summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig4
-rw-r--r--arch/alpha/include/asm/thread_info.h3
-rw-r--r--arch/alpha/include/uapi/asm/Kbuild1
-rw-r--r--arch/alpha/kernel/sys_sio.c35
-rw-r--r--arch/alpha/lib/ev6-memset.S12
-rw-r--r--arch/arc/boot/dts/axc003.dtsi8
-rw-r--r--arch/arc/boot/dts/axc003_idu.dtsi8
-rw-r--r--arch/arc/boot/dts/hsdk.dts8
-rw-r--r--arch/arc/configs/hsdk_defconfig5
-rw-r--r--arch/arc/include/asm/thread_info.h3
-rw-r--r--arch/arc/include/asm/uaccess.h5
-rw-r--r--arch/arc/include/uapi/asm/Kbuild1
-rw-r--r--arch/arc/kernel/setup.c2
-rw-r--r--arch/arc/kernel/stacktrace.c2
-rw-r--r--arch/arc/kernel/traps.c28
-rw-r--r--arch/arc/kernel/troubleshoot.c3
-rw-r--r--arch/arc/plat-axs10x/axs10x.c18
-rw-r--r--arch/arc/plat-hsdk/platform.c42
-rw-r--r--arch/arm/boot/dts/am33xx.dtsi2
-rw-r--r--arch/arm/boot/dts/am4372.dtsi6
-rw-r--r--arch/arm/boot/dts/am437x-cm-t43.dts4
-rw-r--r--arch/arm/boot/dts/armada-385-db-ap.dts1
-rw-r--r--arch/arm/boot/dts/armada-385-linksys.dtsi1
-rw-r--r--arch/arm/boot/dts/armada-385-synology-ds116.dts2
-rw-r--r--arch/arm/boot/dts/armada-388-gp.dts2
-rw-r--r--arch/arm/boot/dts/aspeed-g4.dtsi2
-rw-r--r--arch/arm/boot/dts/at91-tse850-3.dts1
-rw-r--r--arch/arm/boot/dts/bcm-nsp.dtsi4
-rw-r--r--arch/arm/boot/dts/bcm2836.dtsi14
-rw-r--r--arch/arm/boot/dts/bcm2837.dtsi12
-rw-r--r--arch/arm/boot/dts/bcm283x.dtsi2
-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/da850-lcdk.dts4
-rw-r--r--arch/arm/boot/dts/da850-lego-ev3.dts4
-rw-r--r--arch/arm/boot/dts/dm814x.dtsi2
-rw-r--r--arch/arm/boot/dts/exynos5800-peach-pi.dts4
-rw-r--r--arch/arm/boot/dts/imx53.dtsi9
-rw-r--r--arch/arm/boot/dts/imx6ul.dtsi2
-rw-r--r--arch/arm/boot/dts/kirkwood-openblocks_a7.dts10
-rw-r--r--arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts3
-rw-r--r--arch/arm/boot/dts/logicpd-som-lv.dtsi17
-rw-r--r--arch/arm/boot/dts/ls1021a-qds.dts2
-rw-r--r--arch/arm/boot/dts/ls1021a-twr.dts2
-rw-r--r--arch/arm/boot/dts/meson.dtsi18
-rw-r--r--arch/arm/boot/dts/nspire.dtsi1
-rw-r--r--arch/arm/boot/dts/omap2420-n8x0-common.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-beagle-xm.dts1
-rw-r--r--arch/arm/boot/dts/omap3-beagle.dts1
-rw-r--r--arch/arm/boot/dts/omap3-cm-t3x.dtsi2
-rw-r--r--arch/arm/boot/dts/omap3-evm-common.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-gta04.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-igep.dtsi30
-rw-r--r--arch/arm/boot/dts/omap3-igep0020-common.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-igep0030-common.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-lilly-a83x.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-n900.dts1
-rw-r--r--arch/arm/boot/dts/omap3-n950-n9.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-overo-base.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-pandora-common.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-tao3530.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3430-sdp.dts1
-rw-r--r--arch/arm/boot/dts/omap4-droid4-xt894.dts1
-rw-r--r--arch/arm/boot/dts/omap4-duovero.dtsi1
-rw-r--r--arch/arm/boot/dts/omap4-panda-common.dtsi1
-rw-r--r--arch/arm/boot/dts/omap4-var-som-om44.dtsi1
-rw-r--r--arch/arm/boot/dts/omap4.dtsi5
-rw-r--r--arch/arm/boot/dts/omap5-board-common.dtsi2
-rw-r--r--arch/arm/boot/dts/omap5-cm-t54.dts2
-rw-r--r--arch/arm/boot/dts/omap5.dtsi1
-rw-r--r--arch/arm/boot/dts/r8a7790.dtsi1
-rw-r--r--arch/arm/boot/dts/r8a7792.dtsi1
-rw-r--r--arch/arm/boot/dts/r8a7793.dtsi1
-rw-r--r--arch/arm/boot/dts/r8a7794.dtsi1
-rw-r--r--arch/arm/boot/dts/rk3066a-marsboard.dts4
-rw-r--r--arch/arm/boot/dts/rk3288.dtsi2
-rw-r--r--arch/arm/boot/dts/sun4i-a10.dtsi6
-rw-r--r--arch/arm/boot/dts/sun5i-a10s.dtsi4
-rw-r--r--arch/arm/boot/dts/sun6i-a31.dtsi4
-rw-r--r--arch/arm/boot/dts/sun7i-a20.dtsi6
-rw-r--r--arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts1
-rw-r--r--arch/arm/boot/dts/tango4-common.dtsi1
-rw-r--r--arch/arm/boot/dts/vf610-zii-dev-rev-c.dts6
-rw-r--r--arch/arm/configs/aspeed_g4_defconfig1
-rw-r--r--arch/arm/configs/aspeed_g5_defconfig1
-rw-r--r--arch/arm/configs/hisi_defconfig1
-rw-r--r--arch/arm/configs/multi_v7_defconfig1
-rw-r--r--arch/arm/configs/mvebu_v7_defconfig3
-rw-r--r--arch/arm/configs/pxa_defconfig1
-rw-r--r--arch/arm/configs/sama5_defconfig1
-rw-r--r--arch/arm/configs/sunxi_defconfig2
-rw-r--r--arch/arm/configs/tegra_defconfig1
-rw-r--r--arch/arm/configs/vt8500_v6_v7_defconfig1
-rw-r--r--arch/arm/include/asm/kvm_arm.h3
-rw-r--r--arch/arm/include/asm/kvm_host.h10
-rw-r--r--arch/arm/include/asm/kvm_mmu.h17
-rw-r--r--arch/arm/include/asm/pgtable-3level.h1
-rw-r--r--arch/arm/include/asm/thread_info.h3
-rw-r--r--arch/arm/include/uapi/asm/Kbuild1
-rw-r--r--arch/arm/include/uapi/asm/siginfo.h13
-rw-r--r--arch/arm/kernel/entry-header.S4
-rw-r--r--arch/arm/kernel/ptrace.c8
-rw-r--r--arch/arm/kernel/traps.c1
-rw-r--r--arch/arm/lib/csumpartialcopyuser.S4
-rw-r--r--arch/arm/mach-davinci/dm365.c29
-rw-r--r--arch/arm/mach-meson/platsmp.c2
-rw-r--r--arch/arm/mach-omap2/Makefile3
-rw-r--r--arch/arm/mach-omap2/cm_common.c6
-rw-r--r--arch/arm/mach-omap2/gpmc-onenand.c409
-rw-r--r--arch/arm/mach-omap2/omap-secure.c21
-rw-r--r--arch/arm/mach-omap2/omap-secure.h4
-rw-r--r--arch/arm/mach-omap2/omap_device.c10
-rw-r--r--arch/arm/mach-omap2/omap_hwmod_3xxx_data.c1
-rw-r--r--arch/arm/mach-omap2/pm.h4
-rw-r--r--arch/arm/mach-omap2/pm34xx.c13
-rw-r--r--arch/arm/mach-omap2/prcm-common.h1
-rw-r--r--arch/arm/mach-omap2/prm33xx.c12
-rw-r--r--arch/arm/mach-omap2/sleep34xx.S26
-rw-r--r--arch/arm/net/bpf_jit_32.c225
-rw-r--r--arch/arm/vfp/vfpmodule.c2
-rw-r--r--arch/arm64/Kconfig103
-rw-r--r--arch/arm64/Makefile3
-rw-r--r--arch/arm64/boot/dts/Makefile2
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts1
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts1
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts3
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi11
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts2
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi1
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi4
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl.dtsi6
-rw-r--r--arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi13
-rw-r--r--arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi9
-rw-r--r--arch/arm64/boot/dts/renesas/salvator-common.dtsi1
-rw-r--r--arch/arm64/boot/dts/renesas/ulcb.dtsi1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328-rock64.dts2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328.dtsi2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi11
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts1
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts1
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts3
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi4
-rw-r--r--arch/arm64/configs/defconfig2
-rw-r--r--arch/arm64/include/asm/alternative.h2
-rw-r--r--arch/arm64/include/asm/arm_dsu_pmu.h129
-rw-r--r--arch/arm64/include/asm/asm-uaccess.h42
-rw-r--r--arch/arm64/include/asm/assembler.h75
-rw-r--r--arch/arm64/include/asm/cacheflush.h2
-rw-r--r--arch/arm64/include/asm/compat.h64
-rw-r--r--arch/arm64/include/asm/cpucaps.h6
-rw-r--r--arch/arm64/include/asm/cpufeature.h3
-rw-r--r--arch/arm64/include/asm/cputype.h11
-rw-r--r--arch/arm64/include/asm/efi.h16
-rw-r--r--arch/arm64/include/asm/esr.h20
-rw-r--r--arch/arm64/include/asm/exception.h14
-rw-r--r--arch/arm64/include/asm/fixmap.h5
-rw-r--r--arch/arm64/include/asm/fpsimd.h2
-rw-r--r--arch/arm64/include/asm/kernel-pgtable.h59
-rw-r--r--arch/arm64/include/asm/kvm_arm.h5
-rw-r--r--arch/arm64/include/asm/kvm_asm.h2
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h17
-rw-r--r--arch/arm64/include/asm/kvm_host.h20
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h59
-rw-r--r--arch/arm64/include/asm/mmu.h49
-rw-r--r--arch/arm64/include/asm/mmu_context.h71
-rw-r--r--arch/arm64/include/asm/module.h46
-rw-r--r--arch/arm64/include/asm/percpu.h11
-rw-r--r--arch/arm64/include/asm/perf_event.h2
-rw-r--r--arch/arm64/include/asm/pgalloc.h6
-rw-r--r--arch/arm64/include/asm/pgtable-hwdef.h32
-rw-r--r--arch/arm64/include/asm/pgtable-prot.h21
-rw-r--r--arch/arm64/include/asm/pgtable.h99
-rw-r--r--arch/arm64/include/asm/proc-fns.h6
-rw-r--r--arch/arm64/include/asm/processor.h1
-rw-r--r--arch/arm64/include/asm/sdei.h57
-rw-r--r--arch/arm64/include/asm/sections.h1
-rw-r--r--arch/arm64/include/asm/sparsemem.h2
-rw-r--r--arch/arm64/include/asm/stacktrace.h3
-rw-r--r--arch/arm64/include/asm/sysreg.h92
-rw-r--r--arch/arm64/include/asm/thread_info.h2
-rw-r--r--arch/arm64/include/asm/tlbflush.h16
-rw-r--r--arch/arm64/include/asm/traps.h54
-rw-r--r--arch/arm64/include/asm/uaccess.h40
-rw-r--r--arch/arm64/include/asm/vmap_stack.h28
-rw-r--r--arch/arm64/include/uapi/asm/bpf_perf_event.h9
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h1
-rw-r--r--arch/arm64/include/uapi/asm/siginfo.h21
-rw-r--r--arch/arm64/kernel/Makefile8
-rw-r--r--arch/arm64/kernel/acpi.c2
-rw-r--r--arch/arm64/kernel/alternative.c9
-rw-r--r--arch/arm64/kernel/asm-offsets.c12
-rw-r--r--arch/arm64/kernel/bpi.S87
-rw-r--r--arch/arm64/kernel/cpu-reset.S1
-rw-r--r--arch/arm64/kernel/cpu_errata.c192
-rw-r--r--arch/arm64/kernel/cpu_ops.c6
-rw-r--r--arch/arm64/kernel/cpufeature.c149
-rw-r--r--arch/arm64/kernel/cpuidle.c8
-rw-r--r--arch/arm64/kernel/cpuinfo.c1
-rw-r--r--arch/arm64/kernel/debug-monitors.c13
-rw-r--r--arch/arm64/kernel/efi-entry.S2
-rw-r--r--arch/arm64/kernel/efi.c4
-rw-r--r--arch/arm64/kernel/entry.S396
-rw-r--r--arch/arm64/kernel/fpsimd.c61
-rw-r--r--arch/arm64/kernel/ftrace-mod.S18
-rw-r--r--arch/arm64/kernel/ftrace.c14
-rw-r--r--arch/arm64/kernel/head.S246
-rw-r--r--arch/arm64/kernel/hibernate-asm.S12
-rw-r--r--arch/arm64/kernel/hibernate.c5
-rw-r--r--arch/arm64/kernel/hw_breakpoint.c2
-rw-r--r--arch/arm64/kernel/irq.c13
-rw-r--r--arch/arm64/kernel/module-plts.c50
-rw-r--r--arch/arm64/kernel/module.lds1
-rw-r--r--arch/arm64/kernel/perf_event.c6
-rw-r--r--arch/arm64/kernel/process.c21
-rw-r--r--arch/arm64/kernel/ptrace.c42
-rw-r--r--arch/arm64/kernel/relocate_kernel.S1
-rw-r--r--arch/arm64/kernel/sdei.c235
-rw-r--r--arch/arm64/kernel/signal.c7
-rw-r--r--arch/arm64/kernel/signal32.c85
-rw-r--r--arch/arm64/kernel/smp.c11
-rw-r--r--arch/arm64/kernel/suspend.c4
-rw-r--r--arch/arm64/kernel/topology.c16
-rw-r--r--arch/arm64/kernel/traps.c51
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S27
-rw-r--r--arch/arm64/kvm/debug.c21
-rw-r--r--arch/arm64/kvm/handle_exit.c93
-rw-r--r--arch/arm64/kvm/hyp-init.S31
-rw-r--r--arch/arm64/kvm/hyp/debug-sr.c3
-rw-r--r--arch/arm64/kvm/hyp/entry.S35
-rw-r--r--arch/arm64/kvm/hyp/hyp-entry.S18
-rw-r--r--arch/arm64/kvm/hyp/s2-setup.c2
-rw-r--r--arch/arm64/kvm/hyp/switch.c97
-rw-r--r--arch/arm64/kvm/hyp/sysreg-sr.c22
-rw-r--r--arch/arm64/kvm/inject_fault.c13
-rw-r--r--arch/arm64/kvm/sys_regs.c11
-rw-r--r--arch/arm64/lib/clear_user.S4
-rw-r--r--arch/arm64/lib/copy_from_user.S4
-rw-r--r--arch/arm64/lib/copy_in_user.S4
-rw-r--r--arch/arm64/lib/copy_to_user.S4
-rw-r--r--arch/arm64/lib/tishift.S8
-rw-r--r--arch/arm64/mm/cache.S4
-rw-r--r--arch/arm64/mm/context.c85
-rw-r--r--arch/arm64/mm/dump.c2
-rw-r--r--arch/arm64/mm/fault.c136
-rw-r--r--arch/arm64/mm/init.c49
-rw-r--r--arch/arm64/mm/mmu.c47
-rw-r--r--arch/arm64/mm/pgd.c10
-rw-r--r--arch/arm64/mm/proc.S66
-rw-r--r--arch/arm64/net/bpf_jit_comp.c20
-rw-r--r--arch/arm64/xen/hypercall.S4
-rw-r--r--arch/blackfin/include/asm/thread_info.h2
-rw-r--r--arch/blackfin/include/uapi/asm/Kbuild1
-rw-r--r--arch/blackfin/include/uapi/asm/siginfo.h34
-rw-r--r--arch/c6x/include/asm/thread_info.h3
-rw-r--r--arch/c6x/include/uapi/asm/Kbuild1
-rw-r--r--arch/cris/include/asm/processor.h9
-rw-r--r--arch/cris/include/asm/thread_info.h9
-rw-r--r--arch/cris/include/uapi/asm/Kbuild1
-rw-r--r--arch/cris/kernel/vmlinux.lds.S1
-rw-r--r--arch/frv/include/asm/thread_info.h3
-rw-r--r--arch/frv/include/uapi/asm/Kbuild3
-rw-r--r--arch/frv/include/uapi/asm/siginfo.h13
-rw-r--r--arch/h8300/include/asm/thread_info.h3
-rw-r--r--arch/h8300/include/uapi/asm/Kbuild1
-rw-r--r--arch/hexagon/include/asm/thread_info.h3
-rw-r--r--arch/hexagon/include/uapi/asm/Kbuild1
-rw-r--r--arch/hexagon/kernel/vmlinux.lds.S2
-rw-r--r--arch/ia64/Kconfig2
-rw-r--r--arch/ia64/Makefile2
-rw-r--r--arch/ia64/include/asm/atomic.h37
-rw-r--r--arch/ia64/include/asm/thread_info.h4
-rw-r--r--arch/ia64/include/uapi/asm/Kbuild1
-rw-r--r--arch/ia64/include/uapi/asm/siginfo.h96
-rw-r--r--arch/ia64/kernel/Makefile2
-rw-r--r--arch/ia64/kernel/acpi.c5
-rw-r--r--arch/ia64/kernel/init_task.c44
-rw-r--r--arch/ia64/kernel/signal.c52
-rw-r--r--arch/ia64/kernel/time.c2
-rw-r--r--arch/ia64/kernel/vmlinux.lds.S1
-rw-r--r--arch/m32r/include/asm/thread_info.h3
-rw-r--r--arch/m32r/include/uapi/asm/Kbuild1
-rw-r--r--arch/m32r/kernel/traps.c1
-rw-r--r--arch/m68k/configs/amiga_defconfig4
-rw-r--r--arch/m68k/configs/apollo_defconfig4
-rw-r--r--arch/m68k/configs/atari_defconfig4
-rw-r--r--arch/m68k/configs/bvme6000_defconfig4
-rw-r--r--arch/m68k/configs/hp300_defconfig4
-rw-r--r--arch/m68k/configs/mac_defconfig4
-rw-r--r--arch/m68k/configs/multi_defconfig4
-rw-r--r--arch/m68k/configs/mvme147_defconfig4
-rw-r--r--arch/m68k/configs/mvme16x_defconfig4
-rw-r--r--arch/m68k/configs/q40_defconfig4
-rw-r--r--arch/m68k/configs/stmark2_defconfig1
-rw-r--r--arch/m68k/configs/sun3_defconfig4
-rw-r--r--arch/m68k/configs/sun3x_defconfig4
-rw-r--r--arch/m68k/include/asm/macintosh.h9
-rw-r--r--arch/m68k/include/asm/thread_info.h4
-rw-r--r--arch/m68k/include/uapi/asm/Kbuild1
-rw-r--r--arch/m68k/kernel/vmlinux-nommu.lds2
-rw-r--r--arch/m68k/kernel/vmlinux-std.lds2
-rw-r--r--arch/m68k/kernel/vmlinux-sun3.lds2
-rw-r--r--arch/m68k/mac/config.c110
-rw-r--r--arch/m68k/mac/oss.c67
-rw-r--r--arch/m68k/mm/fault.c3
-rw-r--r--arch/metag/include/asm/thread_info.h3
-rw-r--r--arch/metag/include/uapi/asm/Kbuild1
-rw-r--r--arch/metag/include/uapi/asm/siginfo.h7
-rw-r--r--arch/metag/kernel/traps.c2
-rw-r--r--arch/microblaze/include/asm/mmu_context_mm.h1
-rw-r--r--arch/microblaze/include/asm/thread_info.h3
-rw-r--r--arch/microblaze/include/uapi/asm/Kbuild1
-rw-r--r--arch/mips/Kconfig12
-rw-r--r--arch/mips/Kconfig.debug14
-rw-r--r--arch/mips/ar7/platform.c2
-rw-r--r--arch/mips/ath25/devices.c2
-rw-r--r--arch/mips/include/asm/Kbuild1
-rw-r--r--arch/mips/include/asm/compat.h73
-rw-r--r--arch/mips/include/asm/pgtable.h2
-rw-r--r--arch/mips/include/asm/serial.h22
-rw-r--r--arch/mips/include/asm/thread_info.h3
-rw-r--r--arch/mips/include/uapi/asm/Kbuild1
-rw-r--r--arch/mips/include/uapi/asm/siginfo.h86
-rw-r--r--arch/mips/kernel/cps-vec.S2
-rw-r--r--arch/mips/kernel/mips-cm.c1
-rw-r--r--arch/mips/kernel/process.c12
-rw-r--r--arch/mips/kernel/ptrace.c147
-rw-r--r--arch/mips/kernel/signal32.c67
-rw-r--r--arch/mips/kernel/traps.c29
-rw-r--r--arch/mips/kvm/mips.c7
-rw-r--r--arch/mips/lib/Makefile3
-rw-r--r--arch/mips/lib/libgcc.h17
-rw-r--r--arch/mips/lib/multi3.c54
-rw-r--r--arch/mips/mm/uasm-micromips.c2
-rw-r--r--arch/mips/ralink/timer.c4
-rw-r--r--arch/mips/rb532/Makefile4
-rw-r--r--arch/mips/rb532/devices.c4
-rw-r--r--arch/mn10300/include/asm/thread_info.h2
-rw-r--r--arch/mn10300/include/uapi/asm/Kbuild1
-rw-r--r--arch/mn10300/kernel/mn10300-serial.c7
-rw-r--r--arch/mn10300/mm/misalignment.c2
-rw-r--r--arch/nios2/include/asm/thread_info.h3
-rw-r--r--arch/nios2/include/uapi/asm/Kbuild1
-rw-r--r--arch/openrisc/include/asm/processor.h2
-rw-r--r--arch/openrisc/include/asm/thread_info.h2
-rw-r--r--arch/openrisc/include/uapi/asm/Kbuild1
-rw-r--r--arch/openrisc/kernel/traps.c10
-rw-r--r--arch/openrisc/kernel/vmlinux.lds.S1
-rw-r--r--arch/parisc/boot/compressed/misc.c4
-rw-r--r--arch/parisc/include/asm/compat.h64
-rw-r--r--arch/parisc/include/asm/ldcw.h2
-rw-r--r--arch/parisc/include/asm/thread_info.h8
-rw-r--r--arch/parisc/include/uapi/asm/Kbuild1
-rw-r--r--arch/parisc/include/uapi/asm/siginfo.h7
-rw-r--r--arch/parisc/kernel/drivers.c2
-rw-r--r--arch/parisc/kernel/entry.S25
-rw-r--r--arch/parisc/kernel/hpmc.S1
-rw-r--r--arch/parisc/kernel/pacache.S9
-rw-r--r--arch/parisc/kernel/pdt.c2
-rw-r--r--arch/parisc/kernel/process.c39
-rw-r--r--arch/parisc/kernel/signal32.c106
-rw-r--r--arch/parisc/kernel/signal32.h3
-rw-r--r--arch/parisc/kernel/traps.c2
-rw-r--r--arch/parisc/kernel/unwind.c1
-rw-r--r--arch/parisc/lib/delay.c2
-rw-r--r--arch/parisc/mm/init.c10
-rw-r--r--arch/powerpc/Kconfig1
-rw-r--r--arch/powerpc/configs/fsl-emb-nonhw.config1
-rw-r--r--arch/powerpc/configs/powernv_defconfig1
-rw-r--r--arch/powerpc/configs/ppc64_defconfig1
-rw-r--r--arch/powerpc/configs/pseries_defconfig1
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h1
-rw-r--r--arch/powerpc/include/asm/compat.h65
-rw-r--r--arch/powerpc/include/asm/debug.h2
-rw-r--r--arch/powerpc/include/asm/exception-64e.h6
-rw-r--r--arch/powerpc/include/asm/exception-64s.h57
-rw-r--r--arch/powerpc/include/asm/feature-fixups.h13
-rw-r--r--arch/powerpc/include/asm/hvcall.h18
-rw-r--r--arch/powerpc/include/asm/kvm_ppc.h1
-rw-r--r--arch/powerpc/include/asm/machdep.h1
-rw-r--r--arch/powerpc/include/asm/mmu_context.h5
-rw-r--r--arch/powerpc/include/asm/paca.h10
-rw-r--r--arch/powerpc/include/asm/plpar_wrappers.h14
-rw-r--r--arch/powerpc/include/asm/setup.h14
-rw-r--r--arch/powerpc/include/asm/thread_info.h3
-rw-r--r--arch/powerpc/include/uapi/asm/Kbuild1
-rw-r--r--arch/powerpc/include/uapi/asm/kvm.h25
-rw-r--r--arch/powerpc/include/uapi/asm/siginfo.h16
-rw-r--r--arch/powerpc/kernel/asm-offsets.c5
-rw-r--r--arch/powerpc/kernel/cpu_setup_power.S2
-rw-r--r--arch/powerpc/kernel/entry_64.S44
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S137
-rw-r--r--arch/powerpc/kernel/fadump.c22
-rw-r--r--arch/powerpc/kernel/mce.c2
-rw-r--r--arch/powerpc/kernel/misc_64.S2
-rw-r--r--arch/powerpc/kernel/process.c27
-rw-r--r--arch/powerpc/kernel/setup-common.c38
-rw-r--r--arch/powerpc/kernel/setup_64.c139
-rw-r--r--arch/powerpc/kernel/signal_32.c66
-rw-r--r--arch/powerpc/kernel/traps.c22
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S9
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu.c1
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c127
-rw-r--r--arch/powerpc/kvm/book3s_hv.c3
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S9
-rw-r--r--arch/powerpc/kvm/book3s_pr.c2
-rw-r--r--arch/powerpc/kvm/book3s_rmhandlers.S7
-rw-r--r--arch/powerpc/kvm/book3s_segment.S4
-rw-r--r--arch/powerpc/kvm/book3s_xive.c7
-rw-r--r--arch/powerpc/kvm/powerpc.c138
-rw-r--r--arch/powerpc/lib/feature-fixups.c41
-rw-r--r--arch/powerpc/mm/fault.c7
-rw-r--r--arch/powerpc/mm/hash_native_64.c15
-rw-r--r--arch/powerpc/net/bpf_jit_comp64.c6
-rw-r--r--arch/powerpc/perf/core-book3s.c12
-rw-r--r--arch/powerpc/perf/imc-pmu.c17
-rw-r--r--arch/powerpc/platforms/powernv/opal-memory-errors.c2
-rw-r--r--arch/powerpc/platforms/powernv/setup.c49
-rw-r--r--arch/powerpc/platforms/ps3/setup.c15
-rw-r--r--arch/powerpc/platforms/pseries/dlpar.c21
-rw-r--r--arch/powerpc/platforms/pseries/pseries.h2
-rw-r--r--arch/powerpc/platforms/pseries/ras.c3
-rw-r--r--arch/powerpc/platforms/pseries/setup.c36
-rw-r--r--arch/powerpc/sysdev/fsl_msi.c4
-rw-r--r--arch/powerpc/xmon/xmon.c36
-rw-r--r--arch/riscv/configs/defconfig75
-rw-r--r--arch/riscv/include/asm/Kbuild1
-rw-r--r--arch/riscv/include/asm/asm.h12
-rw-r--r--arch/riscv/include/asm/atomic.h103
-rw-r--r--arch/riscv/include/asm/barrier.h36
-rw-r--r--arch/riscv/include/asm/bitops.h2
-rw-r--r--arch/riscv/include/asm/bug.h6
-rw-r--r--arch/riscv/include/asm/cacheflush.h30
-rw-r--r--arch/riscv/include/asm/csr.h8
-rw-r--r--arch/riscv/include/asm/io.h20
-rw-r--r--arch/riscv/include/asm/irqflags.h10
-rw-r--r--arch/riscv/include/asm/mmu.h4
-rw-r--r--arch/riscv/include/asm/mmu_context.h45
-rw-r--r--arch/riscv/include/asm/pgtable.h62
-rw-r--r--arch/riscv/include/asm/ptrace.h2
-rw-r--r--arch/riscv/include/asm/spinlock.h11
-rw-r--r--arch/riscv/include/asm/thread_info.h2
-rw-r--r--arch/riscv/include/asm/timex.h3
-rw-r--r--arch/riscv/include/asm/tlbflush.h9
-rw-r--r--arch/riscv/include/asm/uaccess.h12
-rw-r--r--arch/riscv/include/asm/unistd.h1
-rw-r--r--arch/riscv/include/asm/vdso.h4
-rw-r--r--arch/riscv/include/uapi/asm/Kbuild1
-rw-r--r--arch/riscv/include/uapi/asm/syscalls.h26
-rw-r--r--arch/riscv/kernel/entry.S8
-rw-r--r--arch/riscv/kernel/head.S3
-rw-r--r--arch/riscv/kernel/process.c4
-rw-r--r--arch/riscv/kernel/riscv_ksyms.c3
-rw-r--r--arch/riscv/kernel/setup.c16
-rw-r--r--arch/riscv/kernel/smp.c55
-rw-r--r--arch/riscv/kernel/sys_riscv.c33
-rw-r--r--arch/riscv/kernel/syscall_table.c1
-rw-r--r--arch/riscv/kernel/vdso/Makefile7
-rw-r--r--arch/riscv/kernel/vdso/clock_getres.S26
-rw-r--r--arch/riscv/kernel/vdso/clock_gettime.S26
-rw-r--r--arch/riscv/kernel/vdso/flush_icache.S30
-rw-r--r--arch/riscv/kernel/vdso/getcpu.S26
-rw-r--r--arch/riscv/kernel/vdso/gettimeofday.S26
-rw-r--r--arch/riscv/kernel/vdso/vdso.lds.S7
-rw-r--r--arch/riscv/lib/delay.c1
-rw-r--r--arch/riscv/mm/Makefile1
-rw-r--r--arch/riscv/mm/cacheflush.c23
-rw-r--r--arch/riscv/mm/fault.c2
-rw-r--r--arch/riscv/mm/ioremap.c2
-rw-r--r--arch/s390/Kbuild1
-rw-r--r--arch/s390/Makefile5
-rw-r--r--arch/s390/appldata/Makefile1
-rw-r--r--arch/s390/appldata/appldata_base.c1
-rw-r--r--arch/s390/appldata/appldata_mem.c1
-rw-r--r--arch/s390/appldata/appldata_net_sum.c1
-rw-r--r--arch/s390/appldata/appldata_os.c1
-rw-r--r--arch/s390/boot/compressed/vmlinux.scr1
-rw-r--r--arch/s390/boot/install.sh5
-rw-r--r--arch/s390/crypto/aes_s390.c7
-rw-r--r--arch/s390/crypto/arch_random.c6
-rw-r--r--arch/s390/crypto/crc32-vx.c1
-rw-r--r--arch/s390/crypto/des_s390.c7
-rw-r--r--arch/s390/crypto/ghash_s390.c1
-rw-r--r--arch/s390/crypto/paes_s390.c6
-rw-r--r--arch/s390/crypto/prng.c1
-rw-r--r--arch/s390/crypto/sha.h7
-rw-r--r--arch/s390/crypto/sha1_s390.c7
-rw-r--r--arch/s390/crypto/sha256_s390.c7
-rw-r--r--arch/s390/crypto/sha512_s390.c7
-rw-r--r--arch/s390/crypto/sha_common.c7
-rw-r--r--arch/s390/hypfs/Makefile1
-rw-r--r--arch/s390/hypfs/inode.c2
-rw-r--r--arch/s390/include/asm/Kbuild1
-rw-r--r--arch/s390/include/asm/alternative.h1
-rw-r--r--arch/s390/include/asm/ap.h5
-rw-r--r--arch/s390/include/asm/bugs.h1
-rw-r--r--arch/s390/include/asm/compat.h73
-rw-r--r--arch/s390/include/asm/cpu_mf.h5
-rw-r--r--arch/s390/include/asm/elf.h15
-rw-r--r--arch/s390/include/asm/kprobes.h15
-rw-r--r--arch/s390/include/asm/kvm_host.h8
-rw-r--r--arch/s390/include/asm/kvm_para.h7
-rw-r--r--arch/s390/include/asm/livepatch.h8
-rw-r--r--arch/s390/include/asm/mmu_context.h2
-rw-r--r--arch/s390/include/asm/perf_event.h1
-rw-r--r--arch/s390/include/asm/pgtable.h2
-rw-r--r--arch/s390/include/asm/ptrace.h11
-rw-r--r--arch/s390/include/asm/segment.h1
-rw-r--r--arch/s390/include/asm/switch_to.h27
-rw-r--r--arch/s390/include/asm/syscall.h5
-rw-r--r--arch/s390/include/asm/sysinfo.h5
-rw-r--r--arch/s390/include/asm/thread_info.h2
-rw-r--r--arch/s390/include/asm/topology.h1
-rw-r--r--arch/s390/include/asm/vga.h1
-rw-r--r--arch/s390/include/uapi/asm/Kbuild1
-rw-r--r--arch/s390/include/uapi/asm/bpf_perf_event.h9
-rw-r--r--arch/s390/include/uapi/asm/kvm.h9
-rw-r--r--arch/s390/include/uapi/asm/kvm_para.h4
-rw-r--r--arch/s390/include/uapi/asm/kvm_perf.h4
-rw-r--r--arch/s390/include/uapi/asm/perf_regs.h1
-rw-r--r--arch/s390/include/uapi/asm/ptrace.h125
-rw-r--r--arch/s390/include/uapi/asm/sthyi.h1
-rw-r--r--arch/s390/include/uapi/asm/virtio-ccw.h6
-rw-r--r--arch/s390/include/uapi/asm/vmcp.h1
-rw-r--r--arch/s390/include/uapi/asm/zcrypt.h14
-rw-r--r--arch/s390/kernel/alternative.c1
-rw-r--r--arch/s390/kernel/compat_linux.c1
-rw-r--r--arch/s390/kernel/compat_signal.c100
-rw-r--r--arch/s390/kernel/debug.c2
-rw-r--r--arch/s390/kernel/dis.c10
-rw-r--r--arch/s390/kernel/dumpstack.c1
-rw-r--r--arch/s390/kernel/entry.S15
-rw-r--r--arch/s390/kernel/ipl.c1
-rw-r--r--arch/s390/kernel/kprobes.c15
-rw-r--r--arch/s390/kernel/lgr.c1
-rw-r--r--arch/s390/kernel/module.c15
-rw-r--r--arch/s390/kernel/nmi.c1
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c5
-rw-r--r--arch/s390/kernel/perf_cpum_sf.c5
-rw-r--r--arch/s390/kernel/perf_event.c5
-rw-r--r--arch/s390/kernel/perf_regs.c1
-rw-r--r--arch/s390/kernel/ptrace.c8
-rw-r--r--arch/s390/kernel/setup.c1
-rw-r--r--arch/s390/kernel/smp.c1
-rw-r--r--arch/s390/kernel/stacktrace.c1
-rw-r--r--arch/s390/kernel/sthyi.c5
-rw-r--r--arch/s390/kernel/syscalls.S6
-rw-r--r--arch/s390/kernel/time.c1
-rw-r--r--arch/s390/kernel/topology.c1
-rw-r--r--arch/s390/kernel/vdso.c5
-rw-r--r--arch/s390/kernel/vdso32/clock_getres.S5
-rw-r--r--arch/s390/kernel/vdso32/clock_gettime.S5
-rw-r--r--arch/s390/kernel/vdso32/gettimeofday.S5
-rw-r--r--arch/s390/kernel/vdso64/clock_getres.S5
-rw-r--r--arch/s390/kernel/vdso64/clock_gettime.S5
-rw-r--r--arch/s390/kernel/vdso64/gettimeofday.S5
-rw-r--r--arch/s390/kernel/vdso64/note.S1
-rw-r--r--arch/s390/kernel/vtime.c1
-rw-r--r--arch/s390/kvm/Makefile5
-rw-r--r--arch/s390/kvm/diag.c5
-rw-r--r--arch/s390/kvm/gaccess.h5
-rw-r--r--arch/s390/kvm/guestdbg.c5
-rw-r--r--arch/s390/kvm/intercept.c5
-rw-r--r--arch/s390/kvm/interrupt.c5
-rw-r--r--arch/s390/kvm/irq.h5
-rw-r--r--arch/s390/kvm/kvm-s390.c57
-rw-r--r--arch/s390/kvm/kvm-s390.h5
-rw-r--r--arch/s390/kvm/priv.c18
-rw-r--r--arch/s390/kvm/sigp.c5
-rw-r--r--arch/s390/kvm/vsie.c15
-rw-r--r--arch/s390/lib/uaccess.c2
-rw-r--r--arch/s390/mm/cmm.c1
-rw-r--r--arch/s390/mm/gmap.c1
-rw-r--r--arch/s390/mm/mmap.c16
-rw-r--r--arch/s390/mm/pgalloc.c2
-rw-r--r--arch/s390/mm/pgtable.c1
-rw-r--r--arch/s390/net/Makefile1
-rw-r--r--arch/s390/net/bpf_jit_comp.c11
-rw-r--r--arch/s390/numa/Makefile1
-rw-r--r--arch/s390/pci/Makefile1
-rw-r--r--arch/s390/pci/pci.c1
-rw-r--r--arch/s390/pci/pci_debug.c1
-rw-r--r--arch/s390/pci/pci_dma.c22
-rw-r--r--arch/s390/pci/pci_insn.c4
-rw-r--r--arch/s390/tools/gen_opcode_table.c1
-rw-r--r--arch/score/include/asm/thread_info.h3
-rw-r--r--arch/score/include/uapi/asm/Kbuild1
-rw-r--r--arch/sh/boards/mach-se/770x/setup.c24
-rw-r--r--arch/sh/include/asm/thread_info.h3
-rw-r--r--arch/sh/include/mach-se/mach/se.h1
-rw-r--r--arch/sh/include/uapi/asm/Kbuild1
-rw-r--r--arch/sh/kernel/traps_32.c3
-rw-r--r--arch/sparc/crypto/Makefile2
-rw-r--r--arch/sparc/include/asm/compat.h59
-rw-r--r--arch/sparc/include/asm/pgtable_64.h2
-rw-r--r--arch/sparc/include/asm/thread_info_32.h3
-rw-r--r--arch/sparc/include/asm/thread_info_64.h3
-rw-r--r--arch/sparc/include/uapi/asm/Kbuild1
-rw-r--r--arch/sparc/kernel/signal32.c69
-rw-r--r--arch/sparc/lib/Makefile2
-rw-r--r--arch/sparc/lib/hweight.S4
-rw-r--r--arch/sparc/mm/fault_32.c2
-rw-r--r--arch/sparc/mm/fault_64.c2
-rw-r--r--arch/sparc/net/bpf_jit_comp_64.c6
-rw-r--r--arch/tile/include/asm/compat.h62
-rw-r--r--arch/tile/include/asm/pgtable.h1
-rw-r--r--arch/tile/include/asm/thread_info.h3
-rw-r--r--arch/tile/include/uapi/asm/Kbuild1
-rw-r--r--arch/tile/include/uapi/asm/siginfo.h8
-rw-r--r--arch/tile/kernel/compat_signal.c73
-rw-r--r--arch/tile/kernel/single_step.c24
-rw-r--r--arch/tile/kernel/traps.c4
-rw-r--r--arch/tile/kernel/unaligned.c46
-rw-r--r--arch/um/include/asm/Kbuild1
-rw-r--r--arch/um/include/asm/mmu_context.h3
-rw-r--r--arch/um/include/asm/processor-generic.h5
-rw-r--r--arch/um/include/asm/thread_info.h9
-rw-r--r--arch/um/include/asm/vmlinux.lds.h2
-rw-r--r--arch/um/kernel/dyn.lds.S3
-rw-r--r--arch/um/kernel/trap.c4
-rw-r--r--arch/um/kernel/um_arch.c2
-rw-r--r--arch/um/kernel/uml.lds.S2
-rw-r--r--arch/unicore32/include/asm/mmu_context.h5
-rw-r--r--arch/unicore32/include/asm/thread_info.h3
-rw-r--r--arch/unicore32/include/uapi/asm/Kbuild1
-rw-r--r--arch/unicore32/kernel/traps.c1
-rw-r--r--arch/x86/Kconfig27
-rw-r--r--arch/x86/Kconfig.debug9
-rw-r--r--arch/x86/Makefile8
-rw-r--r--arch/x86/boot/compressed/Makefile1
-rw-r--r--arch/x86/boot/compressed/head_64.S16
-rw-r--r--arch/x86/boot/compressed/misc.c16
-rw-r--r--arch/x86/boot/compressed/pagetable.c3
-rw-r--r--arch/x86/boot/compressed/pgtable_64.c28
-rw-r--r--arch/x86/boot/genimage.sh32
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S5
-rw-r--r--arch/x86/crypto/camellia-aesni-avx-asm_64.S3
-rw-r--r--arch/x86/crypto/camellia-aesni-avx2-asm_64.S3
-rw-r--r--arch/x86/crypto/crc32c-pcl-intel-asm_64.S3
-rw-r--r--arch/x86/crypto/salsa20_glue.c7
-rw-r--r--arch/x86/entry/calling.h147
-rw-r--r--arch/x86/entry/entry_32.S31
-rw-r--r--arch/x86/entry/entry_64.S261
-rw-r--r--arch/x86/entry/entry_64_compat.S32
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c2
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c38
-rw-r--r--arch/x86/events/amd/power.c2
-rw-r--r--arch/x86/events/intel/bts.c18
-rw-r--r--arch/x86/events/intel/core.c5
-rw-r--r--arch/x86/events/intel/ds.c175
-rw-r--r--arch/x86/events/intel/rapl.c4
-rw-r--r--arch/x86/events/msr.c70
-rw-r--r--arch/x86/events/perf_event.h23
-rw-r--r--arch/x86/hyperv/mmu.c12
-rw-r--r--arch/x86/include/asm/acpi.h2
-rw-r--r--arch/x86/include/asm/alternative.h4
-rw-r--r--arch/x86/include/asm/apic.h1
-rw-r--r--arch/x86/include/asm/asm-prototypes.h27
-rw-r--r--arch/x86/include/asm/asm.h2
-rw-r--r--arch/x86/include/asm/compat.h86
-rw-r--r--arch/x86/include/asm/cpu_entry_area.h81
-rw-r--r--arch/x86/include/asm/cpufeature.h9
-rw-r--r--arch/x86/include/asm/cpufeatures.h29
-rw-r--r--arch/x86/include/asm/desc.h14
-rw-r--r--arch/x86/include/asm/disabled-features.h11
-rw-r--r--arch/x86/include/asm/espfix.h7
-rw-r--r--arch/x86/include/asm/fixmap.h7
-rw-r--r--arch/x86/include/asm/fpu/signal.h6
-rw-r--r--arch/x86/include/asm/hypervisor.h26
-rw-r--r--arch/x86/include/asm/i8259.h5
-rw-r--r--arch/x86/include/asm/intel_ds.h36
-rw-r--r--arch/x86/include/asm/invpcid.h53
-rw-r--r--arch/x86/include/asm/irqdomain.h2
-rw-r--r--arch/x86/include/asm/irqflags.h3
-rw-r--r--arch/x86/include/asm/jailhouse_para.h26
-rw-r--r--arch/x86/include/asm/kdebug.h1
-rw-r--r--arch/x86/include/asm/kmemcheck.h1
-rw-r--r--arch/x86/include/asm/kvm_emulate.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h19
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/mem_encrypt.h4
-rw-r--r--arch/x86/include/asm/mmu.h4
-rw-r--r--arch/x86/include/asm/mmu_context.h113
-rw-r--r--arch/x86/include/asm/mpspec_def.h14
-rw-r--r--arch/x86/include/asm/mshyperv.h18
-rw-r--r--arch/x86/include/asm/msr-index.h15
-rw-r--r--arch/x86/include/asm/nospec-branch.h174
-rw-r--r--arch/x86/include/asm/paravirt.h9
-rw-r--r--arch/x86/include/asm/pci_x86.h1
-rw-r--r--arch/x86/include/asm/pgalloc.h11
-rw-r--r--arch/x86/include/asm/pgtable.h38
-rw-r--r--arch/x86/include/asm/pgtable_32_types.h15
-rw-r--r--arch/x86/include/asm/pgtable_64.h92
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h59
-rw-r--r--arch/x86/include/asm/processor-flags.h5
-rw-r--r--arch/x86/include/asm/processor.h85
-rw-r--r--arch/x86/include/asm/pti.h14
-rw-r--r--arch/x86/include/asm/required-features.h3
-rw-r--r--arch/x86/include/asm/segment.h12
-rw-r--r--arch/x86/include/asm/stacktrace.h3
-rw-r--r--arch/x86/include/asm/suspend_32.h8
-rw-r--r--arch/x86/include/asm/suspend_64.h19
-rw-r--r--arch/x86/include/asm/switch_to.h13
-rw-r--r--arch/x86/include/asm/thread_info.h4
-rw-r--r--arch/x86/include/asm/tlbflush.h347
-rw-r--r--arch/x86/include/asm/trace/irq_vectors.h16
-rw-r--r--arch/x86/include/asm/traps.h2
-rw-r--r--arch/x86/include/asm/unwind.h20
-rw-r--r--arch/x86/include/asm/uprobes.h4
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h1
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h14
-rw-r--r--arch/x86/include/asm/uv/uv_mmrs.h749
-rw-r--r--arch/x86/include/asm/vsyscall.h1
-rw-r--r--arch/x86/include/asm/x86_init.h1
-rw-r--r--arch/x86/include/asm/xen/hypercall.h5
-rw-r--r--arch/x86/include/uapi/asm/Kbuild1
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h22
-rw-r--r--arch/x86/include/uapi/asm/processor-flags.h7
-rw-r--r--arch/x86/kernel/Makefile7
-rw-r--r--arch/x86/kernel/acpi/boot.c35
-rw-r--r--arch/x86/kernel/acpi/sleep.c2
-rw-r--r--arch/x86/kernel/alternative.c21
-rw-r--r--arch/x86/kernel/aperture_64.c46
-rw-r--r--arch/x86/kernel/apic/apic.c51
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c26
-rw-r--r--arch/x86/kernel/apic/apic_noop.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c22
-rw-r--r--arch/x86/kernel/apic/msi.c8
-rw-r--r--arch/x86/kernel/apic/probe_32.c2
-rw-r--r--arch/x86/kernel/apic/vector.c31
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c84
-rw-r--r--arch/x86/kernel/asm-offsets.c10
-rw-r--r--arch/x86/kernel/asm-offsets_32.c9
-rw-r--r--arch/x86/kernel/asm-offsets_64.c4
-rw-r--r--arch/x86/kernel/cpu/amd.c35
-rw-r--r--arch/x86/kernel/cpu/bugs.c257
-rw-r--r--arch/x86/kernel/cpu/centaur.c4
-rw-r--r--arch/x86/kernel/cpu/common.c145
-rw-r--r--arch/x86/kernel/cpu/hypervisor.c4
-rw-r--r--arch/x86/kernel/cpu/intel.c77
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.c76
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.h5
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_rdtgroup.c117
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c26
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c28
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c29
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c4
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c42
-rw-r--r--arch/x86/kernel/cpu/scattered.c4
-rw-r--r--arch/x86/kernel/doublefault.c36
-rw-r--r--arch/x86/kernel/dumpstack.c98
-rw-r--r--arch/x86/kernel/dumpstack_32.c6
-rw-r--r--arch/x86/kernel/dumpstack_64.c12
-rw-r--r--arch/x86/kernel/ftrace_32.S6
-rw-r--r--arch/x86/kernel/ftrace_64.S34
-rw-r--r--arch/x86/kernel/head64.c4
-rw-r--r--arch/x86/kernel/head_64.S30
-rw-r--r--arch/x86/kernel/idt.c12
-rw-r--r--arch/x86/kernel/ioport.c2
-rw-r--r--arch/x86/kernel/irq.c12
-rw-r--r--arch/x86/kernel/irq_32.c9
-rw-r--r--arch/x86/kernel/irq_64.c4
-rw-r--r--arch/x86/kernel/irqinit.c3
-rw-r--r--arch/x86/kernel/itmt.c1
-rw-r--r--arch/x86/kernel/jailhouse.c211
-rw-r--r--arch/x86/kernel/kprobes/opt.c23
-rw-r--r--arch/x86/kernel/ldt.c198
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kernel/mpparse.c23
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c2
-rw-r--r--arch/x86/kernel/platform-quirks.c1
-rw-r--r--arch/x86/kernel/process.c47
-rw-r--r--arch/x86/kernel/process_32.c2
-rw-r--r--arch/x86/kernel/process_64.c14
-rw-r--r--arch/x86/kernel/setup.c16
-rw-r--r--arch/x86/kernel/signal_compat.c123
-rw-r--r--arch/x86/kernel/smpboot.c26
-rw-r--r--arch/x86/kernel/stacktrace.c8
-rw-r--r--arch/x86/kernel/tboot.c11
-rw-r--r--arch/x86/kernel/time.c9
-rw-r--r--arch/x86/kernel/tls.c11
-rw-r--r--arch/x86/kernel/traps.c77
-rw-r--r--arch/x86/kernel/tsc.c70
-rw-r--r--arch/x86/kernel/unwind_orc.c136
-rw-r--r--arch/x86/kernel/uprobes.c107
-rw-r--r--arch/x86/kernel/vmlinux.lds.S23
-rw-r--r--arch/x86/kvm/cpuid.h2
-rw-r--r--arch/x86/kvm/emulate.c102
-rw-r--r--arch/x86/kvm/ioapic.c34
-rw-r--r--arch/x86/kvm/lapic.c12
-rw-r--r--arch/x86/kvm/mmu.c27
-rw-r--r--arch/x86/kvm/svm.c25
-rw-r--r--arch/x86/kvm/vmx.c110
-rw-r--r--arch/x86/kvm/x86.c139
-rw-r--r--arch/x86/lib/Makefile2
-rw-r--r--arch/x86/lib/checksum_32.S7
-rw-r--r--arch/x86/lib/delay.c6
-rw-r--r--arch/x86/lib/retpoline.S104
-rw-r--r--arch/x86/lib/x86-opcode-map.txt13
-rw-r--r--arch/x86/mm/Makefile9
-rw-r--r--arch/x86/mm/cpu_entry_area.c166
-rw-r--r--arch/x86/mm/debug_pagetables.c80
-rw-r--r--arch/x86/mm/dump_pagetables.c141
-rw-r--r--arch/x86/mm/extable.c40
-rw-r--r--arch/x86/mm/fault.c33
-rw-r--r--arch/x86/mm/init.c82
-rw-r--r--arch/x86/mm/init_32.c6
-rw-r--r--arch/x86/mm/ioremap.c4
-rw-r--r--arch/x86/mm/kasan_init_64.c47
-rw-r--r--arch/x86/mm/kaslr.c32
-rw-r--r--arch/x86/mm/kmemcheck/error.c1
-rw-r--r--arch/x86/mm/kmemcheck/error.h1
-rw-r--r--arch/x86/mm/kmemcheck/opcode.c1
-rw-r--r--arch/x86/mm/kmemcheck/opcode.h1
-rw-r--r--arch/x86/mm/kmemcheck/pte.c1
-rw-r--r--arch/x86/mm/kmemcheck/pte.h1
-rw-r--r--arch/x86/mm/kmemcheck/selftest.c1
-rw-r--r--arch/x86/mm/kmemcheck/selftest.h1
-rw-r--r--arch/x86/mm/kmemcheck/shadow.h1
-rw-r--r--arch/x86/mm/kmmio.c12
-rw-r--r--arch/x86/mm/mem_encrypt.c360
-rw-r--r--arch/x86/mm/mem_encrypt_boot.S80
-rw-r--r--arch/x86/mm/pgtable.c5
-rw-r--r--arch/x86/mm/pgtable_32.c1
-rw-r--r--arch/x86/mm/pti.c368
-rw-r--r--arch/x86/mm/tlb.c98
-rw-r--r--arch/x86/pci/broadcom_bus.c2
-rw-r--r--arch/x86/pci/common.c5
-rw-r--r--arch/x86/pci/fixup.c60
-rw-r--r--arch/x86/pci/intel_mid_pci.c1
-rw-r--r--arch/x86/platform/efi/efi_64.c8
-rw-r--r--arch/x86/platform/efi/quirks.c13
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_bt.c2
-rw-r--r--arch/x86/platform/intel-mid/intel-mid.c2
-rw-r--r--arch/x86/platform/intel-mid/sfi.c5
-rw-r--r--arch/x86/platform/uv/tlb_uv.c5
-rw-r--r--arch/x86/platform/uv/uv_irq.c2
-rw-r--r--arch/x86/platform/uv/uv_nmi.c4
-rw-r--r--arch/x86/power/cpu.c112
-rw-r--r--arch/x86/tools/Makefile12
-rw-r--r--arch/x86/tools/insn_decoder_test.c (renamed from arch/x86/tools/test_get_len.c)43
-rw-r--r--arch/x86/tools/objdump_reformat.awk (renamed from arch/x86/tools/distill.awk)4
-rw-r--r--arch/x86/xen/apic.c2
-rw-r--r--arch/x86/xen/enlighten.c81
-rw-r--r--arch/x86/xen/enlighten_pv.c42
-rw-r--r--arch/x86/xen/mmu_hvm.c2
-rw-r--r--arch/x86/xen/mmu_pv.c22
-rw-r--r--arch/x86/xen/setup.c6
-rw-r--r--arch/x86/xen/spinlock.c2
-rw-r--r--arch/x86/xen/xen-asm_64.S14
-rw-r--r--arch/x86/xen/xen-ops.h2
-rw-r--r--arch/xtensa/Kconfig7
-rw-r--r--arch/xtensa/Makefile7
-rw-r--r--arch/xtensa/boot/boot-redboot/bootstrap.S1
-rw-r--r--arch/xtensa/boot/lib/Makefile6
-rw-r--r--arch/xtensa/configs/audio_kc705_defconfig1
-rw-r--r--arch/xtensa/configs/cadence_csp_defconfig1
-rw-r--r--arch/xtensa/configs/generic_kc705_defconfig1
-rw-r--r--arch/xtensa/configs/nommu_kc705_defconfig1
-rw-r--r--arch/xtensa/configs/smp_lx200_defconfig1
-rw-r--r--arch/xtensa/include/asm/asmmacro.h40
-rw-r--r--arch/xtensa/include/asm/current.h4
-rw-r--r--arch/xtensa/include/asm/fixmap.h4
-rw-r--r--arch/xtensa/include/asm/futex.h23
-rw-r--r--arch/xtensa/include/asm/highmem.h2
-rw-r--r--arch/xtensa/include/asm/kasan.h37
-rw-r--r--arch/xtensa/include/asm/kmem_layout.h7
-rw-r--r--arch/xtensa/include/asm/linkage.h9
-rw-r--r--arch/xtensa/include/asm/mmu_context.h1
-rw-r--r--arch/xtensa/include/asm/nommu_context.h4
-rw-r--r--arch/xtensa/include/asm/page.h2
-rw-r--r--arch/xtensa/include/asm/pgtable.h3
-rw-r--r--arch/xtensa/include/asm/ptrace.h15
-rw-r--r--arch/xtensa/include/asm/regs.h1
-rw-r--r--arch/xtensa/include/asm/stackprotector.h40
-rw-r--r--arch/xtensa/include/asm/string.h23
-rw-r--r--arch/xtensa/include/asm/thread_info.h16
-rw-r--r--arch/xtensa/include/asm/traps.h35
-rw-r--r--arch/xtensa/include/asm/uaccess.h9
-rw-r--r--arch/xtensa/include/uapi/asm/Kbuild1
-rw-r--r--arch/xtensa/kernel/Makefile3
-rw-r--r--arch/xtensa/kernel/align.S7
-rw-r--r--arch/xtensa/kernel/asm-offsets.c16
-rw-r--r--arch/xtensa/kernel/coprocessor.S3
-rw-r--r--arch/xtensa/kernel/entry.S103
-rw-r--r--arch/xtensa/kernel/head.S10
-rw-r--r--arch/xtensa/kernel/module.c19
-rw-r--r--arch/xtensa/kernel/pci.c30
-rw-r--r--arch/xtensa/kernel/process.c6
-rw-r--r--arch/xtensa/kernel/ptrace.c8
-rw-r--r--arch/xtensa/kernel/setup.c49
-rw-r--r--arch/xtensa/kernel/signal.c8
-rw-r--r--arch/xtensa/kernel/traps.c64
-rw-r--r--arch/xtensa/kernel/vectors.S17
-rw-r--r--arch/xtensa/kernel/vmlinux.lds.S90
-rw-r--r--arch/xtensa/kernel/xtensa_ksyms.c5
-rw-r--r--arch/xtensa/lib/checksum.S74
-rw-r--r--arch/xtensa/lib/memcopy.S81
-rw-r--r--arch/xtensa/lib/memset.S45
-rw-r--r--arch/xtensa/lib/pci-auto.c45
-rw-r--r--arch/xtensa/lib/strncpy_user.S60
-rw-r--r--arch/xtensa/lib/strnlen_user.S28
-rw-r--r--arch/xtensa/lib/usercopy.S138
-rw-r--r--arch/xtensa/mm/Makefile5
-rw-r--r--arch/xtensa/mm/cache.c3
-rw-r--r--arch/xtensa/mm/fault.c22
-rw-r--r--arch/xtensa/mm/init.c36
-rw-r--r--arch/xtensa/mm/kasan_init.c95
-rw-r--r--arch/xtensa/mm/mmu.c31
-rw-r--r--arch/xtensa/mm/tlb.c6
-rw-r--r--arch/xtensa/platforms/iss/console.c4
-rw-r--r--arch/xtensa/platforms/iss/network.c14
914 files changed, 13577 insertions, 6719 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 400b9e1b2f27..a26d6f8ab967 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -234,8 +234,8 @@ config ARCH_HAS_FORTIFY_SOURCE
config ARCH_HAS_SET_MEMORY
bool
-# Select if arch init_task initializer is different to init/init_task.c
-config ARCH_INIT_TASK
+# Select if arch init_task must go in the __init_task_data section
+config ARCH_TASK_STRUCT_ON_STACK
bool
# Select if arch has its private alloc_task_struct() function
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 8c20c5e35432..807d7b9a1860 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -39,9 +39,6 @@ struct thread_info {
.preempt_count = INIT_PREEMPT_COUNT, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* How to get the thread information struct from C. */
register struct thread_info *__current_thread_info __asm__("$8");
#define current_thread_info() __current_thread_info
diff --git a/arch/alpha/include/uapi/asm/Kbuild b/arch/alpha/include/uapi/asm/Kbuild
index 574fe90c8b58..9afaba5e5503 100644
--- a/arch/alpha/include/uapi/asm/Kbuild
+++ b/arch/alpha/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += poll.h
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index 37bd6d9b8eb9..a6bdc1da47ad 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -102,6 +102,15 @@ sio_pci_route(void)
alpha_mv.sys.sio.route_tab);
}
+static bool sio_pci_dev_irq_needs_level(const struct pci_dev *dev)
+{
+ if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
+ (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+ return false;
+
+ return true;
+}
+
static unsigned int __init
sio_collect_irq_levels(void)
{
@@ -110,8 +119,7 @@ sio_collect_irq_levels(void)
/* Iterate through the devices, collecting IRQ levels. */
for_each_pci_dev(dev) {
- if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
- (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+ if (!sio_pci_dev_irq_needs_level(dev))
continue;
if (dev->irq)
@@ -120,8 +128,7 @@ sio_collect_irq_levels(void)
return level_bits;
}
-static void __init
-sio_fixup_irq_levels(unsigned int level_bits)
+static void __sio_fixup_irq_levels(unsigned int level_bits, bool reset)
{
unsigned int old_level_bits;
@@ -139,12 +146,21 @@ sio_fixup_irq_levels(unsigned int level_bits)
*/
old_level_bits = inb(0x4d0) | (inb(0x4d1) << 8);
- level_bits |= (old_level_bits & 0x71ff);
+ if (reset)
+ old_level_bits &= 0x71ff;
+
+ level_bits |= old_level_bits;
outb((level_bits >> 0) & 0xff, 0x4d0);
outb((level_bits >> 8) & 0xff, 0x4d1);
}
+static inline void
+sio_fixup_irq_levels(unsigned int level_bits)
+{
+ __sio_fixup_irq_levels(level_bits, true);
+}
+
static inline int
noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
@@ -181,7 +197,14 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
const long min_idsel = 6, max_idsel = 14, irqs_per_slot = 5;
int irq = COMMON_TABLE_LOOKUP, tmp;
tmp = __kernel_extbl(alpha_mv.sys.sio.route_tab, irq);
- return irq >= 0 ? tmp : -1;
+
+ irq = irq >= 0 ? tmp : -1;
+
+ /* Fixup IRQ level if an actual IRQ mapping is detected */
+ if (sio_pci_dev_irq_needs_level(dev) && irq >= 0)
+ __sio_fixup_irq_levels(1 << irq, false);
+
+ return irq;
}
static inline int
diff --git a/arch/alpha/lib/ev6-memset.S b/arch/alpha/lib/ev6-memset.S
index 316a99aa9efe..1cfcfbbea6f0 100644
--- a/arch/alpha/lib/ev6-memset.S
+++ b/arch/alpha/lib/ev6-memset.S
@@ -18,7 +18,7 @@
* The algorithm for the leading and trailing quadwords remains the same,
* however the loop has been unrolled to enable better memory throughput,
* and the code has been replicated for each of the entry points: __memset
- * and __memsetw to permit better scheduling to eliminate the stalling
+ * and __memset16 to permit better scheduling to eliminate the stalling
* encountered during the mask replication.
* A future enhancement might be to put in a byte store loop for really
* small (say < 32 bytes) memset()s. Whether or not that change would be
@@ -34,7 +34,7 @@
.globl memset
.globl __memset
.globl ___memset
- .globl __memsetw
+ .globl __memset16
.globl __constant_c_memset
.ent ___memset
@@ -415,9 +415,9 @@ end:
* to mask stalls. Note that entry point names also had to change
*/
.align 5
- .ent __memsetw
+ .ent __memset16
-__memsetw:
+__memset16:
.frame $30,0,$26,0
.prologue 0
@@ -596,8 +596,8 @@ end_w:
nop
ret $31,($26),1 # L0 :
- .end __memsetw
- EXPORT_SYMBOL(__memsetw)
+ .end __memset16
+ EXPORT_SYMBOL(__memset16)
memset = ___memset
__memset = ___memset
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 4e6e9f57e790..dc91c663bcc0 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -35,6 +35,14 @@
reg = <0x80 0x10>, <0x100 0x10>;
#clock-cells = <0>;
clocks = <&input_clk>;
+
+ /*
+ * Set initial core pll output frequency to 90MHz.
+ * It will be applied at the core pll driver probing
+ * on early boot.
+ */
+ assigned-clocks = <&core_clk>;
+ assigned-clock-rates = <90000000>;
};
core_intc: archs-intc@cpu {
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 63954a8b0100..69ff4895f2ba 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -35,6 +35,14 @@
reg = <0x80 0x10>, <0x100 0x10>;
#clock-cells = <0>;
clocks = <&input_clk>;
+
+ /*
+ * Set initial core pll output frequency to 100MHz.
+ * It will be applied at the core pll driver probing
+ * on early boot.
+ */
+ assigned-clocks = <&core_clk>;
+ assigned-clock-rates = <100000000>;
};
core_intc: archs-intc@cpu {
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 8f627c200d60..006aa3de5348 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -114,6 +114,14 @@
reg = <0x00 0x10>, <0x14B8 0x4>;
#clock-cells = <0>;
clocks = <&input_clk>;
+
+ /*
+ * Set initial core pll output frequency to 1GHz.
+ * It will be applied at the core pll driver probing
+ * on early boot.
+ */
+ assigned-clocks = <&core_clk>;
+ assigned-clock-rates = <1000000000>;
};
serial: serial@5000 {
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 7b8f8faf8a24..ac6b0ed8341e 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -49,10 +49,11 @@ CONFIG_SERIAL_8250_DW=y
CONFIG_SERIAL_OF_PLATFORM=y
# CONFIG_HW_RANDOM is not set
# CONFIG_HWMON is not set
+CONFIG_DRM=y
+# CONFIG_DRM_FBDEV_EMULATION is not set
+CONFIG_DRM_UDL=y
CONFIG_FB=y
-CONFIG_FB_UDL=y
CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_USB=y
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_HCD_PLATFORM=y
CONFIG_USB_OHCI_HCD=y
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 2d79e527fa50..c85947bac5e5 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -62,9 +62,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
static inline __attribute_const__ struct thread_info *current_thread_info(void)
{
register unsigned long sp asm("sp");
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index f35974ee7264..c9173c02081c 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -668,6 +668,7 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
return 0;
__asm__ __volatile__(
+ " mov lp_count, %5 \n"
" lp 3f \n"
"1: ldb.ab %3, [%2, 1] \n"
" breq.d %3, 0, 3f \n"
@@ -684,8 +685,8 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
" .word 1b, 4b \n"
" .previous \n"
: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
- : "g"(-EFAULT), "l"(count)
- : "memory");
+ : "g"(-EFAULT), "r"(count)
+ : "lp_count", "lp_start", "lp_end", "memory");
return res;
}
diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild
index fa6d0ff4ff89..170b5db64afe 100644
--- a/arch/arc/include/uapi/asm/Kbuild
+++ b/arch/arc/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 7ef7d9a8ff89..9d27331fe69a 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -199,7 +199,7 @@ static void read_arc_build_cfg_regs(void)
unsigned int exec_ctrl;
READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
- cpu->extn.dual_enb = exec_ctrl & 1;
+ cpu->extn.dual_enb = !(exec_ctrl & 1);
/* dual issue always present for this core */
cpu->extn.dual = 1;
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 74315f302971..bf40e06f3fb8 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -163,7 +163,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
*/
static int __print_sym(unsigned int address, void *unused)
{
- __print_symbol(" %s\n", address);
+ printk(" %pS\n", (void *)address);
return 0;
}
diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c
index bcd7c9fc5d0f..b123558bf0bb 100644
--- a/arch/arc/kernel/traps.c
+++ b/arch/arc/kernel/traps.c
@@ -65,12 +65,14 @@ unhandled_exception(const char *str, struct pt_regs *regs, siginfo_t *info)
#define DO_ERROR_INFO(signr, str, name, sicode) \
int name(unsigned long address, struct pt_regs *regs) \
{ \
- siginfo_t info = { \
- .si_signo = signr, \
- .si_errno = 0, \
- .si_code = sicode, \
- .si_addr = (void __user *)address, \
- }; \
+ siginfo_t info; \
+ \
+ clear_siginfo(&info); \
+ info.si_signo = signr; \
+ info.si_errno = 0; \
+ info.si_code = sicode; \
+ info.si_addr = (void __user *)address; \
+ \
return unhandled_exception(str, regs, &info);\
}
@@ -83,6 +85,7 @@ DO_ERROR_INFO(SIGILL, "Illegal Insn (or Seq)", insterror_is_error, ILL_ILLOPC)
DO_ERROR_INFO(SIGBUS, "Invalid Mem Access", __weak do_memory_error, BUS_ADRERR)
DO_ERROR_INFO(SIGTRAP, "Breakpoint Set", trap_is_brkpt, TRAP_BRKPT)
DO_ERROR_INFO(SIGBUS, "Misaligned Access", do_misaligned_error, BUS_ADRALN)
+DO_ERROR_INFO(SIGSEGV, "gcc generated __builtin_trap", do_trap5_error, 0)
/*
* Entry Point for Misaligned Data access Exception, for emulating in software
@@ -115,6 +118,8 @@ void do_machine_check_fault(unsigned long address, struct pt_regs *regs)
* Thus TRAP_S <n> can be used for specific purpose
* -1 used for software breakpointing (gdb)
* -2 used by kprobes
+ * -5 __builtin_trap() generated by gcc (2018.03 onwards) for toggle such as
+ * -fno-isolate-erroneous-paths-dereference
*/
void do_non_swi_trap(unsigned long address, struct pt_regs *regs)
{
@@ -134,6 +139,9 @@ void do_non_swi_trap(unsigned long address, struct pt_regs *regs)
kgdb_trap(regs);
break;
+ case 5:
+ do_trap5_error(address, regs);
+ break;
default:
break;
}
@@ -155,3 +163,11 @@ void do_insterror_or_kprobe(unsigned long address, struct pt_regs *regs)
insterror_is_error(address, regs);
}
+
+/*
+ * abort() call generated by older gcc for __builtin_trap()
+ */
+void abort(void)
+{
+ __asm__ __volatile__("trap_s 5\n");
+}
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 7d8c1d6c2f60..6e9a0a9a6a04 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -163,6 +163,9 @@ static void show_ecr_verbose(struct pt_regs *regs)
else
pr_cont("Bus Error, check PRM\n");
#endif
+ } else if (vec == ECR_V_TRAP) {
+ if (regs->ecr_param == 5)
+ pr_cont("gcc generated __builtin_trap\n");
} else {
pr_cont("Check Programmer's Manual\n");
}
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index f1ac6790da5f..46544e88492d 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -317,25 +317,23 @@ static void __init axs103_early_init(void)
* Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack
* of fudging the freq in DT
*/
+#define AXS103_QUAD_CORE_CPU_FREQ_HZ 50000000
+
unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
if (num_cores > 2) {
- u32 freq = 50, orig;
- /*
- * TODO: use cpu node "cpu-freq" param instead of platform-specific
- * "/cpu_card/core_clk" as it works only if we use fixed-clock for cpu.
- */
+ u32 freq;
int off = fdt_path_offset(initial_boot_params, "/cpu_card/core_clk");
const struct fdt_property *prop;
prop = fdt_get_property(initial_boot_params, off,
- "clock-frequency", NULL);
- orig = be32_to_cpu(*(u32*)(prop->data)) / 1000000;
+ "assigned-clock-rates", NULL);
+ freq = be32_to_cpu(*(u32 *)(prop->data));
/* Patching .dtb in-place with new core clock value */
- if (freq != orig ) {
- freq = cpu_to_be32(freq * 1000000);
+ if (freq != AXS103_QUAD_CORE_CPU_FREQ_HZ) {
+ freq = cpu_to_be32(AXS103_QUAD_CORE_CPU_FREQ_HZ);
fdt_setprop_inplace(initial_boot_params, off,
- "clock-frequency", &freq, sizeof(freq));
+ "assigned-clock-rates", &freq, sizeof(freq));
}
}
#endif
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index fd0ae5e38639..2958aedb649a 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -38,42 +38,6 @@ static void __init hsdk_init_per_cpu(unsigned int cpu)
#define CREG_PAE (CREG_BASE + 0x180)
#define CREG_PAE_UPDATE (CREG_BASE + 0x194)
-#define CREG_CORE_IF_CLK_DIV (CREG_BASE + 0x4B8)
-#define CREG_CORE_IF_CLK_DIV_2 0x1
-#define CGU_BASE ARC_PERIPHERAL_BASE
-#define CGU_PLL_STATUS (ARC_PERIPHERAL_BASE + 0x4)
-#define CGU_PLL_CTRL (ARC_PERIPHERAL_BASE + 0x0)
-#define CGU_PLL_STATUS_LOCK BIT(0)
-#define CGU_PLL_STATUS_ERR BIT(1)
-#define CGU_PLL_CTRL_1GHZ 0x3A10
-#define HSDK_PLL_LOCK_TIMEOUT 500
-
-#define HSDK_PLL_LOCKED() \
- !!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_LOCK)
-
-#define HSDK_PLL_ERR() \
- !!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_ERR)
-
-static void __init hsdk_set_cpu_freq_1ghz(void)
-{
- u32 timeout = HSDK_PLL_LOCK_TIMEOUT;
-
- /*
- * As we set cpu clock which exceeds 500MHz, the divider for the interface
- * clock must be programmed to div-by-2.
- */
- iowrite32(CREG_CORE_IF_CLK_DIV_2, (void __iomem *) CREG_CORE_IF_CLK_DIV);
-
- /* Set cpu clock to 1GHz */
- iowrite32(CGU_PLL_CTRL_1GHZ, (void __iomem *) CGU_PLL_CTRL);
-
- while (!HSDK_PLL_LOCKED() && timeout--)
- cpu_relax();
-
- if (!HSDK_PLL_LOCKED() || HSDK_PLL_ERR())
- pr_err("Failed to setup CPU frequency to 1GHz!");
-}
-
#define SDIO_BASE (ARC_PERIPHERAL_BASE + 0xA000)
#define SDIO_UHS_REG_EXT (SDIO_BASE + 0x108)
#define SDIO_UHS_REG_EXT_DIV_2 (2 << 30)
@@ -98,12 +62,6 @@ static void __init hsdk_init_early(void)
* minimum possible div-by-2.
*/
iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
-
- /*
- * Setup CPU frequency to 1GHz.
- * TODO: remove it after smart hsdk pll driver will be introduced.
- */
- hsdk_set_cpu_freq_1ghz();
}
static const char *hsdk_compat[] __initconst = {
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 1b81c4e75772..d37f95025807 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -630,6 +630,7 @@
reg-names = "phy";
status = "disabled";
ti,ctrl_mod = <&usb_ctrl_mod>;
+ #phy-cells = <0>;
};
usb0: usb@47401000 {
@@ -678,6 +679,7 @@
reg-names = "phy";
status = "disabled";
ti,ctrl_mod = <&usb_ctrl_mod>;
+ #phy-cells = <0>;
};
usb1: usb@47401800 {
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index e5b061469bf8..4714a59fd86d 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -927,7 +927,8 @@
reg = <0x48038000 0x2000>,
<0x46000000 0x400000>;
reg-names = "mpu", "dat";
- interrupts = <80>, <81>;
+ interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "tx", "rx";
status = "disabled";
dmas = <&edma 8 2>,
@@ -941,7 +942,8 @@
reg = <0x4803C000 0x2000>,
<0x46400000 0x400000>;
reg-names = "mpu", "dat";
- interrupts = <82>, <83>;
+ interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "tx", "rx";
status = "disabled";
dmas = <&edma 10 2>,
diff --git a/arch/arm/boot/dts/am437x-cm-t43.dts b/arch/arm/boot/dts/am437x-cm-t43.dts
index 9e92d480576b..3b9a94c274a7 100644
--- a/arch/arm/boot/dts/am437x-cm-t43.dts
+++ b/arch/arm/boot/dts/am437x-cm-t43.dts
@@ -301,8 +301,8 @@
status = "okay";
pinctrl-names = "default";
pinctrl-0 = <&spi0_pins>;
- dmas = <&edma 16
- &edma 17>;
+ dmas = <&edma 16 0
+ &edma 17 0>;
dma-names = "tx0", "rx0";
flash: w25q64cvzpig@0 {
diff --git a/arch/arm/boot/dts/armada-385-db-ap.dts b/arch/arm/boot/dts/armada-385-db-ap.dts
index 25d2d720dc0e..678aa023335d 100644
--- a/arch/arm/boot/dts/armada-385-db-ap.dts
+++ b/arch/arm/boot/dts/armada-385-db-ap.dts
@@ -236,6 +236,7 @@
usb3_phy: usb3_phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&reg_xhci0_vbus>;
+ #phy-cells = <0>;
};
reg_xhci0_vbus: xhci0-vbus {
diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi
index e1f355ffc8f7..434dc9aaa5e4 100644
--- a/arch/arm/boot/dts/armada-385-linksys.dtsi
+++ b/arch/arm/boot/dts/armada-385-linksys.dtsi
@@ -66,6 +66,7 @@
usb3_1_phy: usb3_1-phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&usb3_1_vbus>;
+ #phy-cells = <0>;
};
usb3_1_vbus: usb3_1-vbus {
diff --git a/arch/arm/boot/dts/armada-385-synology-ds116.dts b/arch/arm/boot/dts/armada-385-synology-ds116.dts
index 36ad571e76f3..0a3552ebda3b 100644
--- a/arch/arm/boot/dts/armada-385-synology-ds116.dts
+++ b/arch/arm/boot/dts/armada-385-synology-ds116.dts
@@ -191,11 +191,13 @@
usb3_0_phy: usb3_0_phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&reg_usb3_0_vbus>;
+ #phy-cells = <0>;
};
usb3_1_phy: usb3_1_phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&reg_usb3_1_vbus>;
+ #phy-cells = <0>;
};
reg_usb3_0_vbus: usb3-vbus0 {
diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts
index f503955dbd3b..51b4ee6df130 100644
--- a/arch/arm/boot/dts/armada-388-gp.dts
+++ b/arch/arm/boot/dts/armada-388-gp.dts
@@ -276,11 +276,13 @@
usb2_1_phy: usb2_1_phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&reg_usb2_1_vbus>;
+ #phy-cells = <0>;
};
usb3_phy: usb3_phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&reg_usb3_vbus>;
+ #phy-cells = <0>;
};
reg_usb3_vbus: usb3-vbus {
diff --git a/arch/arm/boot/dts/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed-g4.dtsi
index 45d815a86d42..de08d9045cb8 100644
--- a/arch/arm/boot/dts/aspeed-g4.dtsi
+++ b/arch/arm/boot/dts/aspeed-g4.dtsi
@@ -219,7 +219,7 @@
compatible = "aspeed,ast2400-vuart";
reg = <0x1e787000 0x40>;
reg-shift = <2>;
- interrupts = <10>;
+ interrupts = <8>;
clocks = <&clk_uart>;
no-loopback-test;
status = "disabled";
diff --git a/arch/arm/boot/dts/at91-tse850-3.dts b/arch/arm/boot/dts/at91-tse850-3.dts
index 5f29010cdbd8..9b82cc8843e1 100644
--- a/arch/arm/boot/dts/at91-tse850-3.dts
+++ b/arch/arm/boot/dts/at91-tse850-3.dts
@@ -221,6 +221,7 @@
jc42@18 {
compatible = "nxp,se97b", "jedec,jc-42.4-temp";
reg = <0x18>;
+ smbus-timeout-disable;
};
dpot: mcp4651-104@28 {
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index 528b9e3bc1da..dcc55aa84583 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -85,7 +85,7 @@
timer@20200 {
compatible = "arm,cortex-a9-global-timer";
reg = <0x20200 0x100>;
- interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
clocks = <&periph_clk>;
};
@@ -93,7 +93,7 @@
compatible = "arm,cortex-a9-twd-timer";
reg = <0x20600 0x20>;
interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
- IRQ_TYPE_LEVEL_HIGH)>;
+ IRQ_TYPE_EDGE_RISING)>;
clocks = <&periph_clk>;
};
diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi
index 61e158003509..1dfd76442777 100644
--- a/arch/arm/boot/dts/bcm2836.dtsi
+++ b/arch/arm/boot/dts/bcm2836.dtsi
@@ -13,24 +13,24 @@
compatible = "brcm,bcm2836-l1-intc";
reg = <0x40000000 0x100>;
interrupt-controller;
- #interrupt-cells = <1>;
+ #interrupt-cells = <2>;
interrupt-parent = <&local_intc>;
};
arm-pmu {
compatible = "arm,cortex-a7-pmu";
interrupt-parent = <&local_intc>;
- interrupts = <9>;
+ interrupts = <9 IRQ_TYPE_LEVEL_HIGH>;
};
};
timer {
compatible = "arm,armv7-timer";
interrupt-parent = <&local_intc>;
- interrupts = <0>, // PHYS_SECURE_PPI
- <1>, // PHYS_NONSECURE_PPI
- <3>, // VIRT_PPI
- <2>; // HYP_PPI
+ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>, // PHYS_SECURE_PPI
+ <1 IRQ_TYPE_LEVEL_HIGH>, // PHYS_NONSECURE_PPI
+ <3 IRQ_TYPE_LEVEL_HIGH>, // VIRT_PPI
+ <2 IRQ_TYPE_LEVEL_HIGH>; // HYP_PPI
always-on;
};
@@ -76,7 +76,7 @@
compatible = "brcm,bcm2836-armctrl-ic";
reg = <0x7e00b200 0x200>;
interrupt-parent = <&local_intc>;
- interrupts = <8>;
+ interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
};
&cpu_thermal {
diff --git a/arch/arm/boot/dts/bcm2837.dtsi b/arch/arm/boot/dts/bcm2837.dtsi
index bc1cca5cf43c..efa7d3387ab2 100644
--- a/arch/arm/boot/dts/bcm2837.dtsi
+++ b/arch/arm/boot/dts/bcm2837.dtsi
@@ -12,7 +12,7 @@
compatible = "brcm,bcm2836-l1-intc";
reg = <0x40000000 0x100>;
interrupt-controller;
- #interrupt-cells = <1>;
+ #interrupt-cells = <2>;
interrupt-parent = <&local_intc>;
};
};
@@ -20,10 +20,10 @@
timer {
compatible = "arm,armv7-timer";
interrupt-parent = <&local_intc>;
- interrupts = <0>, // PHYS_SECURE_PPI
- <1>, // PHYS_NONSECURE_PPI
- <3>, // VIRT_PPI
- <2>; // HYP_PPI
+ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>, // PHYS_SECURE_PPI
+ <1 IRQ_TYPE_LEVEL_HIGH>, // PHYS_NONSECURE_PPI
+ <3 IRQ_TYPE_LEVEL_HIGH>, // VIRT_PPI
+ <2 IRQ_TYPE_LEVEL_HIGH>; // HYP_PPI
always-on;
};
@@ -73,7 +73,7 @@
compatible = "brcm,bcm2836-armctrl-ic";
reg = <0x7e00b200 0x200>;
interrupt-parent = <&local_intc>;
- interrupts = <8>;
+ interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
};
&cpu_thermal {
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 013431e3d7c3..18db25a5a66e 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -2,6 +2,7 @@
#include <dt-bindings/clock/bcm2835.h>
#include <dt-bindings/clock/bcm2835-aux.h>
#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
/* firmware-provided startup stubs live here, where the secondary CPUs are
* spinning.
@@ -639,5 +640,6 @@
usbphy: phy {
compatible = "usb-nop-xceiv";
+ #phy-cells = <0>;
};
};
diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts
index 3bc50849d013..b8bde13de90a 100644
--- a/arch/arm/boot/dts/bcm958623hr.dts
+++ b/arch/arm/boot/dts/bcm958623hr.dts
@@ -141,10 +141,6 @@
status = "okay";
};
-&sata {
- status = "okay";
-};
-
&qspi {
bspi-sel = <0>;
flash: m25p80@0 {
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
index d94d14b3c745..6a44b8021702 100644
--- a/arch/arm/boot/dts/bcm958625hr.dts
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -177,10 +177,6 @@
status = "okay";
};
-&sata {
- status = "okay";
-};
-
&srab {
compatible = "brcm,bcm58625-srab", "brcm,nsp-srab";
status = "okay";
diff --git a/arch/arm/boot/dts/da850-lcdk.dts b/arch/arm/boot/dts/da850-lcdk.dts
index eed89e659143..a1f4d6d5a569 100644
--- a/arch/arm/boot/dts/da850-lcdk.dts
+++ b/arch/arm/boot/dts/da850-lcdk.dts
@@ -293,12 +293,12 @@
label = "u-boot env";
reg = <0 0x020000>;
};
- partition@0x020000 {
+ partition@20000 {
/* The LCDK defaults to booting from this partition */
label = "u-boot";
reg = <0x020000 0x080000>;
};
- partition@0x0a0000 {
+ partition@a0000 {
label = "free space";
reg = <0x0a0000 0>;
};
diff --git a/arch/arm/boot/dts/da850-lego-ev3.dts b/arch/arm/boot/dts/da850-lego-ev3.dts
index 413dbd5d9f64..81942ae83e1f 100644
--- a/arch/arm/boot/dts/da850-lego-ev3.dts
+++ b/arch/arm/boot/dts/da850-lego-ev3.dts
@@ -178,7 +178,7 @@
*/
battery {
pinctrl-names = "default";
- pintctrl-0 = <&battery_pins>;
+ pinctrl-0 = <&battery_pins>;
compatible = "lego,ev3-battery";
io-channels = <&adc 4>, <&adc 3>;
io-channel-names = "voltage", "current";
@@ -392,7 +392,7 @@
batt_volt_en {
gpio-hog;
gpios = <6 GPIO_ACTIVE_HIGH>;
- output-low;
+ output-high;
};
};
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index 9708157f5daf..681f5487406e 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -75,6 +75,7 @@
reg = <0x47401300 0x100>;
reg-names = "phy";
ti,ctrl_mod = <&usb_ctrl_mod>;
+ #phy-cells = <0>;
};
usb0: usb@47401000 {
@@ -385,6 +386,7 @@
reg = <0x1b00 0x100>;
reg-names = "phy";
ti,ctrl_mod = <&usb_ctrl_mod>;
+ #phy-cells = <0>;
};
};
diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts
index b2b95ff205e8..0029ec27819c 100644
--- a/arch/arm/boot/dts/exynos5800-peach-pi.dts
+++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts
@@ -664,6 +664,10 @@
status = "okay";
};
+&mixer {
+ status = "okay";
+};
+
/* eMMC flash */
&mmc_0 {
status = "okay";
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 589a67c5f796..84f17f7abb71 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -433,15 +433,6 @@
clock-names = "ipg", "per";
};
- srtc: srtc@53fa4000 {
- compatible = "fsl,imx53-rtc", "fsl,imx25-rtc";
- reg = <0x53fa4000 0x4000>;
- interrupts = <24>;
- interrupt-parent = <&tzic>;
- clocks = <&clks IMX5_CLK_SRTC_GATE>;
- clock-names = "ipg";
- };
-
iomuxc: iomuxc@53fa8000 {
compatible = "fsl,imx53-iomuxc";
reg = <0x53fa8000 0x4000>;
diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi
index d5181f85ca9c..963e1698fe1d 100644
--- a/arch/arm/boot/dts/imx6ul.dtsi
+++ b/arch/arm/boot/dts/imx6ul.dtsi
@@ -68,12 +68,14 @@
clock-latency = <61036>; /* two CLK32 periods */
operating-points = <
/* kHz uV */
+ 696000 1275000
528000 1175000
396000 1025000
198000 950000
>;
fsl,soc-operating-points = <
/* KHz uV */
+ 696000 1275000
528000 1175000
396000 1175000
198000 1175000
diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
index cf2f5240e176..27cc913ca0f5 100644
--- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
+++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
@@ -53,7 +53,8 @@
};
pinctrl: pin-controller@10000 {
- pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>;
+ pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header
+ &pmx_gpio_header_gpo>;
pinctrl-names = "default";
pmx_uart0: pmx-uart0 {
@@ -85,11 +86,16 @@
* ground.
*/
pmx_gpio_header: pmx-gpio-header {
- marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28",
+ marvell,pins = "mpp17", "mpp29", "mpp28",
"mpp35", "mpp34", "mpp40";
marvell,function = "gpio";
};
+ pmx_gpio_header_gpo: pxm-gpio-header-gpo {
+ marvell,pins = "mpp7";
+ marvell,function = "gpo";
+ };
+
pmx_gpio_init: pmx-init {
marvell,pins = "mpp38";
marvell,function = "gpio";
diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
index 38faa90007d7..2fa5eb4bd402 100644
--- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
@@ -72,7 +72,8 @@
};
&gpmc {
- ranges = <1 0 0x08000000 0x1000000>; /* CS1: 16MB for LAN9221 */
+ ranges = <0 0 0x30000000 0x1000000 /* CS0: 16MB for NAND */
+ 1 0 0x2c000000 0x1000000>; /* CS1: 16MB for LAN9221 */
ethernet@gpmc {
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index 26cce4d18405..29cb804d10cc 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -33,11 +33,12 @@
hsusb2_phy: hsusb2_phy {
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>; /* gpio_4 */
+ #phy-cells = <0>;
};
};
&gpmc {
- ranges = <0 0 0x00000000 0x1000000>; /* CS0: 16MB for NAND */
+ ranges = <0 0 0x30000000 0x1000000>; /* CS0: 16MB for NAND */
nand@0,0 {
compatible = "ti,omap2-nand";
@@ -121,7 +122,7 @@
&mmc3 {
interrupts-extended = <&intc 94 &omap3_pmx_core2 0x46>;
- pinctrl-0 = <&mmc3_pins>;
+ pinctrl-0 = <&mmc3_pins &wl127x_gpio>;
pinctrl-names = "default";
vmmc-supply = <&wl12xx_vmmc>;
non-removable;
@@ -132,8 +133,8 @@
wlcore: wlcore@2 {
compatible = "ti,wl1273";
reg = <2>;
- interrupt-parent = <&gpio5>;
- interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */
+ interrupt-parent = <&gpio1>;
+ interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; /* gpio 2 */
ref-clock-frequency = <26000000>;
};
};
@@ -157,8 +158,6 @@
OMAP3_CORE1_IOPAD(0x2166, PIN_INPUT_PULLUP | MUX_MODE3) /* sdmmc2_dat5.sdmmc3_dat1 */
OMAP3_CORE1_IOPAD(0x2168, PIN_INPUT_PULLUP | MUX_MODE3) /* sdmmc2_dat6.sdmmc3_dat2 */
OMAP3_CORE1_IOPAD(0x216a, PIN_INPUT_PULLUP | MUX_MODE3) /* sdmmc2_dat6.sdmmc3_dat3 */
- OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT_PULLUP | MUX_MODE4) /* mcbsp4_clkx.gpio_152 */
- OMAP3_CORE1_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4) /* sys_boot1.gpio_3 */
OMAP3_CORE1_IOPAD(0x21d0, PIN_INPUT_PULLUP | MUX_MODE3) /* mcspi1_cs1.sdmmc3_cmd */
OMAP3_CORE1_IOPAD(0x21d2, PIN_INPUT_PULLUP | MUX_MODE3) /* mcspi1_cs2.sdmmc_clk */
>;
@@ -228,6 +227,12 @@
OMAP3_WKUP_IOPAD(0x2a0e, PIN_OUTPUT | MUX_MODE4) /* sys_boot2.gpio_4 */
>;
};
+ wl127x_gpio: pinmux_wl127x_gpio_pin {
+ pinctrl-single,pins = <
+ OMAP3_WKUP_IOPAD(0x2a0c, PIN_INPUT | MUX_MODE4) /* sys_boot0.gpio_2 */
+ OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4) /* sys_boot1.gpio_3 */
+ >;
+ };
};
&omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/ls1021a-qds.dts b/arch/arm/boot/dts/ls1021a-qds.dts
index 940875316d0f..67b4de0e3439 100644
--- a/arch/arm/boot/dts/ls1021a-qds.dts
+++ b/arch/arm/boot/dts/ls1021a-qds.dts
@@ -215,7 +215,7 @@
reg = <0x2a>;
VDDA-supply = <&reg_3p3v>;
VDDIO-supply = <&reg_3p3v>;
- clocks = <&sys_mclk 1>;
+ clocks = <&sys_mclk>;
};
};
};
diff --git a/arch/arm/boot/dts/ls1021a-twr.dts b/arch/arm/boot/dts/ls1021a-twr.dts
index a8b148ad1dd2..44715c8ef756 100644
--- a/arch/arm/boot/dts/ls1021a-twr.dts
+++ b/arch/arm/boot/dts/ls1021a-twr.dts
@@ -187,7 +187,7 @@
reg = <0x0a>;
VDDA-supply = <&reg_3p3v>;
VDDIO-supply = <&reg_3p3v>;
- clocks = <&sys_mclk 1>;
+ clocks = <&sys_mclk>;
};
};
diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi
index 4926133077b3..0d9faf1a51ea 100644
--- a/arch/arm/boot/dts/meson.dtsi
+++ b/arch/arm/boot/dts/meson.dtsi
@@ -85,15 +85,6 @@
reg = <0x7c00 0x200>;
};
- gpio_intc: interrupt-controller@9880 {
- compatible = "amlogic,meson-gpio-intc";
- reg = <0xc1109880 0x10>;
- interrupt-controller;
- #interrupt-cells = <2>;
- amlogic,channel-interrupts = <64 65 66 67 68 69 70 71>;
- status = "disabled";
- };
-
hwrng: rng@8100 {
compatible = "amlogic,meson-rng";
reg = <0x8100 0x8>;
@@ -191,6 +182,15 @@
status = "disabled";
};
+ gpio_intc: interrupt-controller@9880 {
+ compatible = "amlogic,meson-gpio-intc";
+ reg = <0x9880 0x10>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ amlogic,channel-interrupts = <64 65 66 67 68 69 70 71>;
+ status = "disabled";
+ };
+
wdt: watchdog@9900 {
compatible = "amlogic,meson6-wdt";
reg = <0x9900 0x8>;
diff --git a/arch/arm/boot/dts/nspire.dtsi b/arch/arm/boot/dts/nspire.dtsi
index ec2283b1a638..1a5ae4cd107f 100644
--- a/arch/arm/boot/dts/nspire.dtsi
+++ b/arch/arm/boot/dts/nspire.dtsi
@@ -56,6 +56,7 @@
usb_phy: usb_phy {
compatible = "usb-nop-xceiv";
+ #phy-cells = <0>;
};
vbus_reg: vbus_reg {
diff --git a/arch/arm/boot/dts/omap2420-n8x0-common.dtsi b/arch/arm/boot/dts/omap2420-n8x0-common.dtsi
index 1df3ace3af92..63b0b4921e4e 100644
--- a/arch/arm/boot/dts/omap2420-n8x0-common.dtsi
+++ b/arch/arm/boot/dts/omap2420-n8x0-common.dtsi
@@ -52,6 +52,7 @@
onenand@0,0 {
#address-cells = <1>;
#size-cells = <1>;
+ compatible = "ti,omap2-onenand";
reg = <0 0 0x20000>; /* CS0, offset 0, IO size 128K */
gpmc,sync-read;
diff --git a/arch/arm/boot/dts/omap3-beagle-xm.dts b/arch/arm/boot/dts/omap3-beagle-xm.dts
index 683b96a8f73e..0349fcc9dc26 100644
--- a/arch/arm/boot/dts/omap3-beagle-xm.dts
+++ b/arch/arm/boot/dts/omap3-beagle-xm.dts
@@ -90,6 +90,7 @@
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio5 19 GPIO_ACTIVE_LOW>; /* gpio_147 */
vcc-supply = <&hsusb2_power>;
+ #phy-cells = <0>;
};
tfp410: encoder0 {
diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts
index 4d2eaf843fa9..3ca8991a6c3e 100644
--- a/arch/arm/boot/dts/omap3-beagle.dts
+++ b/arch/arm/boot/dts/omap3-beagle.dts
@@ -64,6 +64,7 @@
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio5 19 GPIO_ACTIVE_LOW>; /* gpio_147 */
vcc-supply = <&hsusb2_power>;
+ #phy-cells = <0>;
};
sound {
diff --git a/arch/arm/boot/dts/omap3-cm-t3x.dtsi b/arch/arm/boot/dts/omap3-cm-t3x.dtsi
index 31d5ebf38892..ab6003fe5a43 100644
--- a/arch/arm/boot/dts/omap3-cm-t3x.dtsi
+++ b/arch/arm/boot/dts/omap3-cm-t3x.dtsi
@@ -43,12 +43,14 @@
hsusb1_phy: hsusb1_phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&hsusb1_power>;
+ #phy-cells = <0>;
};
/* HS USB Host PHY on PORT 2 */
hsusb2_phy: hsusb2_phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&hsusb2_power>;
+ #phy-cells = <0>;
};
ads7846reg: ads7846-reg {
diff --git a/arch/arm/boot/dts/omap3-evm-common.dtsi b/arch/arm/boot/dts/omap3-evm-common.dtsi
index dbc3f030a16c..ee64191e41ca 100644
--- a/arch/arm/boot/dts/omap3-evm-common.dtsi
+++ b/arch/arm/boot/dts/omap3-evm-common.dtsi
@@ -29,6 +29,7 @@
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio1 21 GPIO_ACTIVE_LOW>; /* gpio_21 */
vcc-supply = <&hsusb2_power>;
+ #phy-cells = <0>;
};
leds {
diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi
index 4504908c23fe..3dc56fb156b7 100644
--- a/arch/arm/boot/dts/omap3-gta04.dtsi
+++ b/arch/arm/boot/dts/omap3-gta04.dtsi
@@ -120,6 +120,7 @@
hsusb2_phy: hsusb2_phy {
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio6 14 GPIO_ACTIVE_LOW>;
+ #phy-cells = <0>;
};
tv0: connector {
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index 4ad7d5565906..f33cc80c9dbc 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -147,32 +147,32 @@
gpmc,sync-read;
gpmc,sync-write;
gpmc,burst-length = <16>;
- gpmc,burst-read;
gpmc,burst-wrap;
+ gpmc,burst-read;
gpmc,burst-write;
gpmc,device-width = <2>; /* GPMC_DEVWIDTH_16BIT */
gpmc,mux-add-data = <2>; /* GPMC_MUX_AD */
gpmc,cs-on-ns = <0>;
- gpmc,cs-rd-off-ns = <87>;
- gpmc,cs-wr-off-ns = <87>;
+ gpmc,cs-rd-off-ns = <96>;
+ gpmc,cs-wr-off-ns = <96>;
gpmc,adv-on-ns = <0>;
- gpmc,adv-rd-off-ns = <10>;
- gpmc,adv-wr-off-ns = <10>;
- gpmc,oe-on-ns = <15>;
- gpmc,oe-off-ns = <87>;
+ gpmc,adv-rd-off-ns = <12>;
+ gpmc,adv-wr-off-ns = <12>;
+ gpmc,oe-on-ns = <18>;
+ gpmc,oe-off-ns = <96>;
gpmc,we-on-ns = <0>;
- gpmc,we-off-ns = <87>;
- gpmc,rd-cycle-ns = <112>;
- gpmc,wr-cycle-ns = <112>;
- gpmc,access-ns = <81>;
- gpmc,page-burst-access-ns = <15>;
+ gpmc,we-off-ns = <96>;
+ gpmc,rd-cycle-ns = <114>;
+ gpmc,wr-cycle-ns = <114>;
+ gpmc,access-ns = <90>;
+ gpmc,page-burst-access-ns = <12>;
gpmc,bus-turnaround-ns = <0>;
gpmc,cycle2cycle-delay-ns = <0>;
gpmc,wait-monitoring-ns = <0>;
- gpmc,clk-activation-ns = <5>;
+ gpmc,clk-activation-ns = <6>;
gpmc,wr-data-mux-bus-ns = <30>;
- gpmc,wr-access-ns = <81>;
- gpmc,sync-clk-ps = <15000>;
+ gpmc,wr-access-ns = <90>;
+ gpmc,sync-clk-ps = <12000>;
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
index 667f96245729..ecbec23af49f 100644
--- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
@@ -58,6 +58,7 @@
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio1 24 GPIO_ACTIVE_LOW>; /* gpio_24 */
vcc-supply = <&hsusb1_power>;
+ #phy-cells = <0>;
};
tfp410: encoder {
diff --git a/arch/arm/boot/dts/omap3-igep0030-common.dtsi b/arch/arm/boot/dts/omap3-igep0030-common.dtsi
index e94d9427450c..443f71707437 100644
--- a/arch/arm/boot/dts/omap3-igep0030-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0030-common.dtsi
@@ -37,6 +37,7 @@
hsusb2_phy: hsusb2_phy {
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio2 22 GPIO_ACTIVE_LOW>; /* gpio_54 */
+ #phy-cells = <0>;
};
};
diff --git a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
index 343a36d8031d..7ada1e93e166 100644
--- a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
+++ b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
@@ -51,6 +51,7 @@
hsusb1_phy: hsusb1_phy {
compatible = "usb-nop-xceiv";
vcc-supply = <&reg_vcc3>;
+ #phy-cells = <0>;
};
};
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 669c51c00c00..e7c7b8e50703 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -838,6 +838,7 @@
onenand@0,0 {
#address-cells = <1>;
#size-cells = <1>;
+ compatible = "ti,omap2-onenand";
reg = <0 0 0x20000>; /* CS0, offset 0, IO size 128K */
gpmc,sync-read;
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index 12fbb3da5fce..0d9b85317529 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -367,6 +367,7 @@
onenand@0,0 {
#address-cells = <1>;
#size-cells = <1>;
+ compatible = "ti,omap2-onenand";
reg = <0 0 0x20000>; /* CS0, offset 0, IO size 128K */
gpmc,sync-read;
diff --git a/arch/arm/boot/dts/omap3-overo-base.dtsi b/arch/arm/boot/dts/omap3-overo-base.dtsi
index f25e158e7163..ac141fcd1742 100644
--- a/arch/arm/boot/dts/omap3-overo-base.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-base.dtsi
@@ -51,6 +51,7 @@
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio6 23 GPIO_ACTIVE_LOW>; /* gpio_183 */
vcc-supply = <&hsusb2_power>;
+ #phy-cells = <0>;
};
/* Regulator to trigger the nPoweron signal of the Wifi module */
diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi
index 53e007abdc71..cd53dc6c0051 100644
--- a/arch/arm/boot/dts/omap3-pandora-common.dtsi
+++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi
@@ -205,6 +205,7 @@
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio1 16 GPIO_ACTIVE_LOW>; /* GPIO_16 */
vcc-supply = <&vaux2>;
+ #phy-cells = <0>;
};
/* HS USB Host VBUS supply
diff --git a/arch/arm/boot/dts/omap3-tao3530.dtsi b/arch/arm/boot/dts/omap3-tao3530.dtsi
index 9a601d15247b..6f5bd027b717 100644
--- a/arch/arm/boot/dts/omap3-tao3530.dtsi
+++ b/arch/arm/boot/dts/omap3-tao3530.dtsi
@@ -46,6 +46,7 @@
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio6 2 GPIO_ACTIVE_LOW>; /* gpio_162 */
vcc-supply = <&hsusb2_power>;
+ #phy-cells = <0>;
};
sound {
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 90b5c7148feb..bb33935df7b0 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -715,6 +715,7 @@
compatible = "ti,ohci-omap3";
reg = <0x48064400 0x400>;
interrupts = <76>;
+ remote-wakeup-connected;
};
usbhsehci: ehci@48064800 {
diff --git a/arch/arm/boot/dts/omap3430-sdp.dts b/arch/arm/boot/dts/omap3430-sdp.dts
index 908951eb5943..d652708f6bef 100644
--- a/arch/arm/boot/dts/omap3430-sdp.dts
+++ b/arch/arm/boot/dts/omap3430-sdp.dts
@@ -154,6 +154,7 @@
linux,mtd-name= "samsung,kfm2g16q2m-deb8";
#address-cells = <1>;
#size-cells = <1>;
+ compatible = "ti,omap2-onenand";
reg = <2 0 0x20000>; /* CS2, offset 0, IO size 4 */
gpmc,device-width = <2>;
diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts
index 8b93d37310f2..24a463f8641f 100644
--- a/arch/arm/boot/dts/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts
@@ -73,6 +73,7 @@
/* HS USB Host PHY on PORT 1 */
hsusb1_phy: hsusb1_phy {
compatible = "usb-nop-xceiv";
+ #phy-cells = <0>;
};
/* LCD regulator from sw5 source */
diff --git a/arch/arm/boot/dts/omap4-duovero.dtsi b/arch/arm/boot/dts/omap4-duovero.dtsi
index 6e6810c258eb..eb123b24c8e3 100644
--- a/arch/arm/boot/dts/omap4-duovero.dtsi
+++ b/arch/arm/boot/dts/omap4-duovero.dtsi
@@ -43,6 +43,7 @@
hsusb1_phy: hsusb1_phy {
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio2 30 GPIO_ACTIVE_LOW>; /* gpio_62 */
+ #phy-cells = <0>;
pinctrl-names = "default";
pinctrl-0 = <&hsusb1phy_pins>;
diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi
index 22c1eee9b07a..5501d1b4e6cd 100644
--- a/arch/arm/boot/dts/omap4-panda-common.dtsi
+++ b/arch/arm/boot/dts/omap4-panda-common.dtsi
@@ -89,6 +89,7 @@
hsusb1_phy: hsusb1_phy {
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio2 30 GPIO_ACTIVE_LOW>; /* gpio_62 */
+ #phy-cells = <0>;
vcc-supply = <&hsusb1_power>;
clocks = <&auxclk3_ck>;
clock-names = "main_clk";
diff --git a/arch/arm/boot/dts/omap4-var-som-om44.dtsi b/arch/arm/boot/dts/omap4-var-som-om44.dtsi
index 6500bfc8d130..10fce28ceb5b 100644
--- a/arch/arm/boot/dts/omap4-var-som-om44.dtsi
+++ b/arch/arm/boot/dts/omap4-var-som-om44.dtsi
@@ -44,6 +44,7 @@
reset-gpios = <&gpio6 17 GPIO_ACTIVE_LOW>; /* gpio 177 */
vcc-supply = <&vbat>;
+ #phy-cells = <0>;
clocks = <&auxclk3_ck>;
clock-names = "main_clk";
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 1dc5a76b3c71..cc1a07a3620f 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -398,7 +398,7 @@
elm: elm@48078000 {
compatible = "ti,am3352-elm";
reg = <0x48078000 0x2000>;
- interrupts = <4>;
+ interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
ti,hwmods = "elm";
status = "disabled";
};
@@ -1081,14 +1081,13 @@
usbhsohci: ohci@4a064800 {
compatible = "ti,ohci-omap3";
reg = <0x4a064800 0x400>;
- interrupt-parent = <&gic>;
interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
+ remote-wakeup-connected;
};
usbhsehci: ehci@4a064c00 {
compatible = "ti,ehci-omap";
reg = <0x4a064c00 0x400>;
- interrupt-parent = <&gic>;
interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
};
};
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index 575ecffb0e9e..1b20838bb9a4 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -73,12 +73,14 @@
clocks = <&auxclk1_ck>;
clock-names = "main_clk";
clock-frequency = <19200000>;
+ #phy-cells = <0>;
};
/* HS USB Host PHY on PORT 3 */
hsusb3_phy: hsusb3_phy {
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio3 15 GPIO_ACTIVE_LOW>; /* gpio3_79 ETH_NRESET */
+ #phy-cells = <0>;
};
tpd12s015: encoder {
diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts
index 5b172a04b6f1..5e21fb430a65 100644
--- a/arch/arm/boot/dts/omap5-cm-t54.dts
+++ b/arch/arm/boot/dts/omap5-cm-t54.dts
@@ -63,12 +63,14 @@
hsusb2_phy: hsusb2_phy {
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; /* gpio3_76 HUB_RESET */
+ #phy-cells = <0>;
};
/* HS USB Host PHY on PORT 3 */
hsusb3_phy: hsusb3_phy {
compatible = "usb-nop-xceiv";
reset-gpios = <&gpio3 19 GPIO_ACTIVE_LOW>; /* gpio3_83 ETH_RESET */
+ #phy-cells = <0>;
};
leds {
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 4cd0005e462f..51a7fb3d7b9a 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -940,6 +940,7 @@
compatible = "ti,ohci-omap3";
reg = <0x4a064800 0x400>;
interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
+ remote-wakeup-connected;
};
usbhsehci: ehci@4a064c00 {
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 2f017fee4009..62baabd757b6 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -1201,6 +1201,7 @@
clock-names = "extal", "usb_extal";
#clock-cells = <2>;
#power-domain-cells = <0>;
+ #reset-cells = <1>;
};
prr: chipid@ff000044 {
diff --git a/arch/arm/boot/dts/r8a7792.dtsi b/arch/arm/boot/dts/r8a7792.dtsi
index 131f65b0426e..3d080e07374c 100644
--- a/arch/arm/boot/dts/r8a7792.dtsi
+++ b/arch/arm/boot/dts/r8a7792.dtsi
@@ -829,6 +829,7 @@
clock-names = "extal";
#clock-cells = <2>;
#power-domain-cells = <0>;
+ #reset-cells = <1>;
};
};
diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi
index 58eae569b4e0..0cd1035de1a4 100644
--- a/arch/arm/boot/dts/r8a7793.dtsi
+++ b/arch/arm/boot/dts/r8a7793.dtsi
@@ -1088,6 +1088,7 @@
clock-names = "extal", "usb_extal";
#clock-cells = <2>;
#power-domain-cells = <0>;
+ #reset-cells = <1>;
};
rst: reset-controller@e6160000 {
diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index 905e50c9b524..5643976c1356 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -1099,6 +1099,7 @@
clock-names = "extal", "usb_extal";
#clock-cells = <2>;
#power-domain-cells = <0>;
+ #reset-cells = <1>;
};
rst: reset-controller@e6160000 {
diff --git a/arch/arm/boot/dts/rk3066a-marsboard.dts b/arch/arm/boot/dts/rk3066a-marsboard.dts
index c6d92c25df42..d23ee6d911ac 100644
--- a/arch/arm/boot/dts/rk3066a-marsboard.dts
+++ b/arch/arm/boot/dts/rk3066a-marsboard.dts
@@ -83,6 +83,10 @@
};
};
+&cpu0 {
+ cpu0-supply = <&vdd_arm>;
+};
+
&i2c1 {
status = "okay";
clock-frequency = <400000>;
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index cd24894ee5c6..6102e4e7f35c 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -956,7 +956,7 @@
iep_mmu: iommu@ff900800 {
compatible = "rockchip,iommu";
reg = <0x0 0xff900800 0x0 0x40>;
- interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH 0>;
+ interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "iep_mmu";
#iommu-cells = <0>;
status = "disabled";
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index b91300d49a31..4f2f2eea0755 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -502,8 +502,8 @@
reg = <0x01c16000 0x1000>;
interrupts = <58>;
clocks = <&ccu CLK_AHB_HDMI0>, <&ccu CLK_HDMI>,
- <&ccu 9>,
- <&ccu 18>;
+ <&ccu CLK_PLL_VIDEO0_2X>,
+ <&ccu CLK_PLL_VIDEO1_2X>;
clock-names = "ahb", "mod", "pll-0", "pll-1";
dmas = <&dma SUN4I_DMA_NORMAL 16>,
<&dma SUN4I_DMA_NORMAL 16>,
@@ -1104,7 +1104,7 @@
be1_out_tcon0: endpoint@0 {
reg = <0>;
- remote-endpoint = <&tcon1_in_be0>;
+ remote-endpoint = <&tcon0_in_be1>;
};
be1_out_tcon1: endpoint@1 {
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 6ae4d95e230e..316cb8b2945b 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -82,8 +82,8 @@
reg = <0x01c16000 0x1000>;
interrupts = <58>;
clocks = <&ccu CLK_AHB_HDMI>, <&ccu CLK_HDMI>,
- <&ccu 9>,
- <&ccu 16>;
+ <&ccu CLK_PLL_VIDEO0_2X>,
+ <&ccu CLK_PLL_VIDEO1_2X>;
clock-names = "ahb", "mod", "pll-0", "pll-1";
dmas = <&dma SUN4I_DMA_NORMAL 16>,
<&dma SUN4I_DMA_NORMAL 16>,
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index 8bfa12b548e0..72d3fe44ecaf 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -429,8 +429,8 @@
interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&ccu CLK_AHB1_HDMI>, <&ccu CLK_HDMI>,
<&ccu CLK_HDMI_DDC>,
- <&ccu 7>,
- <&ccu 13>;
+ <&ccu CLK_PLL_VIDEO0_2X>,
+ <&ccu CLK_PLL_VIDEO1_2X>;
clock-names = "ahb", "mod", "ddc", "pll-0", "pll-1";
resets = <&ccu RST_AHB1_HDMI>;
reset-names = "ahb";
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 68dfa82544fc..bd0cd3204273 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -581,8 +581,8 @@
reg = <0x01c16000 0x1000>;
interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&ccu CLK_AHB_HDMI0>, <&ccu CLK_HDMI>,
- <&ccu 9>,
- <&ccu 18>;
+ <&ccu CLK_PLL_VIDEO0_2X>,
+ <&ccu CLK_PLL_VIDEO1_2X>;
clock-names = "ahb", "mod", "pll-0", "pll-1";
dmas = <&dma SUN4I_DMA_NORMAL 16>,
<&dma SUN4I_DMA_NORMAL 16>,
@@ -1354,7 +1354,7 @@
be1_out_tcon0: endpoint@0 {
reg = <0>;
- remote-endpoint = <&tcon1_in_be0>;
+ remote-endpoint = <&tcon0_in_be1>;
};
be1_out_tcon1: endpoint@1 {
diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
index 98715538932f..a021ee6da396 100644
--- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
@@ -146,6 +146,7 @@
status = "okay";
axp81x: pmic@3a3 {
+ compatible = "x-powers,axp813";
reg = <0x3a3>;
interrupt-parent = <&r_intc>;
interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm/boot/dts/tango4-common.dtsi b/arch/arm/boot/dts/tango4-common.dtsi
index 0ec1b0a317b4..ff72a8efb73d 100644
--- a/arch/arm/boot/dts/tango4-common.dtsi
+++ b/arch/arm/boot/dts/tango4-common.dtsi
@@ -156,7 +156,6 @@
reg = <0x6e000 0x400>;
ranges = <0 0x6e000 0x400>;
interrupt-parent = <&gic>;
- interrupt-controller;
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
index 02a6227c717c..4b8edc8982cf 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
@@ -121,7 +121,7 @@
switch0port10: port@10 {
reg = <10>;
label = "dsa";
- phy-mode = "xgmii";
+ phy-mode = "xaui";
link = <&switch1port10>;
};
};
@@ -208,7 +208,7 @@
switch1port10: port@10 {
reg = <10>;
label = "dsa";
- phy-mode = "xgmii";
+ phy-mode = "xaui";
link = <&switch0port10>;
};
};
@@ -359,7 +359,7 @@
};
&i2c1 {
- at24mac602@0 {
+ at24mac602@50 {
compatible = "atmel,24c02";
reg = <0x50>;
read-only;
diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig
index d23b9d56a88b..95946dee9c77 100644
--- a/arch/arm/configs/aspeed_g4_defconfig
+++ b/arch/arm/configs/aspeed_g4_defconfig
@@ -1,7 +1,6 @@
CONFIG_KERNEL_XZ=y
# CONFIG_SWAP is not set
CONFIG_SYSVIPC=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_LOG_BUF_SHIFT=14
diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig
index c0ad7b82086b..8c7ea033cdc2 100644
--- a/arch/arm/configs/aspeed_g5_defconfig
+++ b/arch/arm/configs/aspeed_g5_defconfig
@@ -1,7 +1,6 @@
CONFIG_KERNEL_XZ=y
# CONFIG_SWAP is not set
CONFIG_SYSVIPC=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_LOG_BUF_SHIFT=14
diff --git a/arch/arm/configs/hisi_defconfig b/arch/arm/configs/hisi_defconfig
index b2e340b272ee..74d611e41e02 100644
--- a/arch/arm/configs/hisi_defconfig
+++ b/arch/arm/configs/hisi_defconfig
@@ -1,4 +1,3 @@
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_BLK_DEV_INITRD=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 61509c4b769f..b659244902cd 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -1,6 +1,5 @@
CONFIG_SYSVIPC=y
CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_CGROUPS=y
diff --git a/arch/arm/configs/mvebu_v7_defconfig b/arch/arm/configs/mvebu_v7_defconfig
index 69553704f2dc..ddaeda4f2e82 100644
--- a/arch/arm/configs/mvebu_v7_defconfig
+++ b/arch/arm/configs/mvebu_v7_defconfig
@@ -1,6 +1,5 @@
CONFIG_SYSVIPC=y
CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_BLK_DEV_INITRD=y
@@ -57,7 +56,7 @@ CONFIG_MTD_CFI_STAA=y
CONFIG_MTD_PHYSMAP_OF=y
CONFIG_MTD_M25P80=y
CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_PXA3xx=y
+CONFIG_MTD_NAND_MARVELL=y
CONFIG_MTD_SPI_NOR=y
CONFIG_SRAM=y
CONFIG_MTD_UBI=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 830e817a028a..837d0c9c8b0e 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -1,7 +1,6 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_BSD_PROCESS_ACCT=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index 6529cb43e0fd..2080025556b5 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -2,7 +2,6 @@
# CONFIG_SWAP is not set
CONFIG_SYSVIPC=y
CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_LOG_BUF_SHIFT=14
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 5caaf971fb50..df433abfcb02 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -10,6 +10,7 @@ CONFIG_SMP=y
CONFIG_NR_CPUS=8
CONFIG_AEABI=y
CONFIG_HIGHMEM=y
+CONFIG_CMA=y
CONFIG_ARM_APPENDED_DTB=y
CONFIG_ARM_ATAG_DTB_COMPAT=y
CONFIG_CPU_FREQ=y
@@ -33,6 +34,7 @@ CONFIG_CAN_SUN4I=y
# CONFIG_WIRELESS is not set
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DMA_CMA=y
CONFIG_BLK_DEV_SD=y
CONFIG_ATA=y
CONFIG_AHCI_SUNXI=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 6678f2929356..c819be04187e 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -1,5 +1,4 @@
CONFIG_SYSVIPC=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_IKCONFIG=y
diff --git a/arch/arm/configs/vt8500_v6_v7_defconfig b/arch/arm/configs/vt8500_v6_v7_defconfig
index 1bfaa7bfc392..9b85326ba287 100644
--- a/arch/arm/configs/vt8500_v6_v7_defconfig
+++ b/arch/arm/configs/vt8500_v6_v7_defconfig
@@ -1,4 +1,3 @@
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_BLK_DEV_INITRD=y
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index c8781450905b..3ab8b3781bfe 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -161,8 +161,7 @@
#else
#define VTTBR_X (5 - KVM_T0SZ)
#endif
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X)
#define VTTBR_VMID_SHIFT _AC(48, ULL)
#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 242151ea6908..acbf9ec7b396 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -238,6 +238,9 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
int exception_index);
+static inline void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ int exception_index) {}
+
static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
unsigned long hyp_stack_ptr,
unsigned long vector_ptr)
@@ -285,6 +288,11 @@ static inline void kvm_arm_init_debug(void) {}
static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu,
+ struct kvm_run *run)
+{
+ return false;
+}
int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
@@ -296,4 +304,6 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
/* All host FP/SIMD state is restored on guest exit, so nothing to save: */
static inline void kvm_fpsimd_flush_cpu_state(void) {}
+static inline void kvm_arm_vhe_guest_enter(void) {}
+static inline void kvm_arm_vhe_guest_exit(void) {}
#endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index fa6f2174276b..a2d176a308bd 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -211,6 +211,11 @@ static inline bool __kvm_cpu_uses_extended_idmap(void)
return false;
}
+static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
+{
+ return PTRS_PER_PGD;
+}
+
static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
pgd_t *hyp_pgd,
pgd_t *merged_hyp_pgd,
@@ -221,6 +226,18 @@ static inline unsigned int kvm_get_vmid_bits(void)
return 8;
}
+static inline void *kvm_get_hyp_vector(void)
+{
+ return kvm_ksym_ref(__kvm_hyp_vector);
+}
+
+static inline int kvm_map_vectors(void)
+{
+ return 0;
+}
+
+#define kvm_phys_to_vttbr(addr) (addr)
+
#endif /* !__ASSEMBLY__ */
#endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 2a029bceaf2f..1a7a17b2a1ba 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -221,7 +221,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
}
#define __HAVE_ARCH_PTE_SPECIAL
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) (pmd_isclear((pmd), L_PMD_SECT_RDONLY))
#define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY))
#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 776757d1604a..e71cc35de163 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -75,9 +75,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/*
* how to get the current stack pointer in C
*/
diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild
index 4d53de308ee0..4d1cc1847edf 100644
--- a/arch/arm/include/uapi/asm/Kbuild
+++ b/arch/arm/include/uapi/asm/Kbuild
@@ -7,6 +7,7 @@ generated-y += unistd-oabi.h
generated-y += unistd-eabi.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += ioctl.h
generic-y += ipcbuf.h
diff --git a/arch/arm/include/uapi/asm/siginfo.h b/arch/arm/include/uapi/asm/siginfo.h
new file mode 100644
index 000000000000..d0513880be21
--- /dev/null
+++ b/arch/arm/include/uapi/asm/siginfo.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_SIGINFO_H
+#define __ASM_SIGINFO_H
+
+#include <asm-generic/siginfo.h>
+
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME 0 /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 7f4d80c2db6b..0f07579af472 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -300,7 +300,7 @@
mov r2, sp
ldr r1, [r2, #\offset + S_PSR] @ get calling cpsr
ldr lr, [r2, #\offset + S_PC]! @ get pc
- tst r1, #0xcf
+ tst r1, #PSR_I_BIT | 0x0f
bne 1f
msr spsr_cxsf, r1 @ save in spsr_svc
#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
@@ -332,7 +332,7 @@
ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr
ldr lr, [sp, #\offset + S_PC] @ get pc
add sp, sp, #\offset + S_SP
- tst r1, #0xcf
+ tst r1, #PSR_I_BIT | 0x0f
bne 1f
msr spsr_cxsf, r1 @ save in spsr_svc
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 58e3771e4c5b..7724b0f661b3 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -390,7 +390,6 @@ static void ptrace_hbptriggered(struct perf_event *bp,
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
long num;
int i;
- siginfo_t info;
for (i = 0; i < ARM_MAX_HBP_SLOTS; ++i)
if (current->thread.debug.hbp[i] == bp)
@@ -398,12 +397,7 @@ static void ptrace_hbptriggered(struct perf_event *bp,
num = (i == ARM_MAX_HBP_SLOTS) ? 0 : ptrace_hbp_idx_to_num(i);
- info.si_signo = SIGTRAP;
- info.si_errno = (int)num;
- info.si_code = TRAP_HWBKPT;
- info.si_addr = (void __user *)(bkpt->trigger);
-
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_ptrace_errno_trap((int)num, (void __user *)(bkpt->trigger));
}
/*
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 5cf04888c581..3e26c6f7a191 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -793,7 +793,6 @@ void abort(void)
/* if that doesn't kill us, halt */
panic("Oops failed to kill thread");
}
-EXPORT_SYMBOL(abort);
void __init trap_init(void)
{
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 1712f132b80d..b83fdc06286a 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -85,7 +85,11 @@
.pushsection .text.fixup,"ax"
.align 4
9001: mov r4, #-EFAULT
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+ ldr r5, [sp, #9*4] @ *err_ptr
+#else
ldr r5, [sp, #8*4] @ *err_ptr
+#endif
str r4, [r5]
ldmia sp, {r1, r2} @ retrieve dst, len
add r2, r2, r1
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 8be04ec95adf..5ace9380626a 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -868,10 +868,10 @@ static const struct dma_slave_map dm365_edma_map[] = {
{ "spi_davinci.0", "rx", EDMA_FILTER_PARAM(0, 17) },
{ "spi_davinci.3", "tx", EDMA_FILTER_PARAM(0, 18) },
{ "spi_davinci.3", "rx", EDMA_FILTER_PARAM(0, 19) },
- { "dm6441-mmc.0", "rx", EDMA_FILTER_PARAM(0, 26) },
- { "dm6441-mmc.0", "tx", EDMA_FILTER_PARAM(0, 27) },
- { "dm6441-mmc.1", "rx", EDMA_FILTER_PARAM(0, 30) },
- { "dm6441-mmc.1", "tx", EDMA_FILTER_PARAM(0, 31) },
+ { "da830-mmc.0", "rx", EDMA_FILTER_PARAM(0, 26) },
+ { "da830-mmc.0", "tx", EDMA_FILTER_PARAM(0, 27) },
+ { "da830-mmc.1", "rx", EDMA_FILTER_PARAM(0, 30) },
+ { "da830-mmc.1", "tx", EDMA_FILTER_PARAM(0, 31) },
};
static struct edma_soc_info dm365_edma_pdata = {
@@ -925,12 +925,14 @@ static struct resource edma_resources[] = {
/* not using TC*_ERR */
};
-static struct platform_device dm365_edma_device = {
- .name = "edma",
- .id = 0,
- .dev.platform_data = &dm365_edma_pdata,
- .num_resources = ARRAY_SIZE(edma_resources),
- .resource = edma_resources,
+static const struct platform_device_info dm365_edma_device __initconst = {
+ .name = "edma",
+ .id = 0,
+ .dma_mask = DMA_BIT_MASK(32),
+ .res = edma_resources,
+ .num_res = ARRAY_SIZE(edma_resources),
+ .data = &dm365_edma_pdata,
+ .size_data = sizeof(dm365_edma_pdata),
};
static struct resource dm365_asp_resources[] = {
@@ -1428,13 +1430,18 @@ int __init dm365_init_video(struct vpfe_config *vpfe_cfg,
static int __init dm365_init_devices(void)
{
+ struct platform_device *edma_pdev;
int ret = 0;
if (!cpu_is_davinci_dm365())
return 0;
davinci_cfg_reg(DM365_INT_EDMA_CC);
- platform_device_register(&dm365_edma_device);
+ edma_pdev = platform_device_register_full(&dm365_edma_device);
+ if (IS_ERR(edma_pdev)) {
+ pr_warn("%s: Failed to register eDMA\n", __func__);
+ return PTR_ERR(edma_pdev);
+ }
platform_device_register(&dm365_mdio_device);
platform_device_register(&dm365_emac_device);
diff --git a/arch/arm/mach-meson/platsmp.c b/arch/arm/mach-meson/platsmp.c
index 2555f9056a33..cad7ee8f0d6b 100644
--- a/arch/arm/mach-meson/platsmp.c
+++ b/arch/arm/mach-meson/platsmp.c
@@ -102,7 +102,7 @@ static void __init meson_smp_prepare_cpus(const char *scu_compatible,
scu_base = of_iomap(node, 0);
if (!scu_base) {
- pr_err("Couln't map SCU registers\n");
+ pr_err("Couldn't map SCU registers\n");
return;
}
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 2f722a805948..c15bbcad5f67 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -232,6 +232,3 @@ obj-y += $(omap-hsmmc-m) $(omap-hsmmc-y)
obj-y += omap_phy_internal.o
obj-$(CONFIG_MACH_OMAP2_TUSB6010) += usb-tusb6010.o
-
-onenand-$(CONFIG_MTD_ONENAND_OMAP2) := gpmc-onenand.o
-obj-y += $(onenand-m) $(onenand-y)
diff --git a/arch/arm/mach-omap2/cm_common.c b/arch/arm/mach-omap2/cm_common.c
index d555791cf349..83c6fa74cc31 100644
--- a/arch/arm/mach-omap2/cm_common.c
+++ b/arch/arm/mach-omap2/cm_common.c
@@ -68,14 +68,17 @@ void __init omap2_set_globals_cm(void __iomem *cm, void __iomem *cm2)
int cm_split_idlest_reg(struct clk_omap_reg *idlest_reg, s16 *prcm_inst,
u8 *idlest_reg_id)
{
+ int ret;
if (!cm_ll_data->split_idlest_reg) {
WARN_ONCE(1, "cm: %s: no low-level function defined\n",
__func__);
return -EINVAL;
}
- return cm_ll_data->split_idlest_reg(idlest_reg, prcm_inst,
+ ret = cm_ll_data->split_idlest_reg(idlest_reg, prcm_inst,
idlest_reg_id);
+ *prcm_inst -= cm_base.offset;
+ return ret;
}
/**
@@ -337,6 +340,7 @@ int __init omap2_cm_base_init(void)
if (mem) {
mem->pa = res.start + data->offset;
mem->va = data->mem + data->offset;
+ mem->offset = data->offset;
}
data->np = np;
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
deleted file mode 100644
index 2944af820558..000000000000
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ /dev/null
@@ -1,409 +0,0 @@
-/*
- * linux/arch/arm/mach-omap2/gpmc-onenand.c
- *
- * Copyright (C) 2006 - 2009 Nokia Corporation
- * Contacts: Juha Yrjola
- * Tony Lindgren
- *
- * 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.
