansion_256a
-	AESKEYGENASSIST 0x1 %xmm0 %xmm1
+	aeskeygenassist $0x1, %xmm0, %xmm1
 	call _key_expansion_256b
-	AESKEYGENASSIST 0x2 %xmm2 %xmm1		# round 2
+	aeskeygenassist $0x2, %xmm2, %xmm1	# round 2
 	call _key_expansion_256a
-	AESKEYGENASSIST 0x2 %xmm0 %xmm1
+	aeskeygenassist $0x2, %xmm0, %xmm1
 	call _key_expansion_256b
-	AESKEYGENASSIST 0x4 %xmm2 %xmm1		# round 3
+	aeskeygenassist $0x4, %xmm2, %xmm1	# round 3
 	call _key_expansion_256a
-	AESKEYGENASSIST 0x4 %xmm0 %xmm1
+	aeskeygenassist $0x4, %xmm0, %xmm1
 	call _key_expansion_256b
-	AESKEYGENASSIST 0x8 %xmm2 %xmm1		# round 4
+	aeskeygenassist $0x8, %xmm2, %xmm1	# round 4
 	call _key_expansion_256a
-	AESKEYGENASSIST 0x8 %xmm0 %xmm1
+	aeskeygenassist $0x8, %xmm0, %xmm1
 	call _key_expansion_256b
-	AESKEYGENASSIST 0x10 %xmm2 %xmm1	# round 5
+	aeskeygenassist $0x10, %xmm2, %xmm1	# round 5
 	call _key_expansion_256a
-	AESKEYGENASSIST 0x10 %xmm0 %xmm1
+	aeskeygenassist $0x10, %xmm0, %xmm1
 	call _key_expansion_256b
-	AESKEYGENASSIST 0x20 %xmm2 %xmm1	# round 6
+	aeskeygenassist $0x20, %xmm2, %xmm1	# round 6
 	call _key_expansion_256a
-	AESKEYGENASSIST 0x20 %xmm0 %xmm1
+	aeskeygenassist $0x20, %xmm0, %xmm1
 	call _key_expansion_256b
-	AESKEYGENASSIST 0x40 %xmm2 %xmm1	# round 7
+	aeskeygenassist $0x40, %xmm2, %xmm1	# round 7
 	call _key_expansion_256a
 	jmp .Ldec_key
 .Lenc_key192:
 	movq 0x10(UKEYP), %xmm2		# other user key
-	AESKEYGENASSIST 0x1 %xmm2 %xmm1		# round 1
+	aeskeygenassist $0x1, %xmm2, %xmm1	# round 1
 	call _key_expansion_192a
-	AESKEYGENASSIST 0x2 %xmm2 %xmm1		# round 2
+	aeskeygenassist $0x2, %xmm2, %xmm1	# round 2
 	call _key_expansion_192b
-	AESKEYGENASSIST 0x4 %xmm2 %xmm1		# round 3
+	aeskeygenassist $0x4, %xmm2, %xmm1	# round 3
 	call _key_expansion_192a
-	AESKEYGENASSIST 0x8 %xmm2 %xmm1		# round 4
+	aeskeygenassist $0x8, %xmm2, %xmm1	# round 4
 	call _key_expansion_192b
-	AESKEYGENASSIST 0x10 %xmm2 %xmm1	# round 5
+	aeskeygenassist $0x10, %xmm2, %xmm1	# round 5
 	call _key_expansion_192a
-	AESKEYGENASSIST 0x20 %xmm2 %xmm1	# round 6
+	aeskeygenassist $0x20, %xmm2, %xmm1	# round 6
 	call _key_expansion_192b
-	AESKEYGENASSIST 0x40 %xmm2 %xmm1	# round 7
+	aeskeygenassist $0x40, %xmm2, %xmm1	# round 7
 	call _key_expansion_192a
-	AESKEYGENASSIST 0x80 %xmm2 %xmm1	# round 8
+	aeskeygenassist $0x80, %xmm2, %xmm1	# round 8
 	call _key_expansion_192b
 	jmp .Ldec_key
 .Lenc_key128:
-	AESKEYGENASSIST 0x1 %xmm0 %xmm1		# round 1
+	aeskeygenassist $0x1, %xmm0, %xmm1	# round 1
 	call _key_expansion_128
-	AESKEYGENASSIST 0x2 %xmm0 %xmm1		# round 2
+	aeskeygenassist $0x2, %xmm0, %xmm1	# round 2
 	call _key_expansion_128
-	AESKEYGENASSIST 0x4 %xmm0 %xmm1		# round 3
+	aeskeygenassist $0x4, %xmm0, %xmm1	# round 3
 	call _key_expansion_128
-	AESKEYGENASSIST 0x8 %xmm0 %xmm1		# round 4
+	aeskeygenassist $0x8, %xmm0, %xmm1	# round 4
 	call _key_expansion_128
-	AESKEYGENASSIST 0x10 %xmm0 %xmm1	# round 5
+	aeskeygenassist $0x10, %xmm0, %xmm1	# round 5
 	call _key_expansion_128
-	AESKEYGENASSIST 0x20 %xmm0 %xmm1	# round 6
+	aeskeygenassist $0x20, %xmm0, %xmm1	# round 6
 	call _key_expansion_128
-	AESKEYGENASSIST 0x40 %xmm0 %xmm1	# round 7
+	aeskeygenassist $0x40, %xmm0, %xmm1	# round 7
 	call _key_expansion_128
-	AESKEYGENASSIST 0x80 %xmm0 %xmm1	# round 8
+	aeskeygenassist $0x80, %xmm0, %xmm1	# round 8
 	call _key_expansion_128
-	AESKEYGENASSIST 0x1b %xmm0 %xmm1	# round 9
+	aeskeygenassist $0x1b, %xmm0, %xmm1	# round 9
 	call _key_expansion_128
-	AESKEYGENASSIST 0x36 %xmm0 %xmm1	# round 10
+	aeskeygenassist $0x36, %xmm0, %xmm1	# round 10
 	call _key_expansion_128
 .Ldec_key:
 	sub $0x10, TKEYP
@@ -1927,7 +1926,7 @@ SYM_FUNC_START(aesni_set_key)
 .align 4
 .Ldec_key_loop:
 	movaps (KEYP), %xmm0
-	AESIMC %xmm0 %xmm1
+	aesimc %xmm0, %xmm1
 	movaps %xmm1, (UKEYP)
 	add $0x10, KEYP
 	sub $0x10, UKEYP
@@ -1988,37 +1987,37 @@ SYM_FUNC_START_LOCAL(_aesni_enc1)
 	je .Lenc192
 	add $0x20, TKEYP
 	movaps -0x60(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps -0x50(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 .align 4
 .Lenc192:
 	movaps -0x40(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps -0x30(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 .align 4
 .Lenc128:
 	movaps -0x20(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps -0x10(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps (TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps 0x10(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps 0x20(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps 0x30(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps 0x40(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps 0x50(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps 0x60(TKEYP), KEY
-	AESENC KEY STATE
+	aesenc KEY, STATE
 	movaps 0x70(TKEYP), KEY
-	AESENCLAST KEY STATE
+	aesenclast KEY, STATE
 	ret
 SYM_FUNC_END(_aesni_enc1)
 
@@ -2054,79 +2053,79 @@ SYM_FUNC_START_LOCAL(_aesni_enc4)
 	je .L4enc192
 	add $0x20, TKEYP
 	movaps -0x60(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps -0x50(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 #.align 4
 .L4enc192:
 	movaps -0x40(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps -0x30(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 #.align 4
 .L4enc128:
 	movaps -0x20(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps -0x10(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps (TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps 0x10(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps 0x20(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps 0x30(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps 0x40(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps 0x50(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps 0x60(TKEYP), KEY
-	AESENC KEY STATE1
-	AESENC KEY STATE2
-	AESENC KEY STATE3
-	AESENC KEY STATE4
+	aesenc KEY, STATE1
+	aesenc KEY, STATE2
+	aesenc KEY, STATE3
+	aesenc KEY, STATE4
 	movaps 0x70(TKEYP), KEY
-	AESENCLAST KEY STATE1		# last round
-	AESENCLAST KEY STATE2
-	AESENCLAST KEY STATE3
-	AESENCLAST KEY STATE4
+	aesenclast KEY, STATE1		# last round
+	aesenclast KEY, STATE2
+	aesenclast KEY, STATE3
+	aesenclast KEY, STATE4
 	ret
 SYM_FUNC_END(_aesni_enc4)
 
@@ -2178,37 +2177,37 @@ SYM_FUNC_START_LOCAL(_aesni_dec1)
 	je .Ldec192
 	add $0x20, TKEYP
 	movaps -0x60(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps -0x50(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 .align 4
 .Ldec192:
 	movaps -0x40(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps -0x30(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 .align 4
 .Ldec128:
 	movaps -0x20(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps -0x10(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps (TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps 0x10(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps 0x20(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps 0x30(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps 0x40(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps 0x50(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps 0x60(TKEYP), KEY
-	AESDEC KEY STATE
+	aesdec KEY, STATE
 	movaps 0x70(TKEYP), KEY
-	AESDECLAST KEY STATE
+	aesdeclast KEY, STATE
 	ret
 SYM_FUNC_END(_aesni_dec1)
 
@@ -2244,79 +2243,79 @@ SYM_FUNC_START_LOCAL(_aesni_dec4)
 	je .L4dec192
 	add $0x20, TKEYP
 	movaps -0x60(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps -0x50(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 .align 4
 .L4dec192:
 	movaps -0x40(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps -0x30(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 .align 4
 .L4dec128:
 	movaps -0x20(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps -0x10(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps (TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps 0x10(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps 0x20(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps 0x30(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps 0x40(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps 0x50(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps 0x60(TKEYP), KEY
-	AESDEC KEY STATE1
-	AESDEC KEY STATE2
-	AESDEC KEY STATE3
-	AESDEC KEY STATE4
+	aesdec KEY, STATE1
+	aesdec KEY, STATE2
+	aesdec KEY, STATE3
+	aesdec KEY, STATE4
 	movaps 0x70(TKEYP), KEY
-	AESDECLAST KEY STATE1		# last round
-	AESDECLAST KEY STATE2
-	AESDECLAST KEY STATE3
-	AESDECLAST KEY STATE4
+	aesdeclast KEY, STATE1		# last round
+	aesdeclast KEY, STATE2
+	aesdeclast KEY, STATE3
+	aesdeclast KEY, STATE4
 	ret
 SYM_FUNC_END(_aesni_dec4)
 
@@ -2599,10 +2598,10 @@ SYM_FUNC_END(aesni_cbc_dec)
 SYM_FUNC_START_LOCAL(_aesni_inc_init)
 	movaps .Lbswap_mask, BSWAP_MASK
 	movaps IV, CTR
-	PSHUFB_XMM BSWAP_MASK CTR
+	pshufb BSWAP_MASK, CTR
 	mov $1, TCTR_LOW
-	MOVQ_R64_XMM TCTR_LOW INC
-	MOVQ_R64_XMM CTR TCTR_LOW
+	movq TCTR_LOW, INC
+	movq CTR, TCTR_LOW
 	ret
 SYM_FUNC_END(_aesni_inc_init)
 
@@ -2630,7 +2629,7 @@ SYM_FUNC_START_LOCAL(_aesni_inc)
 	psrldq $8, INC
 .Linc_low:
 	movaps CTR, IV
-	PSHUFB_XMM BSWAP_MASK IV
+	pshufb BSWAP_MASK, IV
 	ret
 SYM_FUNC_END(_aesni_inc)
 
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index 0cea33295287..5fee47956f3b 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -120,7 +120,6 @@
 ##
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 
 # constants in mergeable sections, linker can reorder and merge
 .section	.rodata.cst16.POLY, "aM", @progbits, 16
diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S
index a38ab2512a6f..ca1788bfee16 100644
--- a/arch/x86/crypto/chacha-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha-ssse3-x86_64.S
@@ -120,10 +120,10 @@ SYM_FUNC_START(chacha_block_xor_ssse3)
 	FRAME_BEGIN
 
 	# x0..3 = s0..3
-	movdqa		0x00(%rdi),%xmm0
-	movdqa		0x10(%rdi),%xmm1
-	movdqa		0x20(%rdi),%xmm2
-	movdqa		0x30(%rdi),%xmm3
+	movdqu		0x00(%rdi),%xmm0
+	movdqu		0x10(%rdi),%xmm1
+	movdqu		0x20(%rdi),%xmm2
+	movdqu		0x30(%rdi),%xmm3
 	movdqa		%xmm0,%xmm8
 	movdqa		%xmm1,%xmm9
 	movdqa		%xmm2,%xmm10
@@ -205,10 +205,10 @@ SYM_FUNC_START(hchacha_block_ssse3)
 	# %edx: nrounds
 	FRAME_BEGIN
 
-	movdqa		0x00(%rdi),%xmm0
-	movdqa		0x10(%rdi),%xmm1
-	movdqa		0x20(%rdi),%xmm2
-	movdqa		0x30(%rdi),%xmm3
+	movdqu		0x00(%rdi),%xmm0
+	movdqu		0x10(%rdi),%xmm1
+	movdqu		0x20(%rdi),%xmm2
+	movdqu		0x30(%rdi),%xmm3
 
 	mov		%edx,%r8d
 	call		chacha_permute
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 22250091cdbe..e67a59130025 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -14,8 +14,6 @@
 #include <linux/module.h>
 #include <asm/simd.h>
 
-#define CHACHA_STATE_ALIGN 16
-
 asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
 asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
@@ -124,8 +122,6 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 
 void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
 {
-	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
-
 	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
 		hchacha_block_generic(state, stream, nrounds);
 	} else {
@@ -138,8 +134,6 @@ EXPORT_SYMBOL(hchacha_block_arch);
 
 void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
 {
-	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
-
 	chacha_init_generic(state, key, iv);
 }
 EXPORT_SYMBOL(chacha_init_arch);
@@ -147,8 +141,6 @@ EXPORT_SYMBOL(chacha_init_arch);
 void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
 		       int nrounds)
 {
-	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
-
 	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
 	    bytes <= CHACHA_BLOCK_SIZE)
 		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
@@ -170,15 +162,12 @@ EXPORT_SYMBOL(chacha_crypt_arch);
 static int chacha_simd_stream_xor(struct skcipher_request *req,
 				  const struct chacha_ctx *ctx, const u8 *iv)
 {
-	u32 *state, state_buf[16 + 2] __aligned(8);
+	u32 state[CHACHA_STATE_WORDS] __aligned(8);
 	struct skcipher_walk walk;
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
-	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
-
 	chacha_init_generic(state, ctx->key, iv);
 
 	while (walk.nbytes > 0) {
@@ -217,12 +206,10 @@ static int xchacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	u32 *state, state_buf[16 + 2] __aligned(8);
+	u32 state[CHACHA_STATE_WORDS] __aligned(8);
 	struct chacha_ctx subctx;
 	u8 real_iv[16];
 
-	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
-	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
 	chacha_init_generic(state, ctx->key, req->iv);
 
 	if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
index 9fd28ff65bc2..6e7d4c4d3208 100644
--- a/arch/x86/crypto/crc32-pclmul_asm.S
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -38,7 +38,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 
 
 .section .rodata
@@ -129,17 +128,17 @@ loop_64:/*  64 bytes Full cache line folding */
 #ifdef __x86_64__
 	movdqa  %xmm4, %xmm8
 #endif
-	PCLMULQDQ 00, CONSTANT, %xmm1
-	PCLMULQDQ 00, CONSTANT, %xmm2
-	PCLMULQDQ 00, CONSTANT, %xmm3
+	pclmulqdq $0x00, CONSTANT, %xmm1
+	pclmulqdq $0x00, CONSTANT, %xmm2
+	pclmulqdq $0x00, CONSTANT, %xmm3
 #ifdef __x86_64__
-	PCLMULQDQ 00, CONSTANT, %xmm4
+	pclmulqdq $0x00, CONSTANT, %xmm4
 #endif
-	PCLMULQDQ 0x11, CONSTANT, %xmm5
-	PCLMULQDQ 0x11, CONSTANT, %xmm6
-	PCLMULQDQ 0x11, CONSTANT, %xmm7
+	pclmulqdq $0x11, CONSTANT, %xmm5
+	pclmulqdq $0x11, CONSTANT, %xmm6
+	pclmulqdq $0x11, CONSTANT, %xmm7
 #ifdef __x86_64__
-	PCLMULQDQ 0x11, CONSTANT, %xmm8
+	pclmulqdq $0x11, CONSTANT, %xmm8
 #endif
 	pxor    %xmm5, %xmm1
 	pxor    %xmm6, %xmm2
@@ -149,8 +148,8 @@ loop_64:/*  64 bytes Full cache line folding */
 #else
 	/* xmm8 unsupported for x32 */
 	movdqa  %xmm4, %xmm5
-	PCLMULQDQ 00, CONSTANT, %xmm4
-	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pclmulqdq $0x00, CONSTANT, %xmm4
+	pclmulqdq $0x11, CONSTANT, %xmm5
 	pxor    %xmm5, %xmm4
 #endif
 
@@ -172,20 +171,20 @@ less_64:/*  Folding cache line into 128bit */
 	prefetchnta     (BUF)
 
 	movdqa  %xmm1, %xmm5
-	PCLMULQDQ 0x00, CONSTANT, %xmm1
-	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pclmulqdq $0x00, CONSTANT, %xmm1
+	pclmulqdq $0x11, CONSTANT, %xmm5
 	pxor    %xmm5, %xmm1
 	pxor    %xmm2, %xmm1
 
 	movdqa  %xmm1, %xmm5
-	PCLMULQDQ 0x00, CONSTANT, %xmm1
-	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pclmulqdq $0x00, CONSTANT, %xmm1
+	pclmulqdq $0x11, CONSTANT, %xmm5
 	pxor    %xmm5, %xmm1
 	pxor    %xmm3, %xmm1
 
 	movdqa  %xmm1, %xmm5
-	PCLMULQDQ 0x00, CONSTANT, %xmm1
-	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pclmulqdq $0x00, CONSTANT, %xmm1
+	pclmulqdq $0x11, CONSTANT, %xmm5
 	pxor    %xmm5, %xmm1
 	pxor    %xmm4, %xmm1
 
@@ -193,8 +192,8 @@ less_64:/*  Folding cache line into 128bit */
 	jb      fold_64
 loop_16:/* Folding rest buffer into 128bit */
 	movdqa  %xmm1, %xmm5
-	PCLMULQDQ 0x00, CONSTANT, %xmm1
-	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pclmulqdq $0x00, CONSTANT, %xmm1
+	pclmulqdq $0x11, CONSTANT, %xmm5
 	pxor    %xmm5, %xmm1
 	pxor    (BUF), %xmm1
 	sub     $0x10, LEN
@@ -205,7 +204,7 @@ loop_16:/* Folding rest buffer into 128bit */
 fold_64:
 	/* perform the last 64 bit fold, also adds 32 zeroes
 	 * to the input stream */
-	PCLMULQDQ 0x01, %xmm1, CONSTANT /* R4 * xmm1.low */
+	pclmulqdq $0x01, %xmm1, CONSTANT /* R4 * xmm1.low */
 	psrldq  $0x08, %xmm1
 	pxor    CONSTANT, %xmm1
 
@@ -220,7 +219,7 @@ fold_64:
 #endif
 	psrldq  $0x04, %xmm2
 	pand    %xmm3, %xmm1
-	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	pclmulqdq $0x00, CONSTANT, %xmm1
 	pxor    %xmm2, %xmm1
 
 	/* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
@@ -231,11 +230,11 @@ fold_64:
 #endif
 	movdqa  %xmm1, %xmm2
 	pand    %xmm3, %xmm1
-	PCLMULQDQ 0x10, CONSTANT, %xmm1
+	pclmulqdq $0x10, CONSTANT, %xmm1
 	pand    %xmm3, %xmm1
-	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	pclmulqdq $0x00, CONSTANT, %xmm1
 	pxor    %xmm2, %xmm1
-	PEXTRD  0x01, %xmm1, %eax
+	pextrd  $0x01, %xmm1, %eax
 
 	ret
 SYM_FUNC_END(crc32_pclmul_le_16)
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 8501ec4532f4..884dc767b051 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -43,7 +43,6 @@
  * SOFTWARE.
  */
 
-#include <asm/inst.h>
 #include <linux/linkage.h>
 #include <asm/nospec-branch.h>
 
@@ -170,7 +169,7 @@ continue_block:
 
 	## branch into array
 	lea	jump_table(%rip), %bufp
-	movzxw  (%bufp, %rax, 2), len
+	movzwq  (%bufp, %rax, 2), len
 	lea	crc_array(%rip), %bufp
 	lea     (%bufp, len, 1), %bufp
 	JMP_NOSPEC bufp
@@ -225,10 +224,10 @@ LABEL crc_ %i
 	subq    %rax, tmp			# tmp -= rax*24
 
 	movq    crc_init, %xmm1			# CRC for block 1
-	PCLMULQDQ 0x00,%xmm0,%xmm1		# Multiply by K2
+	pclmulqdq $0x00, %xmm0, %xmm1		# Multiply by K2
 
 	movq    crc1, %xmm2			# CRC for block 2
-	PCLMULQDQ 0x10, %xmm0, %xmm2		# Multiply by K1
+	pclmulqdq $0x10, %xmm0, %xmm2		# Multiply by K1
 
 	pxor    %xmm2,%xmm1
 	movq    %xmm1, %rax
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
index 8a17621f7d3a..8acbb6584a37 100644
--- a/arch/x86/crypto/curve25519-x86_64.c
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -948,10 +948,8 @@ static void store_felem(u64 *b, u64 *f)
 {
 	u64 f30 = f[3U];
 	u64 top_bit0 = f30 >> (u32)63U;
-	u64 carry0;
 	u64 f31;
 	u64 top_bit;
-	u64 carry;
 	u64 f0;
 	u64 f1;
 	u64 f2;
@@ -970,11 +968,11 @@ static void store_felem(u64 *b, u64 *f)
 	u64 o2;
 	u64 o3;
 	f[3U] = f30 & (u64)0x7fffffffffffffffU;
-	carry0 = add_scalar(f, f, (u64)19U * top_bit0);
+	add_scalar(f, f, (u64)19U * top_bit0);
 	f31 = f[3U];
 	top_bit = f31 >> (u32)63U;
 	f[3U] = f31 & (u64)0x7fffffffffffffffU;
-	carry = add_scalar(f, f, (u64)19U * top_bit);
+	add_scalar(f, f, (u64)19U * top_bit);
 	f0 = f[0U];
 	f1 = f[1U];
 	f2 = f[2U];
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index bb9735fbb865..99ac25e18e09 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -14,7 +14,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 #include <asm/frame.h>
 
 .section	.rodata.cst16.bswap_mask, "aM", @progbits, 16
@@ -51,9 +50,9 @@ SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble)
 	pxor DATA, T2
 	pxor SHASH, T3
 
-	PCLMULQDQ 0x00 SHASH DATA	# DATA = a0 * b0
-	PCLMULQDQ 0x11 SHASH T1		# T1 = a1 * b1
-	PCLMULQDQ 0x00 T3 T2		# T2 = (a1 + a0) * (b1 + b0)
+	pclmulqdq $0x00, SHASH, DATA	# DATA = a0 * b0
+	pclmulqdq $0x11, SHASH, T1	# T1 = a1 * b1
+	pclmulqdq $0x00, T3, T2		# T2 = (a1 + a0) * (b1 + b0)
 	pxor DATA, T2
 	pxor T1, T2			# T2 = a0 * b1 + a1 * b0
 
@@ -95,9 +94,9 @@ SYM_FUNC_START(clmul_ghash_mul)
 	movups (%rdi), DATA
 	movups (%rsi), SHASH
 	movaps .Lbswap_mask, BSWAP
-	PSHUFB_XMM BSWAP DATA
+	pshufb BSWAP, DATA
 	call __clmul_gf128mul_ble
-	PSHUFB_XMM BSWAP DATA
+	pshufb BSWAP, DATA
 	movups DATA, (%rdi)
 	FRAME_END
 	ret
@@ -114,18 +113,18 @@ SYM_FUNC_START(clmul_ghash_update)
 	movaps .Lbswap_mask, BSWAP
 	movups (%rdi), DATA
 	movups (%rcx), SHASH
-	PSHUFB_XMM BSWAP DATA
+	pshufb BSWAP, DATA
 .align 4
 .Lupdate_loop:
 	movups (%rsi), IN1
-	PSHUFB_XMM BSWAP IN1
+	pshufb BSWAP, IN1
 	pxor IN1, DATA
 	call __clmul_gf128mul_ble
 	sub $16, %rdx
 	add $16, %rsi
 	cmp $16, %rdx
 	jge .Lupdate_loop
-	PSHUFB_XMM BSWAP DATA
+	pshufb BSWAP, DATA
 	movups DATA, (%rdi)
 .Lupdate_just_ret:
 	FRAME_END
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index b7a5790d8d63..08bf95dbc911 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -7,12 +7,20 @@ KASAN_SANITIZE := n
 UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
-CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
-CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
-CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_64.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_32.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_x32.o	= $(CC_FLAGS_FTRACE)
+
+CFLAGS_common.o			+= -fno-stack-protector
+CFLAGS_syscall_64.o		+= -fno-stack-protector
+CFLAGS_syscall_32.o		+= -fno-stack-protector
+CFLAGS_syscall_x32.o		+= -fno-stack-protector
 
 CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
 CFLAGS_syscall_32.o		+= $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_x32.o		+= $(call cc-option,-Wno-override-init,)
+
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index bd3f14175193..54ad1890aefc 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -45,6 +45,32 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
+/* Check that the stack and regs on entry from user mode are sane. */
+static noinstr void check_user_regs(struct pt_regs *regs)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
+		/*
+		 * Make sure that the entry code gave us a sensible EFLAGS
+		 * register.  Native because we want to check the actual CPU
+		 * state, not the interrupt state as imagined by Xen.
+		 */
+		unsigned long flags = native_save_fl();
+		WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
+				      X86_EFLAGS_NT));
+
+		/* We think we came from user mode. Make sure pt_regs agrees. */
+		WARN_ON_ONCE(!user_mode(regs));
+
+		/*
+		 * All entries from user mode (except #DF) should be on the
+		 * normal thread stack and should have user pt_regs in the
+		 * correct location.
+		 */
+		WARN_ON_ONCE(!on_thread_stack());
+		WARN_ON_ONCE(regs != task_pt_regs(current));
+	}
+}
+
 #ifdef CONFIG_CONTEXT_TRACKING
 /**
  * enter_from_user_mode - Establish state when coming from user mode
@@ -127,9 +153,6 @@ static long syscall_trace_enter(struct pt_regs *regs)
 	unsigned long ret = 0;
 	u32 work;
 
-	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
-		BUG_ON(regs != task_pt_regs(current));
-
 	work = READ_ONCE(ti->flags);
 
 	if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
@@ -271,7 +294,7 @@ static void __prepare_exit_to_usermode(struct pt_regs *regs)
 #endif
 }
 
-__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
+static noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
 {
 	instrumentation_begin();
 	__prepare_exit_to_usermode(regs);
@@ -346,6 +369,8 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 {
 	struct thread_info *ti;
 
+	check_user_regs(regs);
+
 	enter_from_user_mode();
 	instrumentation_begin();
 