- */
-
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/onenand_regs.h>
-#include <linux/io.h>
-#include <linux/omap-gpmc.h>
-#include <linux/platform_data/mtd-onenand-omap2.h>
-#include <linux/err.h>
-
-#include <asm/mach/flash.h>
-
-#include "soc.h"
-
-#define ONENAND_IO_SIZE SZ_128K
-
-#define ONENAND_FLAG_SYNCREAD (1 << 0)
-#define ONENAND_FLAG_SYNCWRITE (1 << 1)
-#define ONENAND_FLAG_HF (1 << 2)
-#define ONENAND_FLAG_VHF (1 << 3)
-
-static unsigned onenand_flags;
-static unsigned latency;
-
-static struct omap_onenand_platform_data *gpmc_onenand_data;
-
-static struct resource gpmc_onenand_resource = {
- .flags = IORESOURCE_MEM,
-};
-
-static struct platform_device gpmc_onenand_device = {
- .name = "omap2-onenand",
- .id = -1,
- .num_resources = 1,
- .resource = &gpmc_onenand_resource,
-};
-
-static struct gpmc_settings onenand_async = {
- .device_width = GPMC_DEVWIDTH_16BIT,
- .mux_add_data = GPMC_MUX_AD,
-};
-
-static struct gpmc_settings onenand_sync = {
- .burst_read = true,
- .burst_wrap = true,
- .burst_len = GPMC_BURST_16,
- .device_width = GPMC_DEVWIDTH_16BIT,
- .mux_add_data = GPMC_MUX_AD,
- .wait_pin = 0,
-};
-
-static void omap2_onenand_calc_async_timings(struct gpmc_timings *t)
-{
- struct gpmc_device_timings dev_t;
- const int t_cer = 15;
- const int t_avdp = 12;
- const int t_aavdh = 7;
- const int t_ce = 76;
- const int t_aa = 76;
- const int t_oe = 20;
- const int t_cez = 20; /* max of t_cez, t_oez */
- const int t_wpl = 40;
- const int t_wph = 30;
-
- memset(&dev_t, 0, sizeof(dev_t));
-
- dev_t.t_avdp_r = max_t(int, t_avdp, t_cer) * 1000;
- dev_t.t_avdp_w = dev_t.t_avdp_r;
- dev_t.t_aavdh = t_aavdh * 1000;
- dev_t.t_aa = t_aa * 1000;
- dev_t.t_ce = t_ce * 1000;
- dev_t.t_oe = t_oe * 1000;
- dev_t.t_cez_r = t_cez * 1000;
- dev_t.t_cez_w = dev_t.t_cez_r;
- dev_t.t_wpl = t_wpl * 1000;
- dev_t.t_wph = t_wph * 1000;
-
- gpmc_calc_timings(t, &onenand_async, &dev_t);
-}
-
-static void omap2_onenand_set_async_mode(void __iomem *onenand_base)
-{
- u32 reg;
-
- /* Ensure sync read and sync write are disabled */
- reg = readw(onenand_base + ONENAND_REG_SYS_CFG1);
- reg &= ~ONENAND_SYS_CFG1_SYNC_READ & ~ONENAND_SYS_CFG1_SYNC_WRITE;
- writew(reg, onenand_base + ONENAND_REG_SYS_CFG1);
-}
-
-static void set_onenand_cfg(void __iomem *onenand_base)
-{
- u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT;
-
- reg |= (latency << ONENAND_SYS_CFG1_BRL_SHIFT) |
- ONENAND_SYS_CFG1_BL_16;
- if (onenand_flags & ONENAND_FLAG_SYNCREAD)
- reg |= ONENAND_SYS_CFG1_SYNC_READ;
- else
- reg &= ~ONENAND_SYS_CFG1_SYNC_READ;
- if (onenand_flags & ONENAND_FLAG_SYNCWRITE)
- reg |= ONENAND_SYS_CFG1_SYNC_WRITE;
- else
- reg &= ~ONENAND_SYS_CFG1_SYNC_WRITE;
- if (onenand_flags & ONENAND_FLAG_HF)
- reg |= ONENAND_SYS_CFG1_HF;
- else
- reg &= ~ONENAND_SYS_CFG1_HF;
- if (onenand_flags & ONENAND_FLAG_VHF)
- reg |= ONENAND_SYS_CFG1_VHF;
- else
- reg &= ~ONENAND_SYS_CFG1_VHF;
-
- writew(reg, onenand_base + ONENAND_REG_SYS_CFG1);
-}
-
-static int omap2_onenand_get_freq(struct omap_onenand_platform_data *cfg,
- void __iomem *onenand_base)
-{
- u16 ver = readw(onenand_base + ONENAND_REG_VERSION_ID);
- int freq;
-
- switch ((ver >> 4) & 0xf) {
- case 0:
- freq = 40;
- break;
- case 1:
- freq = 54;
- break;
- case 2:
- freq = 66;
- break;
- case 3:
- freq = 83;
- break;
- case 4:
- freq = 104;
- break;
- default:
- pr_err("onenand rate not detected, bad GPMC async timings?\n");
- freq = 0;
- }
-
- return freq;
-}
-
-static void omap2_onenand_calc_sync_timings(struct gpmc_timings *t,
- unsigned int flags,
- int freq)
-{
- struct gpmc_device_timings dev_t;
- const int t_cer = 15;
- const int t_avdp = 12;
- const int t_cez = 20; /* max of t_cez, t_oez */
- const int t_wpl = 40;
- const int t_wph = 30;
- int min_gpmc_clk_period, t_ces, t_avds, t_avdh, t_ach, t_aavdh, t_rdyo;
- int div, gpmc_clk_ns;
-
- if (flags & ONENAND_SYNC_READ)
- onenand_flags = ONENAND_FLAG_SYNCREAD;
- else if (flags & ONENAND_SYNC_READWRITE)
- onenand_flags = ONENAND_FLAG_SYNCREAD | ONENAND_FLAG_SYNCWRITE;
-
- switch (freq) {
- case 104:
- min_gpmc_clk_period = 9600; /* 104 MHz */
- t_ces = 3;
- t_avds = 4;
- t_avdh = 2;
- t_ach = 3;
- t_aavdh = 6;
- t_rdyo = 6;
- break;
- case 83:
- min_gpmc_clk_period = 12000; /* 83 MHz */
- t_ces = 5;
- t_avds = 4;
- t_avdh = 2;
- t_ach = 6;
- t_aavdh = 6;
- t_rdyo = 9;
- break;
- case 66:
- min_gpmc_clk_period = 15000; /* 66 MHz */
- t_ces = 6;
- t_avds = 5;
- t_avdh = 2;
- t_ach = 6;
- t_aavdh = 6;
- t_rdyo = 11;
- break;
- default:
- min_gpmc_clk_period = 18500; /* 54 MHz */
- t_ces = 7;
- t_avds = 7;
- t_avdh = 7;
- t_ach = 9;
- t_aavdh = 7;
- t_rdyo = 15;
- onenand_flags &= ~ONENAND_FLAG_SYNCWRITE;
- break;
- }
-
- div = gpmc_calc_divider(min_gpmc_clk_period);
- gpmc_clk_ns = gpmc_ticks_to_ns(div);
- if (gpmc_clk_ns < 15) /* >66MHz */
- onenand_flags |= ONENAND_FLAG_HF;
- else
- onenand_flags &= ~ONENAND_FLAG_HF;
- if (gpmc_clk_ns < 12) /* >83MHz */
- onenand_flags |= ONENAND_FLAG_VHF;
- else
- onenand_flags &= ~ONENAND_FLAG_VHF;
- if (onenand_flags & ONENAND_FLAG_VHF)
- latency = 8;
- else if (onenand_flags & ONENAND_FLAG_HF)
- latency = 6;
- else if (gpmc_clk_ns >= 25) /* 40 MHz*/
- latency = 3;
- else
- latency = 4;
-
- /* Set synchronous read timings */
- memset(&dev_t, 0, sizeof(dev_t));
-
- if (onenand_flags & ONENAND_FLAG_SYNCREAD)
- onenand_sync.sync_read = true;
- if (onenand_flags & ONENAND_FLAG_SYNCWRITE) {
- onenand_sync.sync_write = true;
- onenand_sync.burst_write = true;
- } else {
- dev_t.t_avdp_w = max(t_avdp, t_cer) * 1000;
- dev_t.t_wpl = t_wpl * 1000;
- dev_t.t_wph = t_wph * 1000;
- dev_t.t_aavdh = t_aavdh * 1000;
- }
- dev_t.ce_xdelay = true;
- dev_t.avd_xdelay = true;
- dev_t.oe_xdelay = true;
- dev_t.we_xdelay = true;
- dev_t.clk = min_gpmc_clk_period;
- dev_t.t_bacc = dev_t.clk;
- dev_t.t_ces = t_ces * 1000;
- dev_t.t_avds = t_avds * 1000;
- dev_t.t_avdh = t_avdh * 1000;
- dev_t.t_ach = t_ach * 1000;
- dev_t.cyc_iaa = (latency + 1);
- dev_t.t_cez_r = t_cez * 1000;
- dev_t.t_cez_w = dev_t.t_cez_r;
- dev_t.cyc_aavdh_oe = 1;
- dev_t.t_rdyo = t_rdyo * 1000 + min_gpmc_clk_period;
-
- gpmc_calc_timings(t, &onenand_sync, &dev_t);
-}
-
-static int omap2_onenand_setup_async(void __iomem *onenand_base)
-{
- struct gpmc_timings t;
- int ret;
-
- /*
- * Note that we need to keep sync_write set for the call to
- * omap2_onenand_set_async_mode() to work to detect the onenand
- * supported clock rate for the sync timings.
- */
- if (gpmc_onenand_data->of_node) {
- gpmc_read_settings_dt(gpmc_onenand_data->of_node,
- &onenand_async);
- if (onenand_async.sync_read || onenand_async.sync_write) {
- if (onenand_async.sync_write)
- gpmc_onenand_data->flags |=
- ONENAND_SYNC_READWRITE;
- else
- gpmc_onenand_data->flags |= ONENAND_SYNC_READ;
- onenand_async.sync_read = false;
- }
- }
-
- onenand_async.sync_write = true;
- omap2_onenand_calc_async_timings(&t);
-
- ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async);
- if (ret < 0)
- return ret;
-
- ret = gpmc_cs_set_timings(gpmc_onenand_data->cs, &t, &onenand_async);
- if (ret < 0)
- return ret;
-
- omap2_onenand_set_async_mode(onenand_base);
-
- return 0;
-}
-
-static int omap2_onenand_setup_sync(void __iomem *onenand_base, int *freq_ptr)
-{
- int ret, freq = *freq_ptr;
- struct gpmc_timings t;
-
- if (!freq) {
- /* Very first call freq is not known */
- freq = omap2_onenand_get_freq(gpmc_onenand_data, onenand_base);
- if (!freq)
- return -ENODEV;
- set_onenand_cfg(onenand_base);
- }
-
- if (gpmc_onenand_data->of_node) {
- gpmc_read_settings_dt(gpmc_onenand_data->of_node,
- &onenand_sync);
- } else {
- /*
- * FIXME: Appears to be legacy code from initial ONENAND commit.
- * Unclear what boards this is for and if this can be removed.
- */
- if (!cpu_is_omap34xx())
- onenand_sync.wait_on_read = true;
- }
-
- omap2_onenand_calc_sync_timings(&t, gpmc_onenand_data->flags, freq);
-
- ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_sync);
- if (ret < 0)
- return ret;
-
- ret = gpmc_cs_set_timings(gpmc_onenand_data->cs, &t, &onenand_sync);
- if (ret < 0)
- return ret;
-
- set_onenand_cfg(onenand_base);
-
- *freq_ptr = freq;
-
- return 0;
-}
-
-static int gpmc_onenand_setup(void __iomem *onenand_base, int *freq_ptr)
-{
- struct device *dev = &gpmc_onenand_device.dev;
- unsigned l = ONENAND_SYNC_READ | ONENAND_SYNC_READWRITE;
- int ret;
-
- ret = omap2_onenand_setup_async(onenand_base);
- if (ret) {
- dev_err(dev, "unable to set to async mode\n");
- return ret;
- }
-
- if (!(gpmc_onenand_data->flags & l))
- return 0;
-
- ret = omap2_onenand_setup_sync(onenand_base, freq_ptr);
- if (ret)
- dev_err(dev, "unable to set to sync mode\n");
- return ret;
-}
-
-int gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
-{
- int err;
- struct device *dev = &gpmc_onenand_device.dev;
-
- gpmc_onenand_data = _onenand_data;
- gpmc_onenand_data->onenand_setup = gpmc_onenand_setup;
- gpmc_onenand_device.dev.platform_data = gpmc_onenand_data;
-
- if (cpu_is_omap24xx() &&
- (gpmc_onenand_data->flags & ONENAND_SYNC_READWRITE)) {
- dev_warn(dev, "OneNAND using only SYNC_READ on 24xx\n");
- gpmc_onenand_data->flags &= ~ONENAND_SYNC_READWRITE;
- gpmc_onenand_data->flags |= ONENAND_SYNC_READ;
- }
-
- if (cpu_is_omap34xx())
- gpmc_onenand_data->flags |= ONENAND_IN_OMAP34XX;
- else
- gpmc_onenand_data->flags &= ~ONENAND_IN_OMAP34XX;
-
- err = gpmc_cs_request(gpmc_onenand_data->cs, ONENAND_IO_SIZE,
- (unsigned long *)&gpmc_onenand_resource.start);
- if (err < 0) {
- dev_err(dev, "Cannot request GPMC CS %d, error %d\n",
- gpmc_onenand_data->cs, err);
- return err;
- }
-
- gpmc_onenand_resource.end = gpmc_onenand_resource.start +
- ONENAND_IO_SIZE - 1;
-
- err = platform_device_register(&gpmc_onenand_device);
- if (err) {
- dev_err(dev, "Unable to register OneNAND device\n");
- gpmc_cs_free(gpmc_onenand_data->cs);
- }
-
- return err;
-}
diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c
index 5ac122e88f67..fa7f308c9027 100644
--- a/arch/arm/mach-omap2/omap-secure.c
+++ b/arch/arm/mach-omap2/omap-secure.c
@@ -73,6 +73,27 @@ phys_addr_t omap_secure_ram_mempool_base(void)
return omap_secure_memblock_base;
}
+#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM)
+u32 omap3_save_secure_ram(void __iomem *addr, int size)
+{
+ u32 ret;
+ u32 param[5];
+
+ if (size != OMAP3_SAVE_SECURE_RAM_SZ)
+ return OMAP3_SAVE_SECURE_RAM_SZ;
+
+ param[0] = 4; /* Number of arguments */
+ param[1] = __pa(addr); /* Physical address for saving */
+ param[2] = 0;
+ param[3] = 1;
+ param[4] = 1;
+
+ ret = save_secure_ram_context(__pa(param));
+
+ return ret;
+}
+#endif
+
/**
* rx51_secure_dispatcher: Routine to dispatch secure PPA API calls
* @idx: The PPA API index
diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h
index bae263fba640..c509cde71f93 100644
--- a/arch/arm/mach-omap2/omap-secure.h
+++ b/arch/arm/mach-omap2/omap-secure.h
@@ -31,6 +31,8 @@
/* Maximum Secure memory storage size */
#define OMAP_SECURE_RAM_STORAGE (88 * SZ_1K)
+#define OMAP3_SAVE_SECURE_RAM_SZ 0x803F
+
/* Secure low power HAL API index */
#define OMAP4_HAL_SAVESECURERAM_INDEX 0x1a
#define OMAP4_HAL_SAVEHW_INDEX 0x1b
@@ -65,6 +67,8 @@ extern u32 omap_smc2(u32 id, u32 falg, u32 pargs);
extern u32 omap_smc3(u32 id, u32 process, u32 flag, u32 pargs);
extern phys_addr_t omap_secure_ram_mempool_base(void);
extern int omap_secure_ram_reserve_memblock(void);
+extern u32 save_secure_ram_context(u32 args_pa);
+extern u32 omap3_save_secure_ram(void __iomem *save_regs, int size);
extern u32 rx51_secure_dispatcher(u32 idx, u32 process, u32 flag, u32 nargs,
u32 arg1, u32 arg2, u32 arg3, u32 arg4);
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index d45cbfdb4be6..f0388058b7da 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -391,10 +391,8 @@ omap_device_copy_resources(struct omap_hwmod *oh,
const char *name;
int error, irq = 0;
- if (!oh || !oh->od || !oh->od->pdev) {
- error = -EINVAL;
- goto error;
- }
+ if (!oh || !oh->od || !oh->od->pdev)
+ return -EINVAL;
np = oh->od->pdev->dev.of_node;
if (!np) {
@@ -516,8 +514,10 @@ struct platform_device __init *omap_device_build(const char *pdev_name,
goto odbs_exit1;
od = omap_device_alloc(pdev, &oh, 1);
- if (IS_ERR(od))
+ if (IS_ERR(od)) {
+ ret = PTR_ERR(od);
goto odbs_exit1;
+ }
ret = platform_device_add_data(pdev, pdata, pdata_len);
if (ret)
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index d2106ae4410a..52c9d585b44d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1646,6 +1646,7 @@ static struct omap_hwmod omap3xxx_mmc3_hwmod = {
.main_clk = "mmchs3_fck",
.prcm = {
.omap2 = {
+ .module_offs = CORE_MOD,
.prcm_reg_id = 1,
.module_bit = OMAP3430_EN_MMC3_SHIFT,
.idlest_reg_id = 1,
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index b668719b9b25..8e30772cfe32 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -81,10 +81,6 @@ extern unsigned int omap3_do_wfi_sz;
/* ... and its pointer from SRAM after copy */
extern void (*omap3_do_wfi_sram)(void);
-/* save_secure_ram_context function pointer and size, for copy to SRAM */
-extern int save_secure_ram_context(u32 *addr);
-extern unsigned int save_secure_ram_context_sz;
-
extern void omap3_save_scratchpad_contents(void);
#define PM_RTA_ERRATUM_i608 (1 << 0)
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 841ba19d64a6..36c55547137c 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -48,6 +48,7 @@
#include "prm3xxx.h"
#include "pm.h"
#include "sdrc.h"
+#include "omap-secure.h"
#include "sram.h"
#include "control.h"
#include "vc.h"
@@ -66,7 +67,6 @@ struct power_state {
static LIST_HEAD(pwrst_list);
-static int (*_omap_save_secure_sram)(u32 *addr);
void (*omap3_do_wfi_sram)(void);
static struct powerdomain *mpu_pwrdm, *neon_pwrdm;
@@ -121,8 +121,8 @@ static void omap3_save_secure_ram_context(void)
* will hang the system.
*/
pwrdm_set_next_pwrst(mpu_pwrdm, PWRDM_POWER_ON);
- ret = _omap_save_secure_sram((u32 *)(unsigned long)
- __pa(omap3_secure_ram_storage));
+ ret = omap3_save_secure_ram(omap3_secure_ram_storage,
+ OMAP3_SAVE_SECURE_RAM_SZ);
pwrdm_set_next_pwrst(mpu_pwrdm, mpu_next_state);
/* Following is for error tracking, it should not happen */
if (ret) {
@@ -434,15 +434,10 @@ static int __init pwrdms_setup(struct powerdomain *pwrdm, void *unused)
*
* The minimum set of functions is pushed to SRAM for execution:
* - omap3_do_wfi for erratum i581 WA,
- * - save_secure_ram_context for security extensions.
*/
void omap_push_sram_idle(void)
{
omap3_do_wfi_sram = omap_sram_push(omap3_do_wfi, omap3_do_wfi_sz);
-
- if (omap_type() != OMAP2_DEVICE_TYPE_GP)
- _omap_save_secure_sram = omap_sram_push(save_secure_ram_context,
- save_secure_ram_context_sz);
}
static void __init pm_errata_configure(void)
@@ -553,7 +548,7 @@ int __init omap3_pm_init(void)
clkdm_add_wkdep(neon_clkdm, mpu_clkdm);
if (omap_type() != OMAP2_DEVICE_TYPE_GP) {
omap3_secure_ram_storage =
- kmalloc(0x803F, GFP_KERNEL);
+ kmalloc(OMAP3_SAVE_SECURE_RAM_SZ, GFP_KERNEL);
if (!omap3_secure_ram_storage)
pr_err("Memory allocation failed when allocating for secure sram context\n");
diff --git a/arch/arm/mach-omap2/prcm-common.h b/arch/arm/mach-omap2/prcm-common.h
index 0592b23902c6..0977da0dab76 100644
--- a/arch/arm/mach-omap2/prcm-common.h
+++ b/arch/arm/mach-omap2/prcm-common.h
@@ -528,6 +528,7 @@ struct omap_prcm_irq_setup {
struct omap_domain_base {
u32 pa;
void __iomem *va;
+ s16 offset;
};
/**
diff --git a/arch/arm/mach-omap2/prm33xx.c b/arch/arm/mach-omap2/prm33xx.c
index d2c5bcabdbeb..ebaf80d72a10 100644
--- a/arch/arm/mach-omap2/prm33xx.c
+++ b/arch/arm/mach-omap2/prm33xx.c
@@ -176,17 +176,6 @@ static int am33xx_pwrdm_read_pwrst(struct powerdomain *pwrdm)
return v;
}
-static int am33xx_pwrdm_read_prev_pwrst(struct powerdomain *pwrdm)
-{
- u32 v;
-
- v = am33xx_prm_read_reg(pwrdm->prcm_offs, pwrdm->pwrstst_offs);
- v &= AM33XX_LASTPOWERSTATEENTERED_MASK;
- v >>= AM33XX_LASTPOWERSTATEENTERED_SHIFT;
-
- return v;
-}
-
static int am33xx_pwrdm_set_lowpwrstchange(struct powerdomain *pwrdm)
{
am33xx_prm_rmw_reg_bits(AM33XX_LOWPOWERSTATECHANGE_MASK,
@@ -357,7 +346,6 @@ struct pwrdm_ops am33xx_pwrdm_operations = {
.pwrdm_set_next_pwrst = am33xx_pwrdm_set_next_pwrst,
.pwrdm_read_next_pwrst = am33xx_pwrdm_read_next_pwrst,
.pwrdm_read_pwrst = am33xx_pwrdm_read_pwrst,
- .pwrdm_read_prev_pwrst = am33xx_pwrdm_read_prev_pwrst,
.pwrdm_set_logic_retst = am33xx_pwrdm_set_logic_retst,
.pwrdm_read_logic_pwrst = am33xx_pwrdm_read_logic_pwrst,
.pwrdm_read_logic_retst = am33xx_pwrdm_read_logic_retst,
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index fa5fd24f524c..22daf4efed68 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -93,20 +93,13 @@ ENTRY(enable_omap3630_toggle_l2_on_restore)
ENDPROC(enable_omap3630_toggle_l2_on_restore)
/*
- * Function to call rom code to save secure ram context. This gets
- * relocated to SRAM, so it can be all in .data section. Otherwise
- * we need to initialize api_params separately.
+ * Function to call rom code to save secure ram context.
+ *
+ * r0 = physical address of the parameters
*/
- .data
- .align 3
ENTRY(save_secure_ram_context)
stmfd sp!, {r4 - r11, lr} @ save registers on stack
- adr r3, api_params @ r3 points to parameters
- str r0, [r3,#0x4] @ r0 has sdram address
- ldr r12, high_mask
- and r3, r3, r12
- ldr r12, sram_phy_addr_mask
- orr r3, r3, r12
+ mov r3, r0 @ physical address of parameters
mov r0, #25 @ set service ID for PPA
mov r12, r0 @ copy secure service ID in r12
mov r1, #0 @ set task id for ROM code in r1
@@ -120,18 +113,7 @@ ENTRY(save_secure_ram_context)
nop
nop
ldmfd sp!, {r4 - r11, pc}
- .align
-sram_phy_addr_mask:
- .word SRAM_BASE_P
-high_mask:
- .word 0xffff
-api_params:
- .word 0x4, 0x0, 0x0, 0x1, 0x1
ENDPROC(save_secure_ram_context)
-ENTRY(save_secure_ram_context_sz)
- .word . - save_secure_ram_context
-
- .text
/*
* ======================
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c199990e12b6..323a4df59a6c 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -27,14 +27,58 @@
int bpf_jit_enable __read_mostly;
+/*
+ * eBPF prog stack layout:
+ *
+ * high
+ * original ARM_SP => +-----+
+ * | | callee saved registers
+ * +-----+ <= (BPF_FP + SCRATCH_SIZE)
+ * | ... | eBPF JIT scratch space
+ * eBPF fp register => +-----+
+ * (BPF_FP) | ... | eBPF prog stack
+ * +-----+
+ * |RSVD | JIT scratchpad
+ * current ARM_SP => +-----+ <= (BPF_FP - STACK_SIZE + SCRATCH_SIZE)
+ * | |
+ * | ... | Function call stack
+ * | |
+ * +-----+
+ * low
+ *
+ * The callee saved registers depends on whether frame pointers are enabled.
+ * With frame pointers (to be compliant with the ABI):
+ *
+ * high
+ * original ARM_SP => +------------------+ \
+ * | pc | |
+ * current ARM_FP => +------------------+ } callee saved registers
+ * |r4-r8,r10,fp,ip,lr| |
+ * +------------------+ /
+ * low
+ *
+ * Without frame pointers:
+ *
+ * high
+ * original ARM_SP => +------------------+
+ * | r4-r8,r10,fp,lr | callee saved registers
+ * current ARM_FP => +------------------+
+ * low
+ *
+ * When popping registers off the stack at the end of a BPF function, we
+ * reference them via the current ARM_FP register.
+ */
+#define CALLEE_MASK (1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \
+ 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \
+ 1 << ARM_FP)
+#define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
+#define CALLEE_POP_MASK (CALLEE_MASK | 1 << ARM_PC)
+
#define STACK_OFFSET(k) (k)
#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) /* TEMP Register 1 */
#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* TEMP Register 2 */
#define TCALL_CNT (MAX_BPF_JIT_REG + 2) /* Tail Call Count */
-/* Flags used for JIT optimization */
-#define SEEN_CALL (1 << 0)
-
#define FLAG_IMM_OVERFLOW (1 << 0)
/*
@@ -95,7 +139,6 @@ static const u8 bpf2a32[][2] = {
* idx : index of current last JITed instruction.
* prologue_bytes : bytes used in prologue.
* epilogue_offset : offset of epilogue starting.
- * seen : bit mask used for JIT optimization.
* offsets : array of eBPF instruction offsets in
* JITed code.
* target : final JITed code.
@@ -110,7 +153,6 @@ struct jit_ctx {
unsigned int idx;
unsigned int prologue_bytes;
unsigned int epilogue_offset;
- u32 seen;
u32 flags;
u32 *offsets;
u32 *target;
@@ -179,8 +221,13 @@ static void jit_fill_hole(void *area, unsigned int size)
*ptr++ = __opcode_to_mem_arm(ARM_INST_UDF);
}
-/* Stack must be multiples of 16 Bytes */
-#define STACK_ALIGN(sz) (((sz) + 3) & ~3)
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
+/* EABI requires the stack to be aligned to 64-bit boundaries */
+#define STACK_ALIGNMENT 8
+#else
+/* Stack must be aligned to 32-bit boundaries */
+#define STACK_ALIGNMENT 4
+#endif
/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
* BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
@@ -194,7 +241,7 @@ static void jit_fill_hole(void *area, unsigned int size)
+ SCRATCH_SIZE + \
+ 4 /* extra for skb_copy_bits buffer */)
-#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
+#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
/* Get the offset of eBPF REGISTERs stored on scratch space. */
#define STACK_VAR(off) (STACK_SIZE-off-4)
@@ -285,16 +332,19 @@ static inline void emit_mov_i(const u8 rd, u32 val, struct jit_ctx *ctx)
emit_mov_i_no8m(rd, val, ctx);
}
-static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+static void emit_bx_r(u8 tgt_reg, struct jit_ctx *ctx)
{
- ctx->seen |= SEEN_CALL;
-#if __LINUX_ARM_ARCH__ < 5
- emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
-
if (elf_hwcap & HWCAP_THUMB)
emit(ARM_BX(tgt_reg), ctx);
else
emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+}
+
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 5
+ emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+ emit_bx_r(tgt_reg, ctx);
#else
emit(ARM_BLX_R(tgt_reg), ctx);
#endif
@@ -354,7 +404,6 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
}
/* Call appropriate function */
- ctx->seen |= SEEN_CALL;
emit_mov_i(ARM_IP, op == BPF_DIV ?
(u32)jit_udiv32 : (u32)jit_mod32, ctx);
emit_blx_r(ARM_IP, ctx);
@@ -620,8 +669,6 @@ static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
/* Do LSH operation */
emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
emit(ARM_RSB_I(tmp2[0], rt, 32), ctx);
- /* As we are using ARM_LR */
- ctx->seen |= SEEN_CALL;
emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx);
emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx);
emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
@@ -656,8 +703,6 @@ static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
/* Do the ARSH operation */
emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
- /* As we are using ARM_LR */
- ctx->seen |= SEEN_CALL;
emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
_emit(ARM_COND_MI, ARM_B(0), ctx);
@@ -692,8 +737,6 @@ static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk,
/* Do LSH operation */
emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
- /* As we are using ARM_LR */
- ctx->seen |= SEEN_CALL;
emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
@@ -828,8 +871,6 @@ static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
/* Do Multiplication */
emit(ARM_MUL(ARM_IP, rd, rn), ctx);
emit(ARM_MUL(ARM_LR, rm, rt), ctx);
- /* As we are using ARM_LR */
- ctx->seen |= SEEN_CALL;
emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx);
emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
@@ -872,33 +913,53 @@ static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
}
/* dst = *(size*)(src + off) */
-static inline void emit_ldx_r(const u8 dst, const u8 src, bool dstk,
- const s32 off, struct jit_ctx *ctx, const u8 sz){
+static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
+ s32 off, struct jit_ctx *ctx, const u8 sz){
const u8 *tmp = bpf2a32[TMP_REG_1];
- u8 rd = dstk ? tmp[1] : dst;
+ const u8 *rd = dstk ? tmp : dst;
u8 rm = src;
+ s32 off_max;
- if (off) {
+ if (sz == BPF_H)
+ off_max = 0xff;
+ else
+ off_max = 0xfff;
+
+ if (off < 0 || off > off_max) {
emit_a32_mov_i(tmp[0], off, false, ctx);
emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
rm = tmp[0];
+ off = 0;
+ } else if (rd[1] == rm) {
+ emit(ARM_MOV_R(tmp[0], rm), ctx);
+ rm = tmp[0];
}
switch (sz) {
- case BPF_W:
- /* Load a Word */
- emit(ARM_LDR_I(rd, rm, 0), ctx);
+ case BPF_B:
+ /* Load a Byte */
+ emit(ARM_LDRB_I(rd[1], rm, off), ctx);
+ emit_a32_mov_i(dst[0], 0, dstk, ctx);
break;
case BPF_H:
/* Load a HalfWord */
- emit(ARM_LDRH_I(rd, rm, 0), ctx);
+ emit(ARM_LDRH_I(rd[1], rm, off), ctx);
+ emit_a32_mov_i(dst[0], 0, dstk, ctx);
break;
- case BPF_B:
- /* Load a Byte */
- emit(ARM_LDRB_I(rd, rm, 0), ctx);
+ case BPF_W:
+ /* Load a Word */
+ emit(ARM_LDR_I(rd[1], rm, off), ctx);
+ emit_a32_mov_i(dst[0], 0, dstk, ctx);
+ break;
+ case BPF_DW:
+ /* Load a Double Word */
+ emit(ARM_LDR_I(rd[1], rm, off), ctx);
+ emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
break;
}
if (dstk)
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+ emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx);
+ if (dstk && sz == BPF_DW)
+ emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx);
}
/* Arithmatic Operation */
@@ -906,7 +967,6 @@ static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
const u8 rn, struct jit_ctx *ctx, u8 op) {
switch (op) {
case BPF_JSET:
- ctx->seen |= SEEN_CALL;
emit(ARM_AND_R(ARM_IP, rt, rn), ctx);
emit(ARM_AND_R(ARM_LR, rd, rm), ctx);
emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx);
@@ -945,7 +1005,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
const u8 *tcc = bpf2a32[TCALL_CNT];
const int idx0 = ctx->idx;
#define cur_offset (ctx->idx - idx0)
-#define jmp_offset (out_offset - (cur_offset))
+#define jmp_offset (out_offset - (cur_offset) - 2)
u32 off, lo, hi;
/* if (index >= array->map.max_entries)
@@ -956,7 +1016,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
emit_a32_mov_i(tmp[1], off, false, ctx);
emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
- /* index (64 bit) */
+ /* index is 32-bit for arrays */
emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
/* index >= array->map.max_entries */
emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx);
@@ -997,7 +1057,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
emit_a32_mov_i(tmp2[1], off, false, ctx);
emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
- emit(ARM_BX(tmp[1]), ctx);
+ emit_bx_r(tmp[1], ctx);
/* out: */
if (out_offset == -1)
@@ -1070,54 +1130,22 @@ static void build_prologue(struct jit_ctx *ctx)
const u8 r2 = bpf2a32[BPF_REG_1][1];
const u8 r3 = bpf2a32[BPF_REG_1][0];
const u8 r4 = bpf2a32[BPF_REG_6][1];
- const u8 r5 = bpf2a32[BPF_REG_6][0];
- const u8 r6 = bpf2a32[TMP_REG_1][1];
- const u8 r7 = bpf2a32[TMP_REG_1][0];
- const u8 r8 = bpf2a32[TMP_REG_2][1];
- const u8 r10 = bpf2a32[TMP_REG_2][0];
const u8 fplo = bpf2a32[BPF_REG_FP][1];
const u8 fphi = bpf2a32[BPF_REG_FP][0];
- const u8 sp = ARM_SP;
const u8 *tcc = bpf2a32[TCALL_CNT];
- u16 reg_set = 0;
-
- /*
- * eBPF prog stack layout
- *
- * high
- * original ARM_SP => +-----+ eBPF prologue
- * |FP/LR|
- * current ARM_FP => +-----+
- * | ... | callee saved registers
- * eBPF fp register => +-----+ <= (BPF_FP)
- * | ... | eBPF JIT scratch space
- * | | eBPF prog stack
- * +-----+
- * |RSVD | JIT scratchpad
- * current A64_SP => +-----+ <= (BPF_FP - STACK_SIZE)
- * | |
- * | ... | Function call stack
- * | |
- * +-----+
- * low
- */
-
/* Save callee saved registers. */
- reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
#ifdef CONFIG_FRAME_POINTER
- reg_set |= (1<<ARM_FP) | (1<<ARM_IP) | (1<<ARM_LR) | (1<<ARM_PC);
- emit(ARM_MOV_R(ARM_IP, sp), ctx);
+ u16 reg_set = CALLEE_PUSH_MASK | 1 << ARM_IP | 1 << ARM_PC;
+ emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
emit(ARM_PUSH(reg_set), ctx);
emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
#else
- /* Check if call instruction exists in BPF body */
- if (ctx->seen & SEEN_CALL)
- reg_set |= (1<<ARM_LR);
- emit(ARM_PUSH(reg_set), ctx);
+ emit(ARM_PUSH(CALLEE_PUSH_MASK), ctx);
+ emit(ARM_MOV_R(ARM_FP, ARM_SP), ctx);
#endif
/* Save frame pointer for later */
- emit(ARM_SUB_I(ARM_IP, sp, SCRATCH_SIZE), ctx);
+ emit(ARM_SUB_I(ARM_IP, ARM_SP, SCRATCH_SIZE), ctx);
ctx->stack_size = imm8m(STACK_SIZE);
@@ -1140,33 +1168,19 @@ static void build_prologue(struct jit_ctx *ctx)
/* end of prologue */
}
+/* restore callee saved registers. */
static void build_epilogue(struct jit_ctx *ctx)
{
- const u8 r4 = bpf2a32[BPF_REG_6][1];
- const u8 r5 = bpf2a32[BPF_REG_6][0];
- const u8 r6 = bpf2a32[TMP_REG_1][1];
- const u8 r7 = bpf2a32[TMP_REG_1][0];
- const u8 r8 = bpf2a32[TMP_REG_2][1];
- const u8 r10 = bpf2a32[TMP_REG_2][0];
- u16 reg_set = 0;
-
- /* unwind function call stack */
- emit(ARM_ADD_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
-
- /* restore callee saved registers. */
- reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
#ifdef CONFIG_FRAME_POINTER
- /* the first instruction of the prologue was: mov ip, sp */
- reg_set |= (1<<ARM_FP) | (1<<ARM_SP) | (1<<ARM_PC);
+ /* When using frame pointers, some additional registers need to
+ * be loaded. */
+ u16 reg_set = CALLEE_POP_MASK | 1 << ARM_SP;
+ emit(ARM_SUB_I(ARM_SP, ARM_FP, hweight16(reg_set) * 4), ctx);
emit(ARM_LDM(ARM_SP, reg_set), ctx);
#else
- if (ctx->seen & SEEN_CALL)
- reg_set |= (1<<ARM_PC);
/* Restore callee saved registers. */
- emit(ARM_POP(reg_set), ctx);
- /* Return back to the callee function */
- if (!(ctx->seen & SEEN_CALL))
- emit(ARM_BX(ARM_LR), ctx);
+ emit(ARM_MOV_R(ARM_SP, ARM_FP), ctx);
+ emit(ARM_POP(CALLEE_POP_MASK), ctx);
#endif
}
@@ -1394,8 +1408,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
emit_rev32(rt, rt, ctx);
goto emit_bswap_uxt;
case 64:
- /* Because of the usage of ARM_LR */
- ctx->seen |= SEEN_CALL;
emit_rev32(ARM_LR, rt, ctx);
emit_rev32(rt, rd, ctx);
emit(ARM_MOV_R(rd, ARM_LR), ctx);
@@ -1448,22 +1460,7 @@ exit:
rn = sstk ? tmp2[1] : src_lo;
if (sstk)
emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
- switch (BPF_SIZE(code)) {
- case BPF_W:
- /* Load a Word */
- case BPF_H:
- /* Load a Half-Word */
- case BPF_B:
- /* Load a Byte */
- emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_SIZE(code));
- emit_a32_mov_i(dst_hi, 0, dstk, ctx);
- break;
- case BPF_DW:
- /* Load a double word */
- emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_W);
- emit_ldx_r(dst_hi, rn, dstk, off+4, ctx, BPF_W);
- break;
- }
+ emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
break;
/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
case BPF_LD | BPF_ABS | BPF_W:
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index a71a48e71fff..03c6a3c72f9c 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -257,7 +257,7 @@ static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_
if (exceptions == VFP_EXCEPTION_ERROR) {
vfp_panic("unhandled bounce", inst);
- vfp_raise_sigfpe(0, regs);
+ vfp_raise_sigfpe(FPE_FIXME, regs);
return;
}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a93339f5178f..b488076d63c2 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -522,20 +522,13 @@ config CAVIUM_ERRATUM_30115
config QCOM_FALKOR_ERRATUM_1003
bool "Falkor E1003: Incorrect translation due to ASID change"
default y
- select ARM64_PAN if ARM64_SW_TTBR0_PAN
help
On Falkor v1, an incorrect ASID may be cached in the TLB when ASID
- and BADDR are changed together in TTBRx_EL1. The workaround for this
- issue is to use a reserved ASID in cpu_do_switch_mm() before
- switching to the new ASID. Saying Y here selects ARM64_PAN if
- ARM64_SW_TTBR0_PAN is selected. This is done because implementing and
- maintaining the E1003 workaround in the software PAN emulation code
- would be an unnecessary complication. The affected Falkor v1 CPU
- implements ARMv8.1 hardware PAN support and using hardware PAN
- support versus software PAN emulation is mutually exclusive at
- runtime.
-
- If unsure, say Y.
+ and BADDR are changed together in TTBRx_EL1. Since we keep the ASID
+ in TTBR1_EL1, this situation only occurs in the entry trampoline and
+ then only for entries in the walk cache, since the leaf translation
+ is unchanged. Work around the erratum by invalidating the walk cache
+ entries for the trampoline before entering the kernel proper.
config QCOM_FALKOR_ERRATUM_1009
bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
@@ -557,7 +550,6 @@ config QCOM_QDF2400_ERRATUM_0065
If unsure, say Y.
-
config SOCIONEXT_SYNQUACER_PREITS
bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
default y
@@ -576,6 +568,17 @@ config HISILICON_ERRATUM_161600802
a 128kB offset to be applied to the target address in this commands.
If unsure, say Y.
+
+config QCOM_FALKOR_ERRATUM_E1041
+ bool "Falkor E1041: Speculative instruction fetches might cause errant memory access"
+ default y
+ help
+ Falkor CPU may speculatively fetch instructions from an improper
+ memory location when MMU translation is changed from SCTLR_ELn[M]=1
+ to SCTLR_ELn[M]=0. Prefix an ISB instruction to fix the problem.
+
+ If unsure, say Y.
+
endmenu
@@ -646,6 +649,35 @@ config ARM64_VA_BITS
default 47 if ARM64_VA_BITS_47
default 48 if ARM64_VA_BITS_48
+choice
+ prompt "Physical address space size"
+ default ARM64_PA_BITS_48
+ help
+ Choose the maximum physical address range that the kernel will
+ support.
+
+config ARM64_PA_BITS_48
+ bool "48-bit"
+
+config ARM64_PA_BITS_52
+ bool "52-bit (ARMv8.2)"
+ depends on ARM64_64K_PAGES
+ depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
+ help
+ Enable support for a 52-bit physical address space, introduced as
+ part of the ARMv8.2-LPA extension.
+
+ With this enabled, the kernel will also continue to work on CPUs that
+ do not support ARMv8.2-LPA, but with some added memory overhead (and
+ minor performance overhead).
+
+endchoice
+
+config ARM64_PA_BITS
+ int
+ default 48 if ARM64_PA_BITS_48
+ default 52 if ARM64_PA_BITS_52
+
config CPU_BIG_ENDIAN
bool "Build big-endian kernel"
help
@@ -840,6 +872,35 @@ config FORCE_MAX_ZONEORDER
However for 4K, we choose a higher default value, 11 as opposed to 10, giving us
4M allocations matching the default size used by generic code.
+config UNMAP_KERNEL_AT_EL0
+ bool "Unmap kernel when running in userspace (aka \"KAISER\")" if EXPERT
+ default y
+ help
+ Speculation attacks against some high-performance processors can
+ be used to bypass MMU permission checks and leak kernel data to
+ userspace. This can be defended against by unmapping the kernel
+ when running in userspace, mapping it back in on exception entry
+ via a trampoline page in the vector table.
+
+ If unsure, say Y.
+
+config HARDEN_BRANCH_PREDICTOR
+ bool "Harden the branch predictor against aliasing attacks" if EXPERT
+ default y
+ help
+ Speculation attacks against some high-performance processors rely on
+ being able to manipulate the branch predictor for a victim context by
+ executing aliasing branches in the attacker context. Such attacks
+ can be partially mitigated against by clearing internal branch
+ predictor state and limiting the prediction logic in some situations.
+
+ This config option will take CPU-specific actions to harden the
+ branch predictor against aliasing attacks and may rely on specific
+ instruction sequences or control bits being set by the system
+ firmware.
+
+ If unsure, say Y.
+
menuconfig ARMV8_DEPRECATED
bool "Emulate deprecated/obsolete ARMv8 instructions"
depends on COMPAT
@@ -1011,6 +1072,22 @@ config ARM64_PMEM
operations if DC CVAP is not supported (following the behaviour of
DC CVAP itself if the system does not define a point of persistence).
+config ARM64_RAS_EXTN
+ bool "Enable support for RAS CPU Extensions"
+ default y
+ help
+ CPUs that support the Reliability, Availability and Serviceability
+ (RAS) Extensions, part of ARMv8.2 are able to track faults and
+ errors, classify them and report them to software.
+
+ On CPUs with these extensions system software can use additional
+ barriers to determine if faults are pending and read the
+ classification from a new set of registers.
+
+ Selecting this feature will allow the kernel to use these barriers
+ and access the new registers if the system supports the extension.
+ Platform RAS features may additionally depend on firmware support.
+
endmenu
config ARM64_SVE
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index b35788c909f1..b481b4a7c011 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -83,9 +83,6 @@ endif
ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/arm64/kernel/module.lds
-ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
-KBUILD_LDFLAGS_MODULE += $(objtree)/arch/arm64/kernel/ftrace-mod.o
-endif
endif
# Default value
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index d7c22d51bc50..4aa50b9b26bc 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -12,6 +12,7 @@ subdir-y += cavium
subdir-y += exynos
subdir-y += freescale
subdir-y += hisilicon
+subdir-y += lg
subdir-y += marvell
subdir-y += mediatek
subdir-y += nvidia
@@ -22,5 +23,4 @@ subdir-y += rockchip
subdir-y += socionext
subdir-y += sprd
subdir-y += xilinx
-subdir-y += lg
subdir-y += zte
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
index 45bdbfb96126..4a8d3f83a36e 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
@@ -75,6 +75,7 @@
pinctrl-0 = <&rgmii_pins>;
phy-mode = "rgmii";
phy-handle = <&ext_rgmii_phy>;
+ phy-supply = <&reg_dc1sw>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
index 806442d3e846..604cdaedac38 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
@@ -77,6 +77,7 @@
pinctrl-0 = <&rmii_pins>;
phy-mode = "rmii";
phy-handle = <&ext_rmii_phy1>;
+ phy-supply = <&reg_dc1sw>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
index 0eb2acedf8c3..abe179de35d7 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
@@ -82,6 +82,7 @@
pinctrl-0 = <&rgmii_pins>;
phy-mode = "rgmii";
phy-handle = <&ext_rgmii_phy>;
+ phy-supply = <&reg_dc1sw>;
status = "okay";
};
@@ -95,7 +96,7 @@
&mmc2 {
pinctrl-names = "default";
pinctrl-0 = <&mmc2_pins>;
- vmmc-supply = <&reg_vcc3v3>;
+ vmmc-supply = <&reg_dcdc1>;
vqmmc-supply = <&reg_vcc1v8>;
bus-width = <8>;
non-removable;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
index a5da18a6f286..43418bd881d8 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
@@ -45,19 +45,10 @@
#include "sun50i-a64.dtsi"
-/ {
- reg_vcc3v3: vcc3v3 {
- compatible = "regulator-fixed";
- regulator-name = "vcc3v3";
- regulator-min-microvolt = <3300000>;
- regulator-max-microvolt = <3300000>;
- };
-};
-
&mmc0 {
pinctrl-names = "default";
pinctrl-0 = <&mmc0_pins>;
- vmmc-supply = <&reg_vcc3v3>;
+ vmmc-supply = <&reg_dcdc1>;
non-removable;
disable-wp;
bus-width = <4>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts
index b6b7a561df8c..a42fd79a62a3 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts
@@ -71,7 +71,7 @@
pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
vmmc-supply = <&reg_vcc3v3>;
bus-width = <4>;
- cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>;
+ cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 7c9bdc7ab50b..9db19314c60c 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -66,6 +66,7 @@
<&cpu1>,
<&cpu2>,
<&cpu3>;
+ interrupt-parent = <&intc>;
};
psci {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index ead895a4e9a5..1fb8b9d6cb4e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -753,12 +753,12 @@
&uart_B {
clocks = <&xtal>, <&clkc CLKID_UART1>, <&xtal>;
- clock-names = "xtal", "core", "baud";
+ clock-names = "xtal", "pclk", "baud";
};
&uart_C {
clocks = <&xtal>, <&clkc CLKID_UART2>, <&xtal>;
- clock-names = "xtal", "core", "baud";
+ clock-names = "xtal", "pclk", "baud";
};
&vpu {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 8ed981f59e5a..6524b89e7115 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -688,7 +688,7 @@
&uart_A {
clocks = <&xtal>, <&clkc CLKID_UART0>, <&xtal>;
- clock-names = "xtal", "core", "baud";
+ clock-names = "xtal", "pclk", "baud";
};
&uart_AO {
@@ -703,12 +703,12 @@
&uart_B {
clocks = <&xtal>, <&clkc CLKID_UART1>, <&xtal>;
- clock-names = "xtal", "core", "baud";
+ clock-names = "xtal", "pclk", "baud";
};
&uart_C {
clocks = <&xtal>, <&clkc CLKID_UART2>, <&xtal>;
- clock-names = "xtal", "core", "baud";
+ clock-names = "xtal", "pclk", "baud";
};
&vpu {
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index e3b64d03fbd8..9c7724e82aff 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -63,8 +63,10 @@
cpm_ethernet: ethernet@0 {
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
- clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>, <&cpm_clk 1 5>;
- clock-names = "pp_clk", "gop_clk", "mg_clk";
+ clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>,
+ <&cpm_clk 1 5>, <&cpm_clk 1 18>;
+ clock-names = "pp_clk", "gop_clk",
+ "mg_clk","axi_clk";
marvell,system-controller = <&cpm_syscon0>;
status = "disabled";
dma-coherent;
@@ -155,7 +157,8 @@
#size-cells = <0>;
compatible = "marvell,orion-mdio";
reg = <0x12a200 0x10>;
- clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>;
+ clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>,
+ <&cpm_clk 1 6>, <&cpm_clk 1 18>;
status = "disabled";
};
@@ -338,8 +341,8 @@
compatible = "marvell,armada-cp110-sdhci";
reg = <0x780000 0x300>;
interrupts = <ICU_GRP_NSR 27 IRQ_TYPE_LEVEL_HIGH>;
- clock-names = "core";
- clocks = <&cpm_clk 1 4>;
+ clock-names = "core","axi";
+ clocks = <&cpm_clk 1 4>, <&cpm_clk 1 18>;
dma-coherent;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index 0d51096c69f8..87ac68b2cf37 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -63,8 +63,10 @@
cps_ethernet: ethernet@0 {
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
- clocks = <&cps_clk 1 3>, <&cps_clk 1 9>, <&cps_clk 1 5>;
- clock-names = "pp_clk", "gop_clk", "mg_clk";
+ clocks = <&cps_clk 1 3>, <&cps_clk 1 9>,
+ <&cps_clk 1 5>, <&cps_clk 1 18>;
+ clock-names = "pp_clk", "gop_clk",
+ "mg_clk", "axi_clk";
marvell,system-controller = <&cps_syscon0>;
status = "disabled";
dma-coherent;
@@ -155,7 +157,8 @@
#size-cells = <0>;
compatible = "marvell,orion-mdio";
reg = <0x12a200 0x10>;
- clocks = <&cps_clk 1 9>, <&cps_clk 1 5>;
+ clocks = <&cps_clk 1 9>, <&cps_clk 1 5>,
+ <&cps_clk 1 6>, <&cps_clk 1 18>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index a298df74ca6c..dbe2648649db 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -255,7 +255,6 @@
&avb {
pinctrl-0 = <&avb_pins>;
pinctrl-names = "default";
- renesas,no-ether-link;
phy-handle = <&phy0>;
status = "okay";
diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi
index 0d85b315ce71..73439cf48659 100644
--- a/arch/arm64/boot/dts/renesas/ulcb.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi
@@ -145,7 +145,6 @@
&avb {
pinctrl-0 = <&avb_pins>;
pinctrl-names = "default";
- renesas,no-ether-link;
phy-handle = <&phy0>;
status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index d4f80786e7c2..3890468678ce 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -132,6 +132,8 @@
assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>;
clock_in_out = "input";
+ /* shows instability at 1GBit right now */
+ max-speed = <100>;
phy-supply = <&vcc_io>;
phy-mode = "rgmii";
pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 41d61840fb99..2426da631938 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -514,7 +514,7 @@
tsadc: tsadc@ff250000 {
compatible = "rockchip,rk3328-tsadc";
reg = <0x0 0xff250000 0x0 0x100>;
- interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH 0>;
+ interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
assigned-clocks = <&cru SCLK_TSADC>;
assigned-clock-rates = <50000>;
clocks = <&cru SCLK_TSADC>, <&cru PCLK_TSADC>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index 910628d18add..1fc5060d7027 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -155,17 +155,6 @@
regulator-min-microvolt = <5000000>;
regulator-max-microvolt = <5000000>;
};
-
- vdd_log: vdd-log {
- compatible = "pwm-regulator";
- pwms = <&pwm2 0 25000 0>;
- regulator-name = "vdd_log";
- regulator-min-microvolt = <800000>;
- regulator-max-microvolt = <1400000>;
- regulator-always-on;
- regulator-boot-on;
- status = "okay";
- };
};
&cpu_b0 {
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts
index dd7193acc7df..6bdefb26b329 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts
@@ -40,7 +40,6 @@
};
&ethsc {
- interrupt-parent = <&gpio>;
interrupts = <0 8>;
};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
index d99e3731358c..254d6795c67e 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
@@ -40,7 +40,6 @@
};
&ethsc {
- interrupt-parent = <&gpio>;
interrupts = <0 8>;
};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts
index 864feeb35180..f9f06fcfb94a 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts
@@ -38,8 +38,7 @@
};
&ethsc {
- interrupt-parent = <&gpio>;
- interrupts = <0 8>;
+ interrupts = <4 8>;
};
&serial0 {
diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
index 48e733136db4..0ac2ace82435 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
@@ -198,8 +198,8 @@
gpio-controller;
#gpio-cells = <2>;
gpio-ranges = <&pinctrl 0 0 0>,
- <&pinctrl 96 0 0>,
- <&pinctrl 160 0 0>;
+ <&pinctrl 104 0 0>,
+ <&pinctrl 168 0 0>;
gpio-ranges-group-names = "gpio_range0",
"gpio_range1",
"gpio_range2";
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 6356c6da34ea..b20fa9b31efe 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -161,7 +161,7 @@ CONFIG_MTD_BLOCK=y
CONFIG_MTD_M25P80=y
CONFIG_MTD_NAND=y
CONFIG_MTD_NAND_DENALI_DT=y
-CONFIG_MTD_NAND_PXA3xx=y
+CONFIG_MTD_NAND_MARVELL=y
CONFIG_MTD_SPI_NOR=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_NBD=m
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 4a85c6952a22..669028172fd6 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -12,6 +12,8 @@
#include <linux/stddef.h>
#include <linux/stringify.h>
+extern int alternatives_applied;
+
struct alt_instr {
s32 orig_offset; /* offset to original instruction */
s32 alt_offset; /* offset to replacement instruction */
diff --git a/arch/arm64/include/asm/arm_dsu_pmu.h b/arch/arm64/include/asm/arm_dsu_pmu.h
new file mode 100644
index 000000000000..82e5cc3356bf
--- /dev/null
+++ b/arch/arm64/include/asm/arm_dsu_pmu.h
@@ -0,0 +1,129 @@
+/*
+ * ARM DynamIQ Shared Unit (DSU) PMU Low level register access routines.
+ *
+ * Copyright (C) ARM Limited, 2017.
+ *
+ * Author: Suzuki K Poulose <suzuki.poulose@arm.com>
+ *
+ * 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.
+ */
+
+#include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/barrier.h>
+#include <asm/sysreg.h>
+
+
+#define CLUSTERPMCR_EL1 sys_reg(3, 0, 15, 5, 0)
+#define CLUSTERPMCNTENSET_EL1 sys_reg(3, 0, 15, 5, 1)
+#define CLUSTERPMCNTENCLR_EL1 sys_reg(3, 0, 15, 5, 2)
+#define CLUSTERPMOVSSET_EL1 sys_reg(3, 0, 15, 5, 3)
+#define CLUSTERPMOVSCLR_EL1 sys_reg(3, 0, 15, 5, 4)
+#define CLUSTERPMSELR_EL1 sys_reg(3, 0, 15, 5, 5)
+#define CLUSTERPMINTENSET_EL1 sys_reg(3, 0, 15, 5, 6)
+#define CLUSTERPMINTENCLR_EL1 sys_reg(3, 0, 15, 5, 7)
+#define CLUSTERPMCCNTR_EL1 sys_reg(3, 0, 15, 6, 0)
+#define CLUSTERPMXEVTYPER_EL1 sys_reg(3, 0, 15, 6, 1)
+#define CLUSTERPMXEVCNTR_EL1 sys_reg(3, 0, 15, 6, 2)
+#define CLUSTERPMMDCR_EL1 sys_reg(3, 0, 15, 6, 3)
+#define CLUSTERPMCEID0_EL1 sys_reg(3, 0, 15, 6, 4)
+#define CLUSTERPMCEID1_EL1 sys_reg(3, 0, 15, 6, 5)
+
+static inline u32 __dsu_pmu_read_pmcr(void)
+{
+ return read_sysreg_s(CLUSTERPMCR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmcr(u32 val)
+{
+ write_sysreg_s(val, CLUSTERPMCR_EL1);
+ isb();
+}
+
+static inline u32 __dsu_pmu_get_reset_overflow(void)
+{
+ u32 val = read_sysreg_s(CLUSTERPMOVSCLR_EL1);
+ /* Clear the bit */
+ write_sysreg_s(val, CLUSTERPMOVSCLR_EL1);
+ isb();
+ return val;
+}
+
+static inline void __dsu_pmu_select_counter(int counter)
+{
+ write_sysreg_s(counter, CLUSTERPMSELR_EL1);
+ isb();
+}
+
+static inline u64 __dsu_pmu_read_counter(int counter)
+{
+ __dsu_pmu_select_counter(counter);
+ return read_sysreg_s(CLUSTERPMXEVCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_counter(int counter, u64 val)
+{
+ __dsu_pmu_select_counter(counter);
+ write_sysreg_s(val, CLUSTERPMXEVCNTR_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_set_event(int counter, u32 event)
+{
+ __dsu_pmu_select_counter(counter);
+ write_sysreg_s(event, CLUSTERPMXEVTYPER_EL1);
+ isb();
+}
+
+static inline u64 __dsu_pmu_read_pmccntr(void)
+{
+ return read_sysreg_s(CLUSTERPMCCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmccntr(u64 val)
+{
+ write_sysreg_s(val, CLUSTERPMCCNTR_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_disable_counter(int counter)
+{
+ write_sysreg_s(BIT(counter), CLUSTERPMCNTENCLR_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_enable_counter(int counter)
+{
+ write_sysreg_s(BIT(counter), CLUSTERPMCNTENSET_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_enable(int counter)
+{
+ write_sysreg_s(BIT(counter), CLUSTERPMINTENSET_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_disable(int counter)
+{
+ write_sysreg_s(BIT(counter), CLUSTERPMINTENCLR_EL1);
+ isb();
+}
+
+
+static inline u32 __dsu_pmu_read_pmceid(int n)
+{
+ switch (n) {
+ case 0:
+ return read_sysreg_s(CLUSTERPMCEID0_EL1);
+ case 1:
+ return read_sysreg_s(CLUSTERPMCEID1_EL1);
+ default:
+ BUILD_BUG();
+ return 0;
+ }
+}
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index b3da6c886835..4128bec033f6 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -4,6 +4,7 @@
#include <asm/alternative.h>
#include <asm/kernel-pgtable.h>
+#include <asm/mmu.h>
#include <asm/sysreg.h>
#include <asm/assembler.h>
@@ -12,52 +13,63 @@
*/
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
.macro __uaccess_ttbr0_disable, tmp1
- mrs \tmp1, ttbr1_el1 // swapper_pg_dir
- add \tmp1, \tmp1, #SWAPPER_DIR_SIZE // reserved_ttbr0 at the end of swapper_pg_dir
- msr ttbr0_el1, \tmp1 // set reserved TTBR0_EL1
+ mrs \tmp1, ttbr1_el1 // swapper_pg_dir
+ bic \tmp1, \tmp1, #TTBR_ASID_MASK
+ sub \tmp1, \tmp1, #RESERVED_TTBR0_SIZE // reserved_ttbr0 just before swapper_pg_dir
+ msr ttbr0_el1, \tmp1 // set reserved TTBR0_EL1
+ isb
+ add \tmp1, \tmp1, #RESERVED_TTBR0_SIZE
+ msr ttbr1_el1, \tmp1 // set reserved ASID
isb
.endm
- .macro __uaccess_ttbr0_enable, tmp1
+ .macro __uaccess_ttbr0_enable, tmp1, tmp2
get_thread_info \tmp1
ldr \tmp1, [\tmp1, #TSK_TI_TTBR0] // load saved TTBR0_EL1
+ mrs \tmp2, ttbr1_el1
+ extr \tmp2, \tmp2, \tmp1, #48
+ ror \tmp2, \tmp2, #16
+ msr ttbr1_el1, \tmp2 // set the active ASID
+ isb
msr ttbr0_el1, \tmp1 // set the non-PAN TTBR0_EL1
isb
.endm
- .macro uaccess_ttbr0_disable, tmp1
+ .macro uaccess_ttbr0_disable, tmp1, tmp2
alternative_if_not ARM64_HAS_PAN
+ save_and_disable_irq \tmp2 // avoid preemption
__uaccess_ttbr0_disable \tmp1
+ restore_irq \tmp2
alternative_else_nop_endif
.endm
- .macro uaccess_ttbr0_enable, tmp1, tmp2
+ .macro uaccess_ttbr0_enable, tmp1, tmp2, tmp3
alternative_if_not ARM64_HAS_PAN
- save_and_disable_irq \tmp2 // avoid preemption
- __uaccess_ttbr0_enable \tmp1
- restore_irq \tmp2
+ save_and_disable_irq \tmp3 // avoid preemption
+ __uaccess_ttbr0_enable \tmp1, \tmp2
+ restore_irq \tmp3
alternative_else_nop_endif
.endm
#else
- .macro uaccess_ttbr0_disable, tmp1
+ .macro uaccess_ttbr0_disable, tmp1, tmp2
.endm
- .macro uaccess_ttbr0_enable, tmp1, tmp2
+ .macro uaccess_ttbr0_enable, tmp1, tmp2, tmp3
.endm
#endif
/*
* These macros are no-ops when UAO is present.
*/
- .macro uaccess_disable_not_uao, tmp1
- uaccess_ttbr0_disable \tmp1
+ .macro uaccess_disable_not_uao, tmp1, tmp2
+ uaccess_ttbr0_disable \tmp1, \tmp2
alternative_if ARM64_ALT_PAN_NOT_UAO
SET_PSTATE_PAN(1)
alternative_else_nop_endif
.endm
- .macro uaccess_enable_not_uao, tmp1, tmp2
- uaccess_ttbr0_enable \tmp1, \tmp2
+ .macro uaccess_enable_not_uao, tmp1, tmp2, tmp3
+ uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3
alternative_if ARM64_ALT_PAN_NOT_UAO
SET_PSTATE_PAN(0)
alternative_else_nop_endif
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index aef72d886677..3873dd7b5a32 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -26,7 +26,6 @@
#include <asm/asm-offsets.h>
#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
-#include <asm/mmu_context.h>
#include <asm/page.h>
#include <asm/pgtable-hwdef.h>
#include <asm/ptrace.h>
@@ -110,6 +109,13 @@
.endm
/*
+ * RAS Error Synchronization barrier
+ */
+ .macro esb
+ hint #16
+ .endm
+
+/*
* NOP sequence
*/
.macro nops, num
@@ -255,7 +261,11 @@ lr .req x30 // link register
#else
adr_l \dst, \sym
#endif
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
mrs \tmp, tpidr_el1
+alternative_else
+ mrs \tmp, tpidr_el2
+alternative_endif
add \dst, \dst, \tmp
.endm
@@ -266,7 +276,11 @@ lr .req x30 // link register
*/
.macro ldr_this_cpu dst, sym, tmp
adr_l \dst, \sym
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
mrs \tmp, tpidr_el1
+alternative_else
+ mrs \tmp, tpidr_el2
+alternative_endif
ldr \dst, [\dst, \tmp]
.endm
@@ -344,10 +358,26 @@ alternative_endif
* tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
*/
.macro tcr_set_idmap_t0sz, valreg, tmpreg
-#ifndef CONFIG_ARM64_VA_BITS_48
ldr_l \tmpreg, idmap_t0sz
bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
-#endif
+ .endm
+
+/*
+ * tcr_compute_pa_size - set TCR.(I)PS to the highest supported
+ * ID_AA64MMFR0_EL1.PARange value
+ *
+ * tcr: register with the TCR_ELx value to be updated
+ * pos: IPS or PS bitfield position
+ * tmp{0,1}: temporary registers
+ */
+ .macro tcr_compute_pa_size, tcr, pos, tmp0, tmp1
+ mrs \tmp0, ID_AA64MMFR0_EL1
+ // Narrow PARange to fit the PS field in TCR_ELx
+ ubfx \tmp0, \tmp0, #ID_AA64MMFR0_PARANGE_SHIFT, #3
+ mov \tmp1, #ID_AA64MMFR0_PARANGE_MAX
+ cmp \tmp0, \tmp1
+ csel \tmp0, \tmp1, \tmp0, hi
+ bfi \tcr, \tmp0, \pos, #3
.endm
/*
@@ -478,37 +508,28 @@ alternative_endif
.endm
/*
- * Errata workaround prior to TTBR0_EL1 update
+ * Arrange a physical address in a TTBR register, taking care of 52-bit
+ * addresses.
*
- * val: TTBR value with new BADDR, preserved
- * tmp0: temporary register, clobbered
- * tmp1: other temporary register, clobbered
+ * phys: physical address, preserved
+ * ttbr: returns the TTBR value
*/
- .macro pre_ttbr0_update_workaround, val, tmp0, tmp1
-#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
-alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
- mrs \tmp0, ttbr0_el1
- mov \tmp1, #FALKOR_RESERVED_ASID
- bfi \tmp0, \tmp1, #48, #16 // reserved ASID + old BADDR
- msr ttbr0_el1, \tmp0
- isb
- bfi \tmp0, \val, #0, #48 // reserved ASID + new BADDR
- msr ttbr0_el1, \tmp0
- isb
-alternative_else_nop_endif
+ .macro phys_to_ttbr, phys, ttbr
+#ifdef CONFIG_ARM64_PA_BITS_52
+ orr \ttbr, \phys, \phys, lsr #46
+ and \ttbr, \ttbr, #TTBR_BADDR_MASK_52
+#else
+ mov \ttbr, \phys
#endif
.endm
-/*
- * Errata workaround post TTBR0_EL1 update.
+/**
+ * Errata workaround prior to disable MMU. Insert an ISB immediately prior
+ * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0.
*/
- .macro post_ttbr0_update_workaround
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-alternative_if ARM64_WORKAROUND_CAVIUM_27456
- ic iallu
- dsb nsh
+ .macro pre_disable_mmu_workaround
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_E1041
isb
-alternative_else_nop_endif
#endif
.endm
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 76d1cc85d5b1..955130762a3c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -38,7 +38,7 @@
*
* See Documentation/cachetlb.txt for more information. Please note that
* the implementation assumes non-aliasing VIPT D-cache and (aliasing)
- * VIPT or ASID-tagged VIVT I-cache.
+ * VIPT I-cache.
*
* flush_cache_mm(mm)
*
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index a3c7f271ad4c..c00c62e1a4a3 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -150,70 +150,6 @@ typedef u32 compat_old_sigset_t;
typedef u32 compat_sigset_word;
-typedef union compat_sigval {
- compat_int_t sival_int;
- compat_uptr_t sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[128/sizeof(int) - 3];
-
- /* kill() */
- struct {
- compat_pid_t _pid; /* sender's pid */
- __compat_uid32_t _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- compat_sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- compat_pid_t _pid; /* sender's pid */
- __compat_uid32_t _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- compat_pid_t _pid; /* which child */
- __compat_uid32_t _uid; /* sender's uid */
- int _status; /* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- compat_uptr_t _addr; /* faulting insn/memory ref. */
- short _addr_lsb; /* LSB of the reported address */
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
-
- /* SIGSYS */
- struct {
- compat_uptr_t _call_addr; /* calling user insn */
- int _syscall; /* triggering system call number */
- compat_uint_t _arch; /* AUDIT_ARCH_* of syscall */
- } _sigsys;
- } _sifields;
-} compat_siginfo_t;
-
#define COMPAT_OFF_T_MAX 0x7fffffff
/*
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 2ff7c5e8efab..bb263820de13 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -41,7 +41,11 @@
#define ARM64_WORKAROUND_CAVIUM_30115 20
#define ARM64_HAS_DCPOP 21
#define ARM64_SVE 22
+#define ARM64_UNMAP_KERNEL_AT_EL0 23
+#define ARM64_HARDEN_BRANCH_PREDICTOR 24
+#define ARM64_HARDEN_BP_POST_GUEST_EXIT 25
+#define ARM64_HAS_RAS_EXTN 26
-#define ARM64_NCAPS 23
+#define ARM64_NCAPS 27
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index ac67cfc2585a..060e3a4008ab 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -60,6 +60,9 @@ enum ftr_type {
#define FTR_VISIBLE true /* Feature visible to the user space */
#define FTR_HIDDEN false /* Feature is hidden from the user */
+#define FTR_VISIBLE_IF_IS_ENABLED(config) \
+ (IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN)
+
struct arm64_ftr_bits {
bool sign; /* Value is signed ? */
bool visible;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 235e77d98261..be7bd19c87ec 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -79,26 +79,37 @@
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
#define ARM_CPU_PART_CORTEX_A57 0xD07
+#define ARM_CPU_PART_CORTEX_A72 0xD08
#define ARM_CPU_PART_CORTEX_A53 0xD03
#define ARM_CPU_PART_CORTEX_A73 0xD09
+#define ARM_CPU_PART_CORTEX_A75 0xD0A
#define APM_CPU_PART_POTENZA 0x000
#define CAVIUM_CPU_PART_THUNDERX 0x0A1
#define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2
#define CAVIUM_CPU_PART_THUNDERX_83XX 0x0A3
+#define CAVIUM_CPU_PART_THUNDERX2 0x0AF
#define BRCM_CPU_PART_VULCAN 0x516
#define QCOM_CPU_PART_FALKOR_V1 0x800
+#define QCOM_CPU_PART_FALKOR 0xC00
+#define QCOM_CPU_PART_KRYO 0x200
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
#define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73)
+#define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
+#define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2)
+#define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN)
#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
+#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)
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 650344d01124..8389050328bb 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -121,22 +121,22 @@ static inline void efi_set_pgd(struct mm_struct *mm)
if (mm != current->active_mm) {
/*
* Update the current thread's saved ttbr0 since it is
- * restored as part of a return from exception. Set
- * the hardware TTBR0_EL1 using cpu_switch_mm()
- * directly to enable potential errata workarounds.
+ * restored as part of a return from exception. Enable
+ * access to the valid TTBR0_EL1 and invoke the errata
+ * workaround directly since there is no return from
+ * exception when invoking the EFI run-time services.
*/
update_saved_ttbr0(current, mm);
- cpu_switch_mm(mm->pgd, mm);
+ uaccess_ttbr0_enable();
+ post_ttbr_update_workaround();
} else {
/*
* Defer the switch to the current thread's TTBR0_EL1
* until uaccess_enable(). Restore the current
* thread's saved ttbr0 corresponding to its active_mm
- * (if different from init_mm).
*/
- cpu_set_reserved_ttbr0();
- if (current->active_mm != &init_mm)
- update_saved_ttbr0(current, current->active_mm);
+ uaccess_ttbr0_disable();
+ update_saved_ttbr0(current, current->active_mm);
}
}
}
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 014d7d8edcf9..803443d74926 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -86,6 +86,18 @@
#define ESR_ELx_WNR_SHIFT (6)
#define ESR_ELx_WNR (UL(1) << ESR_ELx_WNR_SHIFT)
+/* Asynchronous Error Type */
+#define ESR_ELx_IDS_SHIFT (24)
+#define ESR_ELx_IDS (UL(1) << ESR_ELx_IDS_SHIFT)
+#define ESR_ELx_AET_SHIFT (10)
+#define ESR_ELx_AET (UL(0x7) << ESR_ELx_AET_SHIFT)
+
+#define ESR_ELx_AET_UC (UL(0) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UEU (UL(1) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UEO (UL(2) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UER (UL(3) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_CE (UL(6) << ESR_ELx_AET_SHIFT)
+
/* Shared ISS field definitions for Data/Instruction aborts */
#define ESR_ELx_SET_SHIFT (11)
#define ESR_ELx_SET_MASK (UL(3) << ESR_ELx_SET_SHIFT)
@@ -100,6 +112,7 @@
#define ESR_ELx_FSC (0x3F)
#define ESR_ELx_FSC_TYPE (0x3C)
#define ESR_ELx_FSC_EXTABT (0x10)
+#define ESR_ELx_FSC_SERROR (0x11)
#define ESR_ELx_FSC_ACCESS (0x08)
#define ESR_ELx_FSC_FAULT (0x04)
#define ESR_ELx_FSC_PERM (0x0C)
@@ -127,6 +140,13 @@
#define ESR_ELx_WFx_ISS_WFE (UL(1) << 0)
#define ESR_ELx_xVC_IMM_MASK ((1UL << 16) - 1)
+#define DISR_EL1_IDS (UL(1) << 24)
+/*
+ * DISR_EL1 and ESR_ELx share the bottom 13 bits, but the RES0 bits may mean
+ * different things in the future...
+ */
+#define DISR_EL1_ESR_MASK (ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC)
+
/* ESR value templates for specific events */
/* BRK instruction trap from AArch64 state */
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 0c2eec490abf..bc30429d8e91 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -18,6 +18,8 @@
#ifndef __ASM_EXCEPTION_H
#define __ASM_EXCEPTION_H
+#include <asm/esr.h>
+
#include <linux/interrupt.h>
#define __exception __attribute__((section(".exception.text")))
@@ -27,4 +29,16 @@
#define __exception_irq_entry __exception
#endif
+static inline u32 disr_to_esr(u64 disr)
+{
+ unsigned int esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT;
+
+ if ((disr & DISR_EL1_IDS) == 0)
+ esr |= (disr & DISR_EL1_ESR_MASK);
+ else
+ esr |= (disr & ESR_ELx_ISS_MASK);
+
+ return esr;
+}
+
#endif /* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 4052ec39e8db..ec1e6d6fa14c 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -58,6 +58,11 @@ enum fixed_addresses {
FIX_APEI_GHES_NMI,
#endif /* CONFIG_ACPI_APEI_GHES */
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ FIX_ENTRY_TRAMP_DATA,
+ FIX_ENTRY_TRAMP_TEXT,
+#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT))
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
__end_of_permanent_fixed_addresses,
/*
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 74f34392a531..8857a0f0d0f7 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -71,7 +71,7 @@ extern void fpsimd_flush_thread(void);
extern void fpsimd_signal_preserve_current_state(void);
extern void fpsimd_preserve_current_state(void);
extern void fpsimd_restore_current_state(void);
-extern void fpsimd_update_current_state(struct fpsimd_state *state);
+extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
extern void fpsimd_flush_task_state(struct task_struct *target);
extern void sve_flush_cpu_state(void);
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 7803343e5881..82386e860dd2 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -52,7 +52,52 @@
#define IDMAP_PGTABLE_LEVELS (ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT))
#endif
-#define SWAPPER_DIR_SIZE (SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
+
+/*
+ * If KASLR is enabled, then an offset K is added to the kernel address
+ * space. The bottom 21 bits of this offset are zero to guarantee 2MB
+ * alignment for PA and VA.
+ *
+ * For each pagetable level of the swapper, we know that the shift will
+ * be larger than 21 (for the 4KB granule case we use section maps thus
+ * the smallest shift is actually 30) thus there is the possibility that
+ * KASLR can increase the number of pagetable entries by 1, so we make
+ * room for this extra entry.
+ *
+ * Note KASLR cannot increase the number of required entries for a level
+ * by more than one because it increments both the virtual start and end
+ * addresses equally (the extra entry comes from the case where the end
+ * address is just pushed over a boundary and the start address isn't).
+ */
+
+#ifdef CONFIG_RANDOMIZE_BASE
+#define EARLY_KASLR (1)
+#else
+#define EARLY_KASLR (0)
+#endif
+
+#define EARLY_ENTRIES(vstart, vend, shift) (((vend) >> (shift)) \
+ - ((vstart) >> (shift)) + 1 + EARLY_KASLR)
+
+#define EARLY_PGDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT))
+
+#if SWAPPER_PGTABLE_LEVELS > 3
+#define EARLY_PUDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT))
+#else
+#define EARLY_PUDS(vstart, vend) (0)
+#endif
+
+#if SWAPPER_PGTABLE_LEVELS > 2
+#define EARLY_PMDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT))
+#else
+#define EARLY_PMDS(vstart, vend) (0)
+#endif
+
+#define EARLY_PAGES(vstart, vend) ( 1 /* PGDIR page */ \
+ + EARLY_PGDS((vstart), (vend)) /* each PGDIR needs a next level page table */ \
+ + EARLY_PUDS((vstart), (vend)) /* each PUD needs a next level page table */ \
+ + EARLY_PMDS((vstart), (vend))) /* each PMD needs a next level page table */
+#define SWAPPER_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
#define IDMAP_DIR_SIZE (IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
@@ -78,8 +123,16 @@
/*
* Initial memory map attributes.
*/
-#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define _SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define SWAPPER_PTE_FLAGS (_SWAPPER_PTE_FLAGS | PTE_NG)
+#define SWAPPER_PMD_FLAGS (_SWAPPER_PMD_FLAGS | PMD_SECT_NG)
+#else
+#define SWAPPER_PTE_FLAGS _SWAPPER_PTE_FLAGS
+#define SWAPPER_PMD_FLAGS _SWAPPER_PMD_FLAGS
+#endif
#if ARM64_SWAPPER_USES_SECTION_MAPS
#define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 7f069ff37f06..b0c84171e6a3 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,8 @@
#include <asm/types.h>
/* Hyp Configuration Register (HCR) bits */
+#define HCR_TEA (UL(1) << 37)
+#define HCR_TERR (UL(1) << 36)
#define HCR_E2H (UL(1) << 34)
#define HCR_ID (UL(1) << 33)
#define HCR_CD (UL(1) << 32)
@@ -170,8 +172,7 @@
#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
#define VTTBR_X (VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
#define VTTBR_VMID_SHIFT (UL(48))
#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index ab4d0a926043..24961b732e65 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -68,6 +68,8 @@ extern u32 __kvm_get_mdcr_el2(void);
extern u32 __init_stage2_translation(void);
+extern void __qcom_hyp_sanitize_btac_predictors(void);
+
#endif
#endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5f28dfa14cee..413dc82b1e89 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -50,6 +50,13 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
if (is_kernel_in_hyp_mode())
vcpu->arch.hcr_el2 |= HCR_E2H;
+ if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) {
+ /* route synchronous external abort exceptions to EL2 */
+ vcpu->arch.hcr_el2 |= HCR_TEA;
+ /* trap error record accesses */
+ vcpu->arch.hcr_el2 |= HCR_TERR;
+ }
+
if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
vcpu->arch.hcr_el2 &= ~HCR_RW;
}
@@ -64,6 +71,11 @@ static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
vcpu->arch.hcr_el2 = hcr;
}
+static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr)
+{
+ vcpu->arch.vsesr_el2 = vsesr;
+}
+
static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
{
return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
@@ -171,6 +183,11 @@ static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
}
+static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.fault.disr_el1;
+}
+
static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu)
{
return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 674912d7a571..4485ae8e98de 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -25,6 +25,7 @@
#include <linux/types.h>
#include <linux/kvm_types.h>
#include <asm/cpufeature.h>
+#include <asm/daifflags.h>
#include <asm/fpsimd.h>
#include <asm/kvm.h>
#include <asm/kvm_asm.h>
@@ -89,6 +90,7 @@ struct kvm_vcpu_fault_info {
u32 esr_el2; /* Hyp Syndrom Register */
u64 far_el2; /* Hyp Fault Address Register */
u64 hpfar_el2; /* Hyp IPA Fault Address Register */
+ u64 disr_el1; /* Deferred [SError] Status Register */
};
/*
@@ -120,6 +122,7 @@ enum vcpu_sysreg {
PAR_EL1, /* Physical Address Register */
MDSCR_EL1, /* Monitor Debug System Control Register */
MDCCINT_EL1, /* Monitor Debug Comms Channel Interrupt Enable Reg */
+ DISR_EL1, /* Deferred Interrupt Status Register */
/* Performance Monitors Registers */
PMCR_EL0, /* Control Register */
@@ -192,6 +195,8 @@ struct kvm_cpu_context {
u64 sys_regs[NR_SYS_REGS];
u32 copro[NR_COPRO_REGS];
};
+
+ struct kvm_vcpu *__hyp_running_vcpu;
};
typedef struct kvm_cpu_context kvm_cpu_context_t;
@@ -277,6 +282,9 @@ struct kvm_vcpu_arch {
/* Detect first run of a vcpu */
bool has_run_once;
+
+ /* Virtual SError ESR to restore when HCR_EL2.VSE is set */
+ u64 vsesr_el2;
};
#define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs)
@@ -340,6 +348,8 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
int exception_index);
+void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ int exception_index);
int kvm_perf_init(void);
int kvm_perf_teardown(void);
@@ -370,6 +380,7 @@ void kvm_arm_init_debug(void);
void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
@@ -395,4 +406,13 @@ static inline void kvm_fpsimd_flush_cpu_state(void)
sve_flush_cpu_state();
}
+static inline void kvm_arm_vhe_guest_enter(void)
+{
+ local_daif_mask();
+}
+
+static inline void kvm_arm_vhe_guest_exit(void)
+{
+ local_daif_restore(DAIF_PROCCTX_NOIRQ);
+}
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 672c8684d5c2..72e279dbae5f 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -273,15 +273,26 @@ void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
static inline bool __kvm_cpu_uses_extended_idmap(void)
{
- return __cpu_uses_extended_idmap();
+ return __cpu_uses_extended_idmap_level();
}
+static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
+{
+ return idmap_ptrs_per_pgd;
+}
+
+/*
+ * Can't use pgd_populate here, because the extended idmap adds an extra level
+ * above CONFIG_PGTABLE_LEVELS (which is 2 or 3 if we're using the extended
+ * idmap), and pgd_populate is only available if CONFIG_PGTABLE_LEVELS = 4.
+ */
static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
pgd_t *hyp_pgd,
pgd_t *merged_hyp_pgd,
unsigned long hyp_idmap_start)
{
int idmap_idx;
+ u64 pgd_addr;
/*
* Use the first entry to access the HYP mappings. It is
@@ -289,7 +300,8 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
* extended idmap.
*/
VM_BUG_ON(pgd_val(merged_hyp_pgd[0]));
- merged_hyp_pgd[0] = __pgd(__pa(hyp_pgd) | PMD_TYPE_TABLE);
+ pgd_addr = __phys_to_pgd_val(__pa(hyp_pgd));
+ merged_hyp_pgd[0] = __pgd(pgd_addr | PMD_TYPE_TABLE);
/*
* Create another extended level entry that points to the boot HYP map,
@@ -299,7 +311,8 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
*/
idmap_idx = hyp_idmap_start >> VA_BITS;
VM_BUG_ON(pgd_val(merged_hyp_pgd[idmap_idx]));
- merged_hyp_pgd[idmap_idx] = __pgd(__pa(boot_hyp_pgd) | PMD_TYPE_TABLE);
+ pgd_addr = __phys_to_pgd_val(__pa(boot_hyp_pgd));
+ merged_hyp_pgd[idmap_idx] = __pgd(pgd_addr | PMD_TYPE_TABLE);
}
static inline unsigned int kvm_get_vmid_bits(void)
@@ -309,5 +322,45 @@ static inline unsigned int kvm_get_vmid_bits(void)
return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
}
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#include <asm/mmu.h>
+
+static inline void *kvm_get_hyp_vector(void)
+{
+ struct bp_hardening_data *data = arm64_get_bp_hardening_data();
+ void *vect = kvm_ksym_ref(__kvm_hyp_vector);
+
+ if (data->fn) {
+ vect = __bp_harden_hyp_vecs_start +
+ data->hyp_vectors_slot * SZ_2K;
+
+ if (!has_vhe())
+ vect = lm_alias(vect);
+ }
+
+ return vect;
+}
+
+static inline int kvm_map_vectors(void)
+{
+ return create_hyp_mappings(kvm_ksym_ref(__bp_harden_hyp_vecs_start),
+ kvm_ksym_ref(__bp_harden_hyp_vecs_end),
+ PAGE_HYP_EXEC);
+}
+
+#else
+static inline void *kvm_get_hyp_vector(void)
+{
+ return kvm_ksym_ref(__kvm_hyp_vector);
+}
+
+static inline int kvm_map_vectors(void)
+{
+ return 0;
+}
+#endif
+
+#define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr)
+
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 0d34bf0a89c7..a050d4f3615d 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -17,6 +17,11 @@
#define __ASM_MMU_H
#define MMCF_AARCH32 0x1 /* mm context flag for AArch32 executables */
+#define USER_ASID_BIT 48
+#define USER_ASID_FLAG (UL(1) << USER_ASID_BIT)
+#define TTBR_ASID_MASK (UL(0xffff) << 48)
+
+#ifndef __ASSEMBLY__
typedef struct {
atomic64_t id;
@@ -31,6 +36,49 @@ typedef struct {
*/
#define ASID(mm) ((mm)->context.id.counter & 0xffff)
+static inline bool arm64_kernel_unmapped_at_el0(void)
+{
+ return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) &&
+ cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
+}
+
+typedef void (*bp_hardening_cb_t)(void);
+
+struct bp_hardening_data {
+ int hyp_vectors_slot;
+ bp_hardening_cb_t fn;
+};
+
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+
+DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
+{
+ return this_cpu_ptr(&bp_hardening_data);
+}
+
+static inline void arm64_apply_bp_hardening(void)
+{
+ struct bp_hardening_data *d;
+
+ if (!cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR))
+ return;
+
+ d = arm64_get_bp_hardening_data();
+ if (d->fn)
+ d->fn();
+}
+#else
+static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
+{
+ return NULL;
+}
+
+static inline void arm64_apply_bp_hardening(void) { }
+#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR */
+
extern void paging_init(void);
extern void bootmem_init(void);
extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
@@ -41,4 +89,5 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
extern void mark_linear_text_alias_ro(void);
+#endif /* !__ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 3257895a9b5e..8d3331985d2e 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -19,8 +19,6 @@
#ifndef __ASM_MMU_CONTEXT_H
#define __ASM_MMU_CONTEXT_H
-#define FALKOR_RESERVED_ASID 1
-
#ifndef __ASSEMBLY__
#include <linux/compiler.h>
@@ -51,23 +49,39 @@ static inline void contextidr_thread_switch(struct task_struct *next)
*/
static inline void cpu_set_reserved_ttbr0(void)
{
- unsigned long ttbr = __pa_symbol(empty_zero_page);
+ unsigned long ttbr = phys_to_ttbr(__pa_symbol(empty_zero_page));
write_sysreg(ttbr, ttbr0_el1);
isb();
}
+static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+ BUG_ON(pgd == swapper_pg_dir);
+ cpu_set_reserved_ttbr0();
+ cpu_do_switch_mm(virt_to_phys(pgd),mm);
+}
+
/*
* TCR.T0SZ value to use when the ID map is active. Usually equals
* TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in
* physical memory, in which case it will be smaller.
*/
extern u64 idmap_t0sz;
+extern u64 idmap_ptrs_per_pgd;
static inline bool __cpu_uses_extended_idmap(void)
{
- return (!IS_ENABLED(CONFIG_ARM64_VA_BITS_48) &&
- unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)));
+ return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS));
+}
+
+/*
+ * True if the extended ID map requires an extra level of translation table
+ * to be configured.
+ */
+static inline bool __cpu_uses_extended_idmap_level(void)
+{
+ return ARM64_HW_PGTABLE_LEVELS(64 - idmap_t0sz) > CONFIG_PGTABLE_LEVELS;
}
/*
@@ -156,29 +170,21 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
#define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 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)
-{
-}
-
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
static inline void update_saved_ttbr0(struct task_struct *tsk,
struct mm_struct *mm)
{
- if (system_uses_ttbr0_pan()) {
- BUG_ON(mm->pgd == swapper_pg_dir);
- task_thread_info(tsk)->ttbr0 =
- virt_to_phys(mm->pgd) | ASID(mm) << 48;
- }
+ u64 ttbr;
+
+ if (!system_uses_ttbr0_pan())
+ return;
+
+ if (mm == &init_mm)
+ ttbr = __pa_symbol(empty_zero_page);
+ else
+ ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48;
+
+ WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr);
}
#else
static inline void update_saved_ttbr0(struct task_struct *tsk,
@@ -187,6 +193,16 @@ static inline void update_saved_ttbr0(struct task_struct *tsk,
}
#endif
+static inline void
+enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+ /*
+ * We don't actually care about the ttbr0 mapping, so point it at the
+ * zero page.
+ */
+ update_saved_ttbr0(tsk, &init_mm);
+}
+
static inline void __switch_mm(struct mm_struct *next)
{
unsigned int cpu = smp_processor_id();
@@ -214,17 +230,16 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
* Update the saved TTBR0_EL1 of the scheduled-in task as the previous
* value may have not been initialised yet (activate_mm caller) or the
* ASID has changed since the last run (following the context switch
- * of another thread of the same process). Avoid setting the reserved
- * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit).
+ * of another thread of the same process).
*/
- if (next != &init_mm)
- update_saved_ttbr0(tsk, next);
+ update_saved_ttbr0(tsk, next);
}
#define deactivate_mm(tsk,mm) do { } while (0)
#define activate_mm(prev,next) switch_mm(prev, next, current)
void verify_cpu_asid_bits(void);
+void post_ttbr_update_workaround(void);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 19bd97671bb8..4f766178fa6f 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -32,7 +32,7 @@ struct mod_arch_specific {
struct mod_plt_sec init;
/* for CONFIG_DYNAMIC_FTRACE */
- void *ftrace_trampoline;
+ struct plt_entry *ftrace_trampoline;
};
#endif
@@ -45,4 +45,48 @@ extern u64 module_alloc_base;
#define module_alloc_base ((u64)_etext - MODULES_VSIZE)
#endif
+struct plt_entry {
+ /*
+ * A program that conforms to the AArch64 Procedure Call Standard
+ * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
+ * IP1 (x17) may be inserted at any branch instruction that is
+ * exposed to a relocation that supports long branches. Since that
+ * is exactly what we are dealing with here, we are free to use x16
+ * as a scratch register in the PLT veneers.
+ */
+ __le32 mov0; /* movn x16, #0x.... */
+ __le32 mov1; /* movk x16, #0x...., lsl #16 */
+ __le32 mov2; /* movk x16, #0x...., lsl #32 */
+ __le32 br; /* br x16 */
+};
+
+static inline struct plt_entry get_plt_entry(u64 val)
+{
+ /*
+ * MOVK/MOVN/MOVZ opcode:
+ * +--------+------------+--------+-----------+-------------+---------+
+ * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
+ * +--------+------------+--------+-----------+-------------+---------+
+ *
+ * Rd := 0x10 (x16)
+ * hw := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
+ * opc := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
+ * sf := 1 (64-bit variant)
+ */
+ return (struct plt_entry){
+ cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5),
+ cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
+ cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
+ cpu_to_le32(0xd61f0200)
+ };
+}
+
+static inline bool plt_entries_equal(const struct plt_entry *a,
+ const struct plt_entry *b)
+{
+ return a->mov0 == b->mov0 &&
+ a->mov1 == b->mov1 &&
+ a->mov2 == b->mov2;
+}
+
#endif /* __ASM_MODULE_H */
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 3bd498e4de4c..43393208229e 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,11 +16,15 @@
#ifndef __ASM_PERCPU_H
#define __ASM_PERCPU_H
+#include <asm/alternative.h>
#include <asm/stack_pointer.h>
static inline void set_my_cpu_offset(unsigned long off)
{
- asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
+ asm volatile(ALTERNATIVE("msr tpidr_el1, %0",
+ "msr tpidr_el2, %0",
+ ARM64_HAS_VIRT_HOST_EXTN)
+ :: "r" (off) : "memory");
}
static inline unsigned long __my_cpu_offset(void)
@@ -31,7 +35,10 @@ static inline unsigned long __my_cpu_offset(void)
* We want to allow caching the value, so avoid using volatile and
* instead use a fake stack read to hazard against barrier().
*/
- asm("mrs %0, tpidr_el1" : "=r" (off) :
+ asm(ALTERNATIVE("mrs %0, tpidr_el1",
+ "mrs %0, tpidr_el2",
+ ARM64_HAS_VIRT_HOST_EXTN)
+ : "=r" (off) :
"Q" (*(const unsigned long *)current_stack_pointer));
return off;
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 8d5cbec17d80..f9ccc36d3dc3 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -18,6 +18,7 @@
#define __ASM_PERF_EVENT_H
#include <asm/stack_pointer.h>
+#include <asm/ptrace.h>
#define ARMV8_PMU_MAX_COUNTERS 32
#define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1)
@@ -79,6 +80,7 @@ struct pt_regs;
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
+#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
#endif
#define perf_arch_fetch_caller_regs(regs, __ip) { \
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 5ca6a573a701..e9d9f1b006ef 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -44,7 +44,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot)
{
- set_pud(pud, __pud(pmd | prot));
+ set_pud(pud, __pud(__phys_to_pud_val(pmd) | prot));
}
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
@@ -73,7 +73,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot)
{
- set_pgd(pgdp, __pgd(pud | prot));
+ set_pgd(pgdp, __pgd(__phys_to_pgd_val(pud) | prot));
}
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
@@ -129,7 +129,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
pmdval_t prot)
{
- set_pmd(pmdp, __pmd(pte | prot));
+ set_pmd(pmdp, __pmd(__phys_to_pmd_val(pte) | prot));
}
/*
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index eb0c2bd90de9..f42836da8723 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -16,6 +16,8 @@
#ifndef __ASM_PGTABLE_HWDEF_H
#define __ASM_PGTABLE_HWDEF_H
+#include <asm/memory.h>
+
/*
* Number of page-table levels required to address 'va_bits' wide
* address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
@@ -116,9 +118,9 @@
* Level 1 descriptor (PUD).
*/
#define PUD_TYPE_TABLE (_AT(pudval_t, 3) << 0)
-#define PUD_TABLE_BIT (_AT(pgdval_t, 1) << 1)
-#define PUD_TYPE_MASK (_AT(pgdval_t, 3) << 0)
-#define PUD_TYPE_SECT (_AT(pgdval_t, 1) << 0)
+#define PUD_TABLE_BIT (_AT(pudval_t, 1) << 1)
+#define PUD_TYPE_MASK (_AT(pudval_t, 3) << 0)
+#define PUD_TYPE_SECT (_AT(pudval_t, 1) << 0)
/*
* Level 2 descriptor (PMD).
@@ -166,6 +168,14 @@
#define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */
#define PTE_HYP_XN (_AT(pteval_t, 1) << 54) /* HYP XN */
+#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define PTE_ADDR_HIGH (_AT(pteval_t, 0xf) << 12)
+#define PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH)
+#else
+#define PTE_ADDR_MASK PTE_ADDR_LOW
+#endif
+
/*
* AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
*/
@@ -196,7 +206,7 @@
/*
* Highest possible physical address supported.
*/
-#define PHYS_MASK_SHIFT (48)
+#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS)
#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1)
/*
@@ -272,9 +282,23 @@
#define TCR_TG1_4K (UL(2) << TCR_TG1_SHIFT)
#define TCR_TG1_64K (UL(3) << TCR_TG1_SHIFT)
+#define TCR_IPS_SHIFT 32
+#define TCR_IPS_MASK (UL(7) << TCR_IPS_SHIFT)
+#define TCR_A1 (UL(1) << 22)
#define TCR_ASID16 (UL(1) << 36)
#define TCR_TBI0 (UL(1) << 37)
#define TCR_HA (UL(1) << 39)
#define TCR_HD (UL(1) << 40)
+/*
+ * TTBR.
+ */
+#ifdef CONFIG_ARM64_PA_BITS_52
+/*
+ * This should be GENMASK_ULL(47, 2).
+ * TTBR_ELx[1] is RES0 in this configuration.
+ */
+#define TTBR_BADDR_MASK_52 (((UL(1) << 46) - 1) << 2)
+#endif
+
#endif
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 0a5635fb0ef9..22a926825e3f 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -34,8 +34,16 @@
#include <asm/pgtable-types.h>
-#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define PROT_DEFAULT (_PROT_DEFAULT | PTE_NG)
+#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_SECT_NG)
+#else
+#define PROT_DEFAULT _PROT_DEFAULT
+#define PROT_SECT_DEFAULT _PROT_SECT_DEFAULT
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
@@ -48,6 +56,7 @@
#define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+#define _HYP_PAGE_DEFAULT (_PAGE_DEFAULT & ~PTE_NG)
#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
@@ -55,15 +64,15 @@
#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
-#define PAGE_HYP __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
-#define PAGE_HYP_EXEC __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
-#define PAGE_HYP_RO __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
+#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_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
-#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
+#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index c9530b5b5ca8..89167c43ebb5 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -42,6 +42,8 @@
#include <asm/cmpxchg.h>
#include <asm/fixmap.h>
#include <linux/mmdebug.h>
+#include <linux/mm_types.h>
+#include <linux/sched.h>
extern void __pte_error(const char *file, int line, unsigned long val);
extern void __pmd_error(const char *file, int line, unsigned long val);
@@ -57,9 +59,22 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte_val(pte))
-#define pte_pfn(pte) ((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
+/*
+ * Macros to convert between a physical address and its placement in a
+ * page table entry, taking care of 52-bit addresses.
+ */
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define __pte_to_phys(pte) \
+ ((pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << 36))
+#define __phys_to_pte_val(phys) (((phys) | ((phys) >> 36)) & PTE_ADDR_MASK)
+#else
+#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_MASK)
+#define __phys_to_pte_val(phys) (phys)
+#endif
-#define pfn_pte(pfn,prot) (__pte(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pte_pfn(pte) (__pte_to_phys(pte) >> PAGE_SHIFT)
+#define pfn_pte(pfn,prot) \
+ __pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
#define pte_none(pte) (!pte_val(pte))
#define pte_clear(mm,addr,ptep) set_pte(ptep, __pte(0))
@@ -149,12 +164,20 @@ static inline pte_t pte_mkwrite(pte_t pte)
static inline pte_t pte_mkclean(pte_t pte)
{
- return clear_pte_bit(pte, __pgprot(PTE_DIRTY));
+ pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY));
+ pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+
+ return pte;
}
static inline pte_t pte_mkdirty(pte_t pte)
{
- return set_pte_bit(pte, __pgprot(PTE_DIRTY));
+ pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
+
+ if (pte_write(pte))
+ pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+
+ return pte;
}
static inline pte_t pte_mkold(pte_t pte)
@@ -207,9 +230,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
}
}
-struct mm_struct;
-struct vm_area_struct;
-
extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
/*
@@ -238,7 +258,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
* hardware updates of the pte (ptep_set_access_flags safely changes
* valid ptes without going through an invalid entry).
*/
- if (pte_valid(*ptep) && pte_valid(pte)) {
+ if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) &&
+ (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) {
VM_WARN_ONCE(!pte_young(pte),
"%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
__func__, pte_val(*ptep), pte_val(pte));
@@ -284,6 +305,11 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
#define __HAVE_ARCH_PTE_SPECIAL
+static inline pte_t pgd_pte(pgd_t pgd)
+{
+ return __pte(pgd_val(pgd));
+}
+
static inline pte_t pud_pte(pud_t pud)
{
return __pte(pud_val(pud));
@@ -345,20 +371,28 @@ static inline int pmd_protnone(pmd_t pmd)
#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd))
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
-#define pmd_pfn(pmd) (((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
-#define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd))
+#define __phys_to_pmd_val(phys) __phys_to_pte_val(phys)
+#define pmd_pfn(pmd) ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot)
#define pud_write(pud) pte_write(pud_pte(pud))
-#define pud_pfn(pud) (((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+
+#define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud))
+#define __phys_to_pud_val(phys) __phys_to_pte_val(phys)
+#define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
+#define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
+#define __pgd_to_phys(pgd) __pte_to_phys(pgd_pte(pgd))
+#define __phys_to_pgd_val(phys) __phys_to_pte_val(phys)
+
#define __pgprot_modify(prot,mask,bits) \
__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
@@ -409,7 +443,7 @@ static inline void pmd_clear(pmd_t *pmdp)
static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
{
- return pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK;
+ return __pmd_to_phys(pmd);
}
/* Find an entry in the third-level page table. */
@@ -427,7 +461,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
#define pte_set_fixmap_offset(pmd, addr) pte_set_fixmap(pte_offset_phys(pmd, addr))
#define pte_clear_fixmap() clear_fixmap(FIX_PTE)
-#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(__pmd_to_phys(pmd)))
/* use ONLY for statically allocated translation tables */
#define pte_offset_kimg(dir,addr) ((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr))))
@@ -460,7 +494,7 @@ static inline void pud_clear(pud_t *pudp)
static inline phys_addr_t pud_page_paddr(pud_t pud)
{
- return pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK;
+ return __pud_to_phys(pud);
}
/* Find an entry in the second-level page table. */
@@ -473,7 +507,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud)
#define pmd_set_fixmap_offset(pud, addr) pmd_set_fixmap(pmd_offset_phys(pud, addr))
#define pmd_clear_fixmap() clear_fixmap(FIX_PMD)
-#define pud_page(pud) pfn_to_page(__phys_to_pfn(pud_val(pud) & PHYS_MASK))
+#define pud_page(pud) pfn_to_page(__phys_to_pfn(__pud_to_phys(pud)))
/* use ONLY for statically allocated translation tables */
#define pmd_offset_kimg(dir,addr) ((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr))))
@@ -512,7 +546,7 @@ static inline void pgd_clear(pgd_t *pgdp)
static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
{
- return pgd_val(pgd) & PHYS_MASK & (s32)PAGE_MASK;
+ return __pgd_to_phys(pgd);
}
/* Find an entry in the frst-level page table. */
@@ -525,7 +559,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
#define pud_set_fixmap_offset(pgd, addr) pud_set_fixmap(pud_offset_phys(pgd, addr))
#define pud_clear_fixmap() clear_fixmap(FIX_PUD)
-#define pgd_page(pgd) pfn_to_page(__phys_to_pfn(pgd_val(pgd) & PHYS_MASK))
+#define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd)))
/* use ONLY for statically allocated translation tables */
#define pud_offset_kimg(dir,addr) ((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr))))
@@ -642,28 +676,23 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * ptep_set_wrprotect - mark read-only while preserving the hardware update of
- * the Access Flag.
+ * ptep_set_wrprotect - mark read-only while trasferring potential hardware
+ * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
*/
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
{
pte_t old_pte, pte;
- /*
- * ptep_set_wrprotect() is only called on CoW mappings which are
- * private (!VM_SHARED) with the pte either read-only (!PTE_WRITE &&
- * PTE_RDONLY) or writable and software-dirty (PTE_WRITE &&
- * !PTE_RDONLY && PTE_DIRTY); see is_cow_mapping() and
- * protection_map[]. There is no race with the hardware update of the
- * dirty state: clearing of PTE_RDONLY when PTE_WRITE (a.k.a. PTE_DBM)
- * is set.
- */
- VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(*ptep),
- "%s: potential race with hardware DBM", __func__);
pte = READ_ONCE(*ptep);
do {
old_pte = pte;
+ /*
+ * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
+ * clear), set the PTE_DIRTY bit.
+ */
+ if (pte_hw_dirty(pte))
+ pte = pte_mkdirty(pte);
pte = pte_wrprotect(pte);
pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
pte_val(old_pte), pte_val(pte));
@@ -680,7 +709,9 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
#endif
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+extern pgd_t swapper_pg_end[];
extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
/*
* Encode and decode a swap entry:
@@ -734,6 +765,12 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
#define kc_vaddr_to_offset(v) ((v) & ~VA_START)
#define kc_offset_to_vaddr(o) ((o) | VA_START)
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
+#else
+#define phys_to_ttbr(addr) (addr)
+#endif
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 14ad6e4e87d1..16cef2e8449e 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -35,12 +35,6 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
#include <asm/memory.h>
-#define cpu_switch_mm(pgd,mm) \
-do { \
- BUG_ON(pgd == swapper_pg_dir); \
- cpu_do_switch_mm(virt_to_phys(pgd),mm); \
-} while (0)
-
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* __ASM_PROCFNS_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 023cacb946c3..cee4ae25a5d1 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -216,6 +216,7 @@ static inline void spin_lock_prefetch(const void *ptr)
int cpu_enable_pan(void *__unused);
int cpu_enable_cache_maint_trap(void *__unused);
+int cpu_clear_disr(void *__unused);
/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
#define SVE_SET_VL(arg) sve_set_current_vl(arg)
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
new file mode 100644
index 000000000000..e073e6886685
--- /dev/null
+++ b/arch/arm64/include/asm/sdei.h
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#ifndef __ASM_SDEI_H
+#define __ASM_SDEI_H
+
+/* Values for sdei_exit_mode */
+#define SDEI_EXIT_HVC 0
+#define SDEI_EXIT_SMC 1
+
+#define SDEI_STACK_SIZE IRQ_STACK_SIZE
+
+#ifndef __ASSEMBLY__
+
+#include <linux/linkage.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/virt.h>
+
+extern unsigned long sdei_exit_mode;
+
+/* Software Delegated Exception entry point from firmware*/
+asmlinkage void __sdei_asm_handler(unsigned long event_num, unsigned long arg,
+ unsigned long pc, unsigned long pstate);
+
+/* and its CONFIG_UNMAP_KERNEL_AT_EL0 trampoline */
+asmlinkage void __sdei_asm_entry_trampoline(unsigned long event_num,
+ unsigned long arg,
+ unsigned long pc,
+ unsigned long pstate);
+
+/*
+ * The above entry point does the minimum to call C code. This function does
+ * anything else, before calling the driver.
+ */
+struct sdei_registered_event;
+asmlinkage unsigned long __sdei_handler(struct pt_regs *regs,
+ struct sdei_registered_event *arg);
+
+unsigned long sdei_arch_get_entry_point(int conduit);
+#define sdei_arch_get_entry_point(x) sdei_arch_get_entry_point(x)
+
+bool _on_sdei_stack(unsigned long sp);
+static inline bool on_sdei_stack(unsigned long sp)
+{
+ if (!IS_ENABLED(CONFIG_VMAP_STACK))
+ return false;
+ if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
+ return false;
+ if (in_nmi())
+ return _on_sdei_stack(sp);
+
+ return false;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_SDEI_H */
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 941267caa39c..caab039d6305 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -28,5 +28,6 @@ extern char __initdata_begin[], __initdata_end[];
extern char __inittext_begin[], __inittext_end[];
extern char __irqentry_text_start[], __irqentry_text_end[];
extern char __mmuoff_data_start[], __mmuoff_data_end[];
+extern char __entry_tramp_text_start[], __entry_tramp_text_end[];
#endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
index 74a9d301819f..b299929fe56c 100644
--- a/arch/arm64/include/asm/sparsemem.h
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -17,7 +17,7 @@
#define __ASM_SPARSEMEM_H
#ifdef CONFIG_SPARSEMEM
-#define MAX_PHYSMEM_BITS 48
+#define MAX_PHYSMEM_BITS CONFIG_ARM64_PA_BITS
#define SECTION_SIZE_BITS 30
#endif
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 6ad30776e984..472ef944e932 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -22,6 +22,7 @@
#include <asm/memory.h>
#include <asm/ptrace.h>
+#include <asm/sdei.h>
struct stackframe {
unsigned long fp;
@@ -85,6 +86,8 @@ static inline bool on_accessible_stack(struct task_struct *tsk, unsigned long sp
return true;
if (on_overflow_stack(sp))
return true;
+ if (on_sdei_stack(sp))
+ return true;
return false;
}
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 08cc88574659..0e1960c59197 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -20,6 +20,7 @@
#ifndef __ASM_SYSREG_H
#define __ASM_SYSREG_H
+#include <asm/compiler.h>
#include <linux/stringify.h>
/*
@@ -175,6 +176,16 @@
#define SYS_AFSR0_EL1 sys_reg(3, 0, 5, 1, 0)
#define SYS_AFSR1_EL1 sys_reg(3, 0, 5, 1, 1)
#define SYS_ESR_EL1 sys_reg(3, 0, 5, 2, 0)
+
+#define SYS_ERRIDR_EL1 sys_reg(3, 0, 5, 3, 0)
+#define SYS_ERRSELR_EL1 sys_reg(3, 0, 5, 3, 1)
+#define SYS_ERXFR_EL1 sys_reg(3, 0, 5, 4, 0)
+#define SYS_ERXCTLR_EL1 sys_reg(3, 0, 5, 4, 1)
+#define SYS_ERXSTATUS_EL1 sys_reg(3, 0, 5, 4, 2)
+#define SYS_ERXADDR_EL1 sys_reg(3, 0, 5, 4, 3)
+#define SYS_ERXMISC0_EL1 sys_reg(3, 0, 5, 5, 0)
+#define SYS_ERXMISC1_EL1 sys_reg(3, 0, 5, 5, 1)
+
#define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0)
#define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0)
@@ -278,6 +289,7 @@
#define SYS_AMAIR_EL1 sys_reg(3, 0, 10, 3, 0)
#define SYS_VBAR_EL1 sys_reg(3, 0, 12, 0, 0)
+#define SYS_DISR_EL1 sys_reg(3, 0, 12, 1, 1)
#define SYS_ICC_IAR0_EL1 sys_reg(3, 0, 12, 8, 0)
#define SYS_ICC_EOIR0_EL1 sys_reg(3, 0, 12, 8, 1)
@@ -353,8 +365,10 @@
#define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0)
#define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1)
+#define SYS_VSESR_EL2 sys_reg(3, 4, 5, 2, 3)
#define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0)
+#define SYS_VDISR_EL2 sys_reg(3, 4, 12, 1, 1)
#define __SYS__AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x)
#define SYS_ICH_AP0R0_EL2 __SYS__AP0Rx_EL2(0)
#define SYS_ICH_AP0R1_EL2 __SYS__AP0Rx_EL2(1)
@@ -398,27 +412,85 @@
/* Common SCTLR_ELx flags. */
#define SCTLR_ELx_EE (1 << 25)
+#define SCTLR_ELx_IESB (1 << 21)
+#define SCTLR_ELx_WXN (1 << 19)
#define SCTLR_ELx_I (1 << 12)
#define SCTLR_ELx_SA (1 << 3)
#define SCTLR_ELx_C (1 << 2)
#define SCTLR_ELx_A (1 << 1)
#define SCTLR_ELx_M 1
+#define SCTLR_ELx_FLAGS (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
+ SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB)
+
+/* SCTLR_EL2 specific flags. */
#define SCTLR_EL2_RES1 ((1 << 4) | (1 << 5) | (1 << 11) | (1 << 16) | \
(1 << 18) | (1 << 22) | (1 << 23) | (1 << 28) | \
(1 << 29))
+#define SCTLR_EL2_RES0 ((1 << 6) | (1 << 7) | (1 << 8) | (1 << 9) | \
+ (1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \
+ (1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \
+ (1 << 27) | (1 << 30) | (1 << 31))
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ENDIAN_SET_EL2 SCTLR_ELx_EE
+#define ENDIAN_CLEAR_EL2 0
+#else
+#define ENDIAN_SET_EL2 0
+#define ENDIAN_CLEAR_EL2 SCTLR_ELx_EE
+#endif
+
+/* SCTLR_EL2 value used for the hyp-stub */
+#define SCTLR_EL2_SET (SCTLR_ELx_IESB | ENDIAN_SET_EL2 | SCTLR_EL2_RES1)
+#define SCTLR_EL2_CLEAR (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
+ SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_WXN | \
+ ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
+
+/* Check all the bits are accounted for */
+#define SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS BUILD_BUG_ON((SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != ~0)
-#define SCTLR_ELx_FLAGS (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
- SCTLR_ELx_SA | SCTLR_ELx_I)
/* SCTLR_EL1 specific flags. */
#define SCTLR_EL1_UCI (1 << 26)
+#define SCTLR_EL1_E0E (1 << 24)
#define SCTLR_EL1_SPAN (1 << 23)
+#define SCTLR_EL1_NTWE (1 << 18)
+#define SCTLR_EL1_NTWI (1 << 16)
#define SCTLR_EL1_UCT (1 << 15)
+#define SCTLR_EL1_DZE (1 << 14)
+#define SCTLR_EL1_UMA (1 << 9)
#define SCTLR_EL1_SED (1 << 8)
+#define SCTLR_EL1_ITD (1 << 7)
#define SCTLR_EL1_CP15BEN (1 << 5)
+#define SCTLR_EL1_SA0 (1 << 4)
+
+#define SCTLR_EL1_RES1 ((1 << 11) | (1 << 20) | (1 << 22) | (1 << 28) | \
+ (1 << 29))
+#define SCTLR_EL1_RES0 ((1 << 6) | (1 << 10) | (1 << 13) | (1 << 17) | \
+ (1 << 27) | (1 << 30) | (1 << 31))
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ENDIAN_SET_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE)
+#define ENDIAN_CLEAR_EL1 0
+#else
+#define ENDIAN_SET_EL1 0
+#define ENDIAN_CLEAR_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE)
+#endif
+
+#define SCTLR_EL1_SET (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA |\
+ SCTLR_EL1_SA0 | SCTLR_EL1_SED | SCTLR_ELx_I |\
+ SCTLR_EL1_DZE | SCTLR_EL1_UCT | SCTLR_EL1_NTWI |\
+ SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\
+ ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_RES1)
+#define SCTLR_EL1_CLEAR (SCTLR_ELx_A | SCTLR_EL1_CP15BEN | SCTLR_EL1_ITD |\
+ SCTLR_EL1_UMA | SCTLR_ELx_WXN | ENDIAN_CLEAR_EL1 |\
+ SCTLR_EL1_RES0)
+
+/* Check all the bits are accounted for */
+#define SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS BUILD_BUG_ON((SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != ~0)
/* id_aa64isar0 */
+#define ID_AA64ISAR0_FHM_SHIFT 48
#define ID_AA64ISAR0_DP_SHIFT 44
#define ID_AA64ISAR0_SM4_SHIFT 40
#define ID_AA64ISAR0_SM3_SHIFT 36
@@ -437,7 +509,10 @@
#define ID_AA64ISAR1_DPB_SHIFT 0
/* id_aa64pfr0 */
+#define ID_AA64PFR0_CSV3_SHIFT 60
+#define ID_AA64PFR0_CSV2_SHIFT 56
#define ID_AA64PFR0_SVE_SHIFT 32
+#define ID_AA64PFR0_RAS_SHIFT 28
#define ID_AA64PFR0_GIC_SHIFT 24
#define ID_AA64PFR0_ASIMD_SHIFT 20
#define ID_AA64PFR0_FP_SHIFT 16
@@ -447,6 +522,7 @@
#define ID_AA64PFR0_EL0_SHIFT 0
#define ID_AA64PFR0_SVE 0x1
+#define ID_AA64PFR0_RAS_V1 0x1
#define ID_AA64PFR0_FP_NI 0xf
#define ID_AA64PFR0_FP_SUPPORTED 0x0
#define ID_AA64PFR0_ASIMD_NI 0xf
@@ -471,6 +547,14 @@
#define ID_AA64MMFR0_TGRAN64_SUPPORTED 0x0
#define ID_AA64MMFR0_TGRAN16_NI 0x0
#define ID_AA64MMFR0_TGRAN16_SUPPORTED 0x1
+#define ID_AA64MMFR0_PARANGE_48 0x5
+#define ID_AA64MMFR0_PARANGE_52 0x6
+
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define ID_AA64MMFR0_PARANGE_MAX ID_AA64MMFR0_PARANGE_52
+#else
+#define ID_AA64MMFR0_PARANGE_MAX ID_AA64MMFR0_PARANGE_48
+#endif
/* id_aa64mmfr1 */
#define ID_AA64MMFR1_PAN_SHIFT 20
@@ -582,6 +666,7 @@
#else
+#include <linux/build_bug.h>
#include <linux/types.h>
asm(
@@ -638,6 +723,9 @@ static inline void config_sctlr_el1(u32 clear, u32 set)
{
u32 val;
+ SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS;
+ SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS;
+
val = read_sysreg(sctlr_el1);
val &= ~clear;
val |= set;
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index eb431286bacd..740aa03c5f0d 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -51,8 +51,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_stack (init_thread_union.stack)
-
#define thread_saved_pc(tsk) \
((unsigned long)(tsk->thread.cpu_context.pc))
#define thread_saved_sp(tsk) \
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index af1c76981911..9e82dd79c7db 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -23,6 +23,7 @@
#include <linux/sched.h>
#include <asm/cputype.h>
+#include <asm/mmu.h>
/*
* Raw TLBI operations.
@@ -54,6 +55,11 @@
#define __tlbi(op, ...) __TLBI_N(op, ##__VA_ARGS__, 1, 0)
+#define __tlbi_user(op, arg) do { \
+ if (arm64_kernel_unmapped_at_el0()) \
+ __tlbi(op, (arg) | USER_ASID_FLAG); \
+} while (0)
+
/*
* TLB Management
* ==============
@@ -115,6 +121,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
dsb(ishst);
__tlbi(aside1is, asid);
+ __tlbi_user(aside1is, asid);
dsb(ish);
}
@@ -125,6 +132,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
dsb(ishst);
__tlbi(vale1is, addr);
+ __tlbi_user(vale1is, addr);
dsb(ish);
}
@@ -151,10 +159,13 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
dsb(ishst);
for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
- if (last_level)
+ if (last_level) {
__tlbi(vale1is, addr);
- else
+ __tlbi_user(vale1is, addr);
+ } else {
__tlbi(vae1is, addr);
+ __tlbi_user(vae1is, addr);
+ }
}
dsb(ish);
}
@@ -194,6 +205,7 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
__tlbi(vae1is, addr);
+ __tlbi_user(vae1is, addr);
dsb(ish);
}
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 1696f9de9359..178e338d2889 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -19,6 +19,7 @@
#define __ASM_TRAP_H
#include <linux/list.h>
+#include <asm/esr.h>
#include <asm/sections.h>
struct pt_regs;
@@ -66,4 +67,57 @@ static inline int in_entry_text(unsigned long ptr)
return ptr >= (unsigned long)&__entry_text_start &&
ptr < (unsigned long)&__entry_text_end;
}
+
+/*
+ * CPUs with the RAS extensions have an Implementation-Defined-Syndrome bit
+ * to indicate whether this ESR has a RAS encoding. CPUs without this feature
+ * have a ISS-Valid bit in the same position.
+ * If this bit is set, we know its not a RAS SError.
+ * If its clear, we need to know if the CPU supports RAS. Uncategorized RAS
+ * errors share the same encoding as an all-zeros encoding from a CPU that
+ * doesn't support RAS.
+ */
+static inline bool arm64_is_ras_serror(u32 esr)
+{
+ WARN_ON(preemptible());
+
+ if (esr & ESR_ELx_IDS)
+ return false;
+
+ if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN))
+ return true;
+ else
+ return false;
+}
+
+/*
+ * Return the AET bits from a RAS SError's ESR.
+ *
+ * It is implementation defined whether Uncategorized errors are containable.
+ * We treat them as Uncontainable.
+ * Non-RAS SError's are reported as Uncontained/Uncategorized.
+ */
+static inline u32 arm64_ras_serror_get_severity(u32 esr)
+{
+ u32 aet = esr & ESR_ELx_AET;
+
+ if (!arm64_is_ras_serror(esr)) {
+ /* Not a RAS error, we can't interpret the ESR. */
+ return ESR_ELx_AET_UC;
+ }
+
+ /*
+ * AET is RES0 if 'the value returned in the DFSC field is not
+ * [ESR_ELx_FSC_SERROR]'
+ */
+ if ((esr & ESR_ELx_FSC) != ESR_ELx_FSC_SERROR) {
+ /* No severity information : Uncategorized */
+ return ESR_ELx_AET_UC;
+ }
+
+ return aet;
+}
+
+bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr);
+void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr);
#endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index fc0f9eb66039..59fda5292936 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -105,17 +105,23 @@ static inline void set_fs(mm_segment_t fs)
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
static inline void __uaccess_ttbr0_disable(void)
{
- unsigned long ttbr;
+ unsigned long flags, ttbr;
- /* reserved_ttbr0 placed at the end of swapper_pg_dir */
- ttbr = read_sysreg(ttbr1_el1) + SWAPPER_DIR_SIZE;
- write_sysreg(ttbr, ttbr0_el1);
+ local_irq_save(flags);
+ ttbr = read_sysreg(ttbr1_el1);
+ ttbr &= ~TTBR_ASID_MASK;
+ /* reserved_ttbr0 placed before swapper_pg_dir */
+ write_sysreg(ttbr - RESERVED_TTBR0_SIZE, ttbr0_el1);
+ isb();
+ /* Set reserved ASID */
+ write_sysreg(ttbr, ttbr1_el1);
isb();
+ local_irq_restore(flags);
}
static inline void __uaccess_ttbr0_enable(void)
{
- unsigned long flags;
+ unsigned long flags, ttbr0, ttbr1;
/*
* Disable interrupts to avoid preemption between reading the 'ttbr0'
@@ -123,7 +129,17 @@ static inline void __uaccess_ttbr0_enable(void)
* roll-over and an update of 'ttbr0'.
*/
local_irq_save(flags);
- write_sysreg(current_thread_info()->ttbr0, ttbr0_el1);
+ ttbr0 = READ_ONCE(current_thread_info()->ttbr0);
+
+ /* Restore active ASID */
+ ttbr1 = read_sysreg(ttbr1_el1);
+ ttbr1 &= ~TTBR_ASID_MASK; /* safety measure */
+ ttbr1 |= ttbr0 & TTBR_ASID_MASK;
+ write_sysreg(ttbr1, ttbr1_el1);
+ isb();
+
+ /* Restore user page table */
+ write_sysreg(ttbr0, ttbr0_el1);
isb();
local_irq_restore(flags);
}
@@ -155,6 +171,18 @@ static inline bool uaccess_ttbr0_enable(void)
}
#endif
+static inline void __uaccess_disable_hw_pan(void)
+{
+ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,
+ CONFIG_ARM64_PAN));
+}
+
+static inline void __uaccess_enable_hw_pan(void)
+{
+ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+ CONFIG_ARM64_PAN));
+}
+
#define __uaccess_disable(alt) \
do { \
if (!uaccess_ttbr0_disable()) \
diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h
new file mode 100644
index 000000000000..0b5ec6e08c10
--- /dev/null
+++ b/arch/arm64/include/asm/vmap_stack.h
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#ifndef __ASM_VMAP_STACK_H
+#define __ASM_VMAP_STACK_H
+
+#include <linux/bug.h>
+#include <linux/gfp.h>
+#include <linux/kconfig.h>
+#include <linux/vmalloc.h>
+#include <asm/memory.h>
+#include <asm/pgtable.h>
+#include <asm/thread_info.h>
+
+/*
+ * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd
+ * stacks need to have the same alignment.
+ */
+static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
+{
+ BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
+
+ return __vmalloc_node_range(stack_size, THREAD_ALIGN,
+ VMALLOC_START, VMALLOC_END,
+ THREADINFO_GFP, PAGE_KERNEL, 0, node,
+ __builtin_return_address(0));
+}
+
+#endif /* __ASM_VMAP_STACK_H */
diff --git a/arch/arm64/include/uapi/asm/bpf_perf_event.h b/arch/arm64/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..b551b741653d
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index cda76fa8b9b2..f018c3deea3b 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -43,5 +43,6 @@
#define HWCAP_ASIMDDP (1 << 20)
#define HWCAP_SHA512 (1 << 21)
#define HWCAP_SVE (1 << 22)
+#define HWCAP_ASIMDFHM (1 << 23)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/siginfo.h b/arch/arm64/include/uapi/asm/siginfo.h
index 574d12f86039..9b4d91277742 100644
--- a/arch/arm64/include/uapi/asm/siginfo.h
+++ b/arch/arm64/include/uapi/asm/siginfo.h
@@ -21,4 +21,25 @@
#include <asm-generic/siginfo.h>
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME 0 /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
+/*
+ * SIGBUS si_codes
+ */
+#ifdef __KERNEL__
+#define BUS_FIXME 0 /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
+/*
+ * SIGTRAP si_codes
+ */
+#ifdef __KERNEL__
+#define TRAP_FIXME 0 /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
#endif
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 8265dd790895..b87541360f43 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -52,6 +52,11 @@ arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \
arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o
arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o
+
+ifeq ($(CONFIG_KVM),y)
+arm64-obj-$(CONFIG_HARDEN_BRANCH_PREDICTOR) += bpi.o
+endif
obj-y += $(arm64-obj-y) vdso/ probes/
obj-m += $(arm64-obj-m)
@@ -61,6 +66,3 @@ extra-y += $(head-y) vmlinux.lds
ifeq ($(CONFIG_DEBUG_EFI),y)
AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\""
endif
-
-# will be included by each individual module but not by the core kernel itself
-extra-$(CONFIG_DYNAMIC_FTRACE) += ftrace-mod.o
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index b3162715ed78..252396a96c78 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -117,7 +117,7 @@ bool __init acpi_psci_present(void)
}
/* Whether HVC must be used instead of SMC as the PSCI conduit */
-bool __init acpi_psci_use_hvc(void)
+bool acpi_psci_use_hvc(void)
{
return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
}
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 6dd0a3a3e5c9..414288a558c8 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -32,6 +32,8 @@
#define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset)
#define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset)
+int alternatives_applied;
+
struct alt_region {
struct alt_instr *begin;
struct alt_instr *end;
@@ -143,7 +145,6 @@ static void __apply_alternatives(void *alt_region, bool use_linear_alias)
*/
static int __apply_alternatives_multi_stop(void *unused)
{
- static int patched = 0;
struct alt_region region = {
.begin = (struct alt_instr *)__alt_instructions,
.end = (struct alt_instr *)__alt_instructions_end,
@@ -151,14 +152,14 @@ static int __apply_alternatives_multi_stop(void *unused)
/* We always have a CPU 0 at this point (__init) */
if (smp_processor_id()) {
- while (!READ_ONCE(patched))
+ while (!READ_ONCE(alternatives_applied))
cpu_relax();
isb();
} else {
- BUG_ON(patched);
+ BUG_ON(alternatives_applied);
__apply_alternatives(&region, true);
/* Barriers provided by the cache flushing */
- WRITE_ONCE(patched, 1);
+ WRITE_ONCE(alternatives_applied, 1);
}
return 0;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 71bf088f1e4b..1303e04110cd 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -18,12 +18,14 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/arm_sdei.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/dma-mapping.h>
#include <linux/kvm_host.h>
#include <linux/suspend.h>
#include <asm/cpufeature.h>
+#include <asm/fixmap.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
#include <asm/smp_plat.h>
@@ -130,6 +132,7 @@ int main(void)
BLANK();
#ifdef CONFIG_KVM_ARM_HOST
DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt));
+ DEFINE(VCPU_FAULT_DISR, offsetof(struct kvm_vcpu, arch.fault.disr_el1));
DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs));
DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs));
DEFINE(CPU_FP_REGS, offsetof(struct kvm_regs, fp_regs));
@@ -148,11 +151,18 @@ int main(void)
DEFINE(ARM_SMCCC_RES_X2_OFFS, offsetof(struct arm_smccc_res, a2));
DEFINE(ARM_SMCCC_QUIRK_ID_OFFS, offsetof(struct arm_smccc_quirk, id));
DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS, offsetof(struct arm_smccc_quirk, state));
-
BLANK();
DEFINE(HIBERN_PBE_ORIG, offsetof(struct pbe, orig_address));
DEFINE(HIBERN_PBE_ADDR, offsetof(struct pbe, address));
DEFINE(HIBERN_PBE_NEXT, offsetof(struct pbe, next));
DEFINE(ARM64_FTR_SYSVAL, offsetof(struct arm64_ftr_reg, sys_val));
+ BLANK();
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ DEFINE(TRAMP_VALIAS, TRAMP_VALIAS);
+#endif
+#ifdef CONFIG_ARM_SDE_INTERFACE
+ DEFINE(SDEI_EVENT_INTREGS, offsetof(struct sdei_registered_event, interrupted_regs));
+ DEFINE(SDEI_EVENT_PRIORITY, offsetof(struct sdei_registered_event, priority));
+#endif
return 0;
}
diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S
new file mode 100644
index 000000000000..76225c2611ea
--- /dev/null
+++ b/arch/arm64/kernel/bpi.S
@@ -0,0 +1,87 @@
+/*
+ * Contains CPU specific branch predictor invalidation sequences
+ *
+ * Copyright (C) 2018 ARM Ltd.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+.macro ventry target
+ .rept 31
+ nop
+ .endr
+ b \target
+.endm
+
+.macro vectors target
+ ventry \target + 0x000
+ ventry \target + 0x080
+ ventry \target + 0x100
+ ventry \target + 0x180
+
+ ventry \target + 0x200
+ ventry \target + 0x280
+ ventry \target + 0x300
+ ventry \target + 0x380
+
+ ventry \target + 0x400
+ ventry \target + 0x480
+ ventry \target + 0x500
+ ventry \target + 0x580
+
+ ventry \target + 0x600
+ ventry \target + 0x680
+ ventry \target + 0x700
+ ventry \target + 0x780
+.endm
+
+ .align 11
+ENTRY(__bp_harden_hyp_vecs_start)
+ .rept 4
+ vectors __kvm_hyp_vector
+ .endr
+ENTRY(__bp_harden_hyp_vecs_end)
+ENTRY(__psci_hyp_bp_inval_start)
+ sub sp, sp, #(8 * 18)
+ stp x16, x17, [sp, #(16 * 0)]
+ stp x14, x15, [sp, #(16 * 1)]
+ stp x12, x13, [sp, #(16 * 2)]
+ stp x10, x11, [sp, #(16 * 3)]
+ stp x8, x9, [sp, #(16 * 4)]
+ stp x6, x7, [sp, #(16 * 5)]
+ stp x4, x5, [sp, #(16 * 6)]
+ stp x2, x3, [sp, #(16 * 7)]
+ stp x0, x1, [sp, #(16 * 8)]
+ mov x0, #0x84000000
+ smc #0
+ ldp x16, x17, [sp, #(16 * 0)]
+ ldp x14, x15, [sp, #(16 * 1)]
+ ldp x12, x13, [sp, #(16 * 2)]
+ ldp x10, x11, [sp, #(16 * 3)]
+ ldp x8, x9, [sp, #(16 * 4)]
+ ldp x6, x7, [sp, #(16 * 5)]
+ ldp x4, x5, [sp, #(16 * 6)]
+ ldp x2, x3, [sp, #(16 * 7)]
+ ldp x0, x1, [sp, #(16 * 8)]
+ add sp, sp, #(8 * 18)
+ENTRY(__psci_hyp_bp_inval_end)
+
+ENTRY(__qcom_hyp_sanitize_link_stack_start)
+ stp x29, x30, [sp, #-16]!
+ .rept 16
+ bl . + 4
+ .endr
+ ldp x29, x30, [sp], #16
+ENTRY(__qcom_hyp_sanitize_link_stack_end)
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 65f42d257414..2a752cb2a0f3 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -37,6 +37,7 @@ ENTRY(__cpu_soft_restart)
mrs x12, sctlr_el1
ldr x13, =SCTLR_ELx_FLAGS
bic x12, x12, x13
+ pre_disable_mmu_workaround
msr sctlr_el1, x12
isb
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0e27f86ee709..ed6881882231 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -30,6 +30,20 @@ is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
entry->midr_range_max);
}
+static bool __maybe_unused
+is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope)
+{
+ u32 model;
+
+ WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+ model = read_cpuid_id();
+ model &= MIDR_IMPLEMENTOR_MASK | (0xf00 << MIDR_PARTNUM_SHIFT) |
+ MIDR_ARCHITECTURE_MASK;
+
+ return model == entry->midr_model;
+}
+
static bool
has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
int scope)
@@ -46,6 +60,127 @@ static int cpu_enable_trap_ctr_access(void *__unused)
return 0;
}
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#include <asm/mmu_context.h>
+#include <asm/cacheflush.h>
+
+DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+#ifdef CONFIG_KVM
+extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[];
+extern char __qcom_hyp_sanitize_link_stack_start[];
+extern char __qcom_hyp_sanitize_link_stack_end[];
+
+static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
+ const char *hyp_vecs_end)
+{
+ void *dst = lm_alias(__bp_harden_hyp_vecs_start + slot * SZ_2K);
+ int i;
+
+ for (i = 0; i < SZ_2K; i += 0x80)
+ memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start);
+
+ flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
+}
+
+static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+ const char *hyp_vecs_start,
+ const char *hyp_vecs_end)
+{
+ static int last_slot = -1;
+ static DEFINE_SPINLOCK(bp_lock);
+ int cpu, slot = -1;
+
+ spin_lock(&bp_lock);
+ for_each_possible_cpu(cpu) {
+ if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
+ slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
+ break;
+ }
+ }
+
+ if (slot == -1) {
+ last_slot++;
+ BUG_ON(((__bp_harden_hyp_vecs_end - __bp_harden_hyp_vecs_start)
+ / SZ_2K) <= last_slot);
+ slot = last_slot;
+ __copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
+ }
+
+ __this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
+ __this_cpu_write(bp_hardening_data.fn, fn);
+ spin_unlock(&bp_lock);
+}
+#else
+#define __psci_hyp_bp_inval_start NULL
+#define __psci_hyp_bp_inval_end NULL
+#define __qcom_hyp_sanitize_link_stack_start NULL
+#define __qcom_hyp_sanitize_link_stack_end NULL
+
+static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+ const char *hyp_vecs_start,
+ const char *hyp_vecs_end)
+{
+ __this_cpu_write(bp_hardening_data.fn, fn);
+}
+#endif /* CONFIG_KVM */
+
+static void install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
+ bp_hardening_cb_t fn,
+ const char *hyp_vecs_start,
+ const char *hyp_vecs_end)
+{
+ u64 pfr0;
+
+ if (!entry->matches(entry, SCOPE_LOCAL_CPU))
+ return;
+
+ pfr0 = read_cpuid(ID_AA64PFR0_EL1);
+ if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
+ return;
+
+ __install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
+}
+
+#include <linux/psci.h>
+
+static int enable_psci_bp_hardening(void *data)
+{
+ const struct arm64_cpu_capabilities *entry = data;
+
+ if (psci_ops.get_version)
+ install_bp_hardening_cb(entry,
+ (bp_hardening_cb_t)psci_ops.get_version,
+ __psci_hyp_bp_inval_start,
+ __psci_hyp_bp_inval_end);
+
+ return 0;
+}
+
+static void qcom_link_stack_sanitization(void)
+{
+ u64 tmp;
+
+ asm volatile("mov %0, x30 \n"
+ ".rept 16 \n"
+ "bl . + 4 \n"
+ ".endr \n"
+ "mov x30, %0 \n"
+ : "=&r" (tmp));
+}
+
+static int qcom_enable_link_stack_sanitization(void *data)
+{
+ const struct arm64_cpu_capabilities *entry = data;
+
+ install_bp_hardening_cb(entry, qcom_link_stack_sanitization,
+ __qcom_hyp_sanitize_link_stack_start,
+ __qcom_hyp_sanitize_link_stack_end);
+
+ return 0;
+}
+#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR */
+
#define MIDR_RANGE(model, min, max) \
.def_scope = SCOPE_LOCAL_CPU, \
.matches = is_affected_midr_range, \
@@ -169,6 +304,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
MIDR_CPU_VAR_REV(0, 0),
MIDR_CPU_VAR_REV(0, 0)),
},
+ {
+ .desc = "Qualcomm Technologies Kryo erratum 1003",
+ .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
+ .def_scope = SCOPE_LOCAL_CPU,
+ .midr_model = MIDR_QCOM_KRYO,
+ .matches = is_kryo_midr,
+ },
#endif
#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
{
@@ -187,6 +329,47 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
},
#endif
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+ {
+ .capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+ .enable = enable_psci_bp_hardening,
+ },
+ {
+ .capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+ .enable = enable_psci_bp_hardening,
+ },
+ {
+ .capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
+ .enable = enable_psci_bp_hardening,
+ },
+ {
+ .capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
+ .enable = enable_psci_bp_hardening,
+ },
+ {
+ .capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+ MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
+ .enable = qcom_enable_link_stack_sanitization,
+ },
+ {
+ .capability = ARM64_HARDEN_BP_POST_GUEST_EXIT,
+ MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
+ },
+ {
+ .capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+ MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+ .enable = enable_psci_bp_hardening,
+ },
+ {
+ .capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+ MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
+ .enable = enable_psci_bp_hardening,
+ },
+#endif
{
}
};
@@ -200,15 +383,18 @@ void verify_local_cpu_errata_workarounds(void)
{
const struct arm64_cpu_capabilities *caps = arm64_errata;
- for (; caps->matches; caps++)
- if (!cpus_have_cap(caps->capability) &&
- caps->matches(caps, SCOPE_LOCAL_CPU)) {
+ for (; caps->matches; caps++) {
+ if (cpus_have_cap(caps->capability)) {
+ if (caps->enable)
+ caps->enable((void *)caps);
+ } else if (caps->matches(caps, SCOPE_LOCAL_CPU)) {
pr_crit("CPU%d: Requires work around for %s, not detected"
" at boot time\n",
smp_processor_id(),
caps->desc ? : "an erratum");
cpu_die_early();
}
+ }
}
void update_cpu_errata_workarounds(void)
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index d16978213c5b..ea001241bdd4 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -31,13 +31,13 @@ extern const struct cpu_operations cpu_psci_ops;
const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
-static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = {
&smp_spin_table_ops,
&cpu_psci_ops,
NULL,
};
-static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const acpi_supported_cpu_ops[] __initconst = {
#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
&acpi_parking_protocol_ops,
#endif
@@ -47,7 +47,7 @@ static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
static const struct cpu_operations * __init cpu_get_ops(const char *name)
{
- const struct cpu_operations **ops;
+ const struct cpu_operations *const *ops;
ops = acpi_disabled ? dt_supported_cpu_ops : acpi_supported_cpu_ops;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c5ba0097887f..0fb6a3151443 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -123,6 +123,7 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
* sync with the documentation of the CPU feature register ABI.
*/
static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM4_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM3_SHIFT, 4, 0),
@@ -145,7 +146,11 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+ FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
@@ -845,6 +850,67 @@ static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unus
ID_AA64PFR0_FP_SHIFT) < 0;
}
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
+
+static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
+ int __unused)
+{
+ u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+ /* Forced on command line? */
+ if (__kpti_forced) {
+ pr_info_once("kernel page table isolation forced %s by command line option\n",
+ __kpti_forced > 0 ? "ON" : "OFF");
+ return __kpti_forced > 0;
+ }
+
+ /* Useful for KASLR robustness */
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+ return true;
+
+ /* Don't force KPTI for CPUs that are not vulnerable */
+ switch (read_cpuid_id() & MIDR_CPU_MODEL_MASK) {
+ case MIDR_CAVIUM_THUNDERX2:
+ case MIDR_BRCM_VULCAN:
+ return false;
+ }
+
+ /* Defer to CPU feature registers */
+ return !cpuid_feature_extract_unsigned_field(pfr0,
+ ID_AA64PFR0_CSV3_SHIFT);
+}
+
+static int __init parse_kpti(char *str)
+{
+ bool enabled;
+ int ret = strtobool(str, &enabled);
+
+ if (ret)
+ return ret;
+
+ __kpti_forced = enabled ? 1 : -1;
+ return 0;
+}
+__setup("kpti=", parse_kpti);
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
+static int cpu_copy_el2regs(void *__unused)
+{
+ /*
+ * Copy register values that aren't redirected by hardware.
+ *
+ * Before code patching, we only set tpidr_el1, all CPUs need to copy
+ * this value to tpidr_el2 before we patch the code. Once we've done
+ * that, freshly-onlined CPUs will set tpidr_el2, so we don't need to
+ * do anything here.
+ */
+ if (!alternatives_applied)
+ write_sysreg(read_sysreg(tpidr_el1), tpidr_el2);
+
+ return 0;
+}
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
@@ -914,6 +980,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.capability = ARM64_HAS_VIRT_HOST_EXTN,
.def_scope = SCOPE_SYSTEM,
.matches = runs_at_el2,
+ .enable = cpu_copy_el2regs,
},
{
.desc = "32-bit EL0 Support",
@@ -931,6 +998,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.def_scope = SCOPE_SYSTEM,
.matches = hyp_offset_low,
},
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ {
+ .desc = "Kernel page table isolation (KPTI)",
+ .capability = ARM64_UNMAP_KERNEL_AT_EL0,
+ .def_scope = SCOPE_SYSTEM,
+ .matches = unmap_kernel_at_el0,
+ },
+#endif
{
/* FP/SIMD is not implemented */
.capability = ARM64_HAS_NO_FPSIMD,
@@ -962,6 +1037,19 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.enable = sve_kernel_enable,
},
#endif /* CONFIG_ARM64_SVE */
+#ifdef CONFIG_ARM64_RAS_EXTN
+ {
+ .desc = "RAS Extension Support",
+ .capability = ARM64_HAS_RAS_EXTN,
+ .def_scope = SCOPE_SYSTEM,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64PFR0_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64PFR0_RAS_SHIFT,
+ .min_field_value = ID_AA64PFR0_RAS_V1,
+ .enable = cpu_clear_disr,
+ },
+#endif /* CONFIG_ARM64_RAS_EXTN */
{},
};
@@ -991,6 +1079,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
@@ -1070,6 +1159,25 @@ static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
cap_set_elf_hwcap(hwcaps);
}
+/*
+ * Check if the current CPU has a given feature capability.
+ * Should be called from non-preemptible context.
+ */
+static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
+ unsigned int cap)
+{
+ const struct arm64_cpu_capabilities *caps;
+
+ if (WARN_ON(preemptible()))
+ return false;
+
+ for (caps = cap_array; caps->matches; caps++)
+ if (caps->capability == cap &&
+ caps->matches(caps, SCOPE_LOCAL_CPU))
+ return true;
+ return false;
+}
+
void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
const char *info)
{
@@ -1105,7 +1213,7 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
* uses an IPI, giving us a PSTATE that disappears when
* we return.
*/
- stop_machine(caps->enable, NULL, cpu_online_mask);
+ stop_machine(caps->enable, (void *)caps, cpu_online_mask);
}
}
}
@@ -1133,8 +1241,9 @@ verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps)
}
static void
-verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
+verify_local_cpu_features(const struct arm64_cpu_capabilities *caps_list)
{
+ const struct arm64_cpu_capabilities *caps = caps_list;
for (; caps->matches; caps++) {
if (!cpus_have_cap(caps->capability))
continue;
@@ -1142,13 +1251,13 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
* If the new CPU misses an advertised feature, we cannot proceed
* further, park the cpu.
*/
- if (!caps->matches(caps, SCOPE_LOCAL_CPU)) {
+ if (!__this_cpu_has_cap(caps_list, caps->capability)) {
pr_crit("CPU%d: missing feature: %s\n",
smp_processor_id(), caps->desc);
cpu_die_early();
}
if (caps->enable)
- caps->enable(NULL);
+ caps->enable((void *)caps);
}
}
@@ -1188,6 +1297,9 @@ static void verify_local_cpu_capabilities(void)
if (system_supports_sve())
verify_sve_features();
+
+ if (system_uses_ttbr0_pan())
+ pr_info("Emulating Privileged Access Never (PAN) using TTBR0_EL1 switching\n");
}
void check_local_cpu_capabilities(void)
@@ -1224,25 +1336,6 @@ static void __init mark_const_caps_ready(void)
static_branch_enable(&arm64_const_caps_ready);
}
-/*
- * Check if the current CPU has a given feature capability.
- * Should be called from non-preemptible context.
- */
-static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
- unsigned int cap)
-{
- const struct arm64_cpu_capabilities *caps;
-
- if (WARN_ON(preemptible()))
- return false;
-
- for (caps = cap_array; caps->desc; caps++)
- if (caps->capability == cap && caps->matches)
- return caps->matches(caps, SCOPE_LOCAL_CPU);
-
- return false;
-}
-
extern const struct arm64_cpu_capabilities arm64_errata[];
bool this_cpu_has_cap(unsigned int cap)
@@ -1386,3 +1479,11 @@ static int __init enable_mrs_emulation(void)
}
core_initcall(enable_mrs_emulation);
+
+int cpu_clear_disr(void *__unused)
+{
+ /* Firmware may have left a deferred SError in this register. */
+ write_sysreg_s(0, SYS_DISR_EL1);
+
+ return 0;
+}
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index fd691087dc9a..f2d13810daa8 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -47,6 +47,8 @@ int arm_cpuidle_suspend(int index)
#include <acpi/processor.h>
+#define ARM64_LPI_IS_RETENTION_STATE(arch_flags) (!(arch_flags))
+
int acpi_processor_ffh_lpi_probe(unsigned int cpu)
{
return arm_cpuidle_init(cpu);
@@ -54,6 +56,10 @@ int acpi_processor_ffh_lpi_probe(unsigned int cpu)
int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
{
- return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
+ if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
+ return CPU_PM_CPU_IDLE_ENTER_RETENTION(arm_cpuidle_suspend,
+ lpi->index);
+ else
+ return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
}
#endif
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 1e2554543506..7f94623df8a5 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -76,6 +76,7 @@ static const char *const hwcap_str[] = {
"asimddp",
"sha512",
"sve",
+ "asimdfhm",
NULL
};
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index a88b6ccebbb4..53781f5687c5 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -209,12 +209,13 @@ NOKPROBE_SYMBOL(call_step_hook);
static void send_user_sigtrap(int si_code)
{
struct pt_regs *regs = current_pt_regs();
- siginfo_t info = {
- .si_signo = SIGTRAP,
- .si_errno = 0,
- .si_code = si_code,
- .si_addr = (void __user *)instruction_pointer(regs),
- };
+ siginfo_t info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGTRAP;
+ info.si_errno = 0;
+ info.si_code = si_code;
+ info.si_addr = (void __user *)instruction_pointer(regs);
if (WARN_ON(!user_mode(regs)))
return;
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 4e6ad355bd05..6b9736c3fb56 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -96,6 +96,7 @@ ENTRY(entry)
mrs x0, sctlr_el2
bic x0, x0, #1 << 0 // clear SCTLR.M
bic x0, x0, #1 << 2 // clear SCTLR.C
+ pre_disable_mmu_workaround
msr sctlr_el2, x0
isb
b 2f
@@ -103,6 +104,7 @@ ENTRY(entry)
mrs x0, sctlr_el1
bic x0, x0, #1 << 0 // clear SCTLR.M
bic x0, x0, #1 << 2 // clear SCTLR.C
+ pre_disable_mmu_workaround
msr sctlr_el1, x0
isb
2:
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 82cd07592519..f85ac58d08a3 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -48,7 +48,9 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md)
return pgprot_val(PAGE_KERNEL_ROX);
/* RW- */
- if (attr & EFI_MEMORY_XP || type != EFI_RUNTIME_SERVICES_CODE)
+ if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) ==
+ EFI_MEMORY_XP) ||
+ type != EFI_RUNTIME_SERVICES_CODE)
return pgprot_val(PAGE_KERNEL);
/* RWX */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6d14b8f29b5f..b34e717d7597 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -28,6 +28,8 @@
#include <asm/errno.h>
#include <asm/esr.h>
#include <asm/irq.h>
+#include <asm/memory.h>
+#include <asm/mmu.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
@@ -69,8 +71,21 @@
#define BAD_FIQ 2
#define BAD_ERROR 3
- .macro kernel_ventry label
+ .macro kernel_ventry, el, label, regsize = 64
.align 7
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+alternative_if ARM64_UNMAP_KERNEL_AT_EL0
+ .if \el == 0
+ .if \regsize == 64
+ mrs x30, tpidrro_el0
+ msr tpidrro_el0, xzr
+ .else
+ mov x30, xzr
+ .endif
+ .endif
+alternative_else_nop_endif
+#endif
+
sub sp, sp, #S_FRAME_SIZE
#ifdef CONFIG_VMAP_STACK
/*
@@ -82,7 +97,7 @@
tbnz x0, #THREAD_SHIFT, 0f
sub x0, sp, x0 // x0'' = sp' - x0' = (sp + x0) - sp = x0
sub sp, sp, x0 // sp'' = sp' - x0 = (sp + x0) - x0 = sp
- b \label
+ b el\()\el\()_\label
0:
/*
@@ -114,7 +129,12 @@
sub sp, sp, x0
mrs x0, tpidrro_el0
#endif
- b \label
+ b el\()\el\()_\label
+ .endm
+
+ .macro tramp_alias, dst, sym
+ mov_q \dst, TRAMP_VALIAS
+ add \dst, \dst, #(\sym - .entry.tramp.text)
.endm
.macro kernel_entry, el, regsize = 64
@@ -185,7 +205,7 @@ alternative_else_nop_endif
.if \el != 0
mrs x21, ttbr0_el1
- tst x21, #0xffff << 48 // Check for the reserved ASID
+ 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
@@ -248,7 +268,7 @@ alternative_else_nop_endif
tbnz x22, #22, 1f // Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
.endif
- __uaccess_ttbr0_enable x0
+ __uaccess_ttbr0_enable x0, x1
.if \el == 0
/*
@@ -257,7 +277,7 @@ alternative_else_nop_endif
* Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
* corruption).
*/
- post_ttbr0_update_workaround
+ bl post_ttbr_update_workaround
.endif
1:
.if \el != 0
@@ -269,18 +289,20 @@ alternative_else_nop_endif
.if \el == 0
ldr x23, [sp, #S_SP] // load return stack pointer
msr sp_el0, x23
+ tst x22, #PSR_MODE32_BIT // native task?
+ b.eq 3f
+
#ifdef CONFIG_ARM64_ERRATUM_845719
alternative_if ARM64_WORKAROUND_845719
- tbz x22, #4, 1f
#ifdef CONFIG_PID_IN_CONTEXTIDR
mrs x29, contextidr_el1
msr contextidr_el1, x29
#else
msr contextidr_el1, xzr
#endif
-1:
alternative_else_nop_endif
#endif
+3:
.endif
msr elr_el1, x21 // set up the return data
@@ -302,7 +324,21 @@ alternative_else_nop_endif
ldp x28, x29, [sp, #16 * 14]
ldr lr, [sp, #S_LR]
add sp, sp, #S_FRAME_SIZE // restore sp
- eret // return to kernel
+
+ .if \el == 0
+alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ bne 4f
+ msr far_el1, x30
+ tramp_alias x30, tramp_exit_native
+ br x30
+4:
+ tramp_alias x30, tramp_exit_compat
+ br x30
+#endif
+ .else
+ eret
+ .endif
.endm
.macro irq_stack_entry
@@ -367,31 +403,31 @@ tsk .req x28 // current thread_info
.align 11
ENTRY(vectors)
- kernel_ventry el1_sync_invalid // Synchronous EL1t
- kernel_ventry el1_irq_invalid // IRQ EL1t
- kernel_ventry el1_fiq_invalid // FIQ EL1t
- kernel_ventry el1_error_invalid // Error EL1t
+ kernel_ventry 1, sync_invalid // Synchronous EL1t
+ kernel_ventry 1, irq_invalid // IRQ EL1t
+ kernel_ventry 1, fiq_invalid // FIQ EL1t
+ kernel_ventry 1, error_invalid // Error EL1t
- kernel_ventry el1_sync // Synchronous EL1h
- kernel_ventry el1_irq // IRQ EL1h
- kernel_ventry el1_fiq_invalid // FIQ EL1h
- kernel_ventry el1_error // Error EL1h
+ kernel_ventry 1, sync // Synchronous EL1h
+ kernel_ventry 1, irq // IRQ EL1h
+ kernel_ventry 1, fiq_invalid // FIQ EL1h
+ kernel_ventry 1, error // Error EL1h
- kernel_ventry el0_sync // Synchronous 64-bit EL0
- kernel_ventry el0_irq // IRQ 64-bit EL0
- kernel_ventry el0_fiq_invalid // FIQ 64-bit EL0
- kernel_ventry el0_error // Error 64-bit EL0
+ kernel_ventry 0, sync // Synchronous 64-bit EL0
+ kernel_ventry 0, irq // IRQ 64-bit EL0
+ kernel_ventry 0, fiq_invalid // FIQ 64-bit EL0
+ kernel_ventry 0, error // Error 64-bit EL0
#ifdef CONFIG_COMPAT
- kernel_ventry el0_sync_compat // Synchronous 32-bit EL0
- kernel_ventry el0_irq_compat // IRQ 32-bit EL0
- kernel_ventry el0_fiq_invalid_compat // FIQ 32-bit EL0
- kernel_ventry el0_error_compat // Error 32-bit EL0
+ kernel_ventry 0, sync_compat, 32 // Synchronous 32-bit EL0
+ kernel_ventry 0, irq_compat, 32 // IRQ 32-bit EL0
+ kernel_ventry 0, fiq_invalid_compat, 32 // FIQ 32-bit EL0
+ kernel_ventry 0, error_compat, 32 // Error 32-bit EL0
#else
- kernel_ventry el0_sync_invalid // Synchronous 32-bit EL0
- kernel_ventry el0_irq_invalid // IRQ 32-bit EL0
- kernel_ventry el0_fiq_invalid // FIQ 32-bit EL0
- kernel_ventry el0_error_invalid // Error 32-bit EL0
+ kernel_ventry 0, sync_invalid, 32 // Synchronous 32-bit EL0
+ kernel_ventry 0, irq_invalid, 32 // IRQ 32-bit EL0
+ kernel_ventry 0, fiq_invalid, 32 // FIQ 32-bit EL0
+ kernel_ventry 0, error_invalid, 32 // Error 32-bit EL0
#endif
END(vectors)
@@ -685,12 +721,15 @@ el0_ia:
* Instruction abort handling
*/
mrs x26, far_el1
- enable_daif
+ enable_da_f
+#ifdef CONFIG_TRACE_IRQFLAGS
+ bl trace_hardirqs_off
+#endif
ct_user_exit
mov x0, x26
mov x1, x25
mov x2, sp
- bl do_mem_abort
+ bl do_el0_ia_bp_hardening
b ret_to_user
el0_fpsimd_acc:
/*
@@ -943,6 +982,124 @@ __ni_sys_trace:
.popsection // .entry.text
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * Exception vectors trampoline.
+ */
+ .pushsection ".entry.tramp.text", "ax"
+
+ .macro tramp_map_kernel, tmp
+ mrs \tmp, ttbr1_el1
+ add \tmp, \tmp, #(PAGE_SIZE + RESERVED_TTBR0_SIZE)
+ bic \tmp, \tmp, #USER_ASID_FLAG
+ msr ttbr1_el1, \tmp
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
+alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
+ /* ASID already in \tmp[63:48] */
+ movk \tmp, #:abs_g2_nc:(TRAMP_VALIAS >> 12)
+ movk \tmp, #:abs_g1_nc:(TRAMP_VALIAS >> 12)
+ /* 2MB boundary containing the vectors, so we nobble the walk cache */
+ movk \tmp, #:abs_g0_nc:((TRAMP_VALIAS & ~(SZ_2M - 1)) >> 12)
+ isb
+ tlbi vae1, \tmp
+ dsb nsh
+alternative_else_nop_endif
+#endif /* CONFIG_QCOM_FALKOR_ERRATUM_1003 */
+ .endm
+
+ .macro tramp_unmap_kernel, tmp
+ mrs \tmp, ttbr1_el1
+ sub \tmp, \tmp, #(PAGE_SIZE + RESERVED_TTBR0_SIZE)
+ orr \tmp, \tmp, #USER_ASID_FLAG
+ msr ttbr1_el1, \tmp
+ /*
+ * We avoid running the post_ttbr_update_workaround here because the
+ * user and kernel ASIDs don't have conflicting mappings, so any
+ * "blessing" as described in:
+ *
+ * http://lkml.kernel.org/r/56BB848A.6060603@caviumnetworks.com
+ *
+ * will not hurt correctness. Whilst this may partially defeat the
+ * point of using split ASIDs in the first place, it avoids
+ * the hit of invalidating the entire I-cache on every return to
+ * userspace.
+ */
+ .endm
+
+ .macro tramp_ventry, regsize = 64
+ .align 7
+1:
+ .if \regsize == 64
+ msr tpidrro_el0, x30 // Restored in kernel_ventry
+ .endif
+ /*
+ * Defend against branch aliasing attacks by pushing a dummy
+ * entry onto the return stack and using a RET instruction to
+ * enter the full-fat kernel vectors.
+ */
+ bl 2f
+ b .
+2:
+ tramp_map_kernel x30
+#ifdef CONFIG_RANDOMIZE_BASE
+ adr x30, tramp_vectors + PAGE_SIZE
+alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
+ ldr x30, [x30]
+#else
+ ldr x30, =vectors
+#endif
+ prfm plil1strm, [x30, #(1b - tramp_vectors)]
+ msr vbar_el1, x30
+ add x30, x30, #(1b - tramp_vectors)
+ isb
+ ret
+ .endm
+
+ .macro tramp_exit, regsize = 64
+ adr x30, tramp_vectors
+ msr vbar_el1, x30
+ tramp_unmap_kernel x30
+ .if \regsize == 64
+ mrs x30, far_el1
+ .endif
+ eret
+ .endm
+
+ .align 11
+ENTRY(tramp_vectors)
+ .space 0x400
+
+ tramp_ventry
+ tramp_ventry
+ tramp_ventry
+ tramp_ventry
+
+ tramp_ventry 32
+ tramp_ventry 32
+ tramp_ventry 32
+ tramp_ventry 32
+END(tramp_vectors)
+
+ENTRY(tramp_exit_native)
+ tramp_exit
+END(tramp_exit_native)
+
+ENTRY(tramp_exit_compat)
+ tramp_exit 32
+END(tramp_exit_compat)
+
+ .ltorg
+ .popsection // .entry.tramp.text
+#ifdef CONFIG_RANDOMIZE_BASE
+ .pushsection ".rodata", "a"
+ .align PAGE_SHIFT
+ .globl __entry_tramp_data_start
+__entry_tramp_data_start:
+ .quad vectors
+ .popsection // .rodata
+#endif /* CONFIG_RANDOMIZE_BASE */
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
/*
* Special system call wrappers.
*/
@@ -996,3 +1153,180 @@ ENTRY(ret_from_fork)
b ret_to_user
ENDPROC(ret_from_fork)
NOKPROBE(ret_from_fork)
+
+#ifdef CONFIG_ARM_SDE_INTERFACE
+
+#include <asm/sdei.h>
+#include <uapi/linux/arm_sdei.h>
+
+.macro sdei_handler_exit exit_mode
+ /* On success, this call never returns... */
+ cmp \exit_mode, #SDEI_EXIT_SMC
+ b.ne 99f
+ smc #0
+ b .
+99: hvc #0
+ b .
+.endm
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * The regular SDEI entry point may have been unmapped along with the rest of
+ * the kernel. This trampoline restores the kernel mapping to make the x1 memory
+ * argument accessible.
+ *
+ * This clobbers x4, __sdei_handler() will restore this from firmware's
+ * copy.
+ */
+.ltorg
+.pushsection ".entry.tramp.text", "ax"
+ENTRY(__sdei_asm_entry_trampoline)
+ mrs x4, ttbr1_el1
+ tbz x4, #USER_ASID_BIT, 1f
+
+ tramp_map_kernel tmp=x4
+ isb
+ mov x4, xzr
+
+ /*
+ * Use reg->interrupted_regs.addr_limit to remember whether to unmap
+ * the kernel on exit.
+ */
+1: str x4, [x1, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
+
+#ifdef CONFIG_RANDOMIZE_BASE
+ adr x4, tramp_vectors + PAGE_SIZE
+ add x4, x4, #:lo12:__sdei_asm_trampoline_next_handler
+ ldr x4, [x4]
+#else
+ ldr x4, =__sdei_asm_handler
+#endif
+ br x4
+ENDPROC(__sdei_asm_entry_trampoline)
+NOKPROBE(__sdei_asm_entry_trampoline)
+
+/*
+ * Make the exit call and restore the original ttbr1_el1
+ *
+ * x0 & x1: setup for the exit API call
+ * x2: exit_mode
+ * x4: struct sdei_registered_event argument from registration time.
+ */
+ENTRY(__sdei_asm_exit_trampoline)
+ ldr x4, [x4, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
+ cbnz x4, 1f
+
+ tramp_unmap_kernel tmp=x4
+
+1: sdei_handler_exit exit_mode=x2
+ENDPROC(__sdei_asm_exit_trampoline)
+NOKPROBE(__sdei_asm_exit_trampoline)
+ .ltorg
+.popsection // .entry.tramp.text
+#ifdef CONFIG_RANDOMIZE_BASE
+.pushsection ".rodata", "a"
+__sdei_asm_trampoline_next_handler:
+ .quad __sdei_asm_handler
+.popsection // .rodata
+#endif /* CONFIG_RANDOMIZE_BASE */
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
+/*
+ * Software Delegated Exception entry point.
+ *
+ * x0: Event number
+ * x1: struct sdei_registered_event argument from registration time.
+ * x2: interrupted PC
+ * x3: interrupted PSTATE
+ * x4: maybe clobbered by the trampoline
+ *
+ * Firmware has preserved x0->x17 for us, we must save/restore the rest to
+ * follow SMC-CC. We save (or retrieve) all the registers as the handler may
+ * want them.
+ */
+ENTRY(__sdei_asm_handler)
+ stp x2, x3, [x1, #SDEI_EVENT_INTREGS + S_PC]
+ stp x4, x5, [x1, #SDEI_EVENT_INTREGS + 16 * 2]
+ stp x6, x7, [x1, #SDEI_EVENT_INTREGS + 16 * 3]
+ stp x8, x9, [x1, #SDEI_EVENT_INTREGS + 16 * 4]
+ stp x10, x11, [x1, #SDEI_EVENT_INTREGS + 16 * 5]
+ stp x12, x13, [x1, #SDEI_EVENT_INTREGS + 16 * 6]
+ stp x14, x15, [x1, #SDEI_EVENT_INTREGS + 16 * 7]
+ stp x16, x17, [x1, #SDEI_EVENT_INTREGS + 16 * 8]
+ stp x18, x19, [x1, #SDEI_EVENT_INTREGS + 16 * 9]
+ stp x20, x21, [x1, #SDEI_EVENT_INTREGS + 16 * 10]
+ stp x22, x23, [x1, #SDEI_EVENT_INTREGS + 16 * 11]
+ stp x24, x25, [x1, #SDEI_EVENT_INTREGS + 16 * 12]
+ stp x26, x27, [x1, #SDEI_EVENT_INTREGS + 16 * 13]
+ stp x28, x29, [x1, #SDEI_EVENT_INTREGS + 16 * 14]
+ mov x4, sp
+ stp lr, x4, [x1, #SDEI_EVENT_INTREGS + S_LR]
+
+ mov x19, x1
+
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * entry.S may have been using sp as a scratch register, find whether
+ * this is a normal or critical event and switch to the appropriate
+ * stack for this CPU.
+ */
+ ldrb w4, [x19, #SDEI_EVENT_PRIORITY]
+ cbnz w4, 1f
+ ldr_this_cpu dst=x5, sym=sdei_stack_normal_ptr, tmp=x6
+ b 2f
+1: ldr_this_cpu dst=x5, sym=sdei_stack_critical_ptr, tmp=x6
+2: mov x6, #SDEI_STACK_SIZE
+ add x5, x5, x6
+ mov sp, x5
+#endif
+
+ /*
+ * We may have interrupted userspace, or a guest, or exit-from or
+ * return-to either of these. We can't trust sp_el0, restore it.
+ */
+ mrs x28, sp_el0
+ ldr_this_cpu dst=x0, sym=__entry_task, tmp=x1
+ msr sp_el0, x0
+
+ /* If we interrupted the kernel point to the previous stack/frame. */
+ and x0, x3, #0xc
+ mrs x1, CurrentEL
+ cmp x0, x1
+ csel x29, x29, xzr, eq // fp, or zero
+ csel x4, x2, xzr, eq // elr, or zero
+
+ stp x29, x4, [sp, #-16]!
+ mov x29, sp
+
+ add x0, x19, #SDEI_EVENT_INTREGS
+ mov x1, x19
+ bl __sdei_handler
+
+ msr sp_el0, x28
+ /* restore regs >x17 that we clobbered */
+ mov x4, x19 // keep x4 for __sdei_asm_exit_trampoline
+ ldp x28, x29, [x4, #SDEI_EVENT_INTREGS + 16 * 14]
+ ldp x18, x19, [x4, #SDEI_EVENT_INTREGS + 16 * 9]
+ ldp lr, x1, [x4, #SDEI_EVENT_INTREGS + S_LR]
+ mov sp, x1
+
+ mov x1, x0 // address to complete_and_resume
+ /* x0 = (x0 <= 1) ? EVENT_COMPLETE:EVENT_COMPLETE_AND_RESUME */
+ cmp x0, #1
+ mov_q x2, SDEI_1_0_FN_SDEI_EVENT_COMPLETE
+ mov_q x3, SDEI_1_0_FN_SDEI_EVENT_COMPLETE_AND_RESUME
+ csel x0, x2, x3, ls
+
+ ldr_l x2, sdei_exit_mode
+
+alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
+ sdei_handler_exit exit_mode=x2
+alternative_else_nop_endif
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline
+ br x5
+#endif
+ENDPROC(__sdei_asm_handler)
+NOKPROBE(__sdei_asm_handler)
+#endif /* CONFIG_ARM_SDE_INTERFACE */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 143b3e72c25e..e7226c4c7493 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -114,7 +114,12 @@
* returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
* whatever is in the FPSIMD registers is not saved to memory, but discarded.
*/
-static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
+struct fpsimd_last_state_struct {
+ struct fpsimd_state *st;
+ bool sve_in_use;
+};
+
+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;
@@ -862,7 +867,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
{
siginfo_t info;
- unsigned int si_code = 0;
+ unsigned int si_code = FPE_FIXME;
if (esr & FPEXC_IOF)
si_code = FPE_FLTINV;
@@ -905,7 +910,7 @@ void fpsimd_thread_switch(struct task_struct *next)
*/
struct fpsimd_state *st = &next->thread.fpsimd_state;
- if (__this_cpu_read(fpsimd_last_state) == st
+ if (__this_cpu_read(fpsimd_last_state.st) == st
&& st->cpu == smp_processor_id())
clear_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
else
@@ -992,6 +997,21 @@ void fpsimd_signal_preserve_current_state(void)
}
/*
+ * Associate current's FPSIMD context with this cpu
+ * Preemption must be disabled when calling this function.
+ */
+static void fpsimd_bind_to_cpu(void)
+{
+ struct fpsimd_last_state_struct *last =
+ this_cpu_ptr(&fpsimd_last_state);
+ struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+ last->st = st;
+ last->sve_in_use = test_thread_flag(TIF_SVE);
+ st->cpu = smp_processor_id();
+}
+
+/*
* Load the userland FPSIMD state of 'current' from memory, but only if the
* FPSIMD state already held in the registers is /not/ the most recent FPSIMD
* state of 'current'
@@ -1004,11 +1024,8 @@ void fpsimd_restore_current_state(void)
local_bh_disable();
if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
- struct fpsimd_state *st = &current->thread.fpsimd_state;
-
task_fpsimd_load();
- __this_cpu_write(fpsimd_last_state, st);
- st->cpu = smp_processor_id();
+ fpsimd_bind_to_cpu();
}
local_bh_enable();
@@ -1019,25 +1036,21 @@ void fpsimd_restore_current_state(void)
* flag that indicates that the FPSIMD register contents are the most recent
* FPSIMD state of 'current'
*/
-void fpsimd_update_current_state(struct fpsimd_state *state)
+void fpsimd_update_current_state(struct user_fpsimd_state const *state)
{
if (!system_supports_fpsimd())
return;
local_bh_disable();
- if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
- current->thread.fpsimd_state = *state;
+ current->thread.fpsimd_state.user_fpsimd = *state;
+ if (system_supports_sve() && test_thread_flag(TIF_SVE))
fpsimd_to_sve(current);
- }
- task_fpsimd_load();
- if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
- struct fpsimd_state *st = &current->thread.fpsimd_state;
+ task_fpsimd_load();
- __this_cpu_write(fpsimd_last_state, st);
- st->cpu = smp_processor_id();
- }
+ if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE))
+ fpsimd_bind_to_cpu();
local_bh_enable();
}
@@ -1052,7 +1065,7 @@ void fpsimd_flush_task_state(struct task_struct *t)
static inline void fpsimd_flush_cpu_state(void)
{
- __this_cpu_write(fpsimd_last_state, NULL);
+ __this_cpu_write(fpsimd_last_state.st, NULL);
}
/*
@@ -1065,14 +1078,10 @@ static inline void fpsimd_flush_cpu_state(void)
#ifdef CONFIG_ARM64_SVE
void sve_flush_cpu_state(void)
{
- struct fpsimd_state *const fpstate = __this_cpu_read(fpsimd_last_state);
- struct task_struct *tsk;
-
- if (!fpstate)
- return;
+ struct fpsimd_last_state_struct const *last =
+ this_cpu_ptr(&fpsimd_last_state);
- tsk = container_of(fpstate, struct task_struct, thread.fpsimd_state);
- if (test_tsk_thread_flag(tsk, TIF_SVE))
+ if (last->st && last->sve_in_use)
fpsimd_flush_cpu_state();
}
#endif /* CONFIG_ARM64_SVE */
@@ -1267,7 +1276,7 @@ static inline void fpsimd_pm_init(void) { }
#ifdef CONFIG_HOTPLUG_CPU
static int fpsimd_cpu_dead(unsigned int cpu)
{
- per_cpu(fpsimd_last_state, cpu) = NULL;
+ per_cpu(fpsimd_last_state.st, cpu) = NULL;
return 0;
}
diff --git a/arch/arm64/kernel/ftrace-mod.S b/arch/arm64/kernel/ftrace-mod.S
deleted file mode 100644
index 00c4025be4ff..000000000000
--- a/arch/arm64/kernel/ftrace-mod.S
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
- *
- * 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.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
- .section ".text.ftrace_trampoline", "ax"
- .align 3
-0: .quad 0
-__ftrace_trampoline:
- ldr x16, 0b
- br x16
-ENDPROC(__ftrace_trampoline)
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index c13b1fca0e5b..50986e388d2b 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -76,7 +76,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
if (offset < -SZ_128M || offset >= SZ_128M) {
#ifdef CONFIG_ARM64_MODULE_PLTS
- unsigned long *trampoline;
+ struct plt_entry trampoline;
struct module *mod;
/*
@@ -104,22 +104,24 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
* is added in the future, but for now, the pr_err() below
* deals with a theoretical issue only.
*/
- trampoline = (unsigned long *)mod->arch.ftrace_trampoline;
- if (trampoline[0] != addr) {
- if (trampoline[0] != 0) {
+ trampoline = get_plt_entry(addr);
+ if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+ &trampoline)) {
+ if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+ &(struct plt_entry){})) {
pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
return -EINVAL;
}
/* point the trampoline to our ftrace entry point */
module_disable_ro(mod);
- trampoline[0] = addr;
+ *mod->arch.ftrace_trampoline = trampoline;
module_enable_ro(mod, true);
/* update trampoline before patching in the branch */
smp_wmb();
}
- addr = (unsigned long)&trampoline[1];
+ addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
#else /* CONFIG_ARM64_MODULE_PLTS */
return -EINVAL;
#endif /* CONFIG_ARM64_MODULE_PLTS */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 67e86a0f57ac..ba3ab04788dc 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -148,6 +148,26 @@ preserve_boot_args:
ENDPROC(preserve_boot_args)
/*
+ * Macro to arrange a physical address in a page table entry, taking care of
+ * 52-bit addresses.
+ *
+ * Preserves: phys
+ * Returns: pte
+ */
+ .macro phys_to_pte, phys, pte
+#ifdef CONFIG_ARM64_PA_BITS_52
+ /*
+ * We assume \phys is 64K aligned and this is guaranteed by only
+ * supporting this configuration with 64K pages.
+ */
+ orr \pte, \phys, \phys, lsr #36
+ and \pte, \pte, #PTE_ADDR_MASK
+#else
+ mov \pte, \phys
+#endif
+ .endm
+
+/*
* Macro to create a table entry to the next page.
*
* tbl: page table address
@@ -156,54 +176,124 @@ ENDPROC(preserve_boot_args)
* ptrs: #imm pointers per table page
*
* Preserves: virt
- * Corrupts: tmp1, tmp2
+ * Corrupts: ptrs, tmp1, tmp2
* Returns: tbl -> next level table page address
*/
.macro create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2
- lsr \tmp1, \virt, #\shift
- and \tmp1, \tmp1, #\ptrs - 1 // table index
- add \tmp2, \tbl, #PAGE_SIZE
+ add \tmp1, \tbl, #PAGE_SIZE
+ phys_to_pte \tmp1, \tmp2
orr \tmp2, \tmp2, #PMD_TYPE_TABLE // address of next table and entry type
+ lsr \tmp1, \virt, #\shift
+ sub \ptrs, \ptrs, #1
+ and \tmp1, \tmp1, \ptrs // table index
str \tmp2, [\tbl, \tmp1, lsl #3]
add \tbl, \tbl, #PAGE_SIZE // next level table page
.endm
/*
- * Macro to populate the PGD (and possibily PUD) for the corresponding
- * block entry in the next level (tbl) for the given virtual address.
+ * Macro to populate page table entries, these entries can be pointers to the next level
+ * or last level entries pointing to physical memory.
+ *
+ * tbl: page table address
+ * rtbl: pointer to page table or physical memory
+ * index: start index to write
+ * eindex: end index to write - [index, eindex] written to
+ * flags: flags for pagetable entry to or in
+ * inc: increment to rtbl between each entry
+ * tmp1: temporary variable
*
- * Preserves: tbl, next, virt
- * Corrupts: tmp1, tmp2
+ * Preserves: tbl, eindex, flags, inc
+ * Corrupts: index, tmp1
+ * Returns: rtbl
*/
- .macro create_pgd_entry, tbl, virt, tmp1, tmp2
- create_table_entry \tbl, \virt, PGDIR_SHIFT, PTRS_PER_PGD, \tmp1, \tmp2
-#if SWAPPER_PGTABLE_LEVELS > 3
- create_table_entry \tbl, \virt, PUD_SHIFT, PTRS_PER_PUD, \tmp1, \tmp2
-#endif
-#if SWAPPER_PGTABLE_LEVELS > 2
- create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
-#endif
+ .macro populate_entries, tbl, rtbl, index, eindex, flags, inc, tmp1
+.Lpe\@: phys_to_pte \rtbl, \tmp1
+ orr \tmp1, \tmp1, \flags // tmp1 = table entry
+ str \tmp1, [\tbl, \index, lsl #3]
+ add \rtbl, \rtbl, \inc // rtbl = pa next level
+ add \index, \index, #1
+ cmp \index, \eindex
+ b.ls .Lpe\@
+ .endm
+
+/*
+ * Compute indices of table entries from virtual address range. If multiple entries
+ * were needed in the previous page table level then the next page table level is assumed
+ * to be composed of multiple pages. (This effectively scales the end index).
+ *
+ * vstart: virtual address of start of range
+ * vend: virtual address of end of range
+ * shift: shift used to transform virtual address into index
+ * ptrs: number of entries in page table
+ * istart: index in table corresponding to vstart
+ * iend: index in table corresponding to vend
+ * count: On entry: how many extra entries were required in previous level, scales
+ * our end index.
+ * On exit: returns how many extra entries required for next page table level
+ *
+ * Preserves: vstart, vend, shift, ptrs
+ * Returns: istart, iend, count
+ */
+ .macro compute_indices, vstart, vend, shift, ptrs, istart, iend, count
+ lsr \iend, \vend, \shift
+ mov \istart, \ptrs
+ sub \istart, \istart, #1
+ and \iend, \iend, \istart // iend = (vend >> shift) & (ptrs - 1)
+ mov \istart, \ptrs
+ mul \istart, \istart, \count
+ add \iend, \iend, \istart // iend += (count - 1) * ptrs
+ // our entries span multiple tables
+
+ lsr \istart, \vstart, \shift
+ mov \count, \ptrs
+ sub \count, \count, #1
+ and \istart, \istart, \count
+
+ sub \count, \iend, \istart
.endm
/*
- * Macro to populate block entries in the page table for the start..end
- * virtual range (inclusive).
+ * Map memory for specified virtual address range. Each level of page table needed supports
+ * multiple entries. If a level requires n entries the next page table level is assumed to be
+ * formed from n pages.
+ *
+ * tbl: location of page table
+ * rtbl: address to be used for first level page table entry (typically tbl + PAGE_SIZE)
+ * vstart: start address to map
+ * vend: end address to map - we map [vstart, vend]
+ * flags: flags to use to map last level entries
+ * phys: physical address corresponding to vstart - physical memory is contiguous
+ * pgds: the number of pgd entries
*
- * Preserves: tbl, flags
- * Corrupts: phys, start, end, pstate
+ * Temporaries: istart, iend, tmp, count, sv - these need to be different registers
+ * Preserves: vstart, vend, flags
+ * Corrupts: tbl, rtbl, istart, iend, tmp, count, sv
*/
- .macro create_block_map, tbl, flags, phys, start, end
- lsr \phys, \phys, #SWAPPER_BLOCK_SHIFT
- lsr \start, \start, #SWAPPER_BLOCK_SHIFT
- and \start, \start, #PTRS_PER_PTE - 1 // table index
- orr \phys, \flags, \phys, lsl #SWAPPER_BLOCK_SHIFT // table entry
- lsr \end, \end, #SWAPPER_BLOCK_SHIFT
- and \end, \end, #PTRS_PER_PTE - 1 // table end index
-9999: str \phys, [\tbl, \start, lsl #3] // store the entry
- add \start, \start, #1 // next entry
- add \phys, \phys, #SWAPPER_BLOCK_SIZE // next block
- cmp \start, \end
- b.ls 9999b
+ .macro map_memory, tbl, rtbl, vstart, vend, flags, phys, pgds, istart, iend, tmp, count, sv
+ add \rtbl, \tbl, #PAGE_SIZE
+ mov \sv, \rtbl
+ mov \count, #0
+ compute_indices \vstart, \vend, #PGDIR_SHIFT, \pgds, \istart, \iend, \count
+ populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp
+ mov \tbl, \sv
+ mov \sv, \rtbl
+
+#if SWAPPER_PGTABLE_LEVELS > 3
+ compute_indices \vstart, \vend, #PUD_SHIFT, #PTRS_PER_PUD, \istart, \iend, \count
+ populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp
+ mov \tbl, \sv
+ mov \sv, \rtbl
+#endif
+
+#if SWAPPER_PGTABLE_LEVELS > 2
+ compute_indices \vstart, \vend, #SWAPPER_TABLE_SHIFT, #PTRS_PER_PMD, \istart, \iend, \count
+ populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp
+ mov \tbl, \sv
+#endif
+
+ compute_indices \vstart, \vend, #SWAPPER_BLOCK_SHIFT, #PTRS_PER_PTE, \istart, \iend, \count
+ bic \count, \phys, #SWAPPER_BLOCK_SIZE - 1
+ populate_entries \tbl, \count, \istart, \iend, \flags, #SWAPPER_BLOCK_SIZE, \tmp
.endm
/*
@@ -221,14 +311,16 @@ __create_page_tables:
* dirty cache lines being evicted.
*/
adrp x0, idmap_pg_dir
- ldr x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+ adrp x1, swapper_pg_end
+ sub x1, x1, x0
bl __inval_dcache_area
/*
* Clear the idmap and swapper page tables.
*/
adrp x0, idmap_pg_dir
- ldr x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+ adrp x1, swapper_pg_end
+ sub x1, x1, x0
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
@@ -244,26 +336,13 @@ __create_page_tables:
adrp x0, idmap_pg_dir
adrp x3, __idmap_text_start // __pa(__idmap_text_start)
-#ifndef CONFIG_ARM64_VA_BITS_48
-#define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3)
-#define EXTRA_PTRS (1 << (48 - EXTRA_SHIFT))
-
- /*
- * If VA_BITS < 48, it may be too small to allow for an ID mapping to be
- * created that covers system RAM if that is located sufficiently high
- * in the physical address space. So for the ID map, use an extended
- * virtual range in that case, by configuring an additional translation
- * level.
- * First, we have to verify our assumption that the current value of
- * VA_BITS was chosen such that all translation levels are fully
- * utilised, and that lowering T0SZ will always result in an additional
- * translation level to be configured.
- */
-#if VA_BITS != EXTRA_SHIFT
-#error "Mismatch between VA_BITS and page size/number of translation levels"
-#endif
-
/*
+ * VA_BITS may be too small to allow for an ID mapping to be created
+ * that covers system RAM if that is located sufficiently high in the
+ * physical address space. So for the ID map, use an extended virtual
+ * range in that case, and configure an additional translation level
+ * if needed.
+ *
* Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
* entire ID map region can be mapped. As T0SZ == (64 - #bits used),
* this number conveniently equals the number of leading zeroes in
@@ -272,21 +351,44 @@ __create_page_tables:
adrp x5, __idmap_text_end
clz x5, x5
cmp x5, TCR_T0SZ(VA_BITS) // default T0SZ small enough?
- b.ge 1f // .. then skip additional level
+ b.ge 1f // .. then skip VA range extension
adr_l x6, idmap_t0sz
str x5, [x6]
dmb sy
dc ivac, x6 // Invalidate potentially stale cache line
- create_table_entry x0, x3, EXTRA_SHIFT, EXTRA_PTRS, x5, x6
-1:
+#if (VA_BITS < 48)
+#define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3)
+#define EXTRA_PTRS (1 << (PHYS_MASK_SHIFT - EXTRA_SHIFT))
+
+ /*
+ * If VA_BITS < 48, we have to configure an additional table level.
+ * First, we have to verify our assumption that the current value of
+ * VA_BITS was chosen such that all translation levels are fully
+ * utilised, and that lowering T0SZ will always result in an additional
+ * translation level to be configured.
+ */
+#if VA_BITS != EXTRA_SHIFT
+#error "Mismatch between VA_BITS and page size/number of translation levels"
#endif
- create_pgd_entry x0, x3, x5, x6
+ mov x4, EXTRA_PTRS
+ create_table_entry x0, x3, EXTRA_SHIFT, x4, x5, x6
+#else
+ /*
+ * If VA_BITS == 48, we don't have to configure an additional
+ * translation level, but the top-level table has more entries.
+ */
+ mov x4, #1 << (PHYS_MASK_SHIFT - PGDIR_SHIFT)
+ str_l x4, idmap_ptrs_per_pgd, x5
+#endif
+1:
+ ldr_l x4, idmap_ptrs_per_pgd
mov x5, x3 // __pa(__idmap_text_start)
adr_l x6, __idmap_text_end // __pa(__idmap_text_end)
- create_block_map x0, x7, x3, x5, x6
+
+ map_memory x0, x1, x3, x6, x7, x3, x4, x10, x11, x12, x13, x14
/*
* Map the kernel image (starting with PHYS_OFFSET).
@@ -294,12 +396,13 @@ __create_page_tables:
adrp x0, swapper_pg_dir
mov_q x5, KIMAGE_VADDR + TEXT_OFFSET // compile time __va(_text)
add x5, x5, x23 // add KASLR displacement
- create_pgd_entry x0, x5, x3, x6
+ mov x4, PTRS_PER_PGD
adrp x6, _end // runtime __pa(_end)
adrp x3, _text // runtime __pa(_text)
sub x6, x6, x3 // _end - _text
add x6, x6, x5 // runtime __va(_end)
- create_block_map x0, x7, x3, x5, x6
+
+ map_memory x0, x1, x5, x6, x7, x3, x4, x10, x11, x12, x13, x14
/*
* Since the page tables have been populated with non-cacheable
@@ -307,7 +410,8 @@ __create_page_tables:
* tables again to remove any speculatively loaded cache lines.
*/
adrp x0, idmap_pg_dir
- ldr x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+ adrp x1, swapper_pg_end
+ sub x1, x1, x0
dmb sy
bl __inval_dcache_area
@@ -388,17 +492,13 @@ ENTRY(el2_setup)
mrs x0, CurrentEL
cmp x0, #CurrentEL_EL2
b.eq 1f
- mrs x0, sctlr_el1
-CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1
-CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1
+ mov_q x0, (SCTLR_EL1_RES1 | ENDIAN_SET_EL1)
msr sctlr_el1, x0
mov w0, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1
isb
ret
-1: mrs x0, sctlr_el2
-CPU_BE( orr x0, x0, #(1 << 25) ) // Set the EE bit for EL2
-CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2
+1: mov_q x0, (SCTLR_EL2_RES1 | ENDIAN_SET_EL2)
msr sctlr_el2, x0
#ifdef CONFIG_ARM64_VHE
@@ -514,10 +614,7 @@ install_el2_stub:
* requires no configuration, and all non-hyp-specific EL2 setup
* will be done via the _EL1 system register aliases in __cpu_setup.
*/
- /* sctlr_el1 */
- mov x0, #0x0800 // Set/clear RES{1,0} bits
-CPU_BE( movk x0, #0x33d0, lsl #16 ) // Set EE and E0E on BE systems
-CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems
+ mov_q x0, (SCTLR_EL1_RES1 | ENDIAN_SET_EL1)
msr sctlr_el1, x0
/* Coprocessor traps. */
@@ -679,8 +776,10 @@ ENTRY(__enable_mmu)
update_early_cpu_boot_status 0, x1, x2
adrp x1, idmap_pg_dir
adrp x2, swapper_pg_dir
- msr ttbr0_el1, x1 // load TTBR0
- msr ttbr1_el1, x2 // load TTBR1
+ phys_to_ttbr x1, x3
+ phys_to_ttbr x2, x4
+ msr ttbr0_el1, x3 // load TTBR0
+ msr ttbr1_el1, x4 // load TTBR1
isb
msr sctlr_el1, x0
isb
@@ -750,6 +849,7 @@ __primary_switch:
* to take into account by discarding the current kernel mapping and
* creating a new one.
*/
+ pre_disable_mmu_workaround
msr sctlr_el1, x20 // disable the MMU
isb
bl __create_page_tables // recreate kernel mapping
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index e56d848b6466..84f5d52fddda 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -33,12 +33,14 @@
* Even switching to our copied tables will cause a changed output address at
* each stage of the walk.
*/
-.macro break_before_make_ttbr_switch zero_page, page_table
- msr ttbr1_el1, \zero_page
+.macro break_before_make_ttbr_switch zero_page, page_table, tmp
+ phys_to_ttbr \zero_page, \tmp
+ msr ttbr1_el1, \tmp
isb
tlbi vmalle1
dsb nsh
- msr ttbr1_el1, \page_table
+ phys_to_ttbr \page_table, \tmp
+ msr ttbr1_el1, \tmp
isb
.endm
@@ -78,7 +80,7 @@ ENTRY(swsusp_arch_suspend_exit)
* We execute from ttbr0, change ttbr1 to our copied linear map tables
* with a break-before-make via the zero page
*/
- break_before_make_ttbr_switch x5, x0
+ break_before_make_ttbr_switch x5, x0, x6
mov x21, x1
mov x30, x2
@@ -109,7 +111,7 @@ ENTRY(swsusp_arch_suspend_exit)
dsb ish /* wait for PoU cleaning to finish */
/* switch to the restored kernels page tables */
- break_before_make_ttbr_switch x25, x21
+ break_before_make_ttbr_switch x25, x21, x6
ic ialluis
dsb ish
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 3009b8b80f08..f20cf7e99249 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -247,8 +247,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
}
pte = pte_offset_kernel(pmd, dst_addr);
- set_pte(pte, __pte(virt_to_phys((void *)dst) |
- pgprot_val(PAGE_KERNEL_EXEC)));
+ set_pte(pte, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
/*
* Load our new page tables. A strict BBM approach requires that we
@@ -264,7 +263,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
*/
cpu_set_reserved_ttbr0();
local_flush_tlb_all();
- write_sysreg(virt_to_phys(pgd), ttbr0_el1);
+ write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1);
isb();
*phys_dst_addr = virt_to_phys((void *)dst);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 749f81779420..74bb56f656ef 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -28,6 +28,7 @@
#include <linux/perf_event.h>
#include <linux/ptrace.h>
#include <linux/smp.h>
+#include <linux/uaccess.h>
#include <asm/compat.h>
#include <asm/current.h>
@@ -36,7 +37,6 @@
#include <asm/traps.h>
#include <asm/cputype.h>
#include <asm/system_misc.h>
-#include <asm/uaccess.h>
/* Breakpoint currently in use for each BRP. */
static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 713561e5bcab..60e5fc661f74 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -29,6 +29,7 @@
#include <linux/irqchip.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
+#include <asm/vmap_stack.h>
unsigned long irq_err_count;
@@ -58,17 +59,7 @@ static void init_irq_stacks(void)
unsigned long *p;
for_each_possible_cpu(cpu) {
- /*
- * To ensure that VMAP'd stack overflow detection works
- * correctly, the IRQ stacks need to have the same
- * alignment as other stacks.
- */
- p = __vmalloc_node_range(IRQ_STACK_SIZE, THREAD_ALIGN,
- VMALLOC_START, VMALLOC_END,
- THREADINFO_GFP, PAGE_KERNEL,
- 0, cpu_to_node(cpu),
- __builtin_return_address(0));
-
+ p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu));
per_cpu(irq_stack_ptr, cpu) = p;
}
}
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index d05dbe658409..ea640f92fe5a 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -11,21 +11,6 @@
#include <linux/module.h>
#include <linux/sort.h>
-struct plt_entry {
- /*
- * A program that conforms to the AArch64 Procedure Call Standard
- * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
- * IP1 (x17) may be inserted at any branch instruction that is
- * exposed to a relocation that supports long branches. Since that
- * is exactly what we are dealing with here, we are free to use x16
- * as a scratch register in the PLT veneers.
- */
- __le32 mov0; /* movn x16, #0x.... */
- __le32 mov1; /* movk x16, #0x...., lsl #16 */
- __le32 mov2; /* movk x16, #0x...., lsl #32 */
- __le32 br; /* br x16 */
-};
-
static bool in_init(const struct module *mod, void *loc)
{
return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
@@ -40,33 +25,14 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
int i = pltsec->plt_num_entries;
u64 val = sym->st_value + rela->r_addend;
- /*
- * MOVK/MOVN/MOVZ opcode:
- * +--------+------------+--------+-----------+-------------+---------+
- * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
- * +--------+------------+--------+-----------+-------------+---------+
- *
- * Rd := 0x10 (x16)
- * hw := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
- * opc := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
- * sf := 1 (64-bit variant)
- */
- plt[i] = (struct plt_entry){
- cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5),
- cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
- cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
- cpu_to_le32(0xd61f0200)
- };
+ plt[i] = get_plt_entry(val);
/*
* Check if the entry we just created is a duplicate. Given that the
* relocations are sorted, this will be the last entry we allocated.
* (if one exists).
*/
- if (i > 0 &&
- plt[i].mov0 == plt[i - 1].mov0 &&
- plt[i].mov1 == plt[i - 1].mov1 &&
- plt[i].mov2 == plt[i - 1].mov2)
+ if (i > 0 && plt_entries_equal(plt + i, plt + i - 1))
return (u64)&plt[i - 1];
pltsec->plt_num_entries++;
@@ -154,6 +120,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
unsigned long core_plts = 0;
unsigned long init_plts = 0;
Elf64_Sym *syms = NULL;
+ Elf_Shdr *tramp = NULL;
int i;
/*
@@ -165,6 +132,10 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
mod->arch.core.plt = sechdrs + i;
else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
mod->arch.init.plt = sechdrs + i;
+ else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
+ !strcmp(secstrings + sechdrs[i].sh_name,
+ ".text.ftrace_trampoline"))
+ tramp = sechdrs + i;
else if (sechdrs[i].sh_type == SHT_SYMTAB)
syms = (Elf64_Sym *)sechdrs[i].sh_addr;
}
@@ -215,5 +186,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
mod->arch.init.plt_num_entries = 0;
mod->arch.init.plt_max_entries = init_plts;
+ if (tramp) {
+ tramp->sh_type = SHT_NOBITS;
+ tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ tramp->sh_addralign = __alignof__(struct plt_entry);
+ tramp->sh_size = sizeof(struct plt_entry);
+ }
+
return 0;
}
diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds
index f7c9781a9d48..22e36a21c113 100644
--- a/arch/arm64/kernel/module.lds
+++ b/arch/arm64/kernel/module.lds
@@ -1,4 +1,5 @@
SECTIONS {
.plt (NOLOAD) : { BYTE(0) }
.init.plt (NOLOAD) : { BYTE(0) }
+ .text.ftrace_trampoline (NOLOAD) : { BYTE(0) }
}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 9eaef51f83ff..3affca3dd96a 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -262,12 +262,6 @@ static const unsigned armv8_a73_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
-
- [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
- [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
-
- [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
- [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
};
static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index b2adcce7bc18..583fd8154695 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -314,6 +314,15 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
clear_tsk_thread_flag(p, TIF_SVE);
p->thread.sve_state = NULL;
+ /*
+ * In case p was allocated the same task_struct pointer as some
+ * other recently-exited task, make sure p is disassociated from
+ * any cpu that may have run that now-exited task recently.
+ * Otherwise we could erroneously skip reloading the FPSIMD
+ * registers for p.
+ */
+ fpsimd_flush_task_state(p);
+
if (likely(!(p->flags & PF_KTHREAD))) {
*childregs = *current_pt_regs();
childregs->regs[0] = 0;
@@ -361,16 +370,14 @@ void tls_preserve_current_state(void)
static void tls_thread_switch(struct task_struct *next)
{
- unsigned long tpidr, tpidrro;
-
tls_preserve_current_state();
- tpidr = *task_user_tls(next);
- tpidrro = is_compat_thread(task_thread_info(next)) ?
- next->thread.tp_value : 0;
+ if (is_compat_thread(task_thread_info(next)))
+ write_sysreg(next->thread.tp_value, tpidrro_el0);
+ else if (!arm64_kernel_unmapped_at_el0())
+ write_sysreg(0, tpidrro_el0);
- write_sysreg(tpidr, tpidr_el0);
- write_sysreg(tpidrro, tpidrro_el0);
+ write_sysreg(*task_user_tls(next), tpidr_el0);
}
/* Restore the UAO state depending on next's addr_limit */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 7c44658b316d..6618036ae6d4 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -180,34 +180,34 @@ static void ptrace_hbptriggered(struct perf_event *bp,
struct pt_regs *regs)
{
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
- siginfo_t info = {
- .si_signo = SIGTRAP,
- .si_errno = 0,
- .si_code = TRAP_HWBKPT,
- .si_addr = (void __user *)(bkpt->trigger),
- };
+ siginfo_t info;
-#ifdef CONFIG_COMPAT
- int i;
+ clear_siginfo(&info);
+ info.si_signo = SIGTRAP;
+ info.si_errno = 0;
+ info.si_code = TRAP_HWBKPT;
+ info.si_addr = (void __user *)(bkpt->trigger);
- if (!is_compat_task())
- goto send_sig;
+#ifdef CONFIG_COMPAT
+ if (is_compat_task()) {
+ int si_errno = 0;
+ int i;
- for (i = 0; i < ARM_MAX_BRP; ++i) {
- if (current->thread.debug.hbp_break[i] == bp) {
- info.si_errno = (i << 1) + 1;
- break;
+ for (i = 0; i < ARM_MAX_BRP; ++i) {
+ if (current->thread.debug.hbp_break[i] == bp) {
+ si_errno = (i << 1) + 1;
+ break;
+ }
}
- }
- for (i = 0; i < ARM_MAX_WRP; ++i) {
- if (current->thread.debug.hbp_watch[i] == bp) {
- info.si_errno = -((i << 1) + 1);
- break;
+ for (i = 0; i < ARM_MAX_WRP; ++i) {
+ if (current->thread.debug.hbp_watch[i] == bp) {
+ si_errno = -((i << 1) + 1);
+ break;
+ }
}
+ force_sig_ptrace_errno_trap(si_errno, (void __user *)bkpt->trigger);
}
-
-send_sig:
#endif
force_sig_info(SIGTRAP, &info, current);
}
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index ce704a4aeadd..f407e422a720 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -45,6 +45,7 @@ ENTRY(arm64_relocate_new_kernel)
mrs x0, sctlr_el2
ldr x1, =SCTLR_ELx_FLAGS
bic x0, x0, x1
+ pre_disable_mmu_workaround
msr sctlr_el2, x0
isb
1:
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
new file mode 100644
index 000000000000..6b8d90d5ceae
--- /dev/null
+++ b/arch/arm64/kernel/sdei.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#define pr_fmt(fmt) "sdei: " fmt
+
+#include <linux/arm_sdei.h>
+#include <linux/hardirq.h>
+#include <linux/irqflags.h>
+#include <linux/sched/task_stack.h>
+#include <linux/uaccess.h>
+
+#include <asm/alternative.h>
+#include <asm/kprobes.h>
+#include <asm/mmu.h>
+#include <asm/ptrace.h>
+#include <asm/sections.h>
+#include <asm/sysreg.h>
+#include <asm/vmap_stack.h>
+
+unsigned long sdei_exit_mode;
+
+/*
+ * VMAP'd stacks checking for stack overflow on exception using sp as a scratch
+ * register, meaning SDEI has to switch to its own stack. We need two stacks as
+ * a critical event may interrupt a normal event that has just taken a
+ * synchronous exception, and is using sp as scratch register. For a critical
+ * event interrupting a normal event, we can't reliably tell if we were on the
+ * sdei stack.
+ * For now, we allocate stacks when the driver is probed.
+ */
+DECLARE_PER_CPU(unsigned long *, sdei_stack_normal_ptr);
+DECLARE_PER_CPU(unsigned long *, sdei_stack_critical_ptr);
+
+#ifdef CONFIG_VMAP_STACK
+DEFINE_PER_CPU(unsigned long *, sdei_stack_normal_ptr);
+DEFINE_PER_CPU(unsigned long *, sdei_stack_critical_ptr);
+#endif
+
+static void _free_sdei_stack(unsigned long * __percpu *ptr, int cpu)
+{
+ unsigned long *p;
+
+ p = per_cpu(*ptr, cpu);
+ if (p) {
+ per_cpu(*ptr, cpu) = NULL;
+ vfree(p);
+ }
+}
+
+static void free_sdei_stacks(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ _free_sdei_stack(&sdei_stack_normal_ptr, cpu);
+ _free_sdei_stack(&sdei_stack_critical_ptr, cpu);
+ }
+}
+
+static int _init_sdei_stack(unsigned long * __percpu *ptr, int cpu)
+{
+ unsigned long *p;
+
+ p = arch_alloc_vmap_stack(SDEI_STACK_SIZE, cpu_to_node(cpu));
+ if (!p)
+ return -ENOMEM;
+ per_cpu(*ptr, cpu) = p;
+
+ return 0;
+}
+
+static int init_sdei_stacks(void)
+{
+ int cpu;
+ int err = 0;
+
+ for_each_possible_cpu(cpu) {
+ err = _init_sdei_stack(&sdei_stack_normal_ptr, cpu);
+ if (err)
+ break;
+ err = _init_sdei_stack(&sdei_stack_critical_ptr, cpu);
+ if (err)
+ break;
+ }
+
+ if (err)
+ free_sdei_stacks();
+
+ return err;
+}
+
+bool _on_sdei_stack(unsigned long sp)
+{
+ unsigned long low, high;
+
+ if (!IS_ENABLED(CONFIG_VMAP_STACK))
+ return false;
+
+ low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
+ high = low + SDEI_STACK_SIZE;
+
+ if (low <= sp && sp < high)
+ return true;
+
+ low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
+ high = low + SDEI_STACK_SIZE;
+
+ return (low <= sp && sp < high);
+}
+
+unsigned long sdei_arch_get_entry_point(int conduit)
+{
+ /*
+ * SDEI works between adjacent exception levels. If we booted at EL1 we
+ * assume a hypervisor is marshalling events. If we booted at EL2 and
+ * dropped to EL1 because we don't support VHE, then we can't support
+ * SDEI.
+ */
+ if (is_hyp_mode_available() && !is_kernel_in_hyp_mode()) {
+ pr_err("Not supported on this hardware/boot configuration\n");
+ return 0;
+ }
+
+ if (IS_ENABLED(CONFIG_VMAP_STACK)) {
+ if (init_sdei_stacks())
+ return 0;
+ }
+
+ sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ if (arm64_kernel_unmapped_at_el0()) {
+ unsigned long offset;
+
+ offset = (unsigned long)__sdei_asm_entry_trampoline -
+ (unsigned long)__entry_tramp_text_start;
+ return TRAMP_VALIAS + offset;
+ } else
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+ return (unsigned long)__sdei_asm_handler;
+
+}
+
+/*
+ * __sdei_handler() returns one of:
+ * SDEI_EV_HANDLED - success, return to the interrupted context.
+ * SDEI_EV_FAILED - failure, return this error code to firmare.
+ * virtual-address - success, return to this address.
+ */
+static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
+ struct sdei_registered_event *arg)
+{
+ u32 mode;
+ int i, err = 0;
+ int clobbered_registers = 4;
+ u64 elr = read_sysreg(elr_el1);
+ u32 kernel_mode = read_sysreg(CurrentEL) | 1; /* +SPSel */
+ unsigned long vbar = read_sysreg(vbar_el1);
+
+ if (arm64_kernel_unmapped_at_el0())
+ clobbered_registers++;
+
+ /* Retrieve the missing registers values */
+ for (i = 0; i < clobbered_registers; i++) {
+ /* from within the handler, this call always succeeds */
+ sdei_api_event_context(i, &regs->regs[i]);
+ }
+
+ /*
+ * We didn't take an exception to get here, set PAN. UAO will be cleared
+ * by sdei_event_handler()s set_fs(USER_DS) call.
+ */
+ __uaccess_enable_hw_pan();
+
+ err = sdei_event_handler(regs, arg);
+ if (err)
+ return SDEI_EV_FAILED;
+
+ if (elr != read_sysreg(elr_el1)) {
+ /*
+ * We took a synchronous exception from the SDEI handler.
+ * This could deadlock, and if you interrupt KVM it will
+ * hyp-panic instead.
+ */
+ pr_warn("unsafe: exception during handler\n");
+ }
+
+ mode = regs->pstate & (PSR_MODE32_BIT | PSR_MODE_MASK);
+
+ /*
+ * If we interrupted the kernel with interrupts masked, we always go
+ * back to wherever we came from.
+ */
+ if (mode == kernel_mode && !interrupts_enabled(regs))
+ return SDEI_EV_HANDLED;
+
+ /*
+ * Otherwise, we pretend this was an IRQ. This lets user space tasks
+ * receive signals before we return to them, and KVM to invoke it's
+ * world switch to do the same.
+ *
+ * See DDI0487B.a Table D1-7 'Vector offsets from vector table base
+ * address'.
+ */
+ if (mode == kernel_mode)
+ return vbar + 0x280;
+ else if (mode & PSR_MODE32_BIT)
+ return vbar + 0x680;
+
+ return vbar + 0x480;
+}
+
+
+asmlinkage __kprobes notrace unsigned long
+__sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
+{
+ unsigned long ret;
+ bool do_nmi_exit = false;
+
+ /*
+ * nmi_enter() deals with printk() re-entrance and use of RCU when
+ * RCU believed this CPU was idle. Because critical events can
+ * interrupt normal events, we may already be in_nmi().
+ */
+ if (!in_nmi()) {
+ nmi_enter();
+ do_nmi_exit = true;
+ }
+
+ ret = _sdei_handler(regs, arg);
+
+ if (do_nmi_exit)
+ nmi_exit();
+
+ return ret;
+}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index b120111a46be..f60c052e8d1c 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -178,7 +178,8 @@ static void __user *apply_user_offset(
static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
{
- struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
+ struct user_fpsimd_state const *fpsimd =
+ &current->thread.fpsimd_state.user_fpsimd;
int err;
/* copy the FP and status/control registers */
@@ -195,7 +196,7 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
{
- struct fpsimd_state fpsimd;
+ struct user_fpsimd_state fpsimd;
__u32 magic, size;
int err = 0;
@@ -266,7 +267,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
{
int err;
unsigned int vq;
- struct fpsimd_state fpsimd;
+ struct user_fpsimd_state fpsimd;
struct sve_context sve;
if (__copy_from_user(&sve, user->sve, sizeof(sve)))
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 22711ee8e36c..79feb861929b 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -125,86 +125,6 @@ static inline int get_sigset_t(sigset_t *set,
return 0;
}
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
- int err;
-
- if (!access_ok(VERIFY_WRITE, to, sizeof(*to)))
- return -EFAULT;
-
- /* If you change siginfo_t structure, please be sure
- * this code is fixed accordingly.
- * It should never copy any pad contained in the structure
- * to avoid security leaks, but must copy the generic
- * 3 ints plus the relevant union member.
- * This routine must convert siginfo from 64bit to 32bit as well
- * at the same time.
- */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user(from->si_code, &to->si_code);
- if (from->si_code < 0)
- err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad,
- SI_PAD_SIZE);
- else switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_KILL:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- case SIL_TIMER:
- err |= __put_user(from->si_tid, &to->si_tid);
- err |= __put_user(from->si_overrun, &to->si_overrun);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- case SIL_POLL:
- err |= __put_user(from->si_band, &to->si_band);
- err |= __put_user(from->si_fd, &to->si_fd);
- break;
- case SIL_FAULT:
- err |= __put_user((compat_uptr_t)(unsigned long)from->si_addr,
- &to->si_addr);
-#ifdef BUS_MCEERR_AO
- /*
- * Other callers might not initialize the si_lsb field,
- * so check explicitly for the right codes here.
- */
- if (from->si_signo == SIGBUS &&
- (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
- err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
-#endif
- break;
- case SIL_CHLD:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_status, &to->si_status);
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- break;
- case SIL_RT:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- case SIL_SYS:
- err |= __put_user((compat_uptr_t)(unsigned long)
- from->si_call_addr, &to->si_call_addr);
- err |= __put_user(from->si_syscall, &to->si_syscall);
- err |= __put_user(from->si_arch, &to->si_arch);
- break;
- }
- return err;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
- if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
- copy_from_user(to->_sifields._pad,
- from->_sifields._pad, SI_PAD_SIZE))
- return -EFAULT;
-
- return 0;
-}
-
/*
* VFP save/restore code.
*
@@ -228,7 +148,8 @@ union __fpsimd_vreg {
static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
{
- struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
+ struct user_fpsimd_state const *fpsimd =
+ &current->thread.fpsimd_state.user_fpsimd;
compat_ulong_t magic = VFP_MAGIC;
compat_ulong_t size = VFP_STORAGE_SIZE;
compat_ulong_t fpscr, fpexc;
@@ -277,7 +198,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame)
{
- struct fpsimd_state fpsimd;
+ struct user_fpsimd_state fpsimd;
compat_ulong_t magic = VFP_MAGIC;
compat_ulong_t size = VFP_STORAGE_SIZE;
compat_ulong_t fpscr;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 551eb07c53b6..3b8ad7be9c33 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -18,6 +18,7 @@
*/
#include <linux/acpi.h>
+#include <linux/arm_sdei.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
@@ -836,6 +837,7 @@ static void ipi_cpu_stop(unsigned int cpu)
set_cpu_online(cpu, false);
local_daif_mask();
+ sdei_mask_local_cpu();
while (1)
cpu_relax();
@@ -853,6 +855,7 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
atomic_dec(&waiting_for_crash_ipi);
local_irq_disable();
+ sdei_mask_local_cpu();
#ifdef CONFIG_HOTPLUG_CPU
if (cpu_ops[cpu]->cpu_die)
@@ -972,6 +975,8 @@ void smp_send_stop(void)
if (num_online_cpus() > 1)
pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(cpu_online_mask));
+
+ sdei_mask_local_cpu();
}
#ifdef CONFIG_KEXEC_CORE
@@ -990,8 +995,10 @@ void crash_smp_send_stop(void)
cpus_stopped = 1;
- if (num_online_cpus() == 1)
+ if (num_online_cpus() == 1) {
+ sdei_mask_local_cpu();
return;
+ }
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
@@ -1009,6 +1016,8 @@ void crash_smp_send_stop(void)
if (atomic_read(&waiting_for_crash_ipi) > 0)
pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(&mask));
+
+ sdei_mask_local_cpu();
}
bool smp_crash_stop_failed(void)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 3fe5ad884418..a307b9e13392 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -2,6 +2,7 @@
#include <linux/ftrace.h>
#include <linux/percpu.h>
#include <linux/slab.h>
+#include <linux/uaccess.h>
#include <asm/alternative.h>
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
@@ -51,8 +52,7 @@ void notrace __cpu_suspend_exit(void)
* PSTATE was not saved over suspend/resume, re-enable any detected
* features that might not have been set correctly.
*/
- asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
- CONFIG_ARM64_PAN));
+ __uaccess_enable_hw_pan();
uao_thread_switch(current);
/*
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 8d48b233e6ce..21868530018e 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -37,18 +37,14 @@ static int __init get_cpu_for_node(struct device_node *node)
if (!cpu_node)
return -1;
- for_each_possible_cpu(cpu) {
- if (of_get_cpu_node(cpu, NULL) == cpu_node) {
- topology_parse_cpu_capacity(cpu_node, cpu);
- of_node_put(cpu_node);
- return cpu;
- }
- }
-
- pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
+ cpu = of_cpu_node_to_id(cpu_node);
+ if (cpu >= 0)
+ topology_parse_cpu_capacity(cpu_node, cpu);
+ else
+ pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
of_node_put(cpu_node);
- return -1;
+ return cpu;
}
static int __init parse_core(struct device_node *core, int cluster_id,
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 3d3588fcd1c7..bbb0fde2780e 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -662,17 +662,58 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs)
}
#endif
-asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
+void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr)
{
- nmi_enter();
-
console_verbose();
pr_crit("SError Interrupt on CPU%d, code 0x%08x -- %s\n",
smp_processor_id(), esr, esr_get_class_string(esr));
- __show_regs(regs);
+ if (regs)
+ __show_regs(regs);
+
+ nmi_panic(regs, "Asynchronous SError Interrupt");
+
+ cpu_park_loop();
+ unreachable();
+}
+
+bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
+{
+ u32 aet = arm64_ras_serror_get_severity(esr);
+
+ switch (aet) {
+ case ESR_ELx_AET_CE: /* corrected error */
+ case ESR_ELx_AET_UEO: /* restartable, not yet consumed */
+ /*
+ * The CPU can make progress. We may take UEO again as
+ * a more severe error.
+ */
+ return false;
+
+ case ESR_ELx_AET_UEU: /* Uncorrected Unrecoverable */
+ case ESR_ELx_AET_UER: /* Uncorrected Recoverable */
+ /*
+ * The CPU can't make progress. The exception may have
+ * been imprecise.
+ */
+ return true;
+
+ case ESR_ELx_AET_UC: /* Uncontainable or Uncategorized error */
+ default:
+ /* Error has been silently propagated */
+ arm64_serror_panic(regs, esr);
+ }
+}
+
+asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
+{
+ nmi_enter();
+
+ /* non-RAS errors are not containable */
+ if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
+ arm64_serror_panic(regs, esr);
- panic("Asynchronous SError Interrupt");
+ nmi_exit();
}
void __pte_error(const char *file, int line, unsigned long val)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 7da3e5c366a0..0221aca6493d 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -57,6 +57,17 @@ jiffies = jiffies_64;
#define HIBERNATE_TEXT
#endif
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define TRAMP_TEXT \
+ . = ALIGN(PAGE_SIZE); \
+ VMLINUX_SYMBOL(__entry_tramp_text_start) = .; \
+ *(.entry.tramp.text) \
+ . = ALIGN(PAGE_SIZE); \
+ VMLINUX_SYMBOL(__entry_tramp_text_end) = .;
+#else
+#define TRAMP_TEXT
+#endif
+
/*
* The size of the PE/COFF section that covers the kernel image, which
* runs from stext to _edata, must be a round multiple of the PE/COFF
@@ -113,6 +124,7 @@ SECTIONS
HYPERVISOR_TEXT
IDMAP_TEXT
HIBERNATE_TEXT
+ TRAMP_TEXT
*(.fixup)
*(.gnu.warning)
. = ALIGN(16);
@@ -206,13 +218,19 @@ SECTIONS
. = ALIGN(PAGE_SIZE);
idmap_pg_dir = .;
. += IDMAP_DIR_SIZE;
- swapper_pg_dir = .;
- . += SWAPPER_DIR_SIZE;
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ tramp_pg_dir = .;
+ . += PAGE_SIZE;
+#endif
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
reserved_ttbr0 = .;
. += RESERVED_TTBR0_SIZE;
#endif
+ swapper_pg_dir = .;
+ . += SWAPPER_DIR_SIZE;
+ swapper_pg_end = .;
__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
_end = .;
@@ -234,7 +252,10 @@ ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
<= SZ_4K, "Hibernate exit text too big or misaligned")
#endif
-
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE,
+ "Entry trampoline text too big")
+#endif
/*
* If padding is applied before .head.text, virt<->phys conversions will fail.
*/
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index dbadfaf850a7..fa63b28c65e0 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -221,3 +221,24 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
}
}
}
+
+
+/*
+ * After successfully emulating an instruction, we might want to
+ * return to user space with a KVM_EXIT_DEBUG. We can only do this
+ * once the emulation is complete, though, so for userspace emulations
+ * we have to wait until we have re-entered KVM before calling this
+ * helper.
+ *
+ * Return true (and set exit_reason) to return to userspace or false
+ * if no further action is required.
+ */
+bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+ run->exit_reason = KVM_EXIT_DEBUG;
+ run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT;
+ return true;
+ }
+ return false;
+}
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index b71247995469..520b0dad3c62 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -23,17 +23,26 @@
#include <linux/kvm_host.h>
#include <asm/esr.h>
+#include <asm/exception.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_coproc.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_psci.h>
+#include <asm/debug-monitors.h>
+#include <asm/traps.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
+static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u32 esr)
+{
+ if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(NULL, esr))
+ kvm_inject_vabt(vcpu);
+}
+
static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
int ret;
@@ -44,7 +53,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
ret = kvm_psci_call(vcpu);
if (ret < 0) {
- kvm_inject_undefined(vcpu);
+ vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
}
@@ -53,7 +62,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
- kvm_inject_undefined(vcpu);
+ vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
}
@@ -187,14 +196,46 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
}
/*
+ * We may be single-stepping an emulated instruction. If the emulation
+ * has been completed in the kernel, we can return to userspace with a
+ * KVM_EXIT_DEBUG, otherwise userspace needs to complete its
+ * emulation first.
+ */
+static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ int handled;
+
+ /*
+ * See ARM ARM B1.14.1: "Hyp traps on instructions
+ * that fail their condition code check"
+ */
+ if (!kvm_condition_valid(vcpu)) {
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+ handled = 1;
+ } else {
+ exit_handle_fn exit_handler;
+
+ exit_handler = kvm_get_exit_handler(vcpu);
+ handled = exit_handler(vcpu, run);
+ }
+
+ /*
+ * kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run
+ * structure if we need to return to userspace.
+ */
+ if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run))
+ handled = 0;
+
+ return handled;
+}
+
+/*
* Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
* proper exit to userspace.
*/
int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
int exception_index)
{
- exit_handle_fn exit_handler;
-
if (ARM_SERROR_PENDING(exception_index)) {
u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
@@ -209,7 +250,6 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
*vcpu_pc(vcpu) -= adj;
}
- kvm_inject_vabt(vcpu);
return 1;
}
@@ -219,21 +259,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
case ARM_EXCEPTION_IRQ:
return 1;
case ARM_EXCEPTION_EL1_SERROR:
- kvm_inject_vabt(vcpu);
- return 1;
- case ARM_EXCEPTION_TRAP:
- /*
- * See ARM ARM B1.14.1: "Hyp traps on instructions
- * that fail their condition code check"
- */
- if (!kvm_condition_valid(vcpu)) {
- kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+ /* We may still need to return for single-step */
+ if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
+ && kvm_arm_handle_step_debug(vcpu, run))
+ return 0;
+ else
return 1;
- }
-
- exit_handler = kvm_get_exit_handler(vcpu);
-
- return exit_handler(vcpu, run);
+ case ARM_EXCEPTION_TRAP:
+ return handle_trap_exceptions(vcpu, run);
case ARM_EXCEPTION_HYP_GONE:
/*
* EL2 has been reset to the hyp-stub. This happens when a guest
@@ -248,3 +281,25 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
return 0;
}
}
+
+/* For exit types that need handling before we can be preempted */
+void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ int exception_index)
+{
+ if (ARM_SERROR_PENDING(exception_index)) {
+ if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN)) {
+ u64 disr = kvm_vcpu_get_disr(vcpu);
+
+ kvm_handle_guest_serror(vcpu, disr_to_esr(disr));
+ } else {
+ kvm_inject_vabt(vcpu);
+ }
+
+ return;
+ }
+
+ exception_index = ARM_EXCEPTION_CODE(exception_index);
+
+ if (exception_index == ARM_EXCEPTION_EL1_SERROR)
+ kvm_handle_guest_serror(vcpu, kvm_vcpu_get_hsr(vcpu));
+}
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 3f9615582377..e086c6eff8c6 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -63,7 +63,8 @@ __do_hyp_init:
cmp x0, #HVC_STUB_HCALL_NR
b.lo __kvm_handle_stub_hvc
- msr ttbr0_el2, x0
+ phys_to_ttbr x0, x4
+ msr ttbr0_el2, x4
mrs x4, tcr_el1
ldr x5, =TCR_EL2_MASK
@@ -71,30 +72,27 @@ __do_hyp_init:
mov x5, #TCR_EL2_RES1
orr x4, x4, x5
-#ifndef CONFIG_ARM64_VA_BITS_48
/*
- * If we are running with VA_BITS < 48, we may be running with an extra
- * level of translation in the ID map. This is only the case if system
- * RAM is out of range for the currently configured page size and number
- * of translation levels, in which case we will also need the extra
- * level for the HYP ID map, or we won't be able to enable the EL2 MMU.
+ * The ID map may be configured to use an extended virtual address
+ * range. This is only the case if system RAM is out of range for the
+ * currently configured page size and VA_BITS, in which case we will
+ * also need the extended virtual range for the HYP ID map, or we won't
+ * be able to enable the EL2 MMU.
*
* However, at EL2, there is only one TTBR register, and we can't switch
* between translation tables *and* update TCR_EL2.T0SZ at the same
- * time. Bottom line: we need the extra level in *both* our translation
- * tables.
+ * time. Bottom line: we need to use the extended range with *both* our
+ * translation tables.
*
* So use the same T0SZ value we use for the ID map.
*/
ldr_l x5, idmap_t0sz
bfi x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
-#endif
+
/*
- * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
- * TCR_EL2.
+ * Set the PS bits in TCR_EL2.
*/
- mrs x5, ID_AA64MMFR0_EL1
- bfi x4, x5, #16, #3
+ tcr_compute_pa_size x4, #TCR_EL2_PS_SHIFT, x5, x6
msr tcr_el2, x4
@@ -122,6 +120,10 @@ CPU_BE( orr x4, x4, #SCTLR_ELx_EE)
kern_hyp_va x2
msr vbar_el2, x2
+ /* copy tpidr_el1 into tpidr_el2 for use by HYP */
+ mrs x1, tpidr_el1
+ msr tpidr_el2, x1
+
/* Hello, World! */
eret
ENDPROC(__kvm_hyp_init)
@@ -151,6 +153,7 @@ reset:
mrs x5, sctlr_el2
ldr x6, =SCTLR_ELx_FLAGS
bic x5, x5, x6 // Clear SCTL_M and etc
+ pre_disable_mmu_workaround
msr sctlr_el2, x5
isb
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index 321c9c05dd9e..f4363d40e2cd 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -74,6 +74,9 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
{
u64 reg;
+ /* Clear pmscr in case of early return */
+ *pmscr_el1 = 0;
+
/* SPE present on this CPU? */
if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
ID_AA64DFR0_PMSVER_SHIFT))
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 12ee62d6d410..fdd1068ee3a5 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -62,8 +62,8 @@ ENTRY(__guest_enter)
// Store the host regs
save_callee_saved_regs x1
- // Store the host_ctxt for use at exit time
- str x1, [sp, #-16]!
+ // Store host_ctxt and vcpu for use at exit time
+ stp x1, x0, [sp, #-16]!
add x18, x0, #VCPU_CONTEXT
@@ -124,6 +124,17 @@ ENTRY(__guest_exit)
// Now restore the host regs
restore_callee_saved_regs x2
+alternative_if ARM64_HAS_RAS_EXTN
+ // If we have the RAS extensions we can consume a pending error
+ // without an unmask-SError and isb.
+ esb
+ mrs_s x2, SYS_DISR_EL1
+ str x2, [x1, #(VCPU_FAULT_DISR - VCPU_CONTEXT)]
+ cbz x2, 1f
+ msr_s SYS_DISR_EL1, xzr
+ orr x0, x0, #(1<<ARM_EXIT_WITH_SERROR_BIT)
+1: ret
+alternative_else
// If we have a pending asynchronous abort, now is the
// time to find out. From your VAXorcist book, page 666:
// "Threaten me not, oh Evil one! For I speak with
@@ -134,7 +145,9 @@ ENTRY(__guest_exit)
mov x5, x0
dsb sy // Synchronize against in-flight ld/st
+ nop
msr daifclr, #4 // Unmask aborts
+alternative_endif
// This is our single instruction exception window. A pending
// SError is guaranteed to occur at the earliest when we unmask
@@ -159,6 +172,10 @@ abort_guest_exit_end:
ENDPROC(__guest_exit)
ENTRY(__fpsimd_guest_restore)
+ // x0: esr
+ // x1: vcpu
+ // x2-x29,lr: vcpu regs
+ // vcpu x0-x1 on the stack
stp x2, x3, [sp, #-16]!
stp x4, lr, [sp, #-16]!
@@ -173,7 +190,7 @@ alternative_else
alternative_endif
isb
- mrs x3, tpidr_el2
+ mov x3, x1
ldr x0, [x3, #VCPU_HOST_CONTEXT]
kern_hyp_va x0
@@ -196,3 +213,15 @@ alternative_endif
eret
ENDPROC(__fpsimd_guest_restore)
+
+ENTRY(__qcom_hyp_sanitize_btac_predictors)
+ /**
+ * Call SMC64 with Silicon provider serviceID 23<<8 (0xc2001700)
+ * 0xC2000000-0xC200FFFF: assigned to SiP Service Calls
+ * b15-b0: contains SiP functionID
+ */
+ movz x0, #0x1700
+ movk x0, #0xc200, lsl #16
+ smc #0
+ ret
+ENDPROC(__qcom_hyp_sanitize_btac_predictors)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 5170ce1021da..e4f37b9dd47c 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -104,6 +104,7 @@ el1_trap:
/*
* x0: ESR_EC
*/
+ ldr x1, [sp, #16 + 8] // vcpu stored by __guest_enter
/*
* We trap the first access to the FP/SIMD to save the host context
@@ -116,19 +117,18 @@ alternative_if_not ARM64_HAS_NO_FPSIMD
b.eq __fpsimd_guest_restore
alternative_else_nop_endif
- mrs x1, tpidr_el2
mov x0, #ARM_EXCEPTION_TRAP
b __guest_exit
el1_irq:
stp x0, x1, [sp, #-16]!
- mrs x1, tpidr_el2
+ ldr x1, [sp, #16 + 8]
mov x0, #ARM_EXCEPTION_IRQ
b __guest_exit
el1_error:
stp x0, x1, [sp, #-16]!
- mrs x1, tpidr_el2
+ ldr x1, [sp, #16 + 8]
mov x0, #ARM_EXCEPTION_EL1_SERROR
b __guest_exit
@@ -163,6 +163,18 @@ ENTRY(__hyp_do_panic)
eret
ENDPROC(__hyp_do_panic)
+ENTRY(__hyp_panic)
+ /*
+ * '=kvm_host_cpu_state' is a host VA from the constant pool, it may
+ * not be accessible by this address from EL2, hyp_panic() converts
+ * it with kern_hyp_va() before use.
+ */
+ ldr x0, =kvm_host_cpu_state
+ mrs x1, tpidr_el2
+ add x0, x0, x1
+ b hyp_panic
+ENDPROC(__hyp_panic)
+
.macro invalid_vector label, target = __hyp_panic
.align 2
\label:
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
index a81f5e10fc8c..603e1ee83e89 100644
--- a/arch/arm64/kvm/hyp/s2-setup.c
+++ b/arch/arm64/kvm/hyp/s2-setup.c
@@ -32,6 +32,8 @@ u32 __hyp_text __init_stage2_translation(void)
* PS is only 3. Fortunately, bit 19 is RES0 in VTCR_EL2...
*/
parange = read_sysreg(id_aa64mmfr0_el1) & 7;
+ if (parange > ID_AA64MMFR0_PARANGE_MAX)
+ parange = ID_AA64MMFR0_PARANGE_MAX;
val |= parange << 16;
/* Compute the actual PARange... */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 525c01f48867..036e1f3d77a6 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -17,11 +17,13 @@
#include <linux/types.h>
#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
static bool __hyp_text __fpsimd_enabled_nvhe(void)
{
@@ -51,7 +53,7 @@ static void __hyp_text __activate_traps_vhe(void)
val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
write_sysreg(val, cpacr_el1);
- write_sysreg(__kvm_hyp_vector, vbar_el1);
+ write_sysreg(kvm_get_hyp_vector(), vbar_el1);
}
static void __hyp_text __activate_traps_nvhe(void)
@@ -92,6 +94,9 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
write_sysreg(val, hcr_el2);
+ if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (val & HCR_VSE))
+ write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+
/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
write_sysreg(1 << 15, hstr_el2);
/*
@@ -234,11 +239,12 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
{
- u64 esr = read_sysreg_el2(esr);
- u8 ec = ESR_ELx_EC(esr);
+ u8 ec;
+ u64 esr;
u64 hpfar, far;
- vcpu->arch.fault.esr_el2 = esr;
+ esr = vcpu->arch.fault.esr_el2;
+ ec = ESR_ELx_EC(esr);
if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
return true;
@@ -269,7 +275,11 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
return true;
}
-static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
+/* Skip an instruction which has been emulated. Returns true if
+ * execution can continue or false if we need to exit hyp mode because
+ * single-step was in effect.
+ */
+static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
{
*vcpu_pc(vcpu) = read_sysreg_el2(elr);
@@ -282,6 +292,14 @@ static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
}
write_sysreg_el2(*vcpu_pc(vcpu), elr);
+
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+ vcpu->arch.fault.esr_el2 =
+ (ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22;
+ return false;
+ } else {
+ return true;
+ }
}
int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
@@ -292,9 +310,9 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
u64 exit_code;
vcpu = kern_hyp_va(vcpu);
- write_sysreg(vcpu, tpidr_el2);
host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+ host_ctxt->__hyp_running_vcpu = vcpu;
guest_ctxt = &vcpu->arch.ctxt;
__sysreg_save_host_state(host_ctxt);
@@ -319,6 +337,8 @@ again:
exit_code = __guest_enter(vcpu, host_ctxt);
/* And we're baaack! */
+ if (ARM_EXCEPTION_CODE(exit_code) != ARM_EXCEPTION_IRQ)
+ vcpu->arch.fault.esr_el2 = read_sysreg_el2(esr);
/*
* We're using the raw exception code in order to only process
* the trap if no SError is pending. We will come back to the
@@ -328,6 +348,18 @@ again:
if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
goto again;
+ if (exit_code == ARM_EXCEPTION_TRAP &&
+ (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
+ kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) &&
+ vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) {
+ u64 val = PSCI_RET_NOT_SUPPORTED;
+ if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+ val = 2;
+
+ vcpu_set_reg(vcpu, 0, val);
+ goto again;
+ }
+
if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
exit_code == ARM_EXCEPTION_TRAP) {
bool valid;
@@ -342,13 +374,21 @@ again:
int ret = __vgic_v2_perform_cpuif_access(vcpu);
if (ret == 1) {
- __skip_instr(vcpu);
- goto again;
+ if (__skip_instr(vcpu))
+ goto again;
+ else
+ exit_code = ARM_EXCEPTION_TRAP;
}
if (ret == -1) {
- /* Promote an illegal access to an SError */
- __skip_instr(vcpu);
+ /* Promote an illegal access to an
+ * SError. If we would be returning
+ * due to single-step clear the SS
+ * bit so handle_exit knows what to
+ * do after dealing with the error.
+ */
+ if (!__skip_instr(vcpu))
+ *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
exit_code = ARM_EXCEPTION_EL1_SERROR;
}
@@ -363,13 +403,23 @@ again:
int ret = __vgic_v3_perform_cpuif_access(vcpu);
if (ret == 1) {
- __skip_instr(vcpu);
- goto again;
+ if (__skip_instr(vcpu))
+ goto again;
+ else
+ exit_code = ARM_EXCEPTION_TRAP;
}
/* 0 falls through to be handled out of EL2 */
}
+ if (cpus_have_const_cap(ARM64_HARDEN_BP_POST_GUEST_EXIT)) {
+ u32 midr = read_cpuid_id();
+
+ /* Apply BTAC predictors mitigation to all Falkor chips */
+ if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)
+ __qcom_hyp_sanitize_btac_predictors();
+ }
+
fp_enabled = __fpsimd_enabled();
__sysreg_save_guest_state(guest_ctxt);
@@ -399,7 +449,8 @@ again:
static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
-static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
+static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
+ struct kvm_vcpu *vcpu)
{
unsigned long str_va;
@@ -413,35 +464,35 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
__hyp_do_panic(str_va,
spsr, elr,
read_sysreg(esr_el2), read_sysreg_el2(far),
- read_sysreg(hpfar_el2), par,
- (void *)read_sysreg(tpidr_el2));
+ read_sysreg(hpfar_el2), par, vcpu);
}
-static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par)
+static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
+ struct kvm_vcpu *vcpu)
{
panic(__hyp_panic_string,
spsr, elr,
read_sysreg_el2(esr), read_sysreg_el2(far),
- read_sysreg(hpfar_el2), par,
- (void *)read_sysreg(tpidr_el2));
+ read_sysreg(hpfar_el2), par, vcpu);
}
static hyp_alternate_select(__hyp_call_panic,
__hyp_call_panic_nvhe, __hyp_call_panic_vhe,
ARM64_HAS_VIRT_HOST_EXTN);
-void __hyp_text __noreturn __hyp_panic(void)
+void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *__host_ctxt)
{
+ struct kvm_vcpu *vcpu = NULL;
+
u64 spsr = read_sysreg_el2(spsr);
u64 elr = read_sysreg_el2(elr);
u64 par = read_sysreg(par_el1);
if (read_sysreg(vttbr_el2)) {
- struct kvm_vcpu *vcpu;
struct kvm_cpu_context *host_ctxt;
- vcpu = (struct kvm_vcpu *)read_sysreg(tpidr_el2);
- host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+ host_ctxt = kern_hyp_va(__host_ctxt);
+ vcpu = host_ctxt->__hyp_running_vcpu;
__timer_disable_traps(vcpu);
__deactivate_traps(vcpu);
__deactivate_vm(vcpu);
@@ -449,7 +500,7 @@ void __hyp_text __noreturn __hyp_panic(void)
}
/* Call panic for real */
- __hyp_call_panic()(spsr, elr, par);
+ __hyp_call_panic()(spsr, elr, par, vcpu);
unreachable();
}
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 934137647837..2c17afd2be96 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -27,8 +27,8 @@ static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
/*
* Non-VHE: Both host and guest must save everything.
*
- * VHE: Host must save tpidr*_el[01], actlr_el1, mdscr_el1, sp0, pc,
- * pstate, and guest must save everything.
+ * VHE: Host must save tpidr*_el0, actlr_el1, mdscr_el1, sp_el0,
+ * and guest must save everything.
*/
static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
@@ -36,11 +36,8 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
ctxt->sys_regs[ACTLR_EL1] = read_sysreg(actlr_el1);
ctxt->sys_regs[TPIDR_EL0] = read_sysreg(tpidr_el0);
ctxt->sys_regs[TPIDRRO_EL0] = read_sysreg(tpidrro_el0);
- ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1);
ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1);
ctxt->gp_regs.regs.sp = read_sysreg(sp_el0);
- ctxt->gp_regs.regs.pc = read_sysreg_el2(elr);
- ctxt->gp_regs.regs.pstate = read_sysreg_el2(spsr);
}
static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
@@ -62,10 +59,16 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(amair);
ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(cntkctl);
ctxt->sys_regs[PAR_EL1] = read_sysreg(par_el1);
+ ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1);
ctxt->gp_regs.sp_el1 = read_sysreg(sp_el1);
ctxt->gp_regs.elr_el1 = read_sysreg_el1(elr);
ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr);
+ ctxt->gp_regs.regs.pc = read_sysreg_el2(elr);
+ ctxt->gp_regs.regs.pstate = read_sysreg_el2(spsr);
+
+ if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+ ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
}
static hyp_alternate_select(__sysreg_call_save_host_state,
@@ -89,11 +92,8 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx
write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1);
write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0);
write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
- write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1);
write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1);
write_sysreg(ctxt->gp_regs.regs.sp, sp_el0);
- write_sysreg_el2(ctxt->gp_regs.regs.pc, elr);
- write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
}
static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
@@ -115,10 +115,16 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], amair);
write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], cntkctl);
write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1);
+ write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1);
write_sysreg(ctxt->gp_regs.sp_el1, sp_el1);
write_sysreg_el1(ctxt->gp_regs.elr_el1, elr);
write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr);
+ write_sysreg_el2(ctxt->gp_regs.regs.pc, elr);
+ write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
+
+ if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+ write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
}
static hyp_alternate_select(__sysreg_call_restore_host_state,
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 8ecbcb40e317..60666a056944 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -164,14 +164,25 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
inject_undef64(vcpu);
}
+static void pend_guest_serror(struct kvm_vcpu *vcpu, u64 esr)
+{
+ vcpu_set_vsesr(vcpu, esr);
+ vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VSE);
+}
+
/**
* kvm_inject_vabt - inject an async abort / SError into the guest
* @vcpu: The VCPU to receive the exception
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
+ *
+ * Systems with the RAS Extensions specify an imp-def ESR (ISV/IDS = 1) with
+ * the remaining ISS all-zeros so that this error is not interpreted as an
+ * uncategorized RAS error. Without the RAS Extensions we can't specify an ESR
+ * value, so the CPU generates an imp-def value.
*/
void kvm_inject_vabt(struct kvm_vcpu *vcpu)
{
- vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VSE);
+ pend_guest_serror(vcpu, ESR_ELx_ISV);
}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 1830ebc227d1..50a43c7b97ca 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1159,6 +1159,16 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 },
{ SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 },
{ SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 },
+
+ { SYS_DESC(SYS_ERRIDR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_ERRSELR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_ERXFR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_ERXCTLR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_ERXSTATUS_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_ERXADDR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
+
{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
@@ -1169,6 +1179,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
{ SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
+ { SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 },
{ SYS_DESC(SYS_ICC_IAR0_EL1), write_to_read_only },
{ SYS_DESC(SYS_ICC_EOIR0_EL1), read_from_write_only },
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index e88fb99c1561..3d69a8d41fa5 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -30,7 +30,7 @@
* Alignment fixed up by hardware.
*/
ENTRY(__clear_user)
- uaccess_enable_not_uao x2, x3
+ uaccess_enable_not_uao x2, x3, x4
mov x2, x1 // save the size for fixup return
subs x1, x1, #8
b.mi 2f
@@ -50,7 +50,7 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2
b.mi 5f
uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
5: mov x0, #0
- uaccess_disable_not_uao x2
+ uaccess_disable_not_uao x2, x3
ret
ENDPROC(__clear_user)
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 4b5d826895ff..20305d485046 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -64,10 +64,10 @@
end .req x5
ENTRY(__arch_copy_from_user)
- uaccess_enable_not_uao x3, x4
+ uaccess_enable_not_uao x3, x4, x5
add end, x0, x2
#include "copy_template.S"
- uaccess_disable_not_uao x3
+ uaccess_disable_not_uao x3, x4
mov x0, #0 // Nothing to copy
ret
ENDPROC(__arch_copy_from_user)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index b24a830419ad..fbb090f431a5 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -65,10 +65,10 @@
end .req x5
ENTRY(raw_copy_in_user)
- uaccess_enable_not_uao x3, x4
+ uaccess_enable_not_uao x3, x4, x5
add end, x0, x2
#include "copy_template.S"
- uaccess_disable_not_uao x3
+ uaccess_disable_not_uao x3, x4
mov x0, #0
ret
ENDPROC(raw_copy_in_user)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 351f0766f7a6..fda6172d6b88 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -63,10 +63,10 @@
end .req x5
ENTRY(__arch_copy_to_user)
- uaccess_enable_not_uao x3, x4
+ uaccess_enable_not_uao x3, x4, x5
add end, x0, x2
#include "copy_template.S"
- uaccess_disable_not_uao x3
+ uaccess_disable_not_uao x3, x4
mov x0, #0
ret
ENDPROC(__arch_copy_to_user)
diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S
index 0179a43cc045..d3db9b2cd479 100644
--- a/arch/arm64/lib/tishift.S
+++ b/arch/arm64/lib/tishift.S
@@ -38,19 +38,19 @@ ENTRY(__ashlti3)
ENDPROC(__ashlti3)
ENTRY(__ashrti3)
- cbz x2, 3f
+ cbz x2, 1f
mov x3, #64
sub x3, x3, x2
cmp x3, #0
- b.le 4f
+ b.le 2f
lsr x0, x0, x2
lsl x3, x1, x3
asr x2, x1, x2
orr x0, x0, x3
mov x1, x2
-3:
+1:
ret
-4:
+2:
neg w0, w3
asr x2, x1, #63
asr x0, x1, x0
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 7f1dbe962cf5..91464e7f77cc 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -49,7 +49,7 @@ ENTRY(flush_icache_range)
* - end - virtual end address of region
*/
ENTRY(__flush_cache_user_range)
- uaccess_ttbr0_enable x2, x3
+ uaccess_ttbr0_enable x2, x3, x4
dcache_line_size x2, x3
sub x3, x2, #1
bic x4, x0, x3
@@ -72,7 +72,7 @@ USER(9f, ic ivau, x4 ) // invalidate I line PoU
isb
mov x0, #0
1:
- uaccess_ttbr0_disable x1
+ uaccess_ttbr0_disable x1, x2
ret
9:
mov x0, #-EFAULT
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index ab9f5f0fb2c7..301417ae2ba8 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -39,7 +39,16 @@ static cpumask_t tlb_flush_pending;
#define ASID_MASK (~GENMASK(asid_bits - 1, 0))
#define ASID_FIRST_VERSION (1UL << asid_bits)
-#define NUM_USER_ASIDS ASID_FIRST_VERSION
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define NUM_USER_ASIDS (ASID_FIRST_VERSION >> 1)
+#define asid2idx(asid) (((asid) & ~ASID_MASK) >> 1)
+#define idx2asid(idx) (((idx) << 1) & ~ASID_MASK)
+#else
+#define NUM_USER_ASIDS (ASID_FIRST_VERSION)
+#define asid2idx(asid) ((asid) & ~ASID_MASK)
+#define idx2asid(idx) asid2idx(idx)
+#endif
/* Get the ASIDBits supported by the current CPU */
static u32 get_cpu_asid_bits(void)
@@ -79,13 +88,6 @@ void verify_cpu_asid_bits(void)
}
}
-static void set_reserved_asid_bits(void)
-{
- if (IS_ENABLED(CONFIG_QCOM_FALKOR_ERRATUM_1003) &&
- cpus_have_const_cap(ARM64_WORKAROUND_QCOM_FALKOR_E1003))
- __set_bit(FALKOR_RESERVED_ASID, asid_map);
-}
-
static void flush_context(unsigned int cpu)
{
int i;
@@ -94,14 +96,6 @@ static void flush_context(unsigned int cpu)
/* Update the list of reserved ASIDs and the ASID bitmap. */
bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
- set_reserved_asid_bits();
-
- /*
- * Ensure the generation bump is observed before we xchg the
- * active_asids.
- */
- smp_wmb();
-
for_each_possible_cpu(i) {
asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
/*
@@ -113,11 +107,14 @@ static void flush_context(unsigned int cpu)
*/
if (asid == 0)
asid = per_cpu(reserved_asids, i);
- __set_bit(asid & ~ASID_MASK, asid_map);
+ __set_bit(asid2idx(asid), asid_map);
per_cpu(reserved_asids, i) = asid;
}
- /* Queue a TLB invalidate and flush the I-cache if necessary. */
+ /*
+ * Queue a TLB invalidation for each CPU to perform on next
+ * context-switch
+ */
cpumask_setall(&tlb_flush_pending);
}
@@ -165,16 +162,16 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
* We had a valid ASID in a previous life, so try to re-use
* it if possible.
*/
- asid &= ~ASID_MASK;
- if (!__test_and_set_bit(asid, asid_map))
+ if (!__test_and_set_bit(asid2idx(asid), asid_map))
return newasid;
}
/*
* Allocate a free ASID. If we can't find one, take a note of the
- * currently active ASIDs and mark the TLBs as requiring flushes.
- * We always count from ASID #1, as we use ASID #0 when setting a
- * reserved TTBR0 for the init_mm.
+ * currently active ASIDs and mark the TLBs as requiring flushes. We
+ * always count from ASID #2 (index 1), as we use ASID #0 when setting
+ * a reserved TTBR0 for the init_mm and we allocate ASIDs in even/odd
+ * pairs.
*/
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
if (asid != NUM_USER_ASIDS)
@@ -191,25 +188,35 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
set_asid:
__set_bit(asid, asid_map);
cur_idx = asid;
- return asid | generation;
+ return idx2asid(asid) | generation;
}
void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
{
unsigned long flags;
- u64 asid;
+ u64 asid, old_active_asid;
asid = atomic64_read(&mm->context.id);
/*
- * The memory ordering here is subtle. We rely on the control
- * dependency between the generation read and the update of
- * active_asids to ensure that we are synchronised with a
- * parallel rollover (i.e. this pairs with the smp_wmb() in
- * flush_context).
+ * The memory ordering here is subtle.
+ * If our active_asids is non-zero and the ASID matches the current
+ * generation, then we update the active_asids entry with a relaxed
+ * cmpxchg. Racing with a concurrent rollover means that either:
+ *
+ * - We get a zero back from the cmpxchg and end up waiting on the
+ * lock. Taking the lock synchronises with the rollover and so
+ * we are forced to see the updated generation.
+ *
+ * - We get a valid ASID back from the cmpxchg, which means the
+ * relaxed xchg in flush_context will treat us as reserved
+ * because atomic RmWs are totally ordered for a given location.
*/
- if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits)
- && atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid))
+ old_active_asid = atomic64_read(&per_cpu(active_asids, cpu));
+ if (old_active_asid &&
+ !((asid ^ atomic64_read(&asid_generation)) >> asid_bits) &&
+ atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu),
+ old_active_asid, asid))
goto switch_mm_fastpath;
raw_spin_lock_irqsave(&cpu_asid_lock, flags);
@@ -227,6 +234,9 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
switch_mm_fastpath:
+
+ arm64_apply_bp_hardening();
+
/*
* Defer TTBR0_EL1 setting for user threads to uaccess_enable() when
* emulating PAN.
@@ -235,6 +245,15 @@ switch_mm_fastpath:
cpu_switch_mm(mm->pgd, mm);
}
+/* Errata workaround post TTBRx_EL1 update. */
+asmlinkage void post_ttbr_update_workaround(void)
+{
+ asm(ALTERNATIVE("nop; nop; nop",
+ "ic iallu; dsb nsh; isb",
+ ARM64_WORKAROUND_CAVIUM_27456,
+ CONFIG_CAVIUM_ERRATUM_27456));
+}
+
static int asids_init(void)
{
asid_bits = get_cpu_asid_bits();
@@ -250,8 +269,6 @@ static int asids_init(void)
panic("Failed to allocate bitmap for %lu ASIDs\n",
NUM_USER_ASIDS);
- set_reserved_asid_bits();
-
pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
return 0;
}
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index ca74a2aace42..7b60d62ac593 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -389,7 +389,7 @@ void ptdump_check_wx(void)
.check_wx = true,
};
- walk_pgd(&st, &init_mm, 0);
+ walk_pgd(&st, &init_mm, VA_START);
note_page(&st, 0, 0, 0);
if (st.wx_pages || st.uxn_pages)
pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 22168cd0dde7..ce441d29e7f6 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -574,7 +574,6 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
struct siginfo info;
const struct fault_info *inf;
- int ret = 0;
inf = esr_to_fault_info(esr);
pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
@@ -589,7 +588,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
if (interrupts_enabled(regs))
nmi_enter();
- ret = ghes_notify_sea();
+ ghes_notify_sea();
if (interrupts_enabled(regs))
nmi_exit();
@@ -597,81 +596,81 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
info.si_signo = SIGBUS;
info.si_errno = 0;
- info.si_code = 0;
+ info.si_code = BUS_FIXME;
if (esr & ESR_ELx_FnV)
info.si_addr = NULL;
else
info.si_addr = (void __user *)addr;
arm64_notify_die("", regs, &info, esr);
- return ret;
+ return 0;
}
static const struct fault_info fault_info[] = {
- { do_bad, SIGBUS, 0, "ttbr address size fault" },
- { do_bad, SIGBUS, 0, "level 1 address size fault" },
- { do_bad, SIGBUS, 0, "level 2 address size fault" },
- { do_bad, SIGBUS, 0, "level 3 address size fault" },
+ { do_bad, SIGBUS, BUS_FIXME, "ttbr address size fault" },
+ { do_bad, SIGBUS, BUS_FIXME, "level 1 address size fault" },
+ { do_bad, SIGBUS, BUS_FIXME, "level 2 address size fault" },
+ { do_bad, SIGBUS, BUS_FIXME, "level 3 address size fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
- { do_bad, SIGBUS, 0, "unknown 8" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 8" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" },
- { do_bad, SIGBUS, 0, "unknown 12" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 12" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
- { do_sea, SIGBUS, 0, "synchronous external abort" },
- { do_bad, SIGBUS, 0, "unknown 17" },
- { do_bad, SIGBUS, 0, "unknown 18" },
- { do_bad, SIGBUS, 0, "unknown 19" },
- { do_sea, SIGBUS, 0, "level 0 (translation table walk)" },
- { do_sea, SIGBUS, 0, "level 1 (translation table walk)" },
- { do_sea, SIGBUS, 0, "level 2 (translation table walk)" },
- { do_sea, SIGBUS, 0, "level 3 (translation table walk)" },
- { do_sea, SIGBUS, 0, "synchronous parity or ECC error" }, // Reserved when RAS is implemented
- { do_bad, SIGBUS, 0, "unknown 25" },
- { do_bad, SIGBUS, 0, "unknown 26" },
- { do_bad, SIGBUS, 0, "unknown 27" },
- { do_sea, SIGBUS, 0, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
- { do_sea, SIGBUS, 0, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
- { do_sea, SIGBUS, 0, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
- { do_sea, SIGBUS, 0, "level 3 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
- { do_bad, SIGBUS, 0, "unknown 32" },
+ { do_sea, SIGBUS, BUS_FIXME, "synchronous external abort" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 17" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 18" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 19" },
+ { do_sea, SIGBUS, BUS_FIXME, "level 0 (translation table walk)" },
+ { do_sea, SIGBUS, BUS_FIXME, "level 1 (translation table walk)" },
+ { do_sea, SIGBUS, BUS_FIXME, "level 2 (translation table walk)" },
+ { do_sea, SIGBUS, BUS_FIXME, "level 3 (translation table walk)" },
+ { do_sea, SIGBUS, BUS_FIXME, "synchronous parity or ECC error" }, // Reserved when RAS is implemented
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 25" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 26" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 27" },
+ { do_sea, SIGBUS, BUS_FIXME, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
+ { do_sea, SIGBUS, BUS_FIXME, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
+ { do_sea, SIGBUS, BUS_FIXME, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
+ { do_sea, SIGBUS, BUS_FIXME, "level 3 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 32" },
{ do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" },
- { do_bad, SIGBUS, 0, "unknown 34" },
- { do_bad, SIGBUS, 0, "unknown 35" },
- { do_bad, SIGBUS, 0, "unknown 36" },
- { do_bad, SIGBUS, 0, "unknown 37" },
- { do_bad, SIGBUS, 0, "unknown 38" },
- { do_bad, SIGBUS, 0, "unknown 39" },
- { do_bad, SIGBUS, 0, "unknown 40" },
- { do_bad, SIGBUS, 0, "unknown 41" },
- { do_bad, SIGBUS, 0, "unknown 42" },
- { do_bad, SIGBUS, 0, "unknown 43" },
- { do_bad, SIGBUS, 0, "unknown 44" },
- { do_bad, SIGBUS, 0, "unknown 45" },
- { do_bad, SIGBUS, 0, "unknown 46" },
- { do_bad, SIGBUS, 0, "unknown 47" },
- { do_bad, SIGBUS, 0, "TLB conflict abort" },
- { do_bad, SIGBUS, 0, "Unsupported atomic hardware update fault" },
- { do_bad, SIGBUS, 0, "unknown 50" },
- { do_bad, SIGBUS, 0, "unknown 51" },
- { do_bad, SIGBUS, 0, "implementation fault (lockdown abort)" },
- { do_bad, SIGBUS, 0, "implementation fault (unsupported exclusive)" },
- { do_bad, SIGBUS, 0, "unknown 54" },
- { do_bad, SIGBUS, 0, "unknown 55" },
- { do_bad, SIGBUS, 0, "unknown 56" },
- { do_bad, SIGBUS, 0, "unknown 57" },
- { do_bad, SIGBUS, 0, "unknown 58" },
- { do_bad, SIGBUS, 0, "unknown 59" },
- { do_bad, SIGBUS, 0, "unknown 60" },
- { do_bad, SIGBUS, 0, "section domain fault" },
- { do_bad, SIGBUS, 0, "page domain fault" },
- { do_bad, SIGBUS, 0, "unknown 63" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 34" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 35" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 36" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 37" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 38" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 39" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 40" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 41" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 42" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 43" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 44" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 45" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 46" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 47" },
+ { do_bad, SIGBUS, BUS_FIXME, "TLB conflict abort" },
+ { do_bad, SIGBUS, BUS_FIXME, "Unsupported atomic hardware update fault" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 50" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 51" },
+ { do_bad, SIGBUS, BUS_FIXME, "implementation fault (lockdown abort)" },
+ { do_bad, SIGBUS, BUS_FIXME, "implementation fault (unsupported exclusive)" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 54" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 55" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 56" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 57" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 58" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 59" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 60" },
+ { do_bad, SIGBUS, BUS_FIXME, "section domain fault" },
+ { do_bad, SIGBUS, BUS_FIXME, "page domain fault" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 63" },
};
int handle_guest_sea(phys_addr_t addr, unsigned int esr)
@@ -708,6 +707,23 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
arm64_notify_die("", regs, &info, esr);
}
+asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
+ unsigned int esr,
+ struct pt_regs *regs)
+{
+ /*
+ * We've taken an instruction abort from userspace and not yet
+ * re-enabled IRQs. If the address is a kernel address, apply
+ * BP hardening prior to enabling IRQs and pre-emption.
+ */
+ if (addr > TASK_SIZE)
+ arm64_apply_bp_hardening();
+
+ local_irq_enable();
+ do_mem_abort(addr, esr, regs);
+}
+
+
asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
unsigned int esr,
struct pt_regs *regs)
@@ -740,11 +756,11 @@ static struct fault_info __refdata debug_fault_info[] = {
{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware breakpoint" },
{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware single-step" },
{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware watchpoint" },
- { do_bad, SIGBUS, 0, "unknown 3" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 3" },
{ do_bad, SIGTRAP, TRAP_BRKPT, "aarch32 BKPT" },
- { do_bad, SIGTRAP, 0, "aarch32 vector catch" },
+ { do_bad, SIGTRAP, TRAP_FIXME, "aarch32 vector catch" },
{ early_brk64, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" },
- { do_bad, SIGBUS, 0, "unknown 7" },
+ { do_bad, SIGBUS, BUS_FIXME, "unknown 7" },
};
void __init hook_debug_fault_code(int nr,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 5960bef0170d..c903f7ccbdd2 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -366,6 +366,9 @@ void __init arm64_memblock_init(void)
/* Handle linux,usable-memory-range property */
fdt_enforce_memory_region();
+ /* Remove memory above our supported physical address size */
+ memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
+
/*
* Ensure that the linear region takes up exactly half of the kernel
* virtual address space. This way, we can distinguish a linear address
@@ -476,6 +479,8 @@ void __init arm64_memblock_init(void)
reserve_elfcorehdr();
+ high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
+
dma_contiguous_reserve(arm64_dma_phys_limit);
memblock_allow_resize();
@@ -502,7 +507,6 @@ void __init bootmem_init(void)
sparse_init();
zone_sizes_init(min, max);
- high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
memblock_dump_all();
}
@@ -599,49 +603,6 @@ void __init mem_init(void)
mem_init_print_info(NULL);
-#define MLK(b, t) b, t, ((t) - (b)) >> 10
-#define MLM(b, t) b, t, ((t) - (b)) >> 20
-#define MLG(b, t) b, t, ((t) - (b)) >> 30
-#define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
-
- pr_notice("Virtual kernel memory layout:\n");
-#ifdef CONFIG_KASAN
- pr_notice(" kasan : 0x%16lx - 0x%16lx (%6ld GB)\n",
- MLG(KASAN_SHADOW_START, KASAN_SHADOW_END));
-#endif
- pr_notice(" modules : 0x%16lx - 0x%16lx (%6ld MB)\n",
- MLM(MODULES_VADDR, MODULES_END));
- pr_notice(" vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n",
- MLG(VMALLOC_START, VMALLOC_END));
- pr_notice(" .text : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(_text, _etext));
- pr_notice(" .rodata : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(__start_rodata, __init_begin));
- pr_notice(" .init : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(__init_begin, __init_end));
- pr_notice(" .data : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(_sdata, _edata));
- pr_notice(" .bss : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(__bss_start, __bss_stop));
- pr_notice(" fixed : 0x%16lx - 0x%16lx (%6ld KB)\n",
- MLK(FIXADDR_START, FIXADDR_TOP));
- pr_notice(" PCI I/O : 0x%16lx - 0x%16lx (%6ld MB)\n",
- MLM(PCI_IO_START, PCI_IO_END));
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
- pr_notice(" vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n",
- MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE));
- pr_notice(" 0x%16lx - 0x%16lx (%6ld MB actual)\n",
- MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
- (unsigned long)virt_to_page(high_memory)));
-#endif
- pr_notice(" memory : 0x%16lx - 0x%16lx (%6ld MB)\n",
- MLM(__phys_to_virt(memblock_start_of_DRAM()),
- (unsigned long)high_memory));
-
-#undef MLK
-#undef MLM
-#undef MLK_ROUNDUP
-
/*
* Check boundaries twice: Some fundamental inconsistencies can be
* detected at build time already.
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 267d2b79d52d..b44992ec9643 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -50,6 +50,7 @@
#define NO_CONT_MAPPINGS BIT(1)
u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
u64 kimage_voffset __ro_after_init;
EXPORT_SYMBOL(kimage_voffset);
@@ -525,6 +526,35 @@ static int __init parse_rodata(char *arg)
}
early_param("rodata", parse_rodata);
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __init map_entry_trampoline(void)
+{
+ pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+ phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
+
+ /* The trampoline is always mapped and can therefore be global */
+ pgprot_val(prot) &= ~PTE_NG;
+
+ /* Map only the text into the trampoline page table */
+ memset(tramp_pg_dir, 0, PGD_SIZE);
+ __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
+ prot, pgd_pgtable_alloc, 0);
+
+ /* Map both the text and data into the kernel page table */
+ __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+ extern char __entry_tramp_data_start[];
+
+ __set_fixmap(FIX_ENTRY_TRAMP_DATA,
+ __pa_symbol(__entry_tramp_data_start),
+ PAGE_KERNEL_RO);
+ }
+
+ return 0;
+}
+core_initcall(map_entry_trampoline);
+#endif
+
/*
* Create fine-grained mappings for the kernel.
*/
@@ -570,8 +600,8 @@ static void __init map_kernel(pgd_t *pgd)
* entry instead.
*/
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
- set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START),
- __pud(__pa_symbol(bm_pmd) | PUD_TYPE_TABLE));
+ pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START),
+ lm_alias(bm_pmd));
pud_clear_fixmap();
} else {
BUG();
@@ -612,7 +642,8 @@ void __init paging_init(void)
* allocated with it.
*/
memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
- SWAPPER_DIR_SIZE - PAGE_SIZE);
+ __pa_symbol(swapper_pg_end) - __pa_symbol(swapper_pg_dir)
+ - PAGE_SIZE);
}
/*
@@ -686,7 +717,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
if (!p)
return -ENOMEM;
- set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL));
+ pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL));
} else
vmemmap_verify((pte_t *)pmd, node, addr, next);
} while (addr = next, addr != end);
@@ -879,15 +910,19 @@ int __init arch_ioremap_pmd_supported(void)
int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
{
+ pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
+ pgprot_val(mk_sect_prot(prot)));
BUG_ON(phys & ~PUD_MASK);
- set_pud(pud, __pud(phys | PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))));
+ set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot));
return 1;
}
int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
{
+ pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
+ pgprot_val(mk_sect_prot(prot)));
BUG_ON(phys & ~PMD_MASK);
- set_pmd(pmd, __pmd(phys | PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))));
+ set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot));
return 1;
}
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 371c5f03a170..289f9113a27a 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -26,7 +26,7 @@
#include <asm/page.h>
#include <asm/tlbflush.h>
-static struct kmem_cache *pgd_cache;
+static struct kmem_cache *pgd_cache __ro_after_init;
pgd_t *pgd_alloc(struct mm_struct *mm)
{
@@ -49,6 +49,14 @@ void __init pgd_cache_init(void)
if (PGD_SIZE == PAGE_SIZE)
return;
+#ifdef CONFIG_ARM64_PA_BITS_52
+ /*
+ * With 52-bit physical addresses, the architecture requires the
+ * top-level table to be aligned to at least 64 bytes.
+ */
+ BUILD_BUG_ON(PGD_SIZE < 64);
+#endif
+
/*
* Naturally aligned pgds required by the architecture.