@@ -409,6 +434,8 @@ static void do_syscall_32_irqs_on(struct pt_regs *regs)
 /* Handles int $0x80 */
 __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
+	check_user_regs(regs);
+
 	enter_from_user_mode();
 	instrumentation_begin();
 
@@ -460,6 +487,8 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
 					vdso_image_32.sym_int80_landing_pad;
 	bool success;
 
+	check_user_regs(regs);
+
 	/*
 	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
 	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
@@ -510,6 +539,18 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
 		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
 #endif
 }
+
+/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
+__visible noinstr long do_SYSENTER_32(struct pt_regs *regs)
+{
+	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
+	regs->sp = regs->bp;
+
+	/* SYSENTER clobbers EFLAGS.IF.  Assume it was set in usermode. */
+	regs->flags |= X86_EFLAGS_IF;
+
+	return do_fast_syscall_32(regs);
+}
 #endif
 
 SYSCALL_DEFINE0(ni_syscall)
@@ -518,8 +559,7 @@ SYSCALL_DEFINE0(ni_syscall)
 }
 
 /**
- * idtentry_enter_cond_rcu - Handle state tracking on idtentry with conditional
- *			     RCU handling
+ * idtentry_enter - Handle state tracking on ordinary idtentries
  * @regs:	Pointer to pt_regs of interrupted context
  *
  * Invokes:
@@ -531,6 +571,9 @@ SYSCALL_DEFINE0(ni_syscall)
  *  - The hardirq tracer to keep the state consistent as low level ASM
  *    entry disabled interrupts.
  *
+ * As a precondition, this requires that the entry came from user mode,
+ * idle, or a kernel context in which RCU is watching.
+ *
  * For kernel mode entries RCU handling is done conditional. If RCU is
  * watching then the only RCU requirement is to check whether the tick has
  * to be restarted. If RCU is not watching then rcu_irq_enter() has to be
@@ -544,17 +587,21 @@ SYSCALL_DEFINE0(ni_syscall)
  * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
  * would not be possible.
  *
- * Returns: True if RCU has been adjusted on a kernel entry
- *	    False otherwise
+ * Returns: An opaque object that must be passed to idtentry_exit()
  *
- * The return value must be fed into the rcu_exit argument of
- * idtentry_exit_cond_rcu().
+ * The return value must be fed into the state argument of
+ * idtentry_exit().
  */
-bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
+noinstr idtentry_state_t idtentry_enter(struct pt_regs *regs)
 {
+	idtentry_state_t ret = {
+		.exit_rcu = false,
+	};
+
 	if (user_mode(regs)) {
+		check_user_regs(regs);
 		enter_from_user_mode();
-		return false;
+		return ret;
 	}
 
 	/*
@@ -592,7 +639,8 @@ bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
 		trace_hardirqs_off_finish();
 		instrumentation_end();
 
-		return true;
+		ret.exit_rcu = true;
+		return ret;
 	}
 
 	/*
@@ -607,7 +655,7 @@ bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
 	trace_hardirqs_off();
 	instrumentation_end();
 
-	return false;
+	return ret;
 }
 
 static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
@@ -625,10 +673,9 @@ static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
 }
 
 /**
- * idtentry_exit_cond_rcu - Handle return from exception with conditional RCU
- *			    handling
+ * idtentry_exit - Handle return from exception that used idtentry_enter()
  * @regs:	Pointer to pt_regs (exception entry regs)
- * @rcu_exit:	Invoke rcu_irq_exit() if true
+ * @state:	Return value from matching call to idtentry_enter()
  *
  * Depending on the return target (kernel/user) this runs the necessary
  * preemption and work checks if possible and reguired and returns to
@@ -637,10 +684,10 @@ static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
  * This is the last action before returning to the low level ASM code which
  * just needs to return to the appropriate context.
  *
- * Counterpart to idtentry_enter_cond_rcu(). The return value of the entry
- * function must be fed into the @rcu_exit argument.
+ * Counterpart to idtentry_enter(). The return value of the entry
+ * function must be fed into the @state argument.
  */
-void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
+noinstr void idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
 {
 	lockdep_assert_irqs_disabled();
 
@@ -653,7 +700,7 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
 		 * carefully and needs the same ordering of lockdep/tracing
 		 * and RCU as the return to user mode path.
 		 */
-		if (rcu_exit) {
+		if (state.exit_rcu) {
 			instrumentation_begin();
 			/* Tell the tracer that IRET will enable interrupts */
 			trace_hardirqs_on_prepare();
@@ -672,7 +719,7 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
 		 * IRQ flags state is correct already. Just tell RCU if it
 		 * was not watching on entry.
 		 */
-		if (rcu_exit)
+		if (state.exit_rcu)
 			rcu_irq_exit();
 	}
 }
@@ -684,8 +731,9 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
  * Invokes enter_from_user_mode() to establish the proper context for
  * NOHZ_FULL. Otherwise scheduling on exit would not be possible.
  */
-void noinstr idtentry_enter_user(struct pt_regs *regs)
+noinstr void idtentry_enter_user(struct pt_regs *regs)
 {
+	check_user_regs(regs);
 	enter_from_user_mode();
 }
 
@@ -701,13 +749,47 @@ void noinstr idtentry_enter_user(struct pt_regs *regs)
  *
  * Counterpart to idtentry_enter_user().
  */
-void noinstr idtentry_exit_user(struct pt_regs *regs)
+noinstr void idtentry_exit_user(struct pt_regs *regs)
 {
 	lockdep_assert_irqs_disabled();
 
 	prepare_exit_to_usermode(regs);
 }
 
+noinstr bool idtentry_enter_nmi(struct pt_regs *regs)
+{
+	bool irq_state = lockdep_hardirqs_enabled();
+
+	__nmi_enter();
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirq_enter();
+	rcu_nmi_enter();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	ftrace_nmi_enter();
+	instrumentation_end();
+
+	return irq_state;
+}
+
+noinstr void idtentry_exit_nmi(struct pt_regs *regs, bool restore)
+{
+	instrumentation_begin();
+	ftrace_nmi_exit();
+	if (restore) {
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	}
+	instrumentation_end();
+
+	rcu_nmi_exit();
+	lockdep_hardirq_exit();
+	if (restore)
+		lockdep_hardirqs_on(CALLER_ADDR0);
+	__nmi_exit();
+}
+
 #ifdef CONFIG_XEN_PV
 #ifndef CONFIG_PREEMPTION
 /*
@@ -757,9 +839,10 @@ static void __xen_pv_evtchn_do_upcall(void)
 __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;
-	bool inhcall, rcu_exit;
+	bool inhcall;
+	idtentry_state_t state;
 
-	rcu_exit = idtentry_enter_cond_rcu(regs);
+	state = idtentry_enter(regs);
 	old_regs = set_irq_regs(regs);
 
 	instrumentation_begin();
@@ -769,13 +852,13 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 
 	inhcall = get_and_clear_inhcall();
-	if (inhcall && !WARN_ON_ONCE(rcu_exit)) {
+	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
 		instrumentation_begin();
 		idtentry_exit_cond_resched(regs, true);
 		instrumentation_end();
 		restore_inhcall(inhcall);
 	} else {
-		idtentry_exit_cond_rcu(regs, rcu_exit);
+		idtentry_exit(regs, state);
 	}
 }
 #endif /* CONFIG_XEN_PV */
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 024d7d276cd4..2d0bd5d5f032 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -933,9 +933,8 @@ SYM_FUNC_START(entry_SYSENTER_32)
 
 .Lsysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
-	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
+	pushl	$0			/* pt_regs->sp (placeholder) */
 	pushfl				/* pt_regs->flags (except IF = 0) */
-	orl	$X86_EFLAGS_IF, (%esp)	/* Fix IF */
 	pushl	$__USER_CS		/* pt_regs->cs */
 	pushl	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushl	%eax			/* pt_regs->orig_ax */
@@ -965,7 +964,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
 .Lsysenter_flags_fixed:
 
 	movl	%esp, %eax
-	call	do_fast_syscall_32
+	call	do_SYSENTER_32
 	/* XEN PV guests always use IRET path */
 	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
 		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 0f974ae01e62..541fdaf64045 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -57,29 +57,30 @@ SYM_CODE_START(entry_SYSENTER_compat)
 
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
-	/*
-	 * User tracing code (ptrace or signal handlers) might assume that
-	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
-	 * syscall.  Just in case the high bits are nonzero, zero-extend
-	 * the syscall number.  (This could almost certainly be deleted
-	 * with no ill effects.)
-	 */
-	movl	%eax, %eax
-
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER32_DS		/* pt_regs->ss */
-	pushq	%rbp			/* pt_regs->sp (stashed in bp) */
+	pushq	$0			/* pt_regs->sp = 0 (placeholder) */
 
 	/*
 	 * Push flags.  This is nasty.  First, interrupts are currently
-	 * off, but we need pt_regs->flags to have IF set.  Second, even
-	 * if TF was set when SYSENTER started, it's clear by now.  We fix
-	 * that later using TIF_SINGLESTEP.
+	 * off, but we need pt_regs->flags to have IF set.  Second, if TS
+	 * was set in usermode, it's still set, and we're singlestepping
+	 * through this code.  do_SYSENTER_32() will fix up IF.
 	 */
 	pushfq				/* pt_regs->flags (except IF = 0) */
-	orl	$X86_EFLAGS_IF, (%rsp)	/* Fix saved flags */
 	pushq	$__USER32_CS		/* pt_regs->cs */
 	pushq	$0			/* pt_regs->ip = 0 (placeholder) */
+SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
+
+	/*
+	 * User tracing code (ptrace or signal handlers) might assume that
+	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
+	 * syscall.  Just in case the high bits are nonzero, zero-extend
+	 * the syscall number.  (This could almost certainly be deleted
+	 * with no ill effects.)
+	 */
+	movl	%eax, %eax
+
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
@@ -135,7 +136,7 @@ SYM_CODE_START(entry_SYSENTER_compat)
 .Lsysenter_flags_fixed:
 
 	movq	%rsp, %rdi
-	call	do_fast_syscall_32
+	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
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 12c42eba77ec..9933c0e8e97a 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y					+= core.o probe.o
-obj-$(PERF_EVENTS_INTEL_RAPL)		+= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= rapl.o
 obj-y					+= amd/
 obj-$(CONFIG_X86_LOCAL_APIC)            += msr.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 4103665c6e03..1cbf57dc2ac8 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -71,10 +71,9 @@ u64 x86_perf_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
-	int idx = hwc->idx;
 	u64 delta;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -359,6 +358,7 @@ void x86_release_hardware(void)
 	if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) {
 		release_pmc_hardware();
 		release_ds_buffers();
+		release_lbr_buffers();
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 }
@@ -1097,22 +1097,31 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 				struct cpu_hw_events *cpuc, int i)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	int idx;
 
-	hwc->idx = cpuc->assign[i];
+	idx = hwc->idx = cpuc->assign[i];
 	hwc->last_cpu = smp_processor_id();
 	hwc->last_tag = ++cpuc->tags[i];
 
-	if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
+	switch (hwc->idx) {
+	case INTEL_PMC_IDX_FIXED_BTS:
+	case INTEL_PMC_IDX_FIXED_VLBR:
 		hwc->config_base = 0;
 		hwc->event_base	= 0;
-	} else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
+		break;
+
+	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
-		hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
-	} else {
+		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
+				(idx - INTEL_PMC_IDX_FIXED);
+		hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | 1<<30;
+		break;
+
+	default:
 		hwc->config_base = x86_pmu_config_addr(hwc->idx);
 		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
 		hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx);
+		break;
 	}
 }
 
@@ -1233,7 +1242,7 @@ int x86_perf_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0, idx = hwc->idx;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -2363,7 +2372,6 @@ static struct pmu pmu = {
 
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
-	.task_ctx_size          = sizeof(struct x86_perf_task_context),
 	.swap_task_ctx		= x86_pmu_swap_task_ctx,
 	.check_period		= x86_pmu_check_period,
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ca35c8b5ee10..50963472ee85 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2136,8 +2136,35 @@ static inline void intel_pmu_ack_status(u64 ack)
 	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
-static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static inline bool event_is_checkpointed(struct perf_event *event)
 {
+	return unlikely(event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
+static inline void intel_set_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (event->attr.exclude_host)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	if (event->attr.exclude_guest)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	if (event_is_checkpointed(event))
+		__set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static inline void intel_clear_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static void intel_pmu_disable_fixed(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
@@ -2148,30 +2175,22 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 	wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static inline bool event_is_checkpointed(struct perf_event *event)
-{
-	return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
-}
-
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx = hwc->idx;
 
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_clear_masks(event, idx);
+		x86_pmu_disable_event(event);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_clear_masks(event, idx);
+		intel_pmu_disable_fixed(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
-		return;
-	}
-
-	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
-
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
-		intel_pmu_disable_fixed(hwc);
-	else
-		x86_pmu_disable_event(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_clear_masks(event, idx);
 
 	/*
 	 * Needs to be called after x86_pmu_disable_event,
@@ -2238,33 +2257,23 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
-		if (!__this_cpu_read(cpu_hw_events.enabled))
-			return;
-
-		intel_pmu_enable_bts(hwc->config);
-		return;
-	}
-
-	if (event->attr.exclude_host)
-		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
-	if (event->attr.exclude_guest)
-		cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
-
-	if (unlikely(event_is_checkpointed(event)))
-		cpuc->intel_cp_status |= (1ull << hwc->idx);
+	int idx = hwc->idx;
 
 	if (unlikely(event->attr.precise_ip))
 		intel_pmu_pebs_enable(event);
 
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_set_masks(event, idx);
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_set_masks(event, idx);
 		intel_pmu_enable_fixed(event);
-		return;
-	}
-
-	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
+		if (!__this_cpu_read(cpu_hw_events.enabled))
+			return;
+		intel_pmu_enable_bts(hwc->config);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_set_masks(event, idx);
 }
 
 static void intel_pmu_add_event(struct perf_event *event)
@@ -2614,6 +2623,20 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
+/*
+ * Note: matches a fake event, like Fixed2.
+ */
+static struct event_constraint *
+intel_vlbr_constraints(struct perf_event *event)
+{
+	struct event_constraint *c = &vlbr_constraint;
+
+	if (unlikely(constraint_match(c, event->hw.config)))
+		return c;
+
+	return NULL;
+}
+
 static int intel_alt_er(int idx, u64 config)
 {
 	int alt_idx = idx;
@@ -2804,6 +2827,10 @@ __intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct event_constraint *c;
 
+	c = intel_vlbr_constraints(event);
+	if (c)
+		return c;
+
 	c = intel_bts_constraints(event);
 	if (c)
 		return c;
@@ -3951,6 +3978,11 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_dead		= intel_pmu_cpu_dead,
 
 	.check_period		= intel_pmu_check_period,
+
+	.lbr_reset		= intel_pmu_lbr_reset_64,
+	.lbr_read		= intel_pmu_lbr_read_64,
+	.lbr_save		= intel_pmu_lbr_save,
+	.lbr_restore		= intel_pmu_lbr_restore,
 };
 
 static __initconst const struct x86_pmu intel_pmu = {
@@ -3996,6 +4028,11 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.check_period		= intel_pmu_check_period,
 
 	.aux_output_match	= intel_pmu_aux_output_match,
+
+	.lbr_reset		= intel_pmu_lbr_reset_64,
+	.lbr_read		= intel_pmu_lbr_read_64,
+	.lbr_save		= intel_pmu_lbr_save,
+	.lbr_restore		= intel_pmu_lbr_restore,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -4622,6 +4659,14 @@ __init int intel_pmu_init(void)
 		x86_pmu.intel_cap.capabilities = capabilities;
 	}
 
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) {
+		x86_pmu.lbr_reset = intel_pmu_lbr_reset_32;
+		x86_pmu.lbr_read = intel_pmu_lbr_read_32;
+	}
+
+	if (boot_cpu_has(X86_FEATURE_ARCH_LBR))
+		intel_pmu_arch_lbr_init();
+
 	intel_ds_init();
 
 	x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index dc43cc124e09..86848c57b55e 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -954,7 +954,7 @@ static void adaptive_pebs_record_size_update(void)
 	if (pebs_data_cfg & PEBS_DATACFG_XMMS)
 		sz += sizeof(struct pebs_xmm);
 	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
-		sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+		sz += x86_pmu.lbr_nr * sizeof(struct lbr_entry);
 
 	cpuc->pebs_record_size = sz;
 }
@@ -1595,10 +1595,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	}
 
 	if (format_size & PEBS_DATACFG_LBRS) {
-		struct pebs_lbr *lbr = next_record;
+		struct lbr_entry *lbr = next_record;
 		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
 					& 0xff) + 1;
-		next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+		next_record = next_record + num_lbr * sizeof(struct lbr_entry);
 
 		if (has_branch_stack(event)) {
 			intel_pmu_store_pebs_lbrs(lbr);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 65113b16804a..63f58bdf556c 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -8,17 +8,6 @@
 
 #include "../perf_event.h"
 
-enum {
-	LBR_FORMAT_32		= 0x00,
-	LBR_FORMAT_LIP		= 0x01,
-	LBR_FORMAT_EIP		= 0x02,
-	LBR_FORMAT_EIP_FLAGS	= 0x03,
-	LBR_FORMAT_EIP_FLAGS2	= 0x04,
-	LBR_FORMAT_INFO		= 0x05,
-	LBR_FORMAT_TIME		= 0x06,
-	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_TIME,
-};
-
 static const enum {
 	LBR_EIP_FLAGS		= 1,
 	LBR_TSX			= 2,
@@ -143,8 +132,54 @@ enum {
 	 X86_BR_IRQ		|\
 	 X86_BR_INT)
 
+/*
+ * Intel LBR_CTL bits
+ *
+ * Hardware branch filter for Arch LBR
+ */
+#define ARCH_LBR_KERNEL_BIT		1  /* capture at ring0 */
+#define ARCH_LBR_USER_BIT		2  /* capture at ring > 0 */
+#define ARCH_LBR_CALL_STACK_BIT		3  /* enable call stack */
+#define ARCH_LBR_JCC_BIT		16 /* capture conditional branches */
+#define ARCH_LBR_REL_JMP_BIT		17 /* capture relative jumps */
+#define ARCH_LBR_IND_JMP_BIT		18 /* capture indirect jumps */
+#define ARCH_LBR_REL_CALL_BIT		19 /* capture relative calls */
+#define ARCH_LBR_IND_CALL_BIT		20 /* capture indirect calls */
+#define ARCH_LBR_RETURN_BIT		21 /* capture near returns */
+#define ARCH_LBR_OTHER_BRANCH_BIT	22 /* capture other branches */
+
+#define ARCH_LBR_KERNEL			(1ULL << ARCH_LBR_KERNEL_BIT)
+#define ARCH_LBR_USER			(1ULL << ARCH_LBR_USER_BIT)
+#define ARCH_LBR_CALL_STACK		(1ULL << ARCH_LBR_CALL_STACK_BIT)
+#define ARCH_LBR_JCC			(1ULL << ARCH_LBR_JCC_BIT)
+#define ARCH_LBR_REL_JMP		(1ULL << ARCH_LBR_REL_JMP_BIT)
+#define ARCH_LBR_IND_JMP		(1ULL << ARCH_LBR_IND_JMP_BIT)
+#define ARCH_LBR_REL_CALL		(1ULL << ARCH_LBR_REL_CALL_BIT)
+#define ARCH_LBR_IND_CALL		(1ULL << ARCH_LBR_IND_CALL_BIT)
+#define ARCH_LBR_RETURN			(1ULL << ARCH_LBR_RETURN_BIT)
+#define ARCH_LBR_OTHER_BRANCH		(1ULL << ARCH_LBR_OTHER_BRANCH_BIT)
+
+#define ARCH_LBR_ANY			 \
+	(ARCH_LBR_JCC			|\
+	 ARCH_LBR_REL_JMP		|\
+	 ARCH_LBR_IND_JMP		|\
+	 ARCH_LBR_REL_CALL		|\
+	 ARCH_LBR_IND_CALL		|\
+	 ARCH_LBR_RETURN		|\
+	 ARCH_LBR_OTHER_BRANCH)
+
+#define ARCH_LBR_CTL_MASK			0x7f000e
+
 static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
 
+static __always_inline bool is_lbr_call_stack_bit_set(u64 config)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return !!(config & ARCH_LBR_CALL_STACK);
+
+	return !!(config & LBR_CALL_STACK);
+}
+
 /*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
@@ -168,33 +203,46 @@ static void __intel_pmu_lbr_enable(bool pmi)
 	 */
 	if (cpuc->lbr_sel)
 		lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
-	if (!pmi && cpuc->lbr_sel)
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && !pmi && cpuc->lbr_sel)
 		wrmsrl(MSR_LBR_SELECT, lbr_select);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	orig_debugctl = debugctl;
-	debugctl |= DEBUGCTLMSR_LBR;
+
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
+		debugctl |= DEBUGCTLMSR_LBR;
 	/*
 	 * LBR callstack does not work well with FREEZE_LBRS_ON_PMI.
 	 * If FREEZE_LBRS_ON_PMI is set, PMI near call/return instructions
 	 * may cause superfluous increase/decrease of LBR_TOS.
 	 */
-	if (!(lbr_select & LBR_CALL_STACK))
+	if (is_lbr_call_stack_bit_set(lbr_select))
+		debugctl &= ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
+	else
 		debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
+
 	if (orig_debugctl != debugctl)
 		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+		wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
 }
 
 static void __intel_pmu_lbr_disable(void)
 {
 	u64 debugctl;
 
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
+		wrmsrl(MSR_ARCH_LBR_CTL, 0);
+		return;
+	}
+
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 }
 
-static void intel_pmu_lbr_reset_32(void)
+void intel_pmu_lbr_reset_32(void)
 {
 	int i;
 
@@ -202,7 +250,7 @@ static void intel_pmu_lbr_reset_32(void)
 		wrmsrl(x86_pmu.lbr_from + i, 0);
 }
 
-static void intel_pmu_lbr_reset_64(void)
+void intel_pmu_lbr_reset_64(void)
 {
 	int i;
 
@@ -210,10 +258,16 @@ static void intel_pmu_lbr_reset_64(void)
 		wrmsrl(x86_pmu.lbr_from + i, 0);
 		wrmsrl(x86_pmu.lbr_to   + i, 0);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-			wrmsrl(MSR_LBR_INFO_0 + i, 0);
+			wrmsrl(x86_pmu.lbr_info + i, 0);
 	}
 }
 
+static void intel_pmu_arch_lbr_reset(void)
+{
+	/* Write to ARCH_LBR_DEPTH MSR, all LBR entries are reset to 0 */
+	wrmsrl(MSR_ARCH_LBR_DEPTH, x86_pmu.lbr_nr);
+}
+
 void intel_pmu_lbr_reset(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -221,10 +275,7 @@ void intel_pmu_lbr_reset(void)
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
-		intel_pmu_lbr_reset_32();
-	else
-		intel_pmu_lbr_reset_64();
+	x86_pmu.lbr_reset();
 
 	cpuc->last_task_ctx = NULL;
 	cpuc->last_log_id = 0;
@@ -308,69 +359,97 @@ static u64 lbr_from_signext_quirk_rd(u64 val)
 	return val;
 }
 
-static inline void wrlbr_from(unsigned int idx, u64 val)
+static __always_inline void wrlbr_from(unsigned int idx, u64 val)
 {
 	val = lbr_from_signext_quirk_wr(val);
 	wrmsrl(x86_pmu.lbr_from + idx, val);
 }
 
-static inline void wrlbr_to(unsigned int idx, u64 val)
+static __always_inline void wrlbr_to(unsigned int idx, u64 val)
 {
 	wrmsrl(x86_pmu.lbr_to + idx, val);
 }
 
-static inline u64 rdlbr_from(unsigned int idx)
+static __always_inline void wrlbr_info(unsigned int idx, u64 val)
+{
+	wrmsrl(x86_pmu.lbr_info + idx, val);
+}
+
+static __always_inline u64 rdlbr_from(unsigned int idx, struct lbr_entry *lbr)
 {
 	u64 val;
 
+	if (lbr)
+		return lbr->from;
+
 	rdmsrl(x86_pmu.lbr_from + idx, val);
 
 	return lbr_from_signext_quirk_rd(val);
 }
 
-static inline u64 rdlbr_to(unsigned int idx)
+static __always_inline u64 rdlbr_to(unsigned int idx, struct lbr_entry *lbr)
 {
 	u64 val;
 
+	if (lbr)
+		return lbr->to;
+
 	rdmsrl(x86_pmu.lbr_to + idx, val);
 
 	return val;
 }
 
-static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
+static __always_inline u64 rdlbr_info(unsigned int idx, struct lbr_entry *lbr)
+{
+	u64 val;
+
+	if (lbr)
+		return lbr->info;
+
+	rdmsrl(x86_pmu.lbr_info + idx, val);
+
+	return val;
+}
+
+static inline void
+wrlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info)
+{
+	wrlbr_from(idx, lbr->from);
+	wrlbr_to(idx, lbr->to);
+	if (need_info)
+		wrlbr_info(idx, lbr->info);
+}
+
+static inline bool
+rdlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info)
+{
+	u64 from = rdlbr_from(idx, NULL);
+
+	/* Don't read invalid entry */
+	if (!from)
+		return false;
+
+	lbr->from = from;
+	lbr->to = rdlbr_to(idx, NULL);
+	if (need_info)
+		lbr->info = rdlbr_info(idx, NULL);
+
+	return true;
+}
+
+void intel_pmu_lbr_restore(void *ctx)
 {
+	bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO;
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_task_context *task_ctx = ctx;
 	int i;
 	unsigned lbr_idx, mask;
-	u64 tos;
-
-	if (task_ctx->lbr_callstack_users == 0 ||
-	    task_ctx->lbr_stack_state == LBR_NONE) {
-		intel_pmu_lbr_reset();
-		return;
-	}
-
-	tos = task_ctx->tos;
-	/*
-	 * Does not restore the LBR registers, if
-	 * - No one else touched them, and
-	 * - Did not enter C6
-	 */
-	if ((task_ctx == cpuc->last_task_ctx) &&
-	    (task_ctx->log_id == cpuc->last_log_id) &&
-	    rdlbr_from(tos)) {
-		task_ctx->lbr_stack_state = LBR_NONE;
-		return;
-	}
+	u64 tos = task_ctx->tos;
 
 	mask = x86_pmu.lbr_nr - 1;
 	for (i = 0; i < task_ctx->valid_lbrs; i++) {
 		lbr_idx = (tos - i) & mask;
-		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
-		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
-
-		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
+		wrlbr_all(&task_ctx->lbr[i], lbr_idx, need_info);
 	}
 
 	for (; i < x86_pmu.lbr_nr; i++) {
@@ -378,49 +457,149 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		wrlbr_from(lbr_idx, 0);
 		wrlbr_to(lbr_idx, 0);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+			wrlbr_info(lbr_idx, 0);
 	}
 
 	wrmsrl(x86_pmu.lbr_tos, tos);
-	task_ctx->lbr_stack_state = LBR_NONE;
+
+	if (cpuc->lbr_select)
+		wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
 }
 
-static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
+static void intel_pmu_arch_lbr_restore(void *ctx)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	unsigned lbr_idx, mask;
-	u64 tos, from;
+	struct x86_perf_task_context_arch_lbr *task_ctx = ctx;
+	struct lbr_entry *entries = task_ctx->entries;
 	int i;
 
-	if (task_ctx->lbr_callstack_users == 0) {
-		task_ctx->lbr_stack_state = LBR_NONE;
+	/* Fast reset the LBRs before restore if the call stack is not full. */
+	if (!entries[x86_pmu.lbr_nr - 1].from)
+		intel_pmu_arch_lbr_reset();
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!entries[i].from)
+			break;
+		wrlbr_all(&entries[i], i, true);
+	}
+}
+
+/*
+ * Restore the Architecture LBR state from the xsave area in the perf
+ * context data for the task via the XRSTORS instruction.
+ */
+static void intel_pmu_arch_lbr_xrstors(void *ctx)
+{
+	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;
+
+	copy_kernel_to_dynamic_supervisor(&task_ctx->xsave, XFEATURE_MASK_LBR);
+}
+
+static __always_inline bool lbr_is_reset_in_cstate(void *ctx)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return x86_pmu.lbr_deep_c_reset && !rdlbr_from(0, NULL);
+
+	return !rdlbr_from(((struct x86_perf_task_context *)ctx)->tos, NULL);
+}
+
+static void __intel_pmu_lbr_restore(void *ctx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (task_context_opt(ctx)->lbr_callstack_users == 0 ||
+	    task_context_opt(ctx)->lbr_stack_state == LBR_NONE) {
+		intel_pmu_lbr_reset();
+		return;
+	}
+
+	/*
+	 * Does not restore the LBR registers, if
+	 * - No one else touched them, and
+	 * - Was not cleared in Cstate
+	 */
+	if ((ctx == cpuc->last_task_ctx) &&
+	    (task_context_opt(ctx)->log_id == cpuc->last_log_id) &&
+	    !lbr_is_reset_in_cstate(ctx)) {
+		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
 		return;
 	}
 
+	x86_pmu.lbr_restore(ctx);
+
+	task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
+}
+
+void intel_pmu_lbr_save(void *ctx)
+{
+	bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_task_context *task_ctx = ctx;
+	unsigned lbr_idx, mask;
+	u64 tos;
+	int i;
+
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		lbr_idx = (tos - i) & mask;
-		from = rdlbr_from(lbr_idx);
-		if (!from)
+		if (!rdlbr_all(&task_ctx->lbr[i], lbr_idx, need_info))
 			break;
-		task_ctx->lbr_from[i] = from;
-		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
-		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
 	task_ctx->valid_lbrs = i;
 	task_ctx->tos = tos;
-	task_ctx->lbr_stack_state = LBR_VALID;
 
-	cpuc->last_task_ctx = task_ctx;
-	cpuc->last_log_id = ++task_ctx->log_id;
+	if (cpuc->lbr_select)
+		rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
+}
+
+static void intel_pmu_arch_lbr_save(void *ctx)
+{
+	struct x86_perf_task_context_arch_lbr *task_ctx = ctx;
+	struct lbr_entry *entries = task_ctx->entries;
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!rdlbr_all(&entries[i], i, true))
+			break;
+	}
+
+	/* LBR call stack is not full. Reset is required in restore. */
+	if (i < x86_pmu.lbr_nr)
+		entries[x86_pmu.lbr_nr - 1].from = 0;
+}
+
+/*
+ * Save the Architecture LBR state to the xsave area in the perf
+ * context data for the task via the XSAVES instruction.
+ */
+static void intel_pmu_arch_lbr_xsaves(void *ctx)
+{
+	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;
+
+	copy_dynamic_supervisor_to_kernel(&task_ctx->xsave, XFEATURE_MASK_LBR);
+}
+
+static void __intel_pmu_lbr_save(void *ctx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (task_context_opt(ctx)->lbr_callstack_users == 0) {
+		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
+		return;
+	}
+
+	x86_pmu.lbr_save(ctx);
+
+	task_context_opt(ctx)->lbr_stack_state = LBR_VALID;
+
+	cpuc->last_task_ctx = ctx;
+	cpuc->last_log_id = ++task_context_opt(ctx)->log_id;
 }
 
 void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
 				 struct perf_event_context *next)
 {
-	struct x86_perf_task_context *prev_ctx_data, *next_ctx_data;
+	void *prev_ctx_data, *next_ctx_data;
 
 	swap(prev->task_ctx_data, next->task_ctx_data);
 
@@ -436,14 +615,14 @@ void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
 	if (!prev_ctx_data || !next_ctx_data)
 		return;
 
-	swap(prev_ctx_data->lbr_callstack_users,
-	     next_ctx_data->lbr_callstack_users);
+	swap(task_context_opt(prev_ctx_data)->lbr_callstack_users,
+	     task_context_opt(next_ctx_data)->lbr_callstack_users);
 }
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct x86_perf_task_context *task_ctx;
+	void *task_ctx;
 
 	if (!cpuc->lbr_users)
 		return;
@@ -479,18 +658,19 @@ static inline bool branch_user_callstack(unsigned br_sel)
 
 void intel_pmu_lbr_add(struct perf_event *event)
 {
+	struct kmem_cache *kmem_cache = event->pmu->task_ctx_cache;
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct x86_perf_task_context *task_ctx;
 
 	if (!x86_pmu.lbr_nr)
 		return;
 
+	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
+		cpuc->lbr_select = 1;
+
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
-	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) {
-		task_ctx = event->ctx->task_ctx_data;
-		task_ctx->lbr_callstack_users++;
-	}
+	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data)
+		task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users++;
 
 	/*
 	 * Request pmu::sched_task() callback, which will fire inside the
@@ -516,21 +696,44 @@ void intel_pmu_lbr_add(struct perf_event *event)
 	perf_sched_cb_inc(event->ctx->pmu);
 	if (!cpuc->lbr_users++ && !event->total_time_running)
 		intel_pmu_lbr_reset();
+
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
+	    kmem_cache && !cpuc->lbr_xsave &&
+	    (cpuc->lbr_users != cpuc->lbr_pebs_users))
+		cpuc->lbr_xsave = kmem_cache_alloc(kmem_cache, GFP_KERNEL);
+}
+
+void release_lbr_buffers(void)
+{
+	struct kmem_cache *kmem_cache = x86_get_pmu()->task_ctx_cache;
+	struct cpu_hw_events *cpuc;
+	int cpu;
+
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return;
+
+	for_each_possible_cpu(cpu) {
+		cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
+		if (kmem_cache && cpuc->lbr_xsave) {
+			kmem_cache_free(kmem_cache, cpuc->lbr_xsave);
+			cpuc->lbr_xsave = NULL;
+		}
+	}
 }
 
 void intel_pmu_lbr_del(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct x86_perf_task_context *task_ctx;
 
 	if (!x86_pmu.lbr_nr)
 		return;
 
 	if (branch_user_callstack(cpuc->br_sel) &&
-	    event->ctx->task_ctx_data) {
-		task_ctx = event->ctx->task_ctx_data;
-		task_ctx->lbr_callstack_users--;
-	}
+	    event->ctx->task_ctx_data)
+		task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users--;
+
+	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
+		cpuc->lbr_select = 0;
 
 	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
 		cpuc->lbr_pebs_users--;
@@ -540,11 +743,19 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	perf_sched_cb_dec(event->ctx->pmu);
 }
 
+static inline bool vlbr_exclude_host(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	return test_bit(INTEL_PMC_IDX_FIXED_VLBR,
+		(unsigned long *)&cpuc->intel_ctrl_guest_mask);
+}
+
 void intel_pmu_lbr_enable_all(bool pmi)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users)
+	if (cpuc->lbr_users && !vlbr_exclude_host())
 		__intel_pmu_lbr_enable(pmi);
 }
 
@@ -552,11 +763,11 @@ void intel_pmu_lbr_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users)
+	if (cpuc->lbr_users && !vlbr_exclude_host())
 		__intel_pmu_lbr_disable();
 }
 
-static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
+void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 {
 	unsigned long mask = x86_pmu.lbr_nr - 1;
 	u64 tos = intel_pmu_lbr_tos();
@@ -593,7 +804,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
  * is the same as the linear address, allowing us to merge the LIP and EIP
  * LBR formats.
  */
-static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
+void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
 	bool need_info = false, call_stack = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
@@ -616,8 +827,8 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		u16 cycles = 0;
 		int lbr_flags = lbr_desc[lbr_format];
 
-		from = rdlbr_from(lbr_idx);
-		to   = rdlbr_to(lbr_idx);
+		from = rdlbr_from(lbr_idx, NULL);
+		to   = rdlbr_to(lbr_idx, NULL);
 
 		/*
 		 * Read LBR call stack entries
@@ -629,7 +840,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
 
-			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info);
+			info = rdlbr_info(lbr_idx, NULL);
 			mis = !!(info & LBR_INFO_MISPRED);
 			pred = !mis;
 			in_tx = !!(info & LBR_INFO_IN_TX);
@@ -684,6 +895,93 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	cpuc->lbr_stack.hw_idx = tos;
 }
 
+static __always_inline int get_lbr_br_type(u64 info)
+{
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) || !x86_pmu.lbr_br_type)
+		return 0;
+
+	return (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET;
+}
+
+static __always_inline bool get_lbr_mispred(u64 info)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred)
+		return 0;
+
+	return !!(info & LBR_INFO_MISPRED);
+}
+
+static __always_inline bool get_lbr_predicted(u64 info)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred)
+		return 0;
+
+	return !(info & LBR_INFO_MISPRED);
+}
+
+static __always_inline bool get_lbr_cycles(u64 info)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
+	    !(x86_pmu.lbr_timed_lbr && info & LBR_INFO_CYC_CNT_VALID))
+		return 0;
+
+	return info & LBR_INFO_CYCLES;
+}
+
+static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
+				struct lbr_entry *entries)
+{
+	struct perf_branch_entry *e;
+	struct lbr_entry *lbr;
+	u64 from, to, info;
+	int i;
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		lbr = entries ? &entries[i] : NULL;
+		e = &cpuc->lbr_entries[i];
+
+		from = rdlbr_from(i, lbr);
+		/*
+		 * Read LBR entries until invalid entry (0s) is detected.
+		 */
+		if (!from)
+			break;
+
+		to = rdlbr_to(i, lbr);
+		info = rdlbr_info(i, lbr);
+
+		e->from		= from;
+		e->to		= to;
+		e->mispred	= get_lbr_mispred(info);
+		e->predicted	= get_lbr_predicted(info);
+		e->in_tx	= !!(info & LBR_INFO_IN_TX);
+		e->abort	= !!(info & LBR_INFO_ABORT);
+		e->cycles	= get_lbr_cycles(info);
+		e->type		= get_lbr_br_type(info);
+		e->reserved	= 0;
+	}
+
+	cpuc->lbr_stack.nr = i;
+}
+
+static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc)
+{
+	intel_pmu_store_lbr(cpuc, NULL);
+}
+
+static void intel_pmu_arch_lbr_read_xsave(struct cpu_hw_events *cpuc)
+{
+	struct x86_perf_task_context_arch_lbr_xsave *xsave = cpuc->lbr_xsave;
+
+	if (!xsave) {
+		intel_pmu_store_lbr(cpuc, NULL);
+		return;
+	}
+	copy_dynamic_supervisor_to_kernel(&xsave->xsave, XFEATURE_MASK_LBR);
+
+	intel_pmu_store_lbr(cpuc, xsave->lbr.entries);
+}
+
 void intel_pmu_lbr_read(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -694,13 +992,11 @@ void intel_pmu_lbr_read(void)
 	 * This could be smarter and actually check the event,
 	 * but this simple approach seems to work for now.
 	 */
-	if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
+	if (!cpuc->lbr_users || vlbr_exclude_host() ||
+	    cpuc->lbr_users == cpuc->lbr_pebs_users)
 		return;
 
-	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
-		intel_pmu_lbr_read_32(cpuc);
-	else
-		intel_pmu_lbr_read_64(cpuc);
+	x86_pmu.lbr_read(cpuc);
 
 	intel_pmu_lbr_filter(cpuc);
 }
@@ -800,6 +1096,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 	reg = &event->hw.branch_reg;
 	reg->idx = EXTRA_REG_LBR;
 
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
+		reg->config = mask;
+		return 0;
+	}
+
 	/*
 	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate
 	 * in suppress mode. So LBR_SELECT should be set to
@@ -1056,6 +1357,27 @@ common_branch_type(int type)
 	return PERF_BR_UNKNOWN;
 }
 
+enum {
+	ARCH_LBR_BR_TYPE_JCC			= 0,
+	ARCH_LBR_BR_TYPE_NEAR_IND_JMP		= 1,
+	ARCH_LBR_BR_TYPE_NEAR_REL_JMP		= 2,
+	ARCH_LBR_BR_TYPE_NEAR_IND_CALL		= 3,
+	ARCH_LBR_BR_TYPE_NEAR_REL_CALL		= 4,
+	ARCH_LBR_BR_TYPE_NEAR_RET		= 5,
+	ARCH_LBR_BR_TYPE_KNOWN_MAX		= ARCH_LBR_BR_TYPE_NEAR_RET,
+
+	ARCH_LBR_BR_TYPE_MAP_MAX		= 16,
+};
+
+static const int arch_lbr_br_type_map[ARCH_LBR_BR_TYPE_MAP_MAX] = {
+	[ARCH_LBR_BR_TYPE_JCC]			= X86_BR_JCC,
+	[ARCH_LBR_BR_TYPE_NEAR_IND_JMP]		= X86_BR_IND_JMP,
+	[ARCH_LBR_BR_TYPE_NEAR_REL_JMP]		= X86_BR_JMP,
+	[ARCH_LBR_BR_TYPE_NEAR_IND_CALL]	= X86_BR_IND_CALL,
+	[ARCH_LBR_BR_TYPE_NEAR_REL_CALL]	= X86_BR_CALL,
+	[ARCH_LBR_BR_TYPE_NEAR_RET]		= X86_BR_RET,
+};
+
 /*
  * implement actual branch filter based on user demand.
  * Hardware may not exactly satisfy that request, thus
@@ -1068,7 +1390,7 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 {
 	u64 from, to;
 	int br_sel = cpuc->br_sel;
-	int i, j, type;
+	int i, j, type, to_plm;
 	bool compress = false;
 
 	/* if sampling all branches, then nothing to filter */
@@ -1080,8 +1402,19 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 
 		from = cpuc->lbr_entries[i].from;
 		to = cpuc->lbr_entries[i].to;
+		type = cpuc->lbr_entries[i].type;
 
-		type = branch_type(from, to, cpuc->lbr_entries[i].abort);
+		/*
+		 * Parse the branch type recorded in LBR_x_INFO MSR.
+		 * Doesn't support OTHER_BRANCH decoding for now.
+		 * OTHER_BRANCH branch type still rely on software decoding.
+		 */
+		if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
+		    type <= ARCH_LBR_BR_TYPE_KNOWN_MAX) {
+			to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
+			type = arch_lbr_br_type_map[type] | to_plm;
+		} else
+			type = branch_type(from, to, cpuc->lbr_entries[i].abort);
 		if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) {
 			if (cpuc->lbr_entries[i].in_tx)
 				type |= X86_BR_IN_TX;
@@ -1116,32 +1449,18 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	}
 }
 
-void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	int i;
-
-	cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
 
-	/* Cannot get TOS for large PEBS */
-	if (cpuc->n_pebs == cpuc->n_large_pebs)
+	/* Cannot get TOS for large PEBS and Arch LBR */
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR) ||
+	    (cpuc->n_pebs == cpuc->n_large_pebs))
 		cpuc->lbr_stack.hw_idx = -1ULL;
 	else
 		cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos();
 
-	for (i = 0; i < x86_pmu.lbr_nr; i++) {
-		u64 info = lbr->lbr[i].info;
-		struct perf_branch_entry *e = &cpuc->lbr_entries[i];
-
-		e->from		= lbr->lbr[i].from;
-		e->to		= lbr->lbr[i].to;
-		e->mispred	= !!(info & LBR_INFO_MISPRED);
-		e->predicted	= !(info & LBR_INFO_MISPRED);
-		e->in_tx	= !!(info & LBR_INFO_IN_TX);
-		e->abort	= !!(info & LBR_INFO_ABORT);
-		e->cycles	= info & LBR_INFO_CYCLES;
-		e->reserved	= 0;
-	}
+	intel_pmu_store_lbr(cpuc, lbr);
 	intel_pmu_lbr_filter(cpuc);
 }
 
@@ -1198,6 +1517,26 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= LBR_REL_CALL,
 };
 
+static int arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= ARCH_LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= ARCH_LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= ARCH_LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= ARCH_LBR_RETURN |
+						  ARCH_LBR_OTHER_BRANCH,
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]     = ARCH_LBR_REL_CALL |
+						  ARCH_LBR_IND_CALL |
+						  ARCH_LBR_OTHER_BRANCH,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]     = ARCH_LBR_IND_CALL,
+	[PERF_SAMPLE_BRANCH_COND_SHIFT]         = ARCH_LBR_JCC,
+	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]   = ARCH_LBR_REL_CALL |
+						  ARCH_LBR_IND_CALL |
+						  ARCH_LBR_RETURN |
+						  ARCH_LBR_CALL_STACK,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= ARCH_LBR_IND_JMP,
+	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= ARCH_LBR_REL_CALL,
+};
+
 /* core */
 void __init intel_pmu_lbr_init_core(void)
 {
@@ -1251,9 +1590,17 @@ void __init intel_pmu_lbr_init_snb(void)
 	 */
 }
 
+static inline struct kmem_cache *
+create_lbr_kmem_cache(size_t size, size_t align)
+{
+	return kmem_cache_create("x86_lbr", size, align, 0, NULL);
+}
+
 /* haswell */
 void intel_pmu_lbr_init_hsw(void)
 {
+	size_t size = sizeof(struct x86_perf_task_context);
+
 	x86_pmu.lbr_nr	 = 16;
 	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
 	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
@@ -1262,6 +1609,8 @@ void intel_pmu_lbr_init_hsw(void)
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
 
+	x86_get_pmu()->task_ctx_cache = create_lbr_kmem_cache(size, 0);
+
 	if (lbr_from_signext_quirk_needed())
 		static_branch_enable(&lbr_from_quirk_key);
 }
@@ -1269,14 +1618,19 @@ void intel_pmu_lbr_init_hsw(void)
 /* skylake */
 __init void intel_pmu_lbr_init_skl(void)
 {
+	size_t size = sizeof(struct x86_perf_task_context);
+
 	x86_pmu.lbr_nr	 = 32;
 	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
 	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
 	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
+	x86_pmu.lbr_info = MSR_LBR_INFO_0;
 
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
 
+	x86_get_pmu()->task_ctx_cache = create_lbr_kmem_cache(size, 0);
+
 	/*
 	 * SW branch filter usage:
 	 * - support syscall, sysret capture.
@@ -1343,3 +1697,152 @@ void intel_pmu_lbr_init_knl(void)
 	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
 		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
 }
+
+/*
+ * LBR state size is variable based on the max number of registers.
+ * This calculates the expected state size, which should match
+ * what the hardware enumerates for the size of XFEATURE_LBR.
+ */
+static inline unsigned int get_lbr_state_size(void)
+{
+	return sizeof(struct arch_lbr_state) +
+	       x86_pmu.lbr_nr * sizeof(struct lbr_entry);
+}
+
+static bool is_arch_lbr_xsave_available(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_XSAVES))
+		return false;
+
+	/*
+	 * Check the LBR state with the corresponding software structure.
+	 * Disable LBR XSAVES support if the size doesn't match.
+	 */
+	if (WARN_ON(xfeature_size(XFEATURE_LBR) != get_lbr_state_size()))
+		return false;
+
+	return true;
+}
+
+void __init intel_pmu_arch_lbr_init(void)
+{
+	struct pmu *pmu = x86_get_pmu();
+	union cpuid28_eax eax;
+	union cpuid28_ebx ebx;
+	union cpuid28_ecx ecx;
+	unsigned int unused_edx;
+	bool arch_lbr_xsave;
+	size_t size;
+	u64 lbr_nr;
+
+	/* Arch LBR Capabilities */
+	cpuid(28, &eax.full, &ebx.full, &ecx.full, &unused_edx);
+
+	lbr_nr = fls(eax.split.lbr_depth_mask) * 8;
+	if (!lbr_nr)
+		goto clear_arch_lbr;
+
+	/* Apply the max depth of Arch LBR */
+	if (wrmsrl_safe(MSR_ARCH_LBR_DEPTH, lbr_nr))
+		goto clear_arch_lbr;
+
+	x86_pmu.lbr_depth_mask = eax.split.lbr_depth_mask;
+	x86_pmu.lbr_deep_c_reset = eax.split.lbr_deep_c_reset;
+	x86_pmu.lbr_lip = eax.split.lbr_lip;
+	x86_pmu.lbr_cpl = ebx.split.lbr_cpl;
+	x86_pmu.lbr_filter = ebx.split.lbr_filter;
+	x86_pmu.lbr_call_stack = ebx.split.lbr_call_stack;
+	x86_pmu.lbr_mispred = ecx.split.lbr_mispred;
+	x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr;
+	x86_pmu.lbr_br_type = ecx.split.lbr_br_type;
+	x86_pmu.lbr_nr = lbr_nr;
+
+
+	arch_lbr_xsave = is_arch_lbr_xsave_available();
+	if (arch_lbr_xsave) {
+		size = sizeof(struct x86_perf_task_context_arch_lbr_xsave) +
+		       get_lbr_state_size();
+		pmu->task_ctx_cache = create_lbr_kmem_cache(size,
+							    XSAVE_ALIGNMENT);
+	}
+
+	if (!pmu->task_ctx_cache) {
+		arch_lbr_xsave = false;
+
+		size = sizeof(struct x86_perf_task_context_arch_lbr) +
+		       lbr_nr * sizeof(struct lbr_entry);
+		pmu->task_ctx_cache = create_lbr_kmem_cache(size, 0);
+	}
+
+	x86_pmu.lbr_from = MSR_ARCH_LBR_FROM_0;
+	x86_pmu.lbr_to = MSR_ARCH_LBR_TO_0;
+	x86_pmu.lbr_info = MSR_ARCH_LBR_INFO_0;
+
+	/* LBR callstack requires both CPL and Branch Filtering support */
+	if (!x86_pmu.lbr_cpl ||
+	    !x86_pmu.lbr_filter ||
+	    !x86_pmu.lbr_call_stack)
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_NOT_SUPP;
+
+	if (!x86_pmu.lbr_cpl) {
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_NOT_SUPP;
+	} else if (!x86_pmu.lbr_filter) {
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_NOT_SUPP;
+		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_NOT_SUPP;
+	}
+
+	x86_pmu.lbr_ctl_mask = ARCH_LBR_CTL_MASK;
+	x86_pmu.lbr_ctl_map  = arch_lbr_ctl_map;
+
+	if (!x86_pmu.lbr_cpl && !x86_pmu.lbr_filter)
+		x86_pmu.lbr_ctl_map = NULL;
+
+	x86_pmu.lbr_reset = intel_pmu_arch_lbr_reset;
+	if (arch_lbr_xsave) {
+		x86_pmu.lbr_save = intel_pmu_arch_lbr_xsaves;
+		x86_pmu.lbr_restore = intel_pmu_arch_lbr_xrstors;
+		x86_pmu.lbr_read = intel_pmu_arch_lbr_read_xsave;
+		pr_cont("XSAVE ");
+	} else {
+		x86_pmu.lbr_save = intel_pmu_arch_lbr_save;
+		x86_pmu.lbr_restore = intel_pmu_arch_lbr_restore;
+		x86_pmu.lbr_read = intel_pmu_arch_lbr_read;
+	}
+
+	pr_cont("Architectural LBR, ");
+
+	return;
+
+clear_arch_lbr:
+	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR);
+}
+
+/**
+ * x86_perf_get_lbr - get the LBR records information
+ *
+ * @lbr: the caller's memory to store the LBR records information
+ *
+ * Returns: 0 indicates the LBR info has been successfully obtained
+ */
+int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+{
+	int lbr_fmt = x86_pmu.intel_cap.lbr_format;
+
+	lbr->nr = x86_pmu.lbr_nr;
+	lbr->from = x86_pmu.lbr_from;
+	lbr->to = x86_pmu.lbr_to;
+	lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
+
+struct event_constraint vlbr_constraint =
+	__EVENT_CONSTRAINT(INTEL_FIXED_VLBR_EVENT, (1ULL << INTEL_PMC_IDX_FIXED_VLBR),
+			  FIXED_EVENT_FLAGS, 1, 0, PERF_X86_EVENT_LBR_SELECT);
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index cf76d6631afa..d5c6d3b340c5 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -16,7 +16,7 @@ struct pci_driver *uncore_pci_driver;
 DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
 struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
 struct pci_extra_dev *uncore_extra_pci_dev;
-static int max_dies;
+int __uncore_max_dies;
 
 /* mask of cpus that collect uncore events */
 static cpumask_t uncore_cpu_mask;
@@ -108,7 +108,7 @@ struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu
 	 * The unsigned check also catches the '-1' return value for non
 	 * existent mappings in the topology map.
 	 */
-	return dieid < max_dies ? pmu->boxes[dieid] : NULL;
+	return dieid < uncore_max_dies() ? pmu->boxes[dieid] : NULL;
 }
 
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -132,6 +132,9 @@ u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
 	if (!box->io_addr)
 		return 0;
 
+	if (!uncore_mmio_is_valid_offset(box, event->hw.event_base))
+		return 0;
+
 	return readq(box->io_addr + event->hw.event_base);
 }
 
@@ -843,10 +846,12 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 			.read		= uncore_pmu_event_read,
 			.module		= THIS_MODULE,
 			.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+			.attr_update	= pmu->type->attr_update,
 		};
 	} else {
 		pmu->pmu = *pmu->type->pmu;
 		pmu->pmu.attr_groups = pmu->type->attr_groups;
+		pmu->pmu.attr_update = pmu->type->attr_update;
 	}
 
 	if (pmu->type->num_boxes == 1) {
@@ -877,7 +882,7 @@ static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
 {
 	int die;
 
-	for (die = 0; die < max_dies; die++)
+	for (die = 0; die < uncore_max_dies(); die++)
 		kfree(pmu->boxes[die]);
 	kfree(pmu->boxes);
 }
@@ -887,6 +892,9 @@ static void uncore_type_exit(struct intel_uncore_type *type)
 	struct intel_uncore_pmu *pmu = type->pmus;
 	int i;
 
+	if (type->cleanup_mapping)
+		type->cleanup_mapping(type);
+
 	if (pmu) {
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
 			uncore_pmu_unregister(pmu);
@@ -915,7 +923,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	if (!pmus)
 		return -ENOMEM;
 
-	size = max_dies * sizeof(struct intel_uncore_box *);
+	size = uncore_max_dies() * sizeof(struct intel_uncore_box *);
 
 	for (i = 0; i < type->num_boxes; i++) {
 		pmus[i].func_id	= setid ? i : -1;
@@ -954,6 +962,9 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 
 	type->pmu_group = &uncore_pmu_attr_group;
 
+	if (type->set_mapping)
+		type->set_mapping(type);
+
 	return 0;
 
 err:
@@ -1112,7 +1123,7 @@ static int __init uncore_pci_init(void)
 	size_t size;
 	int ret;
 
-	size = max_dies * sizeof(struct pci_extra_dev);
+	size = uncore_max_dies() * sizeof(struct pci_extra_dev);
 	uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
 	if (!uncore_extra_pci_dev) {
 		ret = -ENOMEM;
@@ -1514,6 +1525,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&skx_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&skl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&skl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&skl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&skl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI,	&icl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_uncore_init),
@@ -1539,7 +1552,8 @@ static int __init intel_uncore_init(void)
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return -ENODEV;
 