*/
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 95233dfc4c39..9f177aac6390 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -70,7 +70,11 @@ ENTRY(cpu_do_suspend)
mrs x8, mdscr_el1
mrs x9, oslsr_el1
mrs x10, sctlr_el1
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
mrs x11, tpidr_el1
+alternative_else
+ mrs x11, tpidr_el2
+alternative_endif
mrs x12, sp_el0
stp x2, x3, [x0]
stp x4, xzr, [x0, #16]
@@ -116,7 +120,11 @@ ENTRY(cpu_do_resume)
msr mdscr_el1, x10
msr sctlr_el1, x12
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
msr tpidr_el1, x13
+alternative_else
+ msr tpidr_el2, x13
+alternative_endif
msr sp_el0, x14
/*
* Restore oslsr_el1 by writing oslar_el1
@@ -124,6 +132,11 @@ ENTRY(cpu_do_resume)
ubfx x11, x11, #1, #1
msr oslar_el1, x11
reset_pmuserenr_el0 x0 // Disable PMU access from EL0
+
+alternative_if ARM64_HAS_RAS_EXTN
+ msr_s SYS_DISR_EL1, xzr
+alternative_else_nop_endif
+
isb
ret
ENDPROC(cpu_do_resume)
@@ -138,13 +151,18 @@ ENDPROC(cpu_do_resume)
* - pgd_phys - physical address of new TTB
*/
ENTRY(cpu_do_switch_mm)
- pre_ttbr0_update_workaround x0, x2, x3
+ mrs x2, ttbr1_el1
mmid x1, x1 // get mm->context.id
- bfi x0, x1, #48, #16 // set the ASID
- msr ttbr0_el1, x0 // set TTBR0
+ phys_to_ttbr x0, x3
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ bfi x3, x1, #48, #16 // set the ASID field in TTBR0
+#endif
+ bfi x2, x1, #48, #16 // set the ASID
+ msr ttbr1_el1, x2 // in TTBR1 (since TCR.A1 is set)
isb
- post_ttbr0_update_workaround
- ret
+ msr ttbr0_el1, x3 // now update TTBR0
+ isb
+ b post_ttbr_update_workaround // Back to C code...
ENDPROC(cpu_do_switch_mm)
.pushsection ".idmap.text", "ax"
@@ -158,14 +176,16 @@ ENTRY(idmap_cpu_replace_ttbr1)
save_and_disable_daif flags=x2
adrp x1, empty_zero_page
- msr ttbr1_el1, x1
+ phys_to_ttbr x1, x3
+ msr ttbr1_el1, x3
isb
tlbi vmalle1
dsb nsh
isb
- msr ttbr1_el1, x0
+ phys_to_ttbr x0, x3
+ msr ttbr1_el1, x3
isb
restore_daif x2
@@ -214,25 +234,19 @@ ENTRY(__cpu_setup)
/*
* Prepare SCTLR
*/
- adr x5, crval
- ldp w5, w6, [x5]
- mrs x0, sctlr_el1
- bic x0, x0, x5 // clear bits
- orr x0, x0, x6 // set bits
+ mov_q x0, SCTLR_EL1_SET
/*
* Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
* both user and kernel.
*/
ldr x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
- TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0
+ TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0 | TCR_A1
tcr_set_idmap_t0sz x10, x9
/*
- * Read the PARange bits from ID_AA64MMFR0_EL1 and set the IPS bits in
- * TCR_EL1.
+ * Set the IPS bits in TCR_EL1.
*/
- mrs x9, ID_AA64MMFR0_EL1
- bfi x10, x9, #32, #3
+ tcr_compute_pa_size x10, #TCR_IPS_SHIFT, x5, x6
#ifdef CONFIG_ARM64_HW_AFDBM
/*
* Hardware update of the Access and Dirty bits.
@@ -249,21 +263,3 @@ ENTRY(__cpu_setup)
msr tcr_el1, x10
ret // return to head.S
ENDPROC(__cpu_setup)
-
- /*
- * We set the desired value explicitly, including those of the
- * reserved bits. The values of bits EE & E0E were set early in
- * el2_setup, which are left untouched below.
- *
- * n n T
- * U E WT T UD US IHBS
- * CE0 XWHW CZ ME TEEA S
- * .... .IEE .... NEAI TE.I ..AD DEN0 ACAM
- * 0011 0... 1101 ..0. ..0. 10.. .0.. .... < hardware reserved
- * .... .1.. .... 01.1 11.1 ..01 0.01 1101 < software settings
- */
- .type crval, #object
-crval:
- .word 0xfcffffff // clear
- .word 0x34d5d91d // set
- .popsection
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ba38d403abb2..bb32f7f6dd0f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -148,7 +148,8 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
/* Stack must be multiples of 16B */
#define STACK_ALIGN(sz) (((sz) + 15) & ~15)
-#define PROLOGUE_OFFSET 8
+/* Tail call offset to jump into */
+#define PROLOGUE_OFFSET 7
static int build_prologue(struct jit_ctx *ctx)
{
@@ -200,19 +201,19 @@ static int build_prologue(struct jit_ctx *ctx)
/* Initialize tail_call_cnt */
emit(A64_MOVZ(1, tcc, 0, 0), ctx);
- /* 4 byte extra for skb_copy_bits buffer */
- ctx->stack_size = prog->aux->stack_depth + 4;
- ctx->stack_size = STACK_ALIGN(ctx->stack_size);
-
- /* Set up function call stack */
- emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
-
cur_offset = ctx->idx - idx0;
if (cur_offset != PROLOGUE_OFFSET) {
pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
cur_offset, PROLOGUE_OFFSET);
return -1;
}
+
+ /* 4 byte extra for skb_copy_bits buffer */
+ ctx->stack_size = prog->aux->stack_depth + 4;
+ ctx->stack_size = STACK_ALIGN(ctx->stack_size);
+
+ /* Set up function call stack */
+ emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
return 0;
}
@@ -260,11 +261,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
emit(A64_LDR64(prg, tmp, prg), ctx);
emit(A64_CBZ(1, prg, jmp_offset), ctx);
- /* goto *(prog->bpf_func + prologue_size); */
+ /* goto *(prog->bpf_func + prologue_offset); */
off = offsetof(struct bpf_prog, bpf_func);
emit_a64_mov_i64(tmp, off, ctx);
emit(A64_LDR64(tmp, prg, tmp), ctx);
emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
+ emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
emit(A64_BR(tmp), ctx);
/* out: */
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 401ceb71540c..c5f05c4a4d00 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -101,12 +101,12 @@ ENTRY(privcmd_call)
* need the explicit uaccess_enable/disable if the TTBR0 PAN emulation
* is enabled (it implies that hardware UAO and PAN disabled).
*/
- uaccess_ttbr0_enable x6, x7
+ uaccess_ttbr0_enable x6, x7, x8
hvc XEN_IMM
/*
* Disable userspace access from kernel once the hyp call completed.
*/
- uaccess_ttbr0_disable x6
+ uaccess_ttbr0_disable x6, x7
ret
ENDPROC(privcmd_call);
diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h
index 2966b93850a1..a5aeab4e5f2d 100644
--- a/arch/blackfin/include/asm/thread_info.h
+++ b/arch/blackfin/include/asm/thread_info.h
@@ -56,8 +56,6 @@ struct thread_info {
.cpu = 0, \
.preempt_count = INIT_PREEMPT_COUNT, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
/* Given a task stack pointer, you can find its corresponding
* thread_info structure just by masking it to the THREAD_SIZE
diff --git a/arch/blackfin/include/uapi/asm/Kbuild b/arch/blackfin/include/uapi/asm/Kbuild
index aa624b4ab655..2240b38c2915 100644
--- a/arch/blackfin/include/uapi/asm/Kbuild
+++ b/arch/blackfin/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += ioctl.h
generic-y += ipcbuf.h
diff --git a/arch/blackfin/include/uapi/asm/siginfo.h b/arch/blackfin/include/uapi/asm/siginfo.h
index b1db506c8d2e..2dd8c9c39248 100644
--- a/arch/blackfin/include/uapi/asm/siginfo.h
+++ b/arch/blackfin/include/uapi/asm/siginfo.h
@@ -11,40 +11,6 @@
#include <linux/types.h>
#include <asm-generic/siginfo.h>
-#define UID16_SIGINFO_COMPAT_NEEDED
-
#define si_uid16 _sifields._kill._uid
-#define ILL_ILLPARAOP 2 /* illegal opcode combine ********** */
-#define ILL_ILLEXCPT 4 /* unrecoverable exception ********** */
-#define ILL_CPLB_VI 9 /* D/I CPLB protect violation ******** */
-#define ILL_CPLB_MISS 10 /* D/I CPLB miss ******** */
-#define ILL_CPLB_MULHIT 11 /* D/I CPLB multiple hit ******** */
-#undef NSIGILL
-#define NSIGILL 11
-
-/*
- * SIGBUS si_codes
- */
-#define BUS_OPFETCH 4 /* error from instruction fetch ******** */
-#undef NSIGBUS
-#define NSIGBUS 4
-
-/*
- * SIGTRAP si_codes
- */
-#define TRAP_STEP 1 /* single-step breakpoint************* */
-#define TRAP_TRACEFLOW 2 /* trace buffer overflow ************* */
-#define TRAP_WATCHPT 3 /* watchpoint match ************* */
-#define TRAP_ILLTRAP 4 /* illegal trap ************* */
-#undef NSIGTRAP
-#define NSIGTRAP 4
-
-/*
- * SIGSEGV si_codes
- */
-#define SEGV_STACKFLOW 3 /* stack overflow */
-#undef NSIGSEGV
-#define NSIGSEGV 3
-
#endif /* _UAPI_BFIN_SIGINFO_H */
diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h
index acc70c135ab8..59a5697fe0f3 100644
--- a/arch/c6x/include/asm/thread_info.h
+++ b/arch/c6x/include/asm/thread_info.h
@@ -60,9 +60,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* get the thread information struct of current task */
static inline __attribute__((const))
struct thread_info *current_thread_info(void)
diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild
index 67ee896a76a7..26644e15d854 100644
--- a/arch/c6x/include/uapi/asm/Kbuild
+++ b/arch/c6x/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 124dd5ec7f65..ee4d8b03d048 100644
--- a/arch/cris/include/asm/processor.h
+++ b/arch/cris/include/asm/processor.h
@@ -26,13 +26,6 @@ struct task_struct;
*/
#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3))
-/* THREAD_SIZE is the size of the thread_info/kernel_stack combo.
- * normally, the stack is found by doing something like p + THREAD_SIZE
- * in CRIS, a page is 8192 bytes, which seems like a sane size
- */
-#define THREAD_SIZE PAGE_SIZE
-#define THREAD_SIZE_ORDER (0)
-
/*
* At user->kernel entry, the pt_regs struct is stacked on the top of the kernel-stack.
* This macro allows us to find those regs for a task.
@@ -59,8 +52,6 @@ static inline void release_thread(struct task_struct *dead_task)
/* Nothing needs to be done. */
}
-#define init_stack (init_thread_union.stack)
-
#define cpu_relax() barrier()
void default_idle(void);
diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h
index 472830c90997..996fef3be1d5 100644
--- a/arch/cris/include/asm/thread_info.h
+++ b/arch/cris/include/asm/thread_info.h
@@ -20,6 +20,13 @@
#endif
+/* THREAD_SIZE is the size of the thread_info/kernel_stack combo.
+ * normally, the stack is found by doing something like p + THREAD_SIZE
+ * in CRIS, a page is 8192 bytes, which seems like a sane size
+ */
+#define THREAD_SIZE PAGE_SIZE
+#define THREAD_SIZE_ORDER (0)
+
/*
* low level task data that entry.S needs immediate access to
* - this struct should fit entirely inside of one cache line
@@ -56,8 +63,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-
#endif /* !__ASSEMBLY__ */
/*
diff --git a/arch/cris/include/uapi/asm/Kbuild b/arch/cris/include/uapi/asm/Kbuild
index 3687b54bb18e..3470c6e9c7b9 100644
--- a/arch/cris/include/uapi/asm/Kbuild
+++ b/arch/cris/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S
index 6d1dbc1ba767..9b232e0f673e 100644
--- a/arch/cris/kernel/vmlinux.lds.S
+++ b/arch/cris/kernel/vmlinux.lds.S
@@ -11,6 +11,7 @@
#include <asm-generic/vmlinux.lds.h>
#include <asm/page.h>
+#include <asm/thread_info.h>
#ifdef CONFIG_ETRAX_VMEM_SIZE
#define __CONFIG_ETRAX_VMEM_SIZE CONFIG_ETRAX_VMEM_SIZE
diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h
index ccba3b6ce918..0f950845fad9 100644
--- a/arch/frv/include/asm/thread_info.h
+++ b/arch/frv/include/asm/thread_info.h
@@ -64,9 +64,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
register struct thread_info *__current_thread_info asm("gr15");
diff --git a/arch/frv/include/uapi/asm/Kbuild b/arch/frv/include/uapi/asm/Kbuild
index b15bf6bc0e94..5354b0f84d41 100644
--- a/arch/frv/include/uapi/asm/Kbuild
+++ b/arch/frv/include/uapi/asm/Kbuild
@@ -1,2 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += siginfo.h
+generic-y += bpf_perf_event.h
diff --git a/arch/frv/include/uapi/asm/siginfo.h b/arch/frv/include/uapi/asm/siginfo.h
deleted file mode 100644
index 4c8c975747ac..000000000000
--- a/arch/frv/include/uapi/asm/siginfo.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_SIGINFO_H
-#define _ASM_SIGINFO_H
-
-#include <linux/types.h>
-#include <asm-generic/siginfo.h>
-
-#define FPE_MDAOVF 9 /* media overflow */
-#undef NSIGFPE
-#define NSIGFPE 9
-
-#endif
-
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
index 072b92c0d8b5..0cdaa302d3d2 100644
--- a/arch/h8300/include/asm/thread_info.h
+++ b/arch/h8300/include/asm/thread_info.h
@@ -46,9 +46,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
static inline struct thread_info *current_thread_info(void)
{
diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild
index 187aed820e71..2f65f78792cb 100644
--- a/arch/h8300/include/uapi/asm/Kbuild
+++ b/arch/h8300/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h
index b80fe1db7b64..f41f9c6f0e31 100644
--- a/arch/hexagon/include/asm/thread_info.h
+++ b/arch/hexagon/include/asm/thread_info.h
@@ -84,9 +84,6 @@ struct thread_info {
.regs = NULL, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* Tacky preprocessor trickery */
#define qqstr(s) qstr(s)
#define qstr(s) #s
diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild
index cb5df3aad3a8..41a176dbb53e 100644
--- a/arch/hexagon/include/uapi/asm/Kbuild
+++ b/arch/hexagon/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
index ec87e67feb19..ad69d181c939 100644
--- a/arch/hexagon/kernel/vmlinux.lds.S
+++ b/arch/hexagon/kernel/vmlinux.lds.S
@@ -22,6 +22,8 @@
#include <asm/asm-offsets.h> /* Most of the kernel defines are here */
#include <asm/mem-layout.h> /* except for page_offset */
#include <asm/cache.h> /* and now we're pulling cache line size */
+#include <asm/thread_info.h> /* and we need THREAD_SIZE too */
+
OUTPUT_ARCH(hexagon)
ENTRY(stext)
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 49583c5a5d44..315c51f58811 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -43,7 +43,7 @@ config IA64
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select GENERIC_IOMAP
select GENERIC_SMP_IDLE_THREAD
- select ARCH_INIT_TASK
+ select ARCH_TASK_STRUCT_ON_STACK
select ARCH_TASK_STRUCT_ALLOCATOR
select ARCH_THREAD_STACK_ALLOCATOR
select ARCH_CLOCKSOURCE_DATA
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index c100d780f1eb..2dd7f519ad0b 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -42,7 +42,7 @@ $(error Sorry, you need a newer version of the assember, one that is built from
endif
KBUILD_CFLAGS += $(cflags-y)
-head-y := arch/ia64/kernel/head.o arch/ia64/kernel/init_task.o
+head-y := arch/ia64/kernel/head.o
libs-y += arch/ia64/lib/
core-y += arch/ia64/kernel/ arch/ia64/mm/
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 28e02c99be6d..762eeb0fcc1d 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -65,29 +65,30 @@ ia64_atomic_fetch_##op (int i, atomic_t *v) \
ATOMIC_OPS(add, +)
ATOMIC_OPS(sub, -)
-#define atomic_add_return(i,v) \
+#ifdef __OPTIMIZE__
+#define __ia64_atomic_const(i) __builtin_constant_p(i) ? \
+ ((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 || \
+ (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0
+
+#define atomic_add_return(i, v) \
({ \
- int __ia64_aar_i = (i); \
- (__builtin_constant_p(i) \
- && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \
- || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \
- || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \
- || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \
- ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \
- : ia64_atomic_add(__ia64_aar_i, v); \
+ int __i = (i); \
+ static const int __ia64_atomic_p = __ia64_atomic_const(i); \
+ __ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) : \
+ ia64_atomic_add(__i, v); \
})
-#define atomic_sub_return(i,v) \
+#define atomic_sub_return(i, v) \
({ \
- int __ia64_asr_i = (i); \
- (__builtin_constant_p(i) \
- && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \
- || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \
- || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \
- || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \
- ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \
- : ia64_atomic_sub(__ia64_asr_i, v); \
+ int __i = (i); \
+ static const int __ia64_atomic_p = __ia64_atomic_const(i); \
+ __ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) : \
+ ia64_atomic_sub(__i, v); \
})
+#else
+#define atomic_add_return(i, v) ia64_atomic_add(i, v)
+#define atomic_sub_return(i, v) ia64_atomic_sub(i, v)
+#endif
#define atomic_fetch_add(i,v) \
({ \
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index 1d172a4119a7..64a1011f6812 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -12,6 +12,8 @@
#include <asm/processor.h>
#include <asm/ptrace.h>
+#define THREAD_SIZE KERNEL_STACK_SIZE
+
#ifndef __ASSEMBLY__
/*
@@ -41,8 +43,6 @@ struct thread_info {
#endif
};
-#define THREAD_SIZE KERNEL_STACK_SIZE
-
#define INIT_THREAD_INFO(tsk) \
{ \
.task = &tsk, \
diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild
index 4c9825edd4a3..c0527cfc48f0 100644
--- a/arch/ia64/include/uapi/asm/Kbuild
+++ b/arch/ia64/include/uapi/asm/Kbuild
@@ -1,5 +1,6 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += kvm_para.h
generic-y += poll.h
diff --git a/arch/ia64/include/uapi/asm/siginfo.h b/arch/ia64/include/uapi/asm/siginfo.h
index f3a02a10c3a3..5aa454ed89db 100644
--- a/arch/ia64/include/uapi/asm/siginfo.h
+++ b/arch/ia64/include/uapi/asm/siginfo.h
@@ -11,77 +11,8 @@
#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
-#define HAVE_ARCH_SIGINFO_T
-#define HAVE_ARCH_COPY_SIGINFO_TO_USER
-
#include <asm-generic/siginfo.h>
-typedef struct siginfo {
- int si_signo;
- int si_errno;
- int si_code;
- int __pad0;
-
- union {
- int _pad[SI_PAD_SIZE];
-
- /* kill() */
- struct {
- pid_t _pid; /* sender's pid */
- uid_t _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- char _pad[sizeof(__ARCH_SI_UID_T) - sizeof(int)];
- sigval_t _sigval; /* must overlay ._rt._sigval! */
- int _sys_private; /* not to be passed to user */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- pid_t _pid; /* sender's pid */
- uid_t _uid; /* sender's uid */
- sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- pid_t _pid; /* which child */
- uid_t _uid; /* sender's uid */
- int _status; /* exit code */
- clock_t _utime;
- clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- void __user *_addr; /* faulting insn/memory ref. */
- int _imm; /* immediate value for "break" */
- unsigned int _flags; /* see below */
- unsigned long _isr; /* isr */
- short _addr_lsb; /* lsb of faulting address */
- union {
- /* used when si_code=SEGV_BNDERR */
- struct {
- void __user *_lower;
- void __user *_upper;
- } _addr_bnd;
- /* used when si_code=SEGV_PKUERR */
- __u32 _pkey;
- };
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- long _band; /* POLL_IN, POLL_OUT, POLL_MSG (XPG requires a "long") */
- int _fd;
- } _sigpoll;
- } _sifields;
-} siginfo_t;
-
#define si_imm _sifields._sigfault._imm /* as per UNIX SysV ABI spec */
#define si_flags _sifields._sigfault._flags
/*
@@ -97,37 +28,10 @@ typedef struct siginfo {
#define __ISR_VALID (1 << __ISR_VALID_BIT)
/*
- * SIGILL si_codes
- */
-#define ILL_BADIADDR 9 /* unimplemented instruction address */
-#define __ILL_BREAK 10 /* illegal break */
-#define __ILL_BNDMOD 11 /* bundle-update (modification) in progress */
-#undef NSIGILL
-#define NSIGILL 11
-
-/*
* SIGFPE si_codes
*/
#ifdef __KERNEL__
#define FPE_FIXME 0 /* Broken dup of SI_USER */
#endif /* __KERNEL__ */
-#define __FPE_DECOVF 9 /* decimal overflow */
-#define __FPE_DECDIV 10 /* decimal division by zero */
-#define __FPE_DECERR 11 /* packed decimal error */
-#define __FPE_INVASC 12 /* invalid ASCII digit */
-#define __FPE_INVDEC 13 /* invalid decimal digit */
-#undef NSIGFPE
-#define NSIGFPE 13
-
-/*
- * SIGSEGV si_codes
- */
-#define __SEGV_PSTKOVF 4 /* paragraph stack overflow */
-#undef NSIGSEGV
-#define NSIGSEGV 4
-
-#undef NSIGTRAP
-#define NSIGTRAP 4
-
#endif /* _UAPI_ASM_IA64_SIGINFO_H */
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 14ad79f394e5..0b4c65a1af25 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -7,7 +7,7 @@ ifdef CONFIG_DYNAMIC_FTRACE
CFLAGS_REMOVE_ftrace.o = -pg
endif
-extra-y := head.o init_task.o vmlinux.lds
+extra-y := head.o vmlinux.lds
obj-y := entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \
irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o \
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 1d29b2f8726b..1dacbf5e9e09 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -504,6 +504,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
if (!(ma->flags & ACPI_SRAT_MEM_ENABLED))
return -1;
+ if (num_node_memblks >= NR_NODE_MEMBLKS) {
+ pr_err("NUMA: too many memblk ranges\n");
+ return -EINVAL;
+ }
+
/* record this node in proximity bitmap */
pxm_bit_set(pxm);
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
deleted file mode 100644
index 8df9245e29d9..000000000000
--- a/arch/ia64/kernel/init_task.c
+++ /dev/null
@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This is where we statically allocate and initialize the initial
- * task.
- *
- * Copyright (C) 1999, 2002-2003 Hewlett-Packard Co
- * David Mosberger-Tang <davidm@hpl.hp.com>
- */
-
-#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/init_task.h>
-#include <linux/mqueue.h>
-
-#include <linux/uaccess.h>
-#include <asm/pgtable.h>
-
-static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
-static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-/*
- * Initial task structure.
- *
- * We need to make sure that this is properly aligned due to the way process stacks are
- * handled. This is done by having a special ".data..init_task" section...
- */
-#define init_thread_info init_task_mem.s.thread_info
-#define init_stack init_task_mem.stack
-
-union {
- struct {
- struct task_struct task;
- struct thread_info thread_info;
- } s;
- unsigned long stack[KERNEL_STACK_SIZE/sizeof (unsigned long)];
-} init_task_mem asm ("init_task") __init_task_data =
- {{
- .task = INIT_TASK(init_task_mem.s.task),
- .thread_info = INIT_THREAD_INFO(init_task_mem.s.task)
-}};
-
-EXPORT_SYMBOL(init_task);
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index a254cc98f95c..54547c7cf8a2 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -105,58 +105,6 @@ restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr)
return err;
}
-int
-copy_siginfo_to_user (siginfo_t __user *to, const siginfo_t *from)
-{
- if (!access_ok(VERIFY_WRITE, to, sizeof(siginfo_t)))
- return -EFAULT;
- if (from->si_code < 0) {
- if (__copy_to_user(to, from, sizeof(siginfo_t)))
- return -EFAULT;
- return 0;
- } else {
- int err;
-
- /*
- * If you change siginfo_t structure, please be sure this code is fixed
- * accordingly. It should never copy any pad contained in the structure
- * to avoid security leaks, but must copy the generic 3 ints plus the
- * relevant union member.
- */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user(from->si_code, &to->si_code);
- switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_FAULT:
- err |= __put_user(from->si_flags, &to->si_flags);
- err |= __put_user(from->si_isr, &to->si_isr);
- case SIL_POLL:
- err |= __put_user(from->si_addr, &to->si_addr);
- err |= __put_user(from->si_imm, &to->si_imm);
- break;
- case SIL_TIMER:
- err |= __put_user(from->si_tid, &to->si_tid);
- err |= __put_user(from->si_overrun, &to->si_overrun);
- err |= __put_user(from->si_ptr, &to->si_ptr);
- break;
- case SIL_RT:
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_ptr, &to->si_ptr);
- break;
- case SIL_CHLD:
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- err |= __put_user(from->si_status, &to->si_status);
- case SIL_KILL:
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_pid, &to->si_pid);
- break;
- }
- return err;
- }
-}
-
long
ia64_rt_sigreturn (struct sigscratch *scr)
{
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index c6ecb97151a2..9025699049ca 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -88,7 +88,7 @@ void vtime_flush(struct task_struct *tsk)
}
if (ti->softirq_time) {
- delta = cycle_to_nsec(ti->softirq_time));
+ delta = cycle_to_nsec(ti->softirq_time);
account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ);
}
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 58db59da0bd8..b0b2070e0591 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -3,6 +3,7 @@
#include <asm/cache.h>
#include <asm/ptrace.h>
#include <asm/pgtable.h>
+#include <asm/thread_info.h>
#include <asm-generic/vmlinux.lds.h>
diff --git a/arch/m32r/include/asm/thread_info.h b/arch/m32r/include/asm/thread_info.h
index b3a215b0ce0a..ba00f1032587 100644
--- a/arch/m32r/include/asm/thread_info.h
+++ b/arch/m32r/include/asm/thread_info.h
@@ -56,9 +56,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
static inline struct thread_info *current_thread_info(void)
{
diff --git a/arch/m32r/include/uapi/asm/Kbuild b/arch/m32r/include/uapi/asm/Kbuild
index 21f241553a2e..c3df55aeefe7 100644
--- a/arch/m32r/include/uapi/asm/Kbuild
+++ b/arch/m32r/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += kvm_para.h
generic-y += poll.h
generic-y += siginfo.h
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index cb79fba79d43..b88a8dd14933 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -122,7 +122,6 @@ void abort(void)
/* if that doesn't kill us, halt */
panic("Oops failed to kill thread");
}
-EXPORT_SYMBOL(abort);
void __init trap_init(void)
{
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 5b5fa9831b4d..e0b285e1e75f 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -454,7 +454,6 @@ CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PPS_CLIENT_PARPORT=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FB_CIRRUS=y
CONFIG_FB_AMIGA=y
@@ -595,6 +594,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -624,6 +624,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -653,3 +654,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 72a7764b74ed..3281026a3e15 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -422,7 +422,6 @@ CONFIG_NTP_PPS=y
CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
@@ -554,6 +553,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -583,6 +583,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -612,3 +613,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 884b43a2f0d9..e943fad480cf 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -437,7 +437,6 @@ CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PPS_CLIENT_PARPORT=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FB_ATARI=y
CONFIG_FRAMEBUFFER_CONSOLE=y
@@ -576,6 +575,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -605,6 +605,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -634,3 +635,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index fcfa60d31499..700c2310c336 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -420,7 +420,6 @@ CONFIG_NTP_PPS=y
CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
@@ -546,6 +545,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -575,6 +575,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -604,3 +605,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 9d597bbbbbfe..271d57fa4301 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -425,7 +425,6 @@ CONFIG_NTP_PPS=y
CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
@@ -556,6 +555,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -585,6 +585,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -614,3 +615,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 45da20d1286c..88761b867975 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -447,7 +447,6 @@ CONFIG_NTP_PPS=y
CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FB_VALKYRIE=y
CONFIG_FB_MAC=y
@@ -578,6 +577,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -607,6 +607,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -636,3 +637,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index fda880c10861..7cb35dadf03b 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -504,7 +504,6 @@ CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PPS_CLIENT_PARPORT=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FB_CIRRUS=y
CONFIG_FB_AMIGA=y
@@ -658,6 +657,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -687,6 +687,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -716,3 +717,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 7d5e4863efec..b139d7b68393 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -420,7 +420,6 @@ CONFIG_NTP_PPS=y
CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
@@ -546,6 +545,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -575,6 +575,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -604,3 +605,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 7763b71a9c49..398346138769 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -420,7 +420,6 @@ CONFIG_NTP_PPS=y
CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
@@ -546,6 +545,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -575,6 +575,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -604,3 +605,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 17eaebfa3e19..14c608326f6d 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -437,7 +437,6 @@ CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PPS_CLIENT_PARPORT=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
@@ -569,6 +568,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -598,6 +598,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -627,3 +628,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/stmark2_defconfig b/arch/m68k/configs/stmark2_defconfig
index 55e55dbc2fb6..3d07b1de7eb0 100644
--- a/arch/m68k/configs/stmark2_defconfig
+++ b/arch/m68k/configs/stmark2_defconfig
@@ -5,7 +5,6 @@ CONFIG_SYSVIPC=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_NAMESPACES=y
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../uClinux-dist/romfs"
# CONFIG_RD_BZIP2 is not set
# CONFIG_RD_LZMA is not set
# CONFIG_RD_XZ is not set
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index d1cb7a04ae1d..97dec0bf52f1 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -419,7 +419,6 @@ CONFIG_NTP_PPS=y
CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
@@ -548,6 +547,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -576,6 +576,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -605,3 +606,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index ea3a331c62d5..56df28d6d91d 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -419,7 +419,6 @@ CONFIG_NTP_PPS=y
CONFIG_PPS_CLIENT_LDISC=m
CONFIG_PTP_1588_CLOCK=m
# CONFIG_HWMON is not set
-# CONFIG_RC_CORE is not set
CONFIG_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
@@ -548,6 +547,7 @@ CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_FIND_BIT=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_SYSCTL=m
CONFIG_TEST_UDELAY=m
@@ -577,6 +577,7 @@ CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -606,3 +607,4 @@ CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_STRING_SELFTEST=m
diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
index f42c27400dbc..9b840c03ebb7 100644
--- a/arch/m68k/include/asm/macintosh.h
+++ b/arch/m68k/include/asm/macintosh.h
@@ -33,7 +33,7 @@ struct mac_model
char ide_type;
char scc_type;
char ether_type;
- char nubus_type;
+ char expansion_type;
char floppy_type;
};
@@ -73,8 +73,11 @@ struct mac_model
#define MAC_ETHER_SONIC 1
#define MAC_ETHER_MACE 2
-#define MAC_NO_NUBUS 0
-#define MAC_NUBUS 1
+#define MAC_EXP_NONE 0
+#define MAC_EXP_PDS 1 /* Accepts only a PDS card */
+#define MAC_EXP_NUBUS 2 /* Accepts only NuBus card(s) */
+#define MAC_EXP_PDS_NUBUS 3 /* Accepts PDS card and/or NuBus card(s) */
+#define MAC_EXP_PDS_COMM 4 /* Accepts PDS card or Comm Slot card */
#define MAC_FLOPPY_IWM 0
#define MAC_FLOPPY_SWIM_ADDR1 1
diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h
index 928035591f2e..015f1ca38305 100644
--- a/arch/m68k/include/asm/thread_info.h
+++ b/arch/m68k/include/asm/thread_info.h
@@ -41,8 +41,6 @@ struct thread_info {
.preempt_count = INIT_PREEMPT_COUNT, \
}
-#define init_stack (init_thread_union.stack)
-
#ifndef __ASSEMBLY__
/* how to get the thread information struct from C */
static inline struct thread_info *current_thread_info(void)
@@ -58,8 +56,6 @@ static inline struct thread_info *current_thread_info(void)
}
#endif
-#define init_thread_info (init_thread_union.thread_info)
-
/* entry.S relies on these definitions!
* bits 0-7 are tested at every exception exit
* bits 8-15 are also tested at syscall exit
diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild
index 3717b64a620d..c2e26a44c482 100644
--- a/arch/m68k/include/uapi/asm/Kbuild
+++ b/arch/m68k/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += ioctl.h
generic-y += ipcbuf.h
diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds
index 3aa571a513b5..cf6edda38971 100644
--- a/arch/m68k/kernel/vmlinux-nommu.lds
+++ b/arch/m68k/kernel/vmlinux-nommu.lds
@@ -45,6 +45,8 @@ SECTIONS {
.text : {
HEAD_TEXT
TEXT_TEXT
+ IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
SCHED_TEXT
CPUIDLE_TEXT
LOCK_TEXT
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 89172b8974b9..625a5785804f 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -16,6 +16,8 @@ SECTIONS
.text : {
HEAD_TEXT
TEXT_TEXT
+ IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
SCHED_TEXT
CPUIDLE_TEXT
LOCK_TEXT
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index 293990efc917..9868270b0984 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -16,6 +16,8 @@ SECTIONS
.text : {
HEAD_TEXT
TEXT_TEXT
+ IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
SCHED_TEXT
CPUIDLE_TEXT
LOCK_TEXT
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 16cd5cea5207..d3d435248a24 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -212,7 +212,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_II,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_IWM,
},
@@ -227,7 +227,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_II,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_IWM,
}, {
.ident = MAC_MODEL_IIX,
@@ -236,7 +236,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_II,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_IICX,
@@ -245,7 +245,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_II,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_SE30,
@@ -254,7 +254,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_II,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
@@ -272,7 +272,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_IIFX,
@@ -281,7 +281,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_IIFX,
.scc_type = MAC_SCC_IOP,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_IOP,
}, {
.ident = MAC_MODEL_IISI,
@@ -290,7 +290,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_IIVI,
@@ -299,7 +299,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_IIVX,
@@ -308,7 +308,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
@@ -323,7 +323,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_CCL,
@@ -332,7 +331,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_CCLII,
@@ -341,7 +340,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
@@ -356,7 +355,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_LCII,
@@ -365,7 +364,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_LCIII,
@@ -374,7 +373,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
@@ -395,7 +394,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_Q605_ACC,
@@ -404,7 +403,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_Q610,
@@ -414,7 +413,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_QUADRA,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_Q630,
@@ -424,8 +423,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA,
.ide_type = MAC_IDE_QUADRA,
.scc_type = MAC_SCC_QUADRA,
- .ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_COMM,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_Q650,
@@ -435,7 +433,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_QUADRA,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
},
/* The Q700 does have a NS Sonic */
@@ -447,7 +445,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA2,
.scc_type = MAC_SCC_QUADRA,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_Q800,
@@ -457,7 +455,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_QUADRA,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_Q840,
@@ -467,7 +465,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA3,
.scc_type = MAC_SCC_PSC,
.ether_type = MAC_ETHER_MACE,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_AV,
}, {
.ident = MAC_MODEL_Q900,
@@ -477,7 +475,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA2,
.scc_type = MAC_SCC_IOP,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_IOP,
}, {
.ident = MAC_MODEL_Q950,
@@ -487,7 +485,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA2,
.scc_type = MAC_SCC_IOP,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_IOP,
},
@@ -502,7 +500,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_P475,
@@ -511,7 +509,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_P475F,
@@ -520,7 +518,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_P520,
@@ -529,7 +527,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_P550,
@@ -538,7 +536,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
/* These have the comm slot, and therefore possibly SONIC ethernet */
@@ -549,8 +547,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_II,
- .ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_COMM,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_P588,
@@ -560,8 +557,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA,
.ide_type = MAC_IDE_QUADRA,
.scc_type = MAC_SCC_II,
- .ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_COMM,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_TV,
@@ -570,7 +566,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_P600,
@@ -579,7 +574,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_LC,
.scc_type = MAC_SCC_II,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
@@ -596,7 +591,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_QUADRA,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_C650,
@@ -606,7 +601,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA,
.scc_type = MAC_SCC_QUADRA,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR1,
}, {
.ident = MAC_MODEL_C660,
@@ -616,7 +611,7 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_QUADRA3,
.scc_type = MAC_SCC_PSC,
.ether_type = MAC_ETHER_MACE,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_PDS_NUBUS,
.floppy_type = MAC_FLOPPY_AV,
},
@@ -633,7 +628,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB145,
@@ -642,7 +636,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB150,
@@ -652,7 +645,6 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_OLD,
.ide_type = MAC_IDE_PB,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB160,
@@ -661,7 +653,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB165,
@@ -670,7 +661,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB165C,
@@ -679,7 +669,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB170,
@@ -688,7 +677,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB180,
@@ -697,7 +685,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB180C,
@@ -706,7 +693,6 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_QUADRA,
.scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB190,
@@ -716,7 +702,6 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_LATE,
.ide_type = MAC_IDE_BABOON,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB520,
@@ -726,7 +711,6 @@ static struct mac_model mac_data_table[] = {
.scsi_type = MAC_SCSI_LATE,
.scc_type = MAC_SCC_QUADRA,
.ether_type = MAC_ETHER_SONIC,
- .nubus_type = MAC_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
@@ -743,7 +727,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_DUO,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB230,
@@ -752,7 +736,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_DUO,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB250,
@@ -761,7 +745,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_DUO,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB270C,
@@ -770,7 +754,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_DUO,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB280,
@@ -779,7 +763,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_DUO,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
}, {
.ident = MAC_MODEL_PB280C,
@@ -788,7 +772,7 @@ static struct mac_model mac_data_table[] = {
.via_type = MAC_VIA_IICI,
.scsi_type = MAC_SCSI_DUO,
.scc_type = MAC_SCC_QUADRA,
- .nubus_type = MAC_NUBUS,
+ .expansion_type = MAC_EXP_NUBUS,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
@@ -1100,14 +1084,12 @@ int __init mac_platform_init(void)
* Ethernet device
*/
- switch (macintosh_config->ether_type) {
- case MAC_ETHER_SONIC:
+ if (macintosh_config->ether_type == MAC_ETHER_SONIC ||
+ macintosh_config->expansion_type == MAC_EXP_PDS_COMM)
platform_device_register_simple("macsonic", -1, NULL, 0);
- break;
- case MAC_ETHER_MACE:
+
+ if (macintosh_config->ether_type == MAC_ETHER_MACE)
platform_device_register_simple("macmace", -1, NULL, 0);
- break;
- }
return 0;
}
diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
index 3f81892527ad..921e6c092f2c 100644
--- a/arch/m68k/mac/oss.c
+++ b/arch/m68k/mac/oss.c
@@ -53,56 +53,41 @@ void __init oss_init(void)
}
/*
- * Handle miscellaneous OSS interrupts.
+ * Handle OSS interrupts.
+ * XXX how do you clear a pending IRQ? is it even necessary?
*/
-static void oss_irq(struct irq_desc *desc)
+static void oss_iopism_irq(struct irq_desc *desc)
{
- int events = oss->irq_pending &
- (OSS_IP_IOPSCC | OSS_IP_SCSI | OSS_IP_IOPISM);
-
- if (events & OSS_IP_IOPSCC) {
- oss->irq_pending &= ~OSS_IP_IOPSCC;
- generic_handle_irq(IRQ_MAC_SCC);
- }
-
- if (events & OSS_IP_SCSI) {
- oss->irq_pending &= ~OSS_IP_SCSI;
- generic_handle_irq(IRQ_MAC_SCSI);
- }
-
- if (events & OSS_IP_IOPISM) {
- oss->irq_pending &= ~OSS_IP_IOPISM;
- generic_handle_irq(IRQ_MAC_ADB);
- }
+ generic_handle_irq(IRQ_MAC_ADB);
}
-/*
- * Nubus IRQ handler, OSS style
- *
- * Unlike the VIA/RBV this is on its own autovector interrupt level.
- */
+static void oss_scsi_irq(struct irq_desc *desc)
+{
+ generic_handle_irq(IRQ_MAC_SCSI);
+}
static void oss_nubus_irq(struct irq_desc *desc)
{
- int events, irq_bit, i;
+ u16 events, irq_bit;
+ int irq_num;
events = oss->irq_pending & OSS_IP_NUBUS;
- if (!events)
- return;
-
- /* There are only six slots on the OSS, not seven */
-
- i = 6;
- irq_bit = 0x40;
+ irq_num = NUBUS_SOURCE_BASE + 5;
+ irq_bit = OSS_IP_NUBUS5;
do {
- --i;
- irq_bit >>= 1;
if (events & irq_bit) {
- oss->irq_pending &= ~irq_bit;
- generic_handle_irq(NUBUS_SOURCE_BASE + i);
+ events &= ~irq_bit;
+ generic_handle_irq(irq_num);
}
- } while(events & (irq_bit - 1));
+ --irq_num;
+ irq_bit >>= 1;
+ } while (events);
+}
+
+static void oss_iopscc_irq(struct irq_desc *desc)
+{
+ generic_handle_irq(IRQ_MAC_SCC);
}
/*
@@ -122,14 +107,14 @@ static void oss_nubus_irq(struct irq_desc *desc)
void __init oss_register_interrupts(void)
{
- irq_set_chained_handler(OSS_IRQLEV_IOPISM, oss_irq);
- irq_set_chained_handler(OSS_IRQLEV_SCSI, oss_irq);
+ irq_set_chained_handler(OSS_IRQLEV_IOPISM, oss_iopism_irq);
+ irq_set_chained_handler(OSS_IRQLEV_SCSI, oss_scsi_irq);
irq_set_chained_handler(OSS_IRQLEV_NUBUS, oss_nubus_irq);
- irq_set_chained_handler(OSS_IRQLEV_IOPSCC, oss_irq);
+ irq_set_chained_handler(OSS_IRQLEV_IOPSCC, oss_iopscc_irq);
irq_set_chained_handler(OSS_IRQLEV_VIA1, via1_irq);
/* OSS_VIA1 gets enabled here because it has no machspec interrupt. */
- oss->irq_level[OSS_VIA1] = IRQ_AUTO_6;
+ oss->irq_level[OSS_VIA1] = OSS_IRQLEV_VIA1;
}
/*
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 127d7c1f2090..03253c4f8e6a 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -21,8 +21,9 @@ extern void die_if_kernel(char *, struct pt_regs *, long);
int send_fault_sig(struct pt_regs *regs)
{
- siginfo_t siginfo = { 0, 0, 0, };
+ siginfo_t siginfo;
+ clear_siginfo(&siginfo);
siginfo.si_signo = current->thread.signo;
siginfo.si_code = current->thread.code;
siginfo.si_addr = (void *)current->thread.faddr;
diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h
index 554f73a77e6e..a1a9c7f5ca8c 100644
--- a/arch/metag/include/asm/thread_info.h
+++ b/arch/metag/include/asm/thread_info.h
@@ -74,9 +74,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the current stack pointer from C */
register unsigned long current_stack_pointer asm("A0StP") __used;
diff --git a/arch/metag/include/uapi/asm/Kbuild b/arch/metag/include/uapi/asm/Kbuild
index 6ac763d9a3e3..f9eaf07d29f8 100644
--- a/arch/metag/include/uapi/asm/Kbuild
+++ b/arch/metag/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/metag/include/uapi/asm/siginfo.h b/arch/metag/include/uapi/asm/siginfo.h
index b54ef7186ca3..9a3f6cde9487 100644
--- a/arch/metag/include/uapi/asm/siginfo.h
+++ b/arch/metag/include/uapi/asm/siginfo.h
@@ -6,4 +6,11 @@
#include <asm-generic/siginfo.h>
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME 0 /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
#endif
diff --git a/arch/metag/kernel/traps.c b/arch/metag/kernel/traps.c
index 444851e510d5..3b62b1b0c0b5 100644
--- a/arch/metag/kernel/traps.c
+++ b/arch/metag/kernel/traps.c
@@ -735,7 +735,7 @@ TBIRES fpe_handler(TBIRES State, int SigNum, int Triggers, int Inst, PTBI pTBI)
else if (error_state & TXSTAT_FPE_INEXACT_BIT)
info.si_code = FPE_FLTRES;
else
- info.si_code = 0;
+ info.si_code = FPE_FIXME;
info.si_errno = 0;
info.si_addr = (__force void __user *)regs->ctx.CurrPC;
force_sig_info(SIGFPE, &info, current);
diff --git a/arch/microblaze/include/asm/mmu_context_mm.h b/arch/microblaze/include/asm/mmu_context_mm.h
index 99472d2ca340..97559fe0b953 100644
--- a/arch/microblaze/include/asm/mmu_context_mm.h
+++ b/arch/microblaze/include/asm/mmu_context_mm.h
@@ -13,6 +13,7 @@
#include <linux/atomic.h>
#include <linux/mm_types.h>
+#include <linux/sched.h>
#include <asm/bitops.h>
#include <asm/mmu.h>
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index e7e8954e9815..9afe4b5bd6c8 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -86,9 +86,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
static inline struct thread_info *current_thread_info(void)
{
diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild
index 06609ca36115..2c6a6bffea32 100644
--- a/arch/microblaze/include/uapi/asm/Kbuild
+++ b/arch/microblaze/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 350a990fc719..8e0b3702f1c0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -259,6 +259,7 @@ config BCM47XX
select LEDS_GPIO_REGISTER
select BCM47XX_NVRAM
select BCM47XX_SPROM
+ select BCM47XX_SSB if !BCM47XX_BCMA
help
Support for BCM47XX based boards
@@ -389,6 +390,7 @@ config LANTIQ
select SYS_SUPPORTS_32BIT_KERNEL
select SYS_SUPPORTS_MIPS16
select SYS_SUPPORTS_MULTITHREADING
+ select SYS_SUPPORTS_VPE_LOADER
select SYS_HAS_EARLY_PRINTK
select GPIOLIB
select SWAP_IO_SPACE
@@ -516,6 +518,7 @@ config MIPS_MALTA
select SYS_SUPPORTS_MIPS16
select SYS_SUPPORTS_MULTITHREADING
select SYS_SUPPORTS_SMARTMIPS
+ select SYS_SUPPORTS_VPE_LOADER
select SYS_SUPPORTS_ZBOOT
select SYS_SUPPORTS_RELOCATABLE
select USE_OF
@@ -2281,9 +2284,16 @@ config MIPSR2_TO_R6_EMULATOR
The only reason this is a build-time option is to save ~14K from the
final kernel image.
+config SYS_SUPPORTS_VPE_LOADER
+ bool
+ depends on SYS_SUPPORTS_MULTITHREADING
+ help
+ Indicates that the platform supports the VPE loader, and provides
+ physical_memsize.
+
config MIPS_VPE_LOADER
bool "VPE loader support."
- depends on SYS_SUPPORTS_MULTITHREADING && MODULES
+ depends on SYS_SUPPORTS_VPE_LOADER && MODULES
select CPU_MIPSR2_IRQ_VI
select CPU_MIPSR2_IRQ_EI
select MIPS_MT
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 464af5e025d6..0749c3724543 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -124,30 +124,36 @@ config SCACHE_DEBUGFS
If unsure, say N.
-menuconfig MIPS_CPS_NS16550
+menuconfig MIPS_CPS_NS16550_BOOL
bool "CPS SMP NS16550 UART output"
depends on MIPS_CPS
help
Output debug information via an ns16550 compatible UART if exceptions
occur early in the boot process of a secondary core.
-if MIPS_CPS_NS16550
+if MIPS_CPS_NS16550_BOOL
+
+config MIPS_CPS_NS16550
+ def_bool MIPS_CPS_NS16550_BASE != 0
config MIPS_CPS_NS16550_BASE
hex "UART Base Address"
default 0x1b0003f8 if MIPS_MALTA
+ default 0
help
The base address of the ns16550 compatible UART on which to output
debug information from the early stages of core startup.
+ This is only used if non-zero.
+
config MIPS_CPS_NS16550_SHIFT
int "UART Register Shift"
- default 0 if MIPS_MALTA
+ default 0
help
The number of bits to shift ns16550 register indices by in order to
form their addresses. That is, log base 2 of the span between
adjacent ns16550 registers in the system.
-endif # MIPS_CPS_NS16550
+endif # MIPS_CPS_NS16550_BOOL
endmenu
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 4674f1efbe7a..e1675c25d5d4 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -575,7 +575,7 @@ static int __init ar7_register_uarts(void)
uart_port.type = PORT_AR7;
uart_port.uartclk = clk_get_rate(bus_clk) / 2;
uart_port.iotype = UPIO_MEM32;
- uart_port.flags = UPF_FIXED_TYPE;
+ uart_port.flags = UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF;
uart_port.regshift = 2;
uart_port.line = 0;
diff --git a/arch/mips/ath25/devices.c b/arch/mips/ath25/devices.c
index e1156347da53..301a9028273c 100644
--- a/arch/mips/ath25/devices.c
+++ b/arch/mips/ath25/devices.c
@@ -73,6 +73,7 @@ const char *get_system_type(void)
void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
{
+#ifdef CONFIG_SERIAL_8250_CONSOLE
struct uart_port s;
memset(&s, 0, sizeof(s));
@@ -85,6 +86,7 @@ void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
s.uartclk = uartclk;
early_serial_setup(&s);
+#endif /* CONFIG_SERIAL_8250_CONSOLE */
}
int __init ath25_add_wmac(int nr, u32 base, int irq)
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 7c8aab23bce8..b1f66699677d 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -16,7 +16,6 @@ generic-y += qrwlock.h
generic-y += qspinlock.h
generic-y += sections.h
generic-y += segment.h
-generic-y += serial.h
generic-y += trace_clock.h
generic-y += unaligned.h
generic-y += user.h
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 49691331ada4..946681db8dc3 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -126,79 +126,6 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */
typedef u32 compat_sigset_word;
-typedef union compat_sigval {
- compat_int_t sival_int;
- compat_uptr_t sival_ptr;
-} compat_sigval_t;
-
-/* Can't use the generic version because si_code and si_errno are swapped */
-
-#define SI_PAD_SIZE32 (128/sizeof(int) - 3)
-
-typedef struct compat_siginfo {
- int si_signo;
- int si_code;
- int si_errno;
-
- union {
- int _pad[128 / sizeof(int) - 3];
-
- /* kill() */
- struct {
- compat_pid_t _pid; /* sender's pid */
- __compat_uid32_t _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- compat_sigval_t _sigval; /* same as below */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- compat_pid_t _pid; /* sender's pid */
- __compat_uid32_t _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- compat_pid_t _pid; /* which child */
- __compat_uid32_t _uid; /* sender's uid */
- int _status; /* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- compat_uptr_t _addr; /* faulting insn/memory ref. */
-#ifdef __ARCH_SI_TRAPNO
- int _trapno; /* TRAP # which caused the signal */
-#endif
- short _addr_lsb; /* LSB of the reported address */
- struct {
- compat_uptr_t _lower;
- compat_uptr_t _upper;
- } _addr_bnd;
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
-
- struct {
- compat_uptr_t _call_addr; /* calling insn */
- int _syscall; /* triggering system call number */
- compat_uint_t _arch; /* AUDIT_ARCH_* of syscall */
- } _sigsys;
- } _sifields;
-} compat_siginfo_t;
-
#define COMPAT_OFF_T_MAX 0x7fffffff
/*
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 9e9e94415d08..1a508a74d48d 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -552,7 +552,7 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd);
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return !!(pmd_val(pmd) & _PAGE_WRITE);
diff --git a/arch/mips/include/asm/serial.h b/arch/mips/include/asm/serial.h
new file mode 100644
index 000000000000..1d830c6666c2
--- /dev/null
+++ b/arch/mips/include/asm/serial.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2017 MIPS Tech, LLC
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+#ifndef __ASM__SERIAL_H
+#define __ASM__SERIAL_H
+
+#ifdef CONFIG_MIPS_GENERIC
+/*
+ * Generic kernels cannot know a correct value for all platforms at
+ * compile time. Set it to 0 to prevent 8250_early using it
+ */
+#define BASE_BAUD 0
+#else
+#include <asm-generic/serial.h>
+#endif
+
+#endif /* __ASM__SERIAL_H */
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 5e8927f99a76..4993db40482c 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -49,9 +49,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* How to get the thread information struct from C. */
register struct thread_info *__current_thread_info __asm__("$28");
diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild
index a0266feba9e6..7a4becd8963a 100644
--- a/arch/mips/include/uapi/asm/Kbuild
+++ b/arch/mips/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += ipcbuf.h
diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h
index f17d8163dec6..262504bd59a5 100644
--- a/arch/mips/include/uapi/asm/siginfo.h
+++ b/arch/mips/include/uapi/asm/siginfo.h
@@ -14,8 +14,6 @@
#define __ARCH_SIGEV_PREAMBLE_SIZE (sizeof(long) + 2*sizeof(int))
#undef __ARCH_SI_TRAPNO /* exception code needs to fill this ... */
-#define HAVE_ARCH_SIGINFO_T
-
/*
* Careful to keep union _sifields from shifting ...
*/
@@ -27,92 +25,10 @@
#error _MIPS_SZLONG neither 32 nor 64
#endif
-#define __ARCH_SIGSYS
+#define __ARCH_HAS_SWAPPED_SIGINFO
#include <asm-generic/siginfo.h>
-/* We can't use generic siginfo_t, because our si_code and si_errno are swapped */
-typedef struct siginfo {
- int si_signo;
- int si_code;
- int si_errno;
- int __pad0[SI_MAX_SIZE / sizeof(int) - SI_PAD_SIZE - 3];
-
- union {
- int _pad[SI_PAD_SIZE];
-
- /* kill() */
- struct {
- __kernel_pid_t _pid; /* sender's pid */
- __ARCH_SI_UID_T _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- __kernel_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- char _pad[sizeof( __ARCH_SI_UID_T) - sizeof(int)];
- sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- __kernel_pid_t _pid; /* sender's pid */
- __ARCH_SI_UID_T _uid; /* sender's uid */
- sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- __kernel_pid_t _pid; /* which child */
- __ARCH_SI_UID_T _uid; /* sender's uid */
- int _status; /* exit code */
- __kernel_clock_t _utime;
- __kernel_clock_t _stime;
- } _sigchld;
-
- /* IRIX SIGCHLD */
- struct {
- __kernel_pid_t _pid; /* which child */
- __kernel_clock_t _utime;
- int _status; /* exit code */
- __kernel_clock_t _stime;
- } _irix_sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- void __user *_addr; /* faulting insn/memory ref. */
-#ifdef __ARCH_SI_TRAPNO
- int _trapno; /* TRAP # which caused the signal */
-#endif
- short _addr_lsb;
- union {
- /* used when si_code=SEGV_BNDERR */
- struct {
- void __user *_lower;
- void __user *_upper;
- } _addr_bnd;
- /* used when si_code=SEGV_PKUERR */
- __u32 _pkey;
- };
- } _sigfault;
-
- /* SIGPOLL, SIGXFSZ (To do ...) */
- struct {
- __ARCH_SI_BAND_T _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
-
- /* SIGSYS */
- struct {
- void __user *_call_addr; /* calling user insn */
- int _syscall; /* triggering system call number */
- unsigned int _arch; /* AUDIT_ARCH_* of syscall */
- } _sigsys;
- } _sifields;
-} siginfo_t;
-
/*
* si_code values
* Again these have been chosen to be IRIX compatible.
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index c7ed26029cbb..e68e6e04063a 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -235,6 +235,7 @@ LEAF(mips_cps_core_init)
has_mt t0, 3f
.set push
+ .set MIPS_ISA_LEVEL_RAW
.set mt
/* Only allow 1 TC per VPE to execute... */
@@ -388,6 +389,7 @@ LEAF(mips_cps_boot_vpes)
#elif defined(CONFIG_MIPS_MT)
.set push
+ .set MIPS_ISA_LEVEL_RAW
.set mt
/* If the core doesn't support MT then return */
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index dd5567b1e305..8f5bd04f320a 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -292,7 +292,6 @@ void mips_cm_lock_other(unsigned int cluster, unsigned int core,
*this_cpu_ptr(&cm_core_lock_flags));
} else {
WARN_ON(cluster != 0);
- WARN_ON(vp != 0);
WARN_ON(block != CM_GCR_Cx_OTHER_BLOCK_LOCAL);
/*
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 45d0b6b037ee..57028d49c202 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -705,6 +705,18 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
struct task_struct *t;
int max_users;
+ /* If nothing to change, return right away, successfully. */
+ if (value == mips_get_process_fp_mode(task))
+ return 0;
+
+ /* Only accept a mode change if 64-bit FP enabled for o32. */
+ if (!IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT))
+ return -EOPNOTSUPP;
+
+ /* And only for o32 tasks. */
+ if (IS_ENABLED(CONFIG_64BIT) && !test_thread_flag(TIF_32BIT_REGS))
+ return -EOPNOTSUPP;
+
/* Check the value is valid */
if (value & ~known_bits)
return -EOPNOTSUPP;
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index efbd8df8b665..0b23b1ad99e6 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -419,63 +419,160 @@ static int gpr64_set(struct task_struct *target,
#endif /* CONFIG_64BIT */
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer,
+ * !CONFIG_CPU_HAS_MSA variant. FP context's general register slots
+ * correspond 1:1 to buffer slots. Only general registers are copied.
+ */
+static int fpr_get_fpa(struct task_struct *target,
+ unsigned int *pos, unsigned int *count,
+ void **kbuf, void __user **ubuf)
+{
+ return user_regset_copyout(pos, count, kbuf, ubuf,
+ &target->thread.fpu,
+ 0, NUM_FPU_REGS * sizeof(elf_fpreg_t));
+}
+
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer,
+ * CONFIG_CPU_HAS_MSA variant. Only lower 64 bits of FP context's
+ * general register slots are copied to buffer slots. Only general
+ * registers are copied.
+ */
+static int fpr_get_msa(struct task_struct *target,
+ unsigned int *pos, unsigned int *count,
+ void **kbuf, void __user **ubuf)
+{
+ unsigned int i;
+ u64 fpr_val;
+ int err;
+
+ BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+ for (i = 0; i < NUM_FPU_REGS; i++) {
+ fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0);
+ err = user_regset_copyout(pos, count, kbuf, ubuf,
+ &fpr_val, i * sizeof(elf_fpreg_t),
+ (i + 1) * sizeof(elf_fpreg_t));
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer.
+ * Choose the appropriate helper for general registers, and then copy
+ * the FCSR register separately.
+ */
static int fpr_get(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
- unsigned i;
+ const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
int err;
- u64 fpr_val;
- /* XXX fcr31 */
+ if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
+ err = fpr_get_fpa(target, &pos, &count, &kbuf, &ubuf);
+ else
+ err = fpr_get_msa(target, &pos, &count, &kbuf, &ubuf);
+ if (err)
+ return err;
- if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t))
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu,
- 0, sizeof(elf_fpregset_t));
+ err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &target->thread.fpu.fcr31,
+ fcr31_pos, fcr31_pos + sizeof(u32));
- for (i = 0; i < NUM_FPU_REGS; i++) {
- fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0);
- err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &fpr_val, i * sizeof(elf_fpreg_t),
- (i + 1) * sizeof(elf_fpreg_t));
+ return err;
+}
+
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context,
+ * !CONFIG_CPU_HAS_MSA variant. Buffer slots correspond 1:1 to FP
+ * context's general register slots. Only general registers are copied.
+ */
+static int fpr_set_fpa(struct task_struct *target,
+ unsigned int *pos, unsigned int *count,
+ const void **kbuf, const void __user **ubuf)
+{
+ return user_regset_copyin(pos, count, kbuf, ubuf,
+ &target->thread.fpu,
+ 0, NUM_FPU_REGS * sizeof(elf_fpreg_t));
+}
+
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context,
+ * CONFIG_CPU_HAS_MSA variant. Buffer slots are copied to lower 64
+ * bits only of FP context's general register slots. Only general
+ * registers are copied.
+ */
+static int fpr_set_msa(struct task_struct *target,
+ unsigned int *pos, unsigned int *count,
+ const void **kbuf, const void __user **ubuf)
+{
+ unsigned int i;
+ u64 fpr_val;
+ int err;
+
+ BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+ for (i = 0; i < NUM_FPU_REGS && *count > 0; i++) {
+ err = user_regset_copyin(pos, count, kbuf, ubuf,
+ &fpr_val, i * sizeof(elf_fpreg_t),
+ (i + 1) * sizeof(elf_fpreg_t));
if (err)
return err;
+ set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val);
}
return 0;
}
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context.
+ * Choose the appropriate helper for general registers, and then copy
+ * the FCSR register separately.
+ *
+ * We optimize for the case where `count % sizeof(elf_fpreg_t) == 0',
+ * which is supposed to have been guaranteed by the kernel before
+ * calling us, e.g. in `ptrace_regset'. We enforce that requirement,
+ * so that we can safely avoid preinitializing temporaries for
+ * partial register writes.
+ */
static int fpr_set(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- unsigned i;
+ const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+ u32 fcr31;
int err;
- u64 fpr_val;
- /* XXX fcr31 */
+ BUG_ON(count % sizeof(elf_fpreg_t));
+
+ if (pos + count > sizeof(elf_fpregset_t))
+ return -EIO;
init_fp_ctx(target);
- if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t))
- return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu,
- 0, sizeof(elf_fpregset_t));
+ if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
+ err = fpr_set_fpa(target, &pos, &count, &kbuf, &ubuf);
+ else
+ err = fpr_set_msa(target, &pos, &count, &kbuf, &ubuf);
+ if (err)
+ return err;
- BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
- for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) {
+ if (count > 0) {
err = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &fpr_val, i * sizeof(elf_fpreg_t),
- (i + 1) * sizeof(elf_fpreg_t));
+ &fcr31,
+ fcr31_pos, fcr31_pos + sizeof(u32));
if (err)
return err;
- set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val);
+
+ ptrace_setfcr31(target, fcr31);
}
- return 0;
+ return err;
}
enum mips_regset {
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index cf5c7c05e5a3..c4db910a8794 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -76,70 +76,3 @@ SYSCALL_DEFINE3(32_sigaction, long, sig, const struct compat_sigaction __user *,
return ret;
}
-
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
- int err;
-
- if (!access_ok (VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
- return -EFAULT;
-
- /* If you change siginfo_t structure, please be sure
- this code is fixed accordingly.
- It should never copy any pad contained in the structure
- to avoid security leaks, but must copy the generic
- 3 ints plus the relevant union member.
- This routine must convert siginfo from 64bit to 32bit as well
- at the same time. */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user(from->si_code, &to->si_code);
- if (from->si_code < 0)
- err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
- else {
- switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_TIMER:
- err |= __put_user(from->si_tid, &to->si_tid);
- err |= __put_user(from->si_overrun, &to->si_overrun);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- case SIL_CHLD:
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- err |= __put_user(from->si_status, &to->si_status);
- case SIL_KILL:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- case SIL_FAULT:
- err |= __put_user((unsigned long)from->si_addr, &to->si_addr);
- break;
- case SIL_POLL:
- err |= __put_user(from->si_band, &to->si_band);
- err |= __put_user(from->si_fd, &to->si_fd);
- break;
- case SIL_RT:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- case SIL_SYS:
- err |= __copy_to_user(&to->si_call_addr, &from->si_call_addr,
- sizeof(compat_uptr_t));
- err |= __put_user(from->si_syscall, &to->si_syscall);
- err |= __put_user(from->si_arch, &to->si_arch);
- break;
- }
- }
- return err;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
- if (copy_from_user(to, from, 3*sizeof(int)) ||
- copy_from_user(to->_sifields._pad,
- from->_sifields._pad, SI_PAD_SIZE32))
- return -EFAULT;
-
- return 0;
-}
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 5d19ed07e99d..0ae4a731cc12 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -699,11 +699,12 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
asmlinkage void do_ov(struct pt_regs *regs)
{
enum ctx_state prev_state;
- siginfo_t info = {
- .si_signo = SIGFPE,
- .si_code = FPE_INTOVF,
- .si_addr = (void __user *)regs->cp0_epc,
- };
+ siginfo_t info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGFPE;
+ info.si_code = FPE_INTOVF;
+ info.si_addr = (void __user *)regs->cp0_epc;
prev_state = exception_enter();
die_if_kernel("Integer overflow", regs);
@@ -721,7 +722,11 @@ asmlinkage void do_ov(struct pt_regs *regs)
void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
struct task_struct *tsk)
{
- struct siginfo si = { .si_addr = fault_addr, .si_signo = SIGFPE };
+ struct siginfo si;
+
+ clear_siginfo(&si);
+ si.si_addr = fault_addr;
+ si.si_signo = SIGFPE;
if (fcr31 & FPU_CSR_INV_X)
si.si_code = FPE_FLTINV;
@@ -739,9 +744,10 @@ void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
{
- struct siginfo si = { 0 };
+ struct siginfo si;
struct vm_area_struct *vma;
+ clear_siginfo(&si);
switch (sig) {
case 0:
return 0;
@@ -890,9 +896,10 @@ out:
void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
const char *str)
{
- siginfo_t info = { 0 };
+ siginfo_t info;
char b[40];
+ clear_siginfo(&info);
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_TRAP, str, regs, code, current->thread.trap_nr,
SIGTRAP) == NOTIFY_STOP)
@@ -1499,9 +1506,13 @@ asmlinkage void do_mdmx(struct pt_regs *regs)
*/
asmlinkage void do_watch(struct pt_regs *regs)
{
- siginfo_t info = { .si_signo = SIGTRAP, .si_code = TRAP_HWBKPT };
+ siginfo_t info;
enum ctx_state prev_state;
+ clear_siginfo(&info);
+ info.si_signo = SIGTRAP;
+ info.si_code = TRAP_HWBKPT;
+
prev_state = exception_enter();
/*
* Clear WP (bit 22) bit of cause register so we don't loop
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index d535edc01434..75fdeaa8c62f 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -445,10 +445,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
int r = -EINTR;
- sigset_t sigsaved;
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_sigset_activate(vcpu);
if (vcpu->mmio_needed) {
if (!vcpu->mmio_is_write)
@@ -480,8 +478,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
local_irq_enable();
out:
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
return r;
}
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 78c2affeabf8..e84e12655fa8 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -16,4 +16,5 @@ obj-$(CONFIG_CPU_R3000) += r3k_dump_tlb.o
obj-$(CONFIG_CPU_TX39XX) += r3k_dump_tlb.o
# libgcc-style stuff needed in the kernel
-obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o
+obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o multi3.o \
+ ucmpdi2.o
diff --git a/arch/mips/lib/libgcc.h b/arch/mips/lib/libgcc.h
index 28002ed90c2c..199a7f96282f 100644
--- a/arch/mips/lib/libgcc.h
+++ b/arch/mips/lib/libgcc.h
@@ -10,10 +10,18 @@ typedef int word_type __attribute__ ((mode (__word__)));
struct DWstruct {
int high, low;
};
+
+struct TWstruct {
+ long long high, low;
+};
#elif defined(__LITTLE_ENDIAN)
struct DWstruct {
int low, high;
};
+
+struct TWstruct {
+ long long low, high;
+};
#else
#error I feel sick.
#endif
@@ -23,4 +31,13 @@ typedef union {
long long ll;
} DWunion;
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6)
+typedef int ti_type __attribute__((mode(TI)));
+
+typedef union {
+ struct TWstruct s;
+ ti_type ti;
+} TWunion;
+#endif
+
#endif /* __ASM_LIBGCC_H */
diff --git a/arch/mips/lib/multi3.c b/arch/mips/lib/multi3.c
new file mode 100644
index 000000000000..111ad475aa0c
--- /dev/null
+++ b/arch/mips/lib/multi3.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+
+#include "libgcc.h"
+
+/*
+ * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that
+ * specific case only we'll implement it here.
+ *
+ * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981
+ */
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7)
+
+/* multiply 64-bit values, low 64-bits returned */
+static inline long long notrace dmulu(long long a, long long b)
+{
+ long long res;
+
+ asm ("dmulu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+ return res;
+}
+
+/* multiply 64-bit unsigned values, high 64-bits of 128-bit result returned */
+static inline long long notrace dmuhu(long long a, long long b)
+{
+ long long res;
+
+ asm ("dmuhu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+ return res;
+}
+
+/* multiply 128-bit values, low 128-bits returned */
+ti_type notrace __multi3(ti_type a, ti_type b)
+{
+ TWunion res, aa, bb;
+
+ aa.ti = a;
+ bb.ti = b;
+
+ /*
+ * a * b = (a.lo * b.lo)
+ * + 2^64 * (a.hi * b.lo + a.lo * b.hi)
+ * [+ 2^128 * (a.hi * b.hi)]
+ */
+ res.s.low = dmulu(aa.s.low, bb.s.low);
+ res.s.high = dmuhu(aa.s.low, bb.s.low);
+ res.s.high += dmulu(aa.s.high, bb.s.low);
+ res.s.high += dmulu(aa.s.low, bb.s.high);
+
+ return res.ti;
+}
+EXPORT_SYMBOL(__multi3);
+
+#endif /* 64BIT && CPU_MIPSR6 && GCC7 */
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index cdb5a191b9d5..9bb6baa45da3 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -40,7 +40,7 @@
#include "uasm.c"
-static const struct insn const insn_table_MM[insn_invalid] = {
+static const struct insn insn_table_MM[insn_invalid] = {
[insn_addu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD},
[insn_addiu] = {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
[insn_and] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD},
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
index d4469b20d176..4f46a4509f79 100644
--- a/arch/mips/ralink/timer.c
+++ b/arch/mips/ralink/timer.c
@@ -109,9 +109,9 @@ static int rt_timer_probe(struct platform_device *pdev)
}
rt->irq = platform_get_irq(pdev, 0);
- if (!rt->irq) {
+ if (rt->irq < 0) {
dev_err(&pdev->dev, "failed to load irq\n");
- return -ENOENT;
+ return rt->irq;
}
rt->membase = devm_ioremap_resource(&pdev->dev, res);
diff --git a/arch/mips/rb532/Makefile b/arch/mips/rb532/Makefile
index efdecdb6e3ea..8186afca2234 100644
--- a/arch/mips/rb532/Makefile
+++ b/arch/mips/rb532/Makefile
@@ -2,4 +2,6 @@
# Makefile for the RB532 board specific parts of the kernel
#
-obj-y += irq.o time.o setup.o serial.o prom.o gpio.o devices.o
+obj-$(CONFIG_SERIAL_8250_CONSOLE) += serial.o
+
+obj-y += irq.o time.o setup.o prom.o gpio.o devices.o
diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c
index 32ea3e6731d6..354d258396ff 100644
--- a/arch/mips/rb532/devices.c
+++ b/arch/mips/rb532/devices.c
@@ -310,6 +310,8 @@ static int __init plat_setup_devices(void)
return platform_add_devices(rb532_devs, ARRAY_SIZE(rb532_devs));
}
+#ifdef CONFIG_NET
+
static int __init setup_kmac(char *s)
{
printk(KERN_INFO "korina mac = %s\n", s);
@@ -322,4 +324,6 @@ static int __init setup_kmac(char *s)
__setup("kmac=", setup_kmac);
+#endif /* CONFIG_NET */
+
arch_initcall(plat_setup_devices);
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index f5f90bbf019d..1748a7b25bf8 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -79,8 +79,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
#define init_uregs \
((struct pt_regs *) \
((unsigned long) init_stack + THREAD_SIZE - sizeof(struct pt_regs)))
diff --git a/arch/mn10300/include/uapi/asm/Kbuild b/arch/mn10300/include/uapi/asm/Kbuild
index 162fbdbb5fd5..b04fd1632051 100644
--- a/arch/mn10300/include/uapi/asm/Kbuild
+++ b/arch/mn10300/include/uapi/asm/Kbuild
@@ -1,5 +1,6 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += poll.h
generic-y += siginfo.h
diff --git a/arch/mn10300/kernel/mn10300-serial.c b/arch/mn10300/kernel/mn10300-serial.c
index d7ef1232a82a..4994b570dfd9 100644
--- a/arch/mn10300/kernel/mn10300-serial.c
+++ b/arch/mn10300/kernel/mn10300-serial.c
@@ -550,7 +550,7 @@ try_again:
return;
}
- smp_read_barrier_depends();
+ /* READ_ONCE() enforces dependency, but dangerous through integer!!! */
ch = port->rx_buffer[ix++];
st = port->rx_buffer[ix++];
smp_mb();
@@ -1728,7 +1728,10 @@ static int mn10300_serial_poll_get_char(struct uart_port *_port)
if (CIRC_CNT(port->rx_inp, ix, MNSC_BUFFER_SIZE) == 0)
return NO_POLL_CHAR;
- smp_read_barrier_depends();
+ /*
+ * READ_ONCE() enforces dependency, but dangerous
+ * through integer!!!
+ */
ch = port->rx_buffer[ix++];
st = port->rx_buffer[ix++];
smp_mb();
diff --git a/arch/mn10300/mm/misalignment.c b/arch/mn10300/mm/misalignment.c
index b39a388825ae..8ace89617c1c 100644
--- a/arch/mn10300/mm/misalignment.c
+++ b/arch/mn10300/mm/misalignment.c
@@ -437,7 +437,7 @@ transfer_failed:
info.si_signo = SIGSEGV;
info.si_errno = 0;
- info.si_code = 0;
+ info.si_code = SEGV_MAPERR;
info.si_addr = (void *) regs->pc;
force_sig_info(SIGSEGV, &info, current);
return;
diff --git a/arch/nios2/include/asm/thread_info.h b/arch/nios2/include/asm/thread_info.h
index d69c338bd19c..7349a4fa635b 100644
--- a/arch/nios2/include/asm/thread_info.h
+++ b/arch/nios2/include/asm/thread_info.h
@@ -63,9 +63,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
static inline struct thread_info *current_thread_info(void)
{
diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild
index ffca24da7647..13a3d77b4d7b 100644
--- a/arch/nios2/include/uapi/asm/Kbuild
+++ b/arch/nios2/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h
index 396d8f306c21..af31a9fe736a 100644
--- a/arch/openrisc/include/asm/processor.h
+++ b/arch/openrisc/include/asm/processor.h
@@ -84,8 +84,6 @@ void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp);
void release_thread(struct task_struct *);
unsigned long get_wchan(struct task_struct *p);
-#define init_stack (init_thread_union.stack)
-
#define cpu_relax() barrier()
#endif /* __ASSEMBLY__ */
diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h
index c229aa6bb502..5c15dfa2fd4f 100644
--- a/arch/openrisc/include/asm/thread_info.h
+++ b/arch/openrisc/include/asm/thread_info.h
@@ -79,8 +79,6 @@ struct thread_info {
.ksp = 0, \
}
-#define init_thread_info (init_thread_union.thread_info)
-
/* how to get the thread information struct from C */
register struct thread_info *current_thread_info_reg asm("r10");
#define current_thread_info() (current_thread_info_reg)
diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild
index 62286dbeb904..130c16ccba0a 100644
--- a/arch/openrisc/include/uapi/asm/Kbuild
+++ b/arch/openrisc/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 4085d72fa5ae..9e38dc66c9e4 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -266,12 +266,12 @@ asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address)
siginfo_t info;
if (user_mode(regs)) {
- /* Send a SIGSEGV */
- info.si_signo = SIGSEGV;
+ /* Send a SIGBUS */
+ info.si_signo = SIGBUS;
info.si_errno = 0;
- /* info.si_code has been set above */
- info.si_addr = (void *)address;
- force_sig_info(SIGSEGV, &info, current);
+ info.si_code = BUS_ADRALN;
+ info.si_addr = (void __user *)address;
+ force_sig_info(SIGBUS, &info, current);
} else {
printk("KERNEL: Unaligned Access 0x%.8lx\n", address);
show_registers(regs);
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 00ddb7804be4..953bdcd54efe 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -28,6 +28,7 @@
#include <asm/page.h>
#include <asm/cache.h>
+#include <asm/thread_info.h>
#include <asm-generic/vmlinux.lds.h>
#ifdef __OR1K__
diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c
index 9345b44b86f0..f57118e1f6b4 100644
--- a/arch/parisc/boot/compressed/misc.c
+++ b/arch/parisc/boot/compressed/misc.c
@@ -123,8 +123,8 @@ int puts(const char *s)
while ((nuline = strchr(s, '\n')) != NULL) {
if (nuline != s)
pdc_iodc_print(s, nuline - s);
- pdc_iodc_print("\r\n", 2);
- s = nuline + 1;
+ pdc_iodc_print("\r\n", 2);
+ s = nuline + 1;
}
if (*s != '\0')
pdc_iodc_print(s, strlen(s));
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index acf8aa07cbe0..c22db5323244 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -130,70 +130,6 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */
typedef u32 compat_sigset_word;
-typedef union compat_sigval {
- compat_int_t sival_int;
- compat_uptr_t sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[128/sizeof(int) - 3];
-
- /* kill() */
- struct {
- unsigned int _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- char _pad[sizeof(unsigned int) - sizeof(int)];
- compat_sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- unsigned int _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- unsigned int _pid; /* which child */
- unsigned int _uid; /* sender's uid */
- int _status; /* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- unsigned int _addr; /* faulting insn/memory ref. */
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
-
- /* SIGSYS */
- struct {
- compat_uptr_t _call_addr; /* calling user insn */
- int _syscall; /* triggering system call number */
- compat_uint_t _arch; /* AUDIT_ARCH_* of syscall */
- } _sigsys;
- } _sifields;
-} compat_siginfo_t;
-
#define COMPAT_OFF_T_MAX 0x7fffffff
struct compat_ipc64_perm {
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index dd5a08aaa4da..3eb4bfc1fb36 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -12,6 +12,7 @@
for the semaphore. */
#define __PA_LDCW_ALIGNMENT 16
+#define __PA_LDCW_ALIGN_ORDER 4
#define __ldcw_align(a) ({ \
unsigned long __ret = (unsigned long) &(a)->lock[0]; \
__ret = (__ret + __PA_LDCW_ALIGNMENT - 1) \
@@ -29,6 +30,7 @@
ldcd). */
#define __PA_LDCW_ALIGNMENT 4
+#define __PA_LDCW_ALIGN_ORDER 2
#define __ldcw_align(a) (&(a)->slock)
#define __LDCW "ldcw,co"
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index c980a02a52bc..285757544cca 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -25,9 +25,6 @@ struct thread_info {
.preempt_count = INIT_PREEMPT_COUNT, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
#define current_thread_info() ((struct thread_info *)mfctl(30))
@@ -35,7 +32,12 @@ struct thread_info {
/* thread information allocation */
+#ifdef CONFIG_IRQSTACKS
+#define THREAD_SIZE_ORDER 2 /* PA-RISC requires at least 16k stack */
+#else
#define THREAD_SIZE_ORDER 3 /* PA-RISC requires at least 32k stack */
+#endif
+
/* Be sure to hunt all references to this down when you change the size of
* the kernel stack */
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild
index 196d2a4efb31..286ef5a5904b 100644
--- a/arch/parisc/include/uapi/asm/Kbuild
+++ b/arch/parisc/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
+generic-y += bpf_perf_event.h
generic-y += kvm_para.h
generic-y += param.h
generic-y += poll.h
diff --git a/arch/parisc/include/uapi/asm/siginfo.h b/arch/parisc/include/uapi/asm/siginfo.h
index 4a1062e05aaf..be40331f757d 100644
--- a/arch/parisc/include/uapi/asm/siginfo.h
+++ b/arch/parisc/include/uapi/asm/siginfo.h
@@ -8,4 +8,11 @@
#include <asm-generic/siginfo.h>
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME 0 /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
#endif
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index d8f77358e2ba..29b99b8964aa 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -870,7 +870,7 @@ static void print_parisc_device(struct parisc_device *dev)
static int count;
print_pa_hwpath(dev, hw_path);
- printk(KERN_INFO "%d. %s at 0x%p [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
+ printk(KERN_INFO "%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
++count, dev->name, (void*) dev->hpa.start, hw_path, dev->id.hw_type,
dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index a4fd296c958e..e95207c0565e 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -35,6 +35,7 @@
#include <asm/pgtable.h>
#include <asm/signal.h>
#include <asm/unistd.h>
+#include <asm/ldcw.h>
#include <asm/thread_info.h>
#include <linux/linkage.h>
@@ -46,6 +47,14 @@
#endif
.import pa_tlb_lock,data
+ .macro load_pa_tlb_lock reg
+#if __PA_LDCW_ALIGNMENT > 4
+ load32 PA(pa_tlb_lock) + __PA_LDCW_ALIGNMENT-1, \reg
+ depi 0,31,__PA_LDCW_ALIGN_ORDER, \reg
+#else
+ load32 PA(pa_tlb_lock), \reg
+#endif
+ .endm
/* space_to_prot macro creates a prot id from a space id */
@@ -457,7 +466,7 @@
.macro tlb_lock spc,ptp,pte,tmp,tmp1,fault
#ifdef CONFIG_SMP
cmpib,COND(=),n 0,\spc,2f
- load32 PA(pa_tlb_lock),\tmp
+ load_pa_tlb_lock \tmp
1: LDCW 0(\tmp),\tmp1
cmpib,COND(=) 0,\tmp1,1b
nop
@@ -480,7 +489,7 @@
/* Release pa_tlb_lock lock. */
.macro tlb_unlock1 spc,tmp
#ifdef CONFIG_SMP
- load32 PA(pa_tlb_lock),\tmp
+ load_pa_tlb_lock \tmp
tlb_unlock0 \spc,\tmp
#endif
.endm
@@ -878,9 +887,6 @@ ENTRY_CFI(syscall_exit_rfi)
STREG %r19,PT_SR7(%r16)
intr_return:
- /* NOTE: Need to enable interrupts incase we schedule. */
- ssm PSW_SM_I, %r0
-
/* check for reschedule */
mfctl %cr30,%r1
LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */
@@ -907,6 +913,11 @@ intr_check_sig:
LDREG PT_IASQ1(%r16), %r20
cmpib,COND(=),n 0,%r20,intr_restore /* backward */
+ /* NOTE: We need to enable interrupts if we have to deliver
+ * signals. We used to do this earlier but it caused kernel
+ * stack overflows. */
+ ssm PSW_SM_I, %r0
+
copy %r0, %r25 /* long in_syscall = 0 */
#ifdef CONFIG_64BIT
ldo -16(%r30),%r29 /* Reference param save area */
@@ -958,6 +969,10 @@ intr_do_resched:
cmpib,COND(=) 0, %r20, intr_do_preempt
nop
+ /* NOTE: We need to enable interrupts if we schedule. We used
+ * to do this earlier but it caused kernel stack overflows. */
+ ssm PSW_SM_I, %r0
+
#ifdef CONFIG_64BIT
ldo -16(%r30),%r29 /* Reference param save area */
#endif
diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S
index e3a8e5e4d5de..8d072c44f300 100644
--- a/arch/parisc/kernel/hpmc.S
+++ b/arch/parisc/kernel/hpmc.S
@@ -305,6 +305,7 @@ ENDPROC_CFI(os_hpmc)
__INITRODATA
+ .align 4
.export os_hpmc_size
os_hpmc_size:
.word .os_hpmc_end-.os_hpmc
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index adf7187f8951..2d40c4ff3f69 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -36,6 +36,7 @@
#include <asm/assembly.h>
#include <asm/pgtable.h>
#include <asm/cache.h>
+#include <asm/ldcw.h>
#include <linux/linkage.h>
.text
@@ -333,8 +334,12 @@ ENDPROC_CFI(flush_data_cache_local)
.macro tlb_lock la,flags,tmp
#ifdef CONFIG_SMP
- ldil L%pa_tlb_lock,%r1
- ldo R%pa_tlb_lock(%r1),\la
+#if __PA_LDCW_ALIGNMENT > 4
+ load32 pa_tlb_lock + __PA_LDCW_ALIGNMENT-1, \la
+ depi 0,31,__PA_LDCW_ALIGN_ORDER, \la
+#else
+ load32 pa_tlb_lock, \la
+#endif
rsm PSW_SM_I,\flags
1: LDCW 0(\la),\tmp
cmpib,<>,n 0,\tmp,3f
diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c
index e07eb34c8750..36434d4da381 100644
--- a/arch/parisc/kernel/pdt.c
+++ b/arch/parisc/kernel/pdt.c
@@ -325,7 +325,7 @@ static int pdt_mainloop(void *unused)
#ifdef CONFIG_MEMORY_FAILURE
if ((pde & PDT_ADDR_PERM_ERR) ||
((pde & PDT_ADDR_SINGLE_ERR) == 0))
- memory_failure(pde >> PAGE_SHIFT, 0, 0);
+ memory_failure(pde >> PAGE_SHIFT, 0);
else
soft_offline_page(
pfn_to_page(pde >> PAGE_SHIFT), 0);
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 30f92391a93e..cad3e8661cd6 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -39,6 +39,7 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/fs.h>
+#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/personality.h>
#include <linux/ptrace.h>
@@ -184,6 +185,44 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r)
}
/*
+ * Idle thread support
+ *
+ * Detect when running on QEMU with SeaBIOS PDC Firmware and let
+ * QEMU idle the host too.
+ */
+
+int running_on_qemu __read_mostly;
+
+void __cpuidle arch_cpu_idle_dead(void)
+{
+ /* nop on real hardware, qemu will offline CPU. */
+ asm volatile("or %%r31,%%r31,%%r31\n":::);
+}
+
+void __cpuidle arch_cpu_idle(void)
+{
+ local_irq_enable();
+
+ /* nop on real hardware, qemu will idle sleep. */
+ asm volatile("or %%r10,%%r10,%%r10\n":::);
+}
+
+static int __init parisc_idle_init(void)
+{
+ const char *marker;
+
+ /* check QEMU/SeaBIOS marker in PAGE0 */
+ marker = (char *) &PAGE0->pad0;
+ running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0);
+
+ if (!running_on_qemu)
+ cpu_idle_poll_ctrl(1);
+
+ return 0;
+}
+arch_initcall(parisc_idle_init);
+
+/*
* Copy architecture-specific thread state
*/
int
diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c
index 41afa9cd1f55..e8ef3eb69449 100644
--- a/arch/parisc/kernel/signal32.c
+++ b/arch/parisc/kernel/signal32.c
@@ -260,109 +260,3 @@ setup_sigcontext32(struct compat_sigcontext __user *sc, struct compat_regfile __
return err;
}
-
-int
-copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from)
-{
- compat_uptr_t addr;
- int err;
-
- if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
- return -EFAULT;
-
- err = __get_user(to->si_signo, &from->si_signo);
- err |= __get_user(to->si_errno, &from->si_errno);
- err |= __get_user(to->si_code, &from->si_code);
-
- if (to->si_code < 0)
- err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
- else {
- switch (siginfo_layout(to->si_signo, to->si_code)) {
- case SIL_CHLD:
- err |= __get_user(to->si_utime, &from->si_utime);
- err |= __get_user(to->si_stime, &from->si_stime);
- err |= __get_user(to->si_status, &from->si_status);
- default:
- case SIL_KILL:
- err |= __get_user(to->si_pid, &from->si_pid);
- err |= __get_user(to->si_uid, &from->si_uid);
- break;
- case SIL_FAULT:
- err |= __get_user(addr, &from->si_addr);
- to->si_addr = compat_ptr(addr);
- break;
- case SIL_POLL:
- err |= __get_user(to->si_band, &from->si_band);
- err |= __get_user(to->si_fd, &from->si_fd);
- break;
- case SIL_RT:
- err |= __get_user(to->si_pid, &from->si_pid);
- err |= __get_user(to->si_uid, &from->si_uid);
- err |= __get_user(to->si_int, &from->si_int);
- break;
- }
- }
- return err;
-}
-
-int
-copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from)
-{
- compat_uptr_t addr;
- compat_int_t val;
- int err;
-
- if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
- return -EFAULT;
-
- /* If you change siginfo_t structure, please be sure
- this code is fixed accordingly.
- It should never copy any pad contained in the structure
- to avoid security leaks, but must copy the generic
- 3 ints plus the relevant union member.
- This routine must convert siginfo from 64bit to 32bit as well
- at the same time. */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user(from->si_code, &to->si_code);
- if (from->si_code < 0)
- err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
- else {
- switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_CHLD:
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- err |= __put_user(from->si_status, &to->si_status);
- case SIL_KILL:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- case SIL_FAULT:
- addr = ptr_to_compat(from->si_addr);
- err |= __put_user(addr, &to->si_addr);
- break;
- case SIL_POLL:
- err |= __put_user(from->si_band, &to->si_band);
- err |= __put_user(from->si_fd, &to->si_fd);
- break;
- case SIL_TIMER:
- err |= __put_user(from->si_tid, &to->si_tid);
- err |= __put_user(from->si_overrun, &to->si_overrun);
- val = (compat_int_t)from->si_int;
- err |= __put_user(val, &to->si_int);
- break;
- case SIL_RT:
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_pid, &to->si_pid);
- val = (compat_int_t)from->si_int;
- err |= __put_user(val, &to->si_int);
- break;
- case SIL_SYS:
- err |= __put_user(ptr_to_compat(from->si_call_addr), &to->si_call_addr);
- err |= __put_user(from->si_syscall, &to->si_syscall);
- err |= __put_user(from->si_arch, &to->si_arch);
- break;
- }
- }
- return err;
-}
diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h
index 719e7417732c..a271dc0976ce 100644
--- a/arch/parisc/kernel/signal32.h
+++ b/arch/parisc/kernel/signal32.h
@@ -34,9 +34,6 @@ struct compat_ucontext {
/* ELF32 signal handling */
-int copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from);
-int copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from);
-
/* In a deft move of uber-hackery, we decide to carry the top half of all
* 64-bit registers in a non-portable, non-ABI, hidden structure.
* Userspace can read the hidden structure if it *wants* but is never
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 8453724b8009..c919e6c0a687 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -629,7 +629,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
si.si_signo = SIGFPE;
/* Set to zero, and let the userspace app figure it out from
the insn pointed to by si_addr */
- si.si_code = 0;
+ si.si_code = FPE_FIXME;
si.si_addr = (void __user *) regs->iaoq[0];
force_sig_info(SIGFPE, &si, current);
return;
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 5a657986ebbf..143f90e2f9f3 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -15,7 +15,6 @@
#include <linux/slab.h>
#include <linux/kallsyms.h>
#include <linux/sort.h>
-#include <linux/sched.h>
#include <linux/uaccess.h>
#include <asm/assembly.h>
diff --git a/arch/parisc/lib/delay.c b/arch/parisc/lib/delay.c
index 7eab4bb8abe6..66e506520505 100644
--- a/arch/parisc/lib/delay.c
+++ b/arch/parisc/lib/delay.c
@@ -16,9 +16,7 @@
#include <linux/preempt.h>
#include <linux/init.h>
-#include <asm/processor.h>
#include <asm/delay.h>
-
#include <asm/special_insns.h> /* for mfctl() */
#include <asm/processor.h> /* for boot_cpu_data */
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 13f7854e0d49..48f41399fc0b 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -631,11 +631,11 @@ void __init mem_init(void)
mem_init_print_info(NULL);
#ifdef CONFIG_DEBUG_KERNEL /* double-sanity-check paranoia */
printk("virtual kernel memory layout:\n"
- " vmalloc : 0x%p - 0x%p (%4ld MB)\n"
- " memory : 0x%p - 0x%p (%4ld MB)\n"
- " .init : 0x%p - 0x%p (%4ld kB)\n"
- " .data : 0x%p - 0x%p (%4ld kB)\n"
- " .text : 0x%p - 0x%p (%4ld kB)\n",
+ " vmalloc : 0x%px - 0x%px (%4ld MB)\n"
+ " memory : 0x%px - 0x%px (%4ld MB)\n"
+ " .init : 0x%px - 0x%px (%4ld kB)\n"
+ " .data : 0x%px - 0x%px (%4ld kB)\n"
+ " .text : 0x%px - 0x%px (%4ld kB)\n",
(void*)VMALLOC_START, (void*)VMALLOC_END,
(VMALLOC_END - VMALLOC_START) >> 20,
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c51e6ce42e7a..2ed525a44734 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -166,6 +166,7 @@ config PPC
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select GENERIC_CMOS_UPDATE
select GENERIC_CPU_AUTOPROBE
+ select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64
select GENERIC_IRQ_SHOW
select GENERIC_IRQ_SHOW_LEVEL
select GENERIC_SMP_IDLE_THREAD
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index cc49c95494da..e0567dc41968 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -71,7 +71,6 @@ CONFIG_IP_ROUTE_MULTIPATH=y
CONFIG_IP_ROUTE_VERBOSE=y
CONFIG_IP_SCTP=m
CONFIG_IPV6=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_ISO9660_FS=m
CONFIG_JFFS2_FS_DEBUG=1
CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 4891bbed6258..73dab7a37386 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -4,7 +4,6 @@ CONFIG_CPU_LITTLE_ENDIAN=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_AUDIT=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_TASKSTATS=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 6ddca80c52c3..5033e630afea 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -1,7 +1,6 @@
CONFIG_PPC64=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_TASKSTATS=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index bde2cd1005a2..0dd5cf7b566d 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -3,7 +3,6 @@ CONFIG_NR_CPUS=2048
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_AUDIT=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_TASKSTATS=y
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 9a677cd5997f..44697817ccc6 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1005,7 +1005,6 @@ static inline int pmd_protnone(pmd_t pmd)
}
#endif /* CONFIG_NUMA_BALANCING */
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
#define __pmd_write(pmd) __pte_write(pmd_pte(pmd))
#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd))
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 8a2aecfe9b02..62168e1158f1 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -119,71 +119,6 @@ typedef u32 compat_old_sigset_t;
typedef u32 compat_sigset_word;
-typedef union compat_sigval {
- compat_int_t sival_int;
- compat_uptr_t sival_ptr;
-} compat_sigval_t;
-
-#define SI_PAD_SIZE32 (128/sizeof(int) - 3)
-
-typedef struct compat_siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[SI_PAD_SIZE32];
-
- /* kill() */
- struct {
- compat_pid_t _pid; /* sender's pid */
- __compat_uid_t _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- compat_sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- compat_pid_t _pid; /* sender's pid */
- __compat_uid_t _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- compat_pid_t _pid; /* which child */
- __compat_uid_t _uid; /* sender's uid */
- int _status; /* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */
- struct {
- unsigned int _addr; /* faulting insn/memory ref. */
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
-
- /* SIGSYS */
- struct {
- unsigned int _call_addr; /* calling insn */
- int _syscall; /* triggering system call number */
- unsigned int _arch; /* AUDIT_ARCH_* of syscall */
- } _sigsys;
- } _sifields;
-} compat_siginfo_t;
-
#define COMPAT_OFF_T_MAX 0x7fffffff
/*
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
index 14e71ff6579e..fc97404de0a3 100644
--- a/arch/powerpc/include/asm/debug.h
+++ b/arch/powerpc/include/asm/debug.h
@@ -49,7 +49,7 @@ void set_breakpoint(struct arch_hw_breakpoint *brk);
void __set_breakpoint(struct arch_hw_breakpoint *brk);
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
extern void do_send_trap(struct pt_regs *regs, unsigned long address,
- unsigned long error_code, int signal_code, int brkpt);
+ unsigned long error_code, int brkpt);
#else
extern void do_break(struct pt_regs *regs, unsigned long address,
diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
index a703452d67b6..555e22d5e07f 100644
--- a/arch/powerpc/include/asm/exception-64e.h
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -209,5 +209,11 @@ exc_##label##_book3e:
ori r3,r3,vector_offset@l; \
mtspr SPRN_IVOR##vector_number,r3;
+#define RFI_TO_KERNEL \
+ rfi
+
+#define RFI_TO_USER \
+ rfi
+
#endif /* _ASM_POWERPC_EXCEPTION_64E_H */
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index b27205297e1d..7197b179c1b1 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -74,6 +74,59 @@
*/
#define EX_R3 EX_DAR
+/*
+ * Macros for annotating the expected destination of (h)rfid
+ *
+ * The nop instructions allow us to insert one or more instructions to flush the
+ * L1-D cache when returning to userspace or a guest.
+ */
+#define RFI_FLUSH_SLOT \
+ RFI_FLUSH_FIXUP_SECTION; \
+ nop; \
+ nop; \
+ nop
+
+#define RFI_TO_KERNEL \
+ rfid
+
+#define RFI_TO_USER \
+ RFI_FLUSH_SLOT; \
+ rfid; \
+ b rfi_flush_fallback
+
+#define RFI_TO_USER_OR_KERNEL \
+ RFI_FLUSH_SLOT; \
+ rfid; \
+ b rfi_flush_fallback
+
+#define RFI_TO_GUEST \
+ RFI_FLUSH_SLOT; \
+ rfid; \
+ b rfi_flush_fallback
+
+#define HRFI_TO_KERNEL \
+ hrfid
+
+#define HRFI_TO_USER \
+ RFI_FLUSH_SLOT; \
+ hrfid; \
+ b hrfi_flush_fallback
+
+#define HRFI_TO_USER_OR_KERNEL \
+ RFI_FLUSH_SLOT; \
+ hrfid; \
+ b hrfi_flush_fallback
+
+#define HRFI_TO_GUEST \
+ RFI_FLUSH_SLOT; \
+ hrfid; \
+ b hrfi_flush_fallback
+
+#define HRFI_TO_UNKNOWN \
+ RFI_FLUSH_SLOT; \
+ hrfid; \
+ b hrfi_flush_fallback
+
#ifdef CONFIG_RELOCATABLE
#define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \
mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \
@@ -218,7 +271,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
mtspr SPRN_##h##SRR0,r12; \
mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \
mtspr SPRN_##h##SRR1,r10; \
- h##rfid; \
+ h##RFI_TO_KERNEL; \
b . /* prevent speculative execution */
#define EXCEPTION_PROLOG_PSERIES_1(label, h) \
__EXCEPTION_PROLOG_PSERIES_1(label, h)
@@ -232,7 +285,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
mtspr SPRN_##h##SRR0,r12; \
mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \
mtspr SPRN_##h##SRR1,r10; \
- h##rfid; \
+ h##RFI_TO_KERNEL; \
b . /* prevent speculative execution */
#define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) \
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 8f88f771cc55..1e82eb3caabd 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -187,7 +187,20 @@ label##3: \
FTR_ENTRY_OFFSET label##1b-label##3b; \
.popsection;
+#define RFI_FLUSH_FIXUP_SECTION \
+951: \
+ .pushsection __rfi_flush_fixup,"a"; \
+ .align 2; \
+952: \
+ FTR_ENTRY_OFFSET 951b-952b; \
+ .popsection;
+
+
#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
+
void apply_feature_fixups(void);
void setup_feature_keys(void);
#endif
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index a409177be8bd..eca3f9c68907 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -241,6 +241,7 @@
#define H_GET_HCA_INFO 0x1B8
#define H_GET_PERF_COUNT 0x1BC
#define H_MANAGE_TRACE 0x1C0
+#define H_GET_CPU_CHARACTERISTICS 0x1C8
#define H_FREE_LOGICAL_LAN_BUFFER 0x1D4
#define H_QUERY_INT_STATE 0x1E4
#define H_POLL_PENDING 0x1D8
@@ -330,6 +331,17 @@
#define H_SIGNAL_SYS_RESET_ALL_OTHERS -2
/* >= 0 values are CPU number */
+/* H_GET_CPU_CHARACTERISTICS return values */
+#define H_CPU_CHAR_SPEC_BAR_ORI31 (1ull << 63) // IBM bit 0
+#define H_CPU_CHAR_BCCTRL_SERIALISED (1ull << 62) // IBM bit 1
+#define H_CPU_CHAR_L1D_FLUSH_ORI30 (1ull << 61) // IBM bit 2
+#define H_CPU_CHAR_L1D_FLUSH_TRIG2 (1ull << 60) // IBM bit 3
+#define H_CPU_CHAR_L1D_THREAD_PRIV (1ull << 59) // IBM bit 4
+
+#define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0
+#define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1
+#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2
+
/* Flag values used in H_REGISTER_PROC_TBL hcall */
#define PROC_TABLE_OP_MASK 0x18
#define PROC_TABLE_DEREG 0x10
@@ -341,6 +353,7 @@
#define PROC_TABLE_GTSE 0x01
#ifndef __ASSEMBLY__
+#include <linux/types.h>
/**
* plpar_hcall_norets: - Make a pseries hypervisor call with no return arguments
@@ -436,6 +449,11 @@ static inline unsigned int get_longbusy_msecs(int longbusy_rc)
}
}
+struct h_cpu_char_result {
+ u64 character;
+ u64 behaviour;
+};
+
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_HVCALL_H */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 96753f3aac6d..941c2a3f231b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -180,6 +180,7 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
struct iommu_group *grp);
extern int kvmppc_switch_mmu_to_hpt(struct kvm *kvm);
extern int kvmppc_switch_mmu_to_radix(struct kvm *kvm);
+extern void kvmppc_setup_partition_table(struct kvm *kvm);
extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce_64 *args);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 73b92017b6d7..cd2fc1cc1cc7 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -76,6 +76,7 @@ struct machdep_calls {
void __noreturn (*restart)(char *cmd);
void __noreturn (*halt)(void);
+ void (*panic)(char *str);
void (*cpu_die)(void);
long (*time_init)(void); /* Optional, may be NULL */
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 6177d43f0ce8..e2a2b8400490 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -160,9 +160,10 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
#endif
}
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
- struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+ struct mm_struct *mm)
{
+ return 0;
}
#ifndef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 3892db93b837..23ac7fc0af23 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -232,6 +232,16 @@ struct paca_struct {
struct sibling_subcore_state *sibling_subcore_state;
#endif
#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ /*
+ * rfi fallback flush must be in its own cacheline to prevent
+ * other paca data leaking into the L1d
+ */
+ u64 exrfi[EX_SIZE] __aligned(0x80);
+ void *rfi_flush_fallback_area;
+ u64 l1d_flush_congruence;
+ u64 l1d_flush_sets;
+#endif
};
extern void copy_mm_to_paca(struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 7f01b22fa6cb..55eddf50d149 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -326,4 +326,18 @@ static inline long plapr_signal_sys_reset(long cpu)
return plpar_hcall_norets(H_SIGNAL_SYS_RESET, cpu);
}
+static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
+{
+ unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+ long rc;
+
+ rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf);
+ if (rc == H_SUCCESS) {
+ p->character = retbuf[0];
+ p->behaviour = retbuf[1];
+ }
+
+ return rc;
+}
+
#endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 257d23dbf55d..469b7fdc9be4 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -24,6 +24,7 @@ extern void reloc_got2(unsigned long);
void check_for_initrd(void);
void initmem_init(void);
+void setup_panic(void);
#define ARCH_PANIC_TIMEOUT 180
#ifdef CONFIG_PPC_PSERIES
@@ -38,6 +39,19 @@ static inline void pseries_big_endian_exceptions(void) {}
static inline void pseries_little_endian_exceptions(void) {}
#endif /* CONFIG_PPC_PSERIES */
+void rfi_flush_enable(bool enable);
+
+/* These are bit flags */
+enum l1d_flush_type {
+ L1D_FLUSH_NONE = 0x1,
+ L1D_FLUSH_FALLBACK = 0x2,
+ L1D_FLUSH_ORI = 0x4,
+ L1D_FLUSH_MTTRIG = 0x8,
+};
+
+void __init setup_rfi_flush(enum l1d_flush_type, bool enable);
+void do_rfi_flush_fixups(enum l1d_flush_type types);
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index a264c3ad366b..4a12c00f8de3 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -58,9 +58,6 @@ struct thread_info {
.flags = 0, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT)
/* how to get the thread information struct from C */
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 0d960ef78a9a..1a6ed5919ffd 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += param.h
generic-y += poll.h
generic-y += resource.h
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 61d6049f4c1e..637b7263cb86 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info {
__u32 ap_encodings[8];
};
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+ __u64 character; /* characteristics of the CPU */
+ __u64 behaviour; /* recommended software behaviour */
+ __u64 character_mask; /* valid bits in character */
+ __u64 behaviour_mask; /* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 (1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED (1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 (1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 (1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV (1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61)
+
/* Per-vcpu XICS interrupt controller state */
#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
diff --git a/arch/powerpc/include/uapi/asm/siginfo.h b/arch/powerpc/include/uapi/asm/siginfo.h
index 1a691141e49f..9f142451a01f 100644
--- a/arch/powerpc/include/uapi/asm/siginfo.h
+++ b/arch/powerpc/include/uapi/asm/siginfo.h
@@ -15,7 +15,19 @@
#include <asm-generic/siginfo.h>
-#undef NSIGTRAP
-#define NSIGTRAP 4
+/*
+ * SIGFPE si_codes
+ */
+#ifdef __KERNEL__
+#define FPE_FIXME 0 /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
+/*
+ * SIGTRAP si_codes
+ */
+#ifdef __KERNEL__
+#define TRAP_FIXME 0 /* Broken dup of SI_USER */
+#endif /* __KERNEL__ */
+
#endif /* _ASM_POWERPC_SIGINFO_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6b958414b4e0..f390d57cf2e1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -237,6 +237,11 @@ int main(void)
OFFSET(PACA_NMI_EMERG_SP, paca_struct, nmi_emergency_sp);
OFFSET(PACA_IN_MCE, paca_struct, in_mce);
OFFSET(PACA_IN_NMI, paca_struct, in_nmi);
+ OFFSET(PACA_RFI_FLUSH_FALLBACK_AREA, paca_struct, rfi_flush_fallback_area);
+ OFFSET(PACA_EXRFI, paca_struct, exrfi);
+ OFFSET(PACA_L1D_FLUSH_CONGRUENCE, paca_struct, l1d_flush_congruence);
+ OFFSET(PACA_L1D_FLUSH_SETS, paca_struct, l1d_flush_sets);
+
#endif
OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 610955fe8b81..679bbe714e85 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -102,6 +102,7 @@ _GLOBAL(__setup_cpu_power9)
li r0,0
mtspr SPRN_PSSCR,r0
mtspr SPRN_LPID,r0
+ mtspr SPRN_PID,r0
mfspr r3,SPRN_LPCR
LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
or r3, r3, r4
@@ -126,6 +127,7 @@ _GLOBAL(__restore_cpu_power9)
li r0,0
mtspr SPRN_PSSCR,r0
mtspr SPRN_LPID,r0
+ mtspr SPRN_PID,r0
mfspr r3,SPRN_LPCR
LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
or r3, r3, r4
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 3320bcac7192..2748584b767d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -37,6 +37,11 @@
#include <asm/tm.h>
#include <asm/ppc-opcode.h>
#include <asm/export.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
/*
* System calls.
@@ -262,13 +267,23 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
ld r13,GPR13(r1) /* only restore r13 if returning to usermode */
+ ld r2,GPR2(r1)
+ ld r1,GPR1(r1)
+ mtlr r4
+ mtcr r5
+ mtspr SPRN_SRR0,r7
+ mtspr SPRN_SRR1,r8
+ RFI_TO_USER
+ b . /* prevent speculative execution */
+
+ /* exit to kernel */
1: ld r2,GPR2(r1)
ld r1,GPR1(r1)
mtlr r4
mtcr r5
mtspr SPRN_SRR0,r7
mtspr SPRN_SRR1,r8
- RFI
+ RFI_TO_KERNEL
b . /* prevent speculative execution */
.Lsyscall_error:
@@ -397,8 +412,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
mtmsrd r10, 1
mtspr SPRN_SRR0, r11
mtspr SPRN_SRR1, r12
-
- rfid
+ RFI_TO_USER
b . /* prevent speculative execution */
#endif
_ASM_NOKPROBE_SYMBOL(system_call_common);
@@ -878,7 +892,7 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
REST_GPR(13, r1)
-1:
+
mtspr SPRN_SRR1,r3
ld r2,_CCR(r1)
@@ -891,8 +905,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
ld r3,GPR3(r1)
ld r4,GPR4(r1)
ld r1,GPR1(r1)
+ RFI_TO_USER
+ b . /* prevent speculative execution */
- rfid
+1: mtspr SPRN_SRR1,r3
+
+ ld r2,_CCR(r1)
+ mtcrf 0xFF,r2
+ ld r2,_NIP(r1)
+ mtspr SPRN_SRR0,r2
+
+ ld r0,GPR0(r1)
+ ld r2,GPR2(r1)
+ ld r3,GPR3(r1)
+ ld r4,GPR4(r1)
+ ld r1,GPR1(r1)
+ RFI_TO_KERNEL
b . /* prevent speculative execution */
#endif /* CONFIG_PPC_BOOK3E */
@@ -1073,7 +1101,7 @@ __enter_rtas:
mtspr SPRN_SRR0,r5
mtspr SPRN_SRR1,r6
- rfid
+ RFI_TO_KERNEL
b . /* prevent speculative execution */
rtas_return_loc:
@@ -1098,7 +1126,7 @@ rtas_return_loc:
mtspr SPRN_SRR0,r3
mtspr SPRN_SRR1,r4
- rfid
+ RFI_TO_KERNEL
b . /* prevent speculative execution */
_ASM_NOKPROBE_SYMBOL(__enter_rtas)
_ASM_NOKPROBE_SYMBOL(rtas_return_loc)
@@ -1171,7 +1199,7 @@ _GLOBAL(enter_prom)
LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE)
andc r11,r11,r12
mtsrr1 r11
- rfid
+ RFI_TO_KERNEL
#endif /* CONFIG_PPC_BOOK3E */
1: /* Return from OF */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e441b469dc8f..2dc10bf646b8 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -256,7 +256,7 @@ BEGIN_FTR_SECTION
LOAD_HANDLER(r12, machine_check_handle_early)
1: mtspr SPRN_SRR0,r12
mtspr SPRN_SRR1,r11
- rfid
+ RFI_TO_KERNEL
b . /* prevent speculative execution */
2:
/* Stack overflow. Stay on emergency stack and panic.
@@ -445,7 +445,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
li r3,MSR_ME
andc r10,r10,r3 /* Turn off MSR_ME */
mtspr SPRN_SRR1,r10
- rfid
+ RFI_TO_KERNEL
b .
2:
/*
@@ -463,7 +463,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
*/
bl machine_check_queue_event
MACHINE_CHECK_HANDLER_WINDUP
- rfid
+ RFI_TO_USER_OR_KERNEL
9:
/* Deliver the machine check to host kernel in V mode. */
MACHINE_CHECK_HANDLER_WINDUP
@@ -598,6 +598,9 @@ EXC_COMMON_BEGIN(slb_miss_common)
stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */
std r10,PACA_EXSLB+EX_LR(r13) /* save LR */
+ andi. r9,r11,MSR_PR // Check for exception from userspace
+ cmpdi cr4,r9,MSR_PR // And save the result in CR4 for later
+
/*
* Test MSR_RI before calling slb_allocate_realmode, because the
* MSR in r11 gets clobbered. However we still want to allocate
@@ -624,9 +627,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
/* All done -- return from exception. */
+ bne cr4,1f /* returning to kernel */
+
.machine push
.machine "power4"
mtcrf 0x80,r9
+ mtcrf 0x08,r9 /* MSR[PR] indication is in cr4 */
mtcrf 0x04,r9 /* MSR[RI] indication is in cr5 */
mtcrf 0x02,r9 /* I/D indication is in cr6 */
mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */
@@ -640,9 +646,30 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
ld r11,PACA_EXSLB+EX_R11(r13)
ld r12,PACA_EXSLB+EX_R12(r13)
ld r13,PACA_EXSLB+EX_R13(r13)
- rfid
+ RFI_TO_USER
+ b . /* prevent speculative execution */
+1:
+.machine push
+.machine "power4"
+ mtcrf 0x80,r9
+ mtcrf 0x08,r9 /* MSR[PR] indication is in cr4 */
+ mtcrf 0x04,r9 /* MSR[RI] indication is in cr5 */
+ mtcrf 0x02,r9 /* I/D indication is in cr6 */
+ mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */
+.machine pop
+
+ RESTORE_CTR(r9, PACA_EXSLB)
+ RESTORE_PPR_PACA(PACA_EXSLB, r9)
+ mr r3,r12
+ ld r9,PACA_EXSLB+EX_R9(r13)
+ ld r10,PACA_EXSLB+EX_R10(r13)
+ ld r11,PACA_EXSLB+EX_R11(r13)
+ ld r12,PACA_EXSLB+EX_R12(r13)
+ ld r13,PACA_EXSLB+EX_R13(r13)
+ RFI_TO_KERNEL
b . /* prevent speculative execution */
+
2: std r3,PACA_EXSLB+EX_DAR(r13)
mr r3,r12
mfspr r11,SPRN_SRR0
@@ -651,7 +678,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
mtspr SPRN_SRR0,r10
ld r10,PACAKMSR(r13)
mtspr SPRN_SRR1,r10
- rfid
+ RFI_TO_KERNEL
b .
8: std r3,PACA_EXSLB+EX_DAR(r13)
@@ -662,7 +689,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
mtspr SPRN_SRR0,r10
ld r10,PACAKMSR(r13)
mtspr SPRN_SRR1,r10
- rfid
+ RFI_TO_KERNEL
b .
EXC_COMMON_BEGIN(unrecov_slb)
@@ -901,7 +928,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
mtspr SPRN_SRR0,r10 ; \
ld r10,PACAKMSR(r13) ; \
mtspr SPRN_SRR1,r10 ; \
- rfid ; \
+ RFI_TO_KERNEL ; \
b . ; /* prevent speculative execution */
#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
@@ -917,7 +944,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \
xori r12,r12,MSR_LE ; \
mtspr SPRN_SRR1,r12 ; \
mr r13,r9 ; \
- rfid ; /* return to userspace */ \
+ RFI_TO_USER ; /* return to userspace */ \
b . ; /* prevent speculative execution */
#else
#define SYSCALL_FASTENDIAN_TEST
@@ -1063,7 +1090,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early)
mtcr r11
REST_GPR(11, r1)
ld r1,GPR1(r1)
- hrfid
+ HRFI_TO_USER_OR_KERNEL
1: mtcr r11
REST_GPR(11, r1)
@@ -1314,7 +1341,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
ld r11,PACA_EXGEN+EX_R11(r13)
ld r12,PACA_EXGEN+EX_R12(r13)
ld r13,PACA_EXGEN+EX_R13(r13)
- HRFID
+ HRFI_TO_UNKNOWN
b .
#endif
@@ -1418,10 +1445,94 @@ masked_##_H##interrupt: \
ld r10,PACA_EXGEN+EX_R10(r13); \
ld r11,PACA_EXGEN+EX_R11(r13); \
/* returns to kernel where r13 must be set up, so don't restore it */ \
- ##_H##rfid; \
+ ##_H##RFI_TO_KERNEL; \
b .; \
MASKED_DEC_HANDLER(_H)
+TRAMP_REAL_BEGIN(rfi_flush_fallback)
+ SET_SCRATCH0(r13);
+ GET_PACA(r13);
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ std r12,PACA_EXRFI+EX_R12(r13)
+ std r8,PACA_EXRFI+EX_R13(r13)
+ mfctr r9
+ ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+ ld r11,PACA_L1D_FLUSH_SETS(r13)
+ ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13)
+ /*
+ * The load adresses are at staggered offsets within cachelines,
+ * which suits some pipelines better (on others it should not
+ * hurt).
+ */
+ addi r12,r12,8
+ mtctr r11
+ DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+ /* order ld/st prior to dcbt stop all streams with flushing */
+ sync
+1: li r8,0
+ .rept 8 /* 8-way set associative */
+ ldx r11,r10,r8
+ add r8,r8,r12
+ xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not
+ add r8,r8,r11 // Add 0, this creates a dependency on the ldx
+ .endr
+ addi r10,r10,128 /* 128 byte cache line */
+ bdnz 1b
+
+ mtctr r9
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ ld r12,PACA_EXRFI+EX_R12(r13)
+ ld r8,PACA_EXRFI+EX_R13(r13)
+ GET_SCRATCH0(r13);
+ rfid
+
+TRAMP_REAL_BEGIN(hrfi_flush_fallback)
+ SET_SCRATCH0(r13);
+ GET_PACA(r13);
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ std r12,PACA_EXRFI+EX_R12(r13)
+ std r8,PACA_EXRFI+EX_R13(r13)
+ mfctr r9
+ ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+ ld r11,PACA_L1D_FLUSH_SETS(r13)
+ ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13)
+ /*
+ * The load adresses are at staggered offsets within cachelines,
+ * which suits some pipelines better (on others it should not
+ * hurt).
+ */
+ addi r12,r12,8
+ mtctr r11
+ DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+ /* order ld/st prior to dcbt stop all streams with flushing */
+ sync
+1: li r8,0
+ .rept 8 /* 8-way set associative */
+ ldx r11,r10,r8
+ add r8,r8,r12
+ xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not
+ add r8,r8,r11 // Add 0, this creates a dependency on the ldx
+ .endr
+ addi r10,r10,128 /* 128 byte cache line */
+ bdnz 1b
+
+ mtctr r9
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ ld r12,PACA_EXRFI+EX_R12(r13)
+ ld r8,PACA_EXRFI+EX_R13(r13)
+ GET_SCRATCH0(r13);
+ hrfid
+
/*
* Real mode exceptions actually use this too, but alternate
* instruction code patches (which end up in the common .text area)
@@ -1441,7 +1552,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
addi r13, r13, 4
mtspr SPRN_SRR0, r13
GET_SCRATCH0(r13)
- rfid
+ RFI_TO_KERNEL
b .
TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
@@ -1453,7 +1564,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
addi r13, r13, 4
mtspr SPRN_HSRR0, r13
GET_SCRATCH0(r13)
- hrfid
+ HRFI_TO_KERNEL
b .
#endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 04ea5c04fd24..3c2c2688918f 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -1462,25 +1462,6 @@ static void fadump_init_files(void)
return;
}
-static int fadump_panic_event(struct notifier_block *this,
- unsigned long event, void *ptr)
-{
- /*
- * If firmware-assisted dump has been registered then trigger
- * firmware-assisted dump and let firmware handle everything
- * else. If this returns, then fadump was not registered, so
- * go through the rest of the panic path.
- */
- crash_fadump(NULL, ptr);
-
- return NOTIFY_DONE;
-}
-
-static struct notifier_block fadump_panic_block = {
- .notifier_call = fadump_panic_event,
- .priority = INT_MIN /* may not return; must be done last */
-};
-
/*
* Prepare for firmware-assisted dump.
*/
@@ -1513,9 +1494,6 @@ int __init setup_fadump(void)
init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
fadump_init_files();
- atomic_notifier_chain_register(&panic_notifier_list,
- &fadump_panic_block);
-
return 1;
}
subsys_initcall(setup_fadump);
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 742e4658c5dc..71e8a1b8c86e 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -273,7 +273,7 @@ static void machine_process_ue_event(struct work_struct *work)
pfn = evt->u.ue_error.physical_address >>
PAGE_SHIFT;
- memory_failure(pfn, SIGBUS, 0);
+ memory_failure(pfn, 0);
} else
pr_warn("Failed to identify bad address from "
"where the uncorrectable error (UE) "
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 8ac0bd2bddb0..3280953a82cf 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -623,7 +623,9 @@ BEGIN_FTR_SECTION
* NOTE, we rely on r0 being 0 from above.
*/
mtspr SPRN_IAMR,r0
+BEGIN_FTR_SECTION_NESTED(42)
mtspr SPRN_AMOR,r0
+END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
/* save regs for local vars on new stack.
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index bfdd783e3916..4208cbe2fb7f 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -601,21 +601,16 @@ EXPORT_SYMBOL(flush_all_to_thread);
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
void do_send_trap(struct pt_regs *regs, unsigned long address,
- unsigned long error_code, int signal_code, int breakpt)
+ unsigned long error_code, int breakpt)
{
- siginfo_t info;
-
- current->thread.trap_nr = signal_code;
+ current->thread.trap_nr = TRAP_HWBKPT;
if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
11, SIGSEGV) == NOTIFY_STOP)
return;
/* Deliver the signal to userspace */
- info.si_signo = SIGTRAP;
- info.si_errno = breakpt; /* breakpoint or watchpoint id */
- info.si_code = signal_code;
- info.si_addr = (void __user *)address;
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_ptrace_errno_trap(breakpt, /* breakpoint or watchpoint id */
+ (void __user *)address);
}
#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
void do_break (struct pt_regs *regs, unsigned long address,
@@ -1403,7 +1398,7 @@ void show_regs(struct pt_regs * regs)
printk("NIP: "REG" LR: "REG" CTR: "REG"\n",
regs->nip, regs->link, regs->ctr);
- printk("REGS: %p TRAP: %04lx %s (%s)\n",
+ printk("REGS: %px TRAP: %04lx %s (%s)\n",
regs, regs->trap, print_tainted(), init_utsname()->release);
printk("MSR: "REG" ", regs->msr);
print_msr_bits(regs->msr);
@@ -1569,16 +1564,22 @@ void arch_release_task_struct(struct task_struct *t)
*/
int set_thread_tidr(struct task_struct *t)
{
+ int rc;
+
if (!cpu_has_feature(CPU_FTR_ARCH_300))
return -EINVAL;
if (t != current)
return -EINVAL;
- t->thread.tidr = assign_thread_tidr();
- if (t->thread.tidr < 0)
- return t->thread.tidr;
+ if (t->thread.tidr)
+ return 0;
+
+ rc = assign_thread_tidr();
+ if (rc < 0)
+ return rc;
+ t->thread.tidr = rc;
mtspr(SPRN_TIDR, t->thread.tidr);
return 0;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 2075322cd225..8fd3a70047f1 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -242,14 +242,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
unsigned short maj;
unsigned short min;
- /* We only show online cpus: disable preempt (overzealous, I
- * knew) to prevent cpu going down. */
- preempt_disable();
- if (!cpu_online(cpu_id)) {
- preempt_enable();
- return 0;
- }
-
#ifdef CONFIG_SMP
pvr = per_cpu(cpu_pvr, cpu_id);
#else
@@ -358,9 +350,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
#ifdef CONFIG_SMP
seq_printf(m, "\n");
#endif
-
- preempt_enable();
-
/* If this is the last cpu, print the summary */
if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids)
show_cpuinfo_summary(m);
@@ -704,6 +693,30 @@ int check_legacy_ioport(unsigned long base_port)
}
EXPORT_SYMBOL(check_legacy_ioport);
+static int ppc_panic_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ /*
+ * If firmware-assisted dump has been registered then trigger
+ * firmware-assisted dump and let firmware handle everything else.
+ */
+ crash_fadump(NULL, ptr);
+ ppc_md.panic(ptr); /* May not return */
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block ppc_panic_block = {
+ .notifier_call = ppc_panic_event,
+ .priority = INT_MIN /* may not return; must be done last */
+};
+
+void __init setup_panic(void)
+{
+ if (!ppc_md.panic)
+ return;
+ atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
+}
+
#ifdef CONFIG_CHECK_CACHE_COHERENCY
/*
* For platforms that have configurable cache-coherency. This function
@@ -848,6 +861,9 @@ void __init setup_arch(char **cmdline_p)
/* Probe the machine type, establish ppc_md. */
probe_machine();
+ /* Setup panic notifier if requested by the platform. */
+ setup_panic();
+
/*
* Configure ppc_md.power_save (ppc32 only, 64-bit machines do
* it from their respective probe() function.
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 8956a9856604..e67413f4a8f0 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -38,6 +38,7 @@
#include <linux/memory.h>
#include <linux/nmi.h>
+#include <asm/debugfs.h>
#include <asm/io.h>
#include <asm/kdump.h>
#include <asm/prom.h>
@@ -801,3 +802,141 @@ static int __init disable_hardlockup_detector(void)
return 0;
}
early_initcall(disable_hardlockup_detector);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+static enum l1d_flush_type enabled_flush_types;
+static void *l1d_flush_fallback_area;
+static bool no_rfi_flush;
+bool rfi_flush;
+
+static int __init handle_no_rfi_flush(char *p)
+{
+ pr_info("rfi-flush: disabled on command line.");
+ no_rfi_flush = true;
+ return 0;
+}
+early_param("no_rfi_flush", handle_no_rfi_flush);
+
+/*
+ * The RFI flush is not KPTI, but because users will see doco that says to use
+ * nopti we hijack that option here to also disable the RFI flush.
+ */
+static int __init handle_no_pti(char *p)
+{
+ pr_info("rfi-flush: disabling due to 'nopti' on command line.\n");
+ handle_no_rfi_flush(NULL);
+ return 0;
+}
+early_param("nopti", handle_no_pti);
+
+static void do_nothing(void *unused)
+{
+ /*
+ * We don't need to do the flush explicitly, just enter+exit kernel is
+ * sufficient, the RFI exit handlers will do the right thing.
+ */
+}
+
+void rfi_flush_enable(bool enable)
+{
+ if (rfi_flush == enable)
+ return;
+
+ if (enable) {
+ do_rfi_flush_fixups(enabled_flush_types);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else
+ do_rfi_flush_fixups(L1D_FLUSH_NONE);
+
+ rfi_flush = enable;
+}
+
+static void init_fallback_flush(void)
+{
+ u64 l1d_size, limit;
+ int cpu;
+
+ l1d_size = ppc64_caches.l1d.size;
+ limit = min(safe_stack_limit(), ppc64_rma_size);
+
+ /*
+ * Align to L1d size, and size it at 2x L1d size, to catch possible
+ * hardware prefetch runoff. We don't have a recipe for load patterns to
+ * reliably avoid the prefetcher.
+ */
+ l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit));
+ memset(l1d_flush_fallback_area, 0, l1d_size * 2);
+
+ for_each_possible_cpu(cpu) {
+ /*
+ * The fallback flush is currently coded for 8-way
+ * associativity. Different associativity is possible, but it
+ * will be treated as 8-way and may not evict the lines as
+ * effectively.
+ *
+ * 128 byte lines are mandatory.
+ */
+ u64 c = l1d_size / 8;
+
+ paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
+ paca[cpu].l1d_flush_congruence = c;
+ paca[cpu].l1d_flush_sets = c / 128;
+ }
+}
+
+void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
+{
+ if (types & L1D_FLUSH_FALLBACK) {
+ pr_info("rfi-flush: Using fallback displacement flush\n");
+ init_fallback_flush();
+ }
+
+ if (types & L1D_FLUSH_ORI)
+ pr_info("rfi-flush: Using ori type flush\n");
+
+ if (types & L1D_FLUSH_MTTRIG)
+ pr_info("rfi-flush: Using mttrig type flush\n");
+
+ enabled_flush_types = types;
+
+ if (!no_rfi_flush)
+ rfi_flush_enable(enable);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int rfi_flush_set(void *data, u64 val)
+{
+ if (val == 1)
+ rfi_flush_enable(true);
+ else if (val == 0)
+ rfi_flush_enable(false);
+ else
+ return -EINVAL;
+
+ return 0;
+}
+
+static int rfi_flush_get(void *data, u64 *val)
+{
+ *val = rfi_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
+
+static __init int rfi_flush_debugfs_init(void)
+{
+ debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+ return 0;
+}
+device_initcall(rfi_flush_debugfs_init);
+#endif
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ if (rfi_flush)
+ return sprintf(buf, "Mitigation: RFI Flush\n");
+
+ return sprintf(buf, "Vulnerable\n");
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 9ffd73296f64..aded81169648 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -873,75 +873,9 @@ static long restore_tm_user_regs(struct pt_regs *regs,
#endif
#ifdef CONFIG_PPC64
-int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
-{
- int err;
-
- if (!access_ok (VERIFY_WRITE, d, sizeof(*d)))
- return -EFAULT;
-
- /* If you change siginfo_t structure, please be sure
- * this code is fixed accordingly.
- * It should never copy any pad contained in the structure
- * to avoid security leaks, but must copy the generic
- * 3 ints plus the relevant union member.
- * This routine must convert siginfo from 64bit to 32bit as well
- * at the same time.