-	max_dies = topology_max_packages() * topology_max_die_per_package();
+	__uncore_max_dies =
+		topology_max_packages() * topology_max_die_per_package();
 
 	uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
 	if (uncore_init->pci_init) {
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index b469ddd45515..105fdc69825e 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -61,6 +61,7 @@ struct intel_uncore_type {
 		unsigned msr_offset;
 		unsigned mmio_offset;
 	};
+	unsigned mmio_map_size;
 	unsigned num_shared_regs:8;
 	unsigned single_fixed:1;
 	unsigned pair_ctr_ctl:1;
@@ -72,7 +73,19 @@ struct intel_uncore_type {
 	struct uncore_event_desc *event_descs;
 	struct freerunning_counters *freerunning;
 	const struct attribute_group *attr_groups[4];
+	const struct attribute_group **attr_update;
 	struct pmu *pmu; /* for custom pmu ops */
+	/*
+	 * Uncore PMU would store relevant platform topology configuration here
+	 * to identify which platform component each PMON block of that type is
+	 * supposed to monitor.
+	 */
+	u64 *topology;
+	/*
+	 * Optional callbacks for managing mapping of Uncore units to PMONs
+	 */
+	int (*set_mapping)(struct intel_uncore_type *type);
+	void (*cleanup_mapping)(struct intel_uncore_type *type);
 };
 
 #define pmu_group attr_groups[0]
@@ -169,6 +182,18 @@ int uncore_pcibus_to_physid(struct pci_bus *bus);
 ssize_t uncore_event_show(struct kobject *kobj,
 			  struct kobj_attribute *attr, char *buf);
 
+static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev)
+{
+	return container_of(dev_get_drvdata(dev), struct intel_uncore_pmu, pmu);
+}
+
+#define to_device_attribute(n)	container_of(n, struct device_attribute, attr)
+#define to_dev_ext_attribute(n)	container_of(n, struct dev_ext_attribute, attr)
+#define attr_to_ext_attr(n)	to_dev_ext_attribute(to_device_attribute(n))
+
+extern int __uncore_max_dies;
+#define uncore_max_dies()	(__uncore_max_dies)
+
 #define INTEL_UNCORE_EVENT_DESC(_name, _config)			\
 {								\
 	.attr	= __ATTR(_name, 0444, uncore_event_show, NULL),	\
@@ -196,6 +221,18 @@ static inline bool uncore_pmc_freerunning(int idx)
 	return idx == UNCORE_PMC_IDX_FREERUNNING;
 }
 
+static inline bool uncore_mmio_is_valid_offset(struct intel_uncore_box *box,
+					       unsigned long offset)
+{
+	if (offset < box->pmu->type->mmio_map_size)
+		return true;
+
+	pr_warn_once("perf uncore: Invalid offset 0x%lx exceeds mapped area of %s.\n",
+		     offset, box->pmu->type->name);
+
+	return false;
+}
+
 static inline
 unsigned int uncore_mmio_box_ctl(struct intel_uncore_box *box)
 {
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 3de1065eefc4..cb94ba86efd2 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -42,6 +42,17 @@
 #define PCI_DEVICE_ID_INTEL_WHL_UQ_IMC		0x3ed0
 #define PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC	0x3e34
 #define PCI_DEVICE_ID_INTEL_WHL_UD_IMC		0x3e35
+#define PCI_DEVICE_ID_INTEL_CML_H1_IMC		0x9b44
+#define PCI_DEVICE_ID_INTEL_CML_H2_IMC		0x9b54
+#define PCI_DEVICE_ID_INTEL_CML_H3_IMC		0x9b64
+#define PCI_DEVICE_ID_INTEL_CML_U1_IMC		0x9b51
+#define PCI_DEVICE_ID_INTEL_CML_U2_IMC		0x9b61
+#define PCI_DEVICE_ID_INTEL_CML_U3_IMC		0x9b71
+#define PCI_DEVICE_ID_INTEL_CML_S1_IMC		0x9b33
+#define PCI_DEVICE_ID_INTEL_CML_S2_IMC		0x9b43
+#define PCI_DEVICE_ID_INTEL_CML_S3_IMC		0x9b53
+#define PCI_DEVICE_ID_INTEL_CML_S4_IMC		0x9b63
+#define PCI_DEVICE_ID_INTEL_CML_S5_IMC		0x9b73
 #define PCI_DEVICE_ID_INTEL_ICL_U_IMC		0x8a02
 #define PCI_DEVICE_ID_INTEL_ICL_U2_IMC		0x8a12
 #define PCI_DEVICE_ID_INTEL_TGL_U1_IMC		0x9a02
@@ -415,6 +426,7 @@ static const struct attribute_group snb_uncore_imc_format_group = {
 
 static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
 {
+	struct intel_uncore_type *type = box->pmu->type;
 	struct pci_dev *pdev = box->pci_dev;
 	int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
 	resource_size_t addr;
@@ -430,7 +442,10 @@ static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
 
 	addr &= ~(PAGE_SIZE - 1);
 
-	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+	box->io_addr = ioremap(addr, type->mmio_map_size);
+	if (!box->io_addr)
+		pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name);
+
 	box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
 }
 
@@ -586,6 +601,7 @@ static struct intel_uncore_type snb_uncore_imc = {
 	.num_counters   = 2,
 	.num_boxes	= 1,
 	.num_freerunning_types	= SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+	.mmio_map_size	= SNB_UNCORE_PCI_IMC_MAP_SIZE,
 	.freerunning	= snb_uncore_imc_freerunning,
 	.event_descs	= snb_uncore_imc_events,
 	.format_group	= &snb_uncore_imc_format_group,
@@ -771,6 +787,50 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UD_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H1_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_H3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U1_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_U3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S1_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S4_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CML_S5_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -863,6 +923,17 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(WHL_UQ_IMC, &skl_uncore_pci_driver),	/* 8th Gen Core U Mobile Quad Core */
 	IMC_DEV(WHL_4_UQ_IMC, &skl_uncore_pci_driver),	/* 8th Gen Core U Mobile Quad Core */
 	IMC_DEV(WHL_UD_IMC, &skl_uncore_pci_driver),	/* 8th Gen Core U Mobile Dual Core */
+	IMC_DEV(CML_H1_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_H2_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_H3_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_U1_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_U2_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_U3_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S1_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S2_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S3_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S4_IMC, &skl_uncore_pci_driver),
+	IMC_DEV(CML_S5_IMC, &skl_uncore_pci_driver),
 	IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver),	/* 10th Gen Core Mobile */
 	IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver),	/* 10th Gen Core Mobile */
 	{  /* end marker */ }
@@ -1085,11 +1156,13 @@ static struct pci_dev *tgl_uncore_get_mc_dev(void)
 }
 
 #define TGL_UNCORE_MMIO_IMC_MEM_OFFSET		0x10000
+#define TGL_UNCORE_PCI_IMC_MAP_SIZE		0xe000
 
 static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = tgl_uncore_get_mc_dev();
 	struct intel_uncore_pmu *pmu = box->pmu;
+	struct intel_uncore_type *type = pmu->type;
 	resource_size_t addr;
 	u32 mch_bar;
 
@@ -1112,7 +1185,9 @@ static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
 	addr |= ((resource_size_t)mch_bar << 32);
 #endif
 
-	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+	box->io_addr = ioremap(addr, type->mmio_map_size);
+	if (!box->io_addr)
+		pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name);
 }
 
 static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = {
@@ -1138,6 +1213,7 @@ static struct intel_uncore_type tgl_uncore_imc_free_running = {
 	.num_counters		= 3,
 	.num_boxes		= 2,
 	.num_freerunning_types	= TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+	.mmio_map_size		= TGL_UNCORE_PCI_IMC_MAP_SIZE,
 	.freerunning		= tgl_uncore_imc_freerunning,
 	.ops			= &tgl_uncore_imc_freerunning_ops,
 	.event_descs		= tgl_uncore_imc_events,
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 07652fa20ebb..62e88ad919ff 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -273,6 +273,30 @@
 #define SKX_CPUNODEID			0xc0
 #define SKX_GIDNIDMAP			0xd4
 
+/*
+ * The CPU_BUS_NUMBER MSR returns the values of the respective CPUBUSNO CSR
+ * that BIOS programmed. MSR has package scope.
+ * |  Bit  |  Default  |  Description
+ * | [63]  |    00h    | VALID - When set, indicates the CPU bus
+ *                       numbers have been initialized. (RO)
+ * |[62:48]|    ---    | Reserved
+ * |[47:40]|    00h    | BUS_NUM_5 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(5). (RO)
+ * |[39:32]|    00h    | BUS_NUM_4 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(4). (RO)
+ * |[31:24]|    00h    | BUS_NUM_3 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(3). (RO)
+ * |[23:16]|    00h    | BUS_NUM_2 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(2). (RO)
+ * |[15:8] |    00h    | BUS_NUM_1 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(1). (RO)
+ * | [7:0] |    00h    | BUS_NUM_0 — Return the bus number BIOS assigned
+ *                       CPUBUSNO(0). (RO)
+ */
+#define SKX_MSR_CPU_BUS_NUMBER		0x300
+#define SKX_MSR_CPU_BUS_VALID_BIT	(1ULL << 63)
+#define BUS_NUM_STRIDE			8
+
 /* SKX CHA */
 #define SKX_CHA_MSR_PMON_BOX_FILTER_TID		(0x1ffULL << 0)
 #define SKX_CHA_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 9)
@@ -3612,6 +3636,170 @@ static struct intel_uncore_ops skx_uncore_iio_ops = {
 	.read_counter		= uncore_msr_read_counter,
 };
 
+static inline u8 skx_iio_stack(struct intel_uncore_pmu *pmu, int die)
+{
+	return pmu->type->topology[die] >> (pmu->pmu_idx * BUS_NUM_STRIDE);
+}
+
+static umode_t
+skx_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die)
+{
+	struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(kobj_to_dev(kobj));
+
+	/* Root bus 0x00 is valid only for die 0 AND pmu_idx = 0. */
+	return (!skx_iio_stack(pmu, die) && pmu->pmu_idx) ? 0 : attr->mode;
+}
+
+static ssize_t skx_iio_mapping_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct pci_bus *bus = pci_find_next_bus(NULL);
+	struct intel_uncore_pmu *uncore_pmu = dev_to_uncore_pmu(dev);
+	struct dev_ext_attribute *ea = to_dev_ext_attribute(attr);
+	long die = (long)ea->var;
+
+	/*
+	 * Current implementation is for single segment configuration hence it's
+	 * safe to take the segment value from the first available root bus.
+	 */
+	return sprintf(buf, "%04x:%02x\n", pci_domain_nr(bus),
+					   skx_iio_stack(uncore_pmu, die));
+}
+
+static int skx_msr_cpu_bus_read(int cpu, u64 *topology)
+{
+	u64 msr_value;
+
+	if (rdmsrl_on_cpu(cpu, SKX_MSR_CPU_BUS_NUMBER, &msr_value) ||
+			!(msr_value & SKX_MSR_CPU_BUS_VALID_BIT))
+		return -ENXIO;
+
+	*topology = msr_value;
+
+	return 0;
+}
+
+static int die_to_cpu(int die)
+{
+	int res = 0, cpu, current_die;
+	/*
+	 * Using cpus_read_lock() to ensure cpu is not going down between
+	 * looking at cpu_online_mask.
+	 */
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		current_die = topology_logical_die_id(cpu);
+		if (current_die == die) {
+			res = cpu;
+			break;
+		}
+	}
+	cpus_read_unlock();
+	return res;
+}
+
+static int skx_iio_get_topology(struct intel_uncore_type *type)
+{
+	int i, ret;
+	struct pci_bus *bus = NULL;
+
+	/*
+	 * Verified single-segment environments only; disabled for multiple
+	 * segment topologies for now except VMD domains.
+	 * VMD domains start at 0x10000 to not clash with ACPI _SEG domains.
+	 */
+	while ((bus = pci_find_next_bus(bus))
+		&& (!pci_domain_nr(bus) || pci_domain_nr(bus) > 0xffff))
+		;
+	if (bus)
+		return -EPERM;
+
+	type->topology = kcalloc(uncore_max_dies(), sizeof(u64), GFP_KERNEL);
+	if (!type->topology)
+		return -ENOMEM;
+
+	for (i = 0; i < uncore_max_dies(); i++) {
+		ret = skx_msr_cpu_bus_read(die_to_cpu(i), &type->topology[i]);
+		if (ret) {
+			kfree(type->topology);
+			type->topology = NULL;
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static struct attribute_group skx_iio_mapping_group = {
+	.is_visible	= skx_iio_mapping_visible,
+};
+
+static const struct attribute_group *skx_iio_attr_update[] = {
+	&skx_iio_mapping_group,
+	NULL,
+};
+
+static int skx_iio_set_mapping(struct intel_uncore_type *type)
+{
+	char buf[64];
+	int ret;
+	long die = -1;
+	struct attribute **attrs = NULL;
+	struct dev_ext_attribute *eas = NULL;
+
+	ret = skx_iio_get_topology(type);
+	if (ret)
+		return ret;
+
+	/* One more for NULL. */
+	attrs = kcalloc((uncore_max_dies() + 1), sizeof(*attrs), GFP_KERNEL);
+	if (!attrs)
+		goto err;
+
+	eas = kcalloc(uncore_max_dies(), sizeof(*eas), GFP_KERNEL);
+	if (!eas)
+		goto err;
+
+	for (die = 0; die < uncore_max_dies(); die++) {
+		sprintf(buf, "die%ld", die);
+		sysfs_attr_init(&eas[die].attr.attr);
+		eas[die].attr.attr.name = kstrdup(buf, GFP_KERNEL);
+		if (!eas[die].attr.attr.name)
+			goto err;
+		eas[die].attr.attr.mode = 0444;
+		eas[die].attr.show = skx_iio_mapping_show;
+		eas[die].attr.store = NULL;
+		eas[die].var = (void *)die;
+		attrs[die] = &eas[die].attr.attr;
+	}
+	skx_iio_mapping_group.attrs = attrs;
+
+	return 0;
+err:
+	for (; die >= 0; die--)
+		kfree(eas[die].attr.attr.name);
+	kfree(eas);
+	kfree(attrs);
+	kfree(type->topology);
+	type->attr_update = NULL;
+	return -ENOMEM;
+}
+
+static void skx_iio_cleanup_mapping(struct intel_uncore_type *type)
+{
+	struct attribute **attr = skx_iio_mapping_group.attrs;
+
+	if (!attr)
+		return;
+
+	for (; *attr; attr++)
+		kfree((*attr)->name);
+	kfree(attr_to_ext_attr(*skx_iio_mapping_group.attrs));
+	kfree(skx_iio_mapping_group.attrs);
+	skx_iio_mapping_group.attrs = NULL;
+	kfree(type->topology);
+}
+
 static struct intel_uncore_type skx_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
@@ -3626,6 +3814,9 @@ static struct intel_uncore_type skx_uncore_iio = {
 	.constraints		= skx_uncore_iio_constraints,
 	.ops			= &skx_uncore_iio_ops,
 	.format_group		= &skx_uncore_iio_format_group,
+	.attr_update		= skx_iio_attr_update,
+	.set_mapping		= skx_iio_set_mapping,
+	.cleanup_mapping	= skx_iio_cleanup_mapping,
 };
 
 enum perf_uncore_iio_freerunning_type_id {
@@ -4421,6 +4612,7 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
 				       unsigned int box_ctl, int mem_offset)
 {
 	struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid);
+	struct intel_uncore_type *type = box->pmu->type;
 	resource_size_t addr;
 	u32 pci_dword;
 
@@ -4435,9 +4627,11 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
 
 	addr += box_ctl;
 
-	box->io_addr = ioremap(addr, SNR_IMC_MMIO_SIZE);
-	if (!box->io_addr)
+	box->io_addr = ioremap(addr, type->mmio_map_size);
+	if (!box->io_addr) {
+		pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name);
 		return;
+	}
 
 	writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
 }
@@ -4480,6 +4674,9 @@ static void snr_uncore_mmio_enable_event(struct intel_uncore_box *box,
 	if (!box->io_addr)
 		return;
 
+	if (!uncore_mmio_is_valid_offset(box, hwc->config_base))
+		return;
+
 	writel(hwc->config | SNBEP_PMON_CTL_EN,
 	       box->io_addr + hwc->config_base);
 }
@@ -4492,6 +4689,9 @@ static void snr_uncore_mmio_disable_event(struct intel_uncore_box *box,
 	if (!box->io_addr)
 		return;
 
+	if (!uncore_mmio_is_valid_offset(box, hwc->config_base))
+		return;
+
 	writel(hwc->config, box->io_addr + hwc->config_base);
 }
 
@@ -4530,6 +4730,7 @@ static struct intel_uncore_type snr_uncore_imc = {
 	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
 	.box_ctl	= SNR_IMC_MMIO_PMON_BOX_CTL,
 	.mmio_offset	= SNR_IMC_MMIO_OFFSET,
+	.mmio_map_size	= SNR_IMC_MMIO_SIZE,
 	.ops		= &snr_uncore_mmio_ops,
 	.format_group	= &skx_uncore_format_group,
 };
@@ -4570,6 +4771,7 @@ static struct intel_uncore_type snr_uncore_imc_free_running = {
 	.num_counters		= 3,
 	.num_boxes		= 1,
 	.num_freerunning_types	= SNR_IMC_FREERUNNING_TYPE_MAX,
+	.mmio_map_size		= SNR_IMC_MMIO_SIZE,
 	.freerunning		= snr_imc_freerunning,
 	.ops			= &snr_uncore_imc_freerunning_ops,
 	.event_descs		= snr_uncore_imc_freerunning_events,
@@ -4987,6 +5189,7 @@ static struct intel_uncore_type icx_uncore_imc = {
 	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
 	.box_ctl	= SNR_IMC_MMIO_PMON_BOX_CTL,
 	.mmio_offset	= SNR_IMC_MMIO_OFFSET,
+	.mmio_map_size	= SNR_IMC_MMIO_SIZE,
 	.ops		= &icx_uncore_mmio_ops,
 	.format_group	= &skx_uncore_format_group,
 };
@@ -5044,6 +5247,7 @@ static struct intel_uncore_type icx_uncore_imc_free_running = {
 	.num_counters		= 5,
 	.num_boxes		= 4,
 	.num_freerunning_types	= ICX_IMC_FREERUNNING_TYPE_MAX,
+	.mmio_map_size		= SNR_IMC_MMIO_SIZE,
 	.freerunning		= icx_imc_freerunning,
 	.ops			= &icx_uncore_imc_freerunning_ops,
 	.event_descs		= icx_uncore_imc_freerunning_events,
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index e17a3d8a47ed..7b68ab5f19e7 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -78,6 +78,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
 #define PERF_X86_EVENT_PEBS_VIA_PT	0x0800 /* use PT buffer for PEBS */
 #define PERF_X86_EVENT_PAIR		0x1000 /* Large Increment per Cycle */
+#define PERF_X86_EVENT_LBR_SELECT	0x2000 /* Save/Restore MSR_LBR_SELECT */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -179,6 +180,17 @@ struct x86_perf_task_context;
 #define MAX_LBR_ENTRIES		32
 
 enum {
+	LBR_FORMAT_32		= 0x00,
+	LBR_FORMAT_LIP		= 0x01,
+	LBR_FORMAT_EIP		= 0x02,
+	LBR_FORMAT_EIP_FLAGS	= 0x03,
+	LBR_FORMAT_EIP_FLAGS2	= 0x04,
+	LBR_FORMAT_INFO		= 0x05,
+	LBR_FORMAT_TIME		= 0x06,
+	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_TIME,
+};
+
+enum {
 	X86_PERF_KFREE_SHARED = 0,
 	X86_PERF_KFREE_EXCL   = 1,
 	X86_PERF_KFREE_MAX
@@ -233,10 +245,15 @@ struct cpu_hw_events {
 	int				lbr_pebs_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
-	struct er_account		*lbr_sel;
+	union {
+		struct er_account		*lbr_sel;
+		struct er_account		*lbr_ctl;
+	};
 	u64				br_sel;
-	struct x86_perf_task_context	*last_task_ctx;
+	void				*last_task_ctx;
 	int				last_log_id;
+	int				lbr_select;
+	void				*lbr_xsave;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -673,14 +690,38 @@ struct x86_pmu {
 	/*
 	 * Intel LBR
 	 */
-	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
-	int		lbr_nr;			   /* hardware stack size */
-	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
-	const int	*lbr_sel_map;		   /* lbr_select mappings */
+	unsigned int	lbr_tos, lbr_from, lbr_to,
+			lbr_info, lbr_nr;	   /* LBR base regs and size */
+	union {
+		u64	lbr_sel_mask;		   /* LBR_SELECT valid bits */
+		u64	lbr_ctl_mask;		   /* LBR_CTL valid bits */
+	};
+	union {
+		const int	*lbr_sel_map;	   /* lbr_select mappings */
+		int		*lbr_ctl_map;	   /* LBR_CTL mappings */
+	};
 	bool		lbr_double_abort;	   /* duplicated lbr aborts */
 	bool		lbr_pt_coexist;		   /* (LBR|BTS) may coexist with PT */
 
 	/*
+	 * Intel Architectural LBR CPUID Enumeration
+	 */
+	unsigned int	lbr_depth_mask:8;
+	unsigned int	lbr_deep_c_reset:1;
+	unsigned int	lbr_lip:1;
+	unsigned int	lbr_cpl:1;
+	unsigned int	lbr_filter:1;
+	unsigned int	lbr_call_stack:1;
+	unsigned int	lbr_mispred:1;
+	unsigned int	lbr_timed_lbr:1;
+	unsigned int	lbr_br_type:1;
+
+	void		(*lbr_reset)(void);
+	void		(*lbr_read)(struct cpu_hw_events *cpuc);
+	void		(*lbr_save)(void *ctx);
+	void		(*lbr_restore)(void *ctx);
+
+	/*
 	 * Intel PT/LBR/BTS are exclusive
 	 */
 	atomic_t	lbr_exclusive[x86_lbr_exclusive_max];
@@ -718,17 +759,46 @@ struct x86_pmu {
 	int (*aux_output_match) (struct perf_event *event);
 };
 
-struct x86_perf_task_context {
-	u64 lbr_from[MAX_LBR_ENTRIES];
-	u64 lbr_to[MAX_LBR_ENTRIES];
-	u64 lbr_info[MAX_LBR_ENTRIES];
-	int tos;
-	int valid_lbrs;
+struct x86_perf_task_context_opt {
 	int lbr_callstack_users;
 	int lbr_stack_state;
 	int log_id;
 };
 
+struct x86_perf_task_context {
+	u64 lbr_sel;
+	int tos;
+	int valid_lbrs;
+	struct x86_perf_task_context_opt opt;
+	struct lbr_entry lbr[MAX_LBR_ENTRIES];
+};
+
+struct x86_perf_task_context_arch_lbr {
+	struct x86_perf_task_context_opt opt;
+	struct lbr_entry entries[];
+};
+
+/*
+ * Add padding to guarantee the 64-byte alignment of the state buffer.
+ *
+ * The structure is dynamically allocated. The size of the LBR state may vary
+ * based on the number of LBR registers.
+ *
+ * Do not put anything after the LBR state.
+ */
+struct x86_perf_task_context_arch_lbr_xsave {
+	struct x86_perf_task_context_opt		opt;
+
+	union {
+		struct xregs_state			xsave;
+		struct {
+			struct fxregs_state		i387;
+			struct xstate_header		header;
+			struct arch_lbr_state		lbr;
+		} __attribute__ ((packed, aligned (XSAVE_ALIGNMENT)));
+	};
+};
+
 #define x86_add_quirk(func_)						\
 do {									\
 	static struct x86_pmu_quirk __quirk __initdata = {		\
@@ -777,6 +847,14 @@ static struct perf_pmu_events_ht_attr event_attr_##v = {		\
 struct pmu *x86_get_pmu(void);
 extern struct x86_pmu x86_pmu __read_mostly;
 
+static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
+{
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return &((struct x86_perf_task_context_arch_lbr *)ctx)->opt;
+
+	return &((struct x86_perf_task_context *)ctx)->opt;
+}
+
 static inline bool x86_pmu_has_lbr_callstack(void)
 {
 	return  x86_pmu.lbr_sel_map &&
@@ -989,7 +1067,10 @@ void release_ds_buffers(void);
 
 void reserve_ds_buffers(void);
 
+void release_lbr_buffers(void);
+
 extern struct event_constraint bts_constraint;
+extern struct event_constraint vlbr_constraint;
 
 void intel_pmu_enable_bts(u64 config);
 
@@ -1041,7 +1122,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
 
 void intel_pmu_auto_reload_read(struct perf_event *event);
 
-void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 
 void intel_ds_init(void);
 
@@ -1054,6 +1135,10 @@ u64 lbr_from_signext_quirk_wr(u64 val);
 
 void intel_pmu_lbr_reset(void);
 
+void intel_pmu_lbr_reset_32(void);
+
+void intel_pmu_lbr_reset_64(void);
+
 void intel_pmu_lbr_add(struct perf_event *event);
 
 void intel_pmu_lbr_del(struct perf_event *event);
@@ -1064,6 +1149,14 @@ void intel_pmu_lbr_disable_all(void);
 
 void intel_pmu_lbr_read(void);
 
+void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc);
+
+void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc);
+
+void intel_pmu_lbr_save(void *ctx);
+
+void intel_pmu_lbr_restore(void *ctx);
+
 void intel_pmu_lbr_init_core(void);
 
 void intel_pmu_lbr_init_nhm(void);
@@ -1080,6 +1173,8 @@ void intel_pmu_lbr_init_skl(void);
 
 void intel_pmu_lbr_init_knl(void);
 
+void intel_pmu_arch_lbr_init(void);
+
 void intel_pmu_pebs_data_source_nhm(void);
 
 void intel_pmu_pebs_data_source_skl(bool pmem);
@@ -1115,6 +1210,10 @@ static inline void release_ds_buffers(void)
 {
 }
 
+static inline void release_lbr_buffers(void)
+{
+}
+
 static inline int intel_pmu_init(void)
 {
 	return 0;
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 0f2bf59f4354..68b38820b10e 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -787,7 +787,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
-	X86_MATCH_VENDOR_FAM(AMD, 0x17, &model_amd_fam17h),
+	X86_MATCH_VENDOR_FAM(AMD,	0x17,		&model_amd_fam17h),
+	X86_MATCH_VENDOR_FAM(HYGON,	0x18,		&model_amd_fam17h),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index 898fa1ae9ceb..e68827e604ad 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Zhoaxin PMU; like Intel Architectural PerfMon-v2
+ * Zhaoxin PMU; like Intel Architectural PerfMon-v2
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index a54c6a401581..6035df1b49e1 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -375,7 +375,10 @@ void __init hyperv_init(void)
 	guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
-	hv_hypercall_pg = vmalloc_exec(PAGE_SIZE);
+	hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
+			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
+			VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
+			__builtin_return_address(0));
 	if (hv_hypercall_pg == NULL) {
 		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 		goto remove_cpuhp_state;
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index bf35e476a776..b6cac6e9bb70 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -14,8 +14,6 @@
  * resource counting etc..
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 /**
  * arch_atomic_read - read atomic variable
  * @v: pointer of type atomic_t
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 35460fef39b8..0367efdc5b7a 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr)
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
-static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
 {
-	/*
-	 * Because this is a plain access, we need to disable KCSAN here to
-	 * avoid double instrumentation via instrumented bitops.
-	 */
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index fb34ff641e0a..297fa12e7e27 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_BUG_H
 
 #include <linux/stringify.h>
+#include <linux/instrumentation.h>
 
 /*
  * Despite that some emulators terminate on UD2, we use it for WARN().
@@ -75,6 +76,12 @@ do {								\
 	unreachable();						\
 } while (0)
 
+/*
+ * This instrumentation_begin() is strictly speaking incorrect; but it
+ * suppresses the complaints from WARN()s in noinstr code. If such a WARN()
+ * were to trigger, we'd rather wreck the machine in an attempt to get the
+ * message out than not know about it.
+ */
 #define __WARN_FLAGS(flags)					\
 do {								\
 	instrumentation_begin();				\
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index dd17c2da1af5..da78ccbd493b 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip)
 	return false;
 }
 #endif
+#ifdef CONFIG_IA32_FEAT_CTL
+void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
+#else
+static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
+#endif
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 02dabc9e77b0..72ba4c59ad05 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -366,6 +366,7 @@
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
+#define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 6722ffcef2e6..3afa990d756b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask;
 
 extern void setup_cpu_local_masks(void);
 
+/*
+ * NMI and MCE exceptions need cpu_is_offline() _really_ early,
+ * provide an arch_ special for them to avoid instrumentation.
+ */
+#if NR_CPUS > 1
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return arch_test_bit(cpu, cpumask_bits(cpu_online_mask));
+}
+#else
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return cpu == 0;
+}
+#endif
+
+#define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index 9b8cb50768c2..b8f1dc0761e4 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -74,16 +74,26 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 #else
 # include <asm-generic/div64.h>
 
-static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+/*
+ * Will generate an #DE when the result doesn't fit u64, could fix with an
+ * __ex_table[] entry when it becomes an issue.
+ */
+static inline u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div)
 {
 	u64 q;
 
 	asm ("mulq %2; divq %3" : "=a" (q)
-				: "a" (a), "rm" ((u64)mul), "rm" ((u64)div)
+				: "a" (a), "rm" (mul), "rm" (div)
 				: "rdx");
 
 	return q;
 }
+#define mul_u64_u64_div_u64 mul_u64_u64_div_u64
+
+static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+{
+	return mul_u64_u64_div_u64(a, mul, div);
+}
 #define mul_u64_u32_div	mul_u64_u32_div
 
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 42159f45bf9c..6b10cdaa7c96 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -274,7 +274,7 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
  */
 static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 {
-	u64 mask = -1;
+	u64 mask = xfeatures_mask_all;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
 	int err;
@@ -320,7 +320,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
  */
 static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
 {
-	u64 mask = -1;
+	u64 mask = xfeatures_mask_all;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
 	int err;
@@ -356,6 +356,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
  */
 static inline int copy_xregs_to_user(struct xregs_state __user *buf)
 {
+	u64 mask = xfeatures_mask_user();
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
 	int err;
 
 	/*
@@ -367,7 +370,7 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf)
 		return -EFAULT;
 
 	stac();
-	XSTATE_OP(XSAVE, buf, -1, -1, err);
+	XSTATE_OP(XSAVE, buf, lmask, hmask, err);
 	clac();
 
 	return err;
@@ -408,43 +411,7 @@ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask)
 	return err;
 }
 
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact and we can
- * keep registers active.
- *
- * The legacy FNSAVE instruction cleared all FPU state
- * unconditionally, so registers are essentially destroyed.
- * Modern FPU state can be kept in registers, if there are
- * no pending FP exceptions.
- */
-static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
-{
-	if (likely(use_xsave())) {
-		copy_xregs_to_kernel(&fpu->state.xsave);
-
-		/*
-		 * AVX512 state is tracked here because its use is
-		 * known to slow the max clock speed of the core.
-		 */
-		if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
-			fpu->avx512_timestamp = jiffies;
-		return 1;
-	}
-
-	if (likely(use_fxsr())) {
-		copy_fxregs_to_kernel(fpu);
-		return 1;
-	}
-
-	/*
-	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
-	 * so we have to mark them inactive:
-	 */
-	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
-
-	return 0;
-}
+extern int copy_fpregs_to_fpstate(struct fpu *fpu);
 
 static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask)
 {
@@ -623,6 +590,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
  * MXCSR and XCR definitions:
  */
 
+static inline void ldmxcsr(u32 mxcsr)
+{
+	asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
 extern unsigned int mxcsr_feature_mask;
 
 #define XCR_XFEATURE_ENABLED_MASK	0x00000000
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index f098f6cab94b..c87364ea6446 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -114,6 +114,12 @@ enum xfeature {
 	XFEATURE_Hi16_ZMM,
 	XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
 	XFEATURE_PKRU,
+	XFEATURE_RSRVD_COMP_10,
+	XFEATURE_RSRVD_COMP_11,
+	XFEATURE_RSRVD_COMP_12,
+	XFEATURE_RSRVD_COMP_13,
+	XFEATURE_RSRVD_COMP_14,
+	XFEATURE_LBR,
 
 	XFEATURE_MAX,
 };
@@ -128,6 +134,7 @@ enum xfeature {
 #define XFEATURE_MASK_Hi16_ZMM		(1 << XFEATURE_Hi16_ZMM)
 #define XFEATURE_MASK_PT		(1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
 #define XFEATURE_MASK_PKRU		(1 << XFEATURE_PKRU)
+#define XFEATURE_MASK_LBR		(1 << XFEATURE_LBR)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
 #define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \
@@ -229,6 +236,26 @@ struct pkru_state {
 	u32				pad;
 } __packed;
 
+/*
+ * State component 15: Architectural LBR configuration state.
+ * The size of Arch LBR state depends on the number of LBRs (lbr_depth).
+ */
+
+struct lbr_entry {
+	u64 from;
+	u64 to;
+	u64 info;
+};
+
+struct arch_lbr_state {
+	u64 lbr_ctl;
+	u64 lbr_depth;
+	u64 ler_from;
+	u64 ler_to;
+	u64 ler_info;
+	struct lbr_entry		entries[];
+} __packed;
+
 struct xstate_header {
 	u64				xfeatures;
 	u64				xcomp_bv;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 422d8369012a..1559554af931 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -21,6 +21,8 @@
 #define XSAVE_YMM_SIZE	    256
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
+#define XSAVE_ALIGNMENT     64
+
 /* All currently supported user features */
 #define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \
 				      XFEATURE_MASK_SSE | \
@@ -36,6 +38,27 @@
 #define XFEATURE_MASK_SUPERVISOR_SUPPORTED (0)
 
 /*
+ * A supervisor state component may not always contain valuable information,
+ * and its size may be huge. Saving/restoring such supervisor state components
+ * at each context switch can cause high CPU and space overhead, which should
+ * be avoided. Such supervisor state components should only be saved/restored
+ * on demand. The on-demand dynamic supervisor features are set in this mask.
+ *
+ * Unlike the existing supported supervisor features, a dynamic supervisor
+ * feature does not allocate a buffer in task->fpu, and the corresponding
+ * supervisor state component cannot be saved/restored at each context switch.
+ *
+ * To support a dynamic supervisor feature, a developer should follow the
+ * dos and don'ts as below:
+ * - Do dynamically allocate a buffer for the supervisor state component.
+ * - Do manually invoke the XSAVES/XRSTORS instruction to save/restore the
+ *   state component to/from the buffer.
+ * - Don't set the bit corresponding to the dynamic supervisor feature in
+ *   IA32_XSS at run time, since it has been set at boot time.
+ */
+#define XFEATURE_MASK_DYNAMIC (XFEATURE_MASK_LBR)
+
+/*
  * Unsupported supervisor features. When a supervisor feature in this mask is
  * supported in the future, move it to the supported supervisor feature mask.
  */
@@ -43,6 +66,7 @@
 
 /* All supervisor states including supported and unsupported states. */
 #define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \
+				      XFEATURE_MASK_DYNAMIC | \
 				      XFEATURE_MASK_SUPERVISOR_UNSUPPORTED)
 
 #ifdef CONFIG_X86_64
@@ -63,6 +87,14 @@ static inline u64 xfeatures_mask_user(void)
 	return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED;
 }
 
+static inline u64 xfeatures_mask_dynamic(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_ARCH_LBR))
+		return XFEATURE_MASK_DYNAMIC & ~XFEATURE_MASK_LBR;
+
+	return XFEATURE_MASK_DYNAMIC;
+}
+
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
 extern void __init update_regset_xstate_info(unsigned int size,
@@ -71,11 +103,15 @@ extern void __init update_regset_xstate_info(unsigned int size,
 void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
 const void *get_xsave_field_ptr(int xfeature_nr);
 int using_compacted_format(void);
+int xfeature_size(int xfeature_nr);
 int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
 int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
 int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
 int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
 void copy_supervisor_to_kernel(struct xregs_state *xsave);
+void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask);
+void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask);
+
 
 /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
 int validate_user_xstate_header(const struct xstate_header *hdr);
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index cf51c50eb356..d74128c964f8 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -13,8 +13,15 @@
 void idtentry_enter_user(struct pt_regs *regs);
 void idtentry_exit_user(struct pt_regs *regs);
 
-bool idtentry_enter_cond_rcu(struct pt_regs *regs);
-void idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit);
+typedef struct idtentry_state {
+	bool exit_rcu;
+} idtentry_state_t;
+
+idtentry_state_t idtentry_enter(struct pt_regs *regs);
+void idtentry_exit(struct pt_regs *regs, idtentry_state_t state);
+
+bool idtentry_enter_nmi(struct pt_regs *regs);
+void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
 
 /**
  * DECLARE_IDTENTRY - Declare functions for simple IDT entry points
@@ -54,12 +61,12 @@ static __always_inline void __##func(struct pt_regs *regs);		\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__##func (regs);						\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs)
@@ -101,12 +108,12 @@ static __always_inline void __##func(struct pt_regs *regs,		\
 __visible noinstr void func(struct pt_regs *regs,			\
 			    unsigned long error_code)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__##func (regs, error_code);					\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs,		\
@@ -199,7 +206,7 @@ static __always_inline void __##func(struct pt_regs *regs, u8 vector);	\
 __visible noinstr void func(struct pt_regs *regs,			\
 			    unsigned long error_code)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	irq_enter_rcu();						\
@@ -207,7 +214,7 @@ __visible noinstr void func(struct pt_regs *regs,			\
 	__##func (regs, (u8)error_code);				\
 	irq_exit_rcu();							\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs, u8 vector)
@@ -241,7 +248,7 @@ static void __##func(struct pt_regs *regs);				\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	irq_enter_rcu();						\
@@ -249,7 +256,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	run_on_irqstack_cond(__##func, regs, regs);			\
 	irq_exit_rcu();							\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static noinline void __##func(struct pt_regs *regs)
@@ -270,7 +277,7 @@ static __always_inline void __##func(struct pt_regs *regs);		\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__irq_enter_raw();						\
@@ -278,7 +285,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	__##func (regs);						\
 	__irq_exit_raw();						\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs)
@@ -353,10 +360,6 @@ static __always_inline void __##func(struct pt_regs *regs)
 
 #else	/* CONFIG_X86_64 */
 
-/* Maps to a regular IDTENTRY on 32bit for now */
-# define DECLARE_IDTENTRY_IST		DECLARE_IDTENTRY
-# define DEFINE_IDTENTRY_IST		DEFINE_IDTENTRY
-
 /**
  * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant
  * @vector:	Vector number (ignored for C)
@@ -387,28 +390,18 @@ __visible noinstr void func(struct pt_regs *regs,			\
 #endif	/* !CONFIG_X86_64 */
 
 /* C-Code mapping */
+#define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
+#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
+
+#ifdef CONFIG_X86_64
 #define DECLARE_IDTENTRY_MCE		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE_USER	DEFINE_IDTENTRY_NOIST
 
-#define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
-#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
-
 #define DECLARE_IDTENTRY_DEBUG		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG_USER	DEFINE_IDTENTRY_NOIST
-
-/**
- * DECLARE_IDTENTRY_XEN - Declare functions for XEN redirect IDT entry points
- * @vector:	Vector number (ignored for C)
- * @func:	Function name of the entry point
- *
- * Used for xennmi and xendebug redirections. No DEFINE as this is all ASM
- * indirection magic.
- */
-#define DECLARE_IDTENTRY_XEN(vector, func)				\
-	asmlinkage void xen_asm_exc_xen##func(void);			\
-	asmlinkage void asm_exc_xen##func(void)
+#endif
 
 #else /* !__ASSEMBLY__ */
 
@@ -455,9 +448,6 @@ __visible noinstr void func(struct pt_regs *regs,			\
 # define DECLARE_IDTENTRY_MCE(vector, func)				\
 	DECLARE_IDTENTRY(vector, func)
 
-# define DECLARE_IDTENTRY_DEBUG(vector, func)				\
-	DECLARE_IDTENTRY(vector, func)
-
 /* No ASM emitted for DF as this goes through a C shim */
 # define DECLARE_IDTENTRY_DF(vector, func)
 
@@ -469,10 +459,6 @@ __visible noinstr void func(struct pt_regs *regs,			\
 /* No ASM code emitted for NMI */
 #define DECLARE_IDTENTRY_NMI(vector, func)
 
-/* XEN NMI and DB wrapper */
-#define DECLARE_IDTENTRY_XEN(vector, func)				\
-	idtentry vector asm_exc_xen##func exc_##func has_error_code=0
-
 /*
  * ASM code to emit the common vector entry stubs where each stub is
  * packed into 8 bytes.
@@ -490,16 +476,15 @@ __visible noinstr void func(struct pt_regs *regs,			\
 	.align 8
 SYM_CODE_START(irq_entries_start)
     vector=FIRST_EXTERNAL_VECTOR
-    pos = .
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_common_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
-    pos=pos+8
-    vector=vector+1
+	. = 0b + 8
+	vector = vector+1
     .endr
 SYM_CODE_END(irq_entries_start)
 
@@ -507,16 +492,15 @@ SYM_CODE_END(irq_entries_start)
 	.align 8
 SYM_CODE_START(spurious_entries_start)
     vector=FIRST_SYSTEM_VECTOR
-    pos = .
     .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_spurious_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
-    pos=pos+8
-    vector=vector+1
+	. = 0b + 8
+	vector = vector+1
     .endr
 SYM_CODE_END(spurious_entries_start)
 #endif
@@ -565,16 +549,28 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_BP,		exc_int3);
 DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF,	exc_page_fault);
 
 #ifdef CONFIG_X86_MCE
+#ifdef CONFIG_X86_64
 DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);
+#else
+DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	exc_machine_check);
+#endif
 #endif
 
 /* NMI */
 DECLARE_IDTENTRY_NMI(X86_TRAP_NMI,	exc_nmi);
-DECLARE_IDTENTRY_XEN(X86_TRAP_NMI,	nmi);
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
+DECLARE_IDTENTRY_RAW(X86_TRAP_NMI,	xenpv_exc_nmi);
+#endif
 
 /* #DB */
+#ifdef CONFIG_X86_64
 DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB,	exc_debug);
-DECLARE_IDTENTRY_XEN(X86_TRAP_DB,	debug);
+#else
+DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	exc_debug);
+#endif
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
+DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
+#endif
 
 /* #DF */
 DECLARE_IDTENTRY_DF(X86_TRAP_DF,	exc_double_fault);
@@ -635,8 +631,8 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,	sysvec_kvm_posted_intr_nested
 
 #if IS_ENABLED(CONFIG_HYPERV)
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index f5a796da07f8..438ccd4f3cc4 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -12,7 +12,6 @@
 
 #define REG_TYPE_R32		0
 #define REG_TYPE_R64		1
-#define REG_TYPE_XMM		2
 #define REG_TYPE_INVALID	100
 
 	.macro R32_NUM opd r32
@@ -123,77 +122,18 @@
 #endif
 	.endm
 
-	.macro XMM_NUM opd xmm
-	\opd = REG_NUM_INVALID
-	.ifc \xmm,%xmm0
-	\opd = 0
-	.endif
-	.ifc \xmm,%xmm1
-	\opd = 1
-	.endif
-	.ifc \xmm,%xmm2
-	\opd = 2
-	.endif
-	.ifc \xmm,%xmm3
-	\opd = 3
-	.endif
-	.ifc \xmm,%xmm4
-	\opd = 4
-	.endif
-	.ifc \xmm,%xmm5
-	\opd = 5
-	.endif
-	.ifc \xmm,%xmm6
-	\opd = 6
-	.endif
-	.ifc \xmm,%xmm7
-	\opd = 7
-	.endif
-	.ifc \xmm,%xmm8
-	\opd = 8
-	.endif
-	.ifc \xmm,%xmm9
-	\opd = 9
-	.endif
-	.ifc \xmm,%xmm10
-	\opd = 10
-	.endif
-	.ifc \xmm,%xmm11
-	\opd = 11
-	.endif
-	.ifc \xmm,%xmm12
-	\opd = 12
-	.endif
-	.ifc \xmm,%xmm13
-	\opd = 13
-	.endif
-	.ifc \xmm,%xmm14
-	\opd = 14
-	.endif
-	.ifc \xmm,%xmm15
-	\opd = 15
-	.endif
-	.endm
-
 	.macro REG_TYPE type reg
 	R32_NUM reg_type_r32 \reg
 	R64_NUM reg_type_r64 \reg
-	XMM_NUM reg_type_xmm \reg
 	.if reg_type_r64 <> REG_NUM_INVALID
 	\type = REG_TYPE_R64
 	.elseif reg_type_r32 <> REG_NUM_INVALID
 	\type = REG_TYPE_R32
-	.elseif reg_type_xmm <> REG_NUM_INVALID
-	\type = REG_TYPE_XMM
 	.else
 	\type = REG_TYPE_INVALID
 	.endif
 	.endm
 
-	.macro PFX_OPD_SIZE
-	.byte 0x66
-	.endm
-
 	.macro PFX_REX opd1 opd2 W=0
 	.if ((\opd1 | \opd2) & 8) || \W
 	.byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1) | (\W << 3)
@@ -203,109 +143,6 @@
 	.macro MODRM mod opd1 opd2
 	.byte \mod | (\opd1 & 7) | ((\opd2 & 7) << 3)
 	.endm
-
-	.macro PSHUFB_XMM xmm1 xmm2
-	XMM_NUM pshufb_opd1 \xmm1
-	XMM_NUM pshufb_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX pshufb_opd1 pshufb_opd2
-	.byte 0x0f, 0x38, 0x00
-	MODRM 0xc0 pshufb_opd1 pshufb_opd2
-	.endm
-
-	.macro PCLMULQDQ imm8 xmm1 xmm2
-	XMM_NUM clmul_opd1 \xmm1
-	XMM_NUM clmul_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX clmul_opd1 clmul_opd2
-	.byte 0x0f, 0x3a, 0x44
-	MODRM 0xc0 clmul_opd1 clmul_opd2
-	.byte \imm8
-	.endm
-
-	.macro PEXTRD imm8 xmm gpr
-	R32_NUM extrd_opd1 \gpr
-	XMM_NUM extrd_opd2 \xmm
-	PFX_OPD_SIZE
-	PFX_REX extrd_opd1 extrd_opd2
-	.byte 0x0f, 0x3a, 0x16
-	MODRM 0xc0 extrd_opd1 extrd_opd2
-	.byte \imm8
-	.endm
-
-	.macro AESKEYGENASSIST rcon xmm1 xmm2
-	XMM_NUM aeskeygen_opd1 \xmm1
-	XMM_NUM aeskeygen_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aeskeygen_opd1 aeskeygen_opd2
-	.byte 0x0f, 0x3a, 0xdf
-	MODRM 0xc0 aeskeygen_opd1 aeskeygen_opd2
-	.byte \rcon
-	.endm
-
-	.macro AESIMC xmm1 xmm2
-	XMM_NUM aesimc_opd1 \xmm1
-	XMM_NUM aesimc_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesimc_opd1 aesimc_opd2
-	.byte 0x0f, 0x38, 0xdb
-	MODRM 0xc0 aesimc_opd1 aesimc_opd2
-	.endm
-
-	.macro AESENC xmm1 xmm2
-	XMM_NUM aesenc_opd1 \xmm1
-	XMM_NUM aesenc_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesenc_opd1 aesenc_opd2
-	.byte 0x0f, 0x38, 0xdc
-	MODRM 0xc0 aesenc_opd1 aesenc_opd2
-	.endm
-
-	.macro AESENCLAST xmm1 xmm2
-	XMM_NUM aesenclast_opd1 \xmm1
-	XMM_NUM aesenclast_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesenclast_opd1 aesenclast_opd2
-	.byte 0x0f, 0x38, 0xdd
-	MODRM 0xc0 aesenclast_opd1 aesenclast_opd2
-	.endm
-
-	.macro AESDEC xmm1 xmm2
-	XMM_NUM aesdec_opd1 \xmm1
-	XMM_NUM aesdec_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesdec_opd1 aesdec_opd2
-	.byte 0x0f, 0x38, 0xde
-	MODRM 0xc0 aesdec_opd1 aesdec_opd2
-	.endm
-
-	.macro AESDECLAST xmm1 xmm2
-	XMM_NUM aesdeclast_opd1 \xmm1
-	XMM_NUM aesdeclast_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesdeclast_opd1 aesdeclast_opd2
-	.byte 0x0f, 0x38, 0xdf
-	MODRM 0xc0 aesdeclast_opd1 aesdeclast_opd2
-	.endm
-
-	.macro MOVQ_R64_XMM opd1 opd2
-	REG_TYPE movq_r64_xmm_opd1_type \opd1
-	.if movq_r64_xmm_opd1_type == REG_TYPE_XMM
-	XMM_NUM movq_r64_xmm_opd1 \opd1
-	R64_NUM movq_r64_xmm_opd2 \opd2
-	.else
-	R64_NUM movq_r64_xmm_opd1 \opd1
-	XMM_NUM movq_r64_xmm_opd2 \opd2
-	.endif
-	PFX_OPD_SIZE
-	PFX_REX movq_r64_xmm_opd1 movq_r64_xmm_opd2 1
-	.if movq_r64_xmm_opd1_type == REG_TYPE_XMM
-	.byte 0x0f, 0x7e
-	.else
-	.byte 0x0f, 0x6e
-	.endif
-	MODRM 0xc0 movq_r64_xmm_opd1 movq_r64_xmm_opd2
-	.endm
 #endif
 
 #endif
diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h
index ac1a99ffbd8d..7f080f5c7def 100644
--- a/arch/x86/include/asm/io_bitmap.h
+++ b/arch/x86/include/asm/io_bitmap.h
@@ -19,12 +19,28 @@ struct task_struct;
 void io_bitmap_share(struct task_struct *tsk);
 void io_bitmap_exit(struct task_struct *tsk);
 
+static inline void native_tss_invalidate_io_bitmap(void)
+{
+	/*
+	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
+	 * TSS limit so any subsequent I/O access from user space will
+	 * trigger a #GP.
+	 *
+	 * This is correct even when VMEXIT rewrites the TSS limit
+	 * to 0x67 as the only requirement is that the base points
+	 * outside the limit.
+	 */
+	this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base,
+		       IO_BITMAP_OFFSET_INVALID);
+}
+
 void native_tss_update_io_bitmap(void);
 
 #ifdef CONFIG_PARAVIRT_XXL
 #include <asm/paravirt.h>
 #else
 #define tss_update_io_bitmap native_tss_update_io_bitmap
+#define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap
 #endif
 
 #else
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 5270ff39b9af..a1911fea8739 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -39,6 +39,7 @@
 #define BT_MBI_UNIT_PMC		0x04
 #define BT_MBI_UNIT_GFX		0x06
 #define BT_MBI_UNIT_SMI		0x0C
+#define BT_MBI_UNIT_CCK		0x14
 #define BT_MBI_UNIT_USB		0x43
 #define BT_MBI_UNIT_SATA	0xA3
 #define BT_MBI_UNIT_PCIE	0xA6
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 073eb7ad2f56..143bc9abe99c 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -66,6 +66,8 @@ struct arch_specific_insn {
 	 */
 	bool boostable;
 	bool if_modifier;
+	/* Number of bytes of text poked */
+	int tp_len;
 };
 
 struct arch_optimized_insn {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f8998e97457f..be5363b21540 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -943,7 +943,7 @@ struct kvm_arch {
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
-	bool apic_map_dirty;
+	atomic_t apic_map_dirty;
 
 	bool apic_access_page_done;
 	unsigned long apicv_inhibit_reasons;
@@ -1220,7 +1220,7 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
-	int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e8370e64a155..bdc07fc6e517 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -158,7 +158,23 @@
 #define LBR_INFO_MISPRED		BIT_ULL(63)
 #define LBR_INFO_IN_TX			BIT_ULL(62)
 #define LBR_INFO_ABORT			BIT_ULL(61)
+#define LBR_INFO_CYC_CNT_VALID		BIT_ULL(60)
 #define LBR_INFO_CYCLES			0xffff
+#define LBR_INFO_BR_TYPE_OFFSET		56
+#define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
+
+#define MSR_ARCH_LBR_CTL		0x000014ce
+#define ARCH_LBR_CTL_LBREN		BIT(0)
+#define ARCH_LBR_CTL_CPL_OFFSET		1
+#define ARCH_LBR_CTL_CPL		(0x3ull << ARCH_LBR_CTL_CPL_OFFSET)
+#define ARCH_LBR_CTL_STACK_OFFSET	3
+#define ARCH_LBR_CTL_STACK		(0x1ull << ARCH_LBR_CTL_STACK_OFFSET)
+#define ARCH_LBR_CTL_FILTER_OFFSET	16
+#define ARCH_LBR_CTL_FILTER		(0x7full << ARCH_LBR_CTL_FILTER_OFFSET)
+#define MSR_ARCH_LBR_DEPTH		0x000014cf
+#define MSR_ARCH_LBR_FROM_0		0x00001500
+#define MSR_ARCH_LBR_TO_0		0x00001600
+#define MSR_ARCH_LBR_INFO_0		0x00001200
 
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_PEBS_DATA_CFG		0x000003f2
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 73d997aa2966..e039a933aca3 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -25,8 +25,6 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-u32 get_umwait_control_msr(void);
-
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
 {
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5ca5d297df75..3d2afecde50c 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -302,6 +302,11 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static inline void tss_invalidate_io_bitmap(void)
+{
+	PVOP_VCALL0(cpu.invalidate_io_bitmap);
+}
+
 static inline void tss_update_io_bitmap(void)
 {
 	PVOP_VCALL0(cpu.update_io_bitmap);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 732f62e04ddb..8dfcb2508e6d 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -141,6 +141,7 @@ struct pv_cpu_ops {
 	void (*load_sp0)(unsigned long sp0);
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	void (*invalidate_io_bitmap)(void);
 	void (*update_io_bitmap)(void);
 #endif
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index e855e9cf2c37..0c1b13720525 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -142,6 +142,46 @@ union cpuid10_edx {
 	unsigned int full;
 };
 