- */
- err = __put_user(s->si_signo, &d->si_signo);
- err |= __put_user(s->si_errno, &d->si_errno);
- err |= __put_user(s->si_code, &d->si_code);
- if (s->si_code < 0)
- err |= __copy_to_user(&d->_sifields._pad, &s->_sifields._pad,
- SI_PAD_SIZE32);
- else switch(siginfo_layout(s->si_signo, s->si_code)) {
- case SIL_CHLD:
- err |= __put_user(s->si_pid, &d->si_pid);
- err |= __put_user(s->si_uid, &d->si_uid);
- err |= __put_user(s->si_utime, &d->si_utime);
- err |= __put_user(s->si_stime, &d->si_stime);
- err |= __put_user(s->si_status, &d->si_status);
- break;
- case SIL_FAULT:
- err |= __put_user((unsigned int)(unsigned long)s->si_addr,
- &d->si_addr);
- break;
- case SIL_POLL:
- err |= __put_user(s->si_band, &d->si_band);
- err |= __put_user(s->si_fd, &d->si_fd);
- break;
- case SIL_TIMER:
- err |= __put_user(s->si_tid, &d->si_tid);
- err |= __put_user(s->si_overrun, &d->si_overrun);
- err |= __put_user(s->si_int, &d->si_int);
- break;
- case SIL_SYS:
- err |= __put_user(ptr_to_compat(s->si_call_addr), &d->si_call_addr);
- err |= __put_user(s->si_syscall, &d->si_syscall);
- err |= __put_user(s->si_arch, &d->si_arch);
- break;
- case SIL_RT:
- err |= __put_user(s->si_int, &d->si_int);
- /* fallthrough */
- case SIL_KILL:
- err |= __put_user(s->si_pid, &d->si_pid);
- err |= __put_user(s->si_uid, &d->si_uid);
- break;
- }
- return err;
-}
#define copy_siginfo_to_user copy_siginfo_to_user32
-int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
-{
- if (copy_from_user(to, from, 3*sizeof(int)) ||
- copy_from_user(to->_sifields._pad,
- from->_sifields._pad, SI_PAD_SIZE32))
- return -EFAULT;
-
- return 0;
-}
#endif /* CONFIG_PPC64 */
/*
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f3eb61be0d30..c93f1e6a9fff 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -917,7 +917,7 @@ void unknown_exception(struct pt_regs *regs)
printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
regs->nip, regs->msr, regs->trap);
- _exception(SIGTRAP, regs, 0, 0);
+ _exception(SIGTRAP, regs, TRAP_FIXME, 0);
exception_exit(prev_state);
}
@@ -939,7 +939,7 @@ bail:
void RunModeException(struct pt_regs *regs)
{
- _exception(SIGTRAP, regs, 0, 0);
+ _exception(SIGTRAP, regs, TRAP_FIXME, 0);
}
void single_step_exception(struct pt_regs *regs)
@@ -978,7 +978,7 @@ static void emulate_single_step(struct pt_regs *regs)
static inline int __parse_fpscr(unsigned long fpscr)
{
- int ret = 0;
+ int ret = FPE_FIXME;
/* Invalid operation */
if ((fpscr & FPSCR_VE) && (fpscr & FPSCR_VX))
@@ -1750,34 +1750,34 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status)
#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
current->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
#endif
- do_send_trap(regs, mfspr(SPRN_DAC1), debug_status, TRAP_HWBKPT,
+ do_send_trap(regs, mfspr(SPRN_DAC1), debug_status,
5);
changed |= 0x01;
} else if (debug_status & (DBSR_DAC2R | DBSR_DAC2W)) {
dbcr_dac(current) &= ~(DBCR_DAC2R | DBCR_DAC2W);
- do_send_trap(regs, mfspr(SPRN_DAC2), debug_status, TRAP_HWBKPT,
+ do_send_trap(regs, mfspr(SPRN_DAC2), debug_status,
6);
changed |= 0x01;
} else if (debug_status & DBSR_IAC1) {
current->thread.debug.dbcr0 &= ~DBCR0_IAC1;
dbcr_iac_range(current) &= ~DBCR_IAC12MODE;
- do_send_trap(regs, mfspr(SPRN_IAC1), debug_status, TRAP_HWBKPT,
+ do_send_trap(regs, mfspr(SPRN_IAC1), debug_status,
1);
changed |= 0x01;
} else if (debug_status & DBSR_IAC2) {
current->thread.debug.dbcr0 &= ~DBCR0_IAC2;
- do_send_trap(regs, mfspr(SPRN_IAC2), debug_status, TRAP_HWBKPT,
+ do_send_trap(regs, mfspr(SPRN_IAC2), debug_status,
2);
changed |= 0x01;
} else if (debug_status & DBSR_IAC3) {
current->thread.debug.dbcr0 &= ~DBCR0_IAC3;
dbcr_iac_range(current) &= ~DBCR_IAC34MODE;
- do_send_trap(regs, mfspr(SPRN_IAC3), debug_status, TRAP_HWBKPT,
+ do_send_trap(regs, mfspr(SPRN_IAC3), debug_status,
3);
changed |= 0x01;
} else if (debug_status & DBSR_IAC4) {
current->thread.debug.dbcr0 &= ~DBCR0_IAC4;
- do_send_trap(regs, mfspr(SPRN_IAC4), debug_status, TRAP_HWBKPT,
+ do_send_trap(regs, mfspr(SPRN_IAC4), debug_status,
4);
changed |= 0x01;
}
@@ -1929,7 +1929,7 @@ void SPEFloatingPointException(struct pt_regs *regs)
extern int do_spe_mathemu(struct pt_regs *regs);
unsigned long spefscr;
int fpexc_mode;
- int code = 0;
+ int code = FPE_FIXME;
int err;
flush_spe_to_thread(current);
@@ -1998,7 +1998,7 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
printk(KERN_ERR "unrecognized spe instruction "
"in %s at %lx\n", current->comm, regs->nip);
} else {
- _exception(SIGFPE, regs, 0, regs->nip);
+ _exception(SIGFPE, regs, FPE_FIXME, regs->nip);
return;
}
}
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 0494e1566ee2..307843d23682 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -132,6 +132,15 @@ SECTIONS
/* Read-only data */
RO_DATA(PAGE_SIZE)
+#ifdef CONFIG_PPC64
+ . = ALIGN(8);
+ __rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
+ __start___rfi_flush_fixup = .;
+ *(__rfi_flush_fixup)
+ __stop___rfi_flush_fixup = .;
+ }
+#endif
+
EXCEPTION_TABLE(0)
NOTES :kernel :notes
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 29ebe2fd5867..a93d719edc90 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -235,6 +235,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
gpte->may_read = true;
gpte->may_write = true;
gpte->page_size = MMU_PAGE_4K;
+ gpte->wimg = HPTE_R_M;
return 0;
}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 235319c2574e..b73dbc9e797d 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -65,11 +65,17 @@ struct kvm_resize_hpt {
u32 order;
/* These fields protected by kvm->lock */
+
+ /* Possible values and their usage:
+ * <0 an error occurred during allocation,
+ * -EBUSY allocation is in the progress,
+ * 0 allocation made successfuly.
+ */
int error;
- bool prepare_done;
- /* Private to the work thread, until prepare_done is true,
- * then protected by kvm->resize_hpt_sem */
+ /* Private to the work thread, until error != -EBUSY,
+ * then protected by kvm->lock.
+ */
struct kvm_hpt_info hpt;
};
@@ -159,8 +165,6 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
* Reset all the reverse-mapping chains for all memslots
*/
kvmppc_rmap_reset(kvm);
- /* Ensure that each vcpu will flush its TLB on next entry. */
- cpumask_setall(&kvm->arch.need_tlb_flush);
err = 0;
goto out;
}
@@ -176,6 +180,10 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
kvmppc_set_hpt(kvm, &info);
out:
+ if (err == 0)
+ /* Ensure that each vcpu will flush its TLB on next entry. */
+ cpumask_setall(&kvm->arch.need_tlb_flush);
+
mutex_unlock(&kvm->lock);
return err;
}
@@ -1238,8 +1246,9 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
unsigned long vpte, rpte, guest_rpte;
int ret;
struct revmap_entry *rev;
- unsigned long apsize, psize, avpn, pteg, hash;
+ unsigned long apsize, avpn, pteg, hash;
unsigned long new_idx, new_pteg, replace_vpte;
+ int pshift;
hptep = (__be64 *)(old->virt + (idx << 4));
@@ -1298,8 +1307,8 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
goto out;
rpte = be64_to_cpu(hptep[1]);
- psize = hpte_base_page_size(vpte, rpte);
- avpn = HPTE_V_AVPN_VAL(vpte) & ~((psize - 1) >> 23);
+ pshift = kvmppc_hpte_base_page_shift(vpte, rpte);
+ avpn = HPTE_V_AVPN_VAL(vpte) & ~(((1ul << pshift) - 1) >> 23);
pteg = idx / HPTES_PER_GROUP;
if (vpte & HPTE_V_SECONDARY)
pteg = ~pteg;
@@ -1311,20 +1320,20 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
offset = (avpn & 0x1f) << 23;
vsid = avpn >> 5;
/* We can find more bits from the pteg value */
- if (psize < (1ULL << 23))
- offset |= ((vsid ^ pteg) & old_hash_mask) * psize;
+ if (pshift < 23)
+ offset |= ((vsid ^ pteg) & old_hash_mask) << pshift;
- hash = vsid ^ (offset / psize);
+ hash = vsid ^ (offset >> pshift);
} else {
unsigned long offset, vsid;
/* We only have 40 - 23 bits of seg_off in avpn */
offset = (avpn & 0x1ffff) << 23;
vsid = avpn >> 17;
- if (psize < (1ULL << 23))
- offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) * psize;
+ if (pshift < 23)
+ offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) << pshift;
- hash = vsid ^ (vsid << 25) ^ (offset / psize);
+ hash = vsid ^ (vsid << 25) ^ (offset >> pshift);
}
new_pteg = hash & new_hash_mask;
@@ -1412,16 +1421,20 @@ static void resize_hpt_pivot(struct kvm_resize_hpt *resize)
static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize)
{
- BUG_ON(kvm->arch.resize_hpt != resize);
+ if (WARN_ON(!mutex_is_locked(&kvm->lock)))
+ return;
if (!resize)
return;
- if (resize->hpt.virt)
- kvmppc_free_hpt(&resize->hpt);
+ if (resize->error != -EBUSY) {
+ if (resize->hpt.virt)
+ kvmppc_free_hpt(&resize->hpt);
+ kfree(resize);
+ }
- kvm->arch.resize_hpt = NULL;
- kfree(resize);
+ if (kvm->arch.resize_hpt == resize)
+ kvm->arch.resize_hpt = NULL;
}
static void resize_hpt_prepare_work(struct work_struct *work)
@@ -1430,17 +1443,41 @@ static void resize_hpt_prepare_work(struct work_struct *work)
struct kvm_resize_hpt,
work);
struct kvm *kvm = resize->kvm;
- int err;
+ int err = 0;
- resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
- resize->order);
-
- err = resize_hpt_allocate(resize);
+ if (WARN_ON(resize->error != -EBUSY))
+ return;
mutex_lock(&kvm->lock);
+ /* Request is still current? */
+ if (kvm->arch.resize_hpt == resize) {
+ /* We may request large allocations here:
+ * do not sleep with kvm->lock held for a while.
+ */
+ mutex_unlock(&kvm->lock);
+
+ resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
+ resize->order);
+
+ err = resize_hpt_allocate(resize);
+
+ /* We have strict assumption about -EBUSY
+ * when preparing for HPT resize.
+ */
+ if (WARN_ON(err == -EBUSY))
+ err = -EINPROGRESS;
+
+ mutex_lock(&kvm->lock);
+ /* It is possible that kvm->arch.resize_hpt != resize
+ * after we grab kvm->lock again.
+ */
+ }
+
resize->error = err;
- resize->prepare_done = true;
+
+ if (kvm->arch.resize_hpt != resize)
+ resize_hpt_release(kvm, resize);
mutex_unlock(&kvm->lock);
}
@@ -1465,14 +1502,12 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
if (resize) {
if (resize->order == shift) {
- /* Suitable resize in progress */
- if (resize->prepare_done) {
- ret = resize->error;
- if (ret != 0)
- resize_hpt_release(kvm, resize);
- } else {
+ /* Suitable resize in progress? */
+ ret = resize->error;
+ if (ret == -EBUSY)
ret = 100; /* estimated time in ms */
- }
+ else if (ret)
+ resize_hpt_release(kvm, resize);
goto out;
}
@@ -1492,6 +1527,8 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
ret = -ENOMEM;
goto out;
}
+
+ resize->error = -EBUSY;
resize->order = shift;
resize->kvm = kvm;
INIT_WORK(&resize->work, resize_hpt_prepare_work);
@@ -1546,16 +1583,12 @@ long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm,
if (!resize || (resize->order != shift))
goto out;
- ret = -EBUSY;
- if (!resize->prepare_done)
- goto out;
-
ret = resize->error;
- if (ret != 0)
+ if (ret)
goto out;
ret = resize_hpt_rehash(resize);
- if (ret != 0)
+ if (ret)
goto out;
resize_hpt_pivot(resize);
@@ -1801,6 +1834,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
ssize_t nb;
long int err, ret;
int mmu_ready;
+ int pshift;
if (!access_ok(VERIFY_READ, buf, count))
return -EFAULT;
@@ -1855,6 +1889,9 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
err = -EINVAL;
if (!(v & HPTE_V_VALID))
goto out;
+ pshift = kvmppc_hpte_base_page_shift(v, r);
+ if (pshift <= 0)
+ goto out;
lbuf += 2;
nb += HPTE_SIZE;
@@ -1869,14 +1906,18 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
goto out;
}
if (!mmu_ready && is_vrma_hpte(v)) {
- unsigned long psize = hpte_base_page_size(v, r);
- unsigned long senc = slb_pgsize_encoding(psize);
- unsigned long lpcr;
+ unsigned long senc, lpcr;
+ senc = slb_pgsize_encoding(1ul << pshift);
kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
- lpcr = senc << (LPCR_VRMASD_SH - 4);
- kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+ if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+ lpcr = senc << (LPCR_VRMASD_SH - 4);
+ kvmppc_update_lpcr(kvm, lpcr,
+ LPCR_VRMASD);
+ } else {
+ kvmppc_setup_partition_table(kvm);
+ }
mmu_ready = 1;
}
++i;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 79ea3d9269db..2d46037ce936 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -120,7 +120,6 @@ MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
-static void kvmppc_setup_partition_table(struct kvm *kvm);
static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
int *ip)
@@ -3574,7 +3573,7 @@ static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
return;
}
-static void kvmppc_setup_partition_table(struct kvm *kvm)
+void kvmppc_setup_partition_table(struct kvm *kvm)
{
unsigned long dw0, dw1;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 2659844784b8..9c61f736c75b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -79,7 +79,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline)
mtmsrd r0,1 /* clear RI in MSR */
mtsrr0 r5
mtsrr1 r6
- RFI
+ RFI_TO_KERNEL
kvmppc_call_hv_entry:
BEGIN_FTR_SECTION
@@ -199,7 +199,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtmsrd r6, 1 /* Clear RI in MSR */
mtsrr0 r8
mtsrr1 r7
- RFI
+ RFI_TO_KERNEL
/* Virtual-mode return */
.Lvirt_return:
@@ -1167,8 +1167,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
ld r0, VCPU_GPR(R0)(r4)
ld r4, VCPU_GPR(R4)(r4)
-
- hrfid
+ HRFI_TO_GUEST
b .
secondary_too_late:
@@ -3320,7 +3319,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
ld r4, PACAKMSR(r13)
mtspr SPRN_SRR0, r3
mtspr SPRN_SRR1, r4
- rfid
+ RFI_TO_KERNEL
9: addi r3, r1, STACK_FRAME_OVERHEAD
bl kvmppc_bad_interrupt
b 9b
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index d0dc8624198f..7deaeeb14b93 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -60,6 +60,7 @@ static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
#define MSR_USER32 MSR_USER
#define MSR_USER64 MSR_USER
#define HW_PAGE_SIZE PAGE_SIZE
+#define HPTE_R_M _PAGE_COHERENT
#endif
static bool kvmppc_is_split_real(struct kvm_vcpu *vcpu)
@@ -557,6 +558,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
pte.eaddr = eaddr;
pte.vpage = eaddr >> 12;
pte.page_size = MMU_PAGE_64K;
+ pte.wimg = HPTE_R_M;
}
switch (kvmppc_get_msr(vcpu) & (MSR_DR|MSR_IR)) {
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 42a4b237df5f..34a5adeff084 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -46,6 +46,9 @@
#define FUNC(name) name
+#define RFI_TO_KERNEL RFI
+#define RFI_TO_GUEST RFI
+
.macro INTERRUPT_TRAMPOLINE intno
.global kvmppc_trampoline_\intno
@@ -141,7 +144,7 @@ kvmppc_handler_skip_ins:
GET_SCRATCH0(r13)
/* And get back into the code */
- RFI
+ RFI_TO_KERNEL
#endif
/*
@@ -164,6 +167,6 @@ _GLOBAL_TOC(kvmppc_entry_trampoline)
ori r5, r5, MSR_EE
mtsrr0 r7
mtsrr1 r6
- RFI
+ RFI_TO_KERNEL
#include "book3s_segment.S"
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 2a2b96d53999..93a180ceefad 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -156,7 +156,7 @@ no_dcbz32_on:
PPC_LL r9, SVCPU_R9(r3)
PPC_LL r3, (SVCPU_R3)(r3)
- RFI
+ RFI_TO_GUEST
kvmppc_handler_trampoline_enter_end:
@@ -407,5 +407,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
cmpwi r12, BOOK3S_INTERRUPT_DOORBELL
beqa BOOK3S_INTERRUPT_DOORBELL
- RFI
+ RFI_TO_KERNEL
kvmppc_handler_trampoline_exit_end:
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index bf457843e032..0d750d274c4e 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -725,7 +725,8 @@ u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu)
/* Return the per-cpu state for state saving/migration */
return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT |
- (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT;
+ (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT |
+ (u64)0xff << KVM_REG_PPC_ICP_PPRI_SHIFT;
}
int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
@@ -1558,7 +1559,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
/*
* Restore P and Q. If the interrupt was pending, we
- * force both P and Q, which will trigger a resend.
+ * force Q and !P, which will trigger a resend.
*
* That means that a guest that had both an interrupt
* pending (queued) and Q set will restore with only
@@ -1566,7 +1567,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
* is perfectly fine as coalescing interrupts that haven't
* been presented yet is always allowed.
*/
- if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
+ if (val & KVM_XICS_PRESENTED && !(val & KVM_XICS_PENDING))
state->old_p = true;
if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING)
state->old_q = true;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6b6c53c42ac9..0a7c88786ec0 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -39,6 +39,10 @@
#include <asm/iommu.h>
#include <asm/switch_to.h>
#include <asm/xive.h>
+#ifdef CONFIG_PPC_PSERIES
+#include <asm/hvcall.h>
+#include <asm/plpar_wrappers.h>
+#endif
#include "timing.h"
#include "irq.h"
@@ -548,6 +552,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
#ifdef CONFIG_KVM_XICS
case KVM_CAP_IRQ_XICS:
#endif
+ case KVM_CAP_PPC_GET_CPU_CHAR:
r = 1;
break;
@@ -1407,7 +1412,6 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
int r;
- sigset_t sigsaved;
if (vcpu->mmio_needed) {
vcpu->mmio_needed = 0;
@@ -1448,16 +1452,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
#endif
}
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_sigset_activate(vcpu);
if (run->immediate_exit)
r = -EINTR;
else
r = kvmppc_vcpu_run(run, vcpu);
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
return r;
}
@@ -1762,6 +1764,124 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
return r;
}
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * These functions check whether the underlying hardware is safe
+ * against attacks based on observing the effects of speculatively
+ * executed instructions, and whether it supplies instructions for
+ * use in workarounds. The information comes from firmware, either
+ * via the device tree on powernv platforms or from an hcall on
+ * pseries platforms.
+ */
+#ifdef CONFIG_PPC_PSERIES
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+ struct h_cpu_char_result c;
+ unsigned long rc;
+
+ if (!machine_is(pseries))
+ return -ENOTTY;
+
+ rc = plpar_get_cpu_characteristics(&c);
+ if (rc == H_SUCCESS) {
+ cp->character = c.character;
+ cp->behaviour = c.behaviour;
+ cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+ KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+ KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+ KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+ KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+ KVM_PPC_CPU_CHAR_BR_HINT_HONOURED |
+ KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF |
+ KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+ cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+ KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+ KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+ }
+ return 0;
+}
+#else
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+ return -ENOTTY;
+}
+#endif
+
+static inline bool have_fw_feat(struct device_node *fw_features,
+ const char *state, const char *name)
+{
+ struct device_node *np;
+ bool r = false;
+
+ np = of_get_child_by_name(fw_features, name);
+ if (np) {
+ r = of_property_read_bool(np, state);
+ of_node_put(np);
+ }
+ return r;
+}
+
+static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+ struct device_node *np, *fw_features;
+ int r;
+
+ memset(cp, 0, sizeof(*cp));
+ r = pseries_get_cpu_char(cp);
+ if (r != -ENOTTY)
+ return r;
+
+ np = of_find_node_by_name(NULL, "ibm,opal");
+ if (np) {
+ fw_features = of_get_child_by_name(np, "fw-features");
+ of_node_put(np);
+ if (!fw_features)
+ return 0;
+ if (have_fw_feat(fw_features, "enabled",
+ "inst-spec-barrier-ori31,31,0"))
+ cp->character |= KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31;
+ if (have_fw_feat(fw_features, "enabled",
+ "fw-bcctrl-serialized"))
+ cp->character |= KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED;
+ if (have_fw_feat(fw_features, "enabled",
+ "inst-l1d-flush-ori30,30,0"))
+ cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30;
+ if (have_fw_feat(fw_features, "enabled",
+ "inst-l1d-flush-trig2"))
+ cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2;
+ if (have_fw_feat(fw_features, "enabled",
+ "fw-l1d-thread-split"))
+ cp->character |= KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
+ if (have_fw_feat(fw_features, "enabled",
+ "fw-count-cache-disabled"))
+ cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+ cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+ KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+ KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+ KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+ KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+ KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+
+ if (have_fw_feat(fw_features, "enabled",
+ "speculation-policy-favor-security"))
+ cp->behaviour |= KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY;
+ if (!have_fw_feat(fw_features, "disabled",
+ "needs-l1d-flush-msr-pr-0-to-1"))
+ cp->behaviour |= KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR;
+ if (!have_fw_feat(fw_features, "disabled",
+ "needs-spec-barrier-for-bound-checks"))
+ cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+ cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+ KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+ KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+
+ of_node_put(fw_features);
+ }
+
+ return 0;
+}
+#endif
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -1864,6 +1984,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EFAULT;
break;
}
+ case KVM_PPC_GET_CPU_CHAR: {
+ struct kvm_ppc_cpu_char cpuchar;
+
+ r = kvmppc_get_cpu_char(&cpuchar);
+ if (r >= 0 && copy_to_user(argp, &cpuchar, sizeof(cpuchar)))
+ r = -EFAULT;
+ break;
+ }
default: {
struct kvm *kvm = filp->private_data;
r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 41cf5ae273cf..a95ea007d654 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -116,6 +116,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
}
}
+#ifdef CONFIG_PPC_BOOK3S_64
+void do_rfi_flush_fixups(enum l1d_flush_type types)
+{
+ unsigned int instrs[3], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___rfi_flush_fixup),
+ end = PTRRELOC(&__stop___rfi_flush_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+
+ if (types & L1D_FLUSH_FALLBACK)
+ /* b .+16 to fallback flush */
+ instrs[0] = 0x48000010;
+
+ i = 0;
+ if (types & L1D_FLUSH_ORI) {
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+ }
+
+ if (types & L1D_FLUSH_MTTRIG)
+ instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction(dest, instrs[0]);
+ patch_instruction(dest + 1, instrs[1]);
+ patch_instruction(dest + 2, instrs[2]);
+ }
+
+ printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i);
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
{
long *start, *end;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 4797d08581ce..6e1e39035380 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -145,6 +145,11 @@ static noinline int bad_area(struct pt_regs *regs, unsigned long address)
return __bad_area(regs, address, SEGV_MAPERR);
}
+static noinline int bad_access(struct pt_regs *regs, unsigned long address)
+{
+ return __bad_area(regs, address, SEGV_ACCERR);
+}
+
static int do_sigbus(struct pt_regs *regs, unsigned long address,
unsigned int fault)
{
@@ -490,7 +495,7 @@ retry:
good_area:
if (unlikely(access_error(is_write, is_exec, vma)))
- return bad_area(regs, address);
+ return bad_access(regs, address);
/*
* If for any reason at all we couldn't handle the fault,
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 3848af167df9..640cf566e986 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -47,7 +47,8 @@
DEFINE_RAW_SPINLOCK(native_tlbie_lock);
-static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+static inline unsigned long ___tlbie(unsigned long vpn, int psize,
+ int apsize, int ssize)
{
unsigned long va;
unsigned int penc;
@@ -100,7 +101,15 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
: "memory");
break;
}
- trace_tlbie(0, 0, va, 0, 0, 0, 0);
+ return va;
+}
+
+static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+ unsigned long rb;
+
+ rb = ___tlbie(vpn, psize, apsize, ssize);
+ trace_tlbie(0, 0, rb, 0, 0, 0, 0);
}
static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
@@ -652,7 +661,7 @@ static void native_hpte_clear(void)
if (hpte_v & HPTE_V_VALID) {
hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
hptep->v = 0;
- __tlbie(vpn, psize, apsize, ssize);
+ ___tlbie(vpn, psize, apsize, ssize);
}
}
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 46d74e81aff1..d183b4801bdb 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -763,7 +763,8 @@ emit_clear:
func = (u8 *) __bpf_call_base + imm;
/* Save skb pointer if we need to re-cache skb data */
- if (bpf_helper_changes_pkt_data(func))
+ if ((ctx->seen & SEEN_SKB) &&
+ bpf_helper_changes_pkt_data(func))
PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
bpf_jit_emit_func_call(image, ctx, (u64)func);
@@ -772,7 +773,8 @@ emit_clear:
PPC_MR(b2p[BPF_REG_0], 3);
/* refresh skb cache */
- if (bpf_helper_changes_pkt_data(func)) {
+ if ((ctx->seen & SEEN_SKB) &&
+ bpf_helper_changes_pkt_data(func)) {
/* reload skb pointer to r3 */
PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
bpf_jit_emit_skb_loads(image, ctx);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 9e3da168d54c..fce545774d50 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -410,8 +410,12 @@ static __u64 power_pmu_bhrb_to(u64 addr)
int ret;
__u64 target;
- if (is_kernel_addr(addr))
- return branch_target((unsigned int *)addr);
+ if (is_kernel_addr(addr)) {
+ if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+ return 0;
+
+ return branch_target(&instr);
+ }
/* Userspace: need copy instruction here then translate it */
pagefault_disable();
@@ -1415,7 +1419,7 @@ static int collect_events(struct perf_event *group, int max_count,
int n = 0;
struct perf_event *event;
- if (!is_software_event(group)) {
+ if (group->pmu->task_ctx_nr == perf_hw_context) {
if (n >= max_count)
return -1;
ctrs[n] = group;
@@ -1423,7 +1427,7 @@ static int collect_events(struct perf_event *group, int max_count,
events[n++] = group->hw.config;
}
list_for_each_entry(event, &group->sibling_list, group_entry) {
- if (!is_software_event(event) &&
+ if (event->pmu->task_ctx_nr == perf_hw_context &&
event->state != PERF_EVENT_STATE_OFF) {
if (n >= max_count)
return -1;
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 0ead3cd73caa..be4e7f84f70a 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -310,6 +310,19 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu)
return 0;
/*
+ * Check whether nest_imc is registered. We could end up here if the
+ * cpuhotplug callback registration fails. i.e, callback invokes the
+ * offline path for all successfully registered nodes. At this stage,
+ * nest_imc pmu will not be registered and we should return here.
+ *
+ * We return with a zero since this is not an offline failure. And
+ * cpuhp_setup_state() returns the actual failure reason to the caller,
+ * which in turn will call the cleanup routine.
+ */
+ if (!nest_pmus)
+ return 0;
+
+ /*
* Now that this cpu is one of the designated,
* find a next cpu a) which is online and b) in same chip.
*/
@@ -1171,6 +1184,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
if (nest_pmus == 1) {
cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
kfree(nest_imc_refc);
+ kfree(per_nest_pmu_arr);
}
if (nest_pmus > 0)
@@ -1195,7 +1209,6 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
kfree(pmu_ptr);
- kfree(per_nest_pmu_arr);
return;
}
@@ -1309,6 +1322,8 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
ret = nest_pmu_cpumask_init();
if (ret) {
mutex_unlock(&nest_init_lock);
+ kfree(nest_imc_refc);
+ kfree(per_nest_pmu_arr);
goto err_free;
}
}
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
index d9916ea62305..8ddc1accf199 100644
--- a/arch/powerpc/platforms/powernv/opal-memory-errors.c
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -60,7 +60,7 @@ static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt)
}
for (; paddr_start < paddr_end; paddr_start += PAGE_SIZE) {
- memory_failure(paddr_start >> PAGE_SHIFT, 0, 0);
+ memory_failure(paddr_start >> PAGE_SHIFT, 0);
}
}
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 1edfbc1e40f4..4fb21e17504a 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -37,13 +37,62 @@
#include <asm/kexec.h>
#include <asm/smp.h>
#include <asm/tm.h>
+#include <asm/setup.h>
#include "powernv.h"
+static void pnv_setup_rfi_flush(void)
+{
+ struct device_node *np, *fw_features;
+ enum l1d_flush_type type;
+ int enable;
+
+ /* Default to fallback in case fw-features are not available */
+ type = L1D_FLUSH_FALLBACK;
+ enable = 1;
+
+ np = of_find_node_by_name(NULL, "ibm,opal");
+ fw_features = of_get_child_by_name(np, "fw-features");
+ of_node_put(np);
+
+ if (fw_features) {
+ np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2");
+ if (np && of_property_read_bool(np, "enabled"))
+ type = L1D_FLUSH_MTTRIG;
+
+ of_node_put(np);
+
+ np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0");
+ if (np && of_property_read_bool(np, "enabled"))
+ type = L1D_FLUSH_ORI;
+
+ of_node_put(np);
+
+ /* Enable unless firmware says NOT to */
+ enable = 2;
+ np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0");
+ if (np && of_property_read_bool(np, "disabled"))
+ enable--;
+
+ of_node_put(np);
+
+ np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1");
+ if (np && of_property_read_bool(np, "disabled"))
+ enable--;
+
+ of_node_put(np);
+ of_node_put(fw_features);
+ }
+
+ setup_rfi_flush(type, enable > 0);
+}
+
static void __init pnv_setup_arch(void)
{
set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
+ pnv_setup_rfi_flush();
+
/* Initialize SMP */
pnv_smp_init();
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 9dabea6e1443..6244bc849469 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -104,6 +104,20 @@ static void __noreturn ps3_halt(void)
ps3_sys_manager_halt(); /* never returns */
}
+static void ps3_panic(char *str)
+{
+ DBG("%s:%d %s\n", __func__, __LINE__, str);
+
+ smp_send_stop();
+ printk("\n");
+ printk(" System does not reboot automatically.\n");
+ printk(" Please press POWER button.\n");
+ printk("\n");
+
+ while(1)
+ lv1_pause(1);
+}
+
#if defined(CONFIG_FB_PS3) || defined(CONFIG_FB_PS3_MODULE) || \
defined(CONFIG_PS3_FLASH) || defined(CONFIG_PS3_FLASH_MODULE)
static void __init prealloc(struct ps3_prealloc *p)
@@ -255,6 +269,7 @@ define_machine(ps3) {
.probe = ps3_probe,
.setup_arch = ps3_setup_arch,
.init_IRQ = ps3_init_IRQ,
+ .panic = ps3_panic,
.get_boot_time = ps3_get_boot_time,
.set_dabr = ps3_set_dabr,
.calibrate_decr = ps3_calibrate_decr,
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 6e35780c5962..a0b20c03f078 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -574,11 +574,26 @@ static ssize_t dlpar_show(struct class *class, struct class_attribute *attr,
static CLASS_ATTR_RW(dlpar);
-static int __init pseries_dlpar_init(void)
+int __init dlpar_workqueue_init(void)
{
+ if (pseries_hp_wq)
+ return 0;
+
pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue",
- WQ_UNBOUND, 1);
+ WQ_UNBOUND, 1);
+
+ return pseries_hp_wq ? 0 : -ENOMEM;
+}
+
+static int __init dlpar_sysfs_init(void)
+{
+ int rc;
+
+ rc = dlpar_workqueue_init();
+ if (rc)
+ return rc;
+
return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr);
}
-machine_device_initcall(pseries, pseries_dlpar_init);
+machine_device_initcall(pseries, dlpar_sysfs_init);
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 4470a3194311..1ae1d9f4dbe9 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -98,4 +98,6 @@ static inline unsigned long cmo_get_page_size(void)
return CMO_PageSize;
}
+int dlpar_workqueue_init(void);
+
#endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 4923ffe230cf..81d8614e7379 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -69,7 +69,8 @@ static int __init init_ras_IRQ(void)
/* Hotplug Events */
np = of_find_node_by_path("/event-sources/hot-plug-events");
if (np != NULL) {
- request_event_sources_irqs(np, ras_hotplug_interrupt,
+ if (dlpar_workqueue_init() == 0)
+ request_event_sources_irqs(np, ras_hotplug_interrupt,
"RAS_HOTPLUG");
of_node_put(np);
}
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 5f1beb8367ac..ae4f596273b5 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -459,6 +459,39 @@ static void __init find_and_init_phbs(void)
of_pci_check_probe_only();
}
+static void pseries_setup_rfi_flush(void)
+{
+ struct h_cpu_char_result result;
+ enum l1d_flush_type types;
+ bool enable;
+ long rc;
+
+ /* Enable by default */
+ enable = true;
+
+ rc = plpar_get_cpu_characteristics(&result);
+ if (rc == H_SUCCESS) {
+ types = L1D_FLUSH_NONE;
+
+ if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2)
+ types |= L1D_FLUSH_MTTRIG;
+ if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30)
+ types |= L1D_FLUSH_ORI;
+
+ /* Use fallback if nothing set in hcall */
+ if (types == L1D_FLUSH_NONE)
+ types = L1D_FLUSH_FALLBACK;
+
+ if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
+ enable = false;
+ } else {
+ /* Default to fallback if case hcall is not available */
+ types = L1D_FLUSH_FALLBACK;
+ }
+
+ setup_rfi_flush(types, enable);
+}
+
static void __init pSeries_setup_arch(void)
{
set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
@@ -476,6 +509,8 @@ static void __init pSeries_setup_arch(void)
fwnmi_init();
+ pseries_setup_rfi_flush();
+
/* By default, only probe PCI (can be overridden by rtas_pci) */
pci_add_flags(PCI_PROBE_ONLY);
@@ -726,6 +761,7 @@ define_machine(pseries) {
.pcibios_fixup = pSeries_final_fixup,
.restart = rtas_restart,
.halt = rtas_halt,
+ .panic = rtas_os_term,
.get_boot_time = rtas_get_boot_time,
.get_rtc_time = rtas_get_rtc_time,
.set_rtc_time = rtas_set_rtc_time,
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 44cbf4c12ea1..df95102e732c 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -354,6 +354,7 @@ static int fsl_of_msi_remove(struct platform_device *ofdev)
}
static struct lock_class_key fsl_msi_irq_class;
+static struct lock_class_key fsl_msi_irq_request_class;
static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
int offset, int irq_index)
@@ -373,7 +374,8 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
dev_err(&dev->dev, "No memory for MSI cascade data\n");
return -ENOMEM;
}
- irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class);
+ irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class,
+ &fsl_msi_irq_request_class);
cascade_data->index = offset;
cascade_data->msi_data = msi;
cascade_data->virq = virt_msir;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 1b2d8cb49abb..0ddc7ac6c5f1 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1590,7 +1590,7 @@ static void print_bug_trap(struct pt_regs *regs)
printf("kernel BUG at %s:%u!\n",
bug->file, bug->line);
#else
- printf("kernel BUG at %p!\n", (void *)bug->bug_addr);
+ printf("kernel BUG at %px!\n", (void *)bug->bug_addr);
#endif
#endif /* CONFIG_BUG */
}
@@ -2329,7 +2329,7 @@ static void dump_one_paca(int cpu)
p = &paca[cpu];
- printf("paca for cpu 0x%x @ %p:\n", cpu, p);
+ printf("paca for cpu 0x%x @ %px:\n", cpu, p);
printf(" %-*s = %s\n", 20, "possible", cpu_possible(cpu) ? "yes" : "no");
printf(" %-*s = %s\n", 20, "present", cpu_present(cpu) ? "yes" : "no");
@@ -2344,10 +2344,10 @@ static void dump_one_paca(int cpu)
DUMP(p, kernel_toc, "lx");
DUMP(p, kernelbase, "lx");
DUMP(p, kernel_msr, "lx");
- DUMP(p, emergency_sp, "p");
+ DUMP(p, emergency_sp, "px");
#ifdef CONFIG_PPC_BOOK3S_64
- DUMP(p, nmi_emergency_sp, "p");
- DUMP(p, mc_emergency_sp, "p");
+ DUMP(p, nmi_emergency_sp, "px");
+ DUMP(p, mc_emergency_sp, "px");
DUMP(p, in_nmi, "x");
DUMP(p, in_mce, "x");
DUMP(p, hmi_event_available, "x");
@@ -2375,17 +2375,21 @@ static void dump_one_paca(int cpu)
DUMP(p, slb_cache_ptr, "x");
for (i = 0; i < SLB_CACHE_ENTRIES; i++)
printf(" slb_cache[%d]: = 0x%016lx\n", i, p->slb_cache[i]);
+
+ DUMP(p, rfi_flush_fallback_area, "px");
+ DUMP(p, l1d_flush_congruence, "llx");
+ DUMP(p, l1d_flush_sets, "llx");
#endif
DUMP(p, dscr_default, "llx");
#ifdef CONFIG_PPC_BOOK3E
- DUMP(p, pgd, "p");
- DUMP(p, kernel_pgd, "p");
- DUMP(p, tcd_ptr, "p");
- DUMP(p, mc_kstack, "p");
- DUMP(p, crit_kstack, "p");
- DUMP(p, dbg_kstack, "p");
+ DUMP(p, pgd, "px");
+ DUMP(p, kernel_pgd, "px");
+ DUMP(p, tcd_ptr, "px");
+ DUMP(p, mc_kstack, "px");
+ DUMP(p, crit_kstack, "px");
+ DUMP(p, dbg_kstack, "px");
#endif
- DUMP(p, __current, "p");
+ DUMP(p, __current, "px");
DUMP(p, kstack, "lx");
printf(" kstack_base = 0x%016lx\n", p->kstack & ~(THREAD_SIZE - 1));
DUMP(p, stab_rr, "lx");
@@ -2403,7 +2407,7 @@ static void dump_one_paca(int cpu)
#endif
#ifdef CONFIG_PPC_POWERNV
- DUMP(p, core_idle_state_ptr, "p");
+ DUMP(p, core_idle_state_ptr, "px");
DUMP(p, thread_idle_state, "x");
DUMP(p, thread_mask, "x");
DUMP(p, subcore_sibling_mask, "x");
@@ -2945,7 +2949,7 @@ static void show_task(struct task_struct *tsk)
(tsk->exit_state & EXIT_DEAD) ? 'E' :
(tsk->state & TASK_INTERRUPTIBLE) ? 'S' : '?';
- printf("%p %016lx %6d %6d %c %2d %s\n", tsk,
+ printf("%px %016lx %6d %6d %c %2d %s\n", tsk,
tsk->thread.ksp,
tsk->pid, tsk->parent->pid,
state, task_thread_info(tsk)->cpu,
@@ -2988,7 +2992,7 @@ static void show_pte(unsigned long addr)
if (setjmp(bus_error_jmp) != 0) {
catch_memory_errors = 0;
- printf("*** Error dumping pte for task %p\n", tsk);
+ printf("*** Error dumping pte for task %px\n", tsk);
return;
}
@@ -3074,7 +3078,7 @@ static void show_tasks(void)
if (setjmp(bus_error_jmp) != 0) {
catch_memory_errors = 0;
- printf("*** Error dumping task %p\n", tsk);
+ printf("*** Error dumping task %px\n", tsk);
return;
}
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index e69de29bb2d1..47dacf06c679 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -0,0 +1,75 @@
+CONFIG_SMP=y
+CONFIG_PCI=y
+CONFIG_PCIE_XILINX=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_RAS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+# CONFIG_RCU_TRACE is not set
+CONFIG_CRYPTO_USER_API_HASH=y
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 18158be62a2b..970460a0b492 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -40,6 +40,7 @@ generic-y += resource.h
generic-y += scatterlist.h
generic-y += sections.h
generic-y += sembuf.h
+generic-y += serial.h
generic-y += setup.h
generic-y += shmbuf.h
generic-y += shmparam.h
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 6cbbb6a68d76..5ad4cb622bed 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -58,17 +58,17 @@
#endif
#if (__SIZEOF_INT__ == 4)
-#define INT __ASM_STR(.word)
-#define SZINT __ASM_STR(4)
-#define LGINT __ASM_STR(2)
+#define RISCV_INT __ASM_STR(.word)
+#define RISCV_SZINT __ASM_STR(4)
+#define RISCV_LGINT __ASM_STR(2)
#else
#error "Unexpected __SIZEOF_INT__"
#endif
#if (__SIZEOF_SHORT__ == 2)
-#define SHORT __ASM_STR(.half)
-#define SZSHORT __ASM_STR(2)
-#define LGSHORT __ASM_STR(1)
+#define RISCV_SHORT __ASM_STR(.half)
+#define RISCV_SZSHORT __ASM_STR(2)
+#define RISCV_LGSHORT __ASM_STR(1)
#else
#error "Unexpected __SIZEOF_SHORT__"
#endif
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index e2e37c57cbeb..e65d1cd89e28 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -50,30 +50,30 @@ static __always_inline void atomic64_set(atomic64_t *v, long i)
* have the AQ or RL bits set. These don't return anything, so there's only
* one version to worry about.
*/
-#define ATOMIC_OP(op, asm_op, c_op, I, asm_type, c_type, prefix) \
-static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
-{ \
- __asm__ __volatile__ ( \
- "amo" #asm_op "." #asm_type " zero, %1, %0" \
- : "+A" (v->counter) \
- : "r" (I) \
- : "memory"); \
+#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix) \
+static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
+{ \
+ __asm__ __volatile__ ( \
+ "amo" #asm_op "." #asm_type " zero, %1, %0" \
+ : "+A" (v->counter) \
+ : "r" (I) \
+ : "memory"); \
}
#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP (op, asm_op, c_op, I, w, int, )
+#define ATOMIC_OPS(op, asm_op, I) \
+ ATOMIC_OP (op, asm_op, I, w, int, )
#else
-#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP (op, asm_op, c_op, I, w, int, ) \
- ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I) \
+ ATOMIC_OP (op, asm_op, I, w, int, ) \
+ ATOMIC_OP (op, asm_op, I, d, long, 64)
#endif
-ATOMIC_OPS(add, add, +, i)
-ATOMIC_OPS(sub, add, +, -i)
-ATOMIC_OPS(and, and, &, i)
-ATOMIC_OPS( or, or, |, i)
-ATOMIC_OPS(xor, xor, ^, i)
+ATOMIC_OPS(add, add, i)
+ATOMIC_OPS(sub, add, -i)
+ATOMIC_OPS(and, and, i)
+ATOMIC_OPS( or, or, i)
+ATOMIC_OPS(xor, xor, i)
#undef ATOMIC_OP
#undef ATOMIC_OPS
@@ -83,7 +83,7 @@ ATOMIC_OPS(xor, xor, ^, i)
* There's two flavors of these: the arithmatic ops have both fetch and return
* versions, while the logical ops only have fetch versions.
*/
-#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix) \
+#define ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, asm_type, c_type, prefix) \
static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v) \
{ \
register c_type ret; \
@@ -103,13 +103,13 @@ static __always_inline c_type atomic##prefix##_##op##_return##c_or(c_type i, ato
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, I, asm_or, c_or, w, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, I, asm_or, c_or, w, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64) \
+ ATOMIC_FETCH_OP (op, asm_op, I, asm_or, c_or, d, long, 64) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
#endif
@@ -126,28 +126,28 @@ ATOMIC_OPS(sub, add, +, -i, .aqrl, )
#undef ATOMIC_OPS
#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
- ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, )
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w, int, )
#else
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
- ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
- ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, d, long, 64)
#endif
-ATOMIC_OPS(and, and, &, i, , _relaxed)
-ATOMIC_OPS(and, and, &, i, .aq , _acquire)
-ATOMIC_OPS(and, and, &, i, .rl , _release)
-ATOMIC_OPS(and, and, &, i, .aqrl, )
+ATOMIC_OPS(and, and, i, , _relaxed)
+ATOMIC_OPS(and, and, i, .aq , _acquire)
+ATOMIC_OPS(and, and, i, .rl , _release)
+ATOMIC_OPS(and, and, i, .aqrl, )
-ATOMIC_OPS( or, or, |, i, , _relaxed)
-ATOMIC_OPS( or, or, |, i, .aq , _acquire)
-ATOMIC_OPS( or, or, |, i, .rl , _release)
-ATOMIC_OPS( or, or, |, i, .aqrl, )
+ATOMIC_OPS( or, or, i, , _relaxed)
+ATOMIC_OPS( or, or, i, .aq , _acquire)
+ATOMIC_OPS( or, or, i, .rl , _release)
+ATOMIC_OPS( or, or, i, .aqrl, )
-ATOMIC_OPS(xor, xor, ^, i, , _relaxed)
-ATOMIC_OPS(xor, xor, ^, i, .aq , _acquire)
-ATOMIC_OPS(xor, xor, ^, i, .rl , _release)
-ATOMIC_OPS(xor, xor, ^, i, .aqrl, )
+ATOMIC_OPS(xor, xor, i, , _relaxed)
+ATOMIC_OPS(xor, xor, i, .aq , _acquire)
+ATOMIC_OPS(xor, xor, i, .rl , _release)
+ATOMIC_OPS(xor, xor, i, .aqrl, )
#undef ATOMIC_OPS
@@ -182,13 +182,13 @@ ATOMIC_OPS(add_negative, add, <, 0)
#undef ATOMIC_OP
#undef ATOMIC_OPS
-#define ATOMIC_OP(op, func_op, c_op, I, c_type, prefix) \
+#define ATOMIC_OP(op, func_op, I, c_type, prefix) \
static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v) \
{ \
atomic##prefix##_##func_op(I, v); \
}
-#define ATOMIC_FETCH_OP(op, func_op, c_op, I, c_type, prefix) \
+#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix) \
static __always_inline c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \
{ \
return atomic##prefix##_fetch_##func_op(I, v); \
@@ -202,16 +202,16 @@ static __always_inline c_type atomic##prefix##_##op##_return(atomic##prefix##_t
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP (op, asm_op, c_op, I, int, ) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, int, ) \
+ ATOMIC_OP (op, asm_op, I, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, I, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP (op, asm_op, c_op, I, int, ) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, int, ) \
+ ATOMIC_OP (op, asm_op, I, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, I, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) \
- ATOMIC_OP (op, asm_op, c_op, I, long, 64) \
- ATOMIC_FETCH_OP (op, asm_op, c_op, I, long, 64) \
+ ATOMIC_OP (op, asm_op, I, long, 64) \
+ ATOMIC_FETCH_OP (op, asm_op, I, long, 64) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
#endif
@@ -300,8 +300,13 @@ static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
/*
* atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
- * {cmp,}xchg and the operations that return, so they need a barrier. We just
- * use the other implementations directly.
+ * {cmp,}xchg and the operations that return, so they need a barrier.
+ */
+/*
+ * FIXME: atomic_cmpxchg_{acquire,release,relaxed} are all implemented by
+ * assigning the same barrier to both the LR and SC operations, but that might
+ * not make any sense. We're waiting on a memory model specification to
+ * determine exactly what the right thing to do is here.
*/
#define ATOMIC_OP(c_t, prefix, c_or, size, asm_or) \
static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) \
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 183534b7c39b..c0319cbf1eec 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -39,27 +39,23 @@
#define smp_wmb() RISCV_FENCE(w,w)
/*
- * These fences exist to enforce ordering around the relaxed AMOs. The
- * documentation defines that
- * "
- * atomic_fetch_add();
- * is equivalent to:
- * smp_mb__before_atomic();
- * atomic_fetch_add_relaxed();
- * smp_mb__after_atomic();
- * "
- * So we emit full fences on both sides.
- */
-#define __smb_mb__before_atomic() smp_mb()
-#define __smb_mb__after_atomic() smp_mb()
-
-/*
- * These barriers prevent accesses performed outside a spinlock from being moved
- * inside a spinlock. Since RISC-V sets the aq/rl bits on our spinlock only
- * enforce release consistency, we need full fences here.
+ * This is a very specific barrier: it's currently only used in two places in
+ * the kernel, both in the scheduler. See include/linux/spinlock.h for the two
+ * orderings it guarantees, but the "critical section is RCsc" guarantee
+ * mandates a barrier on RISC-V. The sequence looks like:
+ *
+ * lr.aq lock
+ * sc lock <= LOCKED
+ * smp_mb__after_spinlock()
+ * // critical section
+ * lr lock
+ * sc.rl lock <= UNLOCKED
+ *
+ * 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.
*/
-#define smb_mb__before_spinlock() smp_mb()
-#define smb_mb__after_spinlock() smp_mb()
+#define smp_mb__after_spinlock() RISCV_FENCE(rw,rw)
#include <asm-generic/barrier.h>
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 7c281ef1d583..f30daf26f08f 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -67,7 +67,7 @@
: "memory");
#define __test_and_op_bit(op, mod, nr, addr) \
- __test_and_op_bit_ord(op, mod, nr, addr, )
+ __test_and_op_bit_ord(op, mod, nr, addr, .aqrl)
#define __op_bit(op, mod, nr, addr) \
__op_bit_ord(op, mod, nr, addr, )
diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h
index c3e13764a943..bfc7f099ab1f 100644
--- a/arch/riscv/include/asm/bug.h
+++ b/arch/riscv/include/asm/bug.h
@@ -27,8 +27,8 @@
typedef u32 bug_insn_t;
#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-#define __BUG_ENTRY_ADDR INT " 1b - 2b"
-#define __BUG_ENTRY_FILE INT " %0 - 2b"
+#define __BUG_ENTRY_ADDR RISCV_INT " 1b - 2b"
+#define __BUG_ENTRY_FILE RISCV_INT " %0 - 2b"
#else
#define __BUG_ENTRY_ADDR RISCV_PTR " 1b"
#define __BUG_ENTRY_FILE RISCV_PTR " %0"
@@ -38,7 +38,7 @@ typedef u32 bug_insn_t;
#define __BUG_ENTRY \
__BUG_ENTRY_ADDR "\n\t" \
__BUG_ENTRY_FILE "\n\t" \
- SHORT " %1"
+ RISCV_SHORT " %1"
#else
#define __BUG_ENTRY \
__BUG_ENTRY_ADDR
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 0595585013b0..efd89a88d2d0 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -18,22 +18,44 @@
#undef flush_icache_range
#undef flush_icache_user_range
+#undef flush_dcache_page
static inline void local_flush_icache_all(void)
{
asm volatile ("fence.i" ::: "memory");
}
+#define PG_dcache_clean PG_arch_1
+
+static inline void flush_dcache_page(struct page *page)
+{
+ if (test_bit(PG_dcache_clean, &page->flags))
+ clear_bit(PG_dcache_clean, &page->flags);
+}
+
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range(start, end) flush_icache_all()
+#define flush_icache_user_range(vma, pg, addr, len) flush_icache_all()
+
#ifndef CONFIG_SMP
-#define flush_icache_range(start, end) local_flush_icache_all()
-#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()
+#define flush_icache_all() local_flush_icache_all()
+#define flush_icache_mm(mm, local) flush_icache_all()
#else /* CONFIG_SMP */
-#define flush_icache_range(start, end) sbi_remote_fence_i(0)
-#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)
+#define flush_icache_all() sbi_remote_fence_i(0)
+void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
+/*
+ * Bits in sys_riscv_flush_icache()'s flags argument.
+ */
+#define SYS_RISCV_FLUSH_ICACHE_LOCAL 1UL
+#define SYS_RISCV_FLUSH_ICACHE_ALL (SYS_RISCV_FLUSH_ICACHE_LOCAL)
+
#endif /* _ASM_RISCV_CACHEFLUSH_H */
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 0d64bc9f4f91..3c7a2c97e377 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -17,10 +17,10 @@
#include <linux/const.h>
/* Status register flags */
-#define SR_IE _AC(0x00000002, UL) /* Interrupt Enable */
-#define SR_PIE _AC(0x00000020, UL) /* Previous IE */
-#define SR_PS _AC(0x00000100, UL) /* Previously Supervisor */
-#define SR_SUM _AC(0x00040000, UL) /* Supervisor may access User Memory */
+#define SR_SIE _AC(0x00000002, UL) /* Supervisor Interrupt Enable */
+#define SR_SPIE _AC(0x00000020, UL) /* Previous Supervisor IE */
+#define SR_SPP _AC(0x00000100, UL) /* Previously Supervisor */
+#define SR_SUM _AC(0x00040000, UL) /* Supervisor may access User Memory */
#define SR_FS _AC(0x00006000, UL) /* Floating-point Status */
#define SR_FS_OFF _AC(0x00000000, UL)
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index c1f32cfcc79b..b269451e7e85 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -19,7 +19,7 @@
#ifndef _ASM_RISCV_IO_H
#define _ASM_RISCV_IO_H
-#ifdef CONFIG_MMU
+#include <linux/types.h>
extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
@@ -32,9 +32,7 @@ extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
#define ioremap_wc(addr, size) ioremap((addr), (size))
#define ioremap_wt(addr, size) ioremap((addr), (size))
-extern void iounmap(void __iomem *addr);
-
-#endif /* CONFIG_MMU */
+extern void iounmap(volatile void __iomem *addr);
/* Generic IO read/write. These perform native-endian accesses. */
#define __raw_writeb __raw_writeb
@@ -250,7 +248,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
const ctype *buf = buffer; \
\
do { \
- __raw_writeq(*buf++, addr); \
+ __raw_write ## len(*buf++, addr); \
} while (--count); \
} \
afence; \
@@ -266,9 +264,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar())
__io_reads_ins(ins, u8, b, __io_pbr(), __io_par())
__io_reads_ins(ins, u16, w, __io_pbr(), __io_par())
__io_reads_ins(ins, u32, l, __io_pbr(), __io_par())
-#define insb(addr, buffer, count) __insb((void __iomem *)addr, buffer, count)
-#define insw(addr, buffer, count) __insw((void __iomem *)addr, buffer, count)
-#define insl(addr, buffer, count) __insl((void __iomem *)addr, buffer, count)
+#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count)
+#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count)
+#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count)
__io_writes_outs(writes, u8, b, __io_bw(), __io_aw())
__io_writes_outs(writes, u16, w, __io_bw(), __io_aw())
@@ -280,9 +278,9 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw())
__io_writes_outs(outs, u8, b, __io_pbw(), __io_paw())
__io_writes_outs(outs, u16, w, __io_pbw(), __io_paw())
__io_writes_outs(outs, u32, l, __io_pbw(), __io_paw())
-#define outsb(addr, buffer, count) __outsb((void __iomem *)addr, buffer, count)
-#define outsw(addr, buffer, count) __outsw((void __iomem *)addr, buffer, count)
-#define outsl(addr, buffer, count) __outsl((void __iomem *)addr, buffer, count)
+#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count)
+#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count)
+#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count)
#ifdef CONFIG_64BIT
__io_reads_ins(reads, u64, q, __io_br(), __io_ar())
diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
index 6fdc860d7f84..07a3c6d5706f 100644
--- a/arch/riscv/include/asm/irqflags.h
+++ b/arch/riscv/include/asm/irqflags.h
@@ -27,25 +27,25 @@ static inline unsigned long arch_local_save_flags(void)
/* unconditionally enable interrupts */
static inline void arch_local_irq_enable(void)
{
- csr_set(sstatus, SR_IE);
+ csr_set(sstatus, SR_SIE);
}
/* unconditionally disable interrupts */
static inline void arch_local_irq_disable(void)
{
- csr_clear(sstatus, SR_IE);
+ csr_clear(sstatus, SR_SIE);
}
/* get status and disable interrupts */
static inline unsigned long arch_local_irq_save(void)
{
- return csr_read_clear(sstatus, SR_IE);
+ return csr_read_clear(sstatus, SR_SIE);
}
/* test flags */
static inline int arch_irqs_disabled_flags(unsigned long flags)
{
- return !(flags & SR_IE);
+ return !(flags & SR_SIE);
}
/* test hardware interrupt enable bit */
@@ -57,7 +57,7 @@ static inline int arch_irqs_disabled(void)
/* set interrupt enabled status */
static inline void arch_local_irq_restore(unsigned long flags)
{
- csr_set(sstatus, flags & SR_IE);
+ csr_set(sstatus, flags & SR_SIE);
}
#endif /* _ASM_RISCV_IRQFLAGS_H */
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index 66805cba9a27..5df2dccdba12 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -19,6 +19,10 @@
typedef struct {
void *vdso;
+#ifdef CONFIG_SMP
+ /* A local icache flush is needed before user execution can resume. */
+ cpumask_t icache_stale_mask;
+#endif
} mm_context_t;
#endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
index de1fc1631fc4..97424834dce2 100644
--- a/arch/riscv/include/asm/mmu_context.h
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -1,5 +1,6 @@
/*
* Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -14,11 +15,13 @@
#ifndef _ASM_RISCV_MMU_CONTEXT_H
#define _ASM_RISCV_MMU_CONTEXT_H
+#include <linux/mm_types.h>
#include <asm-generic/mm_hooks.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
static inline void enter_lazy_tlb(struct mm_struct *mm,
struct task_struct *task)
@@ -46,12 +49,54 @@ static inline void set_pgdir(pgd_t *pgd)
csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE);
}
+/*
+ * When necessary, performs a deferred icache flush for the given MM context,
+ * on the local CPU. RISC-V has no direct mechanism for instruction cache
+ * shoot downs, so instead we send an IPI that informs the remote harts they
+ * need to flush their local instruction caches. To avoid pathologically slow
+ * behavior in a common case (a bunch of single-hart processes on a many-hart
+ * machine, ie 'make -j') we avoid the IPIs for harts that are not currently
+ * executing a MM context and instead schedule a deferred local instruction
+ * cache flush to be performed before execution resumes on each hart. This
+ * actually performs that local instruction cache flush, which implicitly only
+ * refers to the current hart.
+ */
+static inline void flush_icache_deferred(struct mm_struct *mm)
+{
+#ifdef CONFIG_SMP
+ unsigned int cpu = smp_processor_id();
+ cpumask_t *mask = &mm->context.icache_stale_mask;
+
+ if (cpumask_test_cpu(cpu, mask)) {
+ cpumask_clear_cpu(cpu, mask);
+ /*
+ * Ensure the remote hart's writes are visible to this hart.
+ * This pairs with a barrier in flush_icache_mm.
+ */
+ smp_mb();
+ local_flush_icache_all();
+ }
+#endif
+}
+
static inline void switch_mm(struct mm_struct *prev,
struct mm_struct *next, struct task_struct *task)
{
if (likely(prev != next)) {
+ /*
+ * Mark the current MM context as inactive, and the next as
+ * active. This is at least used by the icache flushing
+ * routines in order to determine who should
+ */
+ unsigned int cpu = smp_processor_id();
+
+ cpumask_clear_cpu(cpu, mm_cpumask(prev));
+ cpumask_set_cpu(cpu, mm_cpumask(next));
+
set_pgdir(next->pgd);
local_flush_tlb_all();
+
+ flush_icache_deferred(next);
}
}
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 3399257780b2..16301966d65b 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -20,8 +20,6 @@
#ifndef __ASSEMBLY__
-#ifdef CONFIG_MMU
-
/* Page Upper Directory not used in RISC-V */
#include <asm-generic/pgtable-nopud.h>
#include <asm/page.h>
@@ -178,28 +176,6 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr)
#define pte_offset_map(dir, addr) pte_offset_kernel((dir), (addr))
#define pte_unmap(pte) ((void)(pte))
-/*
- * Certain architectures need to do special things when PTEs within
- * a page table are directly modified. Thus, the following hook is
- * made available.
- */
-static inline void set_pte(pte_t *ptep, pte_t pteval)
-{
- *ptep = pteval;
-}
-
-static inline void set_pte_at(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep, pte_t pteval)
-{
- set_pte(ptep, pteval);
-}
-
-static inline void pte_clear(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep)
-{
- set_pte_at(mm, addr, ptep, __pte(0));
-}
-
static inline int pte_present(pte_t pte)
{
return (pte_val(pte) & _PAGE_PRESENT);
@@ -210,21 +186,22 @@ static inline int pte_none(pte_t pte)
return (pte_val(pte) == 0);
}
-/* static inline int pte_read(pte_t pte) */
-
static inline int pte_write(pte_t pte)
{
return pte_val(pte) & _PAGE_WRITE;
}
+static inline int pte_exec(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_EXEC;
+}
+
static inline int pte_huge(pte_t pte)
{
return pte_present(pte)
&& (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
}
-/* static inline int pte_exec(pte_t pte) */
-
static inline int pte_dirty(pte_t pte)
{
return pte_val(pte) & _PAGE_DIRTY;
@@ -311,6 +288,33 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
return pte_val(pte_a) == pte_val(pte_b);
}
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified. Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+ *ptep = pteval;
+}
+
+void flush_icache_pte(pte_t pte);
+
+static inline void set_pte_at(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+ if (pte_present(pteval) && pte_exec(pteval))
+ flush_icache_pte(pteval);
+
+ set_pte(ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ set_pte_at(mm, addr, ptep, __pte(0));
+}
+
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
static inline int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
@@ -407,8 +411,6 @@ static inline void pgtable_cache_init(void)
/* No page table caches to initialize */
}
-#endif /* CONFIG_MMU */
-
#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1)
#define VMALLOC_END (PAGE_OFFSET - 1)
#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE)
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index 93b8956e25e4..2c5df945d43c 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -66,7 +66,7 @@ struct pt_regs {
#define REG_FMT "%08lx"
#endif
-#define user_mode(regs) (((regs)->sstatus & SR_PS) == 0)
+#define user_mode(regs) (((regs)->sstatus & SR_SPP) == 0)
/* Helpers for working with the instruction pointer */
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
index 04c71d938afd..2fd27e8ef1fd 100644
--- a/arch/riscv/include/asm/spinlock.h
+++ b/arch/riscv/include/asm/spinlock.h
@@ -24,7 +24,7 @@
/* FIXME: Replace this with a ticket lock, like MIPS. */
-#define arch_spin_is_locked(x) ((x)->lock != 0)
+#define arch_spin_is_locked(x) (READ_ONCE((x)->lock) != 0)
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
@@ -58,15 +58,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
}
}
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
- smp_rmb();
- do {
- cpu_relax();
- } while (arch_spin_is_locked(lock));
- smp_acquire__after_ctrl_dep();
-}
-
/***********************************************************/
static inline void arch_read_lock(arch_rwlock_t *lock)
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 22c3536ed281..f8fa1cd2dad9 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -64,8 +64,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_stack (init_thread_union.stack)
-
#endif /* !__ASSEMBLY__ */
/*
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index 3df4932d8964..2f26989cb864 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -18,7 +18,7 @@
typedef unsigned long cycles_t;
-static inline cycles_t get_cycles(void)
+static inline cycles_t get_cycles_inline(void)
{
cycles_t n;
@@ -27,6 +27,7 @@ static inline cycles_t get_cycles(void)
: "=r" (n));
return n;
}
+#define get_cycles get_cycles_inline
#ifdef CONFIG_64BIT
static inline uint64_t get_cycles64(void)
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 5ee4ae370b5e..7b9c24ebdf52 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -15,9 +15,12 @@
#ifndef _ASM_RISCV_TLBFLUSH_H
#define _ASM_RISCV_TLBFLUSH_H
-#ifdef CONFIG_MMU
+#include <linux/mm_types.h>
-/* Flush entire local TLB */
+/*
+ * Flush entire local TLB. 'sfence.vma' implicitly fences with the instruction
+ * cache as well, so a 'fence.i' is not necessary.
+ */
static inline void local_flush_tlb_all(void)
{
__asm__ __volatile__ ("sfence.vma" : : : "memory");
@@ -59,6 +62,4 @@ static inline void flush_tlb_kernel_range(unsigned long start,
flush_tlb_all();
}
-#endif /* CONFIG_MMU */
-
#endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 27b90d64814b..14b0b22fb578 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -127,7 +127,6 @@ extern int fixup_exception(struct pt_regs *state);
* call.
*/
-#ifdef CONFIG_MMU
#define __get_user_asm(insn, x, ptr, err) \
do { \
uintptr_t __tmp; \
@@ -153,13 +152,11 @@ do { \
__disable_user_access(); \
(x) = __x; \
} while (0)
-#endif /* CONFIG_MMU */
#ifdef CONFIG_64BIT
#define __get_user_8(x, ptr, err) \
__get_user_asm("ld", x, ptr, err)
#else /* !CONFIG_64BIT */
-#ifdef CONFIG_MMU
#define __get_user_8(x, ptr, err) \
do { \
u32 __user *__ptr = (u32 __user *)(ptr); \
@@ -193,7 +190,6 @@ do { \
(x) = (__typeof__(x))((__typeof__((x)-(x)))( \
(((u64)__hi << 32) | __lo))); \
} while (0)
-#endif /* CONFIG_MMU */
#endif /* CONFIG_64BIT */
@@ -267,8 +263,6 @@ do { \
((x) = 0, -EFAULT); \
})
-
-#ifdef CONFIG_MMU
#define __put_user_asm(insn, x, ptr, err) \
do { \
uintptr_t __tmp; \
@@ -292,14 +286,11 @@ do { \
: "rJ" (__x), "i" (-EFAULT)); \
__disable_user_access(); \
} while (0)
-#endif /* CONFIG_MMU */
-
#ifdef CONFIG_64BIT
#define __put_user_8(x, ptr, err) \
__put_user_asm("sd", x, ptr, err)
#else /* !CONFIG_64BIT */
-#ifdef CONFIG_MMU
#define __put_user_8(x, ptr, err) \
do { \
u32 __user *__ptr = (u32 __user *)(ptr); \
@@ -329,7 +320,6 @@ do { \
: "rJ" (__x), "rJ" (__x >> 32), "i" (-EFAULT)); \
__disable_user_access(); \
} while (0)
-#endif /* CONFIG_MMU */
#endif /* CONFIG_64BIT */
@@ -438,7 +428,6 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
* will set "err" to -EFAULT, while successful accesses return the previous
* value.
*/
-#ifdef CONFIG_MMU
#define __cmpxchg_user(ptr, old, new, err, size, lrb, scb) \
({ \
__typeof__(ptr) __ptr = (ptr); \
@@ -508,6 +497,5 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
(err) = __err; \
__ret; \
})
-#endif /* CONFIG_MMU */
#endif /* _ASM_RISCV_UACCESS_H */
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
index 9f250ed007cd..2f704a5c4196 100644
--- a/arch/riscv/include/asm/unistd.h
+++ b/arch/riscv/include/asm/unistd.h
@@ -14,3 +14,4 @@
#define __ARCH_HAVE_MMU
#define __ARCH_WANT_SYS_CLONE
#include <uapi/asm/unistd.h>
+#include <uapi/asm/syscalls.h>
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index 602f61257553..541544d64c33 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -38,4 +38,8 @@ struct vdso_data {
(void __user *)((unsigned long)(base) + __vdso_##name); \
})
+#ifdef CONFIG_SMP
+asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+#endif
+
#endif /* _ASM_RISCV_VDSO_H */
diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild
index 5ded96b06352..7e91f4850475 100644
--- a/arch/riscv/include/uapi/asm/Kbuild
+++ b/arch/riscv/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += setup.h
generic-y += unistd.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/riscv/include/uapi/asm/syscalls.h b/arch/riscv/include/uapi/asm/syscalls.h
new file mode 100644
index 000000000000..818655b0d535
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/syscalls.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM__UAPI__SYSCALLS_H
+#define _ASM__UAPI__SYSCALLS_H
+
+/*
+ * Allows the instruction cache to be flushed from userspace. Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart. There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller. We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
+
+#endif
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 20ee86f782a9..7404ec222406 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -196,7 +196,7 @@ handle_syscall:
addi s2, s2, 0x4
REG_S s2, PT_SEPC(sp)
/* System calls run with interrupts enabled */
- csrs sstatus, SR_IE
+ csrs sstatus, SR_SIE
/* Trace syscalls, but only if requested by the user. */
REG_L t0, TASK_TI_FLAGS(tp)
andi t0, t0, _TIF_SYSCALL_TRACE
@@ -224,8 +224,8 @@ ret_from_syscall:
ret_from_exception:
REG_L s0, PT_SSTATUS(sp)
- csrc sstatus, SR_IE
- andi s0, s0, SR_PS
+ csrc sstatus, SR_SIE
+ andi s0, s0, SR_SPP
bnez s0, restore_all
resume_userspace:
@@ -255,7 +255,7 @@ work_pending:
bnez s1, work_resched
work_notifysig:
/* Handle pending signals and notify-resume requests */
- csrs sstatus, SR_IE /* Enable interrupts for do_notify_resume() */
+ csrs sstatus, SR_SIE /* Enable interrupts for do_notify_resume() */
move a0, sp /* pt_regs */
move a1, s0 /* current_thread_info->flags */
tail do_notify_resume
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 76af908f87c1..78f670d70133 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -152,6 +152,3 @@ END(_start)
__PAGE_ALIGNED_BSS
/* Empty zero page */
.balign PAGE_SIZE
-ENTRY(empty_zero_page)
- .fill (empty_zero_page + PAGE_SIZE) - ., 1, 0x00
-END(empty_zero_page)
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 0d90dcc1fbd3..d74d4adf2d54 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -76,7 +76,7 @@ void show_regs(struct pt_regs *regs)
void start_thread(struct pt_regs *regs, unsigned long pc,
unsigned long sp)
{
- regs->sstatus = SR_PIE /* User mode, irqs on */ | SR_FS_INITIAL;
+ regs->sstatus = SR_SPIE /* User mode, irqs on */ | SR_FS_INITIAL;
regs->sepc = pc;
regs->sp = sp;
set_fs(USER_DS);
@@ -110,7 +110,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
const register unsigned long gp __asm__ ("gp");
memset(childregs, 0, sizeof(struct pt_regs));
childregs->gp = gp;
- childregs->sstatus = SR_PS | SR_PIE; /* Supervisor, irqs on */
+ childregs->sstatus = SR_SPP | SR_SPIE; /* Supervisor, irqs on */
p->thread.ra = (unsigned long)ret_from_kernel_thread;
p->thread.s[0] = usp; /* fn */
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
index 23cc81ec9e94..551734248748 100644
--- a/arch/riscv/kernel/riscv_ksyms.c
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -12,4 +12,7 @@
/*
* Assembly functions that may be used (directly or indirectly) by modules
*/
+EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(__copy_user);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memcpy);
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index de7db114c315..cb7b0c63014e 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -38,10 +38,6 @@
#include <asm/tlbflush.h>
#include <asm/thread_info.h>
-#ifdef CONFIG_HVC_RISCV_SBI
-#include <asm/hvc_riscv_sbi.h>
-#endif
-
#ifdef CONFIG_DUMMY_CONSOLE
struct screen_info screen_info = {
.orig_video_lines = 30,
@@ -58,7 +54,12 @@ static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
#endif /* CONFIG_CMDLINE_BOOL */
unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
unsigned long pfn_base;
+EXPORT_SYMBOL(pfn_base);
+
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
/* The lucky hart to first increment this variable will boot the other cores */
atomic_t hart_lottery;
@@ -207,13 +208,6 @@ static void __init setup_bootmem(void)
void __init setup_arch(char **cmdline_p)
{
-#if defined(CONFIG_HVC_RISCV_SBI)
- if (likely(early_console == NULL)) {
- early_console = &riscv_sbi_early_console_dev;
- register_console(early_console);
- }
-#endif
-
#ifdef CONFIG_CMDLINE_BOOL
#ifdef CONFIG_CMDLINE_OVERRIDE
strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index b4a71ec5906f..6d3962435720 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -38,6 +38,13 @@ enum ipi_message_type {
IPI_MAX
};
+
+/* Unsupported */
+int setup_profiling_timer(unsigned int multiplier)
+{
+ return -EINVAL;
+}
+
irqreturn_t handle_ipi(void)
{
unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
@@ -108,3 +115,51 @@ void smp_send_reschedule(int cpu)
{
send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
}
+
+/*
+ * Performs an icache flush for the given MM context. RISC-V has no direct
+ * mechanism for instruction cache shoot downs, so instead we send an IPI that
+ * informs the remote harts they need to flush their local instruction caches.
+ * To avoid pathologically slow behavior in a common case (a bunch of
+ * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
+ * IPIs for harts that are not currently executing a MM context and instead
+ * schedule a deferred local instruction cache flush to be performed before
+ * execution resumes on each hart.
+ */
+void flush_icache_mm(struct mm_struct *mm, bool local)
+{
+ unsigned int cpu;
+ cpumask_t others, *mask;
+
+ preempt_disable();
+
+ /* Mark every hart's icache as needing a flush for this MM. */
+ mask = &mm->context.icache_stale_mask;
+ cpumask_setall(mask);
+ /* Flush this hart's I$ now, and mark it as flushed. */
+ cpu = smp_processor_id();
+ cpumask_clear_cpu(cpu, mask);
+ local_flush_icache_all();
+
+ /*
+ * Flush the I$ of other harts concurrently executing, and mark them as
+ * flushed.
+ */
+ cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+ local |= cpumask_empty(&others);
+ if (mm != current->active_mm || !local)
+ sbi_remote_fence_i(others.bits);
+ else {
+ /*
+ * It's assumed that at least one strongly ordered operation is
+ * performed on this hart between setting a hart's cpumask bit
+ * and scheduling this MM context on that hart. Sending an SBI
+ * remote message will do this, but in the case where no
+ * messages are sent we still need to order this hart's writes
+ * with flush_icache_deferred().
+ */
+ smp_mb();
+ }
+
+ preempt_enable();
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 4351be7d0533..79c78668258e 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -14,8 +14,8 @@
*/
#include <linux/syscalls.h>
-#include <asm/cmpxchg.h>
#include <asm/unistd.h>
+#include <asm/cacheflush.h>
static long riscv_sys_mmap(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags,
@@ -47,3 +47,34 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
}
#endif /* !CONFIG_64BIT */
+
+#ifdef CONFIG_SMP
+/*
+ * Allows the instruction cache to be flushed from userspace. Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart. There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * sys_riscv_flush_icache() is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller. We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
+ uintptr_t, flags)
+{
+ struct mm_struct *mm = current->mm;
+ bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0;
+
+ /* Check the reserved flags. */
+ if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL))
+ return -EINVAL;
+
+ flush_icache_mm(mm, local);
+
+ return 0;
+}
+#endif
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
index 4e30dc5fb593..ade52b903a43 100644
--- a/arch/riscv/kernel/syscall_table.c
+++ b/arch/riscv/kernel/syscall_table.c
@@ -15,6 +15,7 @@
#include <linux/linkage.h>
#include <linux/syscalls.h>
#include <asm-generic/syscalls.h>
+#include <asm/vdso.h>
#undef __SYSCALL
#define __SYSCALL(nr, call) [nr] = (call),
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 523d0a8ac8db..324568d33921 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -1,7 +1,12 @@
# Copied from arch/tile/kernel/vdso/Makefile
# Symbols present in the vdso
-vdso-syms = rt_sigreturn
+vdso-syms = rt_sigreturn
+vdso-syms += gettimeofday
+vdso-syms += clock_gettime
+vdso-syms += clock_getres
+vdso-syms += getcpu
+vdso-syms += flush_icache
# Files to link into the vdso
obj-vdso = $(patsubst %, %.o, $(vdso-syms))
diff --git a/arch/riscv/kernel/vdso/clock_getres.S b/arch/riscv/kernel/vdso/clock_getres.S
new file mode 100644
index 000000000000..edf7e2339648
--- /dev/null
+++ b/arch/riscv/kernel/vdso/clock_getres.S
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_clock_getres(clockid_t clock_id, struct timespec *res); */
+ENTRY(__vdso_clock_getres)
+ .cfi_startproc
+ /* For now, just do the syscall. */
+ li a7, __NR_clock_getres
+ ecall
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_clock_getres)
diff --git a/arch/riscv/kernel/vdso/clock_gettime.S b/arch/riscv/kernel/vdso/clock_gettime.S
new file mode 100644
index 000000000000..aac65676c6d5
--- /dev/null
+++ b/arch/riscv/kernel/vdso/clock_gettime.S
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_clock_gettime(clockid_t clock_id, struct timespec *tp); */
+ENTRY(__vdso_clock_gettime)
+ .cfi_startproc
+ /* For now, just do the syscall. */
+ li a7, __NR_clock_gettime
+ ecall
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_clock_gettime)
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
new file mode 100644
index 000000000000..023e4d4aef58
--- /dev/null
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
+ENTRY(__vdso_flush_icache)
+ .cfi_startproc
+#ifdef CONFIG_SMP
+ li a7, __NR_riscv_flush_icache
+ ecall
+#else
+ fence.i
+ li a0, 0
+#endif
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_flush_icache)
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
new file mode 100644
index 000000000000..cc7e98924484
--- /dev/null
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
+ENTRY(__vdso_getcpu)
+ .cfi_startproc
+ /* For now, just do the syscall. */
+ li a7, __NR_getcpu
+ ecall
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_getcpu)
diff --git a/arch/riscv/kernel/vdso/gettimeofday.S b/arch/riscv/kernel/vdso/gettimeofday.S
new file mode 100644
index 000000000000..da85d33e8990
--- /dev/null
+++ b/arch/riscv/kernel/vdso/gettimeofday.S
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+ .text
+/* int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); */
+ENTRY(__vdso_gettimeofday)
+ .cfi_startproc
+ /* For now, just do the syscall. */
+ li a7, __NR_gettimeofday
+ ecall
+ ret
+ .cfi_endproc
+ENDPROC(__vdso_gettimeofday)
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 8c9dce95c11d..cd1d47e0724b 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -70,8 +70,11 @@ VERSION
LINUX_4.15 {
global:
__vdso_rt_sigreturn;
- __vdso_cmpxchg32;
- __vdso_cmpxchg64;
+ __vdso_gettimeofday;
+ __vdso_clock_gettime;
+ __vdso_clock_getres;
+ __vdso_getcpu;
+ __vdso_flush_icache;
local: *;
};
}
diff --git a/arch/riscv/lib/delay.c b/arch/riscv/lib/delay.c
index 1cc4ac3964b4..dce8ae24c6d3 100644
--- a/arch/riscv/lib/delay.c
+++ b/arch/riscv/lib/delay.c
@@ -84,6 +84,7 @@ void __delay(unsigned long cycles)
while ((unsigned long)(get_cycles() - t0) < cycles)
cpu_relax();
}
+EXPORT_SYMBOL(__delay);
void udelay(unsigned long usecs)
{
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 81f7d9ce6d88..eb22ab49b3e0 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -2,3 +2,4 @@ obj-y += init.o
obj-y += fault.o
obj-y += extable.o
obj-y += ioremap.o
+obj-y += cacheflush.o
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
new file mode 100644
index 000000000000..498c0a0814fe
--- /dev/null
+++ b/arch/riscv/mm/cacheflush.c
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+void flush_icache_pte(pte_t pte)
+{
+ struct page *page = pte_page(pte);
+
+ if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+ flush_icache_all();
+}
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index df2ca3c65048..0713f3c67ab4 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -63,7 +63,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
goto vmalloc_fault;
/* Enable interrupts if they were enabled in the parent context. */
- if (likely(regs->sstatus & SR_PIE))
+ if (likely(regs->sstatus & SR_SPIE))
local_irq_enable();
/*
diff --git a/arch/riscv/mm/ioremap.c b/arch/riscv/mm/ioremap.c
index e99194a4077e..70ef2724cdf6 100644
--- a/arch/riscv/mm/ioremap.c
+++ b/arch/riscv/mm/ioremap.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL(ioremap);
*
* Caller must ensure there is only one unmapping for the same pointer.
*/
-void iounmap(void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
{
vunmap((void *)((unsigned long)addr & PAGE_MASK));
}
diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index eae2c64cf69d..9fdff3fe1a42 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
obj-y += kernel/
obj-y += mm/
obj-$(CONFIG_KVM) += kvm/
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 6b3f41985f28..de54cfc6109d 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
#
# s390/Makefile
#
@@ -6,10 +7,6 @@
# for "archclean" and "archdep" for cleaning up and making dependencies for
# this architecture
#
-# 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) 1994 by Linus Torvalds
#
diff --git a/arch/s390/appldata/Makefile b/arch/s390/appldata/Makefile
index 99f1cf071304..b06def4a4f2f 100644
--- a/arch/s390/appldata/Makefile
+++ b/arch/s390/appldata/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
#
# Makefile for the Linux - z/VM Monitor Stream.
#
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index ef3fb1b9201f..cb6e8066b1ad 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Base infrastructure for Linux-z/VM Monitor Stream, Stage 1.
* Exports appldata_register_ops() and appldata_unregister_ops() for the
diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c
index 598df5708501..e68136c3c23a 100644
--- a/arch/s390/appldata/appldata_mem.c
+++ b/arch/s390/appldata/appldata_mem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Data gathering module for Linux-VM Monitor Stream, Stage 1.
* Collects data related to memory management.
diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c
index 66037d2622b4..8bc14b0d1def 100644
--- a/arch/s390/appldata/appldata_net_sum.c
+++ b/arch/s390/appldata/appldata_net_sum.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Data gathering module for Linux-VM Monitor Stream, Stage 1.
* Collects accumulated network statistics (Packets received/transmitted,
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 45b3178200ab..433a994b1a89 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Data gathering module for Linux-VM Monitor Stream, Stage 1.
* Collects misc. OS related data (CPU utilization, running processes).
diff --git a/arch/s390/boot/compressed/vmlinux.scr b/arch/s390/boot/compressed/vmlinux.scr
index f02382ae5c48..42a242597f34 100644
--- a/arch/s390/boot/compressed/vmlinux.scr
+++ b/arch/s390/boot/compressed/vmlinux.scr
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
SECTIONS
{
.rodata.compressed : {
diff --git a/arch/s390/boot/install.sh b/arch/s390/boot/install.sh
index aed3069699bd..bed227f267ae 100644
--- a/arch/s390/boot/install.sh
+++ b/arch/s390/boot/install.sh
@@ -1,11 +1,8 @@
#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
#
# arch/s390x/boot/install.sh
#
-# 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) 1995 by Linus Torvalds
#
# Adapted from code in arch/i386/boot/Makefile by H. Peter Anvin
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index b48e20dd94e9..d60798737d86 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
@@ -11,12 +12,6 @@
* Harald Freudenberger <freude@de.ibm.com>
*
* Derived from "crypto/aes_generic.c"
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#define KMSG_COMPONENT "aes_s390"
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
index 36aefc07d10c..8720e9203ecf 100644
--- a/arch/s390/crypto/arch_random.c
+++ b/arch/s390/crypto/arch_random.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* s390 arch random implementation.
*
* Copyright IBM Corp. 2017
* Author(s): Harald Freudenberger <freude@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
*/
#include <linux/kernel.h>
diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c
index 992e630c227b..436865926c26 100644
--- a/arch/s390/crypto/crc32-vx.c
+++ b/arch/s390/crypto/crc32-vx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Crypto-API module for CRC-32 algorithms implemented with the
* z/Architecture Vector Extension Facility.
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 0d296662bbf0..5346b5a80bb6 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
@@ -6,12 +7,6 @@
* Copyright IBM Corp. 2003, 2011
* Author(s): Thomas Spatzier
* Jan Glauber (jan.glauber@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
*/
#include <linux/init.h>
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index 564616d48d8b..3b7f96c9eead 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Cryptographic API.
*
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index a4e903ed7e21..003932db8d12 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Cryptographic API.
*
@@ -7,11 +8,6 @@
* Copyright IBM Corp. 2017
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
* Harald Freudenberger <freude@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
*/
#define KMSG_COMPONENT "paes_s390"
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 3e47c4a0f18b..a97a1802cfb4 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2006, 2015
* Author(s): Jan Glauber <jan.glauber@de.ibm.com>
diff --git a/arch/s390/crypto/sha.h b/arch/s390/crypto/sha.h
index 10f200790079..d6f8258b44df 100644
--- a/arch/s390/crypto/sha.h
+++ b/arch/s390/crypto/sha.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Cryptographic API.
*
@@ -5,12 +6,6 @@
*
* Copyright IBM Corp. 2007
* Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#ifndef _CRYPTO_ARCH_S390_SHA_H
#define _CRYPTO_ARCH_S390_SHA_H
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index c7de53d8da75..a00c17f761c1 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
@@ -16,12 +17,6 @@
* Copyright (c) Alan Smithee.
* Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
* Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#include <crypto/internal/hash.h>
#include <linux/init.h>
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index 53c277999a28..944aa6b237cd 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
@@ -6,12 +7,6 @@
* s390 Version:
* Copyright IBM Corp. 2005, 2011
* Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#include <crypto/internal/hash.h>
#include <linux/init.h>
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 2f4caa1ef123..b17eded532b1 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
@@ -5,12 +6,6 @@
*
* Copyright IBM Corp. 2007
* Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#include <crypto/internal/hash.h>
#include <crypto/sha.h>
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index c740f77285b2..cf0718d121bc 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Cryptographic API.
*
@@ -5,12 +6,6 @@
*
* Copyright IBM Corp. 2007
* Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
*/
#include <crypto/internal/hash.h>
diff --git a/arch/s390/hypfs/Makefile b/arch/s390/hypfs/Makefile
index 2ee25ba252d6..06f601509ce9 100644
--- a/arch/s390/hypfs/Makefile
+++ b/arch/s390/hypfs/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
#
# Makefile for the linux hypfs filesystem routines.
#
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index cf8a2d92467f..43bbe63e2992 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -1,9 +1,9 @@
+// SPDX-License-Identifier: GPL-1.0+
/*
* Hypervisor filesystem for Linux on s390.
*
* Copyright IBM Corp. 2006, 2008
* Author(s): Michael Holzheu <holzheu@de.ibm.com>
- * License: GPL
*/
#define KMSG_COMPONENT "hypfs"
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 41c211a4d8b1..048450869328 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
generic-y += asm-offsets.h
generic-y += cacheflush.h
generic-y += clkdev.h
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index a72002056b54..c2cf7bcdef9b 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_S390_ALTERNATIVE_H
#define _ASM_S390_ALTERNATIVE_H
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index c02f4aba88a6..cfce6835b109 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Adjunct processor (AP) interfaces
*
* Copyright IBM Corp. 2017
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Tony Krowiak <akrowia@linux.vnet.ibm.com>
* Martin Schwidefsky <schwidefsky@de.ibm.com>
* Harald Freudenberger <freude@de.ibm.com>
diff --git a/arch/s390/include/asm/bugs.h b/arch/s390/include/asm/bugs.h
index 0f5bd894f4dc..aa42a179be33 100644
--- a/arch/s390/include/asm/bugs.h
+++ b/arch/s390/include/asm/bugs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* S390 version
* Copyright IBM Corp. 1999
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 5e6a63641a5f..9830fb6b076e 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -189,79 +189,6 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */
typedef u32 compat_sigset_word;
-typedef union compat_sigval {
- compat_int_t sival_int;
- compat_uptr_t sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[128/sizeof(int) - 3];
-
- /* kill() */
- struct {
- pid_t _pid; /* sender's pid */
- uid_t _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- compat_sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- pid_t _pid; /* sender's pid */
- uid_t _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- pid_t _pid; /* which child */
- uid_t _uid; /* sender's uid */
- int _status;/* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- __u32 _addr; /* faulting insn/memory ref. - pointer */
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
- } _sifields;
-} compat_siginfo_t;
-
-/*
- * How these fields are to be accessed.
- */
-#define si_pid _sifields._kill._pid
-#define si_uid _sifields._kill._uid
-#define si_status _sifields._sigchld._status
-#define si_utime _sifields._sigchld._utime
-#define si_stime _sifields._sigchld._stime
-#define si_value _sifields._rt._sigval
-#define si_int _sifields._rt._sigval.sival_int
-#define si_ptr _sifields._rt._sigval.sival_ptr
-#define si_addr _sifields._sigfault._addr
-#define si_band _sifields._sigpoll._band
-#define si_fd _sifields._sigpoll._fd
-#define si_tid _sifields._timer._tid
-#define si_overrun _sifields._timer._overrun
-
#define COMPAT_OFF_T_MAX 0x7fffffff
/*
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 792cda339af1..dd08db491b89 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* CPU-measurement facilities
*
* Copyright IBM Corp. 2012
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
* Jan Glauber <jang@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#ifndef _ASM_S390_CPU_MF_H
#define _ASM_S390_CPU_MF_H
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 9a3cb3983c01..1a61b1b997f2 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -194,13 +194,14 @@ struct arch_elf_state {
#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE PAGE_SIZE
-/*
- * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
- * space open for things that want to use the area for 32-bit pointers.
- */
-#define ELF_ET_DYN_BASE (is_compat_task() ? 0x000400000UL : \
- 0x100000000UL)
+/* 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. 64-bit
+ tasks are aligned to 4GB. */
+#define ELF_ET_DYN_BASE (is_compat_task() ? \
+ (STACK_TOP / 3 * 2) : \
+ (STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
/* This yields a mask that user programs can use to figure out what
instruction set this CPU supports. */
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 921391f2341e..13de80cf741c 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
#ifndef _ASM_S390_KPROBES_H
#define _ASM_S390_KPROBES_H
/*
* Kernel Probes (KProbes)
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
* Copyright IBM Corp. 2002, 2006
*
* 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index f3a9b5a445b6..c1b0a9ac1dc8 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* definition for kernel virtual machines on s390
*
* Copyright IBM Corp. 2008, 2009
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
*/
@@ -210,7 +207,8 @@ struct kvm_s390_sie_block {
__u16 ipa; /* 0x0056 */
__u32 ipb; /* 0x0058 */
__u32 scaoh; /* 0x005c */
- __u8 reserved60; /* 0x0060 */
+#define FPF_BPBC 0x20
+ __u8 fpf; /* 0x0060 */
#define ECB_GS 0x40
#define ECB_TE 0x10
#define ECB_SRSI 0x04
diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h
index 41393052ac57..74eeec9c0a80 100644
--- a/arch/s390/include/asm/kvm_para.h
+++ b/arch/s390/include/asm/kvm_para.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* definition for paravirtual devices on s390
*
* Copyright IBM Corp. 2008
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
*/
/*
@@ -20,8 +17,6 @@
*
* Copyright IBM Corp. 2007,2008
* Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
*/
#ifndef __S390_KVM_PARA_H
#define __S390_KVM_PARA_H
diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h
index 6de5c6cb0061..672f95b12d40 100644
--- a/arch/s390/include/asm/livepatch.h
+++ b/arch/s390/include/asm/livepatch.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* livepatch.h - s390-specific Kernel Live Patching Core
*
@@ -7,13 +8,6 @@
* Jiri Slaby
*/
-/*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
#ifndef ASM_LIVEPATCH_H
#define ASM_LIVEPATCH_H
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index f4a07f788f78..65154eaa3714 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -28,7 +28,7 @@ static inline int init_new_context(struct task_struct *tsk,
#ifdef CONFIG_PGSTE
mm->context.alloc_pgste = page_table_allocate_pgste ||
test_thread_flag(TIF_PGSTE) ||
- current->mm->context.alloc_pgste;
+ (current->mm && current->mm->context.alloc_pgste);
mm->context.has_pgste = 0;
mm->context.use_skey = 0;
mm->context.use_cmma = 0;
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index d6c9d1e0dc2d..b9c0e361748b 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -40,6 +40,7 @@ struct pt_regs;
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
+#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
/* Perf pt_regs extension for sample-data-entry indicators */
struct perf_sf_sde_regs {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index d7fe9838084d..0a6b0286c32e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -709,7 +709,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
}
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index a3788dafc0e1..6f70d81c40f2 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -74,9 +74,14 @@ enum {
*/
struct pt_regs
{
- unsigned long args[1];
- psw_t psw;
- unsigned long gprs[NUM_GPRS];
+ union {
+ user_pt_regs user_regs;
+ struct {
+ unsigned long args[1];
+ psw_t psw;
+ unsigned long gprs[NUM_GPRS];
+ };
+ };
unsigned long orig_gpr2;
unsigned int int_code;
unsigned int int_parm;
diff --git a/arch/s390/include/asm/segment.h b/arch/s390/include/asm/segment.h
index 8bfce3475b1c..97a0582b8d0f 100644
--- a/arch/s390/include/asm/segment.h
+++ b/arch/s390/include/asm/segment.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_SEGMENT_H
#define _ASM_SEGMENT_H
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index ec7b476c1ac5..c61b2cc1a8a8 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -30,21 +30,20 @@ static inline void restore_access_regs(unsigned int *acrs)
asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs));
}
-#define switch_to(prev,next,last) do { \
- if (prev->mm) { \
- save_fpu_regs(); \
- save_access_regs(&prev->thread.acrs[0]); \
- save_ri_cb(prev->thread.ri_cb); \
- save_gs_cb(prev->thread.gs_cb); \
- } \
+#define switch_to(prev, next, last) do { \
+ /* save_fpu_regs() sets the CIF_FPU flag, which enforces \
+ * a restore of the floating point / vector registers as \
+ * soon as the next task returns to user space \
+ */ \
+ save_fpu_regs(); \
+ save_access_regs(&prev->thread.acrs[0]); \
+ save_ri_cb(prev->thread.ri_cb); \
+ save_gs_cb(prev->thread.gs_cb); \
update_cr_regs(next); \
- if (next->mm) { \
- set_cpu_flag(CIF_FPU); \
- restore_access_regs(&next->thread.acrs[0]); \
- restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \
- restore_gs_cb(next->thread.gs_cb); \
- } \
- prev = __switch_to(prev,next); \
+ restore_access_regs(&next->thread.acrs[0]); \
+ restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \
+ restore_gs_cb(next->thread.gs_cb); \
+ prev = __switch_to(prev, next); \
} while (0)
#endif /* __ASM_SWITCH_TO_H */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 6bc941be6921..96f9a9151fde 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Access to user system call parameters and results
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#ifndef _ASM_SYSCALL_H
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index a702cb9d4269..25057c118d56 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* definition for store system information stsi
*
* Copyright IBM Corp. 2001, 2008
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Ulrich Weigand <weigand@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
*/
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 0880a37b6d3b..25d6ec3aaddd 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -42,8 +42,6 @@ struct thread_info {
.flags = 0, \
}
-#define init_stack (init_thread_union.stack)
-
void arch_release_task_struct(struct task_struct *tsk);
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 1807229b292f..cca406fdbe51 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -53,6 +53,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu);
static inline void topology_init_early(void) { }
static inline void topology_schedule_update(void) { }
static inline int topology_cpu_init(struct cpu *cpu) { return 0; }
+static inline int topology_cpu_dedicated(int cpu_nr) { return 0; }
static inline void topology_expect_change(void) { }
#endif /* CONFIG_SCHED_TOPOLOGY */
diff --git a/arch/s390/include/asm/vga.h b/arch/s390/include/asm/vga.h
index d375526c261f..605dc46bac5e 100644
--- a/arch/s390/include/asm/vga.h
+++ b/arch/s390/include/asm/vga.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_S390_VGA_H
#define _ASM_S390_VGA_H
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index 098f28778a13..92b7c9b3e641 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
diff --git a/arch/s390/include/uapi/asm/bpf_perf_event.h b/arch/s390/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..cefe7c7cd4f6
--- /dev/null
+++ b/arch/s390/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 9ad172dcd912..4cdaa55fabfe 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -6,10 +6,6 @@
*
* Copyright IBM Corp. 2008
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
*/
@@ -228,6 +224,7 @@ struct kvm_guest_debug_arch {
#define KVM_SYNC_RICCB (1UL << 7)
#define KVM_SYNC_FPRS (1UL << 8)
#define KVM_SYNC_GSCB (1UL << 9)
+#define KVM_SYNC_BPBC (1UL << 10)
/* length and alignment of the sdnx as a power of two */
#define SDNXC 8
#define SDNXL (1UL << SDNXC)
@@ -251,7 +248,9 @@ struct kvm_sync_regs {
};
__u8 reserved[512]; /* for future vector expansion */
__u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
- __u8 padding1[52]; /* riccb needs to be 64byte aligned */
+ __u8 bpbc : 1; /* bp mode */
+ __u8 reserved2 : 7;
+ __u8 padding1[51]; /* riccb needs to be 64byte aligned */
__u8 riccb[64]; /* runtime instrumentation controls block */
__u8 padding2[192]; /* sdnx needs to be 256byte aligned */
union {
diff --git a/arch/s390/include/uapi/asm/kvm_para.h b/arch/s390/include/uapi/asm/kvm_para.h
index 0dc86b3a7cb0..b9ab584adf43 100644
--- a/arch/s390/include/uapi/asm/kvm_para.h
+++ b/arch/s390/include/uapi/asm/kvm_para.h
@@ -4,9 +4,5 @@
*
* Copyright IBM Corp. 2008
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
*/
diff --git a/arch/s390/include/uapi/asm/kvm_perf.h b/arch/s390/include/uapi/asm/kvm_perf.h
index c36c97ffdc6f..84606b8cc49e 100644
--- a/arch/s390/include/uapi/asm/kvm_perf.h
+++ b/arch/s390/include/uapi/asm/kvm_perf.h
@@ -4,10 +4,6 @@
*
* Copyright 2014 IBM Corp.
* Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#ifndef __LINUX_KVM_PERF_S390_H
diff --git a/arch/s390/include/uapi/asm/perf_regs.h b/arch/s390/include/uapi/asm/perf_regs.h
index 7c8564f98205..d17dd9e5d516 100644
--- a/arch/s390/include/uapi/asm/perf_regs.h
+++ b/arch/s390/include/uapi/asm/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _ASM_S390_PERF_REGS_H
#define _ASM_S390_PERF_REGS_H
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 0d23c8ff2900..543dd70e12c8 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -162,7 +162,7 @@
#define GPR_SIZE 8
#define CR_SIZE 8
-#define STACK_FRAME_OVERHEAD 160 /* size of minimum stack frame */
+#define STACK_FRAME_OVERHEAD 160 /* size of minimum stack frame */
#endif /* __s390x__ */
@@ -179,17 +179,16 @@
#define ACR_SIZE 4
-#define PTRACE_OLDSETOPTIONS 21
+#define PTRACE_OLDSETOPTIONS 21
#ifndef __ASSEMBLY__
#include <linux/stddef.h>
#include <linux/types.h>
-typedef union
-{
- float f;
- double d;
- __u64 ui;
+typedef union {
+ float f;
+ double d;
+ __u64 ui;
struct
{
__u32 hi;
@@ -197,23 +196,21 @@ typedef union
} fp;
} freg_t;
-typedef struct
-{
- __u32 fpc;
+typedef struct {
+ __u32 fpc;
__u32 pad;
- freg_t fprs[NUM_FPRS];
+ freg_t fprs[NUM_FPRS];
} s390_fp_regs;
-#define FPC_EXCEPTION_MASK 0xF8000000
-#define FPC_FLAGS_MASK 0x00F80000
-#define FPC_DXC_MASK 0x0000FF00
-#define FPC_RM_MASK 0x00000003
+#define FPC_EXCEPTION_MASK 0xF8000000
+#define FPC_FLAGS_MASK 0x00F80000
+#define FPC_DXC_MASK 0x0000FF00
+#define FPC_RM_MASK 0x00000003
/* this typedef defines how a Program Status Word looks like */
-typedef struct
-{
- unsigned long mask;
- unsigned long addr;
+typedef struct {
+ unsigned long mask;
+ unsigned long addr;
} __attribute__ ((aligned(8))) psw_t;
#ifndef __s390x__
@@ -282,8 +279,7 @@ typedef struct
/*
* The s390_regs structure is used to define the elf_gregset_t.
*/
-typedef struct
-{
+typedef struct {
psw_t psw;
unsigned long gprs[NUM_GPRS];
unsigned int acrs[NUM_ACRS];
@@ -291,24 +287,32 @@ typedef struct
} s390_regs;
/*
+ * The user_pt_regs structure exports the beginning of
+ * the in-kernel pt_regs structure to user space.
+ */
+typedef struct {
+ unsigned long args[1];
+ psw_t psw;
+ unsigned long gprs[NUM_GPRS];
+} user_pt_regs;
+
+/*
* Now for the user space program event recording (trace) definitions.
* The following structures are used only for the ptrace interface, don't
* touch or even look at it if you don't want to modify the user-space
* ptrace interface. In particular stay away from it for in-kernel PER.
*/
-typedef struct
-{
+typedef struct {
unsigned long cr[NUM_CR_WORDS];
} per_cr_words;
#define PER_EM_MASK 0xE8000000UL
-typedef struct
-{
+typedef struct {
#ifdef __s390x__
- unsigned : 32;
+ unsigned : 32;
#endif /* __s390x__ */
- unsigned em_branching : 1;
+ unsigned em_branching : 1;
unsigned em_instruction_fetch : 1;
/*
* Switching on storage alteration automatically fixes
@@ -317,44 +321,41 @@ typedef struct
unsigned em_storage_alteration : 1;
unsigned em_gpr_alt_unused : 1;
unsigned em_store_real_address : 1;
- unsigned : 3;
+ unsigned : 3;
unsigned branch_addr_ctl : 1;
- unsigned : 1;
+ unsigned : 1;
unsigned storage_alt_space_ctl : 1;
- unsigned : 21;
+ unsigned : 21;
unsigned long starting_addr;
unsigned long ending_addr;
} per_cr_bits;
-typedef struct
-{
+typedef struct {
unsigned short perc_atmid;
unsigned long address;
unsigned char access_id;
} per_lowcore_words;
-typedef struct
-{
- unsigned perc_branching : 1;
+typedef struct {
+ unsigned perc_branching : 1;
unsigned perc_instruction_fetch : 1;
unsigned perc_storage_alteration : 1;
- unsigned perc_gpr_alt_unused : 1;
+ unsigned perc_gpr_alt_unused : 1;
unsigned perc_store_real_address : 1;
- unsigned : 3;
- unsigned atmid_psw_bit_31 : 1;
- unsigned atmid_validity_bit : 1;
- unsigned atmid_psw_bit_32 : 1;
- unsigned atmid_psw_bit_5 : 1;
- unsigned atmid_psw_bit_16 : 1;
- unsigned atmid_psw_bit_17 : 1;
- unsigned si : 2;
+ unsigned : 3;
+ unsigned atmid_psw_bit_31 : 1;
+ unsigned atmid_validity_bit : 1;
+ unsigned atmid_psw_bit_32 : 1;
+ unsigned atmid_psw_bit_5 : 1;
+ unsigned atmid_psw_bit_16 : 1;
+ unsigned atmid_psw_bit_17 : 1;
+ unsigned si : 2;
unsigned long address;
- unsigned : 4;
- unsigned access_id : 4;
+ unsigned : 4;
+ unsigned access_id : 4;
} per_lowcore_bits;
-typedef struct
-{
+typedef struct {
union {
per_cr_words words;
per_cr_bits bits;
@@ -364,9 +365,9 @@ typedef struct
* the kernel always sets them to zero. To enable single
* stepping use ptrace(PTRACE_SINGLESTEP) instead.
*/
- unsigned single_step : 1;
+ unsigned single_step : 1;
unsigned instruction_fetch : 1;
- unsigned : 30;
+ unsigned : 30;
/*
* These addresses are copied into cr10 & cr11 if single
* stepping is switched off
@@ -376,11 +377,10 @@ typedef struct
union {
per_lowcore_words words;
per_lowcore_bits bits;
- } lowcore;
+ } lowcore;
} per_struct;
-typedef struct
-{
+typedef struct {
unsigned int len;
unsigned long kernel_addr;
unsigned long process_addr;
@@ -390,12 +390,12 @@ typedef struct
* S/390 specific non posix ptrace requests. I chose unusual values so
* they are unlikely to clash with future ptrace definitions.
*/
-#define PTRACE_PEEKUSR_AREA 0x5000
-#define PTRACE_POKEUSR_AREA 0x5001
+#define PTRACE_PEEKUSR_AREA 0x5000
+#define PTRACE_POKEUSR_AREA 0x5001
#define PTRACE_PEEKTEXT_AREA 0x5002
#define PTRACE_PEEKDATA_AREA 0x5003
#define PTRACE_POKETEXT_AREA 0x5004
-#define PTRACE_POKEDATA_AREA 0x5005
+#define PTRACE_POKEDATA_AREA 0x5005
#define PTRACE_GET_LAST_BREAK 0x5006
#define PTRACE_PEEK_SYSTEM_CALL 0x5007
#define PTRACE_POKE_SYSTEM_CALL 0x5008
@@ -413,21 +413,19 @@ typedef struct
* PT_PROT definition is loosely based on hppa bsd definition in
* gdb/hppab-nat.c
*/
-#define PTRACE_PROT 21
+#define PTRACE_PROT 21
-typedef enum
-{
+typedef enum {
ptprot_set_access_watchpoint,
ptprot_set_write_watchpoint,
ptprot_disable_watchpoint
} ptprot_flags;
-typedef struct
-{
+typedef struct {
unsigned long lowaddr;
unsigned long hiaddr;
ptprot_flags prot;
-} ptprot_area;
+} ptprot_area;
/* Sequence of bytes for breakpoint illegal instruction. */
#define S390_BREAKPOINT {0x0,0x1}
@@ -439,8 +437,7 @@ typedef struct
* The user_regs_struct defines the way the user registers are
* store on the stack for signal handling.
*/
-struct user_regs_struct
-{
+struct user_regs_struct {
psw_t psw;
unsigned long gprs[NUM_GPRS];
unsigned int acrs[NUM_ACRS];
diff --git a/arch/s390/include/uapi/asm/sthyi.h b/arch/s390/include/uapi/asm/sthyi.h
index ec113db4eb7e..b1b022316983 100644
--- a/arch/s390/include/uapi/asm/sthyi.h
+++ b/arch/s390/include/uapi/asm/sthyi.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI_ASM_STHYI_H
#define _UAPI_ASM_STHYI_H
diff --git a/arch/s390/include/uapi/asm/virtio-ccw.h b/arch/s390/include/uapi/asm/virtio-ccw.h
index 967aad390105..2b605f7e8483 100644
--- a/arch/s390/include/uapi/asm/virtio-ccw.h
+++ b/arch/s390/include/uapi/asm/virtio-ccw.h
@@ -1,13 +1,9 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
/*
* Definitions for virtio-ccw devices.
*
* Copyright IBM Corp. 2013
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
*/
#ifndef __KVM_VIRTIO_CCW_H
diff --git a/arch/s390/include/uapi/asm/vmcp.h b/arch/s390/include/uapi/asm/vmcp.h
index 4caf71714a55..aeaaa030030e 100644
--- a/arch/s390/include/uapi/asm/vmcp.h
+++ b/arch/s390/include/uapi/asm/vmcp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* Copyright IBM Corp. 2004, 2005
* Interface implementation for communication with the z/VM control program
diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h
index 137ef473584e..d568307321fc 100644
--- a/arch/s390/include/uapi/asm/zcrypt.h
+++ b/arch/s390/include/uapi/asm/zcrypt.h
@@ -9,20 +9,6 @@
* Eric Rossman (edrossma@us.ibm.com)
*
* Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef __ASM_S390_ZCRYPT_H
diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c
index 315986a06cf5..574e77622c04 100644
--- a/arch/s390/kernel/alternative.c
+++ b/arch/s390/kernel/alternative.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/module.h>
#include <asm/alternative.h>
#include <asm/facility.h>
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index f04db3779b34..59eea9c65d3e 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -263,6 +263,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplis
return retval;
}
+ groups_sort(group_info);
retval = set_current_groups(group_info);
put_group_info(group_info);
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index ef246940b44c..18c1eeb847b2 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -50,106 +50,6 @@ typedef struct
struct ucontext32 uc;
} rt_sigframe32;
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
- int err;
-
- /* If you change siginfo_t structure, please be sure
- this code is fixed accordingly.
- It should never copy any pad contained in the structure
- to avoid security leaks, but must copy the generic
- 3 ints plus the relevant union member.
- This routine must convert siginfo from 64bit to 32bit as well
- at the same time. */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user(from->si_code, &to->si_code);
- if (from->si_code < 0)
- err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
- else {
- switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_RT:
- err |= __put_user(from->si_int, &to->si_int);
- /* fallthrough */
- case SIL_KILL:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- case SIL_CHLD:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- err |= __put_user(from->si_status, &to->si_status);
- break;
- case SIL_FAULT:
- err |= __put_user((unsigned long) from->si_addr,
- &to->si_addr);
- break;
- case SIL_POLL:
- err |= __put_user(from->si_band, &to->si_band);
- err |= __put_user(from->si_fd, &to->si_fd);
- break;
- case SIL_TIMER:
- err |= __put_user(from->si_tid, &to->si_tid);
- err |= __put_user(from->si_overrun, &to->si_overrun);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- default:
- break;
- }
- }
- return err ? -EFAULT : 0;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
- int err;
- u32 tmp;
-
- err = __get_user(to->si_signo, &from->si_signo);
- err |= __get_user(to->si_errno, &from->si_errno);
- err |= __get_user(to->si_code, &from->si_code);
-
- if (to->si_code < 0)
- err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
- else {
- switch (siginfo_layout(to->si_signo, to->si_code)) {
- case SIL_RT:
- err |= __get_user(to->si_int, &from->si_int);
- /* fallthrough */
- case SIL_KILL:
- err |= __get_user(to->si_pid, &from->si_pid);
- err |= __get_user(to->si_uid, &from->si_uid);
- break;
- case SIL_CHLD:
- err |= __get_user(to->si_pid, &from->si_pid);
- err |= __get_user(to->si_uid, &from->si_uid);
- err |= __get_user(to->si_utime, &from->si_utime);
- err |= __get_user(to->si_stime, &from->si_stime);
- err |= __get_user(to->si_status, &from->si_status);
- break;
- case SIL_FAULT:
- err |= __get_user(tmp, &from->si_addr);
- to->si_addr = (void __force __user *)
- (u64) (tmp & PSW32_ADDR_INSN);
- break;
- case SIL_POLL:
- err |= __get_user(to->si_band, &from->si_band);
- err |= __get_user(to->si_fd, &from->si_fd);
- break;
- case SIL_TIMER:
- err |= __get_user(to->si_tid, &from->si_tid);
- err |= __get_user(to->si_overrun, &from->si_overrun);
- err |= __get_user(to->si_int, &from->si_int);
- break;
- default:
- break;
- }
- }
- return err ? -EFAULT : 0;
-}
-
/* Store registers needed to create the signal frame */
static void store_sigregs(void)
{
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 58b9e127b615..80e974adb9e8 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -1392,7 +1392,7 @@ int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view,
else
except_str = "-";
caller = (unsigned long) entry->caller;
- rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %p ",
+ rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %pK ",
area, sec, usec, level, except_str,
entry->id.fields.cpuid, (void *)caller);
return rc;
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 3be829721cf9..b2c68fbf2634 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Disassemble s390 instructions.
*
@@ -396,9 +397,14 @@ struct s390_insn *find_insn(unsigned char *code)
unsigned char opfrag;
int i;
+ /* Search the opcode offset table to find an entry which
+ * matches the beginning of the opcode. If there is no match
+ * the last entry will be used, which is the default entry for
+ * unknown instructions as well as 1-byte opcode instructions.
+ */
for (i = 0; i < ARRAY_SIZE(opcode_offset); i++) {
entry = &opcode_offset[i];
- if (entry->opcode == code[0] || entry->opcode == 0)
+ if (entry->opcode == code[0])
break;
}
@@ -543,7 +549,7 @@ void show_code(struct pt_regs *regs)
start += opsize;
pr_cont("%s", buffer);
ptr = buffer;
- ptr += sprintf(ptr, "\n\t ");
+ ptr += sprintf(ptr, "\n ");
hops++;
}
pr_cont("\n");
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 2aa545dca4d5..5b23c4f6e50c 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Stack dumping functions
*
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index a316cd6999ad..9e5f6cd8e4c2 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -180,18 +180,17 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
*/
ENTRY(__switch_to)
stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task
- lgr %r1,%r2
- aghi %r1,__TASK_thread # thread_struct of prev task
- lg %r5,__TASK_stack(%r3) # start of kernel stack of next
- stg %r15,__THREAD_ksp(%r1) # store kernel stack of prev
- lgr %r1,%r3
- aghi %r1,__TASK_thread # thread_struct of next task
+ lghi %r4,__TASK_stack
+ lghi %r1,__TASK_thread
+ lg %r5,0(%r4,%r3) # start of kernel stack of next
+ stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev
lgr %r15,%r5
aghi %r15,STACK_INIT # end of kernel stack of next
stg %r3,__LC_CURRENT # store task struct of next
stg %r15,__LC_KERNEL_STACK # store end of kernel stack
- lg %r15,__THREAD_ksp(%r1) # load kernel stack of next
- mvc __LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next
+ lg %r15,__THREAD_ksp(%r1,%r3) # load kernel stack of next
+ aghi %r3,__TASK_pid
+ mvc __LC_CURRENT_PID(4,%r0),0(%r3) # store pid of next
lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_LPP
bzr %r14
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 310e59e6eb4b..8ecb8726ac47 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* ipl/reipl/dump support for Linux on s390.
*
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 1a6521af1751..af3722c28fd9 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Kernel Probes (KProbes)
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
* Copyright IBM Corp. 2002, 2006
*
* s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com>
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
index bf9622f0e6b1..452502f9a0d9 100644
--- a/arch/s390/kernel/lgr.c
+++ b/arch/s390/kernel/lgr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Linux Guest Relocation (LGR) detection
*
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 7b87991416fd..b7abfad4fd7d 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Kernel module help for s390.
*
@@ -8,20 +9,6 @@
*
* based on i386 version
* Copyright (C) 2001 Rusty Russell.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/module.h>
#include <linux/elf.h>
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 6ff169253cae..c7a627620e5e 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Machine check handler
*
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 746d03423333..cc085e2d2ce9 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Performance event support for s390x - CPU-measurement Counter Facility
*
* Copyright IBM Corp. 2012, 2017
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#define KMSG_COMPONENT "cpum_cf"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 227b38bd82c9..1c9ddd7aa5ec 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Performance event support for the System z CPU-measurement Sampling Facility
*
* Copyright IBM Corp. 2013
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#define KMSG_COMPONENT "cpum_sf"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 93a386f4a3b5..0d770e513abf 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Performance event support for s390x
*
* Copyright IBM Corp. 2012, 2013
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#define KMSG_COMPONENT "perf"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index f8603ebed669..54e2d634b849 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
#include <linux/perf_regs.h>
#include <linux/kernel.h>
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 26c0523c1488..cd3df5514552 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -1651,6 +1651,14 @@ static const struct user_regset s390_compat_regsets[] = {
.set = s390_gs_cb_set,
},
{
+ .core_note_type = NT_S390_GS_BC,
+ .n = sizeof(struct gs_cb) / sizeof(__u64),
+ .size = sizeof(__u64),
+ .align = sizeof(__u64),
+ .get = s390_gs_bc_get,
+ .set = s390_gs_bc_set,
+ },
+ {
.core_note_type = NT_S390_RI_CB,
.n = sizeof(struct runtime_instr_cb) / sizeof(__u64),
.size = sizeof(__u64),
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 090053cf279b..793da97f9a6e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* S390 version
* Copyright IBM Corp. 1999, 2012
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index cd4334e80b64..b8c1a85bcf2d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -55,6 +55,7 @@
#include <asm/sigp.h>
#include <asm/idle.h>
#include <asm/nmi.h>
+#include <asm/topology.h>
#include "entry.h"
enum {
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index e66687dc6144..460dcfba7d4e 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Stack trace management functions
*
diff --git a/arch/s390/kernel/sthyi.c b/arch/s390/kernel/sthyi.c
index 12981e197f01..80b862e9c53c 100644
--- a/arch/s390/kernel/sthyi.c
+++ b/arch/s390/kernel/sthyi.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* store hypervisor information instruction emulation functions.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Copyright IBM Corp. 2016
* Author(s): Janosch Frank <frankja@linux.vnet.ibm.com>
*/
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 308a7b63348b..f7fc63385553 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -370,10 +370,10 @@ SYSCALL(sys_recvmmsg,compat_sys_recvmmsg)
SYSCALL(sys_sendmmsg,compat_sys_sendmmsg)
SYSCALL(sys_socket,sys_socket)
SYSCALL(sys_socketpair,compat_sys_socketpair) /* 360 */
-SYSCALL(sys_bind,sys_bind)
-SYSCALL(sys_connect,sys_connect)
+SYSCALL(sys_bind,compat_sys_bind)
+SYSCALL(sys_connect,compat_sys_connect)
SYSCALL(sys_listen,sys_listen)
-SYSCALL(sys_accept4,sys_accept4)
+SYSCALL(sys_accept4,compat_sys_accept4)
SYSCALL(sys_getsockopt,compat_sys_getsockopt) /* 365 */
SYSCALL(sys_setsockopt,compat_sys_setsockopt)
SYSCALL(sys_getsockname,compat_sys_getsockname)
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index be6198193ec2..cf561160ea88 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Time of day based timer functions.
*
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index f9b393d4a078..4d5b65e527b5 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2007, 2011
* Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 39a218703c50..f3a1c7c6824e 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* vdso setup for s390
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <linux/init.h>
diff --git a/arch/s390/kernel/vdso32/clock_getres.S b/arch/s390/kernel/vdso32/clock_getres.S
index eca3f001f081..f61df5253c23 100644
--- a/arch/s390/kernel/vdso32/clock_getres.S
+++ b/arch/s390/kernel/vdso32/clock_getres.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of clock_getres() for 32 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
index a5769b83d90e..2d6ec3abe095 100644
--- a/arch/s390/kernel/vdso32/clock_gettime.S
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of clock_gettime() for 32 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
index 63b86dceb0bf..aa8bf13a2edb 100644
--- a/arch/s390/kernel/vdso32/gettimeofday.S
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of gettimeofday() for 32 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
index c8513deb8c66..faf5213b15df 100644
--- a/arch/s390/kernel/vdso64/clock_getres.S
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of clock_getres() for 64 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
index 5d7b56b49458..6046b3bfca46 100644
--- a/arch/s390/kernel/vdso64/clock_gettime.S
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of clock_gettime() for 64 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
index b02e62f3bc12..cc9dbc27da6f 100644
--- a/arch/s390/kernel/vdso64/gettimeofday.S
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Userland implementation of gettimeofday() for 64 bits processes in a
* s390 kernel for use in the vDSO
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
*/
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
diff --git a/arch/s390/kernel/vdso64/note.S b/arch/s390/kernel/vdso64/note.S
index 79a071e4357e..db19d0680a0a 100644
--- a/arch/s390/kernel/vdso64/note.S
+++ b/arch/s390/kernel/vdso64/note.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
* Here we can supply some information useful to userland.
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index dd7178fbb4f3..f24395a01918 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Virtual cpu timer based timer functions.
*
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 6048b1c6e580..05ee90a5ea08 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -1,10 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
# Makefile for kernel virtual machines on s390
#
# Copyright IBM Corp. 2008
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License (version 2 only)
-# as published by the Free Software Foundation.
KVM := ../../../virt/kvm
common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index d93a2c0474bf..89aa114a2cba 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* handling diagnose instructions
*
* Copyright IBM Corp. 2008, 2011
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
*/
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index bec42b852246..f4c51756c462 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* access guest memory
*
* Copyright IBM Corp. 2008, 2014
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
*/
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index bcbd86621d01..b5f3e82006d0 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* kvm guest debug support
*
* Copyright IBM Corp. 2014
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com>
*/
#include <linux/kvm_host.h>
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 8fe034beb623..9c7d70715862 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* in-kernel handling for sie intercepts
*
* Copyright IBM Corp. 2008, 2014
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
*/
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index fa557372d600..024ad8bcc516 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* handling kvm guest interrupts
*
* Copyright IBM Corp. 2008, 2015
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
*/
diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h
index d98e4159643d..484608c71dd0 100644
--- a/arch/s390/kvm/irq.h
+++ b/arch/s390/kvm/irq.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* s390 irqchip routines
*
* Copyright IBM Corp. 2014
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
*/
#ifndef __KVM_IRQ_H
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 98ad8b9e0360..1371dff2b90d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * hosting zSeries kernel virtual machines
+ * hosting IBM Z kernel virtual machines (s390x)
*
- * Copyright IBM Corp. 2008, 2009
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
+ * Copyright IBM Corp. 2008, 2017
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
@@ -424,6 +421,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_GS:
r = test_facility(133);
break;
+ case KVM_CAP_S390_BPB:
+ r = test_facility(82);
+ break;
default:
r = 0;
}
@@ -769,7 +769,7 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
/*
* Must be called with kvm->srcu held to avoid races on memslots, and with
- * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
+ * kvm->slots_lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
*/
static int kvm_s390_vm_start_migration(struct kvm *kvm)
{
@@ -795,11 +795,12 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
if (kvm->arch.use_cmma) {
/*
- * Get the last slot. They should be sorted by base_gfn, so the
- * last slot is also the one at the end of the address space.
- * We have verified above that at least one slot is present.
+ * Get the first slot. They are reverse sorted by base_gfn, so
+ * the first slot is also the one at the end of the address
+ * space. We have verified above that at least one slot is
+ * present.
*/
- ms = slots->memslots + slots->used_slots - 1;
+ ms = slots->memslots;
/* round up so we only use full longs */
ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG);
/* allocate enough bytes to store all the bits */
@@ -824,7 +825,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
}
/*
- * Must be called with kvm->lock to avoid races with ourselves and
+ * Must be called with kvm->slots_lock to avoid races with ourselves and
* kvm_s390_vm_start_migration.
*/
static int kvm_s390_vm_stop_migration(struct kvm *kvm)
@@ -839,6 +840,8 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm)
if (kvm->arch.use_cmma) {
kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION);
+ /* We have to wait for the essa emulation to finish */
+ synchronize_srcu(&kvm->srcu);
vfree(mgs->pgste_bitmap);
}
kfree(mgs);
@@ -848,14 +851,12 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm)
static int kvm_s390_vm_set_migration(struct kvm *kvm,
struct kvm_device_attr *attr)
{
- int idx, res = -ENXIO;
+ int res = -ENXIO;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->slots_lock);
switch (attr->attr) {
case KVM_S390_VM_MIGRATION_START:
- idx = srcu_read_lock(&kvm->srcu);
res = kvm_s390_vm_start_migration(kvm);
- srcu_read_unlock(&kvm->srcu, idx);
break;
case KVM_S390_VM_MIGRATION_STOP:
res = kvm_s390_vm_stop_migration(kvm);
@@ -863,7 +864,7 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm,
default:
break;
}
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->slots_lock);
return res;
}
@@ -1753,7 +1754,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EFAULT;
if (copy_from_user(&args, argp, sizeof(args)))
break;
+ mutex_lock(&kvm->slots_lock);
r = kvm_s390_get_cmma_bits(kvm, &args);
+ mutex_unlock(&kvm->slots_lock);
if (!r) {
r = copy_to_user(argp, &args, sizeof(args));
if (r)
@@ -1767,7 +1770,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EFAULT;
if (copy_from_user(&args, argp, sizeof(args)))
break;
+ mutex_lock(&kvm->slots_lock);
r = kvm_s390_set_cmma_bits(kvm, &args);
+ mutex_unlock(&kvm->slots_lock);
break;
}
default:
@@ -2200,6 +2205,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
kvm_s390_set_prefix(vcpu, 0);
if (test_kvm_facility(vcpu->kvm, 64))
vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+ if (test_kvm_facility(vcpu->kvm, 82))
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
if (test_kvm_facility(vcpu->kvm, 133))
vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
/* fprs can be synchronized via vrs, even if the guest has no vx. With
@@ -2341,6 +2348,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
current->thread.fpu.fpc = 0;
vcpu->arch.sie_block->gbea = 1;
vcpu->arch.sie_block->pp = 0;
+ vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
kvm_clear_async_pf_completion_queue(vcpu);
if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
@@ -3300,6 +3308,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
vcpu->arch.gs_enabled = 1;
}
+ if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+ test_kvm_facility(vcpu->kvm, 82)) {
+ vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+ vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+ }
save_access_regs(vcpu->arch.host_acrs);
restore_access_regs(vcpu->run->s.regs.acrs);
/* save host (userspace) fprs/vrs */
@@ -3346,6 +3359,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_run->s.regs.pft = vcpu->arch.pfault_token;
kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+ kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
save_access_regs(vcpu->run->s.regs.acrs);
restore_access_regs(vcpu->arch.host_acrs);
/* Save guest register state */
@@ -3372,7 +3386,6 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int rc;
- sigset_t sigsaved;
if (kvm_run->immediate_exit)
return -EINTR;
@@ -3382,8 +3395,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 0;
}
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_sigset_activate(vcpu);
if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
kvm_s390_vcpu_start(vcpu);
@@ -3417,8 +3429,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
disable_cpu_timer_accounting(vcpu);
store_regs(vcpu, kvm_run);
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
vcpu->stat.exit_userspace++;
return rc;
@@ -3811,6 +3822,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = -EINVAL;
break;
}
+ /* do not use irq_state.flags, it will break old QEMUs */
r = kvm_s390_set_irq_state(vcpu,
(void __user *) irq_state.buf,
irq_state.len);
@@ -3826,6 +3838,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = -EINVAL;
break;
}
+ /* do not use irq_state.flags, it will break old QEMUs */
r = kvm_s390_get_irq_state(vcpu,
(__u8 __user *) irq_state.buf,
irq_state.len);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 10d65dfbc306..5e46ba429bcb 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* definition for kvm on s390
*
* Copyright IBM Corp. 2008, 2009
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
* Christian Ehrhardt <ehrhardt@de.ibm.com>
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index c954ac49eee4..0714bfa56da0 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* handling privileged instructions
*
* Copyright IBM Corp. 2008, 2013
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
*/
@@ -235,8 +232,6 @@ static int try_handle_skey(struct kvm_vcpu *vcpu)
VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
return -EAGAIN;
}
- if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
- return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
return 0;
}
@@ -247,6 +242,9 @@ static int handle_iske(struct kvm_vcpu *vcpu)
int reg1, reg2;
int rc;
+ if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+ return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
rc = try_handle_skey(vcpu);
if (rc)
return rc != -EAGAIN ? rc : 0;
@@ -276,6 +274,9 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
int reg1, reg2;
int rc;
+ if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+ return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
rc = try_handle_skey(vcpu);
if (rc)
return rc != -EAGAIN ? rc : 0;
@@ -311,6 +312,9 @@ static int handle_sske(struct kvm_vcpu *vcpu)
int reg1, reg2;
int rc;
+ if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+ return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
rc = try_handle_skey(vcpu);
if (rc)
return rc != -EAGAIN ? rc : 0;
@@ -1002,7 +1006,7 @@ static inline int do_essa(struct kvm_vcpu *vcpu, const int orc)
cbrlo[entries] = gfn << PAGE_SHIFT;
}
- if (orc) {
+ if (orc && gfn < ms->bitmap_size) {
/* increment only if we are really flipping the bit to 1 */
if (!test_and_set_bit(gfn, ms->pgste_bitmap))
atomic64_inc(&ms->dirty_pages);
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 9d592ef4104b..c1f5cde2c878 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* handling interprocessor communication
*
* Copyright IBM Corp. 2008, 2013
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
* Christian Ehrhardt <ehrhardt@de.ibm.com>
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index a311938b63b3..751348348477 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* kvm nested virtualization support for s390x
*
* Copyright IBM Corp. 2016
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
* Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com>
*/
#include <linux/vmalloc.h>
@@ -226,6 +223,12 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
memcpy(scb_o->gcr, scb_s->gcr, 128);
scb_o->pp = scb_s->pp;
+ /* branch prediction */
+ if (test_kvm_facility(vcpu->kvm, 82)) {
+ scb_o->fpf &= ~FPF_BPBC;
+ scb_o->fpf |= scb_s->fpf & FPF_BPBC;
+ }
+
/* interrupt intercept */
switch (scb_s->icptcode) {
case ICPT_PROGI:
@@ -268,6 +271,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
scb_s->ecb3 = 0;
scb_s->ecd = 0;
scb_s->fac = 0;
+ scb_s->fpf = 0;
rc = prepare_cpuflags(vcpu, vsie_page);
if (rc)
@@ -327,6 +331,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
prefix_unmapped(vsie_page);
scb_s->ecb |= scb_o->ecb & ECB_TE;
}
+ /* branch prediction */
+ if (test_kvm_facility(vcpu->kvm, 82))
+ scb_s->fpf |= scb_o->fpf & FPF_BPBC;
/* SIMD */
if (test_kvm_facility(vcpu->kvm, 129)) {
scb_s->eca |= scb_o->eca & ECA_VX;
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index cae5a1e16cbd..c4f8039a35e8 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -89,11 +89,11 @@ EXPORT_SYMBOL(enable_sacf_uaccess);
void disable_sacf_uaccess(mm_segment_t old_fs)
{
+ current->thread.mm_segment = old_fs;
if (old_fs == USER_DS && test_facility(27)) {
__ctl_load(S390_lowcore.user_asce, 1, 1);
clear_cpu_flag(CIF_ASCE_PRIMARY);
}
- current->thread.mm_segment = old_fs;
}
EXPORT_SYMBOL(disable_sacf_uaccess);
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 3d017171ff8f..6cf024eb2085 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Collaborative memory management interface.