+/*
+ * Intel Architectural LBR CPUID detection/enumeration details:
+ */
+union cpuid28_eax {
+	struct {
+		/* Supported LBR depth values */
+		unsigned int	lbr_depth_mask:8;
+		unsigned int	reserved:22;
+		/* Deep C-state Reset */
+		unsigned int	lbr_deep_c_reset:1;
+		/* IP values contain LIP */
+		unsigned int	lbr_lip:1;
+	} split;
+	unsigned int		full;
+};
+
+union cpuid28_ebx {
+	struct {
+		/* CPL Filtering Supported */
+		unsigned int    lbr_cpl:1;
+		/* Branch Filtering Supported */
+		unsigned int    lbr_filter:1;
+		/* Call-stack Mode Supported */
+		unsigned int    lbr_call_stack:1;
+	} split;
+	unsigned int            full;
+};
+
+union cpuid28_ecx {
+	struct {
+		/* Mispredict Bit Supported */
+		unsigned int    lbr_mispred:1;
+		/* Timed LBRs Supported */
+		unsigned int    lbr_timed_lbr:1;
+		/* Branch Type Field Supported */
+		unsigned int    lbr_br_type:1;
+	} split;
+	unsigned int            full;
+};
+
 struct x86_pmu_capability {
 	int		version;
 	int		num_counters_gp;
@@ -192,10 +232,30 @@ struct x86_pmu_capability {
 #define GLOBAL_STATUS_UNC_OVF				BIT_ULL(61)
 #define GLOBAL_STATUS_ASIF				BIT_ULL(60)
 #define GLOBAL_STATUS_COUNTERS_FROZEN			BIT_ULL(59)
-#define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(58)
+#define GLOBAL_STATUS_LBRS_FROZEN_BIT			58
+#define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(GLOBAL_STATUS_LBRS_FROZEN_BIT)
 #define GLOBAL_STATUS_TRACE_TOPAPMI			BIT_ULL(55)
 
 /*
+ * We model guest LBR event tracing as another fixed-mode PMC like BTS.
+ *
+ * We choose bit 58 because it's used to indicate LBR stack frozen state
+ * for architectural perfmon v4, also we unconditionally mask that bit in
+ * the handle_pmi_common(), so it'll never be set in the overflow handling.
+ *
+ * With this fake counter assigned, the guest LBR event user (such as KVM),
+ * can program the LBR registers on its own, and we don't actually do anything
+ * with then in the host context.
+ */
+#define INTEL_PMC_IDX_FIXED_VLBR	(GLOBAL_STATUS_LBRS_FROZEN_BIT)
+
+/*
+ * Pseudo-encoding the guest LBR event as event=0x00,umask=0x1b,
+ * since it would claim bit 58 which is effectively Fixed26.
+ */
+#define INTEL_FIXED_VLBR_EVENT	0x1b00
+
+/*
  * Adaptive PEBS v4
  */
 
@@ -222,14 +282,6 @@ struct pebs_xmm {
 	u64 xmm[16*2];	/* two entries for each register */
 };
 
-struct pebs_lbr_entry {
-	u64 from, to, info;
-};
-
-struct pebs_lbr {
-	struct pebs_lbr_entry lbr[0]; /* Variable length */
-};
-
 /*
  * IBS cpuid feature detection
  */
@@ -333,6 +385,13 @@ struct perf_guest_switch_msr {
 	u64 host, guest;
 };
 
+struct x86_pmu_lbr {
+	unsigned int	nr;
+	unsigned int	from;
+	unsigned int	to;
+	unsigned int	info;
+};
+
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 extern void perf_check_microcode(void);
 extern int x86_perf_rdpmc_index(struct perf_event *event);
@@ -348,12 +407,17 @@ static inline void perf_check_microcode(void) { }
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
 extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
+extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
 #else
 static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
 	*nr = 0;
 	return NULL;
 }
+static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+{
+	return -1;
+}
 #endif
 
 #ifdef CONFIG_CPU_SUP_INTEL
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 2da1f95b88d7..816b31c68550 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -194,6 +194,7 @@ enum page_cache_mode {
 #define _PAGE_TABLE_NOENC	 (__PP|__RW|_USR|___A|   0|___D|   0|   0)
 #define _PAGE_TABLE		 (__PP|__RW|_USR|___A|   0|___D|   0|   0| _ENC)
 #define __PAGE_KERNEL_RO	 (__PP|   0|   0|___A|__NX|___D|   0|___G)
+#define __PAGE_KERNEL_ROX	 (__PP|   0|   0|___A|   0|___D|   0|___G)
 #define __PAGE_KERNEL_NOCACHE	 (__PP|__RW|   0|___A|__NX|___D|   0|___G| __NC)
 #define __PAGE_KERNEL_VVAR	 (__PP|   0|_USR|___A|__NX|___D|   0|___G)
 #define __PAGE_KERNEL_LARGE	 (__PP|__RW|   0|___A|__NX|___D|_PSE|___G)
@@ -219,6 +220,7 @@ enum page_cache_mode {
 #define PAGE_KERNEL_RO		__pgprot_mask(__PAGE_KERNEL_RO         | _ENC)
 #define PAGE_KERNEL_EXEC	__pgprot_mask(__PAGE_KERNEL_EXEC       | _ENC)
 #define PAGE_KERNEL_EXEC_NOENC	__pgprot_mask(__PAGE_KERNEL_EXEC       |    0)
+#define PAGE_KERNEL_ROX		__pgprot_mask(__PAGE_KERNEL_ROX        | _ENC)
 #define PAGE_KERNEL_NOCACHE	__pgprot_mask(__PAGE_KERNEL_NOCACHE    | _ENC)
 #define PAGE_KERNEL_LARGE	__pgprot_mask(__PAGE_KERNEL_LARGE      | _ENC)
 #define PAGE_KERNEL_LARGE_EXEC	__pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 42cd333616c4..03b7c4ca425a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -370,7 +370,7 @@ struct x86_hw_tss {
 #define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
 
 struct entry_stack {
-	unsigned long		words[64];
+	char	stack[PAGE_SIZE];
 };
 
 struct entry_stack_page {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index ebedeab48704..255b2dde2c1b 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -278,7 +278,7 @@ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs
 }
 
 /* To avoid include hell, we can't include uaccess.h */
-extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
 
 /**
  * regs_get_kernel_stack_nth() - get Nth entry of the stack
@@ -298,7 +298,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 
 	addr = regs_get_kernel_stack_nth_addr(regs, n);
 	if (addr) {
-		ret = probe_kernel_read(&val, addr, sizeof(val));
+		ret = copy_from_kernel_nofault(&val, addr, sizeof(val));
 		if (!ret)
 			return val;
 	}
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 79d8d5496330..f4234575f3fd 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -193,7 +193,7 @@ static inline void sched_clear_itmt_support(void)
 }
 #endif /* CONFIG_SCHED_MC_PRIO */
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_X86_64)
 #include <asm/cpufeature.h>
 
 DECLARE_STATIC_KEY_FALSE(arch_scale_freq_key);
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 17c5a038f42d..0780f97c1850 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -408,14 +408,15 @@ struct kvm_vmx_nested_state_data {
 };
 
 struct kvm_vmx_nested_state_hdr {
-	__u32 flags;
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
-	__u64 preemption_timer_deadline;
 
 	struct {
 		__u16 flags;
 	} smm;
+
+	__u32 flags;
+	__u64 preemption_timer_deadline;
 };
 
 struct kvm_svm_nested_state_data {
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9e7dc37a8627..20e07feb4064 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -3,6 +3,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/perf_event.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/stringify.h>
@@ -1001,6 +1002,7 @@ struct text_poke_loc {
 	s32 rel32;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	u8 old;
 };
 
 struct bp_patching_desc {
@@ -1168,8 +1170,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	/*
 	 * First step: add a int3 trap to the address that will be patched.
 	 */
-	for (i = 0; i < nr_entries; i++)
+	for (i = 0; i < nr_entries; i++) {
+		tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
 		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
+	}
 
 	text_poke_sync();
 
@@ -1177,14 +1181,45 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
+		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
 		int len = text_opcode_size(tp[i].opcode);
 
 		if (len - INT3_INSN_SIZE > 0) {
+			memcpy(old + INT3_INSN_SIZE,
+			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+			       len - INT3_INSN_SIZE);
 			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
 				  (const char *)tp[i].text + INT3_INSN_SIZE,
 				  len - INT3_INSN_SIZE);
 			do_sync++;
 		}
+
+		/*
+		 * Emit a perf event to record the text poke, primarily to
+		 * support Intel PT decoding which must walk the executable code
+		 * to reconstruct the trace. The flow up to here is:
+		 *   - write INT3 byte
+		 *   - IPI-SYNC
+		 *   - write instruction tail
+		 * At this point the actual control flow will be through the
+		 * INT3 and handler and not hit the old or new instruction.
+		 * Intel PT outputs FUP/TIP packets for the INT3, so the flow
+		 * can still be decoded. Subsequently:
+		 *   - emit RECORD_TEXT_POKE with the new instruction
+		 *   - IPI-SYNC
+		 *   - write first byte
+		 *   - IPI-SYNC
+		 * So before the text poke event timestamp, the decoder will see
+		 * either the old instruction flow or FUP/TIP of INT3. After the
+		 * text poke event timestamp, the decoder will see either the
+		 * new instruction flow or FUP/TIP of INT3. Thus decoders can
+		 * use the timestamp as the point at which to modify the
+		 * executable code.
+		 * The old instruction is recorded so that the event can be
+		 * processed forwards or backwards.
+		 */
+		perf_event_text_poke(text_poke_addr(&tp[i]), old, len,
+				     tp[i].text, len);
 	}
 
 	if (do_sync) {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ce61e3e7d399..21325a4a78b9 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2316,12 +2316,12 @@ static int mp_irqdomain_create(int ioapic)
 	ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops,
 						 (void *)(long)ioapic);
 
-	/* Release fw handle if it was allocated above */
-	if (!cfg->dev)
-		irq_domain_free_fwnode(fn);
-
-	if (!ip->irqdomain)
+	if (!ip->irqdomain) {
+		/* Release fw handle if it was allocated above */
+		if (!cfg->dev)
+			irq_domain_free_fwnode(fn);
 		return -ENOMEM;
+	}
 
 	ip->irqdomain->parent = parent;
 
@@ -2335,8 +2335,13 @@ static int mp_irqdomain_create(int ioapic)
 
 static void ioapic_destroy_irqdomain(int idx)
 {
+	struct ioapic_domain_cfg *cfg = &ioapics[idx].irqdomain_cfg;
+	struct fwnode_handle *fn = ioapics[idx].irqdomain->fwnode;
+
 	if (ioapics[idx].irqdomain) {
 		irq_domain_remove(ioapics[idx].irqdomain);
+		if (!cfg->dev)
+			irq_domain_free_fwnode(fn);
 		ioapics[idx].irqdomain = NULL;
 	}
 }
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 5cbaca58af95..c2b2911feeef 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -263,12 +263,13 @@ void __init arch_init_msi_domain(struct irq_domain *parent)
 		msi_default_domain =
 			pci_msi_create_irq_domain(fn, &pci_msi_domain_info,
 						  parent);
-		irq_domain_free_fwnode(fn);
 	}
-	if (!msi_default_domain)
+	if (!msi_default_domain) {
+		irq_domain_free_fwnode(fn);
 		pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
-	else
+	} else {
 		msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
+	}
 }
 
 #ifdef CONFIG_IRQ_REMAP
@@ -301,7 +302,8 @@ struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent,
 	if (!fn)
 		return NULL;
 	d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent);
-	irq_domain_free_fwnode(fn);
+	if (!d)
+		irq_domain_free_fwnode(fn);
 	return d;
 }
 #endif
@@ -364,7 +366,8 @@ static struct irq_domain *dmar_get_irq_domain(void)
 	if (fn) {
 		dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info,
 						    x86_vector_domain);
-		irq_domain_free_fwnode(fn);
+		if (!dmar_domain)
+			irq_domain_free_fwnode(fn);
 	}
 out:
 	mutex_unlock(&dmar_lock);
@@ -489,7 +492,10 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id)
 	}
 
 	d = msi_create_irq_domain(fn, domain_info, parent);
-	irq_domain_free_fwnode(fn);
+	if (!d) {
+		irq_domain_free_fwnode(fn);
+		kfree(domain_info);
+	}
 	return d;
 }
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index c48be6e1f676..dae32d948bf2 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -446,12 +446,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
 	trace_vector_activate(irqd->irq, apicd->is_managed,
 			      apicd->can_reserve, reserve);
 
-	/* Nothing to do for fixed assigned vectors */
-	if (!apicd->can_reserve && !apicd->is_managed)
-		return 0;
-
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	if (reserve || irqd_is_managed_and_shutdown(irqd))
+	if (!apicd->can_reserve && !apicd->is_managed)
+		assign_irq_vector_any_locked(irqd);
+	else if (reserve || irqd_is_managed_and_shutdown(irqd))
 		vector_assign_managed_shutdown(irqd);
 	else if (apicd->is_managed)
 		ret = activate_managed(irqd);
@@ -562,6 +560,10 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		 * as that can corrupt the affinity move state.
 		 */
 		irqd_set_handle_enforce_irqctx(irqd);
+
+		/* Don't invoke affinity setter on deactivated interrupts */
+		irqd_set_affinity_on_activate(irqd);
+
 		/*
 		 * Legacy vectors are already assigned when the IOAPIC
 		 * takes them over. They stay on the same vector. This is
@@ -709,7 +711,6 @@ int __init arch_early_irq_init(void)
 	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
 						   NULL);
 	BUG_ON(x86_vector_domain == NULL);
-	irq_domain_free_fwnode(fn);
 	irq_set_default_host(x86_vector_domain);
 
 	arch_init_msi_domain(x86_vector_domain);
@@ -775,20 +776,10 @@ void lapic_offline(void)
 static int apic_set_affinity(struct irq_data *irqd,
 			     const struct cpumask *dest, bool force)
 {
-	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	int err;
 
-	/*
-	 * Core code can call here for inactive interrupts. For inactive
-	 * interrupts which use managed or reservation mode there is no
-	 * point in going through the vector assignment right now as the
-	 * activation will assign a vector which fits the destination
-	 * cpumask. Let the core code store the destination mask and be
-	 * done with it.
-	 */
-	if (!irqd_is_activated(irqd) &&
-	    (apicd->is_managed || apicd->can_reserve))
-		return IRQ_SET_MASK_OK;
+	if (WARN_ON_ONCE(!irqd_is_activated(irqd)))
+		return -EIO;
 
 	raw_spin_lock(&vector_lock);
 	cpumask_and(vector_searchmask, dest, cpu_online_mask);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 426792565d86..c5cf336e5077 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -3,6 +3,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/e820/api.h>
 #include <asm/mtrr.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 043d93cdcaad..95c090a45b4b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -347,6 +347,9 @@ out:
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
+/* These bits should not change their value after CPU init is finished. */
+static const unsigned long cr4_pinned_mask =
+	X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE;
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
@@ -371,20 +374,20 @@ EXPORT_SYMBOL(native_write_cr0);
 
 void native_write_cr4(unsigned long val)
 {
-	unsigned long bits_missing = 0;
+	unsigned long bits_changed = 0;
 
 set_register:
 	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
 
 	if (static_branch_likely(&cr_pinning)) {
-		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
-			bits_missing = ~val & cr4_pinned_bits;
-			val |= bits_missing;
+		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {
+			bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits;
+			val = (val & ~cr4_pinned_mask) | cr4_pinned_bits;
 			goto set_register;
 		}
-		/* Warn after we've set the missing bits. */
-		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
-			  bits_missing);
+		/* Warn after we've corrected the changed bits. */
+		WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n",
+			  bits_changed);
 	}
 }
 #if IS_MODULE(CONFIG_LKDTM)
@@ -419,7 +422,7 @@ void cr4_init(void)
 	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4 |= X86_CR4_PCIDE;
 	if (static_branch_likely(&cr_pinning))
-		cr4 |= cr4_pinned_bits;
+		cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits;
 
 	__write_cr4(cr4);
 
@@ -434,10 +437,7 @@ void cr4_init(void)
  */
 static void __init setup_cr_pinning(void)
 {
-	unsigned long mask;
-
-	mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP);
-	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask;
+	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask;
 	static_key_enable(&cr_pinning.key);
 }
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index fb538fccd24c..9d033693519a 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -81,8 +81,4 @@ extern void update_srbds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
-#ifdef CONFIG_IA32_FEAT_CTL
-void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
-#endif
-
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index c25a67a34bd3..0ab48f1cdf84 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -50,6 +50,13 @@ static enum split_lock_detect_state sld_state __ro_after_init = sld_off;
 static u64 msr_test_ctrl_cache __ro_after_init;
 
 /*
+ * With a name like MSR_TEST_CTL it should go without saying, but don't touch
+ * MSR_TEST_CTL unless the CPU is one of the whitelisted models.  Writing it
+ * on CPUs that do not support SLD can cause fireworks, even when writing '0'.
+ */
+static bool cpu_model_supports_sld __ro_after_init;
+
+/*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists
  * CPU models in which having conflicting memory types still leads to
@@ -1071,7 +1078,8 @@ static void sld_update_msr(bool on)
 
 static void split_lock_init(void)
 {
-	split_lock_verify_msr(sld_state != sld_off);
+	if (cpu_model_supports_sld)
+		split_lock_verify_msr(sld_state != sld_off);
 }
 
 static void split_lock_warn(unsigned long ip)
@@ -1177,5 +1185,6 @@ void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
 		return;
 	}
 
+	cpu_model_supports_sld = true;
 	split_lock_setup();
 }
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index ce9120c4f740..14e4b4d17ee5 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1083,7 +1083,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 {
 	unsigned int cpu = smp_processor_id();
 
-	if (cpu_is_offline(cpu) ||
+	if (arch_cpu_is_offline(cpu) ||
 	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
@@ -1901,6 +1901,8 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check;
 
 static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 {
+	WARN_ON_ONCE(user_mode(regs));
+
 	/*
 	 * Only required when from kernel mode. See
 	 * mce_check_crashing_cpu() for details.
@@ -1954,7 +1956,7 @@ DEFINE_IDTENTRY_MCE_USER(exc_machine_check)
 }
 #else
 /* 32bit unified entry point */
-DEFINE_IDTENTRY_MCE(exc_machine_check)
+DEFINE_IDTENTRY_RAW(exc_machine_check)
 {
 	unsigned long dr7;
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 12f967c6b603..6a9df71c1b9e 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -981,10 +981,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 
 		c->x86_cache_max_rmid  = ecx;
 		c->x86_cache_occ_scale = ebx;
-		if (c->x86_vendor == X86_VENDOR_INTEL)
-			c->x86_cache_mbm_width_offset = eax & 0xff;
-		else
-			c->x86_cache_mbm_width_offset = -1;
+		c->x86_cache_mbm_width_offset = eax & 0xff;
+
+		if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset)
+			c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD;
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index f20a47d120b1..5ffa32256b3b 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -37,6 +37,7 @@
 #define MBA_IS_LINEAR			0x4
 #define MBA_MAX_MBPS			U32_MAX
 #define MAX_MBA_BW_AMD			0x800
+#define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 23b4b61319d3..3f844f14fc0a 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
 	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
 	if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
 		_r_cdp = NULL;
+		_d_cdp = NULL;
 		ret = -EINVAL;
 	}
 
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index 300e3fd5ade3..ec8064c0ae03 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -18,12 +18,6 @@
  */
 static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
 
-u32 get_umwait_control_msr(void)
-{
-	return umwait_control_cached;
-}
-EXPORT_SYMBOL_GPL(get_umwait_control_msr);
-
 /*
  * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by
  * hardware or BIOS before kernel boot.
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index df1358ba622b..05fa4ef63490 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -2,6 +2,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 
 #include "cpu.h"
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 456511b2284e..7401cc12c3cc 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -71,6 +71,22 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src,
+		     unsigned int nbytes)
+{
+	if (!user_mode(regs))
+		return copy_from_kernel_nofault(buf, (u8 *)src, nbytes);
+
+	/*
+	 * Make sure userspace isn't trying to trick us into dumping kernel
+	 * memory by pointing the userspace instruction pointer at it.
+	 */
+	if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX))
+		return -EINVAL;
+
+	return copy_from_user_nmi(buf, (void __user *)src, nbytes);
+}
+
 /*
  * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus:
  *
@@ -97,17 +113,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
 #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
 	unsigned long prologue = regs->ip - PROLOGUE_SIZE;
-	bool bad_ip;
-
-	/*
-	 * Make sure userspace isn't trying to trick us into dumping kernel
-	 * memory by pointing the userspace instruction pointer at it.
-	 */
-	bad_ip = user_mode(regs) &&
-		__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
 
-	if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue,
-					OPCODE_BUFSIZE)) {
+	if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
 		printk("%sCode: Bad RIP value.\n", loglvl);
 	} else {
 		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 06c818967bb6..eb86a2b831b1 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -82,6 +82,45 @@ bool irq_fpu_usable(void)
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+	if (likely(use_xsave())) {
+		copy_xregs_to_kernel(&fpu->state.xsave);
+
+		/*
+		 * AVX512 state is tracked here because its use is
+		 * known to slow the max clock speed of the core.
+		 */
+		if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
+			fpu->avx512_timestamp = jiffies;
+		return 1;
+	}
+
+	if (likely(use_fxsr())) {
+		copy_fxregs_to_kernel(fpu);
+		return 1;
+	}
+
+	/*
+	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
+	 * so we have to mark them inactive:
+	 */
+	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+	return 0;
+}
+EXPORT_SYMBOL(copy_fpregs_to_fpstate);
+
 void kernel_fpu_begin(void)
 {
 	preempt_disable();
@@ -101,6 +140,12 @@ void kernel_fpu_begin(void)
 		copy_fpregs_to_fpstate(&current->thread.fpu);
 	}
 	__cpu_invalidate_fpregs_state();
+
+	if (boot_cpu_has(X86_FEATURE_XMM))
+		ldmxcsr(MXCSR_DEFAULT);
+
+	if (boot_cpu_has(X86_FEATURE_FPU))
+		asm volatile ("fninit");
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_begin);
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index bda2e5eaca0e..be2a68a09d19 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -233,8 +233,10 @@ void fpu__init_cpu_xstate(void)
 	/*
 	 * MSR_IA32_XSS sets supervisor states managed by XSAVES.
 	 */
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+				     xfeatures_mask_dynamic());
+	}
 }
 
 static bool xfeature_enabled(enum xfeature xfeature)
@@ -486,7 +488,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
 	return ebx;
 }
 
-static int xfeature_size(int xfeature_nr)
+int xfeature_size(int xfeature_nr)
 {
 	u32 eax, ebx, ecx, edx;
 
@@ -598,7 +600,8 @@ static void check_xstate_against_struct(int nr)
 	 */
 	if ((nr < XFEATURE_YMM) ||
 	    (nr >= XFEATURE_MAX) ||
-	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR)) {
+	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
+	    ((nr >= XFEATURE_RSRVD_COMP_10) && (nr <= XFEATURE_LBR))) {
 		WARN_ONCE(1, "no structure for xstate: %d\n", nr);
 		XSTATE_WARN_ON(1);
 	}
@@ -847,8 +850,10 @@ void fpu__resume_cpu(void)
 	 * Restore IA32_XSS. The same CPUID bit enumerates support
 	 * of XSAVES and MSR_IA32_XSS.
 	 */
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
+				     xfeatures_mask_dynamic());
+	}
 }
 
 /*
@@ -1074,7 +1079,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 		copy_part(offsetof(struct fxregs_state, st_space), 128,
 			  &xsave->i387.st_space, &kbuf, &offset_start, &count);
 	if (header.xfeatures & XFEATURE_MASK_SSE)
-		copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256,
+		copy_part(xstate_offsets[XFEATURE_SSE], 256,
 			  &xsave->i387.xmm_space, &kbuf, &offset_start, &count);
 	/*
 	 * Fill xsave->i387.sw_reserved value for ptrace frame:
@@ -1356,6 +1361,78 @@ void copy_supervisor_to_kernel(struct xregs_state *xstate)
 	}
 }
 
+/**
+ * copy_dynamic_supervisor_to_kernel() - Save dynamic supervisor states to
+ *                                       an xsave area
+ * @xstate: A pointer to an xsave area
+ * @mask: Represent the dynamic supervisor features saved into the xsave area
+ *
+ * Only the dynamic supervisor states sets in the mask are saved into the xsave
+ * area (See the comment in XFEATURE_MASK_DYNAMIC for the details of dynamic
+ * supervisor feature). Besides the dynamic supervisor states, the legacy
+ * region and XSAVE header are also saved into the xsave area. The supervisor
+ * features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and
+ * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not saved.
+ *
+ * The xsave area must be 64-bytes aligned.
+ */
+void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask)
+{
+	u64 dynamic_mask = xfeatures_mask_dynamic() & mask;
+	u32 lmask, hmask;
+	int err;
+
+	if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (WARN_ON_FPU(!dynamic_mask))
+		return;
+
+	lmask = dynamic_mask;
+	hmask = dynamic_mask >> 32;
+
+	XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
+
+	/* Should never fault when copying to a kernel buffer */
+	WARN_ON_FPU(err);
+}
+
+/**
+ * copy_kernel_to_dynamic_supervisor() - Restore dynamic supervisor states from
+ *                                       an xsave area
+ * @xstate: A pointer to an xsave area
+ * @mask: Represent the dynamic supervisor features restored from the xsave area
+ *
+ * Only the dynamic supervisor states sets in the mask are restored from the
+ * xsave area (See the comment in XFEATURE_MASK_DYNAMIC for the details of
+ * dynamic supervisor feature). Besides the dynamic supervisor states, the
+ * legacy region and XSAVE header are also restored from the xsave area. The
+ * supervisor features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and
+ * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not restored.
+ *
+ * The xsave area must be 64-bytes aligned.
+ */
+void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask)
+{
+	u64 dynamic_mask = xfeatures_mask_dynamic() & mask;
+	u32 lmask, hmask;
+	int err;
+
+	if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (WARN_ON_FPU(!dynamic_mask))
+		return;
+
+	lmask = dynamic_mask;
+	hmask = dynamic_mask >> 32;
+
+	XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+
+	/* Should never fault when copying from a kernel buffer */
+	WARN_ON_FPU(err);
+}
+
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 /*
  * Report the amount of time elapsed in millisecond since last AVX512
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c84d28e90a58..51504566b3a6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -86,7 +86,7 @@ static int ftrace_verify_code(unsigned long ip, const char *old_code)
 	 * sure what we read is what we expected it to be before modifying it.
 	 */
 	/* read the text we want to modify */
-	if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
+	if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
 		WARN_ON(1);
 		return -EFAULT;
 	}
@@ -355,7 +355,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
-	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
+	ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
 	if (WARN_ON(ret < 0))
 		goto fail;
 
@@ -363,13 +363,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	/* The trampoline ends with ret(q) */
 	retq = (unsigned long)ftrace_stub;
-	ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+	ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
 	if (WARN_ON(ret < 0))
 		goto fail;
 
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
 		ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller);
-		ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+		ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
 		if (WARN_ON(ret < 0))
 			goto fail;
 	}
@@ -506,7 +506,7 @@ static void *addr_from_call(void *ptr)
 	union text_poke_insn call;
 	int ret;
 
-	ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE);
+	ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE);
 	if (WARN_ON_ONCE(ret < 0))
 		return NULL;
 
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index f3c76252247d..282b4ee1339f 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -207,7 +207,7 @@ spurious_8259A_irq:
 		 * lets ACK and report it. [once per IRQ]
 		 */
 		if (!(spurious_irq_mask & irqmask)) {
-			printk(KERN_DEBUG
+			printk_deferred(KERN_DEBUG
 			       "spurious 8259A interrupt: IRQ%d.\n", irq);
 			spurious_irq_mask |= irqmask;
 		}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index c44fe7d8d9a4..68acd30c6b87 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -732,11 +732,11 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	int err;
 
 	bpt->type = BP_BREAKPOINT;
-	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+	err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
 				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
-	err = probe_kernel_write((char *)bpt->bpt_addr,
+	err = copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
 	if (!err)
 		return err;
@@ -768,7 +768,7 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 	return 0;
 
 knl_write:
-	return probe_kernel_write((char *)bpt->bpt_addr,
+	return copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 3bafe1bd4dc7..fdadc37d72af 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -33,6 +33,7 @@
 #include <linux/hardirq.h>
 #include <linux/preempt.h>
 #include <linux/sched/debug.h>
+#include <linux/perf_event.h>
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
@@ -243,7 +244,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 	 * Fortunately, we know that the original code is the ideal 5-byte
 	 * long NOP.
 	 */
-	if (probe_kernel_read(buf, (void *)addr,
+	if (copy_from_kernel_nofault(buf, (void *)addr,
 		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 		return 0UL;
 