*
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index b2c140193b0a..05d459b638f5 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* KVM guest address space mapping code
*
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 5bea139517a2..831bdcf407bb 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -1,24 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* flexible mmap layout support
*
* Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
* All Rights Reserved.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- *
* Started by Ingo Molnar <mingo@elte.hu>
*/
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 434a9564917b..cb364153c43c 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -83,8 +83,6 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
/* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */
VM_BUG_ON(mm->context.asce_limit < _REGION2_SIZE);
- if (end >= TASK_SIZE_MAX)
- return -ENOMEM;
rc = 0;
notify = 0;
while (mm->context.asce_limit < end) {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index ae677f814bc0..4f2b65d01a70 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2007, 2011
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile
index 90568c33ddb0..e0d5f245e42b 100644
--- a/arch/s390/net/Makefile
+++ b/arch/s390/net/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
#
# Arch-specific network modules
#
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index e81c16838b90..9557d8b516df 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -55,8 +55,7 @@ struct bpf_jit {
#define SEEN_LITERAL 8 /* code uses literals */
#define SEEN_FUNC 16 /* calls C functions */
#define SEEN_TAIL_CALL 32 /* code uses tail calls */
-#define SEEN_SKB_CHANGE 64 /* code changes skb data */
-#define SEEN_REG_AX 128 /* code uses constant blinding */
+#define SEEN_REG_AX 64 /* code uses constant blinding */
#define SEEN_STACK (SEEN_FUNC | SEEN_MEM | SEEN_SKB)
/*
@@ -448,12 +447,12 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
REG_15, 152);
}
- if (jit->seen & SEEN_SKB)
+ if (jit->seen & SEEN_SKB) {
emit_load_skb_data_hlen(jit);
- if (jit->seen & SEEN_SKB_CHANGE)
/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
STK_OFF_SKBP);
+ }
}
/*
@@ -983,8 +982,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
EMIT2(0x0d00, REG_14, REG_W1);
/* lgr %b0,%r2: load return value into %b0 */
EMIT4(0xb9040000, BPF_REG_0, REG_2);
- if (bpf_helper_changes_pkt_data((void *)func)) {
- jit->seen |= SEEN_SKB_CHANGE;
+ if ((jit->seen & SEEN_SKB) &&
+ bpf_helper_changes_pkt_data((void *)func)) {
/* lg %b1,ST_OFF_SKBP(%r15) */
EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
REG_15, STK_OFF_SKBP);
diff --git a/arch/s390/numa/Makefile b/arch/s390/numa/Makefile
index f94ecaffa71b..66c2dff74895 100644
--- a/arch/s390/numa/Makefile
+++ b/arch/s390/numa/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
obj-y += numa.o
obj-y += toptree.o
obj-$(CONFIG_NUMA_EMU) += mode_emu.o
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 805d8b29193a..22d0871291ee 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
#
# Makefile for the s390 PCI subsystem.
#
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 0fe649c0d542..4902fed221c0 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2012
*
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index c2f786f0ea06..b482e95b6249 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2012,2015
*
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 0d300ee00f4e..2d15d84c20ed 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2012
*
@@ -180,6 +181,9 @@ out_unlock:
static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
size_t size, int flags)
{
+ unsigned long irqflags;
+ int ret;
+
/*
* With zdev->tlb_refresh == 0, rpcit is not required to establish new
* translations when previously invalid translation-table entries are
@@ -195,8 +199,22 @@ static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
return 0;
}
- return zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
- PAGE_ALIGN(size));
+ ret = zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
+ PAGE_ALIGN(size));
+ if (ret == -ENOMEM && !s390_iommu_strict) {
+ /* enable the hypervisor to free some resources */
+ if (zpci_refresh_global(zdev))
+ goto out;
+
+ spin_lock_irqsave(&zdev->iommu_bitmap_lock, irqflags);
+ bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap,
+ zdev->lazy_bitmap, zdev->iommu_pages);
+ bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages);
+ spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, irqflags);
+ ret = 0;
+ }
+out:
+ return ret;
}
static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 81b840bc6e4e..f069929e8211 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* s390 specific pci instructions
*
@@ -88,6 +89,9 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
if (cc)
zpci_err_insn(cc, status, addr, range);
+ if (cc == 1 && (status == 4 || status == 16))
+ return -ENOMEM;
+
return (cc) ? -EIO : 0;
}
diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c
index 01d4c5a4bfe9..357d42681cef 100644
--- a/arch/s390/tools/gen_opcode_table.c
+++ b/arch/s390/tools/gen_opcode_table.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Generate opcode table initializers for the in-kernel disassembler.
*
diff --git a/arch/score/include/asm/thread_info.h b/arch/score/include/asm/thread_info.h
index ad51b56e51bd..bc4c7c90550f 100644
--- a/arch/score/include/asm/thread_info.h
+++ b/arch/score/include/asm/thread_info.h
@@ -58,9 +58,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* How to get the thread information struct from C. */
register struct thread_info *__current_thread_info __asm__("r28");
#define current_thread_info() __current_thread_info
diff --git a/arch/score/include/uapi/asm/Kbuild b/arch/score/include/uapi/asm/Kbuild
index 162fbdbb5fd5..b04fd1632051 100644
--- a/arch/score/include/uapi/asm/Kbuild
+++ b/arch/score/include/uapi/asm/Kbuild
@@ -1,5 +1,6 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += poll.h
generic-y += siginfo.h
diff --git a/arch/sh/boards/mach-se/770x/setup.c b/arch/sh/boards/mach-se/770x/setup.c
index 77c35350ee77..412326d59e6f 100644
--- a/arch/sh/boards/mach-se/770x/setup.c
+++ b/arch/sh/boards/mach-se/770x/setup.c
@@ -9,6 +9,7 @@
*/
#include <linux/init.h>
#include <linux/platform_device.h>
+#include <linux/sh_eth.h>
#include <mach-se/mach/se.h>
#include <mach-se/mach/mrshpc.h>
#include <asm/machvec.h>
@@ -115,13 +116,23 @@ static struct platform_device heartbeat_device = {
#if defined(CONFIG_CPU_SUBTYPE_SH7710) ||\
defined(CONFIG_CPU_SUBTYPE_SH7712)
/* SH771X Ethernet driver */
+static struct sh_eth_plat_data sh_eth_plat = {
+ .phy = PHY_ID,
+ .phy_interface = PHY_INTERFACE_MODE_MII,
+};
+
static struct resource sh_eth0_resources[] = {
[0] = {
.start = SH_ETH0_BASE,
- .end = SH_ETH0_BASE + 0x1B8,
+ .end = SH_ETH0_BASE + 0x1B8 - 1,
.flags = IORESOURCE_MEM,
},
[1] = {
+ .start = SH_TSU_BASE,
+ .end = SH_TSU_BASE + 0x200 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [2] = {
.start = SH_ETH0_IRQ,
.end = SH_ETH0_IRQ,
.flags = IORESOURCE_IRQ,
@@ -132,7 +143,7 @@ static struct platform_device sh_eth0_device = {
.name = "sh771x-ether",
.id = 0,
.dev = {
- .platform_data = PHY_ID,
+ .platform_data = &sh_eth_plat,
},
.num_resources = ARRAY_SIZE(sh_eth0_resources),
.resource = sh_eth0_resources,
@@ -141,10 +152,15 @@ static struct platform_device sh_eth0_device = {
static struct resource sh_eth1_resources[] = {
[0] = {
.start = SH_ETH1_BASE,
- .end = SH_ETH1_BASE + 0x1B8,
+ .end = SH_ETH1_BASE + 0x1B8 - 1,
.flags = IORESOURCE_MEM,
},
[1] = {
+ .start = SH_TSU_BASE,
+ .end = SH_TSU_BASE + 0x200 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [2] = {
.start = SH_ETH1_IRQ,
.end = SH_ETH1_IRQ,
.flags = IORESOURCE_IRQ,
@@ -155,7 +171,7 @@ static struct platform_device sh_eth1_device = {
.name = "sh771x-ether",
.id = 1,
.dev = {
- .platform_data = PHY_ID,
+ .platform_data = &sh_eth_plat,
},
.num_resources = ARRAY_SIZE(sh_eth1_resources),
.resource = sh_eth1_resources,
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index becb798f1b04..cf5c792bf70b 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -63,9 +63,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the current stack pointer from C */
register unsigned long current_stack_pointer asm("r15") __used;
diff --git a/arch/sh/include/mach-se/mach/se.h b/arch/sh/include/mach-se/mach/se.h
index 4246ef9b07a3..aa83fe1ff0b1 100644
--- a/arch/sh/include/mach-se/mach/se.h
+++ b/arch/sh/include/mach-se/mach/se.h
@@ -100,6 +100,7 @@
/* Base address */
#define SH_ETH0_BASE 0xA7000000
#define SH_ETH1_BASE 0xA7000400
+#define SH_TSU_BASE 0xA7000800
/* PHY ID */
#if defined(CONFIG_CPU_SUBTYPE_SH7710)
# define PHY_ID 0x00
diff --git a/arch/sh/include/uapi/asm/Kbuild b/arch/sh/include/uapi/asm/Kbuild
index e28531333efa..ba4d39cb321d 100644
--- a/arch/sh/include/uapi/asm/Kbuild
+++ b/arch/sh/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 57cff00cad17..b3770bb26211 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -609,7 +609,8 @@ asmlinkage void do_divide_error(unsigned long r4)
break;
}
- force_sig_info(SIGFPE, &info, current);
+ info.si_signo = SIGFPE;
+ force_sig_info(info.si_signo, &info, current);
}
#endif
diff --git a/arch/sparc/crypto/Makefile b/arch/sparc/crypto/Makefile
index 818d3aa5172e..d257186c27d1 100644
--- a/arch/sparc/crypto/Makefile
+++ b/arch/sparc/crypto/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_CRYPTO_MD5_SPARC64) += md5-sparc64.o
obj-$(CONFIG_CRYPTO_AES_SPARC64) += aes-sparc64.o
obj-$(CONFIG_CRYPTO_DES_SPARC64) += des-sparc64.o
-obj-$(CONFIG_CRYPTO_DES_SPARC64) += camellia-sparc64.o
+obj-$(CONFIG_CRYPTO_CAMELLIA_SPARC64) += camellia-sparc64.o
obj-$(CONFIG_CRYPTO_CRC32C_SPARC64) += crc32c-sparc64.o
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index fa38c78de0f0..615283e16f22 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -149,65 +149,6 @@ typedef u32 compat_old_sigset_t;
typedef u32 compat_sigset_word;
-typedef union compat_sigval {
- compat_int_t sival_int;
- compat_uptr_t sival_ptr;
-} compat_sigval_t;
-
-#define SI_PAD_SIZE32 (128/sizeof(int) - 3)
-
-typedef struct compat_siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[SI_PAD_SIZE32];
-
- /* kill() */
- struct {
- compat_pid_t _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- compat_sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- compat_pid_t _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- compat_pid_t _pid; /* which child */
- unsigned int _uid; /* sender's uid */
- int _status; /* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */
- struct {
- u32 _addr; /* faulting insn/memory ref. */
- int _trapno;
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
- } _sifields;
-} compat_siginfo_t;
-
#define COMPAT_OFF_T_MAX 0x7fffffff
/*
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 5a9e96be1665..9937c5ff94a9 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -715,7 +715,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
return pte_pfn(pte);
}
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline unsigned long pmd_write(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index febaaeb1a0fe..548b366165dd 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -63,9 +63,6 @@ struct thread_info {
.preempt_count = INIT_PREEMPT_COUNT, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
register struct thread_info *current_thread_info_reg asm("g6");
#define current_thread_info() (current_thread_info_reg)
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index caf915321ba9..f7e7b0baec9f 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -120,9 +120,6 @@ struct thread_info {
.preempt_count = INIT_PREEMPT_COUNT, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
register struct thread_info *current_thread_info_reg asm("g6");
#define current_thread_info() (current_thread_info_reg)
diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild
index 2178c78c7c1a..4680ba246b55 100644
--- a/arch/sparc/include/uapi/asm/Kbuild
+++ b/arch/sparc/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += types.h
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 54a6159b9cd8..44d379db3f64 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -70,75 +70,6 @@ struct rt_signal_frame32 {
/* __siginfo_rwin_t * */u32 rwin_save;
} __attribute__((aligned(8)));
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
- int err;
-
- if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
- return -EFAULT;
-
- /* If you change siginfo_t structure, please be sure
- this code is fixed accordingly.
- It should never copy any pad contained in the structure
- to avoid security leaks, but must copy the generic
- 3 ints plus the relevant union member.
- This routine must convert siginfo from 64bit to 32bit as well
- at the same time. */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user(from->si_code, &to->si_code);
- if (from->si_code < 0)
- err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
- else {
- switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_TIMER:
- err |= __put_user(from->si_tid, &to->si_tid);
- err |= __put_user(from->si_overrun, &to->si_overrun);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- case SIL_CHLD:
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- err |= __put_user(from->si_status, &to->si_status);
- default:
- case SIL_KILL:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- case SIL_FAULT:
- err |= __put_user(from->si_trapno, &to->si_trapno);
- err |= __put_user((unsigned long)from->si_addr, &to->si_addr);
- break;
- case SIL_POLL:
- err |= __put_user(from->si_band, &to->si_band);
- err |= __put_user(from->si_fd, &to->si_fd);
- break;
- case SIL_RT:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- }
- }
- return err;
-}
-
-/* CAUTION: This is just a very minimalist implementation for the
- * sake of compat_sys_rt_sigqueueinfo()
- */
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
- if (!access_ok(VERIFY_WRITE, from, sizeof(compat_siginfo_t)))
- return -EFAULT;
-
- if (copy_from_user(to, from, 3*sizeof(int)) ||
- copy_from_user(to->_sifields._pad, from->_sifields._pad,
- SI_PAD_SIZE))
- return -EFAULT;
-
- return 0;
-}
-
/* Checks if the fp is valid. We always build signal frames which are
* 16-byte aligned, therefore we can always enforce that the restore
* frame has that property as well.
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 0f0f76b4f6cd..063556fe2cb1 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -19,7 +19,7 @@ lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
lib-$(CONFIG_SPARC64) += multi3.o
lib-$(CONFIG_SPARC64) += fls.o
lib-$(CONFIG_SPARC64) += fls64.o
-obj-$(CONFIG_SPARC64) += NG4fls.o
+lib-$(CONFIG_SPARC64) += NG4fls.o
lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o
diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S
index e5547b22cd18..0ddbbb031822 100644
--- a/arch/sparc/lib/hweight.S
+++ b/arch/sparc/lib/hweight.S
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(__arch_hweight32)
.previous
ENTRY(__arch_hweight64)
- sethi %hi(__sw_hweight16), %g1
- jmpl %g1 + %lo(__sw_hweight16), %g0
+ sethi %hi(__sw_hweight64), %g1
+ jmpl %g1 + %lo(__sw_hweight64), %g0
nop
ENDPROC(__arch_hweight64)
EXPORT_SYMBOL(__arch_hweight64)
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index be3136f142a9..a8103a84b4ac 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -113,7 +113,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
if (!printk_ratelimit())
return;
- printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+ printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
tsk->comm, task_pid_nr(tsk), address,
(void *)regs->pc, (void *)regs->u_regs[UREG_I7],
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 815c03d7a765..41363f46797b 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -154,7 +154,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
if (!printk_ratelimit())
return;
- printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+ printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
tsk->comm, task_pid_nr(tsk), address,
(void *)regs->tpc, (void *)regs->u_regs[UREG_I7],
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 5765e7e711f7..ff5f9cb3039a 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1245,14 +1245,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
u8 *func = ((u8 *)__bpf_call_base) + imm;
ctx->saw_call = true;
+ if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
+ emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx);
emit_call((u32 *)func, ctx);
emit_nop(ctx);
emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
- if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind)
- load_skb_regs(ctx, bpf2sparc[BPF_REG_6]);
+ if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
+ load_skb_regs(ctx, L7);
break;
}
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index 62a7b83025dd..769ff6ac0bf5 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -110,68 +110,6 @@ struct compat_flock64 {
typedef u32 compat_sigset_word;
-typedef union compat_sigval {
- compat_int_t sival_int;
- compat_uptr_t sival_ptr;
-} compat_sigval_t;
-
-#define COMPAT_SI_PAD_SIZE (128/sizeof(int) - 3)
-
-typedef struct compat_siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[COMPAT_SI_PAD_SIZE];
-
- /* kill() */
- struct {
- unsigned int _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- compat_sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- int _overrun_incr; /* amount to add to overrun */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- unsigned int _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- unsigned int _pid; /* which child */
- unsigned int _uid; /* sender's uid */
- int _status; /* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- unsigned int _addr; /* faulting insn/memory ref. */
-#ifdef __ARCH_SI_TRAPNO
- int _trapno; /* TRAP # which caused the signal */
-#endif
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
- } _sifields;
-} compat_siginfo_t;
-
#define COMPAT_OFF_T_MAX 0x7fffffff
struct compat_ipc64_perm {
diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h
index 2a26cc4fefc2..adfa21b18488 100644
--- a/arch/tile/include/asm/pgtable.h
+++ b/arch/tile/include/asm/pgtable.h
@@ -475,7 +475,6 @@ static inline void pmd_clear(pmd_t *pmdp)
#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd)))
#define pmd_huge_page(pmd) pte_huge(pmd_pte(pmd))
#define pmd_mkhuge(pmd) pte_pmd(pte_mkhuge(pmd_pte(pmd)))
-#define __HAVE_ARCH_PMD_WRITE
#define pfn_pmd(pfn, pgprot) pte_pmd(pfn_pte((pfn), (pgprot)))
#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd))
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index b7659b8f1117..2adcacd85749 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -59,9 +59,6 @@ struct thread_info {
.align_ctl = 0, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
#endif /* !__ASSEMBLY__ */
#if PAGE_SIZE < 8192
diff --git a/arch/tile/include/uapi/asm/Kbuild b/arch/tile/include/uapi/asm/Kbuild
index 5711de0a1b5e..cc439612bcd5 100644
--- a/arch/tile/include/uapi/asm/Kbuild
+++ b/arch/tile/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/tile/include/uapi/asm/siginfo.h b/arch/tile/include/uapi/asm/siginfo.h
index f234d24fff55..a812fcbf4267 100644
--- a/arch/tile/include/uapi/asm/siginfo.h
+++ b/arch/tile/include/uapi/asm/siginfo.h
@@ -24,12 +24,4 @@
#include <asm-generic/siginfo.h>
-/*
- * Additional Tile-specific SIGILL si_codes
- */
-#define ILL_DBLFLT 9 /* double fault */
-#define ILL_HARDWALL 10 /* user networks hardwall violation */
-#undef NSIGILL
-#define NSIGILL 10
-
#endif /* _ASM_TILE_SIGINFO_H */
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index 971d87a1d8cf..a703bd0e0488 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -50,79 +50,6 @@ struct compat_rt_sigframe {
struct compat_ucontext uc;
};
-int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *from)
-{
- int err;
-
- if (!access_ok(VERIFY_WRITE, to, sizeof(struct compat_siginfo)))
- return -EFAULT;
-
- /* If you change siginfo_t structure, please make sure that
- this code is fixed accordingly.
- It should never copy any pad contained in the structure
- to avoid security leaks, but must copy the generic
- 3 ints plus the relevant union member. */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user(from->si_code, &to->si_code);
-
- if (from->si_code < 0) {
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_int, &to->si_int);
- } else {
- /*
- * First 32bits of unions are always present:
- * si_pid === si_band === si_tid === si_addr(LS half)
- */
- err |= __put_user(from->_sifields._pad[0],
- &to->_sifields._pad[0]);
- switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_FAULT:
- break;
- case SIL_CHLD:
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- err |= __put_user(from->si_status, &to->si_status);
- /* FALL THROUGH */
- default:
- case SIL_KILL:
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- case SIL_POLL:
- err |= __put_user(from->si_fd, &to->si_fd);
- break;
- case SIL_TIMER:
- err |= __put_user(from->si_overrun, &to->si_overrun);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- case SIL_RT:
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_int, &to->si_int);
- break;
- }
- }
- return err;
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
-{
- int err;
-
- if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
- return -EFAULT;
-
- err = __get_user(to->si_signo, &from->si_signo);
- err |= __get_user(to->si_errno, &from->si_errno);
- err |= __get_user(to->si_code, &from->si_code);
-
- err |= __get_user(to->si_pid, &from->si_pid);
- err |= __get_user(to->si_uid, &from->si_uid);
- err |= __get_user(to->si_int, &from->si_int);
-
- return err;
-}
-
/* The assembly shim for this function arranges to ignore the return value. */
long compat_sys_rt_sigreturn(void)
{
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index de3eae813e52..479d8033a801 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -163,11 +163,13 @@ static tilepro_bundle_bits rewrite_load_store_unaligned(
* actual bad address in an SPR, which it doesn't.
*/
if (align_ctl == 0) {
- siginfo_t info = {
- .si_signo = SIGBUS,
- .si_code = BUS_ADRALN,
- .si_addr = addr
- };
+ siginfo_t info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGBUS;
+ info.si_code = BUS_ADRALN;
+ info.si_addr = addr;
+
trace_unhandled_signal("unaligned trap", regs,
(unsigned long)addr, SIGBUS);
force_sig_info(info.si_signo, &info, current);
@@ -210,11 +212,13 @@ static tilepro_bundle_bits rewrite_load_store_unaligned(
}
if (err) {
- siginfo_t info = {
- .si_signo = SIGBUS,
- .si_code = BUS_ADRALN,
- .si_addr = addr
- };
+ siginfo_t info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGBUS;
+ info.si_code = BUS_ADRALN;
+ info.si_addr = addr;
+
trace_unhandled_signal("bad address for unaligned fixup", regs,
(unsigned long)addr, SIGBUS);
force_sig_info(info.si_signo, &info, current);
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 9b08c6055f15..83a7186198d7 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -256,12 +256,14 @@ static int do_bpt(struct pt_regs *regs)
void __kprobes do_trap(struct pt_regs *regs, int fault_num,
unsigned long reason)
{
- siginfo_t info = { 0 };
+ siginfo_t info;
int signo, code;
unsigned long address = 0;
tile_bundle_bits instr;
int is_kernel = !user_mode(regs);
+ clear_siginfo(&info);
+
/* Handle breakpoints, etc. */
if (is_kernel && fault_num == INT_ILL && do_bpt(regs))
return;
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index 8149c38f67b6..77a0b6b6a2a1 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -980,11 +980,13 @@ void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle,
}
if ((align_ctl == 0) || unexpected) {
- siginfo_t info = {
- .si_signo = SIGBUS,
- .si_code = BUS_ADRALN,
- .si_addr = (unsigned char __user *)0
- };
+ siginfo_t info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGBUS;
+ info.si_code = BUS_ADRALN;
+ info.si_addr = (unsigned char __user *)0;
+
if (unaligned_printk)
pr_info("Unalign bundle: unexp @%llx, %llx\n",
(unsigned long long)regs->pc,
@@ -1396,11 +1398,12 @@ void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle,
&frag, sizeof(frag));
if (status) {
/* Fail to copy JIT into user land. send SIGSEGV. */
- siginfo_t info = {
- .si_signo = SIGSEGV,
- .si_code = SEGV_MAPERR,
- .si_addr = (void __user *)&jit_code_area[idx]
- };
+ siginfo_t info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGSEGV;
+ info.si_code = SEGV_MAPERR;
+ info.si_addr = (void __user *)&jit_code_area[idx];
pr_warn("Unalign fixup: pid=%d %s jit_code_area=%llx\n",
current->pid, current->comm,
@@ -1511,11 +1514,12 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
* If so, we will trigger SIGBUS.
*/
if ((regs->sp & 0x7) || (regs->ex1) || (align_ctl < 0)) {
- siginfo_t info = {
- .si_signo = SIGBUS,
- .si_code = BUS_ADRALN,
- .si_addr = (unsigned char __user *)0
- };
+ siginfo_t info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGBUS;
+ info.si_code = BUS_ADRALN;
+ info.si_addr = (unsigned char __user *)0;
if (unaligned_printk)
pr_info("Unalign fixup: %d %llx @%llx\n",
@@ -1535,11 +1539,13 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
pc = (tilegx_bundle_bits __user *)(regs->pc);
if (get_user(bundle, pc) != 0) {
/* Probably never be here since pc is valid user address.*/
- siginfo_t info = {
- .si_signo = SIGSEGV,
- .si_code = SEGV_MAPERR,
- .si_addr = (void __user *)pc
- };
+ siginfo_t info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGSEGV;
+ info.si_code = SEGV_MAPERR;
+ info.si_addr = (void __user *)pc;
+
pr_err("Couldn't read instruction at %p trying to step\n", pc);
trace_unhandled_signal("segfault in unalign fixup", regs,
(unsigned long)info.si_addr, SIGSEGV);
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 50a32c33d729..73c57f614c9e 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,4 +1,5 @@
generic-y += barrier.h
+generic-y += bpf_perf_event.h
generic-y += bug.h
generic-y += clkdev.h
generic-y += current.h
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index b668e351fd6c..fca34b2177e2 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -15,9 +15,10 @@ extern void uml_setup_stubs(struct mm_struct *mm);
/*
* Needed since we do not use the asm-generic/mm_hooks.h:
*/
-static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
{
uml_setup_stubs(mm);
+ return 0;
}
extern void arch_exit_mmap(struct mm_struct *mm);
static inline void arch_unmap(struct mm_struct *mm,
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index 86942a492454..b58b746d3f2c 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -58,7 +58,10 @@ static inline void release_thread(struct task_struct *task)
{
}
-#define init_stack (init_thread_union.stack)
+static inline void mm_copy_segments(struct mm_struct *from_mm,
+ struct mm_struct *new_mm)
+{
+}
/*
* User space process size: 3GB (default).
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index 9300f7630d2a..4eecd960ee8c 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -6,6 +6,9 @@
#ifndef __UM_THREAD_INFO_H
#define __UM_THREAD_INFO_H
+#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER
+#define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE)
+
#ifndef __ASSEMBLY__
#include <asm/types.h>
@@ -37,10 +40,6 @@ struct thread_info {
.real_thread = NULL, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
-#define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE)
/* how to get the thread information struct from C */
static inline struct thread_info *current_thread_info(void)
{
@@ -53,8 +52,6 @@ static inline struct thread_info *current_thread_info(void)
return ti;
}
-#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER
-
#endif
#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
diff --git a/arch/um/include/asm/vmlinux.lds.h b/arch/um/include/asm/vmlinux.lds.h
new file mode 100644
index 000000000000..149494ae78ea
--- /dev/null
+++ b/arch/um/include/asm/vmlinux.lds.h
@@ -0,0 +1,2 @@
+#include <asm/thread_info.h>
+#include <asm-generic/vmlinux.lds.h>
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index d417e3899700..5568cf882371 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -1,5 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
#include <asm/page.h>
OUTPUT_FORMAT(ELF_FORMAT)
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 4e6fcb32620f..b2b02df9896e 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -150,7 +150,7 @@ static void show_segv_info(struct uml_pt_regs *regs)
if (!printk_ratelimit())
return;
- printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x",
+ printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
(void *)UPT_IP(regs), (void *)UPT_SP(regs),
@@ -306,7 +306,7 @@ void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
arch_examine_signal(sig, regs);
- memset(&clean_si, 0, sizeof(clean_si));
+ clear_siginfo(&clean_si);
clean_si.si_signo = si->si_signo;
clean_si.si_errno = si->si_errno;
clean_si.si_code = si->si_code;
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index f433690b9b37..a818ccef30ca 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -54,7 +54,7 @@ struct cpuinfo_um boot_cpu_data = {
union thread_union cpu0_irqstack
__attribute__((__section__(".data..init_irqstack"))) =
- { INIT_THREAD_INFO(init_task) };
+ { .thread_info = INIT_THREAD_INFO(init_task) };
/* Changed in setup_arch, which is called in early boot */
static char host_info[(__NEW_UTS_LEN + 1) * 5];
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index 3d6ed6ba5b78..36b07ec09742 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
#include <asm/page.h>
OUTPUT_FORMAT(ELF_FORMAT)
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index 59b06b48f27d..5c205a9cb5a6 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -81,9 +81,10 @@ do { \
} \
} while (0)
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
- struct mm_struct *mm)
+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,
diff --git a/arch/unicore32/include/asm/thread_info.h b/arch/unicore32/include/asm/thread_info.h
index e79ad6d5b5b2..5fb728f3b49a 100644
--- a/arch/unicore32/include/asm/thread_info.h
+++ b/arch/unicore32/include/asm/thread_info.h
@@ -87,9 +87,6 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/*
* how to get the thread information struct from C
*/
diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild
index 759a71411169..8611ef980554 100644
--- a/arch/unicore32/include/uapi/asm/Kbuild
+++ b/arch/unicore32/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
index 5f25b39f04d4..c4ac6043ebb0 100644
--- a/arch/unicore32/kernel/traps.c
+++ b/arch/unicore32/kernel/traps.c
@@ -298,7 +298,6 @@ void abort(void)
/* if that doesn't kill us, halt */
panic("Oops failed to kill thread");
}
-EXPORT_SYMBOL(abort);
void __init trap_init(void)
{
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8eed3f94bfc7..423e4b64e683 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -55,7 +55,6 @@ config X86
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV if X86_64
select ARCH_HAS_PMEM_API if X86_64
- # Causing hangs/crashes, see the commit that added this change for details.
select ARCH_HAS_REFCOUNT
select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64
select ARCH_HAS_SET_MEMORY
@@ -89,6 +88,7 @@ config X86
select GENERIC_CLOCKEVENTS_MIN_ADJUST
select GENERIC_CMOS_UPDATE
select GENERIC_CPU_AUTOPROBE
+ select GENERIC_CPU_VULNERABILITIES
select GENERIC_EARLY_IOREMAP
select GENERIC_FIND_FIRST_BIT
select GENERIC_IOMAP
@@ -429,6 +429,19 @@ config GOLDFISH
def_bool y
depends on X86_GOLDFISH
+config RETPOLINE
+ bool "Avoid speculative indirect branches in kernel"
+ default y
+ help
+ Compile kernel with the retpoline compiler options to guard against
+ kernel-to-user data leaks by avoiding speculative indirect
+ branches. Requires a compiler with -mindirect-branch=thunk-extern
+ support for full protection. The kernel may run slower.
+
+ Without compiler support, at least indirect branches in assembler
+ code are eliminated. Since this includes the syscall entry path,
+ it is not entirely pointless.
+
config INTEL_RDT
bool "Intel Resource Director Technology support"
default n
@@ -797,6 +810,15 @@ config PARAVIRT_TIME_ACCOUNTING
config PARAVIRT_CLOCK
bool
+config JAILHOUSE_GUEST
+ bool "Jailhouse non-root cell support"
+ depends on X86_64 && PCI
+ select X86_PM_TIMER
+ ---help---
+ This option allows to run Linux as guest in a Jailhouse non-root
+ cell. You can leave this option disabled if you only want to start
+ Jailhouse and run Linux afterwards in the root cell.
+
endif #HYPERVISOR_GUEST
config NO_BOOTMEM
@@ -926,7 +948,8 @@ config MAXSMP
config NR_CPUS
int "Maximum number of CPUs" if SMP && !MAXSMP
range 2 8 if SMP && X86_32 && !X86_BIGSMP
- range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK
+ range 2 64 if SMP && X86_32 && X86_BIGSMP
+ range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64
range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
default "1" if !SMP
default "8192" if MAXSMP
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 6293a8768a91..192e4d2f9efc 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -169,14 +169,6 @@ config IOMMU_DEBUG
options. See Documentation/x86/x86_64/boot-options.txt for more
details.
-config IOMMU_STRESS
- bool "Enable IOMMU stress-test mode"
- ---help---
- This option disables various optimizations in IOMMU related
- code to do real stress testing of the IOMMU code. This option
- will cause a performance drop and should only be enabled for
- testing.
-
config IOMMU_LEAK
bool "IOMMU leak tracing"
depends on IOMMU_DEBUG && DMA_API_DEBUG
@@ -400,6 +392,7 @@ config UNWINDER_FRAME_POINTER
config UNWINDER_GUESS
bool "Guess unwinder"
depends on EXPERT
+ depends on !STACKDEPOT
---help---
This option enables the "guess" unwinder for unwinding kernel stack
traces. It scans the stack and reports every kernel text address it
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 3e73bc255e4e..fad55160dcb9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -230,6 +230,14 @@ KBUILD_CFLAGS += -Wno-sign-compare
#
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
+# Avoid indirect branches in kernel to deal with Spectre
+ifdef CONFIG_RETPOLINE
+ RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+ ifneq ($(RETPOLINE_CFLAGS),)
+ KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
+ endif
+endif
+
archscripts: scripts_basic
$(Q)$(MAKE) $(build)=arch/x86/tools relocs
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 1e9c322e973a..f25e1530e064 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -80,6 +80,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o
ifdef CONFIG_X86_64
vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o
vmlinux-objs-y += $(obj)/mem_encrypt.o
+ vmlinux-objs-y += $(obj)/pgtable_64.o
endif
$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 20919b4f3133..fc313e29fe2c 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -305,10 +305,18 @@ ENTRY(startup_64)
leaq boot_stack_end(%rbx), %rsp
#ifdef CONFIG_X86_5LEVEL
- /* Check if 5-level paging has already enabled */
- movq %cr4, %rax
- testl $X86_CR4_LA57, %eax
- jnz lvl5
+ /*
+ * Check if we need to enable 5-level paging.
+ * RSI holds real mode data and need to be preserved across
+ * a function call.
+ */
+ pushq %rsi
+ call l5_paging_required
+ popq %rsi
+
+ /* If l5_paging_required() returned zero, we're done here. */
+ cmpq $0, %rax
+ je lvl5
/*
* At this point we are in long mode with 4-level paging enabled,
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index b50c42455e25..98761a1576ce 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -169,6 +169,16 @@ void __puthex(unsigned long value)
}
}
+static bool l5_supported(void)
+{
+ /* Check if leaf 7 is supported. */
+ if (native_cpuid_eax(0) < 7)
+ return 0;
+
+ /* Check if la57 is supported. */
+ return native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31));
+}
+
#if CONFIG_X86_NEED_RELOCS
static void handle_relocations(void *output, unsigned long output_len,
unsigned long virt_addr)
@@ -362,6 +372,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
console_init();
debug_putstr("early console in extract_kernel\n");
+ if (IS_ENABLED(CONFIG_X86_5LEVEL) && !l5_supported()) {
+ error("This linux kernel as configured requires 5-level paging\n"
+ "This CPU does not support the required 'cr4.la57' feature\n"
+ "Unable to boot - please use a kernel appropriate for your CPU\n");
+ }
+
free_mem_ptr = heap; /* Heap */
free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c
index d5364ca2e3f9..b5e5e02f8cde 100644
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -23,6 +23,9 @@
*/
#undef CONFIG_AMD_MEM_ENCRYPT
+/* No PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_PAGE_TABLE_ISOLATION
+
#include "misc.h"
/* These actually do the work of building the kernel identity maps. */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
new file mode 100644
index 000000000000..b4469a37e9a1
--- /dev/null
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -0,0 +1,28 @@
+#include <asm/processor.h>
+
+/*
+ * __force_order is used by special_insns.h asm code to force instruction
+ * serialization.
+ *
+ * It is not referenced from the code, but GCC < 5 with -fPIE would fail
+ * due to an undefined symbol. Define it to make these ancient GCCs work.
+ */
+unsigned long __force_order;
+
+int l5_paging_required(void)
+{
+ /* Check if leaf 7 is supported. */
+
+ if (native_cpuid_eax(0) < 7)
+ return 0;
+
+ /* Check if la57 is supported. */
+ if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+ return 0;
+
+ /* Check if 5-level paging has already been enabled. */
+ if (native_read_cr4() & X86_CR4_LA57)
+ return 0;
+
+ return 1;
+}
diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh
index 49f4970f693b..6a10d52a4145 100644
--- a/arch/x86/boot/genimage.sh
+++ b/arch/x86/boot/genimage.sh
@@ -44,9 +44,9 @@ FDINITRD=$6
# Make sure the files actually exist
verify "$FBZIMAGE"
-verify "$MTOOLSRC"
genbzdisk() {
+ verify "$MTOOLSRC"
mformat a:
syslinux $FIMAGE
echo "$KCMDLINE" | mcopy - a:syslinux.cfg
@@ -57,6 +57,7 @@ genbzdisk() {
}
genfdimage144() {
+ verify "$MTOOLSRC"
dd if=/dev/zero of=$FIMAGE bs=1024 count=1440 2> /dev/null
mformat v:
syslinux $FIMAGE
@@ -68,6 +69,7 @@ genfdimage144() {
}
genfdimage288() {
+ verify "$MTOOLSRC"
dd if=/dev/zero of=$FIMAGE bs=1024 count=2880 2> /dev/null
mformat w:
syslinux $FIMAGE
@@ -78,39 +80,43 @@ genfdimage288() {
mcopy $FBZIMAGE w:linux
}
-genisoimage() {
+geniso() {
tmp_dir=`dirname $FIMAGE`/isoimage
rm -rf $tmp_dir
mkdir $tmp_dir
- for i in lib lib64 share end ; do
+ for i in lib lib64 share ; do
for j in syslinux ISOLINUX ; do
if [ -f /usr/$i/$j/isolinux.bin ] ; then
isolinux=/usr/$i/$j/isolinux.bin
- cp $isolinux $tmp_dir
fi
done
for j in syslinux syslinux/modules/bios ; do
if [ -f /usr/$i/$j/ldlinux.c32 ]; then
ldlinux=/usr/$i/$j/ldlinux.c32
- cp $ldlinux $tmp_dir
fi
done
if [ -n "$isolinux" -a -n "$ldlinux" ] ; then
break
fi
- if [ $i = end -a -z "$isolinux" ] ; then
- echo 'Need an isolinux.bin file, please install syslinux/isolinux.'
- exit 1
- fi
done
+ if [ -z "$isolinux" ] ; then
+ echo 'Need an isolinux.bin file, please install syslinux/isolinux.'
+ exit 1
+ fi
+ if [ -z "$ldlinux" ] ; then
+ echo 'Need an ldlinux.c32 file, please install syslinux/isolinux.'
+ exit 1
+ fi
+ cp $isolinux $tmp_dir
+ cp $ldlinux $tmp_dir
cp $FBZIMAGE $tmp_dir/linux
echo "$KCMDLINE" > $tmp_dir/isolinux.cfg
if [ -f "$FDINITRD" ] ; then
cp "$FDINITRD" $tmp_dir/initrd.img
fi
- mkisofs -J -r -input-charset=utf-8 -quiet -o $FIMAGE -b isolinux.bin \
- -c boot.cat -no-emul-boot -boot-load-size 4 -boot-info-table \
- $tmp_dir
+ genisoimage -J -r -input-charset=utf-8 -quiet -o $FIMAGE \
+ -b isolinux.bin -c boot.cat -no-emul-boot -boot-load-size 4 \
+ -boot-info-table $tmp_dir
isohybrid $FIMAGE 2>/dev/null || true
rm -rf $tmp_dir
}
@@ -119,6 +125,6 @@ case $1 in
bzdisk) genbzdisk;;
fdimage144) genfdimage144;;
fdimage288) genfdimage288;;
- isoimage) genisoimage;;
+ isoimage) geniso;;
*) echo 'Unknown image format'; exit 1;
esac
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 16627fec80b2..3d09e3aca18d 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -32,6 +32,7 @@
#include <linux/linkage.h>
#include <asm/inst.h>
#include <asm/frame.h>
+#include <asm/nospec-branch.h>
/*
* The following macros are used to move an (un)aligned 16 byte value to/from
@@ -2884,7 +2885,7 @@ ENTRY(aesni_xts_crypt8)
pxor INC, STATE4
movdqu IV, 0x30(OUTP)
- call *%r11
+ CALL_NOSPEC %r11
movdqu 0x00(OUTP), INC
pxor INC, STATE1
@@ -2929,7 +2930,7 @@ ENTRY(aesni_xts_crypt8)
_aesni_gf128mul_x_ble()
movups IV, (IVP)
- call *%r11
+ CALL_NOSPEC %r11
movdqu 0x40(OUTP), INC
pxor INC, STATE1
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index f7c495e2863c..a14af6eb09cb 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -17,6 +17,7 @@
#include <linux/linkage.h>
#include <asm/frame.h>
+#include <asm/nospec-branch.h>
#define CAMELLIA_TABLE_BYTE_LEN 272
@@ -1227,7 +1228,7 @@ camellia_xts_crypt_16way:
vpxor 14 * 16(%rax), %xmm15, %xmm14;
vpxor 15 * 16(%rax), %xmm15, %xmm15;
- call *%r9;
+ CALL_NOSPEC %r9;
addq $(16 * 16), %rsp;
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index eee5b3982cfd..b66bbfa62f50 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -12,6 +12,7 @@
#include <linux/linkage.h>
#include <asm/frame.h>
+#include <asm/nospec-branch.h>
#define CAMELLIA_TABLE_BYTE_LEN 272
@@ -1343,7 +1344,7 @@ camellia_xts_crypt_32way:
vpxor 14 * 32(%rax), %ymm15, %ymm14;
vpxor 15 * 32(%rax), %ymm15, %ymm15;
- call *%r9;
+ CALL_NOSPEC %r9;
addq $(16 * 32), %rsp;
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 7a7de27c6f41..d9b734d0c8cc 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -45,6 +45,7 @@
#include <asm/inst.h>
#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
@@ -172,7 +173,7 @@ continue_block:
movzxw (bufp, %rax, 2), len
lea crc_array(%rip), bufp
lea (bufp, len, 1), bufp
- jmp *bufp
+ JMP_NOSPEC bufp
################################################################
## 2a) PROCESS FULL BLOCKS:
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index 399a29d067d6..cb91a64a99e7 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -59,13 +59,6 @@ static int encrypt(struct blkcipher_desc *desc,
salsa20_ivsetup(ctx, walk.iv);
- if (likely(walk.nbytes == nbytes))
- {
- salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
- walk.dst.virt.addr, nbytes);
- return blkcipher_walk_done(desc, &walk, 0);
- }
-
while (walk.nbytes >= 64) {
salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
walk.dst.virt.addr,
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 3fd8bc560fae..3f48f695d5e6 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -1,6 +1,11 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/jump_label.h>
#include <asm/unwind_hints.h>
+#include <asm/cpufeatures.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
/*
@@ -187,6 +192,148 @@ For 32-bit we have the following conventions - kernel is built with
#endif
.endm
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+/*
+ * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
+ * halves:
+ */
+#define PTI_USER_PGTABLE_BIT PAGE_SHIFT
+#define PTI_USER_PGTABLE_MASK (1 << PTI_USER_PGTABLE_BIT)
+#define PTI_USER_PCID_BIT X86_CR3_PTI_PCID_USER_BIT
+#define PTI_USER_PCID_MASK (1 << PTI_USER_PCID_BIT)
+#define PTI_USER_PGTABLE_AND_PCID_MASK (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
+
+.macro SET_NOFLUSH_BIT reg:req
+ bts $X86_CR3_PCID_NOFLUSH_BIT, \reg
+.endm
+
+.macro ADJUST_KERNEL_CR3 reg:req
+ ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
+ /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+ andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
+.endm
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ mov %cr3, \scratch_reg
+ ADJUST_KERNEL_CR3 \scratch_reg
+ mov \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+#define THIS_CPU_user_pcid_flush_mask \
+ PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ mov %cr3, \scratch_reg
+
+ ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+ /*
+ * Test if the ASID needs a flush.
+ */
+ movq \scratch_reg, \scratch_reg2
+ andq $(0x7FF), \scratch_reg /* mask ASID */
+ bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jnc .Lnoflush_\@
+
+ /* Flush needed, clear the bit */
+ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ movq \scratch_reg2, \scratch_reg
+ jmp .Lwrcr3_pcid_\@
+
+.Lnoflush_\@:
+ movq \scratch_reg2, \scratch_reg
+ SET_NOFLUSH_BIT \scratch_reg
+
+.Lwrcr3_pcid_\@:
+ /* Flip the ASID to the user version */
+ orq $(PTI_USER_PCID_MASK), \scratch_reg
+
+.Lwrcr3_\@:
+ /* Flip the PGD to the user version */
+ orq $(PTI_USER_PGTABLE_MASK), \scratch_reg
+ mov \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+ pushq %rax
+ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+ popq %rax
+.endm
+
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+ ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
+ movq %cr3, \scratch_reg
+ movq \scratch_reg, \save_reg
+ /*
+ * Test the user pagetable bit. If set, then the user page tables
+ * are active. If clear CR3 already has the kernel page table
+ * active.
+ */
+ bt $PTI_USER_PGTABLE_BIT, \scratch_reg
+ jnc .Ldone_\@
+
+ ADJUST_KERNEL_CR3 \scratch_reg
+ movq \scratch_reg, %cr3
+
+.Ldone_\@:
+.endm
+
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+ ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+ /*
+ * KERNEL pages can always resume with NOFLUSH as we do
+ * explicit flushes.
+ */
+ bt $PTI_USER_PGTABLE_BIT, \save_reg
+ jnc .Lnoflush_\@
+
+ /*
+ * Check if there's a pending flush for the user ASID we're
+ * about to set.
+ */
+ movq \save_reg, \scratch_reg
+ andq $(0x7FF), \scratch_reg
+ bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jnc .Lnoflush_\@
+
+ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jmp .Lwrcr3_\@
+
+.Lnoflush_\@:
+ SET_NOFLUSH_BIT \save_reg
+
+.Lwrcr3_\@:
+ /*
+ * The CR3 write could be avoided when not changing its value,
+ * but would require a CR3 read *and* a scratch register.
+ */
+ movq \save_reg, %cr3
+.Lend_\@:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+.endm
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+.endm
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+.endm
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+.endm
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+.endm
+
+#endif
+
#endif /* CONFIG_X86_64 */
/*
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 4838037f97f6..2a35b1e0fb90 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -44,6 +44,7 @@
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/frame.h>
+#include <asm/nospec-branch.h>
.section .entry.text, "ax"
@@ -243,6 +244,18 @@ ENTRY(__switch_to_asm)
movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
#endif
+#ifdef CONFIG_RETPOLINE
+ /*
+ * When switching from a shallower to a deeper call stack
+ * the RSB may either underflow or use entries populated
+ * with userspace addresses. On CPUs where those concerns
+ * exist, overwrite the RSB with entries which capture
+ * speculative execution to prevent attack.
+ */
+ /* Clobbers %ebx */
+ FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
/* restore callee-saved registers */
popl %esi
popl %edi
@@ -290,7 +303,7 @@ ENTRY(ret_from_fork)
/* kernel thread */
1: movl %edi, %eax
- call *%ebx
+ CALL_NOSPEC %ebx
/*
* A kernel thread is allowed to return here after successfully
* calling do_execve(). Exit to userspace to complete the execve()
@@ -919,7 +932,7 @@ common_exception:
movl %ecx, %es
TRACE_IRQS_OFF
movl %esp, %eax # pt_regs pointer
- call *%edi
+ CALL_NOSPEC %edi
jmp ret_from_exception
END(common_exception)
@@ -941,9 +954,10 @@ ENTRY(debug)
movl %esp, %eax # pt_regs pointer
/* Are we currently on the SYSENTER stack? */
- PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
- subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */
- cmpl $SIZEOF_SYSENTER_stack, %ecx
+ movl PER_CPU_VAR(cpu_entry_area), %ecx
+ addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+ subl %eax, %ecx /* ecx = (end of entry_stack) - esp */
+ cmpl $SIZEOF_entry_stack, %ecx
jb .Ldebug_from_sysenter_stack
TRACE_IRQS_OFF
@@ -984,9 +998,10 @@ ENTRY(nmi)
movl %esp, %eax # pt_regs pointer
/* Are we currently on the SYSENTER stack? */
- PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
- subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */
- cmpl $SIZEOF_SYSENTER_stack, %ecx
+ movl PER_CPU_VAR(cpu_entry_area), %ecx
+ addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+ subl %eax, %ecx /* ecx = (end of entry_stack) - esp */
+ cmpl $SIZEOF_entry_stack, %ecx
jb .Lnmi_from_sysenter_stack
/* Not on SYSENTER stack. */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f81d50d7ceac..a83570495162 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -23,7 +23,6 @@
#include <asm/segment.h>
#include <asm/cache.h>
#include <asm/errno.h>
-#include "calling.h"
#include <asm/asm-offsets.h>
#include <asm/msr.h>
#include <asm/unistd.h>
@@ -38,8 +37,11 @@
#include <asm/pgtable_types.h>
#include <asm/export.h>
#include <asm/frame.h>
+#include <asm/nospec-branch.h>
#include <linux/err.h>
+#include "calling.h"
+
.code64
.section .entry.text, "ax"
@@ -140,6 +142,67 @@ END(native_usergs_sysret64)
* with them due to bugs in both AMD and Intel CPUs.
*/
+ .pushsection .entry_trampoline, "ax"
+
+/*
+ * The code in here gets remapped into cpu_entry_area's trampoline. This means
+ * that the assembler and linker have the wrong idea as to where this code
+ * lives (and, in fact, it's mapped more than once, so it's not even at a
+ * fixed address). So we can't reference any symbols outside the entry
+ * trampoline and expect it to work.
+ *
+ * Instead, we carefully abuse %rip-relative addressing.
+ * _entry_trampoline(%rip) refers to the start of the remapped) entry
+ * trampoline. We can thus find cpu_entry_area with this macro:
+ */
+
+#define CPU_ENTRY_AREA \
+ _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
+
+/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
+#define RSP_SCRATCH CPU_ENTRY_AREA_entry_stack + \
+ SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA
+
+ENTRY(entry_SYSCALL_64_trampoline)
+ UNWIND_HINT_EMPTY
+ swapgs
+
+ /* Stash the user RSP. */
+ movq %rsp, RSP_SCRATCH
+
+ /* Note: using %rsp as a scratch reg. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+ /* Load the top of the task stack into RSP */
+ movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
+
+ /* Start building the simulated IRET frame. */
+ pushq $__USER_DS /* pt_regs->ss */
+ pushq RSP_SCRATCH /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+
+ /*
+ * x86 lacks a near absolute jump, and we can't jump to the real
+ * entry text with a relative jump. We could push the target
+ * address and then use retq, but this destroys the pipeline on
+ * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead,
+ * spill RDI and restore it in a second-stage trampoline.
+ */
+ pushq %rdi
+ movq $entry_SYSCALL_64_stage2, %rdi
+ JMP_NOSPEC %rdi
+END(entry_SYSCALL_64_trampoline)
+
+ .popsection
+
+ENTRY(entry_SYSCALL_64_stage2)
+ UNWIND_HINT_EMPTY
+ popq %rdi
+ jmp entry_SYSCALL_64_after_hwframe
+END(entry_SYSCALL_64_stage2)
+
ENTRY(entry_SYSCALL_64)
UNWIND_HINT_EMPTY
/*
@@ -149,6 +212,10 @@ ENTRY(entry_SYSCALL_64)
*/
swapgs
+ /*
+ * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+ * is not required to switch CR3.
+ */
movq %rsp, PER_CPU_VAR(rsp_scratch)
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
@@ -204,7 +271,12 @@ entry_SYSCALL_64_fastpath:
* It might end up jumping to the slow path. If it jumps, RAX
* and all argument registers are clobbered.
*/
+#ifdef CONFIG_RETPOLINE
+ movq sys_call_table(, %rax, 8), %rax
+ call __x86_indirect_thunk_rax
+#else
call *sys_call_table(, %rax, 8)
+#endif
.Lentry_SYSCALL_64_after_fastpath_call:
movq %rax, RAX(%rsp)
@@ -330,8 +402,25 @@ syscall_return_via_sysret:
popq %rsi /* skip rcx */
popq %rdx
popq %rsi
+
+ /*
+ * Now all regs are restored except RSP and RDI.
+ * Save old stack pointer and switch to trampoline stack.
+ */
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+ pushq RSP-RDI(%rdi) /* RSP */
+ pushq (%rdi) /* RDI */
+
+ /*
+ * We are on the trampoline stack. All regs except RDI are live.
+ * We can do future final exit work right here.
+ */
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
popq %rdi
- movq RSP-ORIG_RAX(%rsp), %rsp
+ popq %rsp
USERGS_SYSRET64
END(entry_SYSCALL_64)
@@ -359,7 +448,7 @@ ENTRY(stub_ptregs_64)
jmp entry_SYSCALL64_slow_path
1:
- jmp *%rax /* Called from C */
+ JMP_NOSPEC %rax /* Called from C */
END(stub_ptregs_64)
.macro ptregs_stub func
@@ -402,6 +491,18 @@ ENTRY(__switch_to_asm)
movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
#endif
+#ifdef CONFIG_RETPOLINE
+ /*
+ * When switching from a shallower to a deeper call stack
+ * the RSB may either underflow or use entries populated
+ * with userspace addresses. On CPUs where those concerns
+ * exist, overwrite the RSB with entries which capture
+ * speculative execution to prevent attack.
+ */
+ /* Clobbers %rbx */
+ FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
/* restore callee-saved registers */
popq %r15
popq %r14
@@ -438,7 +539,7 @@ ENTRY(ret_from_fork)
1:
/* kernel thread */
movq %r12, %rdi
- call *%rbx
+ CALL_NOSPEC %rbx
/*
* A kernel thread is allowed to return here after successfully
* calling do_execve(). Exit to userspace to complete the execve()
@@ -466,12 +567,13 @@ END(irq_entries_start)
.macro DEBUG_ENTRY_ASSERT_IRQS_OFF
#ifdef CONFIG_DEBUG_ENTRY
- pushfq
- testl $X86_EFLAGS_IF, (%rsp)
+ pushq %rax
+ SAVE_FLAGS(CLBR_RAX)
+ testl $X86_EFLAGS_IF, %eax
jz .Lokay_\@
ud2
.Lokay_\@:
- addq $8, %rsp
+ popq %rax
#endif
.endm
@@ -563,6 +665,13 @@ END(irq_entries_start)
/* 0(%rsp): ~(interrupt number) */
.macro interrupt func
cld
+
+ testb $3, CS-ORIG_RAX(%rsp)
+ jz 1f
+ SWAPGS
+ call switch_to_thread_stack
+1:
+
ALLOC_PT_GPREGS_ON_STACK
SAVE_C_REGS
SAVE_EXTRA_REGS
@@ -572,12 +681,8 @@ END(irq_entries_start)
jz 1f
/*
- * IRQ from user mode. Switch to kernel gsbase and inform context
- * tracking that we're in kernel mode.
- */
- SWAPGS
-
- /*
+ * IRQ from user mode.
+ *
* We need to tell lockdep that IRQs are off. We can't do this until
* we fix gsbase, and we should do it before enter_from_user_mode
* (which can take locks). Since TRACE_IRQS_OFF idempotent,
@@ -630,10 +735,43 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
ud2
1:
#endif
- SWAPGS
POP_EXTRA_REGS
- POP_C_REGS
- addq $8, %rsp /* skip regs->orig_ax */
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+
+ /*
+ * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+ * Save old stack pointer and switch to trampoline stack.
+ */
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+ /* Copy the IRET frame to the trampoline stack. */
+ pushq 6*8(%rdi) /* SS */
+ pushq 5*8(%rdi) /* RSP */
+ pushq 4*8(%rdi) /* EFLAGS */
+ pushq 3*8(%rdi) /* CS */
+ pushq 2*8(%rdi) /* RIP */
+
+ /* Push user RDI on the trampoline stack. */
+ pushq (%rdi)
+
+ /*
+ * We are on the trampoline stack. All regs except RDI are live.
+ * We can do future final exit work right here.
+ */
+
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
+ /* Restore RDI. */
+ popq %rdi
+ SWAPGS
INTERRUPT_RETURN
@@ -713,7 +851,9 @@ native_irq_return_ldt:
*/
pushq %rdi /* Stash user RDI */
- SWAPGS
+ SWAPGS /* to kernel GS */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */
+
movq PER_CPU_VAR(espfix_waddr), %rdi
movq %rax, (0*8)(%rdi) /* user RAX */
movq (1*8)(%rsp), %rax /* user RIP */
@@ -729,7 +869,6 @@ native_irq_return_ldt:
/* Now RAX == RSP. */
andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */
- popq %rdi /* Restore user RDI */
/*
* espfix_stack[31:16] == 0. The page tables are set up such that
@@ -740,7 +879,11 @@ native_irq_return_ldt:
* still points to an RO alias of the ESPFIX stack.
*/
orq PER_CPU_VAR(espfix_stack), %rax
- SWAPGS
+
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+ SWAPGS /* to user GS */
+ popq %rdi /* Restore user RDI */
+
movq %rax, %rsp
UNWIND_HINT_IRET_REGS offset=8
@@ -829,7 +972,35 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt
/*
* Exception entry points.
*/
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+
+/*
+ * Switch to the thread stack. This is called with the IRET frame and
+ * orig_ax on the stack. (That is, RDI..R12 are not on the stack and
+ * space has not been allocated for them.)
+ */
+ENTRY(switch_to_thread_stack)
+ UNWIND_HINT_FUNC
+
+ pushq %rdi
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
+
+ pushq 7*8(%rdi) /* regs->ss */
+ pushq 6*8(%rdi) /* regs->rsp */
+ pushq 5*8(%rdi) /* regs->eflags */
+ pushq 4*8(%rdi) /* regs->cs */
+ pushq 3*8(%rdi) /* regs->ip */
+ pushq 2*8(%rdi) /* regs->orig_ax */
+ pushq 8(%rdi) /* return address */
+ UNWIND_HINT_FUNC
+
+ movq (%rdi), %rdi
+ ret
+END(switch_to_thread_stack)
.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
ENTRY(\sym)
@@ -848,11 +1019,12 @@ ENTRY(\sym)
ALLOC_PT_GPREGS_ON_STACK
- .if \paranoid
- .if \paranoid == 1
+ .if \paranoid < 2
testb $3, CS(%rsp) /* If coming from userspace, switch stacks */
- jnz 1f
+ jnz .Lfrom_usermode_switch_stack_\@
.endif
+
+ .if \paranoid
call paranoid_entry
.else
call error_entry
@@ -894,20 +1066,15 @@ ENTRY(\sym)
jmp error_exit
.endif
- .if \paranoid == 1
+ .if \paranoid < 2
/*
- * Paranoid entry from userspace. Switch stacks and treat it
+ * Entry from userspace. Switch stacks and treat it
* as a normal entry. This means that paranoid handlers
* run in real process context if user_mode(regs).
*/
-1:
+.Lfrom_usermode_switch_stack_\@:
call error_entry
-
- movq %rsp, %rdi /* pt_regs pointer */
- call sync_regs
- movq %rax, %rsp /* switch stack */
-
movq %rsp, %rdi /* pt_regs pointer */
.if \has_error_code
@@ -1098,7 +1265,7 @@ idtentry async_page_fault do_async_page_fault has_error_code=1
#endif
#ifdef CONFIG_X86_MCE
-idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
+idtentry machine_check do_mce has_error_code=0 paranoid=1
#endif
/*
@@ -1119,7 +1286,11 @@ ENTRY(paranoid_entry)
js 1f /* negative -> in kernel */
SWAPGS
xorl %ebx, %ebx
-1: ret
+
+1:
+ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+
+ ret
END(paranoid_entry)
/*
@@ -1141,6 +1312,7 @@ ENTRY(paranoid_exit)
testl %ebx, %ebx /* swapgs needed? */
jnz .Lparanoid_exit_no_swapgs
TRACE_IRQS_IRETQ
+ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
SWAPGS_UNSAFE_STACK
jmp .Lparanoid_exit_restore
.Lparanoid_exit_no_swapgs:
@@ -1168,8 +1340,18 @@ ENTRY(error_entry)
* from user mode due to an IRET fault.
*/
SWAPGS
+ /* We have user CR3. Change to kernel CR3. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
.Lerror_entry_from_usermode_after_swapgs:
+ /* Put us onto the real thread stack. */
+ popq %r12 /* save return addr in %12 */
+ movq %rsp, %rdi /* arg0 = pt_regs pointer */
+ call sync_regs
+ movq %rax, %rsp /* switch stack */
+ ENCODE_FRAME_POINTER
+ pushq %r12
+
/*
* We need to tell lockdep that IRQs are off. We can't do this until
* we fix gsbase, and we should do it before enter_from_user_mode
@@ -1206,6 +1388,7 @@ ENTRY(error_entry)
* .Lgs_change's error handler with kernel gsbase.
*/
SWAPGS
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
jmp .Lerror_entry_done
.Lbstep_iret:
@@ -1215,10 +1398,11 @@ ENTRY(error_entry)
.Lerror_bad_iret:
/*
- * We came from an IRET to user mode, so we have user gsbase.
- * Switch to kernel gsbase:
+ * We came from an IRET to user mode, so we have user
+ * gsbase and CR3. Switch to kernel gsbase and CR3:
*/
SWAPGS
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
/*
* Pretend that the exception came from user mode: set up pt_regs
@@ -1250,6 +1434,10 @@ END(error_exit)
/*
* Runs on exception stack. Xen PV does not go through this path at all,
* so we can use real assembly here.
+ *
+ * Registers:
+ * %r14: Used to save/restore the CR3 of the interrupted context
+ * when PAGE_TABLE_ISOLATION is in use. Do not clobber.
*/
ENTRY(nmi)
UNWIND_HINT_IRET_REGS
@@ -1313,6 +1501,7 @@ ENTRY(nmi)
swapgs
cld
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
movq %rsp, %rdx
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
UNWIND_HINT_IRET_REGS base=%rdx offset=8
@@ -1565,6 +1754,8 @@ end_repeat_nmi:
movq $-1, %rsi
call do_nmi
+ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
+
testl %ebx, %ebx /* swapgs needed? */
jnz nmi_restore
nmi_swapgs:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 568e130d932c..98d5358e4041 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -48,7 +48,11 @@
*/
ENTRY(entry_SYSENTER_compat)
/* Interrupts are off on entry. */
- SWAPGS_UNSAFE_STACK
+ SWAPGS
+
+ /* We are about to clobber %rsp anyway, clobbering here is OK */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
/*
@@ -186,8 +190,13 @@ ENTRY(entry_SYSCALL_compat)
/* Interrupts are off on entry. */
swapgs
- /* Stash user ESP and switch to the kernel stack. */
+ /* Stash user ESP */
movl %esp, %r8d
+
+ /* Use %rsp as scratch reg. User ESP is stashed in r8 */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+ /* Switch to the kernel stack */
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
/* Construct struct pt_regs on stack */
@@ -256,10 +265,22 @@ sysret32_from_system_call:
* when the system call started, which is already known to user
* code. We zero R8-R10 to avoid info leaks.
*/
+ movq RSP-ORIG_RAX(%rsp), %rsp
+
+ /*
+ * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
+ * on the process stack which is not mapped to userspace and
+ * not readable after we SWITCH_TO_USER_CR3. Delay the CR3
+ * switch until after after the last reference to the process
+ * stack.
+ *
+ * %r8/%r9 are zeroed before the sysret, thus safe to clobber.
+ */
+ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
+
xorq %r8, %r8
xorq %r9, %r9
xorq %r10, %r10
- movq RSP-ORIG_RAX(%rsp), %rsp
swapgs
sysretl
END(entry_SYSCALL_compat)
@@ -306,8 +327,11 @@ ENTRY(entry_INT80_compat)
*/
movl %eax, %eax
- /* Construct struct pt_regs on stack (iret frame is already on stack) */
pushq %rax /* pt_regs->orig_ax */
+
+ /* switch to thread stack expects orig_ax to be pushed */
+ call switch_to_thread_stack
+
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
pushq %rdx /* pt_regs->dx */
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 11b13c4b43d5..f19856d95c60 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -324,5 +324,5 @@ notrace time_t __vdso_time(time_t *t)
*t = result;
return result;
}
-int time(time_t *t)
+time_t time(time_t *t)
__attribute__((weak, alias("__vdso_time")));
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index f279ba2643dc..577fa8adb785 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -37,6 +37,7 @@
#include <asm/unistd.h>
#include <asm/fixmap.h>
#include <asm/traps.h>
+#include <asm/paravirt.h>
#define CREATE_TRACE_POINTS
#include "vsyscall_trace.h"
@@ -138,6 +139,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
WARN_ON_ONCE(address != regs->ip);
+ /* This should be unreachable in NATIVE mode. */
+ if (WARN_ON(vsyscall_mode == NATIVE))
+ return false;
+
if (vsyscall_mode == NONE) {
warn_bad_vsyscall(KERN_INFO, regs,
"vsyscall attempted with vsyscall=none");
@@ -329,16 +334,47 @@ int in_gate_area_no_mm(unsigned long addr)
return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
}
+/*
+ * The VSYSCALL page is the only user-accessible page in the kernel address
+ * range. Normally, the kernel page tables can have _PAGE_USER clear, but
+ * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
+ * are enabled.
+ *
+ * Some day we may create a "minimal" vsyscall mode in which we emulate
+ * vsyscalls but leave the page not present. If so, we skip calling
+ * this.
+ */
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
+ set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+ p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+#if CONFIG_PGTABLE_LEVELS >= 5
+ p4d->p4d |= _PAGE_USER;
+#endif
+ pud = pud_offset(p4d, VSYSCALL_ADDR);
+ set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
+ pmd = pmd_offset(pud, VSYSCALL_ADDR);
+ set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
+}
+
void __init map_vsyscall(void)
{
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
- if (vsyscall_mode != NONE)
+ if (vsyscall_mode != NONE) {
__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
vsyscall_mode == NATIVE
? PAGE_KERNEL_VSYSCALL
: PAGE_KERNEL_VVAR);
+ set_vsyscall_pgtable_user_bits(swapper_pg_dir);
+ }
BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
(unsigned long)VSYSCALL_ADDR);
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index a6eee5ac4f58..2aefacf5c5b2 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -277,7 +277,7 @@ static int __init amd_power_pmu_init(void)
int ret;
if (!x86_match_cpu(cpu_match))
- return 0;
+ return -ENODEV;
if (!boot_cpu_has(X86_FEATURE_ACC_POWER))
return -ENODEV;
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 141e07b06216..24ffa1e88cf9 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -582,6 +582,24 @@ static __init int bts_init(void)
if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
return -ENODEV;
+ if (boot_cpu_has(X86_FEATURE_PTI)) {
+ /*
+ * BTS hardware writes through a virtual memory map we must
+ * either use the kernel physical map, or the user mapping of
+ * the AUX buffer.
+ *
+ * However, since this driver supports per-CPU and per-task inherit
+ * we cannot use the user mapping since it will not be availble
+ * if we're not running the owning process.
+ *
+ * With PTI we can't use the kernal map either, because its not
+ * there when we run userspace.
+ *
+ * For now, disable this driver when using PTI.
+ */
+ return -ENODEV;
+ }
+
bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
PERF_PMU_CAP_EXCLUSIVE;
bts_pmu.task_ctx_nr = perf_sw_context;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 09c26a4f139c..731153a4681e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3847,6 +3847,8 @@ static struct attribute *intel_pmu_attrs[] = {
__init int intel_pmu_init(void)
{
+ struct attribute **extra_attr = NULL;
+ struct attribute **to_free = NULL;
union cpuid10_edx edx;
union cpuid10_eax eax;
union cpuid10_ebx ebx;
@@ -3854,7 +3856,6 @@ __init int intel_pmu_init(void)
unsigned int unused;
struct extra_reg *er;
int version, i;
- struct attribute **extra_attr = NULL;
char *name;
if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
@@ -4294,6 +4295,7 @@ __init int intel_pmu_init(void)
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
extra_attr = merge_attr(extra_attr, skl_format_attr);
+ to_free = extra_attr;
x86_pmu.cpu_events = get_hsw_events_attrs();
intel_pmu_pebs_data_source_skl(
boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
@@ -4401,6 +4403,7 @@ __init int intel_pmu_init(void)
pr_cont("full-width counters, ");
}
+ kfree(to_free);
return 0;
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 3674a4b6f8bd..18c25ab28557 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -3,16 +3,19 @@
#include <linux/types.h>
#include <linux/slab.h>
+#include <asm/cpu_entry_area.h>
#include <asm/perf_event.h>
+#include <asm/tlbflush.h>
#include <asm/insn.h>
#include "../perf_event.h"
+/* Waste a full page so it can be mapped into the cpu_entry_area */
+DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
/* The size of a BTS record in bytes: */
#define BTS_RECORD_SIZE 24
-#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
#define PEBS_FIXUP_SIZE PAGE_SIZE
/*
@@ -279,17 +282,67 @@ void fini_debug_store_on_cpu(int cpu)
static DEFINE_PER_CPU(void *, insn_buffer);
-static int alloc_pebs_buffer(int cpu)
+static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ unsigned long start = (unsigned long)cea;
+ phys_addr_t pa;
+ size_t msz = 0;
+
+ pa = virt_to_phys(addr);
+
+ preempt_disable();
+ for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
+ cea_set_pte(cea, pa, prot);
+
+ /*
+ * This is a cross-CPU update of the cpu_entry_area, we must shoot down
+ * all TLB entries for it.
+ */
+ flush_tlb_kernel_range(start, start + size);
+ preempt_enable();
+}
+
+static void ds_clear_cea(void *cea, size_t size)
+{
+ unsigned long start = (unsigned long)cea;
+ size_t msz = 0;
+
+ preempt_disable();
+ for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
+ cea_set_pte(cea, 0, PAGE_NONE);
+
+ flush_tlb_kernel_range(start, start + size);
+ preempt_enable();
+}
+
+static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
+{
+ unsigned int order = get_order(size);
int node = cpu_to_node(cpu);
- int max;
- void *buffer, *ibuffer;
+ struct page *page;
+
+ page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+ return page ? page_address(page) : NULL;
+}
+
+static void dsfree_pages(const void *buffer, size_t size)
+{
+ if (buffer)
+ free_pages((unsigned long)buffer, get_order(size));
+}
+
+static int alloc_pebs_buffer(int cpu)
+{
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ size_t bsiz = x86_pmu.pebs_buffer_size;
+ int max, node = cpu_to_node(cpu);
+ void *buffer, *ibuffer, *cea;
if (!x86_pmu.pebs)
return 0;
- buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+ buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
if (unlikely(!buffer))
return -ENOMEM;
@@ -300,99 +353,94 @@ static int alloc_pebs_buffer(int cpu)
if (x86_pmu.intel_cap.pebs_format < 2) {
ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
if (!ibuffer) {
- kfree(buffer);
+ dsfree_pages(buffer, bsiz);
return -ENOMEM;
}
per_cpu(insn_buffer, cpu) = ibuffer;
}
-
- max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
-
- ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+ hwev->ds_pebs_vaddr = buffer;
+ /* Update the cpu entry area mapping */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+ ds->pebs_buffer_base = (unsigned long) cea;
+ ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL);
ds->pebs_index = ds->pebs_buffer_base;
- ds->pebs_absolute_maximum = ds->pebs_buffer_base +
- max * x86_pmu.pebs_record_size;
-
+ max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size);
+ ds->pebs_absolute_maximum = ds->pebs_buffer_base + max;
return 0;
}
static void release_pebs_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ void *cea;
- if (!ds || !x86_pmu.pebs)
+ if (!x86_pmu.pebs)
return;
kfree(per_cpu(insn_buffer, cpu));
per_cpu(insn_buffer, cpu) = NULL;
- kfree((void *)(unsigned long)ds->pebs_buffer_base);
- ds->pebs_buffer_base = 0;
+ /* Clear the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+ ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
+ dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
+ hwev->ds_pebs_vaddr = NULL;
}
static int alloc_bts_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
- int node = cpu_to_node(cpu);
- int max, thresh;
- void *buffer;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ void *buffer, *cea;
+ int max;
if (!x86_pmu.bts)
return 0;
- buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+ buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu);
if (unlikely(!buffer)) {
WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
return -ENOMEM;
}
-
- max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
- thresh = max / 16;
-
- ds->bts_buffer_base = (u64)(unsigned long)buffer;
+ hwev->ds_bts_vaddr = buffer;
+ /* Update the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+ ds->bts_buffer_base = (unsigned long) cea;
+ ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
ds->bts_index = ds->bts_buffer_base;
- ds->bts_absolute_maximum = ds->bts_buffer_base +
- max * BTS_RECORD_SIZE;
- ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
- thresh * BTS_RECORD_SIZE;
-
+ max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
+ ds->bts_absolute_maximum = ds->bts_buffer_base + max;
+ ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
return 0;
}
static void release_bts_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ void *cea;
- if (!ds || !x86_pmu.bts)
+ if (!x86_pmu.bts)
return;
- kfree((void *)(unsigned long)ds->bts_buffer_base);
- ds->bts_buffer_base = 0;
+ /* Clear the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+ ds_clear_cea(cea, BTS_BUFFER_SIZE);
+ dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE);
+ hwev->ds_bts_vaddr = NULL;
}
static int alloc_ds_buffer(int cpu)
{
- int node = cpu_to_node(cpu);
- struct debug_store *ds;
-
- ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
- if (unlikely(!ds))
- return -ENOMEM;
+ struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store;
+ memset(ds, 0, sizeof(*ds));
per_cpu(cpu_hw_events, cpu).ds = ds;
-
return 0;
}
static void release_ds_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
- if (!ds)
- return;
-
per_cpu(cpu_hw_events, cpu).ds = NULL;
- kfree(ds);
}
void release_ds_buffers(void)
@@ -402,16 +450,22 @@ void release_ds_buffers(void)
if (!x86_pmu.bts && !x86_pmu.pebs)
return;
- get_online_cpus();
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu)
+ release_ds_buffer(cpu);
+
+ for_each_possible_cpu(cpu) {
+ /*
+ * Again, ignore errors from offline CPUs, they will no longer
+ * observe cpu_hw_events.ds and not program the DS_AREA when
+ * they come up.
+ */
fini_debug_store_on_cpu(cpu);
+ }
for_each_possible_cpu(cpu) {
release_pebs_buffer(cpu);
release_bts_buffer(cpu);
- release_ds_buffer(cpu);
}
- put_online_cpus();
}
void reserve_ds_buffers(void)
@@ -431,8 +485,6 @@ void reserve_ds_buffers(void)
if (!x86_pmu.pebs)
pebs_err = 1;
- get_online_cpus();
-
for_each_possible_cpu(cpu) {
if (alloc_ds_buffer(cpu)) {
bts_err = 1;
@@ -469,11 +521,14 @@ void reserve_ds_buffers(void)
if (x86_pmu.pebs && !pebs_err)
x86_pmu.pebs_active = 1;
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu) {
+ /*
+ * Ignores wrmsr_on_cpu() errors for offline CPUs they
+ * will get this call through intel_pmu_cpu_starting().
+ */
init_debug_store_on_cpu(cpu);
+ }
}
-
- put_online_cpus();
}
/*
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 005908ee9333..a2efb490f743 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -755,14 +755,14 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsw_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init),
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 14efaa0e8684..18e2628e2d8f 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -10,7 +10,9 @@ enum perf_msr_id {
PERF_MSR_SMI = 4,
PERF_MSR_PTSC = 5,
PERF_MSR_IRPERF = 6,
-
+ PERF_MSR_THERM = 7,
+ PERF_MSR_THERM_SNAP = 8,
+ PERF_MSR_THERM_UNIT = 9,
PERF_MSR_EVENT_MAX,
};
@@ -29,6 +31,11 @@ static bool test_irperf(int idx)
return boot_cpu_has(X86_FEATURE_IRPERF);
}
+static bool test_therm_status(int idx)
+{
+ return boot_cpu_has(X86_FEATURE_DTHERM);
+}
+
static bool test_intel(int idx)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
@@ -95,22 +102,28 @@ struct perf_msr {
bool (*test)(int idx);
};
-PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00");
-PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01");
-PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02");
-PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03");
-PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04");
-PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05");
-PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06");
+PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00" );
+PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01" );
+PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02" );
+PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03" );
+PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04" );
+PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05" );
+PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin, evattr_therm, "event=0x07" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, evattr_therm_snap, "1" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, evattr_therm_unit, "C" );
static struct perf_msr msr[] = {
- [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, },
- [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, },
- [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, },
- [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, },
- [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, },
- [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, },
- [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, },
+ [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, },
+ [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, },
+ [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, },
+ [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, },
+ [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, },
+ [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, },
+ [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, },
+ [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &evattr_therm, test_therm_status, },
+ [PERF_MSR_THERM_SNAP] = { MSR_IA32_THERM_STATUS, &evattr_therm_snap, test_therm_status, },
+ [PERF_MSR_THERM_UNIT] = { MSR_IA32_THERM_STATUS, &evattr_therm_unit, test_therm_status, },
};
static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
@@ -161,9 +174,9 @@ static int msr_event_init(struct perf_event *event)
if (!msr[cfg].attr)
return -EINVAL;
- event->hw.idx = -1;
- event->hw.event_base = msr[cfg].msr;
- event->hw.config = cfg;
+ event->hw.idx = -1;
+ event->hw.event_base = msr[cfg].msr;
+ event->hw.config = cfg;
return 0;
}
@@ -184,7 +197,7 @@ static void msr_event_update(struct perf_event *event)
u64 prev, now;
s64 delta;
- /* Careful, an NMI might modify the previous event value. */
+ /* Careful, an NMI might modify the previous event value: */
again:
prev = local64_read(&event->hw.prev_count);
now = msr_read_counter(event);
@@ -193,17 +206,22 @@ again:
goto again;
delta = now - prev;
- if (unlikely(event->hw.event_base == MSR_SMI_COUNT))
+ if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
delta = sign_extend64(delta, 31);
-
- local64_add(delta, &event->count);
+ local64_add(delta, &event->count);
+ } else if (unlikely(event->hw.event_base == MSR_IA32_THERM_STATUS)) {
+ /* If valid, extract digital readout, otherwise set to -1: */
+ now = now & (1ULL << 31) ? (now >> 16) & 0x3f : -1;
+ local64_set(&event->count, now);
+ } else {
+ local64_add(delta, &event->count);
+ }
}
static void msr_event_start(struct perf_event *event, int flags)
{
- u64 now;
+ u64 now = msr_read_counter(event);
- now = msr_read_counter(event);
local64_set(&event->hw.prev_count, now);
}
@@ -250,9 +268,7 @@ static int __init msr_init(void)
for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) {
u64 val;
- /*
- * Virt sucks arse; you cannot tell if a R/O MSR is present :/
- */
+ /* Virt sucks; you cannot tell if a R/O MSR is present :/ */
if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
msr[i].attr = NULL;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f7aaadf9331f..8e4ea143ed96 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -14,6 +14,8 @@
#include <linux/perf_event.h>
+#include <asm/intel_ds.h>
+
/* To enable MSR tracing please use the generic trace points. */
/*
@@ -77,8 +79,6 @@ struct amd_nb {
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS 8
#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1)
/*
@@ -95,23 +95,6 @@ struct amd_nb {
PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)
-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
- u64 bts_buffer_base;
- u64 bts_index;
- u64 bts_absolute_maximum;
- u64 bts_interrupt_threshold;
- u64 pebs_buffer_base;
- u64 pebs_index;
- u64 pebs_absolute_maximum;
- u64 pebs_interrupt_threshold;
- u64 pebs_event_reset[MAX_PEBS_EVENTS];
-};
-
#define PEBS_REGS \
(PERF_REG_X86_AX | \
PERF_REG_X86_BX | \
@@ -216,6 +199,8 @@ struct cpu_hw_events {
* Intel DebugStore bits
*/
struct debug_store *ds;
+ void *ds_pebs_vaddr;
+ void *ds_bts_vaddr;
u64 pebs_enabled;
int n_pebs;
int n_large_pebs;
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 9cc9e1c1e2db..56c9ebac946f 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -137,7 +137,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
}
if (info->mm) {
+ /*
+ * AddressSpace argument must match the CR3 with PCID bits
+ * stripped out.
+ */
flush->address_space = virt_to_phys(info->mm->pgd);
+ flush->address_space &= CR3_ADDR_MASK;
flush->flags = 0;
} else {
flush->address_space = 0;
@@ -219,7 +224,12 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
}
if (info->mm) {
+ /*
+ * AddressSpace argument must match the CR3 with PCID bits
+ * stripped out.
+ */
flush->address_space = virt_to_phys(info->mm->pgd);
+ flush->address_space &= CR3_ADDR_MASK;
flush->flags = 0;
} else {
flush->address_space = 0;
@@ -278,8 +288,6 @@ void hyperv_setup_mmu_ops(void)
if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
return;
- setup_clear_cpu_cap(X86_FEATURE_PCID);
-
if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
pr_info("Using hypercall for remote TLB flush\n");
pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 8d0ec9df1cbe..44f5d79d5105 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -49,7 +49,7 @@ extern int acpi_fix_pin2_polarity;
extern int acpi_disable_cmcff;
extern u8 acpi_sci_flags;
-extern int acpi_sci_override_gsi;
+extern u32 acpi_sci_override_gsi;
void acpi_pic_sci_set_trigger(unsigned int, u16);
struct device;
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index dbfd0854651f..cf5961ca8677 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -140,7 +140,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
- ".popsection"
+ ".popsection\n"
#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
OLDINSTR_2(oldinstr, 1, 2) \
@@ -151,7 +151,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
- ".popsection"
+ ".popsection\n"
/*
* Alternative instructions for different CPU types or capabilities.
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a9e57f08bfa6..98722773391d 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -136,6 +136,7 @@ extern void disconnect_bsp_APIC(int virt_wire_setup);
extern void disable_local_APIC(void);
extern void lapic_shutdown(void);
extern void sync_Arb_IDs(void);
+extern void init_bsp_APIC(void);
extern void apic_intr_mode_init(void);
extern void setup_local_APIC(void);
extern void init_apic_mappings(void);
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index ff700d81e91e..4d111616524b 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -11,7 +11,34 @@
#include <asm/pgtable.h>
#include <asm/special_insns.h>
#include <asm/preempt.h>
+#include <asm/asm.h>
#ifndef CONFIG_X86_CMPXCHG64
extern void cmpxchg8b_emu(void);
#endif
+
+#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_X86_32
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void);
+#else
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void);
+INDIRECT_THUNK(8)
+INDIRECT_THUNK(9)
+INDIRECT_THUNK(10)
+INDIRECT_THUNK(11)
+INDIRECT_THUNK(12)
+INDIRECT_THUNK(13)
+INDIRECT_THUNK(14)
+INDIRECT_THUNK(15)
+#endif
+INDIRECT_THUNK(ax)
+INDIRECT_THUNK(bx)
+INDIRECT_THUNK(cx)
+INDIRECT_THUNK(dx)
+INDIRECT_THUNK(si)
+INDIRECT_THUNK(di)
+INDIRECT_THUNK(bp)
+asmlinkage void __fill_rsb(void);
+asmlinkage void __clear_rsb(void);
+
+#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 219faaec51df..386a6900e206 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -136,6 +136,7 @@
#endif
#ifndef __ASSEMBLY__
+#ifndef __BPF__
/*
* This output constraint should be used for any inline asm which has a "call"
* instruction. Otherwise the asm may be inserted before the frame pointer
@@ -145,5 +146,6 @@
register unsigned long current_stack_pointer asm(_ASM_SP);
#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
#endif
+#endif
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 2cbd75dd2fd3..e1c8dab86670 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -127,88 +127,6 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */
typedef u32 compat_sigset_word;
-typedef union compat_sigval {
- compat_int_t sival_int;
- compat_uptr_t sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[128/sizeof(int) - 3];
-
- /* kill() */
- struct {
- unsigned int _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- compat_sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- int _overrun_incr; /* amount to add to overrun */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- unsigned int _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- unsigned int _pid; /* which child */
- unsigned int _uid; /* sender's uid */
- int _status; /* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGCHLD (x32 version) */
- struct {
- unsigned int _pid; /* which child */
- unsigned int _uid; /* sender's uid */
- int _status; /* exit code */
- compat_s64 _utime;
- compat_s64 _stime;
- } _sigchld_x32;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- unsigned int _addr; /* faulting insn/memory ref. */
- short int _addr_lsb; /* Valid LSB of the reported address. */
- union {
- /* used when si_code=SEGV_BNDERR */
- struct {
- compat_uptr_t _lower;
- compat_uptr_t _upper;
- } _addr_bnd;
- /* used when si_code=SEGV_PKUERR */
- compat_u32 _pkey;
- };
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
-
- struct {
- unsigned int _call_addr; /* calling insn */
- int _syscall; /* triggering system call number */
- unsigned int _arch; /* AUDIT_ARCH_* of syscall */
- } _sigsys;
- } _sifields;
-} compat_siginfo_t;
-
#define COMPAT_OFF_T_MAX 0x7fffffff
struct compat_ipc64_perm {
@@ -331,4 +249,8 @@ static inline bool in_compat_syscall(void)
}
#define in_compat_syscall in_compat_syscall /* override the generic impl */
+struct compat_siginfo;
+int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
+ const siginfo_t *from, bool x32_ABI);
+
#endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
new file mode 100644
index 000000000000..4a7884b8dca5
--- /dev/null
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _ASM_X86_CPU_ENTRY_AREA_H
+#define _ASM_X86_CPU_ENTRY_AREA_H
+
+#include <linux/percpu-defs.h>
+#include <asm/processor.h>
+#include <asm/intel_ds.h>
+
+/*
+ * cpu_entry_area is a percpu region that contains things needed by the CPU
+ * and early entry/exit code. Real types aren't used for all fields here
+ * to avoid circular header dependencies.
+ *
+ * Every field is a virtual alias of some other allocated backing store.
+ * There is no direct allocation of a struct cpu_entry_area.
+ */
+struct cpu_entry_area {
+ char gdt[PAGE_SIZE];
+
+ /*
+ * The GDT is just below entry_stack and thus serves (on x86_64) as
+ * a a read-only guard page.
+ */
+ struct entry_stack_page entry_stack_page;
+
+ /*
+ * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because
+ * we need task switches to work, and task switches write to the TSS.
+ */
+ struct tss_struct tss;
+
+ char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+ /*
+ * Exception stacks used for IST entries.
+ *
+ * In the future, this should have a separate slot for each stack
+ * with guard pages between them.
+ */
+ char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+ /*
+ * Per CPU debug store for Intel performance monitoring. Wastes a
+ * full page at the moment.
+ */
+ struct debug_store cpu_debug_store;
+ /*
+ * The actual PEBS/BTS buffers must be mapped to user space
+ * Reserve enough fixmap PTEs.
+ */
+ struct debug_store_buffers cpu_debug_buffers;
+#endif
+};
+
+#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+
+extern void setup_cpu_entry_areas(void);
+extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+
+#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE
+#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
+
+#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT)
+
+#define CPU_ENTRY_AREA_MAP_SIZE \
+ (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+
+extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
+
+static inline struct entry_stack *cpu_entry_stack(int cpu)
+{
+ return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
+}
+
+#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bf6a76202a77..70eddb3922ff 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -29,6 +29,7 @@ enum cpuid_leafs
CPUID_8000_000A_EDX,
CPUID_7_ECX,
CPUID_8000_0007_EBX,
+ CPUID_7_EDX,
};
#ifdef CONFIG_X86_FEATURE_NAMES
@@ -79,8 +80,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \
REQUIRED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 19))
#define DISABLED_MASK_BIT_SET(feature_bit) \
( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \
@@ -101,8 +103,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \
DISABLED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 19))
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
@@ -135,6 +138,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
set_bit(bit, (unsigned long *)cpu_caps_set); \
} while (0)
+#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+
#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
/*
* Static testing of CPU features. Used the same as boot_cpu_has().
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c0b0e9e8aa66..1d9199e1c2ad 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 18 /* N 32-bit words worth of info */
+#define NCAPINTS 19 /* N 32-bit words worth of info */
#define NBUGINTS 1 /* N 32-bit bug flags */
/*
@@ -197,17 +197,21 @@
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
-
+#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
+#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
+
+#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
@@ -242,6 +246,7 @@
#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */
#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */
#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */
@@ -266,6 +271,10 @@
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */
+#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
@@ -314,6 +323,13 @@
#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */
#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
+#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#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_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+
/*
* BUG word(s)
*/
@@ -339,5 +355,8 @@
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 4011cb03ef08..13c5ee878a47 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -7,6 +7,7 @@
#include <asm/mmu.h>
#include <asm/fixmap.h>
#include <asm/irq_vectors.h>
+#include <asm/cpu_entry_area.h>
#include <linux/smp.h>
#include <linux/percpu.h>
@@ -20,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
desc->type = (info->read_exec_only ^ 1) << 1;
desc->type |= info->contents << 2;
+ /* Set the ACCESS bit so it can be mapped RO */
+ desc->type |= 1;
desc->s = 1;
desc->dpl = 0x3;
@@ -60,17 +63,10 @@ static inline struct desc_struct *get_current_gdt_rw(void)
return this_cpu_ptr(&gdt_page)->gdt;
}
-/* Get the fixmap index for a specific processor */
-static inline unsigned int get_cpu_gdt_ro_index(int cpu)
-{
- return FIX_GDT_REMAP_BEGIN + cpu;
-}
-
/* Provide the fixmap address of the remapped GDT */
static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
{
- unsigned int idx = get_cpu_gdt_ro_index(cpu);
- return (struct desc_struct *)__fix_to_virt(idx);
+ return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt;
}
/* Provide the current read-only GDT */
@@ -185,7 +181,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr,
#endif
}
-static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
+static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr)
{
struct desc_struct *d = get_cpu_gdt_rw(cpu);
tss_desc tss;
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 14d6d5007314..33833d1909af 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -50,6 +50,12 @@
# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31))
#endif
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI 0
+#else
+# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -60,7 +66,7 @@
#define DISABLED_MASK4 (DISABLE_PCID)
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
-#define DISABLED_MASK7 0
+#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
#define DISABLED_MASK9 (DISABLE_MPX)
#define DISABLED_MASK10 0
@@ -71,6 +77,7 @@
#define DISABLED_MASK15 0
#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
#define DISABLED_MASK17 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define DISABLED_MASK18 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 0211029076ea..6777480d8a42 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_ESPFIX_H
#define _ASM_X86_ESPFIX_H
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_ESPFIX64
#include <asm/percpu.h>
@@ -11,7 +11,8 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
extern void init_espfix_bsp(void);
extern void init_espfix_ap(int cpu);
-
-#endif /* CONFIG_X86_64 */
+#else
+static inline void init_espfix_ap(int cpu) { }
+#endif
#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index b0c505fe9a95..64c4a30e0d39 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -44,7 +44,6 @@ extern unsigned long __FIXADDR_TOP;
PAGE_SIZE)
#endif
-
/*
* Here we define all the compile-time 'special' virtual
* addresses. The point is to have a constant address at
@@ -84,7 +83,6 @@ enum fixed_addresses {
FIX_IO_APIC_BASE_0,
FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
#endif
- FIX_RO_IDT, /* Virtual mapping for read-only IDT */
#ifdef CONFIG_X86_32
FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -100,9 +98,6 @@ enum fixed_addresses {
#ifdef CONFIG_X86_INTEL_MID
FIX_LNW_VRTC,
#endif
- /* Fixmap entries to remap the GDTs, one per processor. */
- FIX_GDT_REMAP_BEGIN,
- FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
#ifdef CONFIG_ACPI_APEI_GHES
/* Used for GHES mapping from assorted contexts */
@@ -143,7 +138,7 @@ enum fixed_addresses {
extern void reserve_top_address(unsigned long reserve);
#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
extern int fixmaps_set;
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
index 4df2754ef380..44bbc39a57b3 100644
--- a/arch/x86/include/asm/fpu/signal.h
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -20,12 +20,6 @@ int ia32_setup_frame(int sig, struct ksignal *ksig,
# define ia32_setup_rt_frame __setup_rt_frame
#endif
-#ifdef CONFIG_COMPAT
-int __copy_siginfo_to_user32(compat_siginfo_t __user *to,
- const siginfo_t *from, bool x32_ABI);
-#endif
-
-
extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
struct task_struct *tsk);
extern void convert_to_fxsr(struct task_struct *tsk,
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 1b0a5abcd8ae..8c5aaba6633f 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -20,16 +20,7 @@
#ifndef _ASM_X86_HYPERVISOR_H
#define _ASM_X86_HYPERVISOR_H
-#ifdef CONFIG_HYPERVISOR_GUEST
-
-#include <asm/kvm_para.h>
-#include <asm/x86_init.h>
-#include <asm/xen/hypervisor.h>
-
-/*
- * x86 hypervisor information
- */
-
+/* x86 hypervisor types */
enum x86_hypervisor_type {
X86_HYPER_NATIVE = 0,
X86_HYPER_VMWARE,
@@ -37,8 +28,15 @@ enum x86_hypervisor_type {
X86_HYPER_XEN_PV,
X86_HYPER_XEN_HVM,
X86_HYPER_KVM,
+ X86_HYPER_JAILHOUSE,
};
+#ifdef CONFIG_HYPERVISOR_GUEST
+
+#include <asm/kvm_para.h>
+#include <asm/x86_init.h>
+#include <asm/xen/hypervisor.h>
+
struct hypervisor_x86 {
/* Hypervisor name */
const char *name;
@@ -58,7 +56,15 @@ struct hypervisor_x86 {
extern enum x86_hypervisor_type x86_hyper_type;
extern void init_hypervisor_platform(void);
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+ return x86_hyper_type == type;
+}
#else
static inline void init_hypervisor_platform(void) { }
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+ return type == X86_HYPER_NATIVE;
+}
#endif /* CONFIG_HYPERVISOR_GUEST */
#endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index c8376b40e882..5cdcdbd4d892 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -69,6 +69,11 @@ struct legacy_pic {
extern struct legacy_pic *legacy_pic;
extern struct legacy_pic null_legacy_pic;
+static inline bool has_legacy_pic(void)
+{
+ return legacy_pic != &null_legacy_pic;
+}
+
static inline int nr_legacy_irqs(void)
{
return legacy_pic->nr_legacy_irqs;
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
new file mode 100644
index 000000000000..62a9f4966b42
--- /dev/null
+++ b/arch/x86/include/asm/intel_ds.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS 8
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+ u64 bts_buffer_base;
+ u64 bts_index;
+ u64 bts_absolute_maximum;
+ u64 bts_interrupt_threshold;
+ u64 pebs_buffer_base;
+ u64 pebs_index;
+ u64 pebs_absolute_maximum;
+ u64 pebs_interrupt_threshold;
+ u64 pebs_event_reset[MAX_PEBS_EVENTS];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+ char bts_buffer[BTS_BUFFER_SIZE];
+ char pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif
diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
new file mode 100644
index 000000000000..989cfa86de85
--- /dev/null
+++ b/arch/x86/include/asm/invpcid.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVPCID
+#define _ASM_X86_INVPCID
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+ unsigned long type)
+{
+ struct { u64 d[2]; } desc = { { pcid, addr } };
+
+ /*
+ * The memory clobber is because the whole point is to invalidate
+ * stale TLB entries and, especially if we're flushing global
+ * mappings, we don't want the compiler to reorder any subsequent
+ * memory accesses before the TLB flush.
+ *
+ * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+ * invpcid (%rcx), %rax in long mode.
+ */
+ asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+ : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR 0
+#define INVPCID_TYPE_SINGLE_CTXT 1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL 2
+#define INVPCID_TYPE_ALL_NON_GLOBAL 3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+ unsigned long addr)
+{
+ __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+ __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+ __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+ __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
+#endif /* _ASM_X86_INVPCID */
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
index 139feef467f7..c066ffae222b 100644
--- a/arch/x86/include/asm/irqdomain.h
+++ b/arch/x86/include/asm/irqdomain.h
@@ -44,7 +44,7 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs);
extern int mp_irqdomain_activate(struct irq_domain *domain,
- struct irq_data *irq_data, bool early);
+ struct irq_data *irq_data, bool reserve);
extern void mp_irqdomain_deactivate(struct irq_domain *domain,
struct irq_data *irq_data);
extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c8ef23f2c28f..89f08955fff7 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void)
swapgs; \
sysretl
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x) pushfq; popq %rax
+#endif
#else
#define INTERRUPT_RETURN iret
#define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit
diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h
new file mode 100644
index 000000000000..875b54376689
--- /dev/null
+++ b/arch/x86/include/asm/jailhouse_para.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL2.0 */
+
+/*
+ * Jailhouse paravirt_ops implementation
+ *
+ * Copyright (c) Siemens AG, 2015-2017
+ *
+ * Authors:
+ * Jan Kiszka <jan.kiszka@siemens.com>
+ */
+
+#ifndef _ASM_X86_JAILHOUSE_PARA_H
+#define _ASM_X86_JAILHOUSE_PARA_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_JAILHOUSE_GUEST
+bool jailhouse_paravirt(void);
+#else
+static inline bool jailhouse_paravirt(void)
+{
+ return false;
+}
+#endif
+
+#endif /* _ASM_X86_JAILHOUSE_PARA_H */
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index f86a8caa561e..395c9631e000 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
extern int __must_check __die(const char *, struct pt_regs *, long);
extern void show_stack_regs(struct pt_regs *regs);
extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_iret_regs(struct pt_regs *regs);
extern unsigned long oops_begin(void);
extern void oops_end(unsigned long, struct pt_regs *, int signr);
diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/include/asm/kmemcheck.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 034caa1a084e..b24b1c8b3979 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -214,8 +214,6 @@ struct x86_emulate_ops {
void (*halt)(struct x86_emulate_ctxt *ctxt);
void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
- void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
- void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
int (*intercept)(struct x86_emulate_ctxt *ctxt,
struct x86_instruction_info *info,
enum x86_intercept_stage stage);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1bfb99770c34..516798431328 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,7 +536,20 @@ struct kvm_vcpu_arch {
struct kvm_mmu_memory_cache mmu_page_cache;
struct kvm_mmu_memory_cache mmu_page_header_cache;
+ /*
+ * QEMU userspace and the guest each have their own FPU state.
+ * In vcpu_run, we switch between the user and guest FPU contexts.
+ * While running a VCPU, the VCPU thread will have the guest FPU
+ * context.
+ *
+ * Note that while the PKRU state lives inside the fpu registers,
+ * it is switched out separately at VMENTER and VMEXIT time. The
+ * "guest_fpu" state here contains the guest FPU context, with the
+ * host PRKU bits.
+ */
+ struct fpu user_fpu;
struct fpu guest_fpu;
+
u64 xcr0;
u64 guest_supported_xcr0;
u32 guest_xstate_size;
@@ -1161,7 +1174,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
static inline int emulate_instruction(struct kvm_vcpu *vcpu,
int emulation_type)
{
- return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+ return x86_emulate_instruction(vcpu, 0,
+ emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
}
void kvm_enable_efer_bits(u64);
@@ -1434,4 +1448,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+ unsigned long start, unsigned long end);
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index b1e8d8db921f..96ea4b5ba658 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -376,6 +376,7 @@ struct smca_bank {
extern struct smca_bank smca_banks[MAX_NR_BANKS];
extern const char *smca_get_long_name(enum smca_bank_types t);
+extern bool amd_mce_is_memory_error(struct mce *m);
extern int mce_threshold_create_device(unsigned int cpu);
extern int mce_threshold_remove_device(unsigned int cpu);
@@ -384,6 +385,7 @@ extern int mce_threshold_remove_device(unsigned int cpu);
static inline int mce_threshold_create_device(unsigned int cpu) { return 0; };
static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; };
+static inline bool amd_mce_is_memory_error(struct mce *m) { return false; };
#endif
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index c9459a4c3c68..22c5f3e6f820 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -39,7 +39,7 @@ void __init sme_unmap_bootdata(char *real_mode_data);
void __init sme_early_init(void);
-void __init sme_encrypt_kernel(void);
+void __init sme_encrypt_kernel(struct boot_params *bp);
void __init sme_enable(struct boot_params *bp);
int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
@@ -67,7 +67,7 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
static inline void __init sme_early_init(void) { }
-static inline void __init sme_encrypt_kernel(void) { }
+static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
static inline void __init sme_enable(struct boot_params *bp) { }
static inline bool sme_active(void) { return false; }
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 9ea26f167497..5ff3e8af2c20 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -3,6 +3,7 @@
#define _ASM_X86_MMU_H
#include <linux/spinlock.h>
+#include <linux/rwsem.h>
#include <linux/mutex.h>
#include <linux/atomic.h>
@@ -27,7 +28,8 @@ typedef struct {
atomic64_t tlb_gen;
#ifdef CONFIG_MODIFY_LDT_SYSCALL
- struct ldt_struct *ldt;
+ struct rw_semaphore ldt_usr_sem;
+ struct ldt_struct *ldt;
#endif
#ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 6d16d15d09a0..c931b88982a0 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -50,22 +50,53 @@ struct ldt_struct {
* call gates. On native, we could merge the ldt_struct and LDT
* allocations, but it's not worth trying to optimize.
*/
- struct desc_struct *entries;
- unsigned int nr_entries;
+ struct desc_struct *entries;
+ unsigned int nr_entries;
+
+ /*
+ * If PTI is in use, then the entries array is not mapped while we're
+ * in user mode. The whole array will be aliased at the addressed
+ * given by ldt_slot_va(slot). We use two slots so that we can allocate
+ * and map, and enable a new LDT without invalidating the mapping
+ * of an older, still-in-use LDT.
+ *
+ * slot will be -1 if this LDT doesn't have an alias mapping.
+ */
+ int slot;
};
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+#ifdef CONFIG_X86_64
+ return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+#else
+ BUG();
+#endif
+}
+
/*
* Used for LDT copy/destruction.
*/
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+static inline void init_new_context_ldt(struct mm_struct *mm)
+{
+ mm->context.ldt = NULL;
+ init_rwsem(&mm->context.ldt_usr_sem);
+}
+int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
void destroy_context_ldt(struct mm_struct *mm);
+void ldt_arch_exit_mmap(struct mm_struct *mm);
#else /* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context_ldt(struct task_struct *tsk,
- struct mm_struct *mm)
+static inline void init_new_context_ldt(struct mm_struct *mm) { }
+static inline int ldt_dup_context(struct mm_struct *oldmm,
+ struct mm_struct *mm)
{
return 0;
}
-static inline void destroy_context_ldt(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) { }
+static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
#endif
static inline void load_mm_ldt(struct mm_struct *mm)
@@ -90,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm)
* that we can see.
*/
- if (unlikely(ldt))
- set_ldt(ldt->entries, ldt->nr_entries);
- else
+ if (unlikely(ldt)) {
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+ /*
+ * Whoops -- either the new LDT isn't mapped
+ * (if slot == -1) or is mapped into a bogus
+ * slot (if slot > 1).
+ */
+ clear_LDT();
+ return;
+ }
+
+ /*
+ * If page table isolation is enabled, ldt->entries
+ * will not be mapped in the userspace pagetables.
+ * Tell the CPU to access the LDT through the alias
+ * at ldt_slot_va(ldt->slot).
+ */
+ set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+ } else {
+ set_ldt(ldt->entries, ldt->nr_entries);
+ }
+ } else {
clear_LDT();
+ }
#else
clear_LDT();
#endif
@@ -132,18 +184,21 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
+ mutex_init(&mm->context.lock);
+
mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
atomic64_set(&mm->context.tlb_gen, 0);
- #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
/* pkey 0 is the default and always allocated */
mm->context.pkey_allocation_map = 0x1;
/* -1 means unallocated or invalid */
mm->context.execute_only_pkey = -1;
}
- #endif
- return init_new_context_ldt(tsk, mm);
+#endif
+ init_new_context_ldt(mm);
+ return 0;
}
static inline void destroy_context(struct mm_struct *mm)
{
@@ -176,15 +231,16 @@ do { \
} while (0)
#endif
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
- struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
{
paravirt_arch_dup_mmap(oldmm, mm);
+ return ldt_dup_context(oldmm, mm);
}
static inline void arch_exit_mmap(struct mm_struct *mm)
{
paravirt_arch_exit_mmap(mm);
+ ldt_arch_exit_mmap(mm);
}
#ifdef CONFIG_X86_64
@@ -282,33 +338,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
}
/*
- * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
- * bits. This serves two purposes. It prevents a nasty situation in
- * which PCID-unaware code saves CR3, loads some other value (with PCID
- * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
- * the saved ASID was nonzero. It also means that any bugs involving
- * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
- * deterministically.
- */
-
-static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
-{
- if (static_cpu_has(X86_FEATURE_PCID)) {
- VM_WARN_ON_ONCE(asid > 4094);
- return __sme_pa(mm->pgd) | (asid + 1);
- } else {
- VM_WARN_ON_ONCE(asid != 0);
- return __sme_pa(mm->pgd);
- }
-}
-
-static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
-{
- VM_WARN_ON_ONCE(asid > 4094);
- return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
-}
-
-/*
* This can be used from process context to figure out what the value of
* CR3 is without needing to do a (slow) __read_cr3().
*
@@ -317,7 +346,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
*/
static inline unsigned long __get_current_cr3_fast(void)
{
- unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+ unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
this_cpu_read(cpu_tlbstate.loaded_mm_asid));
/* For now, be very restrictive about when this can be called. */
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index a6bec8028480..6fb923a34309 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -128,9 +128,17 @@ enum mp_irq_source_types {
mp_ExtINT = 3
};
-#define MP_IRQDIR_DEFAULT 0
-#define MP_IRQDIR_HIGH 1
-#define MP_IRQDIR_LOW 3
+#define MP_IRQPOL_DEFAULT 0x0
+#define MP_IRQPOL_ACTIVE_HIGH 0x1
+#define MP_IRQPOL_RESERVED 0x2
+#define MP_IRQPOL_ACTIVE_LOW 0x3
+#define MP_IRQPOL_MASK 0x3
+
+#define MP_IRQTRIG_DEFAULT 0x0
+#define MP_IRQTRIG_EDGE 0x4
+#define MP_IRQTRIG_RESERVED 0x8
+#define MP_IRQTRIG_LEVEL 0xc
+#define MP_IRQTRIG_MASK 0xc
#define MP_APIC_ALL 0xFF
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 5400add2885b..8bf450b13d9f 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -7,6 +7,7 @@
#include <linux/nmi.h>
#include <asm/io.h>
#include <asm/hyperv.h>
+#include <asm/nospec-branch.h>
/*
* The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
@@ -186,10 +187,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
return U64_MAX;
__asm__ __volatile__("mov %4, %%r8\n"
- "call *%5"
+ CALL_NOSPEC
: "=a" (hv_status), ASM_CALL_CONSTRAINT,
"+c" (control), "+d" (input_address)
- : "r" (output_address), "m" (hv_hypercall_pg)
+ : "r" (output_address),
+ THUNK_TARGET(hv_hypercall_pg)
: "cc", "memory", "r8", "r9", "r10", "r11");
#else
u32 input_address_hi = upper_32_bits(input_address);
@@ -200,13 +202,13 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
if (!hv_hypercall_pg)
return U64_MAX;
- __asm__ __volatile__("call *%7"
+ __asm__ __volatile__(CALL_NOSPEC
: "=A" (hv_status),
"+c" (input_address_lo), ASM_CALL_CONSTRAINT
: "A" (control),
"b" (input_address_hi),
"D"(output_address_hi), "S"(output_address_lo),
- "m" (hv_hypercall_pg)
+ THUNK_TARGET(hv_hypercall_pg)
: "cc", "memory");
#endif /* !x86_64 */
return hv_status;
@@ -227,10 +229,10 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
#ifdef CONFIG_X86_64
{
- __asm__ __volatile__("call *%4"
+ __asm__ __volatile__(CALL_NOSPEC
: "=a" (hv_status), ASM_CALL_CONSTRAINT,
"+c" (control), "+d" (input1)
- : "m" (hv_hypercall_pg)
+ : THUNK_TARGET(hv_hypercall_pg)
: "cc", "r8", "r9", "r10", "r11");
}
#else
@@ -238,13 +240,13 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
u32 input1_hi = upper_32_bits(input1);
u32 input1_lo = lower_32_bits(input1);
- __asm__ __volatile__ ("call *%5"
+ __asm__ __volatile__ (CALL_NOSPEC
: "=A"(hv_status),
"+c"(input1_lo),
ASM_CALL_CONSTRAINT
: "A" (control),
"b" (input1_hi),
- "m" (hv_hypercall_pg)
+ THUNK_TARGET(hv_hypercall_pg)
: "cc", "edi", "esi");
}
#endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 34c4922bbc3f..e520a1e6fc11 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -39,6 +39,13 @@
/* Intel MSRs. Some also available on other CPUs */
+#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */
+#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */
+
+#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
+#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */
+
#define MSR_PPIN_CTL 0x0000004e
#define MSR_PPIN 0x0000004f
@@ -57,6 +64,11 @@
#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
#define MSR_MTRRcap 0x000000fe
+
+#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a
+#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */
+
#define MSR_IA32_BBL_CR_CTL 0x00000119
#define MSR_IA32_BBL_CR_CTL3 0x0000011e
@@ -355,6 +367,9 @@
#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL
#define FAM10H_MMIO_CONF_BASE_SHIFT 20
#define MSR_FAM10H_NODE_ID 0xc001100c
+#define MSR_F10H_DECFG 0xc0011029
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
/* K8 MSRs */
#define MSR_K8_TOP_MEM1 0xc001001a
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
new file mode 100644
index 000000000000..d15d471348b8
--- /dev/null
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_X86_NOSPEC_BRANCH_H_
+#define _ASM_X86_NOSPEC_BRANCH_H_
+
+#include <asm/alternative.h>
+#include <asm/alternative-asm.h>
+#include <asm/cpufeatures.h>
+
+#ifdef __ASSEMBLY__
+
+/*
+ * This should be used immediately before a retpoline alternative. It tells
+ * objtool where the retpolines are so that it can make sense of the control
+ * flow by just reading the original instruction(s) and ignoring the
+ * alternatives.
+ */
+.macro ANNOTATE_NOSPEC_ALTERNATIVE
+ .Lannotate_\@:
+ .pushsection .discard.nospec
+ .long .Lannotate_\@ - .
+ .popsection
+.endm
+
+/*
+ * These are the bare retpoline primitives for indirect jmp and call.
+ * Do not use these directly; they only exist to make the ALTERNATIVE
+ * invocation below less ugly.
+ */
+.macro RETPOLINE_JMP reg:req
+ call .Ldo_rop_\@
+.Lspec_trap_\@:
+ pause
+ lfence
+ jmp .Lspec_trap_\@
+.Ldo_rop_\@:
+ mov \reg, (%_ASM_SP)
+ ret
+.endm
+
+/*
+ * This is a wrapper around RETPOLINE_JMP so the called function in reg
+ * returns to the instruction after the macro.
+ */
+.macro RETPOLINE_CALL reg:req
+ jmp .Ldo_call_\@
+.Ldo_retpoline_jmp_\@:
+ RETPOLINE_JMP \reg
+.Ldo_call_\@:
+ call .Ldo_retpoline_jmp_\@
+.endm
+
+/*
+ * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
+ * indirect jmp/call which may be susceptible to the Spectre variant 2
+ * attack.
+ */
+.macro JMP_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+ ANNOTATE_NOSPEC_ALTERNATIVE
+ ALTERNATIVE_2 __stringify(jmp *\reg), \
+ __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \
+ __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+ jmp *\reg
+#endif
+.endm
+
+.macro CALL_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+ ANNOTATE_NOSPEC_ALTERNATIVE
+ ALTERNATIVE_2 __stringify(call *\reg), \
+ __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
+ __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+ call *\reg
+#endif
+.endm
+
+/* This clobbers the BX register */
+.macro FILL_RETURN_BUFFER nr:req ftr:req
+#ifdef CONFIG_RETPOLINE
+ ALTERNATIVE "", "call __clear_rsb", \ftr
+#endif
+.endm
+
+#else /* __ASSEMBLY__ */
+
+#define ANNOTATE_NOSPEC_ALTERNATIVE \
+ "999:\n\t" \
+ ".pushsection .discard.nospec\n\t" \
+ ".long 999b - .\n\t" \
+ ".popsection\n\t"
+
+#if defined(CONFIG_X86_64) && defined(RETPOLINE)
+
+/*
+ * Since the inline asm uses the %V modifier which is only in newer GCC,
+ * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE.
+ */
+# define CALL_NOSPEC \
+ ANNOTATE_NOSPEC_ALTERNATIVE \
+ ALTERNATIVE( \
+ "call *%[thunk_target]\n", \
+ "call __x86_indirect_thunk_%V[thunk_target]\n", \
+ X86_FEATURE_RETPOLINE)
+# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
+
+#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE)
+/*
+ * For i386 we use the original ret-equivalent retpoline, because
+ * otherwise we'll run out of registers. We don't care about CET
+ * here, anyway.
+ */
+# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \
+ " jmp 904f;\n" \
+ " .align 16\n" \
+ "901: call 903f;\n" \
+ "902: pause;\n" \
+ " lfence;\n" \
+ " jmp 902b;\n" \
+ " .align 16\n" \
+ "903: addl $4, %%esp;\n" \
+ " pushl %[thunk_target];\n" \
+ " ret;\n" \
+ " .align 16\n" \
+ "904: call 901b;\n", \
+ X86_FEATURE_RETPOLINE)
+
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#else /* No retpoline for C / inline asm */
+# define CALL_NOSPEC "call *%[thunk_target]\n"
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#endif
+
+/* The Spectre V2 mitigation variants */
+enum spectre_v2_mitigation {
+ SPECTRE_V2_NONE,
+ SPECTRE_V2_RETPOLINE_MINIMAL,
+ SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
+ SPECTRE_V2_RETPOLINE_GENERIC,
+ SPECTRE_V2_RETPOLINE_AMD,
+ SPECTRE_V2_IBRS,
+};
+
+extern char __indirect_thunk_start[];
+extern char __indirect_thunk_end[];
+
+/*
+ * On VMEXIT we must ensure that no RSB predictions learned in the guest
+ * can be followed in the host, by overwriting the RSB completely. Both
+ * retpoline and IBRS mitigations for Spectre v2 need this; only on future
+ * CPUs with IBRS_ATT *might* it be avoided.
+ */
+static inline void vmexit_fill_RSB(void)
+{
+#ifdef CONFIG_RETPOLINE
+ alternative_input("",
+ "call __fill_rsb",
+ X86_FEATURE_RETPOLINE,
+ ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory"));
+#endif
+}
+
+static inline void indirect_branch_prediction_barrier(void)
+{
+ alternative_input("",
+ "call __ibp_barrier",
+ X86_FEATURE_USE_IBPB,
+ ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory"));
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 283efcaac8af..892df375b615 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -927,6 +927,15 @@ extern void default_banner(void);
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \
CLBR_NONE, \
jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(clobbers) \
+ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
+ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \
+ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
+
#endif /* CONFIG_X86_32 */
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 7a5d6695abd3..eb66fa9cd0fc 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -38,6 +38,7 @@ do { \
#define PCI_NOASSIGN_ROMS 0x80000
#define PCI_ROOT_NO_CRS 0x100000
#define PCI_NOASSIGN_BARS 0x200000
+#define PCI_BIG_ROOT_WINDOW 0x400000
extern unsigned int pci_probe;
extern unsigned long pirq_table_addr;
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 4b5e1eafada7..aff42e1da6ee 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
*/
extern gfp_t __userpte_alloc_gfp;
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Instead of one PGD, we acquire two PGDs. Being order-1, it is
+ * both 8k in size and 8k-aligned. That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
+#else
+#define PGD_ALLOCATION_ORDER 0
+#endif
+
/*
* Allocate and free page tables.
*/
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 09f9e1e00e3b..e42b8943cb1a 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD];
int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
void ptdump_walk_pgd_level_checkwx(void);
#ifdef CONFIG_DEBUG_WX
@@ -841,7 +842,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
static inline int p4d_bad(p4d_t p4d)
{
- return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+ unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
+
+ if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ ignore_flags |= _PAGE_NX;
+
+ return (p4d_flags(p4d) & ~ignore_flags) != 0;
}
#endif /* CONFIG_PGTABLE_LEVELS > 3 */
@@ -875,7 +881,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
static inline int pgd_bad(pgd_t pgd)
{
- return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+ unsigned long ignore_flags = _PAGE_USER;
+
+ if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ ignore_flags |= _PAGE_NX;
+
+ return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
}
static inline int pgd_none(pgd_t pgd)
@@ -904,7 +915,11 @@ static inline int pgd_none(pgd_t pgd)
* pgd_offset() returns a (pgd_t *)
* pgd_index() is used get the offset into the pgd page's array of pgd_t's;
*/
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
/*
* a shortcut which implies the use of the kernel's pgd, instead
* of a process's
@@ -1061,7 +1076,7 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp);
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_RW;
@@ -1088,6 +1103,12 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
}
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_RW;
+}
+
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
*
@@ -1100,7 +1121,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
*/
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
- memcpy(dst, src, count * sizeof(pgd_t));
+ memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+ /* Clone the user space pgd as well */
+ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
+ count * sizeof(pgd_t));
+#endif
}
#define PTE_SHIFT ilog2(PTRS_PER_PTE)
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index f2ca9b28fd68..ce245b0cdfca 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
#define LAST_PKMAP 1024
#endif
-#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1)) \
- & PMD_MASK)
+/*
+ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
+ * to avoid include recursion hell
+ */
+#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40)
+
+#define CPU_ENTRY_AREA_BASE \
+ ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK)
+
+#define PKMAP_BASE \
+ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
#ifdef CONFIG_HIGHMEM
# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE)
#else
-# define VMALLOC_END (FIXADDR_START - 2 * PAGE_SIZE)
+# define VMALLOC_END (CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
#endif
#define MODULES_VADDR VMALLOC_START
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e9f05331e732..81462e9a34f6 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -131,9 +131,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
#endif
}
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and
+ * the user one is in the last 4k. To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr |= BIT(bit);
+ return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr &= ~BIT(bit);
+ return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+ return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+ return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+ return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+ return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned. The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+ unsigned long ptr = (unsigned long)__ptr;
+
+ return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return pgd;
+ return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ return pgd;
+}
+#endif
+
static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+ p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
*p4dp = p4d;
+#endif
}
static inline void native_p4d_clear(p4d_t *p4d)
@@ -147,7 +235,11 @@ static inline void native_p4d_clear(p4d_t *p4d)
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ *pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
*pgdp = pgd;
+#endif
}
static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 6d5f45dcd4a1..6b8f73dcbc2c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -75,33 +75,52 @@ typedef struct { pteval_t pte; } pte_t;
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
-/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+/*
+ * See Documentation/x86/x86_64/mm.txt for a description of the memory map.
+ *
+ * Be very careful vs. KASLR when changing anything here. The KASLR address
+ * range must not overlap with anything except the KASAN shadow area, which
+ * is correct as KASAN disables KASLR.
+ */
+#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+
#ifdef CONFIG_X86_5LEVEL
-#define VMALLOC_SIZE_TB _AC(16384, UL)
-#define __VMALLOC_BASE _AC(0xff92000000000000, UL)
-#define __VMEMMAP_BASE _AC(0xffd4000000000000, UL)
+# define VMALLOC_SIZE_TB _AC(12800, UL)
+# define __VMALLOC_BASE _AC(0xffa0000000000000, UL)
+# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL)
+# define LDT_PGD_ENTRY _AC(-112, UL)
+# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#else
-#define VMALLOC_SIZE_TB _AC(32, UL)
-#define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
-#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
+# define VMALLOC_SIZE_TB _AC(32, UL)
+# define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
+# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
+# define LDT_PGD_ENTRY _AC(-3, UL)
+# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#endif
+
#ifdef CONFIG_RANDOMIZE_MEMORY
-#define VMALLOC_START vmalloc_base
-#define VMEMMAP_START vmemmap_base
+# define VMALLOC_START vmalloc_base
+# define VMEMMAP_START vmemmap_base
#else
-#define VMALLOC_START __VMALLOC_BASE
-#define VMEMMAP_START __VMEMMAP_BASE
+# define VMALLOC_START __VMALLOC_BASE
+# define VMEMMAP_START __VMEMMAP_BASE
#endif /* CONFIG_RANDOMIZE_MEMORY */
-#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
-#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
+
+#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+
+#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
/* The module sections ends with the start of the fixmap */
-#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1)
-#define MODULES_LEN (MODULES_END - MODULES_VADDR)
-#define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
-#define EFI_VA_START ( -4 * (_AC(1, UL) << 30))
-#define EFI_VA_END (-68 * (_AC(1, UL) << 30))
+#define MODULES_END _AC(0xffffffffff000000, UL)
+#define MODULES_LEN (MODULES_END - MODULES_VADDR)
+
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
+
+#define CPU_ENTRY_AREA_PGD _AC(-4, UL)
+#define CPU_ENTRY_AREA_BASE (CPU_ENTRY_AREA_PGD << P4D_SHIFT)
+
+#define EFI_VA_START ( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END (-68 * (_AC(1, UL) << 30))
#define EARLY_DYNAMIC_PAGE_TABLES 64
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 43212a43ee69..625a52a5594f 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -38,6 +38,11 @@
#define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull)
#define CR3_PCID_MASK 0xFFFull
#define CR3_NOFLUSH BIT_ULL(63)
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_PCID_USER_BIT 11
+#endif
+
#else
/*
* CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cc16fa882e3e..efbde088a718 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -163,9 +163,9 @@ enum cpuid_regs_idx {
extern struct cpuinfo_x86 boot_cpu_data;
extern struct cpuinfo_x86 new_cpu_data;
-extern struct tss_struct doublefault_tss;
-extern __u32 cpu_caps_cleared[NCAPINTS];
-extern __u32 cpu_caps_set[NCAPINTS];
+extern struct x86_hw_tss doublefault_tss;
+extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
+extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS];
#ifdef CONFIG_SMP
DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
@@ -253,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir)
write_cr3(__sme_pa(pgdir));
}
+/*
+ * Note that while the legacy 'TSS' name comes from 'Task State Segment',
+ * on modern x86 CPUs the TSS also holds information important to 64-bit mode,
+ * unrelated to the task-switch mechanism:
+ */
#ifdef CONFIG_X86_32
/* This is the TSS defined by the hardware. */
struct x86_hw_tss {
@@ -305,7 +310,13 @@ struct x86_hw_tss {
struct x86_hw_tss {
u32 reserved1;
u64 sp0;
+
+ /*
+ * We store cpu_current_top_of_stack in sp1 so it's always accessible.
+ * Linux does not use ring 1, so sp1 is not otherwise needed.
+ */
u64 sp1;
+
u64 sp2;
u64 reserved2;
u64 ist[7];
@@ -323,12 +334,22 @@ struct x86_hw_tss {
#define IO_BITMAP_BITS 65536
#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8)
#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap)
+#define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
#define INVALID_IO_BITMAP_OFFSET 0x8000
+struct entry_stack {
+ unsigned long words[64];
+};
+
+struct entry_stack_page {
+ struct entry_stack stack;
+} __aligned(PAGE_SIZE);
+
struct tss_struct {
/*
- * The hardware state:
+ * The fixed hardware portion. This must not cross a page boundary
+ * at risk of violating the SDM's advice and potentially triggering
+ * errata.
*/
struct x86_hw_tss x86_tss;
@@ -339,18 +360,9 @@ struct tss_struct {
* be within the limit.
*/
unsigned long io_bitmap[IO_BITMAP_LONGS + 1];
+} __aligned(PAGE_SIZE);
-#ifdef CONFIG_X86_32
- /*
- * Space for the temporary SYSENTER stack.
- */
- unsigned long SYSENTER_stack_canary;
- unsigned long SYSENTER_stack[64];
-#endif
-
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
/*
* sizeof(unsigned long) coming from an extra "long" at the end
@@ -364,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
#ifdef CONFIG_X86_32
DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
+#else
+/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
+#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
#endif
/*
@@ -523,7 +538,7 @@ static inline void native_set_iopl_mask(unsigned mask)
static inline void
native_load_sp0(unsigned long sp0)
{
- this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+ this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
}
static inline void native_swapgs(void)
@@ -535,12 +550,12 @@ static inline void native_swapgs(void)
static inline unsigned long current_top_of_stack(void)
{
-#ifdef CONFIG_X86_64
- return this_cpu_read_stable(cpu_tss.x86_tss.sp0);
-#else
- /* sp0 on x86_32 is special in and around vm86 mode. */
+ /*
+ * We can't read directly from tss.sp0: sp0 on x86_32 is special in
+ * and around vm86 mode and sp0 on x86_64 is special because of the
+ * entry trampoline.
+ */
return this_cpu_read_stable(cpu_current_top_of_stack);
-#endif
}
static inline bool on_thread_stack(void)
@@ -837,13 +852,22 @@ static inline void spin_lock_prefetch(const void *x)
#else
/*
- * User space process size. 47bits minus one guard page. The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously. We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
+ * User space process size. This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen. This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
*/
#define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
@@ -947,4 +971,7 @@ bool xen_set_default_idle(void);
void stop_this_cpu(void *dummy);
void df_debug(struct pt_regs *regs, long error_code);
+
+void __ibp_barrier(void);
+
#endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
new file mode 100644
index 000000000000..0b5ef05b2d2d
--- /dev/null
+++ b/arch/x86/include/asm/pti.h
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _ASM_X86_PTI_H
+#define _ASM_X86_PTI_H
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern void pti_init(void);
+extern void pti_check_boottime_disable(void);
+#else
+static inline void pti_check_boottime_disable(void) { }
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PTI_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index d91ba04dd007..fb3a6de7440b 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -106,6 +106,7 @@
#define REQUIRED_MASK15 0
#define REQUIRED_MASK16 (NEED_LA57)
#define REQUIRED_MASK17 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define REQUIRED_MASK18 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index b20f9d623f9c..8f09012b92e7 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -236,11 +236,23 @@
*/
#define EARLY_IDT_HANDLER_SIZE 9
+/*
+ * xen_early_idt_handler_array is for Xen pv guests: for each entry in
+ * early_idt_handler_array it contains a prequel in the form of
+ * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to
+ * max 8 bytes.
+ */
+#define XEN_EARLY_IDT_HANDLER_SIZE 8
+
#ifndef __ASSEMBLY__
extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
extern void early_ignore_irq(void);
+#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
+extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE];
+#endif
+
/*
* Load a segment. Fall back on loading the zero segment if something goes
* wrong. This variant assumes that loading zero fully clears the segment.
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 8da111b3c342..f73706878772 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -16,6 +16,7 @@ enum stack_type {
STACK_TYPE_TASK,
STACK_TYPE_IRQ,
STACK_TYPE_SOFTIRQ,
+ STACK_TYPE_ENTRY,
STACK_TYPE_EXCEPTION,
STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
};
@@ -28,6 +29,8 @@ struct stack_info {
bool in_task_stack(unsigned long *stack, struct task_struct *task,
struct stack_info *info);
+bool in_entry_stack(unsigned long *stack, struct stack_info *info);
+
int get_stack_info(unsigned long *stack, struct task_struct *task,
struct stack_info *info, unsigned long *visit_mask);
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 982c325dad33..8be6afb58471 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -12,7 +12,13 @@
/* image of the saved processor state */
struct saved_context {
- u16 es, fs, gs, ss;
+ /*
+ * On x86_32, all segment registers, with the possible exception of
+ * gs, are saved at kernel entry in pt_regs.
+ */
+#ifdef CONFIG_X86_32_LAZY_GS
+ u16 gs;
+#endif
unsigned long cr0, cr2, cr3, cr4;
u64 misc_enable;
bool misc_enable_saved;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 7306e911faee..a7af9f53c0cb 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -20,8 +20,20 @@
*/
struct saved_context {
struct pt_regs regs;
- u16 ds, es, fs, gs, ss;
- unsigned long gs_base, gs_kernel_base, fs_base;
+
+ /*
+ * User CS and SS are saved in current_pt_regs(). The rest of the
+ * segment selectors need to be saved and restored here.
+ */
+ u16 ds, es, fs, gs;
+
+ /*
+ * Usermode FSBASE and GSBASE may not match the fs and gs selectors,
+ * so we save them separately. We save the kernelmode GSBASE to
+ * restore percpu access after resume.