@@ -346,7 +347,8 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 		return 0;
 
 	/* This can access kernel text if given address is not recovered */
-	if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE))
+	if (copy_from_kernel_nofault(dest, (void *)recovered_insn,
+			MAX_INSN_SIZE))
 		return 0;
 
 	kernel_insn_init(insn, dest, MAX_INSN_SIZE);
@@ -471,6 +473,9 @@ static int arch_copy_kprobe(struct kprobe *p)
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = buf[0];
 
+	p->ainsn.tp_len = len;
+	perf_event_text_poke(p->ainsn.insn, NULL, 0, buf, len);
+
 	/* OK, write back the instruction(s) into ROX insn buffer */
 	text_poke(p->ainsn.insn, buf, len);
 
@@ -502,12 +507,18 @@ int arch_prepare_kprobe(struct kprobe *p)
 
 void arch_arm_kprobe(struct kprobe *p)
 {
-	text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1);
+	u8 int3 = INT3_INSN_OPCODE;
+
+	text_poke(p->addr, &int3, 1);
 	text_poke_sync();
+	perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1);
 }
 
 void arch_disarm_kprobe(struct kprobe *p)
 {
+	u8 int3 = INT3_INSN_OPCODE;
+
+	perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1);
 	text_poke(p->addr, &p->opcode, 1);
 	text_poke_sync();
 }
@@ -515,6 +526,9 @@ void arch_disarm_kprobe(struct kprobe *p)
 void arch_remove_kprobe(struct kprobe *p)
 {
 	if (p->ainsn.insn) {
+		/* Record the perf event before freeing the slot */
+		perf_event_text_poke(p->ainsn.insn, p->ainsn.insn,
+				     p->ainsn.tp_len, NULL, 0);
 		free_insn_slot(p->ainsn.insn, p->ainsn.boostable);
 		p->ainsn.insn = NULL;
 	}
@@ -753,16 +767,11 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
-static struct kprobe kretprobe_kprobe = {
-	.addr = (void *)kretprobe_trampoline,
-};
-
 /*
  * Called from kretprobe_trampoline
  */
 __used __visible void *trampoline_handler(struct pt_regs *regs)
 {
-	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
@@ -772,16 +781,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 	void *frame_pointer;
 	bool skipped = false;
 
-	preempt_disable();
-
 	/*
 	 * Set a dummy kprobe for avoiding kretprobe recursion.
 	 * Since kretprobe never run in kprobe handler, kprobe must not
 	 * be running at this point.
 	 */
-	kcb = get_kprobe_ctlblk();
-	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
-	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+	kprobe_busy_begin();
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -857,7 +862,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+			__this_cpu_write(current_kprobe, &kprobe_busy);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -873,8 +878,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
-	__this_cpu_write(current_kprobe, NULL);
-	preempt_enable();
+	kprobe_busy_end();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 321c19950285..40f380461e6d 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -6,6 +6,7 @@
  * Copyright (C) Hitachi Ltd., 2012
  */
 #include <linux/kprobes.h>
+#include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
 #include <linux/slab.h>
@@ -56,7 +57,7 @@ found:
 	 * overwritten by jump destination address. In this case, original
 	 * bytes must be recovered from op->optinsn.copied_insn buffer.
 	 */
-	if (probe_kernel_read(buf, (void *)addr,
+	if (copy_from_kernel_nofault(buf, (void *)addr,
 		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 		return 0UL;
 
@@ -352,8 +353,15 @@ int arch_within_optimized_kprobe(struct optimized_kprobe *op,
 static
 void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 {
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
+	u8 *slot = op->optinsn.insn;
+	if (slot) {
+		int len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE;
+
+		/* Record the perf event before freeing the slot */
+		if (dirty)
+			perf_event_text_poke(slot, slot, len, NULL, 0);
+
+		free_optinsn_slot(slot, dirty);
 		op->optinsn.insn = NULL;
 		op->optinsn.size = 0;
 	}
@@ -424,8 +432,15 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 			   (u8 *)op->kp.addr + op->optinsn.size);
 	len += JMP32_INSN_SIZE;
 
+	/*
+	 * Note	len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE is also
+	 * used in __arch_remove_optimized_kprobe().
+	 */
+
 	/* We have to use text_poke() for instruction buffer because it is RO */
+	perf_event_text_poke(slot, NULL, 0, buf, len);
 	text_poke(slot, buf, len);
+
 	ret = 0;
 out:
 	kfree(buf);
@@ -477,10 +492,23 @@ void arch_optimize_kprobes(struct list_head *oplist)
  */
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	arch_arm_kprobe(&op->kp);
-	text_poke(op->kp.addr + INT3_INSN_SIZE,
-		  op->optinsn.copied_insn, DISP32_SIZE);
+	u8 new[JMP32_INSN_SIZE] = { INT3_INSN_OPCODE, };
+	u8 old[JMP32_INSN_SIZE];
+	u8 *addr = op->kp.addr;
+
+	memcpy(old, op->kp.addr, JMP32_INSN_SIZE);
+	memcpy(new + INT3_INSN_SIZE,
+	       op->optinsn.copied_insn,
+	       JMP32_INSN_SIZE - INT3_INSN_SIZE);
+
+	text_poke(addr, new, INT3_INSN_SIZE);
 	text_poke_sync();
+	text_poke(addr + INT3_INSN_SIZE,
+		  new + INT3_INSN_SIZE,
+		  JMP32_INSN_SIZE - INT3_INSN_SIZE);
+	text_poke_sync();
+
+	perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
 }
 
 /*
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index df63786e7bfa..3f78482d9496 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -233,7 +233,7 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags);
 noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 {
 	u32 reason = kvm_read_and_reset_apf_flags();
-	bool rcu_exit;
+	idtentry_state_t state;
 
 	switch (reason) {
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
@@ -243,7 +243,7 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 		return false;
 	}
 
-	rcu_exit = idtentry_enter_cond_rcu(regs);
+	state = idtentry_enter(regs);
 	instrumentation_begin();
 
 	/*
@@ -264,7 +264,7 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 	}
 
 	instrumentation_end();
-	idtentry_exit_cond_rcu(regs, rcu_exit);
+	idtentry_exit(regs, state);
 	return true;
 }
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 8748321c4486..b8aee71840ae 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -29,6 +29,8 @@
 #include <asm/mmu_context.h>
 #include <asm/pgtable_areas.h>
 
+#include <xen/xen.h>
+
 /* This is a multiple of PAGE_SIZE. */
 #define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
 
@@ -543,6 +545,28 @@ static int read_default_ldt(void __user *ptr, unsigned long bytecount)
 	return bytecount;
 }
 
+static bool allow_16bit_segments(void)
+{
+	if (!IS_ENABLED(CONFIG_X86_16BIT))
+		return false;
+
+#ifdef CONFIG_XEN_PV
+	/*
+	 * Xen PV does not implement ESPFIX64, which means that 16-bit
+	 * segments will not work correctly.  Until either Xen PV implements
+	 * ESPFIX64 and can signal this fact to the guest or unless someone
+	 * provides compelling evidence that allowing broken 16-bit segments
+	 * is worthwhile, disallow 16-bit segments under Xen PV.
+	 */
+	if (xen_pv_domain()) {
+		pr_info_once("Warning: 16-bit segments do not work correctly in a Xen PV guest\n");
+		return false;
+	}
+#endif
+
+	return true;
+}
+
 static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 {
 	struct mm_struct *mm = current->mm;
@@ -574,7 +598,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		/* The user wants to clear the entry. */
 		memset(&ldt, 0, sizeof(ldt));
 	} else {
-		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+		if (!ldt_info.seg_32bit && !allow_16bit_segments()) {
 			error = -EINVAL;
 			goto out;
 		}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 2de365f15684..4fc9954a9560 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -330,7 +330,6 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 	__this_cpu_write(last_nmi_rip, regs->ip);
 
 	instrumentation_begin();
-	trace_hardirqs_off_finish();
 
 	handled = nmi_handle(NMI_LOCAL, regs);
 	__this_cpu_add(nmi_stats.normal, handled);
@@ -417,8 +416,6 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 		unknown_nmi_error(reason, regs);
 
 out:
-	if (regs->flags & X86_EFLAGS_IF)
-		trace_hardirqs_on_prepare();
 	instrumentation_end();
 }
 
@@ -478,7 +475,9 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7);
 
 DEFINE_IDTENTRY_RAW(exc_nmi)
 {
-	if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id()))
+	bool irq_state;
+
+	if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id()))
 		return;
 
 	if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
@@ -491,14 +490,14 @@ nmi_restart:
 
 	this_cpu_write(nmi_dr7, local_db_save());
 
-	nmi_enter();
+	irq_state = idtentry_enter_nmi(regs);
 
 	inc_irq_stat(__nmi_count);
 
 	if (!ignore_nmis)
 		default_do_nmi(regs);
 
-	nmi_exit();
+	idtentry_exit_nmi(regs, irq_state);
 
 	local_db_restore(this_cpu_read(nmi_dr7));
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 674a7d66d960..de2138ba38e5 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -324,7 +324,8 @@ struct paravirt_patch_template pv_ops = {
 	.cpu.swapgs		= native_swapgs,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-	.cpu.update_io_bitmap	= native_tss_update_io_bitmap,
+	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
+	.cpu.update_io_bitmap		= native_tss_update_io_bitmap,
 #endif
 
 	.cpu.start_context_switch	= paravirt_nop,
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index ee0286390a4c..9e1def3744f2 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -94,12 +94,12 @@ static bool match_id(struct pci_dev *pdev, unsigned short vendor, unsigned short
 }
 
 static bool probe_list(struct pci_dev *pdev, unsigned short vendor,
-		       const unsigned char *rom_list)
+		       const void *rom_list)
 {
 	unsigned short device;
 
 	do {
-		if (probe_kernel_address(rom_list, device) != 0)
+		if (get_kernel_nofault(device, rom_list) != 0)
 			device = 0;
 
 		if (device && match_id(pdev, vendor, device))
@@ -119,19 +119,19 @@ static struct resource *find_oprom(struct pci_dev *pdev)
 	for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) {
 		struct resource *res = &adapter_rom_resources[i];
 		unsigned short offset, vendor, device, list, rev;
-		const unsigned char *rom;
+		const void *rom;
 
 		if (res->end == 0)
 			break;
 
 		rom = isa_bus_to_virt(res->start);
-		if (probe_kernel_address(rom + 0x18, offset) != 0)
+		if (get_kernel_nofault(offset, rom + 0x18) != 0)
 			continue;
 
-		if (probe_kernel_address(rom + offset + 0x4, vendor) != 0)
+		if (get_kernel_nofault(vendor, rom + offset + 0x4) != 0)
 			continue;
 
-		if (probe_kernel_address(rom + offset + 0x6, device) != 0)
+		if (get_kernel_nofault(device, rom + offset + 0x6) != 0)
 			continue;
 
 		if (match_id(pdev, vendor, device)) {
@@ -139,8 +139,8 @@ static struct resource *find_oprom(struct pci_dev *pdev)
 			break;
 		}
 
-		if (probe_kernel_address(rom + offset + 0x8, list) == 0 &&
-		    probe_kernel_address(rom + offset + 0xc, rev) == 0 &&
+		if (get_kernel_nofault(list, rom + offset + 0x8) == 0 &&
+		    get_kernel_nofault(rev, rom + offset + 0xc) == 0 &&
 		    rev >= 3 && list &&
 		    probe_list(pdev, vendor, rom + offset + list)) {
 			oprom = res;
@@ -183,14 +183,14 @@ static int __init romsignature(const unsigned char *rom)
 	const unsigned short * const ptr = (const unsigned short *)rom;
 	unsigned short sig;
 
-	return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE;
+	return get_kernel_nofault(sig, ptr) == 0 && sig == ROMSIGNATURE;
 }
 
 static int __init romchecksum(const unsigned char *rom, unsigned long length)
 {
 	unsigned char sum, c;
 
-	for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--)
+	for (sum = 0; length && get_kernel_nofault(c, rom++) == 0; length--)
 		sum += c;
 	return !length && !sum;
 }
@@ -211,7 +211,7 @@ void __init probe_roms(void)
 
 		video_rom_resource.start = start;
 
-		if (probe_kernel_address(rom + 2, c) != 0)
+		if (get_kernel_nofault(c, rom + 2) != 0)
 			continue;
 
 		/* 0 < length <= 0x7f * 512, historically */
@@ -249,7 +249,7 @@ void __init probe_roms(void)
 		if (!romsignature(rom))
 			continue;
 
-		if (probe_kernel_address(rom + 2, c) != 0)
+		if (get_kernel_nofault(c, rom + 2) != 0)
 			continue;
 
 		/* 0 < length <= 0x7f * 512, historically */
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f362ce0d5ac0..fe67dbd76e51 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -322,20 +322,6 @@ void arch_setup_new_exec(void)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-static inline void tss_invalidate_io_bitmap(struct tss_struct *tss)
-{
-	/*
-	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
-	 * TSS limit so any subsequent I/O access from user space will
-	 * trigger a #GP.
-	 *
-	 * This is correct even when VMEXIT rewrites the TSS limit
-	 * to 0x67 as the only requirement is that the base points
-	 * outside the limit.
-	 */
-	tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
-}
-
 static inline void switch_to_bitmap(unsigned long tifp)
 {
 	/*
@@ -346,7 +332,7 @@ static inline void switch_to_bitmap(unsigned long tifp)
 	 * user mode.
 	 */
 	if (tifp & _TIF_IO_BITMAP)
-		tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw));
+		tss_invalidate_io_bitmap();
 }
 
 static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm)
@@ -380,7 +366,7 @@ void native_tss_update_io_bitmap(void)
 	u16 *base = &tss->x86_tss.io_bitmap_base;
 
 	if (!test_thread_flag(TIF_IO_BITMAP)) {
-		tss_invalidate_io_bitmap(tss);
+		native_tss_invalidate_io_bitmap();
 		return;
 	}
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ffbd9a3d78d8..518ac6bf752e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -56,6 +56,7 @@
 #include <linux/cpuidle.h>
 #include <linux/numa.h>
 #include <linux/pgtable.h>
+#include <linux/overflow.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -1777,6 +1778,7 @@ void native_play_dead(void)
 
 #endif
 
+#ifdef CONFIG_X86_64
 /*
  * APERF/MPERF frequency ratio computation.
  *
@@ -1975,6 +1977,7 @@ static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
 static bool intel_set_max_freq_ratio(void)
 {
 	u64 base_freq, turbo_freq;
+	u64 turbo_ratio;
 
 	if (slv_set_max_freq_ratio(&base_freq, &turbo_freq))
 		goto out;
@@ -2000,15 +2003,23 @@ out:
 	/*
 	 * Some hypervisors advertise X86_FEATURE_APERFMPERF
 	 * but then fill all MSR's with zeroes.
+	 * Some CPUs have turbo boost but don't declare any turbo ratio
+	 * in MSR_TURBO_RATIO_LIMIT.
 	 */
-	if (!base_freq) {
-		pr_debug("Couldn't determine cpu base frequency, necessary for scale-invariant accounting.\n");
+	if (!base_freq || !turbo_freq) {
+		pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n");
 		return false;
 	}
 
-	arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE,
-					base_freq);
+	turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq);
+	if (!turbo_ratio) {
+		pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n");
+		return false;
+	}
+
+	arch_turbo_freq_ratio = turbo_ratio;
 	arch_set_max_freq_ratio(turbo_disabled());
+
 	return true;
 }
 
@@ -2048,11 +2059,19 @@ static void init_freq_invariance(bool secondary)
 	}
 }
 
+static void disable_freq_invariance_workfn(struct work_struct *work)
+{
+	static_branch_disable(&arch_scale_freq_key);
+}
+
+static DECLARE_WORK(disable_freq_invariance_work,
+		    disable_freq_invariance_workfn);
+
 DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
 
 void arch_scale_freq_tick(void)
 {
-	u64 freq_scale;
+	u64 freq_scale = SCHED_CAPACITY_SCALE;
 	u64 aperf, mperf;
 	u64 acnt, mcnt;
 
@@ -2064,19 +2083,32 @@ void arch_scale_freq_tick(void)
 
 	acnt = aperf - this_cpu_read(arch_prev_aperf);
 	mcnt = mperf - this_cpu_read(arch_prev_mperf);
-	if (!mcnt)
-		return;
 
 	this_cpu_write(arch_prev_aperf, aperf);
 	this_cpu_write(arch_prev_mperf, mperf);
 
-	acnt <<= 2*SCHED_CAPACITY_SHIFT;
-	mcnt *= arch_max_freq_ratio;
+	if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
+		goto error;
+
+	if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt)
+		goto error;
 
 	freq_scale = div64_u64(acnt, mcnt);
+	if (!freq_scale)
+		goto error;
 
 	if (freq_scale > SCHED_CAPACITY_SCALE)
 		freq_scale = SCHED_CAPACITY_SCALE;
 
 	this_cpu_write(arch_freq_scale, freq_scale);
+	return;
+
+error:
+	pr_warn("Scheduler frequency invariance went wobbly, disabling!\n");
+	schedule_work(&disable_freq_invariance_work);
+}
+#else
+static inline void init_freq_invariance(bool secondary)
+{
 }
+#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 6ad43fc44556..2fd698e28e4d 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-
 			if (IS_ENABLED(CONFIG_FRAME_POINTER))
 				return -EINVAL;
 		}
@@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 	if (unwind_error(&state))
 		return -EINVAL;
 
-	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
-	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index af75109485c2..8493f55e1167 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -84,17 +84,16 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
 		local_irq_disable();
 }
 
-int is_valid_bugaddr(unsigned long addr)
+__always_inline int is_valid_bugaddr(unsigned long addr)
 {
-	unsigned short ud;
-
 	if (addr < TASK_SIZE_MAX)
 		return 0;
 
-	if (probe_kernel_address((unsigned short *)addr, ud))
-		return 0;
-
-	return ud == INSN_UD0 || ud == INSN_UD2;
+	/*
+	 * We got #UD, if the text isn't readable we'd have gotten
+	 * a different exception.
+	 */
+	return *(unsigned short *)addr == INSN_UD2;
 }
 
 static nokprobe_inline int
@@ -216,46 +215,51 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 		      ILL_ILLOPN, error_get_trap_addr(regs));
 }
 
-DEFINE_IDTENTRY_RAW(exc_invalid_op)
+static noinstr bool handle_bug(struct pt_regs *regs)
 {
-	bool rcu_exit;
+	bool handled = false;
+
+	if (!is_valid_bugaddr(regs->ip))
+		return handled;
 
 	/*
-	 * Handle BUG/WARN like NMIs instead of like normal idtentries:
-	 * if we bugged/warned in a bad RCU context, for example, the last
-	 * thing we want is to BUG/WARN again in the idtentry code, ad
-	 * infinitum.
+	 * All lies, just get the WARN/BUG out.
+	 */
+	instrumentation_begin();
+	/*
+	 * Since we're emulating a CALL with exceptions, restore the interrupt
+	 * state to what it was at the exception site.
 	 */
-	if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) {
-		enum bug_trap_type type;
+	if (regs->flags & X86_EFLAGS_IF)
+		raw_local_irq_enable();
+	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+		regs->ip += LEN_UD2;
+		handled = true;
+	}
+	if (regs->flags & X86_EFLAGS_IF)
+		raw_local_irq_disable();
+	instrumentation_end();
 
-		nmi_enter();
-		instrumentation_begin();
-		trace_hardirqs_off_finish();
-		type = report_bug(regs->ip, regs);
-		if (regs->flags & X86_EFLAGS_IF)
-			trace_hardirqs_on_prepare();
-		instrumentation_end();
-		nmi_exit();
+	return handled;
+}
 
-		if (type == BUG_TRAP_TYPE_WARN) {
-			/* Skip the ud2. */
-			regs->ip += LEN_UD2;
-			return;
-		}
+DEFINE_IDTENTRY_RAW(exc_invalid_op)
+{
+	idtentry_state_t state;
 
-		/*
-		 * Else, if this was a BUG and report_bug returns or if this
-		 * was just a normal #UD, we want to continue onward and
-		 * crash.
-		 */
-	}
+	/*
+	 * We use UD2 as a short encoding for 'CALL __WARN', as such
+	 * handle it before exception entry to avoid recursive WARN
+	 * in case exception entry is the one triggering WARNs.
+	 */
+	if (!user_mode(regs) && handle_bug(regs))
+		return;
 
-	rcu_exit = idtentry_enter_cond_rcu(regs);
+	state = idtentry_enter(regs);
 	instrumentation_begin();
 	handle_invalid_op(regs);
 	instrumentation_end();
-	idtentry_exit_cond_rcu(regs, rcu_exit);
+	idtentry_exit(regs, state);
 }
 
 DEFINE_IDTENTRY(exc_coproc_segment_overrun)
@@ -299,6 +303,8 @@ DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check)
 
 	do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs,
 		error_code, BUS_ADRALN, NULL);
+
+	local_irq_disable();
 }
 
 #ifdef CONFIG_VMAP_STACK
@@ -399,7 +405,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 	}
 #endif
 
-	nmi_enter();
+	idtentry_enter_nmi(regs);
 	instrumentation_begin();
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -488,7 +494,8 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs,
 	u8 insn_buf[MAX_INSN_SIZE];
 	struct insn insn;
 
-	if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
+	if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip,
+			MAX_INSN_SIZE))
 		return GP_NO_HINT;
 
 	kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
@@ -644,15 +651,12 @@ DEFINE_IDTENTRY_RAW(exc_int3)
 		instrumentation_end();
 		idtentry_exit_user(regs);
 	} else {
-		nmi_enter();
+		bool irq_state = idtentry_enter_nmi(regs);
 		instrumentation_begin();
-		trace_hardirqs_off_finish();
 		if (!do_int3(regs))
 			die("int3", regs, 0);
-		if (regs->flags & X86_EFLAGS_IF)
-			trace_hardirqs_on_prepare();
 		instrumentation_end();
-		nmi_exit();
+		idtentry_exit_nmi(regs, irq_state);
 	}
 }
 
@@ -690,13 +694,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 		(struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the temporary storage. */
-	memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
+	__memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
 
 	/* Copy the remainder of the stack from the current stack. */
-	memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
+	__memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
 
 	/* Update the entry stack */
-	memcpy(new_stack, &tmp, sizeof(tmp));
+	__memcpy(new_stack, &tmp, sizeof(tmp));
 
 	BUG_ON(!user_mode(&new_stack->regs));
 	return new_stack;
@@ -860,9 +864,14 @@ out:
 static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 					     unsigned long dr6)
 {
-	nmi_enter();
+	bool irq_state = idtentry_enter_nmi(regs);
 	instrumentation_begin();
-	trace_hardirqs_off_finish();
+
+	/*
+	 * If something gets miswired and we end up here for a user mode
+	 * #DB, we will malfunction.
+	 */
+	WARN_ON_ONCE(user_mode(regs));
 
 	/*
 	 * Catch SYSENTER with TF set and clear DR_STEP. If this hit a
@@ -873,19 +882,24 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 
 	handle_debug(regs, dr6, false);
 
-	if (regs->flags & X86_EFLAGS_IF)
-		trace_hardirqs_on_prepare();
 	instrumentation_end();
-	nmi_exit();
+	idtentry_exit_nmi(regs, irq_state);
 }
 
 static __always_inline void exc_debug_user(struct pt_regs *regs,
 					   unsigned long dr6)
 {
+	/*
+	 * If something gets miswired and we end up here for a kernel mode
+	 * #DB, we will malfunction.
+	 */
+	WARN_ON_ONCE(!user_mode(regs));
+
 	idtentry_enter_user(regs);
 	instrumentation_begin();
 
 	handle_debug(regs, dr6, true);
+
 	instrumentation_end();
 	idtentry_exit_user(regs);
 }
@@ -912,7 +926,7 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 }
 #else
 /* 32 bit does not have separate entry points. */
-DEFINE_IDTENTRY_DEBUG(exc_debug)
+DEFINE_IDTENTRY_RAW(exc_debug)
 {
 	unsigned long dr6, dr7;
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 7f969b2d240f..ec88bbe08a32 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -440,8 +440,11 @@ bool unwind_next_frame(struct unwind_state *state)
 	/*
 	 * Find the orc_entry associated with the text address.
 	 *
-	 * Decrement call return addresses by one so they work for sibling
-	 * calls and calls to noreturn functions.
+	 * For a call frame (as opposed to a signal frame), state->ip points to
+	 * the instruction after the call.  That instruction's stack layout
+	 * could be different from the call instruction's layout, for example
+	 * if the call was to a noreturn function.  So get the ORC data for the
+	 * call instruction itself.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
 	if (!orc) {
@@ -662,6 +665,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		state->sp = task->thread.sp;
 		state->bp = READ_ONCE_NOCHECK(frame->bp);
 		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
+		state->signal = (void *)state->ip == ret_from_fork;
 	}
 
 	if (get_stack_info((unsigned long *)state->sp, state->task,
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3bfc8dd8a43d..9a03e5b23135 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -358,6 +358,7 @@ SECTIONS
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
 		*(.bss..page_aligned)
+		. = ALIGN(PAGE_SIZE);
 		*(BSS_MAIN)
 		BSS_DECRYPTED
 		. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index ff2d0e9ca3bc..cfe83d4ae625 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -7,7 +7,7 @@
 #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
 #define KVM_POSSIBLE_CR4_GUEST_BITS				  \
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)
 
 #define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
 static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 34a7e0533dad..4ce2ddd26c0b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -169,6 +169,18 @@ static void kvm_apic_map_free(struct rcu_head *rcu)
 	kvfree(map);
 }
 
+/*
+ * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock.
+ *
+ * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with
+ * apic_map_lock_held.
+ */
+enum {
+	CLEAN,
+	UPDATE_IN_PROGRESS,
+	DIRTY
+};
+
 void kvm_recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
@@ -176,17 +188,17 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 	int i;
 	u32 max_id = 255; /* enough space for any xAPIC ID */
 
-	if (!kvm->arch.apic_map_dirty) {
-		/*
-		 * Read kvm->arch.apic_map_dirty before
-		 * kvm->arch.apic_map
-		 */
-		smp_rmb();
+	/* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map.  */
+	if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN)
 		return;
-	}
 
 	mutex_lock(&kvm->arch.apic_map_lock);
-	if (!kvm->arch.apic_map_dirty) {
+	/*
+	 * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map
+	 * (if clean) or the APIC registers (if dirty).
+	 */
+	if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty,
+				   DIRTY, UPDATE_IN_PROGRESS) == CLEAN) {
 		/* Someone else has updated the map. */
 		mutex_unlock(&kvm->arch.apic_map_lock);
 		return;
@@ -256,11 +268,11 @@ out:
 			lockdep_is_held(&kvm->arch.apic_map_lock));
 	rcu_assign_pointer(kvm->arch.apic_map, new);
 	/*
-	 * Write kvm->arch.apic_map before
-	 * clearing apic->apic_map_dirty
+	 * Write kvm->arch.apic_map before clearing apic->apic_map_dirty.
+	 * If another update has come in, leave it DIRTY.
 	 */
-	smp_wmb();
-	kvm->arch.apic_map_dirty = false;
+	atomic_cmpxchg_release(&kvm->arch.apic_map_dirty,
+			       UPDATE_IN_PROGRESS, CLEAN);
 	mutex_unlock(&kvm->arch.apic_map_lock);
 
 	if (old)
@@ -282,20 +294,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
 		else
 			static_key_slow_inc(&apic_sw_disabled.key);
 
-		apic->vcpu->kvm->arch.apic_map_dirty = true;
+		atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	}
 }
 
 static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id)
 {
 	kvm_lapic_set_reg(apic, APIC_ID, id << 24);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 {
 	kvm_lapic_set_reg(apic, APIC_LDR, id);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
@@ -311,7 +323,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
 
 	kvm_lapic_set_reg(apic, APIC_ID, id);
 	kvm_lapic_set_reg(apic, APIC_LDR, ldr);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
@@ -1976,7 +1988,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_DFR:
 		if (!apic_x2apic_mode(apic)) {
 			kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
-			apic->vcpu->kvm->arch.apic_map_dirty = true;
+			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 		} else
 			ret = 1;
 		break;
@@ -2183,7 +2195,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
+	if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) ||
 			apic_lvtt_period(apic))
 		return;
 
@@ -2232,7 +2244,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 			static_key_slow_dec_deferred(&apic_hw_disabled);
 		} else {
 			static_key_slow_inc(&apic_hw_disabled.key);
-			vcpu->kvm->arch.apic_map_dirty = true;
+			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 		}
 	}
 
@@ -2273,7 +2285,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	if (!apic)
 		return;
 
-	vcpu->kvm->arch.apic_map_dirty = false;
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
@@ -2567,6 +2578,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 	}
 	memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s));
 
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	kvm_recalculate_apic_map(vcpu->kvm);
 	kvm_apic_set_version(vcpu);
 
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 0ad06bfe2c2c..444bb9c54548 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -222,7 +222,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index fdd05c233308..6d6a0ae7800c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1745,10 +1745,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
  * Emulate arch specific page modification logging for the
  * nested hypervisor
  */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
 {
 	if (kvm_x86_ops.write_log_dirty)
-		return kvm_x86_ops.write_log_dirty(vcpu);
+		return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa);
 
 	return 0;
 }
@@ -4449,7 +4449,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
+			gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index a6d484ea110b..bd70ece1ef8b 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -235,7 +235,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte)
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
-					     int write_fault)
+					     gpa_t addr, int write_fault)
 {
 	unsigned level, index;
 	pt_element_t pte, orig_pte;
@@ -260,7 +260,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 #if PTTYPE == PTTYPE_EPT
-			if (kvm_arch_write_log_dirty(vcpu))
+			if (kvm_arch_write_log_dirty(vcpu, addr))
 				return -EINVAL;
 #endif
 			pte |= PT_GUEST_DIRTY_MASK;
@@ -360,7 +360,6 @@ retry_walk:
 	++walker->level;
 
 	do {
-		gfn_t real_gfn;
 		unsigned long host_addr;
 
 		pt_access = pte_access;
@@ -375,7 +374,7 @@ retry_walk:
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
-		real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
+		real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
 					      nested_access,
 					      &walker->fault);
 
@@ -389,12 +388,10 @@ retry_walk:
 		 * information to fix the exit_qualification or exit_info_1
 		 * fields.
 		 */
-		if (unlikely(real_gfn == UNMAPPED_GVA))
+		if (unlikely(real_gpa == UNMAPPED_GVA))
 			return 0;
 
-		real_gfn = gpa_to_gfn(real_gfn);
-
-		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn,
+		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa),
 					    &walker->pte_writable[walker->level - 1]);
 		if (unlikely(kvm_is_error_hva(host_addr)))
 			goto error;
@@ -457,7 +454,8 @@ retry_walk:
 			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
-		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
+							addr, write_fault);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8ccfa4197d9c..5bbf76189afa 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1090,7 +1090,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 	svm->nested.vmcb = 0;
 	svm->vcpu.arch.hflags = 0;
 
-	if (pause_filter_count) {
+	if (!kvm_pause_in_guest(svm->vcpu.kvm)) {
 		control->pause_filter_count = pause_filter_count;
 		if (pause_filter_thresh)
 			control->pause_filter_thresh = pause_filter_thresh;
@@ -2693,7 +2693,7 @@ static int pause_interception(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	bool in_kernel = (svm_get_cpl(vcpu) == 0);
 
-	if (pause_filter_thresh)
+	if (!kvm_pause_in_guest(vcpu->kvm))
 		grow_ple_window(vcpu);
 
 	kvm_vcpu_on_spin(vcpu, in_kernel);
@@ -3344,7 +3344,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 
 void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
 
-static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	fastpath_t exit_fastpath;
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3780,7 +3780,7 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
-	if (pause_filter_thresh)
+	if (!kvm_pause_in_guest(vcpu->kvm))
 		shrink_ple_window(vcpu);
 }
 
@@ -3958,6 +3958,9 @@ static void svm_vm_destroy(struct kvm *kvm)
 
 static int svm_vm_init(struct kvm *kvm)
 {
+	if (!pause_filter_count || !pause_filter_thresh)
+		kvm->arch.pause_in_guest = true;
+
 	if (avic) {
 		int ret = avic_vm_init(kvm);
 		if (ret)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index d1af20b050a8..11e4df560018 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4109,7 +4109,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 * CR0_GUEST_HOST_MASK is already set in the original vmcs01
 	 * (KVM doesn't change it);
 	 */
-	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
 	vmx_set_cr0(vcpu, vmcs12->host_cr0);
 
 	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
@@ -4259,7 +4259,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 	 */
 	vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
 
-	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
 	vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
 
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
@@ -6079,6 +6079,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	    ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
 		return -EINVAL;
 
+	if (kvm_state->hdr.vmx.flags & ~KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE)
+		return -EINVAL;
+
 	/*
 	 * SMM temporarily disables VMX, so we cannot be in guest mode,
 	 * nor can VMLAUNCH/VMRESUME be pending.  Outside SMM, SMM flags
@@ -6108,9 +6111,16 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	if (ret)
 		return ret;
 
-	/* Empty 'VMXON' state is permitted */
-	if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
-		return 0;
+	/* Empty 'VMXON' state is permitted if no VMCS loaded */
+	if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) {
+		/* See vmx_has_valid_vmcs12.  */
+		if ((kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE) ||
+		    (kvm_state->flags & KVM_STATE_NESTED_EVMCS) ||
+		    (kvm_state->hdr.vmx.vmcs12_pa != -1ull))
+			return -EINVAL;
+		else
+			return 0;
+	}
 
 	if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) {
 		if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa ||
@@ -6176,6 +6186,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 			goto error_guest_mode;
 	}
 
+	vmx->nested.has_preemption_timer_deadline = false;
 	if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) {
 		vmx->nested.has_preemption_timer_deadline = true;
 		vmx->nested.preemption_timer_deadline =
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 758bccc26cf9..197148d76b8f 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -47,6 +47,11 @@ static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu)
 	return to_vmx(vcpu)->nested.cached_shadow_vmcs12;
 }
 
+/*
+ * Note: the same condition is checked against the state provided by userspace
+ * in vmx_set_nested_state; if it is satisfied, the nested state must include
+ * the VMCS12.
+ */
 static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h
index 5c0ff80b85c0..7a3675fddec2 100644
--- a/arch/x86/kvm/vmx/vmcs.h
+++ b/arch/x86/kvm/vmx/vmcs.h
@@ -72,11 +72,24 @@ struct loaded_vmcs {
 	struct vmcs_controls_shadow controls_shadow;
 };
 
+static inline bool is_intr_type(u32 intr_info, u32 type)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK;
+
+	return (intr_info & mask) == (INTR_INFO_VALID_MASK | type);
+}
+
+static inline bool is_intr_type_n(u32 intr_info, u32 type, u8 vector)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK |
+			 INTR_INFO_VECTOR_MASK;
+
+	return (intr_info & mask) == (INTR_INFO_VALID_MASK | type | vector);
+}
+
 static inline bool is_exception_n(u32 intr_info, u8 vector)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+	return is_intr_type_n(intr_info, INTR_TYPE_HARD_EXCEPTION, vector);
 }
 
 static inline bool is_debug(u32 intr_info)
@@ -106,28 +119,23 @@ static inline bool is_gp_fault(u32 intr_info)
 
 static inline bool is_machine_check(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
+	return is_exception_n(intr_info, MC_VECTOR);
 }
 
 /* Undocumented: icebp/int1 */
 static inline bool is_icebp(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+	return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION);
 }
 
 static inline bool is_nmi(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
+	return is_intr_type(intr_info, INTR_TYPE_NMI_INTR);
 }
 
 static inline bool is_external_intr(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
-		== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR);
+	return is_intr_type(intr_info, INTR_TYPE_EXT_INTR);
 }
 
 enum vmcs_field_width {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 36c771728c8c..13745f2a5ecd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -133,9 +133,6 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
 #define KVM_VM_CR0_ALWAYS_ON				\
 	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | 	\
 	 X86_CR0_WP | X86_CR0_PG | X86_CR0_PE)
-#define KVM_CR4_GUEST_OWNED_BITS				      \
-	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD)
 
 #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
@@ -4034,9 +4031,9 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 
 void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
 {
-	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
-	if (enable_ept)
-		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
+	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS;
+	if (!enable_ept)
+		vmx->vcpu.arch.cr4_guest_owned_bits &= ~X86_CR4_PGE;
 	if (is_guest_mode(&vmx->vcpu))
 		vmx->vcpu.arch.cr4_guest_owned_bits &=
 			~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask;
@@ -4333,8 +4330,8 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	/* 22.2.1, 20.8.1 */
 	vm_entry_controls_set(vmx, vmx_vmentry_ctrl());
 
-	vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS;
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS);
+	vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
+	vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits);
 
 	set_cr4_guest_host_mask(vmx);
 
@@ -6606,23 +6603,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host, false);
 }
 
-static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx)
-{
-	u32 host_umwait_control;
-
-	if (!vmx_has_waitpkg(vmx))
-		return;
-
-	host_umwait_control = get_umwait_control_msr();
-
-	if (vmx->msr_ia32_umwait_control != host_umwait_control)
-		add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL,
-			vmx->msr_ia32_umwait_control,
-			host_umwait_control, false);
-	else
-		clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL);
-}
-
 static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6728,9 +6708,7 @@ reenter_guest:
 
 	pt_guest_enter(vmx);
 
-	if (vcpu_to_pmu(vcpu)->version)
-		atomic_switch_perf_msrs(vmx);
-	atomic_switch_umwait_control_msr(vmx);
+	atomic_switch_perf_msrs(vmx);
 
 	if (enable_preemption_timer)
 		vmx_update_hv_timer(vcpu);
@@ -7501,11 +7479,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm)
 	kvm_flush_pml_buffers(kvm);
 }
 
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa, dst;
+	gpa_t dst;
 
 	if (is_guest_mode(vcpu)) {
 		WARN_ON_ONCE(vmx->nested.pml_full);
@@ -7524,7 +7502,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		gpa &= ~0xFFFull;
 		dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;
 
 		if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 8a83b5edc820..639798e4a6ca 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -288,8 +288,6 @@ struct vcpu_vmx {
 
 	u64 current_tsc_ratio;
 
-	u32 host_pkru;
-
 	unsigned long host_debugctlmsr;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00c88c2f34e4..88c593f83b28 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -975,6 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
+		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
+			return 1;
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
@@ -2693,6 +2695,9 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 	if (data & 0x30)
 		return 1;
 
+	if (!lapic_in_kernel(vcpu))
+		return 1;
+
 	vcpu->arch.apf.msr_en_val = data;
 
 	if (!kvm_pv_async_pf_enabled(vcpu)) {
@@ -2856,7 +2861,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
@@ -3196,7 +3201,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_APICBASE:
 		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 	case MSR_IA32_TSCDEADLINE:
 		msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu);
@@ -4603,7 +4608,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EINVAL;
 		user_tsc_khz = (u32)arg;
 
-		if (user_tsc_khz >= kvm_max_guest_tsc_khz)
+		if (kvm_has_tsc_control &&
+		    user_tsc_khz >= kvm_max_guest_tsc_khz)
 			goto out;
 
 		if (user_tsc_khz == 0)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 56b243b14c3a..bbcc05bcefad 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -8,6 +8,8 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
+.pushsection .noinstr.text, "ax"
+
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
  * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
@@ -184,6 +186,8 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	retq
 SYM_FUNC_END(memcpy_orig)
 
+.popsection
+
 #ifndef CONFIG_UML
 
 MCSAFE_TEST_CTL
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index fff28c6f73a2..b0dfac3d3df7 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 	asm volatile(
 		"	testq  %[size8],%[size8]\n"
 		"	jz     4f\n"
+		"	.align 16\n"
 		"0:	movq $0,(%[dst])\n"
 		"	addq   $8,%[dst]\n"
 		"	decl %%ecx ; jnz   0b\n"
diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S
index 3b2b58164ec1..40526dd85137 100644
--- a/arch/x86/math-emu/wm_sqrt.S
+++ b/arch/x86/math-emu/wm_sqrt.S
@@ -209,7 +209,7 @@ sqrt_stage_2_finish:
 
 #ifdef PARANOID
 /* It should be possible to get here only if the arg is ffff....ffff */
-	cmp	$0xffffffff,FPU_fsqrt_arg_1
+	cmpl	$0xffffffff,FPU_fsqrt_arg_1
 	jnz	sqrt_stage_2_error
 #endif /* PARANOID */
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 66be9bd60307..5e41949453cc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -99,7 +99,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
 		return !instr_lo || (instr_lo>>1) == 1;
 	case 0x00:
 		/* Prefetch instruction is 0x0F0D or 0x0F18 */
-		if (probe_kernel_address(instr, opcode))
+		if (get_kernel_nofault(opcode, instr))
 			return 0;
 
 		*prefetch = (instr_lo == 0xF) &&
@@ -133,7 +133,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
 	while (instr < max_instr) {
 		unsigned char opcode;
 
-		if (probe_kernel_address(instr, opcode))
+		if (get_kernel_nofault(opcode, instr))
 			break;
 
 		instr++;
@@ -301,7 +301,7 @@ static int bad_address(void *p)
 {
 	unsigned long dummy;
 
-	return probe_kernel_address((unsigned long *)p, dummy);
+	return get_kernel_nofault(dummy, (unsigned long *)p);
 }
 
 static void dump_pagetable(unsigned long address)
@@ -442,7 +442,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
 		return;
 	}
 
-	if (probe_kernel_read(&desc, (void *)(gdt->address + offset),
+	if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset),
 			      sizeof(struct ldttss_desc))) {
 		pr_alert("%s: 0x%hx -- GDT entry is not readable\n",
 			 name, index);
@@ -1377,7 +1377,7 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code,
 DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 {
 	unsigned long address = read_cr2();
-	bool rcu_exit;
+	idtentry_state_t state;
 
 	prefetchw(&current->mm->mmap_lock);
 
@@ -1412,11 +1412,11 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 	 * code reenabled RCU to avoid subsequent wreckage which helps
 	 * debugability.
 	 */
-	rcu_exit = idtentry_enter_cond_rcu(regs);
+	state = idtentry_enter(regs);
 
 	instrumentation_begin();
 	handle_page_fault(regs, error_code, address);
 	instrumentation_end();
 
-	idtentry_exit_cond_rcu(regs, rcu_exit);
+	idtentry_exit(regs, state);
 }
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bda909e3e37e..8b4afad84f4a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -737,7 +737,7 @@ static void __init test_wp_bit(void)
 
 	__set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO);
 
-	if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
+	if (copy_to_kernel_nofault((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
 		clear_fixmap(FIX_WP_TEST);
 		printk(KERN_CONT "Ok.\n");
 		return;
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index e1d7d7477c22..92ec176a7293 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -9,7 +9,7 @@ static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
 	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
 }
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	unsigned long vaddr = (unsigned long)unsafe_src;
 
@@ -22,7 +22,7 @@ bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
 	       canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr;
 }
 #else
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	return (unsigned long)unsafe_src >= TASK_SIZE_MAX;
 }
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 77e04304a2a7..d1b2a889f035 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -135,7 +135,7 @@ static inline void cpa_inc_2m_checked(void)
 
 static inline void cpa_inc_4k_install(void)
 {
-	cpa_4k_install++;
+	data_race(cpa_4k_install++);
 }
 
 static inline void cpa_inc_lp_sameprot(int level)
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 9c97d814125e..4f15280732ed 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -302,7 +302,7 @@ static const struct pci_raw_ops *__init pci_find_bios(void)
 	     check <= (union bios32 *) __va(0xffff0);
 	     ++check) {
 		long sig;
-		if (probe_kernel_address(&check->fields.signature, sig))
+		if (get_kernel_nofault(sig, &check->fields.signature))
 			continue;
 
 		if (check->fields.signature != BIOS32_SIGNATURE)
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index b8f7f193f383..30bd5714a3d4 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -287,8 +287,8 @@ void intel_scu_devices_create(void)
 
 		adapter = i2c_get_adapter(i2c_bus[i]);
 		if (adapter) {
-			client = i2c_new_device(adapter, i2c_devs[i]);
-			if (!client)
+			client = i2c_new_client_device(adapter, i2c_devs[i]);
+			if (IS_ERR(client))
 				pr_err("can't create i2c device %s\n",
 					i2c_devs[i]->type);
 		} else
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index fc13cbbb2dce..abb6075397f0 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -167,9 +167,10 @@ static struct irq_domain *uv_get_irq_domain(void)
 		goto out;
 
 	uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL);
-	irq_domain_free_fwnode(fn);
 	if (uv_domain)
 		uv_domain->parent = x86_vector_domain;
+	else
+		irq_domain_free_fwnode(fn);
 out:
 	mutex_unlock(&uv_lock);
 
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 7c65102debaf..db1378c6ff26 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -193,6 +193,8 @@ static void fix_processor_context(void)
  */
 static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
+	struct cpuinfo_x86 *c;
+
 	if (ctxt->misc_enable_saved)
 		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
 	/*
@@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	mtrr_bp_restore();
 	perf_restore_debug_store();
 	msr_restore_context(ctxt);
+
+	c = &cpu_data(smp_processor_id());
+	if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL))
+		init_ia32_feat_ctl(c);
 }
 
 /* Needed by apm.c */
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index b04e6e72a592..088bd764e0b7 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -34,6 +34,7 @@ KCOV_INSTRUMENT := n
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
 PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
 PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
+PURGATORY_CFLAGS += $(call cc-option,-fno-stack-protector)
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
 # in turn leaves some undefined symbols like __fentry__ in purgatory and not
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 33b309d65955..c46b9f2e732f 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -386,7 +386,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 
 	preempt_disable();
 
-	probe_kernel_read(&dummy, v, 1);
+	copy_from_kernel_nofault(&dummy, v, 1);
 
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
@@ -598,6 +598,26 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 }
 
 #ifdef CONFIG_X86_64
+void noist_exc_debug(struct pt_regs *regs);
+
+DEFINE_IDTENTRY_RAW(xenpv_exc_nmi)
+{
+	/* On Xen PV, NMI doesn't use IST.  The C part is the sane as native. */
+	exc_nmi(regs);
+}
+
+DEFINE_IDTENTRY_RAW(xenpv_exc_debug)
+{
+	/*
+	 * There's no IST on Xen PV, but we still need to dispatch
+	 * to the correct handler.
+	 */
+	if (user_mode(regs))
+		noist_exc_debug(regs);
+	else
+		exc_debug(regs);
+}
+
 struct trap_array_entry {
 	void (*orig)(void);
 	void (*xen)(void);
@@ -609,18 +629,18 @@ struct trap_array_entry {
 	.xen		= xen_asm_##func,		\
 	.ist_okay	= ist_ok }
 
-#define TRAP_ENTRY_REDIR(func, xenfunc, ist_ok) {	\
+#define TRAP_ENTRY_REDIR(func, ist_ok) {		\
 	.orig		= asm_##func,			\
-	.xen		= xen_asm_##xenfunc,		\
+	.xen		= xen_asm_xenpv_##func,		\
 	.ist_okay	= ist_ok }
 
 static struct trap_array_entry trap_array[] = {
-	TRAP_ENTRY_REDIR(exc_debug, exc_xendebug,	true  ),
+	TRAP_ENTRY_REDIR(exc_debug,			true  ),
 	TRAP_ENTRY(exc_double_fault,			true  ),
 #ifdef CONFIG_X86_MCE
 	TRAP_ENTRY(exc_machine_check,			true  ),
 #endif
-	TRAP_ENTRY_REDIR(exc_nmi, exc_xennmi,		true  ),
+	TRAP_ENTRY_REDIR(exc_nmi,			true  ),
 	TRAP_ENTRY(exc_int3,				false ),
 	TRAP_ENTRY(exc_overflow,			false ),
 #ifdef CONFIG_IA32_EMULATION
@@ -850,6 +870,17 @@ static void xen_load_sp0(unsigned long sp0)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static void xen_invalidate_io_bitmap(void)
+{
+	struct physdev_set_iobitmap iobitmap = {
+		.bitmap = 0,
+		.nr_ports = 0,
+	};
+
+	native_tss_invalidate_io_bitmap();
+	HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap);
+}
+
 static void xen_update_io_bitmap(void)
 {
 	struct physdev_set_iobitmap iobitmap;
@@ -1079,6 +1110,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.load_sp0 = xen_load_sp0,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	.invalidate_io_bitmap = xen_invalidate_io_bitmap,
 	.update_io_bitmap = xen_update_io_bitmap,
 #endif
 	.io_delay = xen_io_delay,
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 5d252aaeade8..aab1d99b2b48 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -29,10 +29,9 @@ _ASM_NOKPROBE(xen_\name)
 .endm
 
 xen_pv_trap asm_exc_divide_error
-xen_pv_trap asm_exc_debug
-xen_pv_trap asm_exc_xendebug
+xen_pv_trap asm_xenpv_exc_debug
 xen_pv_trap asm_exc_int3
-xen_pv_trap asm_exc_xennmi
+xen_pv_trap asm_xenpv_exc_nmi
 xen_pv_trap asm_exc_overflow
 xen_pv_trap asm_exc_bounds
 xen_pv_trap asm_exc_invalid_op
@@ -161,10 +160,22 @@ SYM_FUNC_END(xen_syscall32_target)
 
 /* 32-bit compat sysenter target */
 SYM_FUNC_START(xen_sysenter_target)
-	mov 0*8(%rsp), %rcx
-	mov 1*8(%rsp), %r11
-	mov 5*8(%rsp), %rsp
-	jmp entry_SYSENTER_compat
+	/*
+	 * NB: Xen is polite and clears TF from EFLAGS for us.  This means
+	 * that we don't need to guard against single step exceptions here.
+	 */
+	popq %rcx
+	popq %r11
+
+	/*
+	 * Neither Xen nor the kernel really knows what the old SS and
+	 * CS were.  The kernel expects __USER32_DS and __USER32_CS, so
+	 * report those values even though Xen will guess its own values.
+	 */
+	movq $__USER32_DS, 4*8(%rsp)
+	movq $__USER32_CS, 1*8(%rsp)
+
+	jmp entry_SYSENTER_compat_after_hwframe
 SYM_FUNC_END(xen_sysenter_target)
 
 #else /* !CONFIG_IA32_EMULATION */
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 3e7c6134ed32..744c2f463845 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 /*
  * This Xtensa implementation assumes that the right mechanism
  * for exclusion is for locking interrupts to level EXCM_LEVEL.
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index d8292cc9ebdf..243a5fe79d3c 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -57,7 +57,7 @@ static inline
 __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 				   int len, __wsum sum, int *err_ptr)
 {
-	if (access_ok(dst, len))
+	if (access_ok(src, len))
 		return csum_partial_copy_generic((__force const void *)src, dst,
 					len, sum, err_ptr, NULL);
 	if (len)
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 9bae79f70301..99fcd63ce597 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -362,9 +362,7 @@ irqreturn_t xtensa_pmu_irq_handler(int irq, void *dev_id)
 	struct xtensa_pmu_events *ev = this_cpu_ptr(&xtensa_pmu_events);
 	unsigned i;
 
-	for (i = find_first_bit(ev->used_mask, XCHAL_NUM_PERF_COUNTERS);
-	     i < XCHAL_NUM_PERF_COUNTERS;
-	     i = find_next_bit(ev->used_mask, XCHAL_NUM_PERF_COUNTERS, i + 1)) {
+	for_each_set_bit(i, ev->used_mask, XCHAL_NUM_PERF_COUNTERS) {
 		uint32_t v = get_er(XTENSA_PMU_PMSTAT(i));
 		struct perf_event *event = ev->event[i];
 		struct hw_perf_event *hwc = &event->hw;
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index d9204dc2656e..be2c78f71695 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -724,7 +724,8 @@ c_start(struct seq_file *f, loff_t *pos)
 static void *
 c_next(struct seq_file *f, void *v, loff_t *pos)
 {
-	return NULL;
+	++*pos;
+	return c_start(f, pos);
 }
 
 static void
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 4092555828b1..24cf6972eace 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -87,13 +87,13 @@ void __xtensa_libgcc_window_spill(void)
 }
 EXPORT_SYMBOL(__xtensa_libgcc_window_spill);
 
-unsigned long __sync_fetch_and_and_4(unsigned long *p, unsigned long v)
+unsigned int __sync_fetch_and_and_4(volatile void *p, unsigned int v)
 {
 	BUG();
 }
 EXPORT_SYMBOL(__sync_fetch_and_and_4);
 
-unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v)
+unsigned int __sync_fetch_and_or_4(volatile void *p, unsigned int v)
 {
 	BUG();
 }
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 49322b66cda9..3447556d276d 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -101,9 +101,9 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
 	spin_unlock(&dev->lock);
 }
 
-static blk_qc_t simdisk_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t simdisk_submit_bio(struct bio *bio)
 {
-	struct simdisk *dev = q->queuedata;
+	struct simdisk *dev = bio->bi_disk->private_data;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 	sector_t sector = bio->bi_iter.bi_sector;
@@ -127,8 +127,6 @@ static int simdisk_open(struct block_device *bdev, fmode_t mode)
 	struct simdisk *dev = bdev->bd_disk->private_data;
 
 	spin_lock(&dev->lock);
-	if (!dev->users)
-		check_disk_change(bdev);
 	++dev->users;
 	spin_unlock(&dev->lock);
 	return 0;
@@ -144,6 +142,7 @@ static void simdisk_release(struct gendisk *disk, fmode_t mode)
 
 static const struct block_device_operations simdisk_ops = {
 	.owner		= THIS_MODULE,
+	.submit_bio	= simdisk_submit_bio,
 	.open		= simdisk_open,
 	.release	= simdisk_release,
 };
@@ -267,14 +266,12 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
 	spin_lock_init(&dev->lock);
 	dev->users = 0;
 
-	dev->queue = blk_alloc_queue(simdisk_make_request, NUMA_NO_NODE);
+	dev->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (dev->queue == NULL) {
 		pr_err("blk_alloc_queue failed\n");
 		goto out_alloc_queue;
 	}
 
-	dev->queue->queuedata = dev;
-
 	dev->gd = alloc_disk(SIMDISK_MINORS);
 	if (dev->gd == NULL) {
 		pr_err("alloc_disk failed\n");