+ */
+ unsigned long kernelmode_gs_base, usermode_gs_base, fs_base;
+
unsigned long cr0, cr2, cr3, cr4, cr8;
u64 misc_enable;
bool misc_enable_saved;
@@ -30,8 +42,7 @@ struct saved_context {
u16 gdt_pad; /* Unused */
struct desc_ptr gdt_desc;
u16 idt_pad;
- u16 idt_limit;
- unsigned long idt_base;
+ struct desc_ptr idt;
u16 ldt;
u16 tss;
unsigned long tr;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 8c6bd6863db9..eb5f7999a893 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -16,8 +16,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
struct tss_struct *tss);
/* This runs runs on the previous thread's stack. */
-static inline void prepare_switch_to(struct task_struct *prev,
- struct task_struct *next)
+static inline void prepare_switch_to(struct task_struct *next)
{
#ifdef CONFIG_VMAP_STACK
/*
@@ -70,7 +69,7 @@ struct fork_frame {
#define switch_to(prev, next, last) \
do { \
- prepare_switch_to(prev, next); \
+ prepare_switch_to(next); \
\
((last) = __switch_to_asm((prev), (next))); \
} while (0)
@@ -79,10 +78,10 @@ do { \
static inline void refresh_sysenter_cs(struct thread_struct *thread)
{
/* Only happens when SEP is enabled, no need to test "SEP"arately: */
- if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs))
+ if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs))
return;
- this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs);
+ this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
}
#endif
@@ -90,10 +89,12 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
/* This is used when switching tasks or entering/exiting vm86 mode. */
static inline void update_sp0(struct task_struct *task)
{
+ /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
#ifdef CONFIG_X86_32
load_sp0(task->thread.sp0);
#else
- load_sp0(task_top_of_stack(task));
+ if (static_cpu_has(X86_FEATURE_XENPV))
+ load_sp0(task_top_of_stack(task));
#endif
}
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 70f425947dc5..d25a638a2720 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -62,8 +62,6 @@ struct thread_info {
.flags = 0, \
}
-#define init_stack (init_thread_union.stack)
-
#else /* !__ASSEMBLY__ */
#include <asm/asm-offsets.h>
@@ -207,7 +205,7 @@ static inline int arch_within_stack_frames(const void * const stack,
#else /* !__ASSEMBLY__ */
#ifdef CONFIG_X86_64
-# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1)
#endif
#endif
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 509046cfa5ce..d33e4a26dc7e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -9,70 +9,130 @@
#include <asm/cpufeature.h>
#include <asm/special_insns.h>
#include <asm/smp.h>
+#include <asm/invpcid.h>
+#include <asm/pti.h>
+#include <asm/processor-flags.h>
-static inline void __invpcid(unsigned long pcid, unsigned long addr,
- unsigned long type)
-{
- struct { u64 d[2]; } desc = { { pcid, addr } };
+/*
+ * The x86 feature is called PCID (Process Context IDentifier). It is similar
+ * to what is traditionally called ASID on the RISC processors.
+ *
+ * We don't use the traditional ASID implementation, where each process/mm gets
+ * its own ASID and flush/restart when we run out of ASID space.
+ *
+ * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
+ * that came by on this CPU, allowing cheaper switch_mm between processes on
+ * this CPU.
+ *
+ * We end up with different spaces for different things. To avoid confusion we
+ * use different names for each of them:
+ *
+ * ASID - [0, TLB_NR_DYN_ASIDS-1]
+ * the canonical identifier for an mm
+ *
+ * kPCID - [1, TLB_NR_DYN_ASIDS]
+ * the value we write into the PCID part of CR3; corresponds to the
+ * ASID+1, because PCID 0 is special.
+ *
+ * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ * for KPTI each mm has two address spaces and thus needs two
+ * PCID values, but we can still do with a single ASID denomination
+ * for each mm. Corresponds to kPCID + 2048.
+ *
+ */
- /*
- * The memory clobber is because the whole point is to invalidate
- * stale TLB entries and, especially if we're flushing global
- * mappings, we don't want the compiler to reorder any subsequent
- * memory accesses before the TLB flush.
- *
- * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
- * invpcid (%rcx), %rax in long mode.
- */
- asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
- : : "m" (desc), "a" (type), "c" (&desc) : "memory");
-}
+/* There are 12 bits of space for ASIDS in CR3 */
+#define CR3_HW_ASID_BITS 12
-#define INVPCID_TYPE_INDIV_ADDR 0
-#define INVPCID_TYPE_SINGLE_CTXT 1
-#define INVPCID_TYPE_ALL_INCL_GLOBAL 2
-#define INVPCID_TYPE_ALL_NON_GLOBAL 3
+/*
+ * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * user/kernel switches
+ */
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define PTI_CONSUMED_PCID_BITS 1
+#else
+# define PTI_CONSUMED_PCID_BITS 0
+#endif
-/* Flush all mappings for a given pcid and addr, not including globals. */
-static inline void invpcid_flush_one(unsigned long pcid,
- unsigned long addr)
-{
- __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
-}
+#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)
+
+/*
+ * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid. -1 below to account
+ * for them being zero-based. Another -1 is because PCID 0 is reserved for
+ * use by non-PCID-aware users.
+ */
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
-/* Flush all mappings for a given PCID, not including globals. */
-static inline void invpcid_flush_single_context(unsigned long pcid)
+/*
+ * 6 because 6 should be plenty and struct tlb_state will fit in two cache
+ * lines.
+ */
+#define TLB_NR_DYN_ASIDS 6
+
+/*
+ * Given @asid, compute kPCID
+ */
+static inline u16 kern_pcid(u16 asid)
{
- __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+ VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ /*
+ * Make sure that the dynamic ASID space does not confict with the
+ * bit we are using to switch between user and kernel ASIDs.
+ */
+ BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));
+
+ /*
+ * The ASID being passed in here should have respected the
+ * MAX_ASID_AVAILABLE and thus never have the switch bit set.
+ */
+ VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
+#endif
+ /*
+ * The dynamically-assigned ASIDs that get passed in are small
+ * (<TLB_NR_DYN_ASIDS). They never have the high switch bit set,
+ * so do not bother to clear it.
+ *
+ * If PCID is on, ASID-aware code paths put the ASID+1 into the
+ * PCID bits. This serves two purposes. It prevents a nasty
+ * situation in which PCID-unaware code saves CR3, loads some other
+ * value (with PCID == 0), and then restores CR3, thus corrupting
+ * the TLB for ASID 0 if the saved ASID was nonzero. It also means
+ * that any bugs involving loading a PCID-enabled CR3 with
+ * CR4.PCIDE off will trigger deterministically.
+ */
+ return asid + 1;
}
-/* Flush all mappings, including globals, for all PCIDs. */
-static inline void invpcid_flush_all(void)
+/*
+ * Given @asid, compute uPCID
+ */
+static inline u16 user_pcid(u16 asid)
{
- __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+ u16 ret = kern_pcid(asid);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
+#endif
+ return ret;
}
-/* Flush all mappings for all PCIDs except globals. */
-static inline void invpcid_flush_all_nonglobals(void)
+struct pgd_t;
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
{
- __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+ if (static_cpu_has(X86_FEATURE_PCID)) {
+ return __sme_pa(pgd) | kern_pcid(asid);
+ } else {
+ VM_WARN_ON_ONCE(asid != 0);
+ return __sme_pa(pgd);
+ }
}
-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
{
- u64 new_tlb_gen;
-
- /*
- * Bump the generation count. This also serves as a full barrier
- * that synchronizes with switch_mm(): callers are required to order
- * their read of mm_cpumask after their writes to the paging
- * structures.
- */
- smp_mb__before_atomic();
- new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen);
- smp_mb__after_atomic();
-
- return new_tlb_gen;
+ VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+ VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID));
+ return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
}
#ifdef CONFIG_PARAVIRT
@@ -99,12 +159,6 @@ static inline bool tlb_defer_switch_to_init_mm(void)
return !static_cpu_has(X86_FEATURE_PCID);
}
-/*
- * 6 because 6 should be plenty and struct tlb_state will fit in
- * two cache lines.
- */
-#define TLB_NR_DYN_ASIDS 6
-
struct tlb_context {
u64 ctx_id;
u64 tlb_gen;
@@ -139,6 +193,24 @@ struct tlb_state {
bool is_lazy;
/*
+ * If set we changed the page tables in such a way that we
+ * needed an invalidation of all contexts (aka. PCIDs / ASIDs).
+ * This tells us to go invalidate all the non-loaded ctxs[]
+ * on the next context switch.
+ *
+ * The current ctx was kept up-to-date as it ran and does not
+ * need to be invalidated.
+ */
+ bool invalidate_other;
+
+ /*
+ * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
+ * the corresponding user PCID needs a flush next time we
+ * switch to it; see SWITCH_TO_USER_CR3.
+ */
+ unsigned short user_pcid_flush_mask;
+
+ /*
* Access to this CR4 shadow and to H/W CR4 is protected by
* disabling interrupts when modifying either one.
*/
@@ -173,40 +245,43 @@ static inline void cr4_init_shadow(void)
this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
}
+static inline void __cr4_set(unsigned long cr4)
+{
+ lockdep_assert_irqs_disabled();
+ this_cpu_write(cpu_tlbstate.cr4, cr4);
+ __write_cr4(cr4);
+}
+
/* Set in this cpu's CR4. */
static inline void cr4_set_bits(unsigned long mask)
{
- unsigned long cr4;
+ unsigned long cr4, flags;
+ local_irq_save(flags);
cr4 = this_cpu_read(cpu_tlbstate.cr4);
- if ((cr4 | mask) != cr4) {
- cr4 |= mask;
- this_cpu_write(cpu_tlbstate.cr4, cr4);
- __write_cr4(cr4);
- }
+ if ((cr4 | mask) != cr4)
+ __cr4_set(cr4 | mask);
+ local_irq_restore(flags);
}
/* Clear in this cpu's CR4. */
static inline void cr4_clear_bits(unsigned long mask)
{
- unsigned long cr4;
+ unsigned long cr4, flags;
+ local_irq_save(flags);
cr4 = this_cpu_read(cpu_tlbstate.cr4);
- if ((cr4 & ~mask) != cr4) {
- cr4 &= ~mask;
- this_cpu_write(cpu_tlbstate.cr4, cr4);
- __write_cr4(cr4);
- }
+ if ((cr4 & ~mask) != cr4)
+ __cr4_set(cr4 & ~mask);
+ local_irq_restore(flags);
}
-static inline void cr4_toggle_bits(unsigned long mask)
+static inline void cr4_toggle_bits_irqsoff(unsigned long mask)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
- cr4 ^= mask;
- this_cpu_write(cpu_tlbstate.cr4, cr4);
- __write_cr4(cr4);
+ __cr4_set(cr4 ^ mask);
}
/* Read the CR4 shadow. */
@@ -216,6 +291,14 @@ static inline unsigned long cr4_read_shadow(void)
}
/*
+ * Mark all other ASIDs as invalid, preserves the current.
+ */
+static inline void invalidate_other_asid(void)
+{
+ this_cpu_write(cpu_tlbstate.invalidate_other, true);
+}
+
+/*
* Save some of cr4 feature set we're using (e.g. Pentium 4MB
* enable and PPro Global page enable), so that any CPU's that boot
* up after us can get the correct flags. This should only be used
@@ -234,37 +317,63 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
extern void initialize_tlbstate_and_flush(void);
-static inline void __native_flush_tlb(void)
+/*
+ * Given an ASID, flush the corresponding user ASID. We can delay this
+ * until the next time we switch to it.
+ *
+ * See SWITCH_TO_USER_CR3.
+ */
+static inline void invalidate_user_asid(u16 asid)
{
+ /* There is no user ASID if address space separation is off */
+ if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ return;
+
/*
- * If current->mm == NULL then we borrow a mm which may change during a
- * task switch and therefore we must not be preempted while we write CR3
- * back:
+ * We only have a single ASID if PCID is off and the CR3
+ * write will have flushed it.
*/
- preempt_disable();
- native_write_cr3(__native_read_cr3());
- preempt_enable();
+ if (!cpu_feature_enabled(X86_FEATURE_PCID))
+ return;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ __set_bit(kern_pcid(asid),
+ (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
}
-static inline void __native_flush_tlb_global_irq_disabled(void)
+/*
+ * flush the entire current user mapping
+ */
+static inline void __native_flush_tlb(void)
{
- unsigned long cr4;
+ /*
+ * Preemption or interrupts must be disabled to protect the access
+ * to the per CPU variable and to prevent being preempted between
+ * read_cr3() and write_cr3().
+ */
+ WARN_ON_ONCE(preemptible());
- cr4 = this_cpu_read(cpu_tlbstate.cr4);
- /* clear PGE */
- native_write_cr4(cr4 & ~X86_CR4_PGE);
- /* write old PGE again and flush TLBs */
- native_write_cr4(cr4);
+ invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
+
+ /* If current->mm == NULL then the read_cr3() "borrows" an mm */
+ native_write_cr3(__native_read_cr3());
}
+/*
+ * flush everything
+ */
static inline void __native_flush_tlb_global(void)
{
- unsigned long flags;
+ unsigned long cr4, flags;
if (static_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
+ *
+ * Note, this works with CR4.PCIDE=0 or 1.
*/
invpcid_flush_all();
return;
@@ -277,36 +386,69 @@ static inline void __native_flush_tlb_global(void)
*/
raw_local_irq_save(flags);
- __native_flush_tlb_global_irq_disabled();
+ cr4 = this_cpu_read(cpu_tlbstate.cr4);
+ /* toggle PGE */
+ native_write_cr4(cr4 ^ X86_CR4_PGE);
+ /* write old PGE again and flush TLBs */
+ native_write_cr4(cr4);
raw_local_irq_restore(flags);
}
+/*
+ * flush one page in the user mapping
+ */
static inline void __native_flush_tlb_single(unsigned long addr)
{
+ u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ /*
+ * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
+ * Just use invalidate_user_asid() in case we are called early.
+ */
+ if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
+ invalidate_user_asid(loaded_mm_asid);
+ else
+ invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
}
+/*
+ * flush everything
+ */
static inline void __flush_tlb_all(void)
{
- if (boot_cpu_has(X86_FEATURE_PGE))
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
__flush_tlb_global();
- else
+ } else {
+ /*
+ * !PGE -> !PCID (setup_pcid()), thus every flush is total.
+ */
__flush_tlb();
-
- /*
- * Note: if we somehow had PCID but not PGE, then this wouldn't work --
- * we'd end up flushing kernel translations for the current ASID but
- * we might fail to flush kernel translations for other cached ASIDs.
- *
- * To avoid this issue, we force PCID off if PGE is off.
- */
+ }
}
+/*
+ * flush one page in the kernel mapping
+ */
static inline void __flush_tlb_one(unsigned long addr)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ /*
+ * __flush_tlb_single() will have cleared the TLB entry for this ASID,
+ * but since kernel space is replicated across all, we must also
+ * invalidate all others.
+ */
+ invalidate_other_asid();
}
#define TLB_FLUSH_ALL -1UL
@@ -367,6 +509,17 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info);
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+{
+ /*
+ * Bump the generation count. This also serves as a full barrier
+ * that synchronizes with switch_mm(): callers are required to order
+ * their read of mm_cpumask after their writes to the paging
+ * structures.
+ */
+ return atomic64_inc_return(&mm->context.tlb_gen);
+}
+
static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
struct mm_struct *mm)
{
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 84b9ec0c1bc0..22647a642e98 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -283,34 +283,34 @@ TRACE_EVENT(vector_alloc_managed,
DECLARE_EVENT_CLASS(vector_activate,
TP_PROTO(unsigned int irq, bool is_managed, bool can_reserve,
- bool early),
+ bool reserve),
- TP_ARGS(irq, is_managed, can_reserve, early),
+ TP_ARGS(irq, is_managed, can_reserve, reserve),
TP_STRUCT__entry(
__field( unsigned int, irq )
__field( bool, is_managed )
__field( bool, can_reserve )
- __field( bool, early )
+ __field( bool, reserve )
),
TP_fast_assign(
__entry->irq = irq;
__entry->is_managed = is_managed;
__entry->can_reserve = can_reserve;
- __entry->early = early;
+ __entry->reserve = reserve;
),
- TP_printk("irq=%u is_managed=%d can_reserve=%d early=%d",
+ TP_printk("irq=%u is_managed=%d can_reserve=%d reserve=%d",
__entry->irq, __entry->is_managed, __entry->can_reserve,
- __entry->early)
+ __entry->reserve)
);
#define DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(name) \
DEFINE_EVENT_FN(vector_activate, name, \
TP_PROTO(unsigned int irq, bool is_managed, \
- bool can_reserve, bool early), \
- TP_ARGS(irq, is_managed, can_reserve, early), NULL, NULL); \
+ bool can_reserve, bool reserve), \
+ TP_ARGS(irq, is_managed, can_reserve, reserve), NULL, NULL); \
DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_activate);
DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_deactivate);
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 1fadd310ff68..3de69330e6c5 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long);
dotraplinkage void do_stack_segment(struct pt_regs *, long);
#ifdef CONFIG_X86_64
dotraplinkage void do_double_fault(struct pt_regs *, long);
-asmlinkage struct pt_regs *sync_regs(struct pt_regs *);
#endif
dotraplinkage void do_general_protection(struct pt_regs *, long);
dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
@@ -89,6 +88,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *, long);
#endif
+dotraplinkage void do_mce(struct pt_regs *, long);
static inline int get_si_code(unsigned long condition)
{
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index e9cc6fe1fc6f..1f86e1b0a5cd 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -7,6 +7,9 @@
#include <asm/ptrace.h>
#include <asm/stacktrace.h>
+#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip))
+#define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET)
+
struct unwind_state {
struct stack_info stack_info;
unsigned long stack_mask;
@@ -52,15 +55,28 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
}
#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+/*
+ * If 'partial' returns true, only the iret frame registers are valid.
+ */
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state,
+ bool *partial)
{
if (unwind_done(state))
return NULL;
+ if (partial) {
+#ifdef CONFIG_UNWINDER_ORC
+ *partial = !state->full_regs;
+#else
+ *partial = false;
+#endif
+ }
+
return state->regs;
}
#else
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state,
+ bool *partial)
{
return NULL;
}
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 74f4c2ff6427..d8bfa98fca98 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -53,6 +53,10 @@ struct arch_uprobe {
u8 fixups;
u8 ilen;
} defparam;
+ struct {
+ u8 reg_offset; /* to the start of pt_regs */
+ u8 ilen;
+ } push;
};
};
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 7cac79802ad2..7803114aa140 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -48,7 +48,6 @@
#define UV2_NET_ENDPOINT_INTD 0x28
#define UV_NET_ENDPOINT_INTD (is_uv1_hub() ? \
UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD)
-#define UV_DESC_PSHIFT 49
#define UV_PAYLOADQ_GNODE_SHIFT 49
#define UV_PTC_BASENAME "sgi_uv/ptc_statistics"
#define UV_BAU_BASENAME "sgi_uv/bau_tunables"
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 036e26d63d9a..44cf6d6deb7a 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -241,6 +241,7 @@ static inline int uv_hub_info_check(int version)
#define UV2_HUB_REVISION_BASE 3
#define UV3_HUB_REVISION_BASE 5
#define UV4_HUB_REVISION_BASE 7
+#define UV4A_HUB_REVISION_BASE 8 /* UV4 (fixed) rev 2 */
#ifdef UV1_HUB_IS_SUPPORTED
static inline int is_uv1_hub(void)
@@ -280,6 +281,19 @@ static inline int is_uv3_hub(void)
}
#endif
+/* First test "is UV4A", then "is UV4" */
+#ifdef UV4A_HUB_IS_SUPPORTED
+static inline int is_uv4a_hub(void)
+{
+ return (uv_hub_info->hub_revision >= UV4A_HUB_REVISION_BASE);
+}
+#else
+static inline int is_uv4a_hub(void)
+{
+ return 0;
+}
+#endif
+
#ifdef UV4_HUB_IS_SUPPORTED
static inline int is_uv4_hub(void)
{
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 548d684a7960..ecb9ddef128f 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -39,9 +39,11 @@
* #define UV2Hxxx b
* #define UV3Hxxx c
* #define UV4Hxxx d
+ * #define UV4AHxxx e
* #define UVHxxx (is_uv1_hub() ? UV1Hxxx :
* (is_uv2_hub() ? UV2Hxxx :
* (is_uv3_hub() ? UV3Hxxx :
+ * (is_uv4a_hub() ? UV4AHxxx :
* UV4Hxxx))
*
* If the MMR exists on all hub types > 1 but have different addresses, the
@@ -49,8 +51,10 @@
* #define UV2Hxxx b
* #define UV3Hxxx c
* #define UV4Hxxx d
+ * #define UV4AHxxx e
* #define UVHxxx (is_uv2_hub() ? UV2Hxxx :
* (is_uv3_hub() ? UV3Hxxx :
+ * (is_uv4a_hub() ? UV4AHxxx :
* UV4Hxxx))
*
* union uvh_xxx {
@@ -63,6 +67,7 @@
* } s2;
* struct uv3h_xxx_s { # Full UV3 definition (*)
* } s3;
+ * (NOTE: No struct uv4ah_xxx_s members exist)
* struct uv4h_xxx_s { # Full UV4 definition (*)
* } s4;
* };
@@ -99,6 +104,7 @@
#define UV2_HUB_IS_SUPPORTED 1
#define UV3_HUB_IS_SUPPORTED 1
#define UV4_HUB_IS_SUPPORTED 1
+#define UV4A_HUB_IS_SUPPORTED 1
/* Error function to catch undefined references */
extern unsigned long uv_undefined(char *str);
@@ -2779,35 +2785,47 @@ union uvh_lb_bau_sb_activation_status_1_u {
/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_32)
#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 49
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK 0x7ffe000000000000UL
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 49
#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK 0x7ffe000000000000UL
-
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 49
#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK 0x7ffe000000000000UL
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 49
#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK 0x7ffe000000000000UL
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 49
#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x00003ffffffff000UL
-
-
-union uvh_lb_bau_sb_descriptor_base_u {
- unsigned long v;
- struct uvh_lb_bau_sb_descriptor_base_s {
- unsigned long rsvd_0_11:12;
- unsigned long rsvd_12_48:37;
- unsigned long node_id:14; /* RW */
- unsigned long rsvd_63:1;
- } s;
- struct uv4h_lb_bau_sb_descriptor_base_s {
- unsigned long rsvd_0_11:12;
- unsigned long page_address:34; /* RW */
- unsigned long rsvd_46_48:3;
- unsigned long node_id:14; /* RW */
- unsigned long rsvd_63:1;
- } s4;
-};
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK 0x7ffe000000000000UL
+
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 53
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000ffffffffff000UL
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK 0xffe0000000000000UL
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT ( \
+ is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT : \
+ is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT : \
+ is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT : \
+ is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT : \
+ /*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT)
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK ( \
+ is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK : \
+ is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK : \
+ is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK : \
+ is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK : \
+ /*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK)
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK ( \
+ is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK : \
+ is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK : \
+ is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK : \
+ is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK : \
+ /*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK)
/* ========================================================================= */
/* UVH_NODE_ID */
@@ -3031,6 +3049,41 @@ union uvh_node_present_table_u {
#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
unsigned long v;
@@ -3042,6 +3095,46 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
unsigned long rsvd_53_62:10;
unsigned long enable:1; /* RW */
} s;
+ struct uv1h_rh_gam_alias210_overlay_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s1;
+ struct uvxh_rh_gam_alias210_overlay_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } sx;
+ struct uv2h_rh_gam_alias210_overlay_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s2;
+ struct uv3h_rh_gam_alias210_overlay_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s3;
+ struct uv4h_rh_gam_alias210_overlay_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s4;
};
/* ========================================================================= */
@@ -3064,6 +3157,41 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
unsigned long v;
@@ -3075,6 +3203,46 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
unsigned long rsvd_53_62:10;
unsigned long enable:1; /* RW */
} s;
+ struct uv1h_rh_gam_alias210_overlay_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s1;
+ struct uvxh_rh_gam_alias210_overlay_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } sx;
+ struct uv2h_rh_gam_alias210_overlay_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s2;
+ struct uv3h_rh_gam_alias210_overlay_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s3;
+ struct uv4h_rh_gam_alias210_overlay_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s4;
};
/* ========================================================================= */
@@ -3097,6 +3265,41 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
unsigned long v;
@@ -3108,6 +3311,46 @@ union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
unsigned long rsvd_53_62:10;
unsigned long enable:1; /* RW */
} s;
+ struct uv1h_rh_gam_alias210_overlay_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s1;
+ struct uvxh_rh_gam_alias210_overlay_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } sx;
+ struct uv2h_rh_gam_alias210_overlay_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s2;
+ struct uv3h_rh_gam_alias210_overlay_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s3;
+ struct uv4h_rh_gam_alias210_overlay_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long base:8; /* RW */
+ unsigned long rsvd_32_47:16;
+ unsigned long m_alias:5; /* RW */
+ unsigned long rsvd_53_62:10;
+ unsigned long enable:1; /* RW */
+ } s4;
};
/* ========================================================================= */
@@ -3126,6 +3369,21 @@ union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
unsigned long v;
@@ -3134,6 +3392,31 @@ union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
unsigned long dest_base:22; /* RW */
unsigned long rsvd_46_63:18;
} s;
+ struct uv1h_rh_gam_alias210_redirect_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s1;
+ struct uvxh_rh_gam_alias210_redirect_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } sx;
+ struct uv2h_rh_gam_alias210_redirect_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s2;
+ struct uv3h_rh_gam_alias210_redirect_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s3;
+ struct uv4h_rh_gam_alias210_redirect_config_0_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s4;
};
/* ========================================================================= */
@@ -3152,6 +3435,21 @@ union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
unsigned long v;
@@ -3160,6 +3458,31 @@ union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
unsigned long dest_base:22; /* RW */
unsigned long rsvd_46_63:18;
} s;
+ struct uv1h_rh_gam_alias210_redirect_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s1;
+ struct uvxh_rh_gam_alias210_redirect_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } sx;
+ struct uv2h_rh_gam_alias210_redirect_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s2;
+ struct uv3h_rh_gam_alias210_redirect_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s3;
+ struct uv4h_rh_gam_alias210_redirect_config_1_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s4;
};
/* ========================================================================= */
@@ -3178,6 +3501,21 @@ union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
unsigned long v;
@@ -3186,6 +3524,31 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
unsigned long dest_base:22; /* RW */
unsigned long rsvd_46_63:18;
} s;
+ struct uv1h_rh_gam_alias210_redirect_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s1;
+ struct uvxh_rh_gam_alias210_redirect_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } sx;
+ struct uv2h_rh_gam_alias210_redirect_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s2;
+ struct uv3h_rh_gam_alias210_redirect_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s3;
+ struct uv4h_rh_gam_alias210_redirect_config_2_mmr_s {
+ unsigned long rsvd_0_23:24;
+ unsigned long dest_base:22; /* RW */
+ unsigned long rsvd_46_63:18;
+ } s4;
};
/* ========================================================================= */
@@ -3384,6 +3747,162 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
};
/* ========================================================================= */
+/* UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR uv_undefined("UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR")
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR uv_undefined("UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR")
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x1603000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x483000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR ( \
+ is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR : \
+ is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR : \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR)
+
+
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT 26
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT 46
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT 26
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT 46
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT 52
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK 0x000ffffffc000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK 0x03f0000000000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK)
+
+union uvh_rh_gam_mmioh_overlay_config0_mmr_u {
+ unsigned long v;
+ struct uv3h_rh_gam_mmioh_overlay_config0_mmr_s {
+ unsigned long rsvd_0_25:26;
+ unsigned long base:20; /* RW */
+ unsigned long m_io:6; /* RW */
+ unsigned long n_io:4;
+ unsigned long rsvd_56_62:7;
+ unsigned long enable:1; /* RW */
+ } s3;
+ struct uv4h_rh_gam_mmioh_overlay_config0_mmr_s {
+ unsigned long rsvd_0_25:26;
+ unsigned long base:20; /* RW */
+ unsigned long m_io:6; /* RW */
+ unsigned long n_io:4;
+ unsigned long rsvd_56_62:7;
+ unsigned long enable:1; /* RW */
+ } s4;
+ struct uv4ah_rh_gam_mmioh_overlay_config0_mmr_s {
+ unsigned long rsvd_0_25:26;
+ unsigned long base:26; /* RW */
+ unsigned long m_io:6; /* RW */
+ unsigned long n_io:4;
+ unsigned long undef_62:1; /* Undefined */
+ unsigned long enable:1; /* RW */
+ } s4a;
+};
+
+/* ========================================================================= */
+/* UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR")
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR")
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x1603000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x483000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR ( \
+ is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR : \
+ is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR : \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR)
+
+
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT 26
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT 46
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT 26
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT 46
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT 52
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK 0x000ffffffc000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK 0x03f0000000000000UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK)
+
+union uvh_rh_gam_mmioh_overlay_config1_mmr_u {
+ unsigned long v;
+ struct uv3h_rh_gam_mmioh_overlay_config1_mmr_s {
+ unsigned long rsvd_0_25:26;
+ unsigned long base:20; /* RW */
+ unsigned long m_io:6; /* RW */
+ unsigned long n_io:4;
+ unsigned long rsvd_56_62:7;
+ unsigned long enable:1; /* RW */
+ } s3;
+ struct uv4h_rh_gam_mmioh_overlay_config1_mmr_s {
+ unsigned long rsvd_0_25:26;
+ unsigned long base:20; /* RW */
+ unsigned long m_io:6; /* RW */
+ unsigned long n_io:4;
+ unsigned long rsvd_56_62:7;
+ unsigned long enable:1; /* RW */
+ } s4;
+ struct uv4ah_rh_gam_mmioh_overlay_config1_mmr_s {
+ unsigned long rsvd_0_25:26;
+ unsigned long base:26; /* RW */
+ unsigned long m_io:6; /* RW */
+ unsigned long n_io:4;
+ unsigned long undef_62:1; /* Undefined */
+ unsigned long enable:1; /* RW */
+ } s4a;
+};
+
+/* ========================================================================= */
/* UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR */
/* ========================================================================= */
#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
@@ -3438,6 +3957,112 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u {
};
/* ========================================================================= */
+/* UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR 0x1603800UL
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR 0x483800UL
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR ( \
+ is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR : \
+ is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR : \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR)
+
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH 128
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH 128
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH ( \
+ is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH : \
+ is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH : \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH)
+
+
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000000fffUL
+
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK)
+
+union uvh_rh_gam_mmioh_redirect_config0_mmr_u {
+ unsigned long v;
+ struct uv3h_rh_gam_mmioh_redirect_config0_mmr_s {
+ unsigned long nasid:15; /* RW */
+ unsigned long rsvd_15_63:49;
+ } s3;
+ struct uv4h_rh_gam_mmioh_redirect_config0_mmr_s {
+ unsigned long nasid:15; /* RW */
+ unsigned long rsvd_15_63:49;
+ } s4;
+ struct uv4ah_rh_gam_mmioh_redirect_config0_mmr_s {
+ unsigned long nasid:12; /* RW */
+ unsigned long rsvd_12_63:52;
+ } s4a;
+};
+
+/* ========================================================================= */
+/* UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR 0x1604800UL
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR 0x484800UL
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR ( \
+ is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR : \
+ is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR : \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR)
+
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH 128
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH 128
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH ( \
+ is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH : \
+ is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH : \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH)
+
+
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000000fffUL
+
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK ( \
+ is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK : \
+ is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK : \
+ /*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK)
+
+union uvh_rh_gam_mmioh_redirect_config1_mmr_u {
+ unsigned long v;
+ struct uv3h_rh_gam_mmioh_redirect_config1_mmr_s {
+ unsigned long nasid:15; /* RW */
+ unsigned long rsvd_15_63:49;
+ } s3;
+ struct uv4h_rh_gam_mmioh_redirect_config1_mmr_s {
+ unsigned long nasid:15; /* RW */
+ unsigned long rsvd_15_63:49;
+ } s4;
+ struct uv4ah_rh_gam_mmioh_redirect_config1_mmr_s {
+ unsigned long nasid:12; /* RW */
+ unsigned long rsvd_12_63:52;
+ } s4a;
+};
+
+/* ========================================================================= */
/* UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR */
/* ========================================================================= */
#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
@@ -4138,88 +4763,6 @@ union uv3h_gr0_gam_gr_config_u {
};
/* ========================================================================= */
-/* UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x1603000UL
-
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT 26
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT 46
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK 0x00003ffffc000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK 0x000fc00000000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uv3h_rh_gam_mmioh_overlay_config0_mmr_u {
- unsigned long v;
- struct uv3h_rh_gam_mmioh_overlay_config0_mmr_s {
- unsigned long rsvd_0_25:26;
- unsigned long base:20; /* RW */
- unsigned long m_io:6; /* RW */
- unsigned long n_io:4;
- unsigned long rsvd_56_62:7;
- unsigned long enable:1; /* RW */
- } s3;
-};
-
-/* ========================================================================= */
-/* UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x1604000UL
-
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT 26
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT 46
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK 0x00003ffffc000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK 0x000fc00000000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uv3h_rh_gam_mmioh_overlay_config1_mmr_u {
- unsigned long v;
- struct uv3h_rh_gam_mmioh_overlay_config1_mmr_s {
- unsigned long rsvd_0_25:26;
- unsigned long base:20; /* RW */
- unsigned long m_io:6; /* RW */
- unsigned long n_io:4;
- unsigned long rsvd_56_62:7;
- unsigned long enable:1; /* RW */
- } s3;
-};
-
-/* ========================================================================= */
-/* UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR 0x1603800UL
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH 128
-
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
-
-union uv3h_rh_gam_mmioh_redirect_config0_mmr_u {
- unsigned long v;
- struct uv3h_rh_gam_mmioh_redirect_config0_mmr_s {
- unsigned long nasid:15; /* RW */
- unsigned long rsvd_15_63:49;
- } s3;
-};
-
-/* ========================================================================= */
-/* UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR 0x1604800UL
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH 128
-
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
-
-union uv3h_rh_gam_mmioh_redirect_config1_mmr_u {
- unsigned long v;
- struct uv3h_rh_gam_mmioh_redirect_config1_mmr_s {
- unsigned long nasid:15; /* RW */
- unsigned long rsvd_15_63:49;
- } s3;
-};
-
-/* ========================================================================= */
/* UV4H_LB_PROC_INTD_QUEUE_FIRST */
/* ========================================================================= */
#define UV4H_LB_PROC_INTD_QUEUE_FIRST 0xa4100UL
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index d9a7c659009c..b986b2ca688a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -7,6 +7,7 @@
#ifdef CONFIG_X86_VSYSCALL_EMULATION
extern void map_vsyscall(void);
+extern void set_vsyscall_pgtable_user_bits(pgd_t *root);
/*
* Called on instruction fetch fault in vsyscall page.
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index aa4747569e23..fc2f082ac635 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -212,6 +212,7 @@ enum x86_legacy_i8042_state {
struct x86_legacy_features {
enum x86_legacy_i8042_state i8042;
int rtc;
+ int warm_reset;
int no_vga;
int reserve_bios_regions;
struct x86_legacy_devices devices;
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 7cb282e9e587..bfd882617613 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -44,6 +44,7 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/smap.h>
+#include <asm/nospec-branch.h>
#include <xen/interface/xen.h>
#include <xen/interface/sched.h>
@@ -217,9 +218,9 @@ privcmd_call(unsigned call,
__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
stac();
- asm volatile("call *%[call]"
+ asm volatile(CALL_NOSPEC
: __HYPERCALL_5PARAM
- : [call] "a" (&hypercall_page[call])
+ : [thunk_target] "a" (&hypercall_page[call])
: __HYPERCALL_CLOBBER5);
clac();
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index e9f6b8e332bd..322681622d1e 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generated-y += unistd_32.h
generated-y += unistd_64.h
generated-y += unistd_x32.h
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index afdd5ae0fcc4..aebf60357758 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -9,6 +9,7 @@
#define SETUP_PCI 3
#define SETUP_EFI 4
#define SETUP_APPLE_PROPERTIES 5
+#define SETUP_JAILHOUSE 6
/* ram_size flags */
#define RAMDISK_IMAGE_START_MASK 0x07FF
@@ -126,6 +127,27 @@ struct boot_e820_entry {
__u32 type;
} __attribute__((packed));
+/*
+ * Smallest compatible version of jailhouse_setup_data required by this kernel.
+ */
+#define JAILHOUSE_SETUP_REQUIRED_VERSION 1
+
+/*
+ * The boot loader is passing platform information via this Jailhouse-specific
+ * setup data structure.
+ */
+struct jailhouse_setup_data {
+ u16 version;
+ u16 compatible_version;
+ u16 pm_timer_address;
+ u16 num_cpus;
+ u64 pci_mmconfig_base;
+ u32 tsc_khz;
+ u32 apic_khz;
+ u8 standard_ioapic;
+ u8 cpu_ids[255];
+} __attribute__((packed));
+
/* The so-called "zeropage" */
struct boot_params {
struct screen_info screen_info; /* 0x000 */
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 7e1e730396ae..bcba3c643e63 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -78,7 +78,12 @@
#define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT)
#define X86_CR3_PCD_BIT 4 /* Page Cache Disable */
#define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */
+
+#define X86_CR3_PCID_BITS 12
+#define X86_CR3_PCID_MASK (_AC((1UL << X86_CR3_PCID_BITS) - 1, UL))
+
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
/*
* Intel CPU features in CR4
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 81bb565f4497..29786c87e864 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,10 +29,13 @@ KASAN_SANITIZE_stacktrace.o := n
KASAN_SANITIZE_paravirt.o := n
OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y
-OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y
OBJECT_FILES_NON_STANDARD_test_nx.o := y
OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o := y
+ifdef CONFIG_FRAME_POINTER
+OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y
+endif
+
# If instrumentation of this dir is enabled, boot hangs during first second.
# Probably could be more selective here, but note that files related to irqs,
# boot, dumpstack/stacktrace, etc are either non-interesting or can lead to
@@ -112,6 +115,8 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
+obj-$(CONFIG_JAILHOUSE_GUEST) += jailhouse.o
+
obj-$(CONFIG_EISA) += eisa.o
obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index f4c463df8b08..ec3a286163c3 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -68,8 +68,9 @@ int acpi_ioapic;
int acpi_strict;
int acpi_disable_cmcff;
+/* ACPI SCI override configuration */
u8 acpi_sci_flags __initdata;
-int acpi_sci_override_gsi __initdata;
+u32 acpi_sci_override_gsi __initdata = INVALID_ACPI_IRQ;
int acpi_skip_timer_override __initdata;
int acpi_use_timer_override __initdata;
int acpi_fix_pin2_polarity __initdata;
@@ -112,8 +113,6 @@ static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = {
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
};
-#define ACPI_INVALID_GSI INT_MIN
-
/*
* This is just a simple wrapper around early_memremap(),
* with sanity checks for phys == 0 and size == 0.
@@ -372,7 +371,7 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
* and acpi_isa_irq_to_gsi() may give wrong result.
*/
if (gsi < nr_legacy_irqs() && isa_irq_to_gsi[gsi] == gsi)
- isa_irq_to_gsi[gsi] = ACPI_INVALID_GSI;
+ isa_irq_to_gsi[gsi] = INVALID_ACPI_IRQ;
isa_irq_to_gsi[bus_irq] = gsi;
}
@@ -620,24 +619,24 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
}
rc = acpi_get_override_irq(gsi, &trigger, &polarity);
- if (rc == 0) {
- trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
- polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
- irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
- if (irq >= 0) {
- *irqp = irq;
- return 0;
- }
- }
+ if (rc)
+ return rc;
- return -1;
+ trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+ polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+ irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
+ if (irq < 0)
+ return irq;
+
+ *irqp = irq;
+ return 0;
}
EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi)
{
if (isa_irq < nr_legacy_irqs() &&
- isa_irq_to_gsi[isa_irq] != ACPI_INVALID_GSI) {
+ isa_irq_to_gsi[isa_irq] != INVALID_ACPI_IRQ) {
*gsi = isa_irq_to_gsi[isa_irq];
return 0;
}
@@ -676,8 +675,7 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
mutex_lock(&acpi_ioapic_lock);
irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
/* Don't set up the ACPI SCI because it's already set up */
- if (irq >= 0 && enable_update_mptable &&
- acpi_gbl_FADT.sci_interrupt != gsi)
+ if (irq >= 0 && enable_update_mptable && gsi != acpi_gbl_FADT.sci_interrupt)
mp_config_acpi_gsi(dev, gsi, trigger, polarity);
mutex_unlock(&acpi_ioapic_lock);
#endif
@@ -1211,8 +1209,9 @@ static int __init acpi_parse_madt_ioapic_entries(void)
/*
* If BIOS did not supply an INT_SRC_OVR for the SCI
* pretend we got one so we can set the SCI flags.
+ * But ignore setting up SCI on hardware reduced platforms.
*/
- if (!acpi_sci_override_gsi)
+ if (acpi_sci_override_gsi == INVALID_ACPI_IRQ && !acpi_gbl_reduced_hardware)
acpi_sci_ioapic_setup(acpi_gbl_FADT.sci_interrupt, 0, 0,
acpi_gbl_FADT.sci_interrupt);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 7188aea91549..f1915b744052 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -138,6 +138,8 @@ static int __init acpi_sleep_setup(char *str)
acpi_nvs_nosave_s3();
if (strncmp(str, "old_ordering", 12) == 0)
acpi_old_suspend_ordering();
+ if (strncmp(str, "nobl", 4) == 0)
+ acpi_sleep_no_blacklist();
str = strchr(str, ',');
if (str != NULL)
str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index dbaf14d69ebd..30571fdaaf6f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -298,7 +298,7 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
tgt_rip = next_rip + o_dspl;
n_dspl = tgt_rip - orig_insn;
- DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl);
+ DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl);
if (tgt_rip - orig_insn >= 0) {
if (n_dspl - 2 <= 127)
@@ -344,15 +344,18 @@ done:
static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
{
unsigned long flags;
+ int i;
- if (instr[0] != 0x90)
- return;
+ for (i = 0; i < a->padlen; i++) {
+ if (instr[i] != 0x90)
+ return;
+ }
local_irq_save(flags);
add_nops(instr + (a->instrlen - a->padlen), a->padlen);
local_irq_restore(flags);
- DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
+ DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ",
instr, a->instrlen - a->padlen, a->padlen);
}
@@ -373,7 +376,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
u8 *instr, *replacement;
u8 insnbuf[MAX_PATCH_LEN];
- DPRINTK("alt table %p -> %p", start, end);
+ DPRINTK("alt table %px, -> %px", start, end);
/*
* The scan order should be from start to end. A later scanned
* alternative code can overwrite previously scanned alternative code.
@@ -397,14 +400,14 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
continue;
}
- DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d",
+ DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d",
a->cpuid >> 5,
a->cpuid & 0x1f,
instr, a->instrlen,
replacement, a->replacementlen, a->padlen);
- DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr);
- DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement);
+ DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);
+ DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
memcpy(insnbuf, replacement, a->replacementlen);
insnbuf_sz = a->replacementlen;
@@ -430,7 +433,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
a->instrlen - a->replacementlen);
insnbuf_sz += a->instrlen - a->replacementlen;
}
- DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr);
+ DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr);
text_poke_early(instr, insnbuf, insnbuf_sz);
}
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index f5d92bc3b884..2c4d5ece7456 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -30,6 +30,7 @@
#include <asm/dma.h>
#include <asm/amd_nb.h>
#include <asm/x86_init.h>
+#include <linux/crash_dump.h>
/*
* Using 512M as goal, in case kexec will load kernel_big
@@ -56,6 +57,33 @@ int fallback_aper_force __initdata;
int fix_aperture __initdata = 1;
+#ifdef CONFIG_PROC_VMCORE
+/*
+ * If the first kernel maps the aperture over e820 RAM, the kdump kernel will
+ * use the same range because it will remain configured in the northbridge.
+ * Trying to dump this area via /proc/vmcore may crash the machine, so exclude
+ * it from vmcore.
+ */
+static unsigned long aperture_pfn_start, aperture_page_count;
+
+static int gart_oldmem_pfn_is_ram(unsigned long pfn)
+{
+ return likely((pfn < aperture_pfn_start) ||
+ (pfn >= aperture_pfn_start + aperture_page_count));
+}
+
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+ aperture_pfn_start = aper_base >> PAGE_SHIFT;
+ aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
+ WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram));
+}
+#else
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+}
+#endif
+
/* This code runs before the PCI subsystem is initialized, so just
access the northbridge directly. */
@@ -435,8 +463,16 @@ int __init gart_iommu_hole_init(void)
out:
if (!fix && !fallback_aper_force) {
- if (last_aper_base)
+ if (last_aper_base) {
+ /*
+ * If this is the kdump kernel, the first kernel
+ * may have allocated the range over its e820 RAM
+ * and fixed up the northbridge
+ */
+ exclude_from_vmcore(last_aper_base, last_aper_order);
+
return 1;
+ }
return 0;
}
@@ -473,6 +509,14 @@ out:
return 0;
}
+ /*
+ * If this is the kdump kernel _and_ the first kernel did not
+ * configure the aperture in the northbridge, this range may
+ * overlap with the first kernel's memory. We can't access the
+ * range through vmcore even though it should be part of the dump.
+ */
+ exclude_from_vmcore(aper_alloc, aper_order);
+
/* Fix up the north bridges */
for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
int bus, dev_base, dev_limit;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6e272f3ea984..25ddf02598d2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1286,6 +1286,55 @@ static int __init apic_intr_mode_select(void)
return APIC_SYMMETRIC_IO;
}
+/*
+ * An initial setup of the virtual wire mode.
+ */
+void __init init_bsp_APIC(void)
+{
+ unsigned int value;
+
+ /*
+ * Don't do the setup now if we have a SMP BIOS as the
+ * through-I/O-APIC virtual wire mode might be active.
+ */
+ if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC))
+ return;
+
+ /*
+ * Do not trust the local APIC being empty at bootup.
+ */
+ clear_local_APIC();
+
+ /*
+ * Enable APIC.
+ */
+ value = apic_read(APIC_SPIV);
+ value &= ~APIC_VECTOR_MASK;
+ value |= APIC_SPIV_APIC_ENABLED;
+
+#ifdef CONFIG_X86_32
+ /* This bit is reserved on P4/Xeon and should be cleared */
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+ (boot_cpu_data.x86 == 15))
+ value &= ~APIC_SPIV_FOCUS_DISABLED;
+ else
+#endif
+ value |= APIC_SPIV_FOCUS_DISABLED;
+ value |= SPURIOUS_APIC_VECTOR;
+ apic_write(APIC_SPIV, value);
+
+ /*
+ * Set up the virtual wire mode.
+ */
+ apic_write(APIC_LVT0, APIC_DM_EXTINT);
+ value = APIC_DM_NMI;
+ if (!lapic_is_integrated()) /* 82489DX */
+ value |= APIC_LVT_LEVEL_TRIGGER;
+ if (apic_extnmi == APIC_EXTNMI_NONE)
+ value |= APIC_LVT_MASKED;
+ apic_write(APIC_LVT1, value);
+}
+
/* Init the interrupt delivery mode for the BSP */
void __init apic_intr_mode_init(void)
{
@@ -2626,11 +2675,13 @@ static int __init apic_set_verbosity(char *arg)
apic_verbosity = APIC_DEBUG;
else if (strcmp("verbose", arg) == 0)
apic_verbosity = APIC_VERBOSE;
+#ifdef CONFIG_X86_64
else {
pr_warning("APIC Verbosity level %s not recognised"
" use apic=verbose or apic=debug\n", arg);
return -EINVAL;
}
+#endif
return 0;
}
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index aa85690e9b64..e84c9eb4e5b4 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -19,6 +19,7 @@
#include <asm/smp.h>
#include <asm/apic.h>
#include <asm/ipi.h>
+#include <asm/jailhouse_para.h>
#include <linux/acpi.h>
@@ -84,12 +85,8 @@ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
static void flat_send_IPI_allbutself(int vector)
{
int cpu = smp_processor_id();
-#ifdef CONFIG_HOTPLUG_CPU
- int hotplug = 1;
-#else
- int hotplug = 0;
-#endif
- if (hotplug || vector == NMI_VECTOR) {
+
+ if (IS_ENABLED(CONFIG_HOTPLUG_CPU) || vector == NMI_VECTOR) {
if (!cpumask_equal(cpu_online_mask, cpumask_of(cpu))) {
unsigned long mask = cpumask_bits(cpu_online_mask)[0];
@@ -151,7 +148,7 @@ static struct apic apic_flat __ro_after_init = {
.apic_id_valid = default_apic_id_valid,
.apic_id_registered = flat_apic_id_registered,
- .irq_delivery_mode = dest_LowestPrio,
+ .irq_delivery_mode = dest_Fixed,
.irq_dest_mode = 1, /* logical */
.disable_esr = 0,
@@ -218,6 +215,15 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
return 0;
}
+static void physflat_init_apic_ldr(void)
+{
+ /*
+ * LDR and DFR are not involved in physflat mode, rather:
+ * "In physical destination mode, the destination processor is
+ * specified by its local APIC ID [...]." (Intel SDM, 10.6.2.1)
+ */
+}
+
static void physflat_send_IPI_allbutself(int vector)
{
default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
@@ -230,7 +236,8 @@ static void physflat_send_IPI_all(int vector)
static int physflat_probe(void)
{
- if (apic == &apic_physflat || num_possible_cpus() > 8)
+ if (apic == &apic_physflat || num_possible_cpus() > 8 ||
+ jailhouse_paravirt())
return 1;
return 0;
@@ -251,8 +258,7 @@ static struct apic apic_physflat __ro_after_init = {
.dest_logical = 0,
.check_apicid_used = NULL,
- /* not needed, but shouldn't hurt: */
- .init_apic_ldr = flat_init_apic_ldr,
+ .init_apic_ldr = physflat_init_apic_ldr,
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 7b659c4480c9..5078b5ce63a7 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -110,7 +110,7 @@ struct apic apic_noop __ro_after_init = {
.apic_id_valid = default_apic_id_valid,
.apic_id_registered = noop_apic_id_registered,
- .irq_delivery_mode = dest_LowestPrio,
+ .irq_delivery_mode = dest_Fixed,
/* logical delivery broadcast to all CPUs: */
.irq_dest_mode = 1,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 201579dc5242..8ad2e410974f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -800,18 +800,18 @@ static int irq_polarity(int idx)
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].irqflag & 0x03) {
- case 0:
+ switch (mp_irqs[idx].irqflag & MP_IRQPOL_MASK) {
+ case MP_IRQPOL_DEFAULT:
/* conforms to spec, ie. bus-type dependent polarity */
if (test_bit(bus, mp_bus_not_pci))
return default_ISA_polarity(idx);
else
return default_PCI_polarity(idx);
- case 1:
+ case MP_IRQPOL_ACTIVE_HIGH:
return IOAPIC_POL_HIGH;
- case 2:
+ case MP_IRQPOL_RESERVED:
pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
- case 3:
+ case MP_IRQPOL_ACTIVE_LOW:
default: /* Pointless default required due to do gcc stupidity */
return IOAPIC_POL_LOW;
}
@@ -845,8 +845,8 @@ static int irq_trigger(int idx)
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].irqflag >> 2) & 0x03) {
- case 0:
+ switch (mp_irqs[idx].irqflag & MP_IRQTRIG_MASK) {
+ case MP_IRQTRIG_DEFAULT:
/* conforms to spec, ie. bus-type dependent trigger mode */
if (test_bit(bus, mp_bus_not_pci))
trigger = default_ISA_trigger(idx);
@@ -854,11 +854,11 @@ static int irq_trigger(int idx)
trigger = default_PCI_trigger(idx);
/* Take EISA into account */
return eisa_irq_trigger(idx, bus, trigger);
- case 1:
+ case MP_IRQTRIG_EDGE:
return IOAPIC_EDGE;
- case 2:
+ case MP_IRQTRIG_RESERVED:
pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
- case 3:
+ case MP_IRQTRIG_LEVEL:
default: /* Pointless default required due to do gcc stupidity */
return IOAPIC_LEVEL;
}
@@ -2988,7 +2988,7 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
}
int mp_irqdomain_activate(struct irq_domain *domain,
- struct irq_data *irq_data, bool early)
+ struct irq_data *irq_data, bool reserve)
{
unsigned long flags;
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 9b18be764422..ce503c99f5c4 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -39,17 +39,13 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
((apic->irq_dest_mode == 0) ?
MSI_ADDR_DEST_MODE_PHYSICAL :
MSI_ADDR_DEST_MODE_LOGICAL) |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_ADDR_REDIRECTION_CPU :
- MSI_ADDR_REDIRECTION_LOWPRI) |
+ MSI_ADDR_REDIRECTION_CPU |
MSI_ADDR_DEST_ID(cfg->dest_apicid);
msg->data =
MSI_DATA_TRIGGER_EDGE |
MSI_DATA_LEVEL_ASSERT |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_DATA_DELIVERY_FIXED :
- MSI_DATA_DELIVERY_LOWPRI) |
+ MSI_DATA_DELIVERY_FIXED |
MSI_DATA_VECTOR(cfg->vector);
}
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index fa22017de806..02e8acb134f8 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -105,7 +105,7 @@ static struct apic apic_default __ro_after_init = {
.apic_id_valid = default_apic_id_valid,
.apic_id_registered = default_apic_id_registered,
- .irq_delivery_mode = dest_LowestPrio,
+ .irq_delivery_mode = dest_Fixed,
/* logical delivery broadcast to all CPUs: */
.irq_dest_mode = 1,
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 6a823a25eaff..3cc471beb50b 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -184,6 +184,7 @@ static void reserve_irq_vector_locked(struct irq_data *irqd)
irq_matrix_reserve(vector_matrix);
apicd->can_reserve = true;
apicd->has_reserved = true;
+ irqd_set_can_reserve(irqd);
trace_vector_reserve(irqd->irq, 0);
vector_assign_managed_shutdown(irqd);
}
@@ -368,8 +369,18 @@ static int activate_reserved(struct irq_data *irqd)
int ret;
ret = assign_irq_vector_any_locked(irqd);
- if (!ret)
+ if (!ret) {
apicd->has_reserved = false;
+ /*
+ * Core might have disabled reservation mode after
+ * allocating the irq descriptor. Ideally this should
+ * happen before allocation time, but that would require
+ * completely convoluted ways of transporting that
+ * information.
+ */
+ if (!irqd_can_reserve(irqd))
+ apicd->can_reserve = false;
+ }
return ret;
}
@@ -398,21 +409,21 @@ static int activate_managed(struct irq_data *irqd)
}
static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
- bool early)
+ bool reserve)
{
struct apic_chip_data *apicd = apic_chip_data(irqd);
unsigned long flags;
int ret = 0;
trace_vector_activate(irqd->irq, apicd->is_managed,
- apicd->can_reserve, early);
+ 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 (early || irqd_is_managed_and_shutdown(irqd))
+ if (reserve || irqd_is_managed_and_shutdown(irqd))
vector_assign_managed_shutdown(irqd);
else if (apicd->is_managed)
ret = activate_managed(irqd);
@@ -478,6 +489,7 @@ static bool vector_configure_legacy(unsigned int virq, struct irq_data *irqd,
} else {
/* Release the vector */
apicd->can_reserve = true;
+ irqd_set_can_reserve(irqd);
clear_irq_vector(irqd);
realloc = true;
}
@@ -530,20 +542,23 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
err = assign_irq_vector_policy(irqd, info);
trace_vector_setup(virq + i, false, err);
- if (err)
+ if (err) {
+ irqd->chip_data = NULL;
+ free_apic_chip_data(apicd);
goto error;
+ }
}
return 0;
error:
- x86_vector_free_irqs(domain, virq, i + 1);
+ x86_vector_free_irqs(domain, virq, i);
return err;
}
#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
-void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
- struct irq_data *irqd, int ind)
+static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
+ struct irq_data *irqd, int ind)
{
unsigned int cpu, vector, prev_cpu, prev_vector;
struct apic_chip_data *apicd;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 622f13ca8a94..8b04234e010b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -184,7 +184,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = {
.apic_id_valid = x2apic_apic_id_valid,
.apic_id_registered = x2apic_apic_id_registered,
- .irq_delivery_mode = dest_LowestPrio,
+ .irq_delivery_mode = dest_Fixed,
.irq_dest_mode = 1, /* logical */
.disable_esr = 0,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index e1b8e8bf6b3c..46b675aaf20b 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -137,6 +137,8 @@ static int __init early_get_pnodeid(void)
case UV3_HUB_PART_NUMBER_X:
uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
break;
+
+ /* Update: UV4A has only a modified revision to indicate HUB fixes */
case UV4_HUB_PART_NUMBER:
uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1;
uv_cpuid.gnode_shift = 2; /* min partition is 4 sockets */
@@ -316,6 +318,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
} else if (!strcmp(oem_table_id, "UVH")) {
/* Only UV1 systems: */
uv_system_type = UV_NON_UNIQUE_APIC;
+ x86_platform.legacy.warm_reset = 0;
__this_cpu_write(x2apic_extra_bits, pnodeid << uvh_apicid.s.pnode_shift);
uv_set_apicid_hibit();
uv_apic = 1;
@@ -767,6 +770,7 @@ static __init void map_gru_high(int max_pnode)
return;
}
+ /* Only UV3 has distributed GRU mode */
if (is_uv3_hub() && gru.s3.mode) {
map_gru_distributed(gru.v);
return;
@@ -790,63 +794,61 @@ static __init void map_mmr_high(int max_pnode)
pr_info("UV: MMR disabled\n");
}
-/*
- * This commonality works because both 0 & 1 versions of the MMIOH OVERLAY
- * and REDIRECT MMR regs are exactly the same on UV3.
- */
-struct mmioh_config {
- unsigned long overlay;
- unsigned long redirect;
- char *id;
-};
-
-static __initdata struct mmioh_config mmiohs[] = {
- {
- UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR,
- UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR,
- "MMIOH0"
- },
- {
- UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR,
- UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR,
- "MMIOH1"
- },
-};
-
-/* UV3 & UV4 have identical MMIOH overlay configs */
-static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
+/* UV3/4 have identical MMIOH overlay configs, UV4A is slightly different */
+static __init void map_mmioh_high_uv34(int index, int min_pnode, int max_pnode)
{
- union uv3h_rh_gam_mmioh_overlay_config0_mmr_u overlay;
+ unsigned long overlay;
unsigned long mmr;
unsigned long base;
+ unsigned long nasid_mask;
+ unsigned long m_overlay;
int i, n, shift, m_io, max_io;
int nasid, lnasid, fi, li;
char *id;
- id = mmiohs[index].id;
- overlay.v = uv_read_local_mmr(mmiohs[index].overlay);
-
- pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", id, overlay.v, overlay.s3.base, overlay.s3.m_io);
- if (!overlay.s3.enable) {
+ if (index == 0) {
+ id = "MMIOH0";
+ m_overlay = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR;
+ overlay = uv_read_local_mmr(m_overlay);
+ base = overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK;
+ mmr = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR;
+ m_io = (overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK)
+ >> UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT;
+ shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT;
+ n = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH;
+ nasid_mask = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK;
+ } else {
+ id = "MMIOH1";
+ m_overlay = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR;
+ overlay = uv_read_local_mmr(m_overlay);
+ base = overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK;
+ mmr = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR;
+ m_io = (overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK)
+ >> UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT;
+ shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT;
+ n = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH;
+ nasid_mask = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK;
+ }
+ pr_info("UV: %s overlay 0x%lx base:0x%lx m_io:%d\n", id, overlay, base, m_io);
+ if (!(overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK)) {
pr_info("UV: %s disabled\n", id);
return;
}
- shift = UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT;
- base = (unsigned long)overlay.s3.base;
- m_io = overlay.s3.m_io;
- mmr = mmiohs[index].redirect;
- n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH;
/* Convert to NASID: */
min_pnode *= 2;
max_pnode *= 2;
max_io = lnasid = fi = li = -1;
for (i = 0; i < n; i++) {
- union uv3h_rh_gam_mmioh_redirect_config0_mmr_u redirect;
+ unsigned long m_redirect = mmr + i * 8;
+ unsigned long redirect = uv_read_local_mmr(m_redirect);
+
+ nasid = redirect & nasid_mask;
+ if (i == 0)
+ pr_info("UV: %s redirect base 0x%lx(@0x%lx) 0x%04x\n",
+ id, redirect, m_redirect, nasid);
- redirect.v = uv_read_local_mmr(mmr + i * 8);
- nasid = redirect.s3.nasid;
/* Invalid NASID: */
if (nasid < min_pnode || max_pnode < nasid)
nasid = -1;
@@ -894,8 +896,8 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode)
if (is_uv3_hub() || is_uv4_hub()) {
/* Map both MMIOH regions: */
- map_mmioh_high_uv3(0, min_pnode, max_pnode);
- map_mmioh_high_uv3(1, min_pnode, max_pnode);
+ map_mmioh_high_uv34(0, min_pnode, max_pnode);
+ map_mmioh_high_uv34(1, min_pnode, max_pnode);
return;
}
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 8ea78275480d..76417a9aab73 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -17,6 +17,7 @@
#include <asm/sigframe.h>
#include <asm/bootparam.h>
#include <asm/suspend.h>
+#include <asm/tlbflush.h>
#ifdef CONFIG_XEN
#include <xen/interface/xen.h>
@@ -93,4 +94,13 @@ void common(void) {
BLANK();
DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+
+ /* TLB state for the entry code */
+ OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
+
+ /* Layout info for cpu_entry_area */
+ OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
+ OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
+ OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
+ DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
}
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index dedf428b20b6..fa1261eefa16 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -47,13 +47,8 @@ void foo(void)
BLANK();
/* Offset from the sysenter stack to tss.sp0 */
- DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
- offsetofend(struct tss_struct, SYSENTER_stack));
-
- /* Offset from cpu_tss to SYSENTER_stack */
- OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
- /* Size of SYSENTER_stack */
- DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
+ DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+ offsetofend(struct cpu_entry_area, entry_stack_page.stack));
#ifdef CONFIG_CC_STACKPROTECTOR
BLANK();
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 630212fa9b9d..bf51e51d808d 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -23,6 +23,9 @@ int main(void)
#ifdef CONFIG_PARAVIRT
OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
+#ifdef CONFIG_DEBUG_ENTRY
+ OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl);
+#endif
BLANK();
#endif
@@ -63,6 +66,7 @@ int main(void)
OFFSET(TSS_ist, tss_struct, x86_tss.ist);
OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+ OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
BLANK();
#ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d58184b7cd44..ea831c858195 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -804,8 +804,11 @@ static void init_amd(struct cpuinfo_x86 *c)
case 0x17: init_amd_zn(c); break;
}
- /* Enable workaround for FXSAVE leak */
- if (c->x86 >= 6)
+ /*
+ * Enable workaround for FXSAVE leak on CPUs
+ * without a XSaveErPtr feature
+ */
+ if ((c->x86 >= 6) && (!cpu_has(c, X86_FEATURE_XSAVEERPTR)))
set_cpu_bug(c, X86_BUG_FXSAVE_LEAK);
cpu_detect_cache_sizes(c);
@@ -826,8 +829,32 @@ static void init_amd(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_K8);
if (cpu_has(c, X86_FEATURE_XMM2)) {
- /* MFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+ unsigned long long val;
+ int ret;
+
+ /*
+ * A serializing LFENCE has less overhead than MFENCE, so
+ * use it for execution serialization. On families which
+ * don't have that MSR, LFENCE is already serializing.
+ * msr_set_bit() uses the safe accessors, too, even if the MSR
+ * is not present.
+ */
+ msr_set_bit(MSR_F10H_DECFG,
+ MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+
+ /*
+ * Verify that the MSR write was successful (could be running
+ * under a hypervisor) and only then assume that LFENCE is
+ * serializing.
+ */
+ ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
+ if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
+ /* A serializing LFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+ } else {
+ /* MFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+ }
}
/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ba0b2424c9b0..3bfb2b23d79c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -10,6 +10,11 @@
*/
#include <linux/init.h>
#include <linux/utsname.h>
+#include <linux/cpu.h>
+#include <linux/module.h>
+
+#include <asm/nospec-branch.h>
+#include <asm/cmdline.h>
#include <asm/bugs.h>
#include <asm/processor.h>
#include <asm/processor-flags.h>
@@ -19,6 +24,9 @@
#include <asm/alternative.h>
#include <asm/pgtable.h>
#include <asm/set_memory.h>
+#include <asm/intel-family.h>
+
+static void __init spectre_v2_select_mitigation(void);
void __init check_bugs(void)
{
@@ -29,6 +37,9 @@ void __init check_bugs(void)
print_cpu_info(&boot_cpu_data);
}
+ /* Select the proper spectre mitigation before patching alternatives */
+ spectre_v2_select_mitigation();
+
#ifdef CONFIG_X86_32
/*
* Check whether we are able to run this kernel safely on SMP.
@@ -60,3 +71,249 @@ void __init check_bugs(void)
set_memory_4k((unsigned long)__va(0), 1);
#endif
}
+
+/* The kernel command line selection */
+enum spectre_v2_mitigation_cmd {
+ SPECTRE_V2_CMD_NONE,
+ SPECTRE_V2_CMD_AUTO,
+ SPECTRE_V2_CMD_FORCE,
+ SPECTRE_V2_CMD_RETPOLINE,
+ SPECTRE_V2_CMD_RETPOLINE_GENERIC,
+ SPECTRE_V2_CMD_RETPOLINE_AMD,
+};
+
+static const char *spectre_v2_strings[] = {
+ [SPECTRE_V2_NONE] = "Vulnerable",
+ [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline",
+ [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline",
+ [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline",
+ [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline",
+};
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Spectre V2 : " fmt
+
+static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+
+#ifdef RETPOLINE
+static bool spectre_v2_bad_module;
+
+bool retpoline_module_ok(bool has_retpoline)
+{
+ if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline)
+ return true;
+
+ pr_err("System may be vunerable to spectre v2\n");
+ spectre_v2_bad_module = true;
+ return false;
+}
+
+static inline const char *spectre_v2_module_string(void)
+{
+ return spectre_v2_bad_module ? " - vulnerable module loaded" : "";
+}
+#else
+static inline const char *spectre_v2_module_string(void) { return ""; }
+#endif
+
+static void __init spec2_print_if_insecure(const char *reason)
+{
+ if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+ pr_info("%s\n", reason);
+}
+
+static void __init spec2_print_if_secure(const char *reason)
+{
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+ pr_info("%s\n", reason);
+}
+
+static inline bool retp_compiler(void)
+{
+ return __is_defined(RETPOLINE);
+}
+
+static inline bool match_option(const char *arg, int arglen, const char *opt)
+{
+ int len = strlen(opt);
+
+ return len == arglen && !strncmp(arg, opt, len);
+}
+
+static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
+{
+ char arg[20];
+ int ret;
+
+ ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
+ sizeof(arg));
+ if (ret > 0) {
+ if (match_option(arg, ret, "off")) {
+ goto disable;
+ } else if (match_option(arg, ret, "on")) {
+ spec2_print_if_secure("force enabled on command line.");
+ return SPECTRE_V2_CMD_FORCE;
+ } else if (match_option(arg, ret, "retpoline")) {
+ spec2_print_if_insecure("retpoline selected on command line.");
+ return SPECTRE_V2_CMD_RETPOLINE;
+ } else if (match_option(arg, ret, "retpoline,amd")) {
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+ pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
+ return SPECTRE_V2_CMD_AUTO;
+ }
+ spec2_print_if_insecure("AMD retpoline selected on command line.");
+ return SPECTRE_V2_CMD_RETPOLINE_AMD;
+ } else if (match_option(arg, ret, "retpoline,generic")) {
+ spec2_print_if_insecure("generic retpoline selected on command line.");
+ return SPECTRE_V2_CMD_RETPOLINE_GENERIC;
+ } else if (match_option(arg, ret, "auto")) {
+ return SPECTRE_V2_CMD_AUTO;
+ }
+ }
+
+ if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+ return SPECTRE_V2_CMD_AUTO;
+disable:
+ spec2_print_if_insecure("disabled on command line.");
+ return SPECTRE_V2_CMD_NONE;
+}
+
+/* Check for Skylake-like CPUs (for RSB handling) */
+static bool __init is_skylake_era(void)
+{
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+ boot_cpu_data.x86 == 6) {
+ switch (boot_cpu_data.x86_model) {
+ case INTEL_FAM6_SKYLAKE_MOBILE:
+ case INTEL_FAM6_SKYLAKE_DESKTOP:
+ case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_FAM6_KABYLAKE_MOBILE:
+ case INTEL_FAM6_KABYLAKE_DESKTOP:
+ return true;
+ }
+ }
+ return false;
+}
+
+static void __init spectre_v2_select_mitigation(void)
+{
+ enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
+ enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
+
+ /*
+ * If the CPU is not affected and the command line mode is NONE or AUTO
+ * then nothing to do.
+ */
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
+ (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
+ return;
+
+ switch (cmd) {
+ case SPECTRE_V2_CMD_NONE:
+ return;
+
+ case SPECTRE_V2_CMD_FORCE:
+ /* FALLTRHU */
+ case SPECTRE_V2_CMD_AUTO:
+ goto retpoline_auto;
+
+ case SPECTRE_V2_CMD_RETPOLINE_AMD:
+ if (IS_ENABLED(CONFIG_RETPOLINE))
+ goto retpoline_amd;
+ break;
+ case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
+ if (IS_ENABLED(CONFIG_RETPOLINE))
+ goto retpoline_generic;
+ break;
+ case SPECTRE_V2_CMD_RETPOLINE:
+ if (IS_ENABLED(CONFIG_RETPOLINE))
+ goto retpoline_auto;
+ break;
+ }
+ pr_err("kernel not compiled with retpoline; no mitigation available!");
+ return;
+
+retpoline_auto:
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ retpoline_amd:
+ if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
+ pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+ goto retpoline_generic;
+ }
+ mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
+ SPECTRE_V2_RETPOLINE_MINIMAL_AMD;
+ setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
+ setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+ } else {
+ retpoline_generic:
+ mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC :
+ SPECTRE_V2_RETPOLINE_MINIMAL;
+ setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+ }
+
+ spectre_v2_enabled = mode;
+ pr_info("%s\n", spectre_v2_strings[mode]);
+
+ /*
+ * If neither SMEP or KPTI are available, there is a risk of
+ * hitting userspace addresses in the RSB after a context switch
+ * from a shallow call stack to a deeper one. To prevent this fill
+ * the entire RSB, even when using IBRS.
+ *
+ * Skylake era CPUs have a separate issue with *underflow* of the
+ * RSB, when they will predict 'ret' targets from the generic BTB.
+ * The proper mitigation for this is IBRS. If IBRS is not supported
+ * or deactivated in favour of retpolines the RSB fill on context
+ * switch is required.
+ */
+ if ((!boot_cpu_has(X86_FEATURE_PTI) &&
+ !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
+ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+ pr_info("Filling RSB on context switch\n");
+ }
+
+ /* Initialize Indirect Branch Prediction Barrier if supported */
+ if (boot_cpu_has(X86_FEATURE_IBPB)) {
+ setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
+ pr_info("Enabling Indirect Branch Prediction Barrier\n");
+ }
+}
+
+#undef pr_fmt
+
+#ifdef CONFIG_SYSFS
+ssize_t cpu_show_meltdown(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ return sprintf(buf, "Not affected\n");
+ if (boot_cpu_has(X86_FEATURE_PTI))
+ return sprintf(buf, "Mitigation: PTI\n");
+ return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v1(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
+ return sprintf(buf, "Not affected\n");
+ return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+ return sprintf(buf, "Not affected\n");
+
+ return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+ boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+ spectre_v2_module_string());
+}
+#endif
+
+void __ibp_barrier(void)
+{
+ __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0);
+}
+EXPORT_SYMBOL_GPL(__ibp_barrier);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 68bc6d9b3132..c578cd29c2d2 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -106,6 +106,10 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_64
set_cpu_cap(c, X86_FEATURE_SYSENTER32);
#endif
+ if (c->x86_power & (1 << 8)) {
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+ set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+ }
}
static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index fa998ca8aa5a..c7c996a692fd 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -47,6 +47,8 @@
#include <asm/pat.h>
#include <asm/microcode.h>
#include <asm/microcode_intel.h>
+#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/uv/uv.h>
@@ -476,8 +478,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
return NULL; /* Not found */
}
-__u32 cpu_caps_cleared[NCAPINTS];
-__u32 cpu_caps_set[NCAPINTS];
+__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
+__u32 cpu_caps_set[NCAPINTS + NBUGINTS];
void load_percpu_segment(int cpu)
{
@@ -490,28 +492,23 @@ void load_percpu_segment(int cpu)
load_stack_canary_segment();
}
-/* Setup the fixmap mapping only once per-processor */
-static inline void setup_fixmap_gdt(int cpu)
-{
-#ifdef CONFIG_X86_64
- /* On 64-bit systems, we use a read-only fixmap GDT. */
- pgprot_t prot = PAGE_KERNEL_RO;
-#else
- /*
- * On native 32-bit systems, the GDT cannot be read-only because
- * our double fault handler uses a task gate, and entering through
- * a task gate needs to change an available TSS to busy. If the GDT
- * is read-only, that will triple fault.
- *
- * On Xen PV, the GDT must be read-only because the hypervisor requires
- * it.
- */
- pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ?
- PAGE_KERNEL_RO : PAGE_KERNEL;
+#ifdef CONFIG_X86_32
+/* The 32-bit entry code needs to find cpu_entry_area. */
+DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
#endif
- __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot);
-}
+#ifdef CONFIG_X86_64
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
+ [DEBUG_STACK - 1] = DEBUG_STKSZ
+};
+#endif
/* Load the original GDT from the per-cpu structure */
void load_direct_gdt(int cpu)
@@ -747,7 +744,7 @@ static void apply_forced_caps(struct cpuinfo_x86 *c)
{
int i;
- for (i = 0; i < NCAPINTS; i++) {
+ for (i = 0; i < NCAPINTS + NBUGINTS; i++) {
c->x86_capability[i] &= ~cpu_caps_cleared[i];
c->x86_capability[i] |= cpu_caps_set[i];
}
@@ -774,6 +771,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
c->x86_capability[CPUID_7_0_EBX] = ebx;
c->x86_capability[CPUID_7_ECX] = ecx;
+ c->x86_capability[CPUID_7_EDX] = edx;
}
/* Extended state features: level 0x0000000d */
@@ -881,6 +879,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#endif
}
+static const __initdata struct x86_cpu_id cpu_no_speculation[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY },
+ { X86_VENDOR_CENTAUR, 5 },
+ { X86_VENDOR_INTEL, 5 },
+ { X86_VENDOR_NSC, 5 },
+ { X86_VENDOR_ANY, 4 },
+ {}
+};
+
+static const __initdata struct x86_cpu_id cpu_no_meltdown[] = {
+ { X86_VENDOR_AMD },
+ {}
+};
+
+static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+{
+ u64 ia32_cap = 0;
+
+ if (x86_match_cpu(cpu_no_meltdown))
+ return false;
+
+ if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
+ rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+
+ /* Rogue Data Cache Load? No! */
+ if (ia32_cap & ARCH_CAP_RDCL_NO)
+ return false;
+
+ return true;
+}
+
/*
* Do minimum CPU detection early.
* Fields really needed: vendor, cpuid_level, family, model, mask,
@@ -927,6 +960,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
}
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
+
+ if (!x86_match_cpu(cpu_no_speculation)) {
+ if (cpu_vulnerable_to_meltdown(c))
+ setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+ }
+
fpu__init_system(c);
#ifdef CONFIG_X86_32
@@ -1250,7 +1291,7 @@ void enable_sep_cpu(void)
return;
cpu = get_cpu();
- tss = &per_cpu(cpu_tss, cpu);
+ tss = &per_cpu(cpu_tss_rw, cpu);
/*
* We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
@@ -1259,11 +1300,7 @@ void enable_sep_cpu(void)
tss->x86_tss.ss1 = __KERNEL_CS;
wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
-
- wrmsr(MSR_IA32_SYSENTER_ESP,
- (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
- 0);
-
+ wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
put_cpu();
@@ -1357,25 +1394,22 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
EXPORT_PER_CPU_SYMBOL(__preempt_count);
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
- [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
- [DEBUG_STACK - 1] = DEBUG_STKSZ
-};
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
- [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-
/* May not be marked __init: used by software suspend */
void syscall_init(void)
{
+ extern char _entry_trampoline[];
+ extern char entry_SYSCALL_64_trampoline[];
+
+ int cpu = smp_processor_id();
+ unsigned long SYSCALL64_entry_trampoline =
+ (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline +
+ (entry_SYSCALL_64_trampoline - _entry_trampoline);
+
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
- wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
+ else
+ wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
#ifdef CONFIG_IA32_EMULATION
wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
@@ -1386,7 +1420,7 @@ void syscall_init(void)
* AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
*/
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
#else
wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
@@ -1530,7 +1564,7 @@ void cpu_init(void)
if (cpu)
load_ucode_ap();
- t = &per_cpu(cpu_tss, cpu);
+ t = &per_cpu(cpu_tss_rw, cpu);
oist = &per_cpu(orig_ist, cpu);
#ifdef CONFIG_NUMA
@@ -1569,7 +1603,7 @@ void cpu_init(void)
* set up and load the per-CPU TSS
*/
if (!oist->ist[0]) {
- char *estacks = per_cpu(exception_stacks, cpu);
+ char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
for (v = 0; v < N_EXCEPTION_STACKS; v++) {
estacks += exception_stack_sizes[v];
@@ -1580,7 +1614,7 @@ void cpu_init(void)
}
}
- t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+ t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
/*
* <= is required because the CPU will access up to
@@ -1596,11 +1630,12 @@ void cpu_init(void)
enter_lazy_tlb(&init_mm, me);
/*
- * Initialize the TSS. Don't bother initializing sp0, as the initial
- * task never enters user mode.
+ * Initialize the TSS. sp0 points to the entry trampoline stack
+ * regardless of what task is running.
*/
- set_tss_desc(cpu, t);
+ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
load_TR_desc();
+ load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
load_mm_ldt(&init_mm);
@@ -1612,7 +1647,6 @@ void cpu_init(void)
if (is_uv_system())
uv_cpu_init();
- setup_fixmap_gdt(cpu);
load_fixmap_gdt(cpu);
}
@@ -1622,7 +1656,7 @@ void cpu_init(void)
{
int cpu = smp_processor_id();
struct task_struct *curr = current;
- struct tss_struct *t = &per_cpu(cpu_tss, cpu);
+ struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu);
wait_for_master_cpu(cpu);
@@ -1657,12 +1691,12 @@ void cpu_init(void)
* Initialize the TSS. Don't bother initializing sp0, as the initial
* task never enters user mode.
*/
- set_tss_desc(cpu, t);
+ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
load_TR_desc();
load_mm_ldt(&init_mm);
- t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+ t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
#ifdef CONFIG_DOUBLEFAULT
/* Set up doublefault TSS pointer in the GDT */
@@ -1674,7 +1708,6 @@ void cpu_init(void)
fpu__init_cpu();
- setup_fixmap_gdt(cpu);
load_fixmap_gdt(cpu);
}
#endif
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index bea8d3e24f50..479ca4728de0 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -31,6 +31,7 @@ extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
extern const struct hypervisor_x86 x86_hyper_xen_pv;
extern const struct hypervisor_x86 x86_hyper_xen_hvm;
extern const struct hypervisor_x86 x86_hyper_kvm;
+extern const struct hypervisor_x86 x86_hyper_jailhouse;
static const __initconst struct hypervisor_x86 * const hypervisors[] =
{
@@ -45,6 +46,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] =
#ifdef CONFIG_KVM_GUEST
&x86_hyper_kvm,
#endif
+#ifdef CONFIG_JAILHOUSE_GUEST
+ &x86_hyper_jailhouse,
+#endif
};
enum x86_hypervisor_type x86_hyper_type;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b1af22073e28..6936d14d4c77 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -102,6 +102,59 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
}
+/*
+ * Early microcode releases for the Spectre v2 mitigation were broken.
+ * Information taken from;
+ * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf
+ * - https://kb.vmware.com/s/article/52345
+ * - Microcode revisions observed in the wild
+ * - Release note from 20180108 microcode release
+ */
+struct sku_microcode {
+ u8 model;
+ u8 stepping;
+ u32 microcode;
+};
+static const struct sku_microcode spectre_bad_microcodes[] = {
+ { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 },
+ { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 },
+ { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 },
+ { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 },
+ { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 },
+ { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e },
+ { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c },
+ { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 },
+ { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 },
+ { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 },
+ { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b },
+ { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 },
+ { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 },
+ { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 },
+ { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 },
+ { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 },
+ { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 },
+ { INTEL_FAM6_HASWELL_X, 0x02, 0x3b },
+ { INTEL_FAM6_HASWELL_X, 0x04, 0x10 },
+ { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a },
+ /* Updated in the 20180108 release; blacklist until we know otherwise */
+ { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 },
+ /* Observed in the wild */
+ { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b },
+ { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 },
+};
+
+static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
+ if (c->x86_model == spectre_bad_microcodes[i].model &&
+ c->x86_mask == spectre_bad_microcodes[i].stepping)
+ return (c->microcode <= spectre_bad_microcodes[i].microcode);
+ }
+ return false;
+}
+
static void early_init_intel(struct cpuinfo_x86 *c)
{
u64 misc_enable;
@@ -123,6 +176,30 @@ static void early_init_intel(struct cpuinfo_x86 *c)
c->microcode = intel_get_microcode_revision();
/*
+ * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
+ * and they also have a different bit for STIBP support. Also,
+ * a hypervisor might have set the individual AMD bits even on
+ * Intel CPUs, for finer-grained selection of what's available.
+ */
+ if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
+ set_cpu_cap(c, X86_FEATURE_IBRS);
+ set_cpu_cap(c, X86_FEATURE_IBPB);
+ }
+ if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
+ set_cpu_cap(c, X86_FEATURE_STIBP);
+
+ /* Now if any of them are set, check the blacklist and clear the lot */
+ if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
+ cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) {
+ pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n");
+ clear_cpu_cap(c, X86_FEATURE_IBRS);
+ clear_cpu_cap(c, X86_FEATURE_IBPB);
+ clear_cpu_cap(c, X86_FEATURE_STIBP);
+ clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
+ clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP);
+ }
+
+ /*
* Atom erratum AAE44/AAF40/AAG38/AAH41:
*
* A race condition between speculative fetches and invalidating
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 88dcf8479013..410629f10ad3 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -135,6 +135,40 @@ struct rdt_resource rdt_resources_all[] = {
.format_str = "%d=%0*x",
.fflags = RFTYPE_RES_CACHE,
},
+ [RDT_RESOURCE_L2DATA] =
+ {
+ .rid = RDT_RESOURCE_L2DATA,
+ .name = "L2DATA",
+ .domains = domain_init(RDT_RESOURCE_L2DATA),
+ .msr_base = IA32_L2_CBM_BASE,
+ .msr_update = cat_wrmsr,
+ .cache_level = 2,
+ .cache = {
+ .min_cbm_bits = 1,
+ .cbm_idx_mult = 2,
+ .cbm_idx_offset = 0,
+ },
+ .parse_ctrlval = parse_cbm,
+ .format_str = "%d=%0*x",
+ .fflags = RFTYPE_RES_CACHE,
+ },
+ [RDT_RESOURCE_L2CODE] =
+ {
+ .rid = RDT_RESOURCE_L2CODE,
+ .name = "L2CODE",
+ .domains = domain_init(RDT_RESOURCE_L2CODE),
+ .msr_base = IA32_L2_CBM_BASE,
+ .msr_update = cat_wrmsr,
+ .cache_level = 2,
+ .cache = {
+ .min_cbm_bits = 1,
+ .cbm_idx_mult = 2,
+ .cbm_idx_offset = 1,
+ },
+ .parse_ctrlval = parse_cbm,
+ .format_str = "%d=%0*x",
+ .fflags = RFTYPE_RES_CACHE,
+ },
[RDT_RESOURCE_MBA] =
{
.rid = RDT_RESOURCE_MBA,
@@ -259,15 +293,15 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
r->alloc_enabled = true;
}
-static void rdt_get_cdp_l3_config(int type)
+static void rdt_get_cdp_config(int level, int type)
{
- struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+ struct rdt_resource *r_l = &rdt_resources_all[level];
struct rdt_resource *r = &rdt_resources_all[type];
- r->num_closid = r_l3->num_closid / 2;
- r->cache.cbm_len = r_l3->cache.cbm_len;
- r->default_ctrl = r_l3->default_ctrl;
- r->cache.shareable_bits = r_l3->cache.shareable_bits;
+ r->num_closid = r_l->num_closid / 2;
+ r->cache.cbm_len = r_l->cache.cbm_len;
+ r->default_ctrl = r_l->default_ctrl;
+ r->cache.shareable_bits = r_l->cache.shareable_bits;
r->data_width = (r->cache.cbm_len + 3) / 4;
r->alloc_capable = true;
/*
@@ -277,6 +311,18 @@ static void rdt_get_cdp_l3_config(int type)
r->alloc_enabled = false;
}
+static void rdt_get_cdp_l3_config(void)
+{
+ rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA);
+ rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3CODE);
+}
+
+static void rdt_get_cdp_l2_config(void)
+{
+ rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA);
+ rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE);
+}
+
static int get_cache_id(int cpu, int level)
{
struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
@@ -525,10 +571,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
*/
if (static_branch_unlikely(&rdt_mon_enable_key))
rmdir_mondata_subdir_allrdtgrp(r, d->id);
- kfree(d->ctrl_val);
- kfree(d->rmid_busy_llc);
- kfree(d->mbm_total);
- kfree(d->mbm_local);
list_del(&d->list);
if (is_mbm_enabled())
cancel_delayed_work(&d->mbm_over);
@@ -545,6 +587,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
cancel_delayed_work(&d->cqm_limbo);
}
+ kfree(d->ctrl_val);
+ kfree(d->rmid_busy_llc);
+ kfree(d->mbm_total);
+ kfree(d->mbm_local);
kfree(d);
return;
}
@@ -645,6 +691,7 @@ enum {
RDT_FLAG_L3_CAT,
RDT_FLAG_L3_CDP,
RDT_FLAG_L2_CAT,
+ RDT_FLAG_L2_CDP,
RDT_FLAG_MBA,
};
@@ -667,6 +714,7 @@ static struct rdt_options rdt_options[] __initdata = {
RDT_OPT(RDT_FLAG_L3_CAT, "l3cat", X86_FEATURE_CAT_L3),
RDT_OPT(RDT_FLAG_L3_CDP, "l3cdp", X86_FEATURE_CDP_L3),
RDT_OPT(RDT_FLAG_L2_CAT, "l2cat", X86_FEATURE_CAT_L2),
+ RDT_OPT(RDT_FLAG_L2_CDP, "l2cdp", X86_FEATURE_CDP_L2),
RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA),
};
#define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options)
@@ -729,15 +777,15 @@ static __init bool get_rdt_alloc_resources(void)
if (rdt_cpu_has(X86_FEATURE_CAT_L3)) {
rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]);
- if (rdt_cpu_has(X86_FEATURE_CDP_L3)) {
- rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
- rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
- }
+ if (rdt_cpu_has(X86_FEATURE_CDP_L3))
+ rdt_get_cdp_l3_config();
ret = true;
}
if (rdt_cpu_has(X86_FEATURE_CAT_L2)) {
/* CPUID 0x10.2 fields are same format at 0x10.1 */
rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+ if (rdt_cpu_has(X86_FEATURE_CDP_L2))
+ rdt_get_cdp_l2_config();
ret = true;
}
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 3397244984f5..3fd7a70ee04a 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -7,12 +7,15 @@
#include <linux/jump_label.h>
#define IA32_L3_QOS_CFG 0xc81
+#define IA32_L2_QOS_CFG 0xc82
#define IA32_L3_CBM_BASE 0xc90
#define IA32_L2_CBM_BASE 0xd10
#define IA32_MBA_THRTL_BASE 0xd50
#define L3_QOS_CDP_ENABLE 0x01ULL
+#define L2_QOS_CDP_ENABLE 0x01ULL
+
/*
* Event IDs are used to program IA32_QM_EVTSEL before reading event
* counter from IA32_QM_CTR
@@ -357,6 +360,8 @@ enum {
RDT_RESOURCE_L3DATA,
RDT_RESOURCE_L3CODE,
RDT_RESOURCE_L2,
+ RDT_RESOURCE_L2DATA,
+ RDT_RESOURCE_L2CODE,
RDT_RESOURCE_MBA,
/* Must be the last */
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 64c5ff97ee0d..bdab7d2f51af 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -990,6 +990,7 @@ out_destroy:
kernfs_remove(kn);
return ret;
}
+
static void l3_qos_cfg_update(void *arg)
{
bool *enable = arg;
@@ -997,8 +998,17 @@ static void l3_qos_cfg_update(void *arg)
wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
}
-static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
+static void l2_qos_cfg_update(void *arg)
{
+ bool *enable = arg;
+
+ wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
+}
+
+static int set_cache_qos_cfg(int level, bool enable)
+{
+ void (*update)(void *arg);
+ struct rdt_resource *r_l;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
int cpu;
@@ -1006,16 +1016,24 @@ static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
return -ENOMEM;
- list_for_each_entry(d, &r->domains, list) {
+ if (level == RDT_RESOURCE_L3)
+ update = l3_qos_cfg_update;
+ else if (level == RDT_RESOURCE_L2)
+ update = l2_qos_cfg_update;
+ else
+ return -EINVAL;
+
+ r_l = &rdt_resources_all[level];
+ list_for_each_entry(d, &r_l->domains, list) {
/* Pick one CPU from each domain instance to update MSR */
cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
}
cpu = get_cpu();
/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
if (cpumask_test_cpu(cpu, cpu_mask))
- l3_qos_cfg_update(&enable);
+ update(&enable);
/* Update QOS_CFG MSR on all other cpus in cpu_mask. */
- smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1);
+ smp_call_function_many(cpu_mask, update, &enable, 1);
put_cpu();
free_cpumask_var(cpu_mask);
@@ -1023,52 +1041,99 @@ static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
return 0;
}
-static int cdp_enable(void)
+static int cdp_enable(int level, int data_type, int code_type)
{
- struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA];
- struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE];
- struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+ struct rdt_resource *r_ldata = &rdt_resources_all[data_type];
+ struct rdt_resource *r_lcode = &rdt_resources_all[code_type];
+ struct rdt_resource *r_l = &rdt_resources_all[level];
int ret;
- if (!r_l3->alloc_capable || !r_l3data->alloc_capable ||
- !r_l3code->alloc_capable)
+ if (!r_l->alloc_capable || !r_ldata->alloc_capable ||
+ !r_lcode->alloc_capable)
return -EINVAL;
- ret = set_l3_qos_cfg(r_l3, true);
+ ret = set_cache_qos_cfg(level, true);
if (!ret) {
- r_l3->alloc_enabled = false;
- r_l3data->alloc_enabled = true;
- r_l3code->alloc_enabled = true;
+ r_l->alloc_enabled = false;
+ r_ldata->alloc_enabled = true;
+ r_lcode->alloc_enabled = true;
}
return ret;
}
-static void cdp_disable(void)
+static int cdpl3_enable(void)
{
- struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+ return cdp_enable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA,
+ RDT_RESOURCE_L3CODE);
+}
+
+static int cdpl2_enable(void)
+{
+ return cdp_enable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA,
+ RDT_RESOURCE_L2CODE);
+}
+
+static void cdp_disable(int level, int data_type, int code_type)
+{
+ struct rdt_resource *r = &rdt_resources_all[level];
r->alloc_enabled = r->alloc_capable;
- if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) {
- rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled = false;
- rdt_resources_all[RDT_RESOURCE_L3CODE].alloc_enabled = false;
- set_l3_qos_cfg(r, false);
+ if (rdt_resources_all[data_type].alloc_enabled) {
+ rdt_resources_all[data_type].alloc_enabled = false;
+ rdt_resources_all[code_type].alloc_enabled = false;
+ set_cache_qos_cfg(level, false);
}
}
+static void cdpl3_disable(void)
+{
+ cdp_disable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE);
+}
+
+static void cdpl2_disable(void)
+{
+ cdp_disable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, RDT_RESOURCE_L2CODE);
+}
+
+static void cdp_disable_all(void)
+{
+ if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
+ cdpl3_disable();
+ if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled)
+ cdpl2_disable();
+}
+
static int parse_rdtgroupfs_options(char *data)
{
char *token, *o = data;
int ret = 0;
while ((token = strsep(&o, ",")) != NULL) {
- if (!*token)
- return -EINVAL;
+ if (!*token) {
+ ret = -EINVAL;
+ goto out;
+ }
- if (!strcmp(token, "cdp"))
- ret = cdp_enable();
+ if (!strcmp(token, "cdp")) {
+ ret = cdpl3_enable();
+ if (ret)
+ goto out;
+ } else if (!strcmp(token, "cdpl2")) {
+ ret = cdpl2_enable();
+ if (ret)
+ goto out;
+ } else {
+ ret = -EINVAL;
+ goto out;
+ }
}
+ return 0;
+
+out:
+ pr_err("Invalid mount option \"%s\"\n", token);
+
return ret;
}
@@ -1223,7 +1288,7 @@ out_mongrp:
out_info:
kernfs_remove(kn_info);
out_cdp:
- cdp_disable();
+ cdp_disable_all();
out:
rdt_last_cmd_clear();
mutex_unlock(&rdtgroup_mutex);
@@ -1383,7 +1448,7 @@ static void rdt_kill_sb(struct super_block *sb)
/*Put everything back to default values. */
for_each_alloc_enabled_rdt_resource(r)
reset_all_ctrls(r);
- cdp_disable();
+ cdp_disable_all();
rmdir_all_sub();
static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
static_branch_disable_cpuslocked(&rdt_mon_enable_key);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 4ca632a06e0b..5bbd06f38ff6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -59,6 +59,7 @@ static struct severity {
#define MCGMASK(x, y) .mcgmask = x, .mcgres = y
#define MASK(x, y) .mask = x, .result = y
#define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S)
+#define MCI_UC_AR (MCI_STATUS_UC|MCI_STATUS_AR)
#define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR)
#define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV)
@@ -101,6 +102,22 @@ static struct severity {
NOSER, BITCLR(MCI_STATUS_UC)
),
+ /*
+ * known AO MCACODs reported via MCE or CMC:
+ *
+ * SRAO could be signaled either via a machine check exception or
+ * CMCI with the corresponding bit S 1 or 0. So we don't need to
+ * check bit S for SRAO.
+ */
+ MCESEV(
+ AO, "Action optional: memory scrubbing error",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
+ ),
+ MCESEV(
+ AO, "Action optional: last level cache writeback error",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
+ ),
+
/* ignore OVER for UCNA */
MCESEV(
UCNA, "Uncorrected no action required",
@@ -149,15 +166,6 @@ static struct severity {
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR)
),
- /* known AO MCACODs: */
- MCESEV(
- AO, "Action optional: memory scrubbing error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD_SCRUBMSK, MCI_UC_S|MCACOD_SCRUB)
- ),
- MCESEV(
- AO, "Action optional: last level cache writeback error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|MCACOD_L3WB)
- ),
MCESEV(
SOME, "Action optional: unknown MCACOD",
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index b1d616d08eee..ba1f9555fbc5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -503,10 +503,8 @@ static int mce_usable_address(struct mce *m)
bool mce_is_memory_error(struct mce *m)
{
if (m->cpuvendor == X86_VENDOR_AMD) {
- /* ErrCodeExt[20:16] */
- u8 xec = (m->status >> 16) & 0x1f;
+ return amd_mce_is_memory_error(m);
- return (xec == 0x0 || xec == 0x8);
} else if (m->cpuvendor == X86_VENDOR_INTEL) {
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
@@ -530,6 +528,17 @@ bool mce_is_memory_error(struct mce *m)
}
EXPORT_SYMBOL_GPL(mce_is_memory_error);
+static bool mce_is_correctable(struct mce *m)
+{
+ if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
+ return false;
+
+ if (m->status & MCI_STATUS_UC)
+ return false;
+
+ return true;
+}
+
static bool cec_add_mce(struct mce *m)
{
if (!m)
@@ -537,7 +546,7 @@ static bool cec_add_mce(struct mce *m)
/* We eat only correctable DRAM errors with usable addresses. */
if (mce_is_memory_error(m) &&
- !(m->status & MCI_STATUS_UC) &&
+ mce_is_correctable(m) &&
mce_usable_address(m))
if (!cec_add_elem(m->addr >> PAGE_SHIFT))
return true;
@@ -582,7 +591,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
pfn = mce->addr >> PAGE_SHIFT;
- memory_failure(pfn, MCE_VECTOR, 0);
+ memory_failure(pfn, 0);
}
return NOTIFY_OK;
@@ -1046,7 +1055,7 @@ static int do_memory_failure(struct mce *m)
pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
if (!(m->mcgstatus & MCG_STATUS_RIPV))
flags |= MF_MUST_KILL;
- ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags);
+ ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
if (ret)
pr_err("Memory error not recovered");
return ret;
@@ -1325,7 +1334,7 @@ out_ist:
EXPORT_SYMBOL_GPL(do_machine_check);
#ifndef CONFIG_MEMORY_FAILURE
-int memory_failure(unsigned long pfn, int vector, int flags)
+int memory_failure(unsigned long pfn, int flags)
{
/* mce_severity() should not hand us an ACTION_REQUIRED error */
BUG_ON(flags & MF_ACTION_REQUIRED);
@@ -1785,6 +1794,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
void (*machine_check_vector)(struct pt_regs *, long error_code) =
unexpected_machine_check;
+dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
+{
+ machine_check_vector(regs, error_code);
+}
+
/*
* Called for each booted CPU to set up machine checks.
* Must be called with preempt off:
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 486f640b02ef..0f32ad242324 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -110,6 +110,20 @@ const char *smca_get_long_name(enum smca_bank_types t)
}
EXPORT_SYMBOL_GPL(smca_get_long_name);
+static enum smca_bank_types smca_get_bank_type(struct mce *m)
+{
+ struct smca_bank *b;
+
+ if (m->bank >= N_SMCA_BANK_TYPES)
+ return N_SMCA_BANK_TYPES;
+
+ b = &smca_banks[m->bank];
+ if (!b->hwid)
+ return N_SMCA_BANK_TYPES;
+
+ return b->hwid->bank_type;
+}
+
static struct smca_hwid smca_hwid_mcatypes[] = {
/* { bank_type, hwid_mcatype, xec_bitmap } */
@@ -407,7 +421,9 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
(deferred_error_int_vector != amd_deferred_error_interrupt))
deferred_error_int_vector = amd_deferred_error_interrupt;
- low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+ if (!mce_flags.smca)
+ low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+
wrmsr(MSR_CU_DEF_ERR, low, high);
}
@@ -738,6 +754,17 @@ out_err:
}
EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr);
+bool amd_mce_is_memory_error(struct mce *m)
+{
+ /* ErrCodeExt[20:16] */
+ u8 xec = (m->status >> 16) & 0x1f;
+
+ if (mce_flags.smca)
+ return smca_get_bank_type(m) == SMCA_UMC && xec == 0x0;
+
+ return m->bank == 4 && xec == 0x8;
+}
+
static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
{
struct mce m;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index c6daec4bdba5..330b8462d426 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -470,6 +470,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
#define F14H_MPB_MAX_SIZE 1824
#define F15H_MPB_MAX_SIZE 4096
#define F16H_MPB_MAX_SIZE 3458
+#define F17H_MPB_MAX_SIZE 3200
switch (family) {
case 0x14:
@@ -481,6 +482,9 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
case 0x16:
max_size = F16H_MPB_MAX_SIZE;
break;
+ case 0x17:
+ max_size = F17H_MPB_MAX_SIZE;
+ break;
default:
max_size = F1XH_MPB_MAX_SIZE;
break;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index c4fa4a85d4cb..e4fc595cd6ea 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -239,7 +239,7 @@ static int __init save_microcode_in_initrd(void)
break;
case X86_VENDOR_AMD:
if (c->x86 >= 0x10)
- return save_microcode_in_initrd_amd(cpuid_eax(1));
+ ret = save_microcode_in_initrd_amd(cpuid_eax(1));
break;
default:
break;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 7dbcb7adf797..f7c55b0e753a 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -45,6 +45,9 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
/* Current microcode patch used in early patching on the APs. */
static struct microcode_intel *intel_ucode_patch;
+/* last level cache size per core */
+static int llc_size_per_core;
+
static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
unsigned int s2, unsigned int p2)
{
@@ -565,15 +568,6 @@ static void print_ucode(struct ucode_cpu_info *uci)
}
#else
-/*
- * Flush global tlb. We only do this in x86_64 where paging has been enabled
- * already and PGE should be enabled as well.
- */
-static inline void flush_tlb_early(void)
-{
- __native_flush_tlb_global_irq_disabled();
-}
-
static inline void print_ucode(struct ucode_cpu_info *uci)
{
struct microcode_intel *mc;
@@ -602,10 +596,6 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
if (rev != mc->hdr.rev)
return -1;
-#ifdef CONFIG_X86_64
- /* Flush global tlb. This is precaution. */
- flush_tlb_early();
-#endif
uci->cpu_sig.rev = rev;
if (early)
@@ -923,8 +913,19 @@ static bool is_blacklisted(unsigned int cpu)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
- if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) {
- pr_err_once("late loading on model 79 is disabled.\n");
+ /*
+ * Late loading on model 79 with microcode revision less than 0x0b000021
+ * and LLC size per core bigger than 2.5MB may result in a system hang.
+ * This behavior is documented in item BDF90, #334165 (Intel Xeon
+ * Processor E7-8800/4800 v4 Product Family).
+ */
+ if (c->x86 == 6 &&
+ c->x86_model == INTEL_FAM6_BROADWELL_X &&
+ c->x86_mask == 0x01 &&
+ llc_size_per_core > 2621440 &&
+ c->microcode < 0x0b000021) {
+ pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode);
+ pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
return true;
}
@@ -979,6 +980,15 @@ static struct microcode_ops microcode_intel_ops = {
.apply_microcode = apply_microcode_intel,
};
+static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
+{
+ u64 llc_size = c->x86_cache_size * 1024;
+
+ do_div(llc_size, c->x86_max_cores);
+
+ return (int)llc_size;
+}
+
struct microcode_ops * __init init_intel_microcode(void)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
@@ -989,5 +999,7 @@ struct microcode_ops * __init init_intel_microcode(void)
return NULL;
}
+ llc_size_per_core = calc_llc_size_per_core(c);
+
return &microcode_intel_ops;
}
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 05459ad3db46..4075d2be5357 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -21,12 +21,10 @@ struct cpuid_bit {
static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
- { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 },
- { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 },
- { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 },
{ X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 },
{ X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 },
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
+ { X86_FEATURE_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 },
{ X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 },
{ X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 },
{ X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c
index 0e662c55ae90..0b8cedb20d6d 100644
--- a/arch/x86/kernel/doublefault.c
+++ b/arch/x86/kernel/doublefault.c
@@ -50,25 +50,23 @@ static void doublefault_fn(void)
cpu_relax();
}
-struct tss_struct doublefault_tss __cacheline_aligned = {
- .x86_tss = {
- .sp0 = STACK_START,
- .ss0 = __KERNEL_DS,
- .ldt = 0,
- .io_bitmap_base = INVALID_IO_BITMAP_OFFSET,
-
- .ip = (unsigned long) doublefault_fn,
- /* 0x2 bit is always set */
- .flags = X86_EFLAGS_SF | 0x2,
- .sp = STACK_START,
- .es = __USER_DS,
- .cs = __KERNEL_CS,
- .ss = __KERNEL_DS,
- .ds = __USER_DS,
- .fs = __KERNEL_PERCPU,
-
- .__cr3 = __pa_nodebug(swapper_pg_dir),
- }
+struct x86_hw_tss doublefault_tss __cacheline_aligned = {
+ .sp0 = STACK_START,
+ .ss0 = __KERNEL_DS,
+ .ldt = 0,
+ .io_bitmap_base = INVALID_IO_BITMAP_OFFSET,
+
+ .ip = (unsigned long) doublefault_fn,
+ /* 0x2 bit is always set */
+ .flags = X86_EFLAGS_SF | 0x2,
+ .sp = STACK_START,
+ .es = __USER_DS,
+ .cs = __KERNEL_CS,
+ .ss = __KERNEL_DS,
+ .ds = __USER_DS,
+ .fs = __KERNEL_PERCPU,
+
+ .__cr3 = __pa_nodebug(swapper_pg_dir),
};
/* dummy for do_double_fault() call */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index f13b4c00a5de..afbecff161d1 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -18,6 +18,7 @@
#include <linux/nmi.h>
#include <linux/sysfs.h>
+#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
@@ -43,6 +44,24 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
return true;
}
+bool in_entry_stack(unsigned long *stack, struct stack_info *info)
+{
+ struct entry_stack *ss = cpu_entry_stack(smp_processor_id());
+
+ void *begin = ss;
+ void *end = ss + 1;
+
+ if ((void *)stack < begin || (void *)stack >= end)
+ return false;
+
+ info->type = STACK_TYPE_ENTRY;
+ info->begin = begin;
+ info->end = end;
+ info->next_sp = NULL;
+
+ return true;
+}
+
static void printk_stack_address(unsigned long address, int reliable,
char *log_lvl)
{
@@ -50,6 +69,39 @@ static void printk_stack_address(unsigned long address, int reliable,
printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
}
+void show_iret_regs(struct pt_regs *regs)
+{
+ printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
+ printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
+ regs->sp, regs->flags);
+}
+
+static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
+ bool partial)
+{
+ /*
+ * These on_stack() checks aren't strictly necessary: the unwind code
+ * has already validated the 'regs' pointer. The checks are done for
+ * ordering reasons: if the registers are on the next stack, we don't
+ * want to print them out yet. Otherwise they'll be shown as part of
+ * the wrong stack. Later, when show_trace_log_lvl() switches to the
+ * next stack, this function will be called again with the same regs so
+ * they can be printed in the right context.
+ */
+ if (!partial && on_stack(info, regs, sizeof(*regs))) {
+ __show_regs(regs, 0);
+
+ } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
+ IRET_FRAME_SIZE)) {
+ /*
+ * When an interrupt or exception occurs in entry code, the
+ * full pt_regs might not have been saved yet. In that case
+ * just print the iret frame.
+ */
+ show_iret_regs(regs);
+ }
+}
+
void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, char *log_lvl)
{
@@ -57,11 +109,13 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
struct stack_info stack_info = {0};
unsigned long visit_mask = 0;
int graph_idx = 0;
+ bool partial;
printk("%sCall Trace:\n", log_lvl);
unwind_start(&state, task, regs, stack);
stack = stack ? : get_stack_pointer(task, regs);
+ regs = unwind_get_entry_regs(&state, &partial);
/*
* Iterate through the stacks, starting with the current stack pointer.
@@ -71,31 +125,35 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
* - task stack
* - interrupt stack
* - HW exception stacks (double fault, nmi, debug, mce)
+ * - entry stack
*
- * x86-32 can have up to three stacks:
+ * x86-32 can have up to four stacks:
* - task stack
* - softirq stack
* - hardirq stack
+ * - entry stack
*/
- for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+ for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
const char *stack_name;
- /*
- * If we overflowed the task stack into a guard page, jump back
- * to the bottom of the usable stack.
- */
- if (task_stack_page(task) - (void *)stack < PAGE_SIZE)
- stack = task_stack_page(task);
-
- if (get_stack_info(stack, task, &stack_info, &visit_mask))
- break;
+ if (get_stack_info(stack, task, &stack_info, &visit_mask)) {
+ /*
+ * We weren't on a valid stack. It's possible that
+ * we overflowed a valid stack into a guard page.
+ * See if the next page up is valid so that we can
+ * generate some kind of backtrace if this happens.
+ */
+ stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack);
+ if (get_stack_info(stack, task, &stack_info, &visit_mask))
+ break;
+ }
stack_name = stack_type_name(stack_info.type);
if (stack_name)
printk("%s <%s>\n", log_lvl, stack_name);
- if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
- __show_regs(regs, 0);
+ if (regs)
+ show_regs_if_on_stack(&stack_info, regs, partial);
/*
* Scan the stack, printing any text addresses we find. At the
@@ -119,7 +177,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
/*
* Don't print regs->ip again if it was already printed
- * by __show_regs() below.
+ * by show_regs_if_on_stack().
*/
if (regs && stack == &regs->ip)
goto next;
@@ -154,9 +212,9 @@ next:
unwind_next_frame(&state);
/* if the frame has entry regs, print them */
- regs = unwind_get_entry_regs(&state);
- if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
- __show_regs(regs, 0);
+ regs = unwind_get_entry_regs(&state, &partial);
+ if (regs)
+ show_regs_if_on_stack(&stack_info, regs, partial);
}
if (stack_name)
@@ -252,11 +310,13 @@ int __die(const char *str, struct pt_regs *regs, long err)
unsigned long sp;
#endif
printk(KERN_DEFAULT
- "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter,
+ "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
- IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "");
+ IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "",
+ IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
+ (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index daefae83a3aa..04170f63e3a1 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type)
if (type == STACK_TYPE_SOFTIRQ)
return "SOFTIRQ";
+ if (type == STACK_TYPE_ENTRY)
+ return "ENTRY_TRAMPOLINE";
+
return NULL;
}
@@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
if (task != current)
goto unknown;
+ if (in_entry_stack(stack, info))
+ goto recursion_check;
+
if (in_hardirq_stack(stack, info))
goto recursion_check;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 88ce2ffdb110..563e28d14f2c 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -37,6 +37,15 @@ const char *stack_type_name(enum stack_type type)
if (type == STACK_TYPE_IRQ)
return "IRQ";
+ if (type == STACK_TYPE_ENTRY) {
+ /*
+ * On 64-bit, we have a generic entry stack that we
+ * use for all the kernel entry points, including
+ * SYSENTER.
+ */
+ return "ENTRY_TRAMPOLINE";
+ }
+
if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST)
return exception_stack_names[type - STACK_TYPE_EXCEPTION];
@@ -115,6 +124,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
if (in_irq_stack(stack, info))
goto recursion_check;
+ if (in_entry_stack(stack, info))
+ goto recursion_check;
+
goto unknown;
recursion_check:
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index b6c6468e10bc..4c8440de3355 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -8,6 +8,7 @@
#include <asm/segment.h>
#include <asm/export.h>
#include <asm/ftrace.h>
+#include <asm/nospec-branch.h>
#ifdef CC_USING_FENTRY
# define function_hook __fentry__
@@ -197,7 +198,8 @@ ftrace_stub:
movl 0x4(%ebp), %edx
subl $MCOUNT_INSN_SIZE, %eax
- call *ftrace_trace_function
+ movl ftrace_trace_function, %ecx
+ CALL_NOSPEC %ecx
popl %edx
popl %ecx
@@ -241,5 +243,5 @@ return_to_handler:
movl %eax, %ecx
popl %edx
popl %eax
- jmp *%ecx
+ JMP_NOSPEC %ecx
#endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index c832291d948a..91b2cff4b79a 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -7,7 +7,8 @@
#include <asm/ptrace.h>
#include <asm/ftrace.h>
#include <asm/export.h>
-
+#include <asm/nospec-branch.h>
+#include <asm/unwind_hints.h>
.code64
.section .entry.text, "ax"
@@ -20,7 +21,6 @@ EXPORT_SYMBOL(__fentry__)
EXPORT_SYMBOL(mcount)
#endif
-/* All cases save the original rbp (8 bytes) */
#ifdef CONFIG_FRAME_POINTER
# ifdef CC_USING_FENTRY
/* Save parent and function stack frames (rip and rbp) */
@@ -31,7 +31,7 @@ EXPORT_SYMBOL(mcount)
# endif
#else
/* No need to save a stack frame */
-# define MCOUNT_FRAME_SIZE 8
+# define MCOUNT_FRAME_SIZE 0
#endif /* CONFIG_FRAME_POINTER */
/* Size of stack used to save mcount regs in save_mcount_regs */
@@ -64,10 +64,10 @@ EXPORT_SYMBOL(mcount)
*/
.macro save_mcount_regs added=0
- /* Always save the original rbp */
+#ifdef CONFIG_FRAME_POINTER
+ /* Save the original rbp */
pushq %rbp
-#ifdef CONFIG_FRAME_POINTER
/*
* Stack traces will stop at the ftrace trampoline if the frame pointer
* is not set up properly. If fentry is used, we need to save a frame
@@ -105,7 +105,11 @@ EXPORT_SYMBOL(mcount)
* Save the original RBP. Even though the mcount ABI does not
* require this, it helps out callers.
*/
+#ifdef CONFIG_FRAME_POINTER
movq MCOUNT_REG_SIZE-8(%rsp), %rdx
+#else
+ movq %rbp, %rdx
+#endif
movq %rdx, RBP(%rsp)
/* Copy the parent address into %rsi (second parameter) */
@@ -148,7 +152,7 @@ EXPORT_SYMBOL(mcount)
ENTRY(function_hook)
retq
-END(function_hook)
+ENDPROC(function_hook)
ENTRY(ftrace_caller)
/* save_mcount_regs fills in first two parameters */
@@ -184,7 +188,7 @@ GLOBAL(ftrace_graph_call)
/* This is weak to keep gas from relaxing the jumps */
WEAK(ftrace_stub)
retq
-END(ftrace_caller)
+ENDPROC(ftrace_caller)
ENTRY(ftrace_regs_caller)
/* Save the current flags before any operations that can change them */
@@ -255,7 +259,7 @@ GLOBAL(ftrace_regs_caller_end)
jmp ftrace_epilogue
-END(ftrace_regs_caller)
+ENDPROC(ftrace_regs_caller)
#else /* ! CONFIG_DYNAMIC_FTRACE */
@@ -286,12 +290,12 @@ trace:
* ip and parent ip are used and the list function is called when
* function tracing is enabled.
*/
- call *ftrace_trace_function
-
+ movq ftrace_trace_function, %r8
+ CALL_NOSPEC %r8
restore_mcount_regs
jmp fgraph_trace
-END(function_hook)
+ENDPROC(function_hook)
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -313,9 +317,10 @@ ENTRY(ftrace_graph_caller)
restore_mcount_regs
retq
-END(ftrace_graph_caller)
+ENDPROC(ftrace_graph_caller)
-GLOBAL(return_to_handler)
+ENTRY(return_to_handler)
+ UNWIND_HINT_EMPTY
subq $24, %rsp
/* Save the return values */
@@ -329,5 +334,6 @@ GLOBAL(return_to_handler)
movq 8(%rsp), %rdx
movq (%rsp), %rax
addq $24, %rsp
- jmp *%rdi
+ JMP_NOSPEC %rdi
+END(return_to_handler)
#endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 6a5d757b9cfd..7ba5d819ebe3 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -157,8 +157,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
p = fixup_pointer(&phys_base, physaddr);
*p += load_delta - sme_get_me_mask();
- /* Encrypt the kernel (if SME is active) */
- sme_encrypt_kernel();
+ /* Encrypt the kernel and related (if SME is active) */
+ sme_encrypt_kernel(bp);
/*
* Return the SME encryption mask (if SME is active) to be used as a
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7dca675fe78d..04a625f0fcda 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -341,6 +341,27 @@ GLOBAL(early_recursion_flag)
.balign PAGE_SIZE; \
GLOBAL(name)
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Each PGD needs to be 8k long and 8k aligned. We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define PTI_USER_PGD_FILL 512
+/* This ensures they are 8k-aligned: */
+#define NEXT_PGD_PAGE(name) \
+ .balign 2 * PAGE_SIZE; \
+GLOBAL(name)
+#else
+#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define PTI_USER_PGD_FILL 0
+#endif
+
/* Automate the creation of 1 to 1 mapping pmd entries */
#define PMDS(START, PERM, COUNT) \
i = 0 ; \
@@ -350,13 +371,14 @@ GLOBAL(name)
.endr
__INITDATA
-NEXT_PAGE(early_top_pgt)
+NEXT_PGD_PAGE(early_top_pgt)
.fill 511,8,0
#ifdef CONFIG_X86_5LEVEL
.quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
#else
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
#endif
+ .fill PTI_USER_PGD_FILL,8,0
NEXT_PAGE(early_dynamic_pgts)
.fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -364,13 +386,14 @@ NEXT_PAGE(early_dynamic_pgts)
.data
#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.org init_top_pgt + PGD_PAGE_OFFSET*8, 0
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.org init_top_pgt + PGD_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+ .fill PTI_USER_PGD_FILL,8,0
NEXT_PAGE(level3_ident_pgt)
.quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
@@ -381,8 +404,9 @@ NEXT_PAGE(level2_ident_pgt)
*/
PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
#else
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
.fill 512,8,0
+ .fill PTI_USER_PGD_FILL,8,0
#endif
#ifdef CONFIG_X86_5LEVEL
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index d985cef3984f..56d99be3706a 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -56,7 +56,7 @@ struct idt_data {
* Early traps running on the DEFAULT_STACK because the other interrupt
* stacks work only after cpu_init().
*/
-static const __initdata struct idt_data early_idts[] = {
+static const __initconst struct idt_data early_idts[] = {
INTG(X86_TRAP_DB, debug),
SYSG(X86_TRAP_BP, int3),
#ifdef CONFIG_X86_32
@@ -70,7 +70,7 @@ static const __initdata struct idt_data early_idts[] = {
* the traps which use them are reinitialized with IST after cpu_init() has
* set up TSS.
*/
-static const __initdata struct idt_data def_idts[] = {
+static const __initconst struct idt_data def_idts[] = {
INTG(X86_TRAP_DE, divide_error),
INTG(X86_TRAP_NMI, nmi),
INTG(X86_TRAP_BR, bounds),
@@ -108,7 +108,7 @@ static const __initdata struct idt_data def_idts[] = {
/*
* The APIC and SMP idt entries
*/
-static const __initdata struct idt_data apic_idts[] = {
+static const __initconst struct idt_data apic_idts[] = {
#ifdef CONFIG_SMP
INTG(RESCHEDULE_VECTOR, reschedule_interrupt),
INTG(CALL_FUNCTION_VECTOR, call_function_interrupt),
@@ -150,7 +150,7 @@ static const __initdata struct idt_data apic_idts[] = {
* Early traps running on the DEFAULT_STACK because the other interrupt
* stacks work only after cpu_init().
*/
-static const __initdata struct idt_data early_pf_idts[] = {
+static const __initconst struct idt_data early_pf_idts[] = {
INTG(X86_TRAP_PF, page_fault),
};
@@ -158,7 +158,7 @@ static const __initdata struct idt_data early_pf_idts[] = {
* Override for the debug_idt. Same as the default, but with interrupt
* stack set to DEFAULT_STACK (0). Required for NMI trap handling.
*/
-static const __initdata struct idt_data dbg_idts[] = {
+static const __initconst struct idt_data dbg_idts[] = {
INTG(X86_TRAP_DB, debug),
INTG(X86_TRAP_BP, int3),
};
@@ -180,7 +180,7 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
* The exceptions which use Interrupt stacks. They are setup after
* cpu_init() when the TSS has been initialized.
*/
-static const __initdata struct idt_data ist_idts[] = {
+static const __initconst struct idt_data ist_idts[] = {
ISTG(X86_TRAP_DB, debug, DEBUG_STACK),
ISTG(X86_TRAP_NMI, nmi, NMI_STACK),
SISTG(X86_TRAP_BP, int3, DEBUG_STACK),
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 3feb648781c4..2f723301eb58 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
* because the ->io_bitmap_max value must match the bitmap
* contents:
*/
- tss = &per_cpu(cpu_tss, get_cpu());
+ tss = &per_cpu(cpu_tss_rw, get_cpu());
if (turn_on)
bitmap_clear(t->io_bitmap_ptr, from, num);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 49cfd9fe7589..68e1867cca80 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -219,18 +219,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
/* high bit used in ret_from_ code */
unsigned vector = ~regs->orig_ax;
- /*
- * NB: Unlike exception entries, IRQ entries do not reliably
- * handle context tracking in the low-level entry code. This is
- * because syscall entries execute briefly with IRQs on before
- * updating context tracking state, so we can take an IRQ from
- * kernel mode with CONTEXT_USER. The low-level entry code only
- * updates the context if we came from user mode, so we won't
- * switch to CONTEXT_KERNEL. We'll fix that once the syscall
- * code is cleaned up enough that we can cleanly defer enabling
- * IRQs.
- */
-
entering_irq();
/* entering_irq() tells RCU that we're not quiescent. Check it. */
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index a83b3346a0e1..c1bdbd3d3232 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -20,6 +20,7 @@
#include <linux/mm.h>
#include <asm/apic.h>
+#include <asm/nospec-branch.h>
#ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -55,11 +56,11 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
static void call_on_stack(void *func, void *stack)
{
asm volatile("xchgl %%ebx,%%esp \n"
- "call *%%edi \n"
+ CALL_NOSPEC
"movl %%ebx,%%esp \n"
: "=b" (stack)
: "0" (stack),
- "D"(func)
+ [thunk_target] "D"(func)
: "memory", "cc", "edx", "ecx", "eax");
}
@@ -95,11 +96,11 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
call_on_stack(print_stack_overflow, isp);
asm volatile("xchgl %%ebx,%%esp \n"
- "call *%%edi \n"
+ CALL_NOSPEC
"movl %%ebx,%%esp \n"
: "=a" (arg1), "=b" (isp)
: "0" (desc), "1" (isp),
- "D" (desc->handle_irq)
+ [thunk_target] "D" (desc->handle_irq)
: "memory", "cc", "ecx");
return 1;
}
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 020efbf5786b..d86e344f5b3d 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -57,10 +57,10 @@ static inline void stack_overflow_check(struct pt_regs *regs)
if (regs->sp >= estack_top && regs->sp <= estack_bottom)
return;
- WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+ WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n",
current->comm, curbase, regs->sp,
irq_stack_top, irq_stack_bottom,
- estack_top, estack_bottom);
+ estack_top, estack_bottom, (void *)regs->ip);
if (sysctl_panic_on_stackoverflow)
panic("low stack detected by irq handler - check messages\n");
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 8da3e909e967..a539410c4ea9 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -61,6 +61,9 @@ void __init init_ISA_irqs(void)
struct irq_chip *chip = legacy_pic->chip;
int i;
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+ init_bsp_APIC();
+#endif
legacy_pic->init(0);
for (i = 0; i < nr_legacy_irqs(); i++)
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index f73f475d0573..d177940aa090 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -24,7 +24,6 @@
#include <linux/cpumask.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>
-#include <linux/sched.h>
#include <linux/sysctl.h>
#include <linux/nodemask.h>
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
new file mode 100644
index 000000000000..b68fd895235a
--- /dev/null
+++ b/arch/x86/kernel/jailhouse.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL2.0
+/*
+ * Jailhouse paravirt_ops implementation
+ *
+ * Copyright (c) Siemens AG, 2015-2017
+ *
+ * Authors:
+ * Jan Kiszka <jan.kiszka@siemens.com>
+ */
+
+#include <linux/acpi_pmtmr.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <asm/apic.h>
+#include <asm/cpu.h>
+#include <asm/hypervisor.h>
+#include <asm/i8259.h>
+#include <asm/irqdomain.h>
+#include <asm/pci_x86.h>
+#include <asm/reboot.h>
+#include <asm/setup.h>
+
+static __initdata struct jailhouse_setup_data setup_data;
+static unsigned int precalibrated_tsc_khz;
+
+static uint32_t jailhouse_cpuid_base(void)
+{
+ if (boot_cpu_data.cpuid_level < 0 ||
+ !boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return 0;
+
+ return hypervisor_cpuid_base("Jailhouse\0\0\0", 0);
+}
+
+static uint32_t __init jailhouse_detect(void)
+{
+ return jailhouse_cpuid_base();
+}
+
+static void jailhouse_get_wallclock(struct timespec *now)
+{
+ memset(now, 0, sizeof(*now));
+}
+
+static void __init jailhouse_timer_init(void)
+{
+ lapic_timer_frequency = setup_data.apic_khz * (1000 / HZ);
+}
+
+static unsigned long jailhouse_get_tsc(void)
+{
+ return precalibrated_tsc_khz;
+}
+
+static void __init jailhouse_x2apic_init(void)
+{
+#ifdef CONFIG_X86_X2APIC
+ if (!x2apic_enabled())
+ return;
+ /*
+ * We do not have access to IR inside Jailhouse non-root cells. So
+ * we have to run in physical mode.
+ */
+ x2apic_phys = 1;
+ /*
+ * This will trigger the switch to apic_x2apic_phys. Empty OEM IDs
+ * ensure that only this APIC driver picks up the call.
+ */
+ default_acpi_madt_oem_check("", "");
+#endif
+}
+
+static void __init jailhouse_get_smp_config(unsigned int early)
+{
+ struct ioapic_domain_cfg ioapic_cfg = {
+ .type = IOAPIC_DOMAIN_STRICT,
+ .ops = &mp_ioapic_irqdomain_ops,
+ };
+ struct mpc_intsrc mp_irq = {
+ .type = MP_INTSRC,
+ .irqtype = mp_INT,
+ .irqflag = MP_IRQPOL_ACTIVE_HIGH | MP_IRQTRIG_EDGE,
+ };
+ unsigned int cpu;
+
+ jailhouse_x2apic_init();
+
+ register_lapic_address(0xfee00000);
+
+ for (cpu = 0; cpu < setup_data.num_cpus; cpu++) {
+ generic_processor_info(setup_data.cpu_ids[cpu],
+ boot_cpu_apic_version);
+ }
+
+ smp_found_config = 1;
+
+ if (setup_data.standard_ioapic) {
+ mp_register_ioapic(0, 0xfec00000, gsi_top, &ioapic_cfg);
+
+ /* Register 1:1 mapping for legacy UART IRQs 3 and 4 */
+ mp_irq.srcbusirq = mp_irq.dstirq = 3;
+ mp_save_irq(&mp_irq);
+
+ mp_irq.srcbusirq = mp_irq.dstirq = 4;
+ mp_save_irq(&mp_irq);
+ }
+}
+
+static void jailhouse_no_restart(void)
+{
+ pr_notice("Jailhouse: Restart not supported, halting\n");
+ machine_halt();
+}
+
+static int __init jailhouse_pci_arch_init(void)
+{
+ pci_direct_init(1);
+
+ /*
+ * There are no bridges on the virtual PCI root bus under Jailhouse,
+ * thus no other way to discover all devices than a full scan.
+ * Respect any overrides via the command line, though.
+ */
+ if (pcibios_last_bus < 0)
+ pcibios_last_bus = 0xff;
+
+ return 0;
+}
+
+static void __init jailhouse_init_platform(void)
+{
+ u64 pa_data = boot_params.hdr.setup_data;
+ struct setup_data header;
+ void *mapping;
+
+ x86_init.irqs.pre_vector_init = x86_init_noop;
+ x86_init.timers.timer_init = jailhouse_timer_init;
+ x86_init.mpparse.get_smp_config = jailhouse_get_smp_config;
+ x86_init.pci.arch_init = jailhouse_pci_arch_init;
+
+ x86_platform.calibrate_cpu = jailhouse_get_tsc;
+ x86_platform.calibrate_tsc = jailhouse_get_tsc;
+ x86_platform.get_wallclock = jailhouse_get_wallclock;
+ x86_platform.legacy.rtc = 0;
+ x86_platform.legacy.warm_reset = 0;
+ x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT;
+
+ legacy_pic = &null_legacy_pic;
+
+ machine_ops.emergency_restart = jailhouse_no_restart;
+
+ while (pa_data) {
+ mapping = early_memremap(pa_data, sizeof(header));
+ memcpy(&header, mapping, sizeof(header));
+ early_memunmap(mapping, sizeof(header));
+
+ if (header.type == SETUP_JAILHOUSE &&
+ header.len >= sizeof(setup_data)) {
+ pa_data += offsetof(struct setup_data, data);
+
+ mapping = early_memremap(pa_data, sizeof(setup_data));
+ memcpy(&setup_data, mapping, sizeof(setup_data));
+ early_memunmap(mapping, sizeof(setup_data));
+
+ break;
+ }
+
+ pa_data = header.next;
+ }
+
+ if (!pa_data)
+ panic("Jailhouse: No valid setup data found");
+
+ if (setup_data.compatible_version > JAILHOUSE_SETUP_REQUIRED_VERSION)
+ panic("Jailhouse: Unsupported setup data structure");
+
+ pmtmr_ioport = setup_data.pm_timer_address;
+ pr_debug("Jailhouse: PM-Timer IO Port: %#x\n", pmtmr_ioport);
+
+ precalibrated_tsc_khz = setup_data.tsc_khz;
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+
+ pci_probe = 0;
+
+ /*
+ * Avoid that the kernel complains about missing ACPI tables - there
+ * are none in a non-root cell.
+ */
+ disable_acpi();
+}
+
+bool jailhouse_paravirt(void)
+{
+ return jailhouse_cpuid_base() != 0;
+}
+
+static bool jailhouse_x2apic_available(void)
+{
+ /*
+ * The x2APIC is only available if the root cell enabled it. Jailhouse
+ * does not support switching between xAPIC and x2APIC.
+ */
+ return x2apic_enabled();
+}
+
+const struct hypervisor_x86 x86_hyper_jailhouse __refconst = {
+ .name = "Jailhouse",
+ .detect = jailhouse_detect,
+ .init.init_platform = jailhouse_init_platform,
+ .init.x2apic_available = jailhouse_x2apic_available,
+};
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index e941136e24d8..203d398802a3 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -40,6 +40,7 @@
#include <asm/debugreg.h>
#include <asm/set_memory.h>
#include <asm/sections.h>
+#include <asm/nospec-branch.h>
#include "common.h"
@@ -203,7 +204,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real)
}
/* Check whether insn is indirect jump */
-static int insn_is_indirect_jump(struct insn *insn)
+static int __insn_is_indirect_jump(struct insn *insn)
{
return ((insn->opcode.bytes[0] == 0xff &&
(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
@@ -237,6 +238,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
return (start <= target && target <= start + len);
}
+static int insn_is_indirect_jump(struct insn *insn)
+{
+ int ret = __insn_is_indirect_jump(insn);
+
+#ifdef CONFIG_RETPOLINE
+ /*
+ * Jump to x86_indirect_thunk_* is treated as an indirect jump.
+ * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with
+ * older gcc may use indirect jump. So we add this check instead of
+ * replace indirect-jump check.
+ */
+ if (!ret)
+ ret = insn_jump_into_range(insn,
+ (unsigned long)__indirect_thunk_start,
+ (unsigned long)__indirect_thunk_end -
+ (unsigned long)__indirect_thunk_start);
+#endif
+ return ret;
+}
+
/* Decode whole function to ensure any instructions don't jump into target */
static int can_optimize(unsigned long paddr)
{
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 1c1eae961340..26d713ecad34 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -5,6 +5,11 @@
* Copyright (C) 2002 Andi Kleen
*
* This handles calls from both 32bit and 64bit mode.
+ *
+ * Lock order:
+ * contex.ldt_usr_sem
+ * mmap_sem
+ * context.lock
*/
#include <linux/errno.h>
@@ -19,6 +24,7 @@
#include <linux/uaccess.h>
#include <asm/ldt.h>
+#include <asm/tlb.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
@@ -42,17 +48,15 @@ static void refresh_ldt_segments(void)
#endif
}
-/* context.lock is held for us, so we don't need any locking. */
+/* context.lock is held by the task which issued the smp function call */
static void flush_ldt(void *__mm)
{
struct mm_struct *mm = __mm;
- mm_context_t *pc;
if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm)
return;
- pc = &mm->context;
- set_ldt(pc->ldt->entries, pc->ldt->nr_entries);
+ load_mm_ldt(mm);
refresh_ldt_segments();
}
@@ -89,25 +93,143 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
return NULL;
}
+ /* The new LDT isn't aliased for PTI yet. */
+ new_ldt->slot = -1;
+
new_ldt->nr_entries = num_entries;
return new_ldt;
}
+/*
+ * If PTI is enabled, this maps the LDT into the kernelmode and
+ * usermode tables for the given mm.
+ *
+ * There is no corresponding unmap function. Even if the LDT is freed, we
+ * leave the PTEs around until the slot is reused or the mm is destroyed.
+ * This is harmless: the LDT is always in ordinary memory, and no one will
+ * access the freed slot.
+ *
+ * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
+ * it useful, and the flush would slow down modify_ldt().
+ */
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ bool is_vmalloc, had_top_level_entry;
+ unsigned long va;
+ spinlock_t *ptl;
+ pgd_t *pgd;
+ int i;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return 0;
+
+ /*
+ * Any given ldt_struct should have map_ldt_struct() called at most
+ * once.
+ */
+ WARN_ON(ldt->slot != -1);
+
+ /*
+ * Did we already have the top level entry allocated? We can't
+ * use pgd_none() for this because it doens't do anything on
+ * 4-level page table kernels.
+ */
+ pgd = pgd_offset(mm, LDT_BASE_ADDR);
+ had_top_level_entry = (pgd->pgd != 0);
+
+ is_vmalloc = is_vmalloc_addr(ldt->entries);
+
+ for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+ unsigned long offset = i << PAGE_SHIFT;
+ const void *src = (char *)ldt->entries + offset;
+ unsigned long pfn;
+ pte_t pte, *ptep;
+
+ va = (unsigned long)ldt_slot_va(slot) + offset;
+ pfn = is_vmalloc ? vmalloc_to_pfn(src) :
+ page_to_pfn(virt_to_page(src));
+ /*
+ * Treat the PTI LDT range as a *userspace* range.
+ * get_locked_pte() will allocate all needed pagetables
+ * and account for them in this mm.
+ */
+ ptep = get_locked_pte(mm, va, &ptl);
+ if (!ptep)
+ return -ENOMEM;
+ /*
+ * Map it RO so the easy to find address is not a primary
+ * target via some kernel interface which misses a
+ * permission check.
+ */
+ pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL));
+ set_pte_at(mm, va, ptep, pte);
+ pte_unmap_unlock(ptep, ptl);
+ }
+
+ if (mm->context.ldt) {
+ /*
+ * We already had an LDT. The top-level entry should already
+ * have been allocated and synchronized with the usermode
+ * tables.
+ */
+ WARN_ON(!had_top_level_entry);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
+ } else {
+ /*
+ * This is the first time we're mapping an LDT for this process.
+ * Sync the pgd to the usermode tables.
+ */
+ WARN_ON(had_top_level_entry);
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
+ set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+ }
+ }
+
+ va = (unsigned long)ldt_slot_va(slot);
+ flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
+
+ ldt->slot = slot;
+#endif
+ return 0;
+}
+
+static void free_ldt_pgtables(struct mm_struct *mm)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ struct mmu_gather tlb;
+ unsigned long start = LDT_BASE_ADDR;
+ unsigned long end = start + (1UL << PGDIR_SHIFT);
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ tlb_gather_mmu(&tlb, mm, start, end);
+ free_pgd_range(&tlb, start, end, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+#endif
+}
+
/* After calling this, the LDT is immutable. */
static void finalize_ldt_struct(struct ldt_struct *ldt)
{
paravirt_alloc_ldt(ldt->entries, ldt->nr_entries);
}
-/* context.lock is held */
-static void install_ldt(struct mm_struct *current_mm,
- struct ldt_struct *ldt)
+static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt)
{
+ mutex_lock(&mm->context.lock);
+
/* Synchronizes with READ_ONCE in load_mm_ldt. */
- smp_store_release(&current_mm->context.ldt, ldt);
+ smp_store_release(&mm->context.ldt, ldt);
- /* Activate the LDT for all CPUs using current_mm. */
- on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+ /* Activate the LDT for all CPUs using currents mm. */
+ on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true);
+
+ mutex_unlock(&mm->context.lock);
}
static void free_ldt_struct(struct ldt_struct *ldt)
@@ -124,27 +246,20 @@ static void free_ldt_struct(struct ldt_struct *ldt)
}
/*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
+ * Called on fork from arch_dup_mmap(). Just copy the current LDT state,
+ * the new task is not running, so nothing can be installed.
*/
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
+int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
{
struct ldt_struct *new_ldt;
- struct mm_struct *old_mm;
int retval = 0;
- mutex_init(&mm->context.lock);
- old_mm = current->mm;
- if (!old_mm) {
- mm->context.ldt = NULL;
+ if (!old_mm)
return 0;
- }
mutex_lock(&old_mm->context.lock);
- if (!old_mm->context.ldt) {
- mm->context.ldt = NULL;
+ if (!old_mm->context.ldt)
goto out_unlock;
- }
new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries);
if (!new_ldt) {
@@ -156,6 +271,12 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
new_ldt->nr_entries * LDT_ENTRY_SIZE);
finalize_ldt_struct(new_ldt);
+ retval = map_ldt_struct(mm, new_ldt, 0);
+ if (retval) {
+ free_ldt_pgtables(mm);
+ free_ldt_struct(new_ldt);
+ goto out_unlock;
+ }
mm->context.ldt = new_ldt;
out_unlock:
@@ -174,13 +295,18 @@ void destroy_context_ldt(struct mm_struct *mm)
mm->context.ldt = NULL;
}
+void ldt_arch_exit_mmap(struct mm_struct *mm)
+{
+ free_ldt_pgtables(mm);
+}
+
static int read_ldt(void __user *ptr, unsigned long bytecount)
{
struct mm_struct *mm = current->mm;
unsigned long entries_size;
int retval;
- mutex_lock(&mm->context.lock);
+ down_read(&mm->context.ldt_usr_sem);
if (!mm->context.ldt) {
retval = 0;
@@ -209,7 +335,7 @@ static int read_ldt(void __user *ptr, unsigned long bytecount)
retval = bytecount;
out_unlock:
- mutex_unlock(&mm->context.lock);
+ up_read(&mm->context.ldt_usr_sem);
return retval;
}
@@ -269,7 +395,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
ldt.avl = 0;
}
- mutex_lock(&mm->context.lock);
+ if (down_write_killable(&mm->context.ldt_usr_sem))
+ return -EINTR;
old_ldt = mm->context.ldt;
old_nr_entries = old_ldt ? old_ldt->nr_entries : 0;
@@ -286,12 +413,31 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
new_ldt->entries[ldt_info.entry_number] = ldt;
finalize_ldt_struct(new_ldt);
+ /*
+ * If we are using PTI, map the new LDT into the userspace pagetables.
+ * If there is already an LDT, use the other slot so that other CPUs
+ * will continue to use the old LDT until install_ldt() switches
+ * them over to the new LDT.
+ */
+ error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0);
+ if (error) {
+ /*
+ * This only can fail for the first LDT setup. If an LDT is
+ * already installed then the PTE page is already
+ * populated. Mop up a half populated page table.
+ */
+ if (!WARN_ON_ONCE(old_ldt))
+ free_ldt_pgtables(mm);
+ free_ldt_struct(new_ldt);
+ goto out_unlock;
+ }
+
install_ldt(mm, new_ldt);
free_ldt_struct(old_ldt);
error = 0;
out_unlock:
- mutex_unlock(&mm->context.lock);
+ up_write(&mm->context.ldt_usr_sem);
out:
return error;
}
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 00bc751c861c..edfede768688 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -48,8 +48,6 @@ static void load_segments(void)
"\tmovl $"STR(__KERNEL_DS)",%%eax\n"
"\tmovl %%eax,%%ds\n"
"\tmovl %%eax,%%es\n"
- "\tmovl %%eax,%%fs\n"
- "\tmovl %%eax,%%gs\n"
"\tmovl %%eax,%%ss\n"
: : : "eax", "memory");
#undef STR
@@ -232,8 +230,8 @@ void machine_kexec(struct kimage *image)
* The gdt & idt are now invalid.
* If you want to load them you must set up your own idt & gdt.
*/
- set_gdt(phys_to_virt(0), 0);
idt_invalidate(phys_to_virt(0));
+ set_gdt(phys_to_virt(0), 0);
/* now call it */
image->start = relocate_kernel_ptr((unsigned long)image->head,
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 3a4b12809ab5..27d0a1712663 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -281,7 +281,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
int ELCR_fallback = 0;
intsrc.type = MP_INTSRC;
- intsrc.irqflag = 0; /* conforming */
+ intsrc.irqflag = MP_IRQTRIG_DEFAULT | MP_IRQPOL_DEFAULT;
intsrc.srcbus = 0;
intsrc.dstapic = mpc_ioapic_id(0);
@@ -324,10 +324,13 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
* copy that information over to the MP table in the
* irqflag field (level sensitive, active high polarity).
*/
- if (ELCR_trigger(i))
- intsrc.irqflag = 13;
- else
- intsrc.irqflag = 0;
+ if (ELCR_trigger(i)) {
+ intsrc.irqflag = MP_IRQTRIG_LEVEL |
+ MP_IRQPOL_ACTIVE_HIGH;
+ } else {
+ intsrc.irqflag = MP_IRQTRIG_DEFAULT |
+ MP_IRQPOL_DEFAULT;
+ }
}
intsrc.srcbusirq = i;
@@ -419,7 +422,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
construct_ioapic_table(mpc_default_type);
lintsrc.type = MP_LINTSRC;
- lintsrc.irqflag = 0; /* conforming */
+ lintsrc.irqflag = MP_IRQTRIG_DEFAULT | MP_IRQPOL_DEFAULT;
lintsrc.srcbusid = 0;
lintsrc.srcbusirq = 0;
lintsrc.destapic = MP_APIC_ALL;
@@ -664,7 +667,7 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m)
if (m->irqtype != mp_INT)
return 0;
- if (m->irqflag != 0x0f)
+ if (m->irqflag != (MP_IRQTRIG_LEVEL | MP_IRQPOL_ACTIVE_LOW))
return 0;
/* not legacy */
@@ -673,7 +676,8 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m)
if (mp_irqs[i].irqtype != mp_INT)
continue;
- if (mp_irqs[i].irqflag != 0x0f)
+ if (mp_irqs[i].irqflag != (MP_IRQTRIG_LEVEL |
+ MP_IRQPOL_ACTIVE_LOW))
continue;
if (mp_irqs[i].srcbus != m->srcbus)
@@ -784,7 +788,8 @@ static int __init replace_intsrc_all(struct mpc_table *mpc,
if (mp_irqs[i].irqtype != mp_INT)
continue;
- if (mp_irqs[i].irqflag != 0x0f)
+ if (mp_irqs[i].irqflag != (MP_IRQTRIG_LEVEL |
+ MP_IRQPOL_ACTIVE_LOW))
continue;
if (nr_m_spare > 0) {
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index ac0be8283325..9edadabf04f6 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -10,7 +10,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
@@ -60,7 +59,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_mmu_ops, read_cr2);
PATCH_SITE(pv_mmu_ops, read_cr3);
PATCH_SITE(pv_mmu_ops, write_cr3);
- PATCH_SITE(pv_mmu_ops, flush_tlb_single);
PATCH_SITE(pv_cpu_ops, wbinvd);
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
index 39a59299bfa0..235fe6008ac8 100644
--- a/arch/x86/kernel/platform-quirks.c
+++ b/arch/x86/kernel/platform-quirks.c
@@ -9,6 +9,7 @@ void __init x86_early_init_platform_quirks(void)
{
x86_platform.legacy.i8042 = X86_LEGACY_I8042_EXPECTED_PRESENT;
x86_platform.legacy.rtc = 1;
+ x86_platform.legacy.warm_reset = 1;
x86_platform.legacy.reserve_bios_regions = 0;
x86_platform.legacy.devices.pnpbios = 1;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 97fb3e5737f5..03408b942adb 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -21,7 +21,6 @@
#include <linux/dmi.h>
#include <linux/utsname.h>
#include <linux/stackprotector.h>
-#include <linux/tick.h>
#include <linux/cpuidle.h>
#include <trace/events/power.h>
#include <linux/hw_breakpoint.h>
@@ -47,7 +46,7 @@
* section. Since TSS's are completely CPU-local, we want them
* on exact cacheline boundaries, to eliminate cacheline ping-pong.
*/
-__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
+__visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
.x86_tss = {
/*
* .sp0 is only used when entering ring 0 from a lower
@@ -56,6 +55,16 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
* Poison it.
*/
.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
+
+#ifdef CONFIG_X86_64
+ /*
+ * .sp1 is cpu_current_top_of_stack. The init task never
+ * runs user code, but cpu_current_top_of_stack should still
+ * be well defined before the first context switch.
+ */
+ .sp1 = TOP_OF_INIT_STACK,
+#endif
+
#ifdef CONFIG_X86_32
.ss0 = __KERNEL_DS,
.ss1 = __KERNEL_CS,
@@ -71,11 +80,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
*/
.io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 },
#endif
-#ifdef CONFIG_X86_32
- .SYSENTER_stack_canary = STACK_END_MAGIC,
-#endif
};
-EXPORT_PER_CPU_SYMBOL(cpu_tss);
+EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);
DEFINE_PER_CPU(bool, __tss_limit_invalid);
EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
@@ -104,7 +110,7 @@ void exit_thread(struct task_struct *tsk)
struct fpu *fpu = &t->fpu;
if (bp) {
- struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
+ struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu());
t->io_bitmap_ptr = NULL;
clear_thread_flag(TIF_IO_BITMAP);
@@ -299,7 +305,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
}
if ((tifp ^ tifn) & _TIF_NOTSC)
- cr4_toggle_bits(X86_CR4_TSD);
+ cr4_toggle_bits_irqsoff(X86_CR4_TSD);
if ((tifp ^ tifn) & _TIF_NOCPUID)
set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
@@ -373,19 +379,24 @@ void stop_this_cpu(void *dummy)
disable_local_APIC();
mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
+ /*
+ * Use wbinvd on processors that support SME. This provides support
+ * for performing a successful kexec when going from SME inactive
+ * to SME active (or vice-versa). The cache must be cleared so that
+ * if there are entries with the same physical address, both with and
+ * without the encryption bit, they don't race each other when flushed
+ * and potentially end up with the wrong entry being committed to
+ * memory.
+ */
+ if (boot_cpu_has(X86_FEATURE_SME))
+ native_wbinvd();
for (;;) {
/*
- * Use wbinvd followed by hlt to stop the processor. This
- * provides support for kexec on a processor that supports
- * SME. With kexec, going from SME inactive to SME active
- * requires clearing cache entries so that addresses without
- * the encryption bit set don't corrupt the same physical
- * address that has the encryption bit set when caches are
- * flushed. To achieve this a wbinvd is performed followed by
- * a hlt. Even if the processor is not in the kexec/SME
- * scenario this only adds a wbinvd to a halting processor.
+ * Use native_halt() so that memory contents don't change
+ * (stack usage and variables) after possibly issuing the
+ * native_wbinvd() above.
*/
- asm volatile("wbinvd; hlt" : : : "memory");
+ native_halt();
}
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 45bf0c5f93e1..5224c6099184 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -234,7 +234,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
struct fpu *prev_fpu = &prev->fpu;
struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
- struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
+ struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu);
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index eeeb34f85c25..c75466232016 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -69,9 +69,8 @@ void __show_regs(struct pt_regs *regs, int all)
unsigned int fsindex, gsindex;
unsigned int ds, cs, es;
- printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip);
- printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss,
- regs->sp, regs->flags);
+ show_iret_regs(regs);
+
if (regs->orig_ax != -1)
pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax);
else
@@ -88,6 +87,9 @@ void __show_regs(struct pt_regs *regs, int all)
printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
regs->r13, regs->r14, regs->r15);
+ if (!all)
+ return;
+
asm("movl %%ds,%0" : "=r" (ds));
asm("movl %%cs,%0" : "=r" (cs));
asm("movl %%es,%0" : "=r" (es));
@@ -98,9 +100,6 @@ void __show_regs(struct pt_regs *regs, int all)
rdmsrl(MSR_GS_BASE, gs);
rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
- if (!all)
- return;
-
cr0 = read_cr0();
cr2 = read_cr2();
cr3 = __read_cr3();
@@ -400,7 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
struct fpu *prev_fpu = &prev->fpu;
struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
- struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
+ struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu);
WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
this_cpu_read(irq_count) != -1);
@@ -462,6 +461,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
* Switch the PDA and FPU contexts.
*/
this_cpu_write(current_task, next_p);
+ this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
/* Reload sp0. */
update_sp0(next_p);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 8af2e8d0c0a1..1ae67e982af7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -114,7 +114,6 @@
#include <asm/alternative.h>
#include <asm/prom.h>
#include <asm/microcode.h>
-#include <asm/mmu_context.h>
#include <asm/kaslr.h>
#include <asm/unwind.h>
@@ -364,16 +363,6 @@ static void __init reserve_initrd(void)
!ramdisk_image || !ramdisk_size)
return; /* No initrd provided by bootloader */
- /*
- * If SME is active, this memory will be marked encrypted by the
- * kernel when it is accessed (including relocation). However, the
- * ramdisk image was loaded decrypted by the bootloader, so make
- * sure that it is encrypted before accessing it. For SEV the
- * ramdisk will already be encrypted, so only do this for SME.
- */
- if (sme_active())
- sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image);
-
initrd_start = 0;
mapped_size = memblock_mem_size(max_pfn_mapped);
@@ -906,9 +895,6 @@ void __init setup_arch(char **cmdline_p)
set_bit(EFI_BOOT, &efi.flags);
set_bit(EFI_64BIT, &efi.flags);
}
-
- if (efi_enabled(EFI_BOOT))
- efi_memblock_x86_reserve_range();
#endif
x86_init.oem.arch_setup();
@@ -962,6 +948,8 @@ void __init setup_arch(char **cmdline_p)
parse_early_param();
+ if (efi_enabled(EFI_BOOT))
+ efi_memblock_x86_reserve_range();
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Memory used by the kernel cannot be hot-removed because Linux
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 8c6da1a643da..ac057f9b0763 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -25,8 +25,8 @@ static inline void signal_compat_build_tests(void)
* limits also have to look at this code. Make sure any
* new fields are handled in copy_siginfo_to_user32()!
*/
- BUILD_BUG_ON(NSIGILL != 8);
- BUILD_BUG_ON(NSIGFPE != 8);
+ BUILD_BUG_ON(NSIGILL != 11);
+ BUILD_BUG_ON(NSIGFPE != 13);
BUILD_BUG_ON(NSIGSEGV != 4);
BUILD_BUG_ON(NSIGBUS != 5);
BUILD_BUG_ON(NSIGTRAP != 4);
@@ -64,7 +64,7 @@ static inline void signal_compat_build_tests(void)
CHECK_SI_SIZE (_kill, 2*sizeof(int));
CHECK_CSI_OFFSET(_timer);
- CHECK_CSI_SIZE (_timer, 5*sizeof(int));
+ CHECK_CSI_SIZE (_timer, 3*sizeof(int));
CHECK_SI_SIZE (_timer, 6*sizeof(int));
CHECK_CSI_OFFSET(_rt);
@@ -75,9 +75,11 @@ static inline void signal_compat_build_tests(void)
CHECK_CSI_SIZE (_sigchld, 5*sizeof(int));
CHECK_SI_SIZE (_sigchld, 8*sizeof(int));
+#ifdef CONFIG_X86_X32_ABI
CHECK_CSI_OFFSET(_sigchld_x32);
CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int));
/* no _sigchld_x32 in the generic siginfo_t */
+#endif
CHECK_CSI_OFFSET(_sigfault);
CHECK_CSI_SIZE (_sigfault, 4*sizeof(int));
@@ -96,6 +98,8 @@ static inline void signal_compat_build_tests(void)
void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
{
+ signal_compat_build_tests();
+
/* Don't leak in-kernel non-uapi flags to user-space */
if (oact)
oact->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
@@ -111,116 +115,3 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
if (in_x32_syscall())
act->sa.sa_flags |= SA_X32_ABI;
}
-
-int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
- bool x32_ABI)
-{
- int err = 0;
-
- signal_compat_build_tests();
-
- if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
- return -EFAULT;
-
- put_user_try {
- /* If you change siginfo_t structure, please make sure that
- this code is fixed accordingly.
- It should never copy any pad contained in the structure
- to avoid security leaks, but must copy the generic
- 3 ints plus the relevant union member. */
- put_user_ex(from->si_signo, &to->si_signo);
- put_user_ex(from->si_errno, &to->si_errno);
- put_user_ex(from->si_code, &to->si_code);
-
- if (from->si_code < 0) {
- put_user_ex(from->si_pid, &to->si_pid);
- put_user_ex(from->si_uid, &to->si_uid);
- put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
- } else {
- /*
- * First 32bits of unions are always present:
- * si_pid === si_band === si_tid === si_addr(LS half)
- */
- put_user_ex(from->_sifields._pad[0],
- &to->_sifields._pad[0]);
- switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_FAULT:
- if (from->si_signo == SIGBUS &&
- (from->si_code == BUS_MCEERR_AR ||
- from->si_code == BUS_MCEERR_AO))
- put_user_ex(from->si_addr_lsb, &to->si_addr_lsb);
-
- if (from->si_signo == SIGSEGV) {
- if (from->si_code == SEGV_BNDERR) {
- compat_uptr_t lower = (unsigned long)from->si_lower;
- compat_uptr_t upper = (unsigned long)from->si_upper;
- put_user_ex(lower, &to->si_lower);
- put_user_ex(upper, &to->si_upper);
- }
- if (from->si_code == SEGV_PKUERR)
- put_user_ex(from->si_pkey, &to->si_pkey);
- }
- break;
- case SIL_SYS:
- put_user_ex(from->si_syscall, &to->si_syscall);
- put_user_ex(from->si_arch, &to->si_arch);
- break;
- case SIL_CHLD:
- if (!x32_ABI) {
- put_user_ex(from->si_utime, &to->si_utime);
- put_user_ex(from->si_stime, &to->si_stime);
- } else {
- put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
- put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
- }
- put_user_ex(from->si_status, &to->si_status);
- /* FALL THROUGH */
- case SIL_KILL:
- put_user_ex(from->si_uid, &to->si_uid);
- break;
- case SIL_POLL:
- put_user_ex(from->si_fd, &to->si_fd);
- break;
- case SIL_TIMER:
- put_user_ex(from->si_overrun, &to->si_overrun);
- put_user_ex(ptr_to_compat(from->si_ptr),
- &to->si_ptr);
- break;
- case SIL_RT:
- put_user_ex(from->si_uid, &to->si_uid);
- put_user_ex(from->si_int, &to->si_int);
- break;
- }
- }
- } put_user_catch(err);
-
- return err;
-}
-
-/* from syscall's path, where we know the ABI */
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
-{
- return __copy_siginfo_to_user32(to, from, in_x32_syscall());
-}
-
-int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
-{
- int err = 0;
- u32 ptr32;
-
- if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
- return -EFAULT;
-
- get_user_try {
- get_user_ex(to->si_signo, &from->si_signo);
- get_user_ex(to->si_errno, &from->si_errno);
- get_user_ex(to->si_code, &from->si_code);
-
- get_user_ex(to->si_pid, &from->si_pid);
- get_user_ex(to->si_uid, &from->si_uid);
- get_user_ex(ptr32, &from->si_ptr);
- to->si_ptr = compat_ptr(ptr32);
- } get_user_catch(err);
-
- return err;
-}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3d01df7d7cf6..6f27facbaa9b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -75,7 +75,6 @@
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
#include <asm/i8259.h>
-#include <asm/realmode.h>
#include <asm/misc.h>
#include <asm/qspinlock.h>
@@ -106,7 +105,7 @@ EXPORT_SYMBOL(__max_logical_packages);
static unsigned int logical_packages __read_mostly;
/* Maximum number of SMT threads on any online core */
-int __max_smt_threads __read_mostly;
+int __read_mostly __max_smt_threads = 1;
/* Flag to indicate if a complete sched domain rebuild is required */
bool x86_topology_update;
@@ -126,14 +125,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(0xa, 0xf);
spin_unlock_irqrestore(&rtc_lock, flags);
- local_flush_tlb();
- pr_debug("1.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
start_eip >> 4;
- pr_debug("2.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
start_eip & 0xf;
- pr_debug("3.\n");
}
static inline void smpboot_restore_warm_reset_vector(void)
@@ -141,11 +136,6 @@ static inline void smpboot_restore_warm_reset_vector(void)
unsigned long flags;
/*
- * Install writable page 0 entry to set BIOS data area.
- */
- local_flush_tlb();
-
- /*
* Paranoid: Set warm reset code and vector here back
* to default values.
*/
@@ -237,7 +227,7 @@ static void notrace start_secondary(void *unused)
load_cr3(swapper_pg_dir);
__flush_tlb_all();
#endif
-
+ load_current_idt();
cpu_init();
x86_cpuinit.early_percpu_clock_init();
preempt_disable();
@@ -932,12 +922,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
initial_code = (unsigned long)start_secondary;
initial_stack = idle->thread.sp;
- /*
- * Enable the espfix hack for this CPU
- */
-#ifdef CONFIG_X86_ESPFIX64
+ /* Enable the espfix hack for this CPU */
init_espfix_ap(cpu);
-#endif
/* So we see what's up */
announce_cpu(cpu, apicid);
@@ -947,7 +933,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
* the targeted processor.
*/
- if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+ if (x86_platform.legacy.warm_reset) {
pr_debug("Setting warm reset code and vector.\n");
@@ -1019,7 +1005,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
/* mark "stuck" area as not stuck */
*trampoline_status = 0;
- if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+ if (x86_platform.legacy.warm_reset) {
/*
* Cleanup possible dangling ends...
*/
@@ -1304,7 +1290,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
* Today neither Intel nor AMD support heterogenous systems so
* extrapolate the boot cpu's data to all packages.
*/
- ncpus = cpu_data(0).booted_cores * smp_num_siblings;
+ ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
pr_info("Max logical packages: %u\n", __max_logical_packages);
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 77835bc021c7..093f2ea5dd56 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -102,7 +102,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
- regs = unwind_get_entry_regs(&state);
+ regs = unwind_get_entry_regs(&state, NULL);
if (regs) {
/*
* Kernel mode registers on the stack indicate an
@@ -164,8 +164,12 @@ int save_stack_trace_tsk_reliable(struct task_struct *tsk,
{
int ret;
+ /*
+ * If the task doesn't have a stack (e.g., a zombie), the stack is
+ * "reliably" empty.
+ */
if (!try_get_task_stack(tsk))
- return -EINVAL;
+ return 0;
ret = __save_stack_trace_reliable(trace, tsk);
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index a4eb27918ceb..a2486f444073 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -138,6 +138,17 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
return -1;
set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
pte_unmap(pte);
+
+ /*
+ * PTI poisons low addresses in the kernel page tables in the
+ * name of making them unusable for userspace. To execute
+ * code at such a low address, the poison must be cleared.
+ *
+ * Note: 'pgd' actually gets set in p4d_alloc() _or_
+ * pud_alloc() depending on 4/5-level paging.
+ */
+ pgd->pgd &= ~_PAGE_NX;
+
return 0;
}
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 749d189f8cd4..774ebafa97c4 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -69,9 +69,12 @@ static struct irqaction irq0 = {
static void __init setup_default_timer_irq(void)
{
- if (!nr_legacy_irqs())
- return;
- setup_irq(0, &irq0);
+ /*
+ * Unconditionally register the legacy timer; even without legacy
+ * PIC/PIT we need this for the HPET0 in legacy replacement mode.
+ */
+ if (setup_irq(0, &irq0))
+ pr_info("Failed to register legacy timer interrupt\n");
}
/* Default timer init function */
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 9a9c9b076955..a5b802a12212 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -93,17 +93,10 @@ static void set_tls_desc(struct task_struct *p, int idx,
cpu = get_cpu();
while (n-- > 0) {
- if (LDT_empty(info) || LDT_zero(info)) {
+ if (LDT_empty(info) || LDT_zero(info))
memset(desc, 0, sizeof(*desc));
- } else {
+ else
fill_ldt(desc, info);
-
- /*
- * Always set the accessed bit so that the CPU
- * doesn't try to write to the (read-only) GDT.
- */
- desc->type |= 1;
- }
++info;
++desc;
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 989514c94a55..446c9ef8cfc3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -51,6 +51,7 @@
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/fpu/internal.h>
+#include <asm/cpu_entry_area.h>
#include <asm/mce.h>
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
@@ -348,23 +349,42 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
/*
* If IRET takes a non-IST fault on the espfix64 stack, then we
- * end up promoting it to a doublefault. In that case, modify
- * the stack to make it look like we just entered the #GP
- * handler from user space, similar to bad_iret.
+ * end up promoting it to a doublefault. In that case, take
+ * advantage of the fact that we're not using the normal (TSS.sp0)
+ * stack right now. We can write a fake #GP(0) frame at TSS.sp0
+ * and then modify our own IRET frame so that, when we return,
+ * we land directly at the #GP(0) vector with the stack already
+ * set up according to its expectations.
+ *
+ * The net result is that our #GP handler will think that we
+ * entered from usermode with the bad user context.
*
* No need for ist_enter here because we don't use RCU.
*/
- if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+ if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY &&
regs->cs == __KERNEL_CS &&
regs->ip == (unsigned long)native_irq_return_iret)
{
- struct pt_regs *normal_regs = task_pt_regs(current);
+ struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
- /* Fake a #GP(0) from userspace. */
- memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
- normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */
+ /*
+ * regs->sp points to the failing IRET frame on the
+ * ESPFIX64 stack. Copy it to the entry stack. This fills
+ * in gpregs->ss through gpregs->ip.
+ *
+ */
+ memmove(&gpregs->ip, (void *)regs->sp, 5*8);
+ gpregs->orig_ax = 0; /* Missing (lost) #GP error code */
+
+ /*
+ * Adjust our frame so that we return straight to the #GP
+ * vector with the expected RSP value. This is safe because
+ * we won't enable interupts or schedule before we invoke
+ * general_protection, so nothing will clobber the stack
+ * frame we just set up.
+ */
regs->ip = (unsigned long)general_protection;
- regs->sp = (unsigned long)&normal_regs->orig_ax;
+ regs->sp = (unsigned long)&gpregs->orig_ax;
return;
}
@@ -389,7 +409,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
*
* Processors update CR2 whenever a page fault is detected. If a
* second page fault occurs while an earlier page fault is being
- * deliv- ered, the faulting linear address of the second fault will
+ * delivered, the faulting linear address of the second fault will
* overwrite the contents of CR2 (replacing the previous
* address). These updates to CR2 occur even if the page fault
* results in a double fault or occurs during the delivery of a
@@ -605,14 +625,15 @@ NOKPROBE_SYMBOL(do_int3);
#ifdef CONFIG_X86_64
/*
- * Help handler running on IST stack to switch off the IST stack if the
- * interrupted code was in user mode. The actual stack switch is done in
- * entry_64.S
+ * Help handler running on a per-cpu (IST or entry trampoline) stack
+ * to switch to the normal thread stack if the interrupted code was in
+ * user mode. The actual stack switch is done in entry_64.S
*/
asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
{
- struct pt_regs *regs = task_pt_regs(current);
- *regs = *eregs;
+ struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1;
+ if (regs != eregs)
+ *regs = *eregs;
return regs;
}
NOKPROBE_SYMBOL(sync_regs);
@@ -628,13 +649,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
/*
* This is called from entry_64.S early in handling a fault
* caused by a bad iret to user mode. To handle the fault
- * correctly, we want move our stack frame to task_pt_regs
- * and we want to pretend that the exception came from the
- * iret target.
+ * correctly, we want to move our stack frame to where it would
+ * be had we entered directly on the entry stack (rather than
+ * just below the IRET frame) and we want to pretend that the
+ * exception came from the IRET target.
*/
struct bad_iret_stack *new_stack =
- container_of(task_pt_regs(current),
- struct bad_iret_stack, regs);
+ (struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
/* Copy the IRET target to the new stack. */
memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
@@ -795,14 +816,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
debug_stack_usage_dec();
exit:
-#if defined(CONFIG_X86_32)
- /*
- * This is the most likely code path that involves non-trivial use
- * of the SYSENTER stack. Check that we haven't overrun it.
- */
- WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC,
- "Overran or corrupted SYSENTER stack\n");
-#endif
ist_exit(regs);
}
NOKPROBE_SYMBOL(do_debug);
@@ -929,6 +942,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
void __init trap_init(void)
{
+ /* Init cpu_entry_area before IST entries are set up */
+ setup_cpu_entry_areas();
+
idt_setup_traps();
/*
@@ -936,8 +952,9 @@ void __init trap_init(void)
* "sidt" instruction will not leak the location of the kernel, and
* to defend the IDT against arbitrary memory write vulnerabilities.
* It will be reloaded in cpu_init() */
- __set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
- idt_descr.address = fix_to_virt(FIX_RO_IDT);
+ cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table),
+ PAGE_KERNEL_RO);
+ idt_descr.address = CPU_ENTRY_AREA_RO_IDT;
/*
* Should be a barrier for any external CPU state:
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8ea117f8142e..fb4302738410 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -25,6 +25,7 @@
#include <asm/geode.h>
#include <asm/apic.h>
#include <asm/intel-family.h>
+#include <asm/i8259.h>
unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
@@ -363,6 +364,20 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin)
unsigned long tscmin, tscmax;
int pitcnt;
+ if (!has_legacy_pic()) {
+ /*
+ * Relies on tsc_early_delay_calibrate() to have given us semi
+ * usable udelay(), wait for the same 50ms we would have with
+ * the PIT loop below.
+ */
+ udelay(10 * USEC_PER_MSEC);
+ udelay(10 * USEC_PER_MSEC);
+ udelay(10 * USEC_PER_MSEC);
+ udelay(10 * USEC_PER_MSEC);
+ udelay(10 * USEC_PER_MSEC);
+ return ULONG_MAX;
+ }
+
/* Set the Gate high, disable speaker */
outb((inb(0x61) & ~0x02) | 0x01, 0x61);
@@ -487,6 +502,9 @@ static unsigned long quick_pit_calibrate(void)
u64 tsc, delta;
unsigned long d1, d2;
+ if (!has_legacy_pic())
+ return 0;
+
/* Set the Gate high, disable speaker */
outb((inb(0x61) & ~0x02) | 0x01, 0x61);
@@ -602,7 +620,6 @@ unsigned long native_calibrate_tsc(void)
case INTEL_FAM6_KABYLAKE_DESKTOP:
crystal_khz = 24000; /* 24.0 MHz */
break;
- case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_ATOM_DENVERTON:
crystal_khz = 25000; /* 25.0 MHz */
break;
@@ -612,6 +629,8 @@ unsigned long native_calibrate_tsc(void)
}
}
+ if (crystal_khz == 0)
+ return 0;
/*
* TSC frequency determined by CPUID is a "hardware reported"
* frequency and is the most accurate one so far we have. This
@@ -987,8 +1006,6 @@ static void __init detect_art(void)
/* clocksource code */
-static struct clocksource clocksource_tsc;
-
static void tsc_resume(struct clocksource *cs)
{
tsc_verify_tsc_adjust(true);
@@ -1039,12 +1056,31 @@ static void tsc_cs_tick_stable(struct clocksource *cs)
/*
* .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
*/
+static struct clocksource clocksource_tsc_early = {
+ .name = "tsc-early",
+ .rating = 299,
+ .read = read_tsc,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS |
+ CLOCK_SOURCE_MUST_VERIFY,
+ .archdata = { .vclock_mode = VCLOCK_TSC },
+ .resume = tsc_resume,
+ .mark_unstable = tsc_cs_mark_unstable,
+ .tick_stable = tsc_cs_tick_stable,
+};
+
+/*
+ * Must mark VALID_FOR_HRES early such that when we unregister tsc_early
+ * this one will immediately take over. We will only register if TSC has
+ * been found good.
+ */
static struct clocksource clocksource_tsc = {
.name = "tsc",
.rating = 300,
.read = read_tsc,
.mask = CLOCKSOURCE_MASK(64),
.flags = CLOCK_SOURCE_IS_CONTINUOUS |
+ CLOCK_SOURCE_VALID_FOR_HRES |
CLOCK_SOURCE_MUST_VERIFY,
.archdata = { .vclock_mode = VCLOCK_TSC },
.resume = tsc_resume,
@@ -1168,8 +1204,8 @@ static void tsc_refine_calibration_work(struct work_struct *work)
int cpu;
/* Don't bother refining TSC on unstable systems */
- if (check_tsc_unstable())
- goto out;
+ if (tsc_unstable)
+ return;
/*
* Since the work is started early in boot, we may be
@@ -1221,9 +1257,13 @@ static void tsc_refine_calibration_work(struct work_struct *work)
set_cyc2ns_scale(tsc_khz, cpu, tsc_stop);
out:
+ if (tsc_unstable)
+ return;
+
if (boot_cpu_has(X86_FEATURE_ART))
art_related_clocksource = &clocksource_tsc;
clocksource_register_khz(&clocksource_tsc, tsc_khz);
+ clocksource_unregister(&clocksource_tsc_early);
}
@@ -1232,13 +1272,11 @@ static int __init init_tsc_clocksource(void)
if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
return 0;
+ if (check_tsc_unstable())
+ return 0;
+
if (tsc_clocksource_reliable)
clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
- /* lower the rating if we already know its unstable: */
- if (check_tsc_unstable()) {
- clocksource_tsc.rating = 0;
- clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
- }
if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
@@ -1251,6 +1289,7 @@ static int __init init_tsc_clocksource(void)
if (boot_cpu_has(X86_FEATURE_ART))
art_related_clocksource = &clocksource_tsc;
clocksource_register_khz(&clocksource_tsc, tsc_khz);
+ clocksource_unregister(&clocksource_tsc_early);
return 0;
}
@@ -1315,6 +1354,12 @@ void __init tsc_init(void)
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);
+ if (cpu_khz != tsc_khz) {
+ pr_info("Detected %lu.%03lu MHz TSC",
+ (unsigned long)tsc_khz / 1000,
+ (unsigned long)tsc_khz % 1000);
+ }
+
/* Sanitize TSC ADJUST before cyc2ns gets initialized */
tsc_store_and_check_tsc_adjust(true);
@@ -1349,9 +1394,12 @@ void __init tsc_init(void)
check_system_tsc_reliable();
- if (unsynchronized_tsc())
+ if (unsynchronized_tsc()) {
mark_tsc_unstable("TSCs unsynchronized");
+ return;
+ }
+ clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
detect_art();
}
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index a3f973b2c97a..1f9188f5357c 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -74,8 +74,50 @@ static struct orc_entry *orc_module_find(unsigned long ip)
}
#endif
+#ifdef CONFIG_DYNAMIC_FTRACE
+static struct orc_entry *orc_find(unsigned long ip);
+
+/*
+ * Ftrace dynamic trampolines do not have orc entries of their own.
+ * But they are copies of the ftrace entries that are static and
+ * defined in ftrace_*.S, which do have orc entries.
+ *
+ * If the undwinder comes across a ftrace trampoline, then find the
+ * ftrace function that was used to create it, and use that ftrace
+ * function's orc entrie, as the placement of the return code in
+ * the stack will be identical.
+ */
+static struct orc_entry *orc_ftrace_find(unsigned long ip)
+{
+ struct ftrace_ops *ops;
+ unsigned long caller;
+
+ ops = ftrace_ops_trampoline(ip);
+ if (!ops)
+ return NULL;
+
+ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+ caller = (unsigned long)ftrace_regs_call;
+ else
+ caller = (unsigned long)ftrace_call;
+
+ /* Prevent unlikely recursion */
+ if (ip == caller)
+ return NULL;
+
+ return orc_find(caller);
+}
+#else
+static struct orc_entry *orc_ftrace_find(unsigned long ip)
+{
+ return NULL;
+}
+#endif
+
static struct orc_entry *orc_find(unsigned long ip)
{
+ static struct orc_entry *orc;
+
if (!orc_init)
return NULL;
@@ -111,7 +153,11 @@ static struct orc_entry *orc_find(unsigned long ip)
__stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
/* Module lookup: */
- return orc_module_find(ip);
+ orc = orc_module_find(ip);
+ if (orc)
+ return orc;
+
+ return orc_ftrace_find(ip);
}
static void orc_sort_swap(void *_a, void *_b, int size)
@@ -253,22 +299,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
return NULL;
}
-static bool stack_access_ok(struct unwind_state *state, unsigned long addr,
+static bool stack_access_ok(struct unwind_state *state, unsigned long _addr,
size_t len)
{
struct stack_info *info = &state->stack_info;
+ void *addr = (void *)_addr;
- /*
- * If the address isn't on the current stack, switch to the next one.
- *
- * We may have to traverse multiple stacks to deal with the possibility
- * that info->next_sp could point to an empty stack and the address
- * could be on a subsequent stack.
- */
- while (!on_stack(info, (void *)addr, len))
- if (get_stack_info(info->next_sp, state->task, info,
- &state->stack_mask))
- return false;
+ if (!on_stack(info, addr, len) &&
+ (get_stack_info(addr, state->task, info, &state->stack_mask)))
+ return false;
return true;
}
@@ -283,42 +322,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,
return true;
}
-#define REGS_SIZE (sizeof(struct pt_regs))
-#define SP_OFFSET (offsetof(struct pt_regs, sp))
-#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip))
-#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip))
-
static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
- unsigned long *ip, unsigned long *sp, bool full)
+ unsigned long *ip, unsigned long *sp)
{
- size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE;
- size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET;
- struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE);
-
- if (IS_ENABLED(CONFIG_X86_64)) {
- if (!stack_access_ok(state, addr, regs_size))
- return false;
+ struct pt_regs *regs = (struct pt_regs *)addr;
- *ip = regs->ip;
- *sp = regs->sp;
+ /* x86-32 support will be more complicated due to the &regs->sp hack */
+ BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32));
- return true;
- }
-
- if (!stack_access_ok(state, addr, sp_offset))
+ if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
return false;
*ip = regs->ip;
+ *sp = regs->sp;
+ return true;
+}
- if (user_mode(regs)) {
- if (!stack_access_ok(state, addr + sp_offset,
- REGS_SIZE - SP_OFFSET))
- return false;
+static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr,
+ unsigned long *ip, unsigned long *sp)
+{
+ struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET;
- *sp = regs->sp;
- } else
- *sp = (unsigned long)&regs->sp;
+ if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
+ return false;
+ *ip = regs->ip;
+ *sp = regs->sp;
return true;
}
@@ -327,7 +356,6 @@ bool unwind_next_frame(struct unwind_state *state)
unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
enum stack_type prev_type = state->stack_info.type;
struct orc_entry *orc;
- struct pt_regs *ptregs;
bool indirect = false;
if (unwind_done(state))
@@ -435,7 +463,7 @@ bool unwind_next_frame(struct unwind_state *state)
break;
case ORC_TYPE_REGS:
- if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) {
+ if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
orc_warn("can't dereference registers at %p for ip %pB\n",
(void *)sp, (void *)orig_ip);
goto done;
@@ -447,20 +475,14 @@ bool unwind_next_frame(struct unwind_state *state)
break;
case ORC_TYPE_REGS_IRET:
- if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) {
+ if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
orc_warn("can't dereference iret registers at %p for ip %pB\n",
(void *)sp, (void *)orig_ip);
goto done;
}
- ptregs = container_of((void *)sp, struct pt_regs, ip);
- if ((unsigned long)ptregs >= prev_sp &&
- on_stack(&state->stack_info, ptregs, REGS_SIZE)) {
- state->regs = ptregs;
- state->full_regs = false;
- } else
- state->regs = NULL;
-
+ state->regs = (void *)sp - IRET_FRAME_OFFSET;
+ state->full_regs = false;
state->signal = true;
break;
@@ -553,8 +575,18 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
}
if (get_stack_info((unsigned long *)state->sp, state->task,
- &state->stack_info, &state->stack_mask))
- return;
+ &state->stack_info, &state->stack_mask)) {
+ /*
+ * We weren't on a valid stack. It's possible that
+ * we overflowed a valid stack into a guard page.
+ * See if the next page up is valid so that we can
+ * generate some kind of backtrace if this happens.
+ */
+ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp);
+ if (get_stack_info(next_page, state->task, &state->stack_info,
+ &state->stack_mask))
+ return;
+ }
/*
* The caller can provide the address of the first frame directly
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index a3755d293a48..85c7ef23d99f 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -528,11 +528,11 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
return 0;
}
-static int push_ret_address(struct pt_regs *regs, unsigned long ip)
+static int emulate_push_stack(struct pt_regs *regs, unsigned long val)
{
unsigned long new_sp = regs->sp - sizeof_long();
- if (copy_to_user((void __user *)new_sp, &ip, sizeof_long()))
+ if (copy_to_user((void __user *)new_sp, &val, sizeof_long()))
return -EFAULT;
regs->sp = new_sp;
@@ -566,7 +566,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs
regs->ip += correction;
} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
regs->sp += sizeof_long(); /* Pop incorrect return address */
- if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen))
+ if (emulate_push_stack(regs, utask->vaddr + auprobe->defparam.ilen))
return -ERESTART;
}
/* popf; tell the caller to not touch TF */
@@ -655,7 +655,7 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
*
* But there is corner case, see the comment in ->post_xol().
*/
- if (push_ret_address(regs, new_ip))
+ if (emulate_push_stack(regs, new_ip))
return false;
} else if (!check_jmp_cond(auprobe, regs)) {
offs = 0;
@@ -665,6 +665,16 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
return true;
}
+static bool push_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+ unsigned long *src_ptr = (void *)regs + auprobe->push.reg_offset;
+
+ if (emulate_push_stack(regs, *src_ptr))
+ return false;
+ regs->ip += auprobe->push.ilen;
+ return true;
+}
+
static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
BUG_ON(!branch_is_call(auprobe));
@@ -703,6 +713,10 @@ static const struct uprobe_xol_ops branch_xol_ops = {
.post_xol = branch_post_xol_op,
};
+static const struct uprobe_xol_ops push_xol_ops = {
+ .emulate = push_emulate_op,
+};
+
/* Returns -ENOSYS if branch_xol_ops doesn't handle this insn */
static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
{
@@ -750,6 +764,87 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
return 0;
}
+/* Returns -ENOSYS if push_xol_ops doesn't handle this insn */
+static int push_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
+{
+ u8 opc1 = OPCODE1(insn), reg_offset = 0;
+
+ if (opc1 < 0x50 || opc1 > 0x57)
+ return -ENOSYS;
+
+ if (insn->length > 2)
+ return -ENOSYS;
+ if (insn->length == 2) {
+ /* only support rex_prefix 0x41 (x64 only) */
+#ifdef CONFIG_X86_64
+ if (insn->rex_prefix.nbytes != 1 ||
+ insn->rex_prefix.bytes[0] != 0x41)
+ return -ENOSYS;
+
+ switch (opc1) {
+ case 0x50:
+ reg_offset = offsetof(struct pt_regs, r8);
+ break;
+ case 0x51:
+ reg_offset = offsetof(struct pt_regs, r9);
+ break;
+ case 0x52:
+ reg_offset = offsetof(struct pt_regs, r10);
+ break;
+ case 0x53:
+ reg_offset = offsetof(struct pt_regs, r11);
+ break;
+ case 0x54:
+ reg_offset = offsetof(struct pt_regs, r12);
+ break;
+ case 0x55:
+ reg_offset = offsetof(struct pt_regs, r13);
+ break;
+ case 0x56:
+ reg_offset = offsetof(struct pt_regs, r14);
+ break;
+ case 0x57:
+ reg_offset = offsetof(struct pt_regs, r15);
+ break;
+ }
+#else
+ return -ENOSYS;
+#endif
+ } else {
+ switch (opc1) {
+ case 0x50:
+ reg_offset = offsetof(struct pt_regs, ax);
+ break;
+ case 0x51:
+ reg_offset = offsetof(struct pt_regs, cx);
+ break;
+ case 0x52:
+ reg_offset = offsetof(struct pt_regs, dx);
+ break;
+ case 0x53:
+ reg_offset = offsetof(struct pt_regs, bx);
+ break;
+ case 0x54:
+ reg_offset = offsetof(struct pt_regs, sp);
+ break;
+ case 0x55:
+ reg_offset = offsetof(struct pt_regs, bp);
+ break;
+ case 0x56:
+ reg_offset = offsetof(struct pt_regs, si);
+ break;
+ case 0x57:
+ reg_offset = offsetof(struct pt_regs, di);
+ break;
+ }
+ }
+
+ auprobe->push.reg_offset = reg_offset;
+ auprobe->push.ilen = insn->length;
+ auprobe->ops = &push_xol_ops;
+ return 0;
+}
+
/**
* arch_uprobe_analyze_insn - instruction analysis including validity and fixups.
* @mm: the probed address space.
@@ -771,6 +866,10 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
if (ret != -ENOSYS)
return ret;
+ ret = push_setup_xol_ops(auprobe, &insn);
+ if (ret != -ENOSYS)
+ return ret;
+
/*
* Figure out which fixups default_post_xol_op() will need to perform,
* and annotate defparam->fixups accordingly.
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index a4009fb9be87..9b138a06c1a4 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -61,11 +61,17 @@ jiffies_64 = jiffies;
. = ALIGN(HPAGE_SIZE); \
__end_rodata_hpage_align = .;
+#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE);
+#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE);
+
#else
#define X64_ALIGN_RODATA_BEGIN
#define X64_ALIGN_RODATA_END
+#define ALIGN_ENTRY_TEXT_BEGIN
+#define ALIGN_ENTRY_TEXT_END
+
#endif
PHDRS {
@@ -102,11 +108,28 @@ SECTIONS
CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
+ ALIGN_ENTRY_TEXT_BEGIN
ENTRY_TEXT
IRQENTRY_TEXT
+ ALIGN_ENTRY_TEXT_END
SOFTIRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
+
+#ifdef CONFIG_X86_64
+ . = ALIGN(PAGE_SIZE);
+ _entry_trampoline = .;
+ *(.entry_trampoline)
+ . = ALIGN(PAGE_SIZE);
+ ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
+#endif
+
+#ifdef CONFIG_RETPOLINE
+ __indirect_thunk_start = .;
+ *(.text.__x86.indirect_thunk)
+ __indirect_thunk_end = .;
+#endif
+
/* End of text section */
_etext = .;
} :text = 0x9090
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index cdc70a3a6583..c2cea6651279 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -44,7 +44,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_8086_0001_EDX] = {0x80860001, 0, CPUID_EDX},
[CPUID_1_ECX] = { 1, 0, CPUID_ECX},
[CPUID_C000_0001_EDX] = {0xc0000001, 0, CPUID_EDX},
- [CPUID_8000_0001_ECX] = {0xc0000001, 0, CPUID_ECX},
+ [CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
[CPUID_7_0_EBX] = { 7, 0, CPUID_EBX},
[CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX},
[CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX},
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8079d141792a..290ecf711aec 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -25,6 +25,7 @@
#include <asm/kvm_emulate.h>
#include <linux/stringify.h>
#include <asm/debugreg.h>
+#include <asm/nospec-branch.h>
#include "x86.h"
#include "tss.h"
@@ -1021,8 +1022,8 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf);
flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
- asm("push %[flags]; popf; call *%[fastop]"
- : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags));
+ asm("push %[flags]; popf; " CALL_NOSPEC
+ : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags));
return rc;
}
@@ -1046,7 +1047,6 @@ static void fetch_register_operand(struct operand *op)
static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
{
- ctxt->ops->get_fpu(ctxt);
switch (reg) {
case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1068,13 +1068,11 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
#endif
default: BUG();
}
- ctxt->ops->put_fpu(ctxt);
}
static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
int reg)
{
- ctxt->ops->get_fpu(ctxt);
switch (reg) {
case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1096,12 +1094,10 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
#endif
default: BUG();
}
- ctxt->ops->put_fpu(ctxt);
}
static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
{
- ctxt->ops->get_fpu(ctxt);
switch (reg) {
case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1113,12 +1109,10 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
default: BUG();
}
- ctxt->ops->put_fpu(ctxt);
}
static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
{
- ctxt->ops->get_fpu(ctxt);
switch (reg) {
case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1130,7 +1124,6 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
default: BUG();
}
- ctxt->ops->put_fpu(ctxt);
}
static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1138,9 +1131,7 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt)
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
- ctxt->ops->get_fpu(ctxt);
asm volatile("fninit");
- ctxt->ops->put_fpu(ctxt);
return X86EMUL_CONTINUE;
}
@@ -1151,9 +1142,7 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
- ctxt->ops->get_fpu(ctxt);
asm volatile("fnstcw %0": "+m"(fcw));
- ctxt->ops->put_fpu(ctxt);
ctxt->dst.val = fcw;
@@ -1167,9 +1156,7 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
- ctxt->ops->get_fpu(ctxt);
asm volatile("fnstsw %0": "+m"(fsw));
- ctxt->ops->put_fpu(ctxt);
ctxt->dst.val = fsw;
@@ -2404,9 +2391,21 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
}
static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
- u64 cr0, u64 cr4)
+ u64 cr0, u64 cr3, u64 cr4)
{
int bad;
+ u64 pcid;
+
+ /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */
+ pcid = 0;
+ if (cr4 & X86_CR4_PCIDE) {
+ pcid = cr3 & 0xfff;
+ cr3 &= ~0xfff;
+ }
+
+ bad = ctxt->ops->set_cr(ctxt, 3, cr3);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
/*
* First enable PAE, long mode needs it before CR0.PG = 1 is set.
@@ -2425,6 +2424,12 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
bad = ctxt->ops->set_cr(ctxt, 4, cr4);
if (bad)
return X86EMUL_UNHANDLEABLE;
+ if (pcid) {
+ bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+ }
+
}
return X86EMUL_CONTINUE;
@@ -2435,11 +2440,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
struct desc_struct desc;
struct desc_ptr dt;
u16 selector;
- u32 val, cr0, cr4;
+ u32 val, cr0, cr3, cr4;
int i;
cr0 = GET_SMSTATE(u32, smbase, 0x7ffc);
- ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+ cr3 = GET_SMSTATE(u32, smbase, 0x7ff8);
ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0);
@@ -2481,14 +2486,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
- return rsm_enter_protected_mode(ctxt, cr0, cr4);
+ return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
}
static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
{
struct desc_struct desc;
struct desc_ptr dt;
- u64 val, cr0, cr4;
+ u64 val, cr0, cr3, cr4;
u32 base3;
u16 selector;
int i, r;
@@ -2505,7 +2510,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
cr0 = GET_SMSTATE(u64, smbase, 0x7f58);
- ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u64, smbase, 0x7f50));
+ cr3 = GET_SMSTATE(u64, smbase, 0x7f50);
cr4 = GET_SMSTATE(u64, smbase, 0x7f48);
ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
val = GET_SMSTATE(u64, smbase, 0x7ed0);
@@ -2533,7 +2538,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
dt.address = GET_SMSTATE(u64, smbase, 0x7e68);
ctxt->ops->set_gdt(ctxt, &dt);
- r = rsm_enter_protected_mode(ctxt, cr0, cr4);
+ r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
if (r != X86EMUL_CONTINUE)
return r;
@@ -4001,12 +4006,8 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- ctxt->ops->get_fpu(ctxt);
-
rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
- ctxt->ops->put_fpu(ctxt);
-
if (rc != X86EMUL_CONTINUE)
return rc;
@@ -4014,6 +4015,26 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
fxstate_size(ctxt));
}
+/*
+ * FXRSTOR might restore XMM registers not provided by the guest. Fill
+ * in the host registers (via FXSAVE) instead, so they won't be modified.
+ * (preemption has to stay disabled until FXRSTOR).
+ *
+ * Use noinline to keep the stack for other functions called by callers small.
+ */
+static noinline int fxregs_fixup(struct fxregs_state *fx_state,
+ const size_t used_size)
+{
+ struct fxregs_state fx_tmp;
+ int rc;
+
+ rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_tmp));
+ memcpy((void *)fx_state + used_size, (void *)&fx_tmp + used_size,
+ __fxstate_size(16) - used_size);
+
+ return rc;
+}
+
static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
{
struct fxregs_state fx_state;
@@ -4024,19 +4045,17 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- ctxt->ops->get_fpu(ctxt);
-
size = fxstate_size(ctxt);
+ rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
if (size < __fxstate_size(16)) {
- rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+ rc = fxregs_fixup(&fx_state, size);
if (rc != X86EMUL_CONTINUE)
goto out;
}
- rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
- if (rc != X86EMUL_CONTINUE)
- goto out;
-
if (fx_state.mxcsr >> 16) {
rc = emulate_gp(ctxt, 0);
goto out;
@@ -4046,8 +4065,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
out:
- ctxt->ops->put_fpu(ctxt);
-
return rc;
}
@@ -5000,6 +5017,8 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
bool op_prefix = false;
bool has_seg_override = false;
struct opcode opcode;
+ u16 dummy;
+ struct desc_struct desc;
ctxt->memop.type = OP_NONE;
ctxt->memopp = NULL;
@@ -5018,6 +5037,11 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
switch (mode) {
case X86EMUL_MODE_REAL:
case X86EMUL_MODE_VM86:
+ def_op_bytes = def_ad_bytes = 2;
+ ctxt->ops->get_segment(ctxt, &dummy, &desc, NULL, VCPU_SREG_CS);
+ if (desc.d)
+ def_op_bytes = def_ad_bytes = 4;
+ break;
case X86EMUL_MODE_PROT16:
def_op_bytes = def_ad_bytes = 2;
break;
@@ -5290,9 +5314,7 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
{
int rc;
- ctxt->ops->get_fpu(ctxt);
rc = asm_safe("fwait");
- ctxt->ops->put_fpu(ctxt);
if (unlikely(rc != X86EMUL_CONTINUE))
return emulate_exception(ctxt, MF_VECTOR, 0, false);
@@ -5314,9 +5336,9 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
if (!(ctxt->d & ByteOp))
fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
- asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
+ asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n"
: "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
- [fastop]"+S"(fop), ASM_CALL_CONSTRAINT
+ [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT
: "c"(ctxt->src2.val));
ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index bdff437acbcb..4e822ad363f3 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -209,12 +209,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
old_irr = ioapic->irr;
ioapic->irr |= mask;
- if (edge)
+ if (edge) {
ioapic->irr_delivered &= ~mask;
- if ((edge && old_irr == ioapic->irr) ||
- (!edge && entry.fields.remote_irr)) {
- ret = 0;
- goto out;
+ if (old_irr == ioapic->irr) {
+ ret = 0;
+ goto out;
+ }
}
ret = ioapic_service(ioapic, irq, line_status);
@@ -257,8 +257,7 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
index == RTC_GSI) {
if (kvm_apic_match_dest(vcpu, NULL, 0,
e->fields.dest_id, e->fields.dest_mode) ||
- (e->fields.trig_mode == IOAPIC_EDGE_TRIG &&
- kvm_apic_pending_eoi(vcpu, e->fields.vector)))
+ kvm_apic_pending_eoi(vcpu, e->fields.vector))
__set_bit(e->fields.vector,
ioapic_handled_vectors);
}
@@ -277,6 +276,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
{
unsigned index;
bool mask_before, mask_after;
+ int old_remote_irr, old_delivery_status;
union kvm_ioapic_redirect_entry *e;
switch (ioapic->ioregsel) {
@@ -299,14 +299,28 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
return;
e = &ioapic->redirtbl[index];
mask_before = e->fields.mask;
+ /* Preserve read-only fields */
+ old_remote_irr = e->fields.remote_irr;
+ old_delivery_status = e->fields.delivery_status;
if (ioapic->ioregsel & 1) {
e->bits &= 0xffffffff;
e->bits |= (u64) val << 32;
} else {
e->bits &= ~0xffffffffULL;
e->bits |= (u32) val;
- e->fields.remote_irr = 0;
}
+ e->fields.remote_irr = old_remote_irr;
+ e->fields.delivery_status = old_delivery_status;
+
+ /*
+ * Some OSes (Linux, Xen) assume that Remote IRR bit will
+ * be cleared by IOAPIC hardware when the entry is configured
+ * as edge-triggered. This behavior is used to simulate an
+ * explicit EOI on IOAPICs that don't have the EOI register.
+ */
+ if (e->fields.trig_mode == IOAPIC_EDGE_TRIG)
+ e->fields.remote_irr = 0;
+
mask_after = e->fields.mask;
if (mask_before != mask_after)
kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
@@ -324,7 +338,9 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
struct kvm_lapic_irq irqe;
int ret;
- if (entry->fields.mask)
+ if (entry->fields.mask ||
+ (entry->fields.trig_mode == IOAPIC_LEVEL_TRIG &&
+ entry->fields.remote_irr))
return -1;
ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 943acbf00c69..e2c1fb8d35ce 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -266,9 +266,14 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
recalculate_apic_map(apic->vcpu->kvm);
}
+static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
+{
+ return ((id >> 4) << 16) | (1 << (id & 0xf));
+}
+
static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
{
- u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+ u32 ldr = kvm_apic_calc_x2apic_ldr(id);
WARN_ON_ONCE(id != apic->vcpu->vcpu_id);
@@ -2245,6 +2250,7 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
{
if (apic_x2apic_mode(vcpu->arch.apic)) {
u32 *id = (u32 *)(s->regs + APIC_ID);
+ u32 *ldr = (u32 *)(s->regs + APIC_LDR);
if (vcpu->kvm->arch.x2apic_format) {
if (*id != vcpu->vcpu_id)
@@ -2255,6 +2261,10 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
else
*id <<= 24;
}
+
+ /* In x2APIC mode, the LDR is fixed and based on the id */
+ if (set)
+ *ldr = kvm_apic_calc_x2apic_ldr(*id);
}
return 0;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e5e66e5c6640..2b8eb4da4d08 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3395,7 +3395,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
if(make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
- return 1;
+ return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, 0, 0,
vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
@@ -3410,7 +3410,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
if (make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
- return 1;
+ return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
@@ -3450,7 +3450,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
if (make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
- return 1;
+ return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
@@ -3487,7 +3487,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
if (make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
- return 1;
+ return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL,
0, ACC_ALL);
@@ -3781,7 +3781,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
{
if (unlikely(!lapic_in_kernel(vcpu) ||
- kvm_event_needs_reinjection(vcpu)))
+ kvm_event_needs_reinjection(vcpu) ||
+ vcpu->arch.exception.pending))
return false;
if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
@@ -5465,30 +5466,34 @@ static void mmu_destroy_caches(void)
int kvm_mmu_module_init(void)
{
+ int ret = -ENOMEM;
+
kvm_mmu_clear_all_pte_masks();
pte_list_desc_cache = kmem_cache_create("pte_list_desc",
sizeof(struct pte_list_desc),
0, SLAB_ACCOUNT, NULL);
if (!pte_list_desc_cache)
- goto nomem;
+ goto out;
mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",
sizeof(struct kvm_mmu_page),
0, SLAB_ACCOUNT, NULL);
if (!mmu_page_header_cache)
- goto nomem;
+ goto out;
if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
- goto nomem;
+ goto out;
- register_shrinker(&mmu_shrinker);
+ ret = register_shrinker(&mmu_shrinker);
+ if (ret)
+ goto out;
return 0;
-nomem:
+out:
mmu_destroy_caches();
- return -ENOMEM;
+ return ret;
}
/*
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 59e13a79c2e3..f40d0da1f1d3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -45,6 +45,7 @@
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
#include <asm/irq_remapping.h>
+#include <asm/nospec-branch.h>
#include <asm/virtext.h>
#include "trace.h"
@@ -2197,6 +2198,8 @@ static int ud_interception(struct vcpu_svm *svm)
int er;
er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD);
+ if (er == EMULATE_USER_EXIT)
+ return 0;
if (er != EMULATE_DONE)
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
@@ -4977,6 +4980,25 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%r14, %c[r14](%[svm]) \n\t"
"mov %%r15, %c[r15](%[svm]) \n\t"
#endif
+ /*
+ * Clear host registers marked as clobbered to prevent
+ * speculative use.
+ */
+ "xor %%" _ASM_BX ", %%" _ASM_BX " \n\t"
+ "xor %%" _ASM_CX ", %%" _ASM_CX " \n\t"
+ "xor %%" _ASM_DX ", %%" _ASM_DX " \n\t"
+ "xor %%" _ASM_SI ", %%" _ASM_SI " \n\t"
+ "xor %%" _ASM_DI ", %%" _ASM_DI " \n\t"
+#ifdef CONFIG_X86_64
+ "xor %%r8, %%r8 \n\t"
+ "xor %%r9, %%r9 \n\t"
+ "xor %%r10, %%r10 \n\t"
+ "xor %%r11, %%r11 \n\t"
+ "xor %%r12, %%r12 \n\t"
+ "xor %%r13, %%r13 \n\t"
+ "xor %%r14, %%r14 \n\t"
+ "xor %%r15, %%r15 \n\t"
+#endif
"pop %%" _ASM_BP
:
: [svm]"a"(svm),
@@ -5006,6 +5028,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
#endif
);
+ /* Eliminate branch target predictions from guest mode */
+ vmexit_fill_RSB();
+
#ifdef CONFIG_X86_64
wrmsrl(MSR_GS_BASE, svm->host.gs_base);
#else
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 714a0673ec3c..a8b96dc4cd83 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -50,6 +50,7 @@
#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
+#include <asm/nospec-branch.h>
#include "trace.h"
#include "pmu.h"
@@ -899,8 +900,16 @@ static inline short vmcs_field_to_offset(unsigned long field)
{
BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX);
- if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) ||
- vmcs_field_to_offset_table[field] == 0)
+ if (field >= ARRAY_SIZE(vmcs_field_to_offset_table))
+ return -ENOENT;
+
+ /*
+ * FIXME: Mitigation for CVE-2017-5753. To be replaced with a
+ * generic mechanism.
+ */
+ asm("lfence");
+
+ if (vmcs_field_to_offset_table[field] == 0)
return -ENOENT;
return vmcs_field_to_offset_table[field];
@@ -2300,7 +2309,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
* processors. See 22.2.4.
*/
vmcs_writel(HOST_TR_BASE,
- (unsigned long)this_cpu_ptr(&cpu_tss));
+ (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */
/*
@@ -5600,7 +5609,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
}
- vmcs_writel(GUEST_RFLAGS, 0x02);
+ kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0xfff0);
vmcs_writel(GUEST_GDTR_BASE, 0);
@@ -5915,11 +5924,9 @@ static int handle_exception(struct kvm_vcpu *vcpu)
return 1; /* already handled by vmx_vcpu_run() */
if (is_invalid_opcode(intr_info)) {
- if (is_guest_mode(vcpu)) {
- kvm_queue_exception(vcpu, UD_VECTOR);
- return 1;
- }
er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
+ if (er == EMULATE_USER_EXIT)
+ return 0;
if (er != EMULATE_DONE)
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
@@ -6602,7 +6609,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
if (kvm_test_request(KVM_REQ_EVENT, vcpu))
return 1;
- err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
+ err = emulate_instruction(vcpu, 0);
if (err == EMULATE_USER_EXIT) {
++vcpu->stat.mmio_exits;
@@ -6750,16 +6757,10 @@ static __init int hardware_setup(void)
goto out;
}
- vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
- /*
- * Allow direct access to the PC debug port (it is often used for I/O
- * delays, but the vmexits simply slow things down).
- */
memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
- clear_bit(0x80, vmx_io_bitmap_a);
memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
@@ -7414,10 +7415,11 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
*/
static void free_nested(struct vcpu_vmx *vmx)
{
- if (!vmx->nested.vmxon)
+ if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
vmx->nested.vmxon = false;
+ vmx->nested.smm.vmxon = false;
free_vpid(vmx->nested.vpid02);
vmx->nested.posted_intr_nv = -1;
vmx->nested.current_vmptr = -1ull;
@@ -9127,14 +9129,14 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
#endif
"pushf\n\t"
__ASM_SIZE(push) " $%c[cs]\n\t"
- "call *%[entry]\n\t"
+ CALL_NOSPEC
:
#ifdef CONFIG_X86_64
[sp]"=&r"(tmp),
#endif
ASM_CALL_CONSTRAINT
:
- [entry]"r"(entry),
+ THUNK_TARGET(entry),
[ss]"i"(__KERNEL_DS),
[cs]"i"(__KERNEL_CS)
);
@@ -9419,6 +9421,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
/* Save guest registers, load host registers, keep flags */
"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
"pop %0 \n\t"
+ "setbe %c[fail](%0)\n\t"
"mov %%" _ASM_AX ", %c[rax](%0) \n\t"
"mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
__ASM_SIZE(pop) " %c[rcx](%0) \n\t"
@@ -9435,12 +9438,23 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%r13, %c[r13](%0) \n\t"
"mov %%r14, %c[r14](%0) \n\t"
"mov %%r15, %c[r15](%0) \n\t"
+ "xor %%r8d, %%r8d \n\t"
+ "xor %%r9d, %%r9d \n\t"
+ "xor %%r10d, %%r10d \n\t"
+ "xor %%r11d, %%r11d \n\t"
+ "xor %%r12d, %%r12d \n\t"
+ "xor %%r13d, %%r13d \n\t"
+ "xor %%r14d, %%r14d \n\t"
+ "xor %%r15d, %%r15d \n\t"
#endif
"mov %%cr2, %%" _ASM_AX " \n\t"
"mov %%" _ASM_AX ", %c[cr2](%0) \n\t"
+ "xor %%eax, %%eax \n\t"
+ "xor %%ebx, %%ebx \n\t"
+ "xor %%esi, %%esi \n\t"
+ "xor %%edi, %%edi \n\t"
"pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t"
- "setbe %c[fail](%0) \n\t"
".pushsection .rodata \n\t"
".global vmx_return \n\t"
"vmx_return: " _ASM_PTR " 2b \n\t"
@@ -9477,6 +9491,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
#endif
);
+ /* Eliminate branch target predictions from guest mode */
+ vmexit_fill_RSB();
+
/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
if (debugctlmsr)
update_debugctlmsr(debugctlmsr);
@@ -9800,8 +9817,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
cr4_fixed1_update(X86_CR4_SMEP, ebx, bit(X86_FEATURE_SMEP));
cr4_fixed1_update(X86_CR4_SMAP, ebx, bit(X86_FEATURE_SMAP));
cr4_fixed1_update(X86_CR4_PKE, ecx, bit(X86_FEATURE_PKU));
- /* TODO: Use X86_CR4_UMIP and X86_FEATURE_UMIP macros */
- cr4_fixed1_update(bit(11), ecx, bit(2));
+ cr4_fixed1_update(X86_CR4_UMIP, ecx, bit(X86_FEATURE_UMIP));
#undef cr4_fixed1_update
}
@@ -10875,6 +10891,11 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
return 1;
}
+ if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
+ (is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) ||
+ (vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))
+ return 1;
+
return 0;
}
@@ -11099,13 +11120,12 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qual;
-
- if (kvm_event_needs_reinjection(vcpu))
- return -EBUSY;
+ bool block_nested_events =
+ vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
if (vcpu->arch.exception.pending &&
nested_vmx_check_exception(vcpu, &exit_qual)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
vcpu->arch.exception.pending = false;
@@ -11114,14 +11134,14 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
vmx->nested.preemption_timer_expired) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
return 0;
}
if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
NMI_VECTOR | INTR_TYPE_NMI_INTR |
@@ -11137,7 +11157,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
nested_exit_on_intr(vcpu)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
return 0;
@@ -11324,6 +11344,24 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
kvm_clear_interrupt_queue(vcpu);
}
+static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ u32 entry_failure_code;
+
+ nested_ept_uninit_mmu_context(vcpu);
+
+ /*
+ * Only PDPTE load can fail as the value of cr3 was checked on entry and
+ * couldn't have changed.
+ */
+ if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+ nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
+
+ if (!enable_ept)
+ vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+}
+
/*
* A part of what we need to when the nested L2 guest exits and we want to
* run its L1 parent, is to reset L1's guest state to the host state specified
@@ -11337,7 +11375,6 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
struct kvm_segment seg;
- u32 entry_failure_code;
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->host_ia32_efer;
@@ -11364,17 +11401,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
vmx_set_cr4(vcpu, vmcs12->host_cr4);
- nested_ept_uninit_mmu_context(vcpu);
-
- /*
- * Only PDPTE load can fail as the value of cr3 was checked on entry and
- * couldn't have changed.
- */
- if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
- nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
-
- if (!enable_ept)
- vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+ load_vmcs12_mmu_host_state(vcpu, vmcs12);
if (enable_vpid) {
/*
@@ -11604,6 +11631,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
* accordingly.
*/
nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+ load_vmcs12_mmu_host_state(vcpu, vmcs12);
+
/*
* The emulated instruction was already skipped in
* nested_vmx_run, but the updated RIP was never
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 34c85aa2e2d1..c53298dfbf50 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -107,6 +107,9 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops);
static bool __read_mostly ignore_msrs = 0;
module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
+static bool __read_mostly report_ignored_msrs = true;
+module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
+
unsigned int min_timer_period_us = 500;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
@@ -1795,10 +1798,13 @@ u64 get_kvmclock_ns(struct kvm *kvm)
/* both __this_cpu_read() and rdtsc() should be on the same cpu */
get_cpu();
- kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
- &hv_clock.tsc_shift,
- &hv_clock.tsc_to_system_mul);
- ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+ if (__this_cpu_read(cpu_tsc_khz)) {
+ kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+ &hv_clock.tsc_shift,
+ &hv_clock.tsc_to_system_mul);
+ ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+ } else
+ ret = ktime_get_boot_ns() + ka->kvmclock_offset;
put_cpu();
@@ -1830,6 +1836,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
*/
BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+ if (guest_hv_clock.version & 1)
+ ++guest_hv_clock.version; /* first time write, random junk */
+
vcpu->hv_clock.version = guest_hv_clock.version + 1;
kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
&vcpu->hv_clock,
@@ -2322,7 +2331,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* Drop writes to this legacy MSR -- see rdmsr
* counterpart for further detail.
*/
- vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
+ if (report_ignored_msrs)
+ vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
+ msr, data);
break;
case MSR_AMD64_OSVW_ID_LENGTH:
if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
@@ -2359,8 +2370,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr, data);
return 1;
} else {
- vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
- msr, data);
+ if (report_ignored_msrs)
+ vcpu_unimpl(vcpu,
+ "ignored wrmsr: 0x%x data 0x%llx\n",
+ msr, data);
break;
}
}
@@ -2578,7 +2591,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->index);
return 1;
} else {
- vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index);
+ if (report_ignored_msrs)
+ vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n",
+ msr_info->index);
msr_info->data = 0;
}
break;
@@ -2922,7 +2937,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
srcu_read_unlock(&vcpu->kvm->srcu, idx);
pagefault_enable();
kvm_x86_ops->vcpu_put(vcpu);
- kvm_put_guest_fpu(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
}
@@ -4370,7 +4384,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
addr, n, v))
&& kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
break;
- trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v);
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v);
handled += n;
addr += n;
len -= n;
@@ -4629,7 +4643,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
{
if (vcpu->mmio_read_completed) {
trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
- vcpu->mmio_fragments[0].gpa, *(u64 *)val);
+ vcpu->mmio_fragments[0].gpa, val);
vcpu->mmio_read_completed = 0;
return 1;
}
@@ -4651,14 +4665,14 @@ static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val)
{
- trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val);
+ trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val);
return vcpu_mmio_write(vcpu, gpa, bytes, val);
}
static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
void *val, int bytes)
{
- trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0);
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL);
return X86EMUL_IO_NEEDED;
}
@@ -5237,17 +5251,6 @@ static void emulator_halt(struct x86_emulate_ctxt *ctxt)
emul_to_vcpu(ctxt)->arch.halt_request = 1;
}
-static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt)
-{
- preempt_disable();
- kvm_load_guest_fpu(emul_to_vcpu(ctxt));
-}
-
-static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt)
-{
- preempt_enable();
-}
-
static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
struct x86_instruction_info *info,
enum x86_intercept_stage stage)
@@ -5325,8 +5328,6 @@ static const struct x86_emulate_ops emulate_ops = {
.halt = emulator_halt,
.wbinvd = emulator_wbinvd,
.fix_hypercall = emulator_fix_hypercall,
- .get_fpu = emulator_get_fpu,
- .put_fpu = emulator_put_fpu,
.intercept = emulator_intercept,
.get_cpuid = emulator_get_cpuid,
.set_nmi_mask = emulator_set_nmi_mask,
@@ -5430,7 +5431,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
- r = EMULATE_FAIL;
+ r = EMULATE_USER_EXIT;
}
kvm_queue_exception(vcpu, UD_VECTOR);
@@ -5722,6 +5723,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
emulation_type))
return EMULATE_DONE;
+ if (ctxt->have_exception && inject_emulated_exception(vcpu))
+ return EMULATE_DONE;
if (emulation_type & EMULTYPE_SKIP)
return EMULATE_FAIL;
return handle_emulation_failure(vcpu);
@@ -6761,6 +6764,20 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
kvm_x86_ops->tlb_flush(vcpu);
}
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+ unsigned long start, unsigned long end)
+{
+ unsigned long apic_address;
+
+ /*
+ * The physical address of apic access page is stored in the VMCS.
+ * Update it when it becomes invalid.
+ */
+ apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+ if (start <= apic_address && apic_address < end)
+ kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
{
struct page *page = NULL;
@@ -6935,7 +6952,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
preempt_disable();
kvm_x86_ops->prepare_guest_switch(vcpu);
- kvm_load_guest_fpu(vcpu);
/*
* Disable IRQs before setting IN_GUEST_MODE. Posted interrupt
@@ -7248,14 +7264,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
- struct fpu *fpu = &current->thread.fpu;
int r;
- sigset_t sigsaved;
- fpu__initialize(fpu);
+ kvm_sigset_activate(vcpu);
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+ kvm_load_guest_fpu(vcpu);
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
if (kvm_run->immediate_exit) {
@@ -7297,9 +7310,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
r = vcpu_run(vcpu);
out:
+ kvm_put_guest_fpu(vcpu);
post_kvm_run_save(vcpu);
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ kvm_sigset_deactivate(vcpu);
return r;
}
@@ -7367,7 +7380,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
#endif
kvm_rip_write(vcpu, regs->rip);
- kvm_set_rflags(vcpu, regs->rflags);
+ kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);
vcpu->arch.exception.pending = false;
@@ -7481,6 +7494,29 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
}
EXPORT_SYMBOL_GPL(kvm_task_switch);
+int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+ if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
+ /*
+ * When EFER.LME and CR0.PG are set, the processor is in
+ * 64-bit mode (though maybe in a 32-bit code segment).
+ * CR4.PAE and EFER.LMA must be set.
+ */
+ if (!(sregs->cr4 & X86_CR4_PAE)
+ || !(sregs->efer & EFER_LMA))
+ return -EINVAL;
+ } else {
+ /*
+ * Not in 64-bit mode: EFER.LMA is clear and the code
+ * segment cannot be 64-bit.
+ */
+ if (sregs->efer & EFER_LMA || sregs->cs.l)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
@@ -7493,6 +7529,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
(sregs->cr4 & X86_CR4_OSXSAVE))
return -EINVAL;
+ if (kvm_valid_sregs(vcpu, sregs))
+ return -EINVAL;
+
apic_base_msr.data = sregs->apic_base;
apic_base_msr.host_initiated = true;
if (kvm_set_apic_base(vcpu, &apic_base_msr))
@@ -7690,32 +7729,25 @@ static void fx_init(struct kvm_vcpu *vcpu)
vcpu->arch.cr0 |= X86_CR0_ET;
}
+/* Swap (qemu) user FPU context for the guest FPU context. */
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
- if (vcpu->guest_fpu_loaded)
- return;
-
- /*
- * Restore all possible states in the guest,
- * and assume host would use all available bits.
- * Guest xcr0 would be loaded later.
- */
- vcpu->guest_fpu_loaded = 1;
- __kernel_fpu_begin();
+ preempt_disable();
+ copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
/* PKRU is separately restored in kvm_x86_ops->run. */
__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
~XFEATURE_MASK_PKRU);
+ preempt_enable();
trace_kvm_fpu(1);
}
+/* When vcpu_run ends, restore user space FPU context. */
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
- if (!vcpu->guest_fpu_loaded)
- return;
-
- vcpu->guest_fpu_loaded = 0;
+ preempt_disable();
copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
- __kernel_fpu_end();
+ copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+ preempt_enable();
++vcpu->stat.fpu_reload;
trace_kvm_fpu(0);
}
@@ -7832,7 +7864,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
* To avoid have the INIT path from kvm_apic_has_events() that be
* called with loaded FPU and does not let userspace fix the state.
*/
- kvm_put_guest_fpu(vcpu);
+ if (init_event)
+ kvm_put_guest_fpu(vcpu);
mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave,
XFEATURE_MASK_BNDREGS);
if (mpx_state_buffer)
@@ -7841,6 +7874,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
XFEATURE_MASK_BNDCSR);
if (mpx_state_buffer)
memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
+ if (init_event)
+ kvm_load_guest_fpu(vcpu);
}
if (!init_event) {
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 7b181b61170e..69a473919260 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -26,6 +26,8 @@ lib-y += memcpy_$(BITS).o
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
+lib-$(CONFIG_RETPOLINE) += retpoline.o
+OBJECT_FILES_NON_STANDARD_retpoline.o :=y
obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 4d34bb548b41..46e71a74e612 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -29,7 +29,8 @@
#include <asm/errno.h>
#include <asm/asm.h>
#include <asm/export.h>
-
+#include <asm/nospec-branch.h>
+
/*
* computes a partial checksum, e.g. for TCP/UDP fragments
*/
@@ -156,7 +157,7 @@ ENTRY(csum_partial)
negl %ebx
lea 45f(%ebx,%ebx,2), %ebx
testl %esi, %esi
- jmp *%ebx
+ JMP_NOSPEC %ebx
# Handle 2-byte-aligned regions
20: addw (%esi), %ax
@@ -439,7 +440,7 @@ ENTRY(csum_partial_copy_generic)
andl $-32,%edx
lea 3f(%ebx,%ebx), %ebx
testl %esi, %esi
- jmp *%ebx
+ JMP_NOSPEC %ebx
1: addl $64,%esi
addl $64,%edi
SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl)
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 553f8fd23cc4..f5b7f1b3b6d7 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -107,10 +107,10 @@ static void delay_mwaitx(unsigned long __loops)
delay = min_t(u64, MWAITX_MAX_LOOPS, loops);
/*
- * Use cpu_tss as a cacheline-aligned, seldomly
+ * Use cpu_tss_rw as a cacheline-aligned, seldomly
* accessed per-cpu variable as the monitor target.
*/
- __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0);
+ __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
/*
* AMD, like Intel, supports the EAX hint and EAX=0xf
@@ -162,7 +162,7 @@ void __delay(unsigned long loops)
}
EXPORT_SYMBOL(__delay);
-inline void __const_udelay(unsigned long xloops)
+void __const_udelay(unsigned long xloops)
{
unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy;
int d0;
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
new file mode 100644
index 000000000000..480edc3a5e03
--- /dev/null
+++ b/arch/x86/lib/retpoline.S
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/stringify.h>
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+#include <asm/export.h>
+#include <asm/nospec-branch.h>
+#include <asm/bitsperlong.h>
+
+.macro THUNK reg
+ .section .text.__x86.indirect_thunk
+
+ENTRY(__x86_indirect_thunk_\reg)
+ CFI_STARTPROC
+ JMP_NOSPEC %\reg
+ CFI_ENDPROC
+ENDPROC(__x86_indirect_thunk_\reg)
+.endm
+
+/*
+ * Despite being an assembler file we can't just use .irp here
+ * because __KSYM_DEPS__ only uses the C preprocessor and would
+ * only see one instance of "__x86_indirect_thunk_\reg" rather
+ * than one per register with the correct names. So we do it
+ * the simple and nasty way...
+ */
+#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
+#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
+
+GENERATE_THUNK(_ASM_AX)
+GENERATE_THUNK(_ASM_BX)
+GENERATE_THUNK(_ASM_CX)
+GENERATE_THUNK(_ASM_DX)
+GENERATE_THUNK(_ASM_SI)
+GENERATE_THUNK(_ASM_DI)
+GENERATE_THUNK(_ASM_BP)
+#ifdef CONFIG_64BIT
+GENERATE_THUNK(r8)
+GENERATE_THUNK(r9)
+GENERATE_THUNK(r10)
+GENERATE_THUNK(r11)
+GENERATE_THUNK(r12)
+GENERATE_THUNK(r13)
+GENERATE_THUNK(r14)
+GENERATE_THUNK(r15)
+#endif
+
+/*
+ * Fill the CPU return stack buffer.
+ *
+ * Each entry in the RSB, if used for a speculative 'ret', contains an
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version - two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+.macro STUFF_RSB nr:req sp:req
+ mov $(\nr / 2), %_ASM_BX
+ .align 16
+771:
+ call 772f
+773: /* speculation trap */
+ pause
+ lfence
+ jmp 773b
+ .align 16
+772:
+ call 774f
+775: /* speculation trap */
+ pause
+ lfence
+ jmp 775b
+ .align 16
+774:
+ dec %_ASM_BX
+ jnz 771b
+ add $((BITS_PER_LONG/8) * \nr), \sp
+.endm
+
+#define RSB_FILL_LOOPS 16 /* To avoid underflow */
+
+ENTRY(__fill_rsb)
+ STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP
+ ret
+END(__fill_rsb)
+EXPORT_SYMBOL_GPL(__fill_rsb)
+
+#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */
+
+ENTRY(__clear_rsb)
+ STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP
+ ret
+END(__clear_rsb)
+EXPORT_SYMBOL_GPL(__clear_rsb)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index c4d55919fac1..e0b85930dd77 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
+ff: UD0
EndTable
Table: 3-byte opcode 1 (0x0f 0x38)
@@ -717,7 +717,7 @@ AVXcode: 2
7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
82: INVPCID Gy,Mdq (66)
83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
88: vexpandps/d Vpd,Wpd (66),(ev)
@@ -970,6 +970,15 @@ GrpTable: Grp9
EndTable
GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
EndTable
# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 8e13b8cc6bed..27e9e90a8d35 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -10,7 +10,7 @@ CFLAGS_REMOVE_mem_encrypt.o = -pg
endif
obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
- pat.o pgtable.o physaddr.o setup_nx.o tlb.o
+ pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o
# Make sure __phys_addr has no stackprotector
nostackp := $(call cc-option, -fno-stack-protector)
@@ -41,9 +41,10 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o
obj-$(CONFIG_ACPI_NUMA) += srat.o
obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
-obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
-obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
-obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
+obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
+obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
new file mode 100644
index 000000000000..b9283cc27622
--- /dev/null
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+
+#include <asm/cpu_entry_area.h>
+#include <asm/pgtable.h>
+#include <asm/fixmap.h>
+#include <asm/desc.h>
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
+
+#ifdef CONFIG_X86_64
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+ [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+#endif
+
+struct cpu_entry_area *get_cpu_entry_area(int cpu)
+{
+ unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE;
+ BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
+
+ return (struct cpu_entry_area *) va;
+}
+EXPORT_SYMBOL(get_cpu_entry_area);
+
+void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags)
+{
+ unsigned long va = (unsigned long) cea_vaddr;
+
+ set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags));
+}
+
+static void __init
+cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
+{
+ for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE)
+ cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
+}
+
+static void percpu_setup_debug_store(int cpu)
+{
+#ifdef CONFIG_CPU_SUP_INTEL
+ int npages;
+ void *cea;
+
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return;
+
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_store;
+ npages = sizeof(struct debug_store) / PAGE_SIZE;
+ BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0);
+ cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages,
+ PAGE_KERNEL);
+
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers;
+ /*
+ * Force the population of PMDs for not yet allocated per cpu
+ * memory like debug store buffers.
+ */
+ npages = sizeof(struct debug_store_buffers) / PAGE_SIZE;
+ for (; npages; npages--, cea += PAGE_SIZE)
+ cea_set_pte(cea, 0, PAGE_NONE);
+#endif
+}
+
+/* Setup the fixmap mappings only once per-processor */
+static void __init setup_cpu_entry_area(int cpu)
+{
+#ifdef CONFIG_X86_64
+ extern char _entry_trampoline[];
+
+ /* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
+ pgprot_t gdt_prot = PAGE_KERNEL_RO;
+ pgprot_t tss_prot = PAGE_KERNEL_RO;
+#else
+ /*
+ * On native 32-bit systems, the GDT cannot be read-only because
+ * our double fault handler uses a task gate, and entering through
+ * a task gate needs to change an available TSS to busy. If the
+ * GDT is read-only, that will triple fault. The TSS cannot be
+ * read-only because the CPU writes to it on task switches.
+ *
+ * On Xen PV, the GDT must be read-only because the hypervisor
+ * requires it.
+ */
+ pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ?
+ PAGE_KERNEL_RO : PAGE_KERNEL;
+ pgprot_t tss_prot = PAGE_KERNEL;
+#endif
+
+ cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu),
+ gdt_prot);
+
+ cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page,
+ per_cpu_ptr(&entry_stack_storage, cpu), 1,
+ PAGE_KERNEL);
+
+ /*
+ * The Intel SDM says (Volume 3, 7.2.1):
+ *
+ * Avoid placing a page boundary in the part of the TSS that the
+ * processor reads during a task switch (the first 104 bytes). The
+ * processor may not correctly perform address translations if a
+ * boundary occurs in this area. During a task switch, the processor
+ * reads and writes into the first 104 bytes of each TSS (using
+ * contiguous physical addresses beginning with the physical address
+ * of the first byte of the TSS). So, after TSS access begins, if
+ * part of the 104 bytes is not physically contiguous, the processor
+ * will access incorrect information without generating a page-fault
+ * exception.
+ *
+ * There are also a lot of errata involving the TSS spanning a page
+ * boundary. Assert that we're not doing that.
+ */
+ BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
+ offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
+ BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
+ cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss,
+ &per_cpu(cpu_tss_rw, cpu),
+ sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
+
+#ifdef CONFIG_X86_32
+ per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
+#endif
+
+#ifdef CONFIG_X86_64
+ BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+ BUILD_BUG_ON(sizeof(exception_stacks) !=
+ sizeof(((struct cpu_entry_area *)0)->exception_stacks));
+ cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks,
+ &per_cpu(exception_stacks, cpu),
+ sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL);
+
+ cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
+ __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
+#endif
+ percpu_setup_debug_store(cpu);
+}
+
+static __init void setup_cpu_entry_area_ptes(void)
+{
+#ifdef CONFIG_X86_32
+ unsigned long start, end;
+
+ BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
+ BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
+
+ start = CPU_ENTRY_AREA_BASE;
+ end = start + CPU_ENTRY_AREA_MAP_SIZE;
+
+ /* Careful here: start + PMD_SIZE might wrap around */
+ for (; start < end && start >= CPU_ENTRY_AREA_BASE; start += PMD_SIZE)
+ populate_extra_pte(start);
+#endif
+}
+
+void __init setup_cpu_entry_areas(void)
+{
+ unsigned int cpu;
+
+ setup_cpu_entry_area_ptes();
+
+ for_each_possible_cpu(cpu)
+ setup_cpu_entry_area(cpu);
+}
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
index bfcffdf6c577..421f2664ffa0 100644
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -5,7 +5,7 @@
static int ptdump_show(struct seq_file *m, void *v)
{
- ptdump_walk_pgd_level(m, NULL);
+ ptdump_walk_pgd_level_debugfs(m, NULL, false);
return 0;
}
@@ -22,21 +22,89 @@ static const struct file_operations ptdump_fops = {
.release = single_release,
};
-static struct dentry *pe;
+static int ptdump_show_curknl(struct seq_file *m, void *v)
+{
+ if (current->mm->pgd) {
+ down_read(&current->mm->mmap_sem);
+ ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false);
+ up_read(&current->mm->mmap_sem);
+ }
+ return 0;
+}
+
+static int ptdump_open_curknl(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, ptdump_show_curknl, NULL);
+}
+
+static const struct file_operations ptdump_curknl_fops = {
+ .owner = THIS_MODULE,
+ .open = ptdump_open_curknl,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static struct dentry *pe_curusr;
+
+static int ptdump_show_curusr(struct seq_file *m, void *v)
+{
+ if (current->mm->pgd) {
+ down_read(&current->mm->mmap_sem);
+ ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true);
+ up_read(&current->mm->mmap_sem);
+ }
+ return 0;
+}
+
+static int ptdump_open_curusr(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, ptdump_show_curusr, NULL);
+}
+
+static const struct file_operations ptdump_curusr_fops = {
+ .owner = THIS_MODULE,
+ .open = ptdump_open_curusr,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+#endif
+
+static struct dentry *dir, *pe_knl, *pe_curknl;
static int __init pt_dump_debug_init(void)
{
- pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL,
- &ptdump_fops);
- if (!pe)
+ dir = debugfs_create_dir("page_tables", NULL);
+ if (!dir)
return -ENOMEM;
+ pe_knl = debugfs_create_file("kernel", 0400, dir, NULL,
+ &ptdump_fops);
+ if (!pe_knl)
+ goto err;
+
+ pe_curknl = debugfs_create_file("current_kernel", 0400,
+ dir, NULL, &ptdump_curknl_fops);
+ if (!pe_curknl)
+ goto err;
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pe_curusr = debugfs_create_file("current_user", 0400,
+ dir, NULL, &ptdump_curusr_fops);
+ if (!pe_curusr)
+ goto err;
+#endif
return 0;
+err:
+ debugfs_remove_recursive(dir);
+ return -ENOMEM;
}
static void __exit pt_dump_debug_exit(void)
{
- debugfs_remove_recursive(pe);
+ debugfs_remove_recursive(dir);
}
module_init(pt_dump_debug_init);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 5e3ac6fe6c9e..2a4849e92831 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -44,68 +44,97 @@ struct addr_marker {
unsigned long max_lines;
};
-/* indices for address_markers; keep sync'd w/ address_markers below */
+/* Address space markers hints */
+
+#ifdef CONFIG_X86_64
+
enum address_markers_idx {
USER_SPACE_NR = 0,
-#ifdef CONFIG_X86_64
KERNEL_SPACE_NR,
LOW_KERNEL_NR,
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && defined(CONFIG_X86_5LEVEL)
+ LDT_NR,
+#endif
VMALLOC_START_NR,
VMEMMAP_START_NR,
#ifdef CONFIG_KASAN
KASAN_SHADOW_START_NR,
KASAN_SHADOW_END_NR,
#endif
-# ifdef CONFIG_X86_ESPFIX64
+ CPU_ENTRY_AREA_NR,
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL)
+ LDT_NR,
+#endif
+#ifdef CONFIG_X86_ESPFIX64
ESPFIX_START_NR,
-# endif
+#endif
+#ifdef CONFIG_EFI
+ EFI_END_NR,
+#endif
HIGH_KERNEL_NR,
MODULES_VADDR_NR,
MODULES_END_NR,
-#else
+ FIXADDR_START_NR,
+ END_OF_SPACE_NR,
+};
+
+static struct addr_marker address_markers[] = {
+ [USER_SPACE_NR] = { 0, "User Space" },
+ [KERNEL_SPACE_NR] = { (1UL << 63), "Kernel Space" },
+ [LOW_KERNEL_NR] = { 0UL, "Low Kernel Mapping" },
+ [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" },
+ [VMEMMAP_START_NR] = { 0UL, "Vmemmap" },
+#ifdef CONFIG_KASAN
+ [KASAN_SHADOW_START_NR] = { KASAN_SHADOW_START, "KASAN shadow" },
+ [KASAN_SHADOW_END_NR] = { KASAN_SHADOW_END, "KASAN shadow end" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ [LDT_NR] = { LDT_BASE_ADDR, "LDT remap" },
+#endif
+ [CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
+#ifdef CONFIG_X86_ESPFIX64
+ [ESPFIX_START_NR] = { ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
+#endif
+#ifdef CONFIG_EFI
+ [EFI_END_NR] = { EFI_VA_END, "EFI Runtime Services" },
+#endif
+ [HIGH_KERNEL_NR] = { __START_KERNEL_map, "High Kernel Mapping" },
+ [MODULES_VADDR_NR] = { MODULES_VADDR, "Modules" },
+ [MODULES_END_NR] = { MODULES_END, "End Modules" },
+ [FIXADDR_START_NR] = { FIXADDR_START, "Fixmap Area" },
+ [END_OF_SPACE_NR] = { -1, NULL }
+};
+
+#else /* CONFIG_X86_64 */
+
+enum address_markers_idx {
+ USER_SPACE_NR = 0,
KERNEL_SPACE_NR,
VMALLOC_START_NR,
VMALLOC_END_NR,
-# ifdef CONFIG_HIGHMEM
+#ifdef CONFIG_HIGHMEM
PKMAP_BASE_NR,
-# endif
- FIXADDR_START_NR,
#endif
+ CPU_ENTRY_AREA_NR,
+ FIXADDR_START_NR,
+ END_OF_SPACE_NR,
};
-/* Address space markers hints */
static struct addr_marker address_markers[] = {
- { 0, "User Space" },
-#ifdef CONFIG_X86_64
- { 0x8000000000000000UL, "Kernel Space" },
- { 0/* PAGE_OFFSET */, "Low Kernel Mapping" },
- { 0/* VMALLOC_START */, "vmalloc() Area" },
- { 0/* VMEMMAP_START */, "Vmemmap" },
-#ifdef CONFIG_KASAN
- { KASAN_SHADOW_START, "KASAN shadow" },
- { KASAN_SHADOW_END, "KASAN shadow end" },
+ [USER_SPACE_NR] = { 0, "User Space" },
+ [KERNEL_SPACE_NR] = { PAGE_OFFSET, "Kernel Mapping" },
+ [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" },
+ [VMALLOC_END_NR] = { 0UL, "vmalloc() End" },
+#ifdef CONFIG_HIGHMEM
+ [PKMAP_BASE_NR] = { 0UL, "Persistent kmap() Area" },
#endif
-# ifdef CONFIG_X86_ESPFIX64
- { ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
-# endif
-# ifdef CONFIG_EFI
- { EFI_VA_END, "EFI Runtime Services" },
-# endif
- { __START_KERNEL_map, "High Kernel Mapping" },
- { MODULES_VADDR, "Modules" },
- { MODULES_END, "End Modules" },
-#else
- { PAGE_OFFSET, "Kernel Mapping" },
- { 0/* VMALLOC_START */, "vmalloc() Area" },
- { 0/*VMALLOC_END*/, "vmalloc() End" },
-# ifdef CONFIG_HIGHMEM
- { 0/*PKMAP_BASE*/, "Persistent kmap() Area" },
-# endif
- { 0/*FIXADDR_START*/, "Fixmap Area" },
-#endif
- { -1, NULL } /* End of list */
+ [CPU_ENTRY_AREA_NR] = { 0UL, "CPU entry area" },
+ [FIXADDR_START_NR] = { 0UL, "Fixmap area" },
+ [END_OF_SPACE_NR] = { -1, NULL }
};
+#endif /* !CONFIG_X86_64 */
+
/* Multipliers for offsets within the PTEs */
#define PTE_LEVEL_MULT (PAGE_SIZE)
#define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT)
@@ -140,7 +169,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
static const char * const level_name[] =
{ "cr3", "pgd", "p4d", "pud", "pmd", "pte" };
- if (!pgprot_val(prot)) {
+ if (!(pr & _PAGE_PRESENT)) {
/* Not present */
pt_dump_cont_printf(m, dmsg, " ");
} else {
@@ -447,7 +476,7 @@ static inline bool is_hypervisor_range(int idx)
}
static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
- bool checkwx)
+ bool checkwx, bool dmesg)
{
#ifdef CONFIG_X86_64
pgd_t *start = (pgd_t *) &init_top_pgt;
@@ -460,7 +489,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
if (pgd) {
start = pgd;
- st.to_dmesg = true;
+ st.to_dmesg = dmesg;
}
st.check_wx = checkwx;
@@ -498,13 +527,37 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
{
- ptdump_walk_pgd_level_core(m, pgd, false);
+ ptdump_walk_pgd_level_core(m, pgd, false, true);
+}
+
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ if (user && static_cpu_has(X86_FEATURE_PTI))
+ pgd = kernel_to_user_pgdp(pgd);
+#endif
+ ptdump_walk_pgd_level_core(m, pgd, false, false);
+}
+EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
+
+static void ptdump_walk_user_pgd_level_checkwx(void)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pgd_t *pgd = (pgd_t *) &init_top_pgt;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ pr_info("x86/mm: Checking user space page tables\n");
+ pgd = kernel_to_user_pgdp(pgd);
+ ptdump_walk_pgd_level_core(NULL, pgd, true, false);
+#endif
}
-EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level);
void ptdump_walk_pgd_level_checkwx(void)
{
- ptdump_walk_pgd_level_core(NULL, NULL, true);
+ ptdump_walk_pgd_level_core(NULL, NULL, true, false);
+ ptdump_walk_user_pgd_level_checkwx();
}
static int __init pt_dump_init(void)
@@ -525,8 +578,8 @@ static int __init pt_dump_init(void)
address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE;
# endif
address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
+ address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
#endif
-
return 0;
}
__initcall(pt_dump_init);
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 3321b446b66c..45f5d6cf65ae 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,6 +1,7 @@
#include <linux/extable.h>
#include <linux/uaccess.h>
#include <linux/sched/debug.h>
+#include <xen/xen.h>
#include <asm/fpu/internal.h>
#include <asm/traps.h>
@@ -20,16 +21,16 @@ ex_fixup_handler(const struct exception_table_entry *x)
return (ex_handler_t)((unsigned long)&x->handler + x->handler);
}
-bool ex_handler_default(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_default(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
regs->ip = ex_fixup_addr(fixup);
return true;
}
EXPORT_SYMBOL(ex_handler_default);
-bool ex_handler_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_fault(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
regs->ip = ex_fixup_addr(fixup);
regs->ax = trapnr;
@@ -41,8 +42,8 @@ EXPORT_SYMBOL_GPL(ex_handler_fault);
* Handler for UD0 exception following a failed test against the
* result of a refcount inc/dec/add/sub.
*/
-bool ex_handler_refcount(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
/* First unconditionally saturate the refcount. */
*(int *)regs->cx = INT_MIN / 2;
@@ -82,7 +83,7 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup,
return true;
}
-EXPORT_SYMBOL_GPL(ex_handler_refcount);
+EXPORT_SYMBOL(ex_handler_refcount);
/*
* Handler for when we fail to restore a task's FPU state. We should never get
@@ -94,8 +95,8 @@ EXPORT_SYMBOL_GPL(ex_handler_refcount);
* of vulnerability by restoring from the initial state (essentially, zeroing
* out all the FPU registers) if we can't restore from the task's FPU state.
*/
-bool ex_handler_fprestore(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
regs->ip = ex_fixup_addr(fixup);
@@ -107,8 +108,8 @@ bool ex_handler_fprestore(const struct exception_table_entry *fixup,
}
EXPORT_SYMBOL_GPL(ex_handler_fprestore);
-bool ex_handler_ext(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_ext(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
/* Special hack for uaccess_err */
current->thread.uaccess_err = 1;
@@ -117,8 +118,8 @@ bool ex_handler_ext(const struct exception_table_entry *fixup,
}
EXPORT_SYMBOL(ex_handler_ext);
-bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, regs->ip, (void *)regs->ip))
@@ -132,8 +133,8 @@ bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
}
EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
-bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, (unsigned int)regs->dx,
@@ -146,8 +147,8 @@ bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
}
EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
-bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
if (static_cpu_has(X86_BUG_NULL_SEG))
asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
@@ -156,7 +157,7 @@ bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
}
EXPORT_SYMBOL(ex_handler_clear_fs);
-bool ex_has_fault_handler(unsigned long ip)
+__visible bool ex_has_fault_handler(unsigned long ip)
{
const struct exception_table_entry *e;
ex_handler_t handler;
@@ -212,8 +213,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
* Old CPUs leave the high bits of CS on the stack
* undefined. I'm not sure which CPUs do this, but at least
* the 486 DX works this way.
+ * Xen pv domains are not using the default __KERNEL_CS.
*/
- if (regs->cs != __KERNEL_CS)
+ if (!xen_pv_domain() && regs->cs != __KERNEL_CS)
goto fail;
/*
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 78ca9a8ee454..800de815519c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -172,14 +172,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
* 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really
* faulted on a pte with its pkey=4.
*/
-static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
+static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info,
+ u32 *pkey)
{
/* This is effectively an #ifdef */
if (!boot_cpu_has(X86_FEATURE_OSPKE))
return;
/* Fault not from Protection Keys: nothing to do */
- if (si_code != SEGV_PKUERR)
+ if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV))
return;
/*
* force_sig_info_fault() is called from a number of
@@ -218,7 +219,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
lsb = PAGE_SHIFT;
info.si_addr_lsb = lsb;
- fill_sig_info_pkey(si_code, &info, pkey);
+ fill_sig_info_pkey(si_signo, si_code, &info, pkey);
force_sig_info(si_signo, &info, tsk);
}
@@ -438,18 +439,13 @@ static noinline int vmalloc_fault(unsigned long address)
if (pgd_none(*pgd_ref))
return -1;
- if (pgd_none(*pgd)) {
- set_pgd(pgd, *pgd_ref);
- arch_flush_lazy_mmu_mode();
- } else if (CONFIG_PGTABLE_LEVELS > 4) {
- /*
- * With folded p4d, pgd_none() is always false, so the pgd may
- * point to an empty page table entry and pgd_page_vaddr()
- * will return garbage.
- *
- * We will do the correct sanity check on the p4d level.
- */
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+ if (CONFIG_PGTABLE_LEVELS > 4) {
+ if (pgd_none(*pgd)) {
+ set_pgd(pgd, *pgd_ref);
+ arch_flush_lazy_mmu_mode();
+ } else {
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+ }
}
/* With 4-level paging, copying happens on the p4d level. */
@@ -458,7 +454,7 @@ static noinline int vmalloc_fault(unsigned long address)
if (p4d_none(*p4d_ref))
return -1;
- if (p4d_none(*p4d)) {
+ if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) {
set_p4d(p4d, *p4d_ref);
arch_flush_lazy_mmu_mode();
} else {
@@ -469,6 +465,7 @@ static noinline int vmalloc_fault(unsigned long address)
* Below here mismatches are bugs because these lower tables
* are shared:
*/
+ BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4);
pud = pud_offset(p4d, address);
pud_ref = pud_offset(p4d_ref, address);
@@ -701,7 +698,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
else
printk(KERN_CONT "paging request");
- printk(KERN_CONT " at %p\n", (void *) address);
+ printk(KERN_CONT " at %px\n", (void *) address);
printk(KERN_ALERT "IP: %pS\n", (void *)regs->ip);
dump_pagetable(address);
@@ -860,7 +857,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
if (!printk_ratelimit())
return;
- printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+ printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
tsk->comm, task_pid_nr(tsk), address,
(void *)regs->ip, (void *)regs->sp, error_code);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 6fdf91ef130a..82f5252c723a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -20,6 +20,7 @@
#include <asm/kaslr.h>
#include <asm/hypervisor.h>
#include <asm/cpufeature.h>
+#include <asm/pti.h>
/*
* We need to define the tracepoints somewhere, and tlb.c
@@ -160,6 +161,12 @@ struct map_range {
static int page_size_mask;
+static void enable_global_pages(void)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ __supported_pte_mask |= _PAGE_GLOBAL;
+}
+
static void __init probe_page_size_mask(void)
{
/*
@@ -177,11 +184,11 @@ static void __init probe_page_size_mask(void)
cr4_set_bits_and_update_boot(X86_CR4_PSE);
/* Enable PGE if available */
+ __supported_pte_mask &= ~_PAGE_GLOBAL;
if (boot_cpu_has(X86_FEATURE_PGE)) {
cr4_set_bits_and_update_boot(X86_CR4_PGE);
- __supported_pte_mask |= _PAGE_GLOBAL;
- } else
- __supported_pte_mask &= ~_PAGE_GLOBAL;
+ enable_global_pages();
+ }
/* Enable 1 GB linear kernel mappings if available: */
if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
@@ -194,34 +201,44 @@ static void __init probe_page_size_mask(void)
static void setup_pcid(void)
{
-#ifdef CONFIG_X86_64
- if (boot_cpu_has(X86_FEATURE_PCID)) {
- if (boot_cpu_has(X86_FEATURE_PGE)) {
- /*
- * This can't be cr4_set_bits_and_update_boot() --
- * the trampoline code can't handle CR4.PCIDE and
- * it wouldn't do any good anyway. Despite the name,
- * cr4_set_bits_and_update_boot() doesn't actually
- * cause the bits in question to remain set all the
- * way through the secondary boot asm.
- *
- * Instead, we brute-force it and set CR4.PCIDE
- * manually in start_secondary().
- */
- cr4_set_bits(X86_CR4_PCIDE);
- } else {
- /*
- * flush_tlb_all(), as currently implemented, won't
- * work if PCID is on but PGE is not. Since that
- * combination doesn't exist on real hardware, there's
- * no reason to try to fully support it, but it's
- * polite to avoid corrupting data if we're on
- * an improperly configured VM.
- */
- setup_clear_cpu_cap(X86_FEATURE_PCID);
- }
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ if (!boot_cpu_has(X86_FEATURE_PCID))
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
+ /*
+ * This can't be cr4_set_bits_and_update_boot() -- the
+ * trampoline code can't handle CR4.PCIDE and it wouldn't
+ * do any good anyway. Despite the name,
+ * cr4_set_bits_and_update_boot() doesn't actually cause
+ * the bits in question to remain set all the way through
+ * the secondary boot asm.
+ *
+ * Instead, we brute-force it and set CR4.PCIDE manually in
+ * start_secondary().
+ */
+ cr4_set_bits(X86_CR4_PCIDE);
+
+ /*
+ * INVPCID's single-context modes (2/3) only work if we set
+ * X86_CR4_PCIDE, *and* we INVPCID support. It's unusable
+ * on systems that have X86_CR4_PCIDE clear, or that have
+ * no INVPCID support at all.
+ */
+ if (boot_cpu_has(X86_FEATURE_INVPCID))
+ setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE);
+ } else {
+ /*
+ * flush_tlb_all(), as currently implemented, won't work if
+ * PCID is on but PGE is not. Since that combination
+ * doesn't exist on real hardware, there's no reason to try
+ * to fully support it, but it's polite to avoid corrupting
+ * data if we're on an improperly configured VM.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
}
-#endif
}
#ifdef CONFIG_X86_32
@@ -622,6 +639,7 @@ void __init init_mem_mapping(void)
{
unsigned long end;
+ pti_check_boottime_disable();
probe_page_size_mask();
setup_pcid();
@@ -845,12 +863,12 @@ void __init zone_sizes_init(void)
free_area_init_nodes(max_zone_pfns);
}
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
.loaded_mm = &init_mm,
.next_asid = 1,
.cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */
};
-EXPORT_SYMBOL_GPL(cpu_tlbstate);
+EXPORT_PER_CPU_SYMBOL(cpu_tlbstate);
void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
{
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8a64a6f2848d..135c9a7898c7 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -50,6 +50,7 @@
#include <asm/setup.h>
#include <asm/set_memory.h>
#include <asm/page_types.h>
+#include <asm/cpu_entry_area.h>
#include <asm/init.h>
#include "mm_internal.h"
@@ -766,6 +767,7 @@ void __init mem_init(void)
mem_init_print_info(NULL);
printk(KERN_INFO "virtual kernel memory layout:\n"
" fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
+ " cpu_entry : 0x%08lx - 0x%08lx (%4ld kB)\n"
#ifdef CONFIG_HIGHMEM
" pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
#endif
@@ -777,6 +779,10 @@ void __init mem_init(void)
FIXADDR_START, FIXADDR_TOP,
(FIXADDR_TOP - FIXADDR_START) >> 10,
+ CPU_ENTRY_AREA_BASE,
+ CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE,
+ CPU_ENTRY_AREA_MAP_SIZE >> 10,
+
#ifdef CONFIG_HIGHMEM
PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
(LAST_PKMAP*PAGE_SIZE) >> 10,
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 6e4573b1da34..c45b6ec5357b 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -404,11 +404,11 @@ void iounmap(volatile void __iomem *addr)
return;
}
+ mmiotrace_iounmap(addr);
+
addr = (volatile void __iomem *)
(PAGE_MASK & (unsigned long __force)addr);
- mmiotrace_iounmap(addr);
-
/* Use the vm area unlocked, assuming the caller
ensures there isn't another iounmap for the same address
in parallel. Reuse of the virtual address is prevented by
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 99dfed6dfef8..af6f2f9c6a26 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -15,15 +15,20 @@
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/pgtable.h>
+#include <asm/cpu_entry_area.h>
extern struct range pfn_mapped[E820_MAX_ENTRIES];
static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
-static __init void *early_alloc(size_t size, int nid)
+static __init void *early_alloc(size_t size, int nid, bool panic)
{
- return memblock_virt_alloc_try_nid_nopanic(size, size,
- __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+ if (panic)
+ return memblock_virt_alloc_try_nid(size, size,
+ __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+ else
+ return memblock_virt_alloc_try_nid_nopanic(size, size,
+ __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
}
static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
@@ -37,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
if (boot_cpu_has(X86_FEATURE_PSE) &&
((end - addr) == PMD_SIZE) &&
IS_ALIGNED(addr, PMD_SIZE)) {
- p = early_alloc(PMD_SIZE, nid);
+ p = early_alloc(PMD_SIZE, nid, false);
if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
return;
else if (p)
memblock_free(__pa(p), PMD_SIZE);
}
- p = early_alloc(PAGE_SIZE, nid);
+ p = early_alloc(PAGE_SIZE, nid, true);
pmd_populate_kernel(&init_mm, pmd, p);
}
@@ -56,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
if (!pte_none(*pte))
continue;
- p = early_alloc(PAGE_SIZE, nid);
+ p = early_alloc(PAGE_SIZE, nid, true);
entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL);
set_pte_at(&init_mm, addr, pte, entry);
} while (pte++, addr += PAGE_SIZE, addr != end);
@@ -74,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
if (boot_cpu_has(X86_FEATURE_GBPAGES) &&
((end - addr) == PUD_SIZE) &&
IS_ALIGNED(addr, PUD_SIZE)) {
- p = early_alloc(PUD_SIZE, nid);
+ p = early_alloc(PUD_SIZE, nid, false);
if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
return;
else if (p)
memblock_free(__pa(p), PUD_SIZE);
}
- p = early_alloc(PAGE_SIZE, nid);
+ p = early_alloc(PAGE_SIZE, nid, true);
pud_populate(&init_mm, pud, p);
}
@@ -100,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
unsigned long next;
if (p4d_none(*p4d)) {
- void *p = early_alloc(PAGE_SIZE, nid);
+ void *p = early_alloc(PAGE_SIZE, nid, true);
p4d_populate(&init_mm, p4d, p);
}
@@ -121,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr,
unsigned long next;
if (pgd_none(*pgd)) {
- p = early_alloc(PAGE_SIZE, nid);
+ p = early_alloc(PAGE_SIZE, nid, true);
pgd_populate(&init_mm, pgd, p);
}
@@ -277,6 +282,7 @@ void __init kasan_early_init(void)
void __init kasan_init(void)
{
int i;
+ void *shadow_cpu_entry_begin, *shadow_cpu_entry_end;
#ifdef CONFIG_KASAN_INLINE
register_die_notifier(&kasan_die_notifier);
@@ -321,16 +327,33 @@ void __init kasan_init(void)
map_range(&pfn_mapped[i]);
}
+ shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE;
+ shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin);
+ shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin,
+ PAGE_SIZE);
+
+ shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE +
+ CPU_ENTRY_AREA_MAP_SIZE);
+ shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end);
+ shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end,
+ PAGE_SIZE);
+
kasan_populate_zero_shadow(
kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
- kasan_mem_to_shadow((void *)__START_KERNEL_map));
+ shadow_cpu_entry_begin);
+
+ kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
+ (unsigned long)shadow_cpu_entry_end, 0);
+
+ kasan_populate_zero_shadow(shadow_cpu_entry_end,
+ kasan_mem_to_shadow((void *)__START_KERNEL_map));
kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext),
(unsigned long)kasan_mem_to_shadow(_end),
early_pfn_to_nid(__pa(_stext)));
kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
- (void *)KASAN_SHADOW_END);
+ (void *)KASAN_SHADOW_END);
load_cr3(init_top_pgt);
__flush_tlb_all();
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 879ef930e2c2..aedebd2ebf1e 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -34,25 +34,14 @@
#define TB_SHIFT 40
/*
- * Virtual address start and end range for randomization. The end changes base
- * on configuration to have the highest amount of space for randomization.
- * It increases the possible random position for each randomized region.
+ * Virtual address start and end range for randomization.
*
- * You need to add an if/def entry if you introduce a new memory region
- * compatible with KASLR. Your entry must be in logical order with memory
- * layout. For example, ESPFIX is before EFI because its virtual address is
- * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to
- * ensure that this order is correct and won't be changed.
+ * The end address could depend on more configuration options to make the
+ * highest amount of space for randomization available, but that's too hard
+ * to keep straight and caused issues already.
*/
static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
-
-#if defined(CONFIG_X86_ESPFIX64)
-static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
-#elif defined(CONFIG_EFI)
-static const unsigned long vaddr_end = EFI_VA_END;
-#else
-static const unsigned long vaddr_end = __START_KERNEL_map;
-#endif
+static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
/* Default values */
unsigned long page_offset_base = __PAGE_OFFSET_BASE;
@@ -101,15 +90,12 @@ void __init kernel_randomize_memory(void)
unsigned long remain_entropy;
/*
- * All these BUILD_BUG_ON checks ensures the memory layout is
- * consistent with the vaddr_start/vaddr_end variables.
+ * These BUILD_BUG_ON checks ensure the memory layout is consistent
+ * with the vaddr_start/vaddr_end variables. These checks are very
+ * limited....
*/
BUILD_BUG_ON(vaddr_start >= vaddr_end);
- BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
- vaddr_end >= EFI_VA_END);
- BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
- IS_ENABLED(CONFIG_EFI)) &&
- vaddr_end >= __START_KERNEL_map);
+ BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
if (!kaslr_memory_enabled())
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/error.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/error.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/opcode.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/pte.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/pte.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/selftest.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/selftest.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index c21c2ed04612..58477ec3d66d 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -435,17 +435,18 @@ int register_kmmio_probe(struct kmmio_probe *p)
unsigned long flags;
int ret = 0;
unsigned long size = 0;
+ unsigned long addr = p->addr & PAGE_MASK;
const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
unsigned int l;
pte_t *pte;
spin_lock_irqsave(&kmmio_lock, flags);
- if (get_kmmio_probe(p->addr)) {
+ if (get_kmmio_probe(addr)) {
ret = -EEXIST;
goto out;
}
- pte = lookup_address(p->addr, &l);
+ pte = lookup_address(addr, &l);
if (!pte) {
ret = -EINVAL;
goto out;
@@ -454,7 +455,7 @@ int register_kmmio_probe(struct kmmio_probe *p)
kmmio_count++;
list_add_rcu(&p->list, &kmmio_probes);
while (size < size_lim) {
- if (add_kmmio_fault_page(p->addr + size))
+ if (add_kmmio_fault_page(addr + size))
pr_err("Unable to set page fault.\n");
size += page_level_size(l);
}
@@ -528,19 +529,20 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
{
unsigned long flags;
unsigned long size = 0;
+ unsigned long addr = p->addr & PAGE_MASK;
const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
struct kmmio_fault_page *release_list = NULL;
struct kmmio_delayed_release *drelease;
unsigned int l;
pte_t *pte;
- pte = lookup_address(p->addr, &l);
+ pte = lookup_address(addr, &l);
if (!pte)
return;
spin_lock_irqsave(&kmmio_lock, flags);
while (size < size_lim) {
- release_kmmio_fault_page(p->addr + size, &release_list);
+ release_kmmio_fault_page(addr + size, &release_list);
size += page_level_size(l);
}
list_del_rcu(&p->list);
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index d9a9e9fc75dd..e1d61e8500f9 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -405,13 +405,13 @@ bool sme_active(void)
{
return sme_me_mask && !sev_enabled;
}
-EXPORT_SYMBOL_GPL(sme_active);
+EXPORT_SYMBOL(sme_active);
bool sev_active(void)
{
return sme_me_mask && sev_enabled;
}
-EXPORT_SYMBOL_GPL(sev_active);
+EXPORT_SYMBOL(sev_active);
static const struct dma_map_ops sev_dma_ops = {
.alloc = sev_alloc,
@@ -464,37 +464,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size)
set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT);
}
-static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start,
- unsigned long end)
+struct sme_populate_pgd_data {
+ void *pgtable_area;
+ pgd_t *pgd;
+
+ pmdval_t pmd_flags;
+ pteval_t pte_flags;
+ unsigned long paddr;
+
+ unsigned long vaddr;
+ unsigned long vaddr_end;
+};
+
+static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
{
unsigned long pgd_start, pgd_end, pgd_size;
pgd_t *pgd_p;
- pgd_start = start & PGDIR_MASK;
- pgd_end = end & PGDIR_MASK;
+ pgd_start = ppd->vaddr & PGDIR_MASK;
+ pgd_end = ppd->vaddr_end & PGDIR_MASK;
- pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1);
- pgd_size *= sizeof(pgd_t);
+ pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t);
- pgd_p = pgd_base + pgd_index(start);
+ pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
memset(pgd_p, 0, pgd_size);
}
-#define PGD_FLAGS _KERNPG_TABLE_NOENC
-#define P4D_FLAGS _KERNPG_TABLE_NOENC
-#define PUD_FLAGS _KERNPG_TABLE_NOENC
-#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+#define PGD_FLAGS _KERNPG_TABLE_NOENC
+#define P4D_FLAGS _KERNPG_TABLE_NOENC
+#define PUD_FLAGS _KERNPG_TABLE_NOENC
+#define PMD_FLAGS _KERNPG_TABLE_NOENC
+
+#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+
+#define PMD_FLAGS_DEC PMD_FLAGS_LARGE
+#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+ (_PAGE_PAT | _PAGE_PWT))
+
+#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC)
+
+#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL)
+
+#define PTE_FLAGS_DEC PTE_FLAGS
+#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+ (_PAGE_PAT | _PAGE_PWT))
+
+#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC)
-static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
- unsigned long vaddr, pmdval_t pmd_val)
+static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
{
pgd_t *pgd_p;
p4d_t *p4d_p;
pud_t *pud_p;
pmd_t *pmd_p;
- pgd_p = pgd_base + pgd_index(vaddr);
+ pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
if (native_pgd_val(*pgd_p)) {
if (IS_ENABLED(CONFIG_X86_5LEVEL))
p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
@@ -504,15 +529,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
pgd_t pgd;
if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- p4d_p = pgtable_area;
+ p4d_p = ppd->pgtable_area;
memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D);
- pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
+ ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS);
} else {
- pud_p = pgtable_area;
+ pud_p = ppd->pgtable_area;
memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
- pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
+ ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS);
}
@@ -520,58 +545,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
}
if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- p4d_p += p4d_index(vaddr);
+ p4d_p += p4d_index(ppd->vaddr);
if (native_p4d_val(*p4d_p)) {
pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK);
} else {
p4d_t p4d;
- pud_p = pgtable_area;
+ pud_p = ppd->pgtable_area;
memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
- pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
+ ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS);
native_set_p4d(p4d_p, p4d);
}
}
- pud_p += pud_index(vaddr);
+ pud_p += pud_index(ppd->vaddr);
if (native_pud_val(*pud_p)) {
if (native_pud_val(*pud_p) & _PAGE_PSE)
- goto out;
+ return NULL;
pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK);
} else {
pud_t pud;
- pmd_p = pgtable_area;
+ pmd_p = ppd->pgtable_area;
memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
- pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
+ ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS);
native_set_pud(pud_p, pud);
}
- pmd_p += pmd_index(vaddr);
+ return pmd_p;
+}
+
+static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
+{
+ pmd_t *pmd_p;
+
+ pmd_p = sme_prepare_pgd(ppd);
+ if (!pmd_p)
+ return;
+
+ pmd_p += pmd_index(ppd->vaddr);
if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE))
- native_set_pmd(pmd_p, native_make_pmd(pmd_val));
+ native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags));
+}
-out:
- return pgtable_area;
+static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
+{
+ pmd_t *pmd_p;
+ pte_t *pte_p;
+
+ pmd_p = sme_prepare_pgd(ppd);
+ if (!pmd_p)
+ return;
+
+ pmd_p += pmd_index(ppd->vaddr);
+ if (native_pmd_val(*pmd_p)) {
+ if (native_pmd_val(*pmd_p) & _PAGE_PSE)
+ return;
+
+ pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK);
+ } else {
+ pmd_t pmd;
+
+ pte_p = ppd->pgtable_area;
+ memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE);
+ ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE;
+
+ pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS);
+ native_set_pmd(pmd_p, pmd);
+ }
+
+ pte_p += pte_index(ppd->vaddr);
+ if (!native_pte_val(*pte_p))
+ native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags));
+}
+
+static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
+{
+ while (ppd->vaddr < ppd->vaddr_end) {
+ sme_populate_pgd_large(ppd);
+
+ ppd->vaddr += PMD_PAGE_SIZE;
+ ppd->paddr += PMD_PAGE_SIZE;
+ }
+}
+
+static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
+{
+ while (ppd->vaddr < ppd->vaddr_end) {
+ sme_populate_pgd(ppd);
+
+ ppd->vaddr += PAGE_SIZE;
+ ppd->paddr += PAGE_SIZE;
+ }
+}
+
+static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
+ pmdval_t pmd_flags, pteval_t pte_flags)
+{
+ unsigned long vaddr_end;
+
+ ppd->pmd_flags = pmd_flags;
+ ppd->pte_flags = pte_flags;
+
+ /* Save original end value since we modify the struct value */
+ vaddr_end = ppd->vaddr_end;
+
+ /* If start is not 2MB aligned, create PTE entries */
+ ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE);
+ __sme_map_range_pte(ppd);
+
+ /* Create PMD entries */
+ ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK;
+ __sme_map_range_pmd(ppd);
+
+ /* If end is not 2MB aligned, create PTE entries */
+ ppd->vaddr_end = vaddr_end;
+ __sme_map_range_pte(ppd);
+}
+
+static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
+}
+
+static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
+}
+
+static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
}
static unsigned long __init sme_pgtable_calc(unsigned long len)
{
- unsigned long p4d_size, pud_size, pmd_size;
+ unsigned long p4d_size, pud_size, pmd_size, pte_size;
unsigned long total;
/*
* Perform a relatively simplistic calculation of the pagetable
- * entries that are needed. That mappings will be covered by 2MB
- * PMD entries so we can conservatively calculate the required
+ * entries that are needed. Those mappings will be covered mostly
+ * by 2MB PMD entries so we can conservatively calculate the required
* number of P4D, PUD and PMD structures needed to perform the
- * mappings. Incrementing the count for each covers the case where
- * the addresses cross entries.
+ * mappings. For mappings that are not 2MB aligned, PTE mappings
+ * would be needed for the start and end portion of the address range
+ * that fall outside of the 2MB alignment. This results in, at most,
+ * two extra pages to hold PTE entries for each range that is mapped.
+ * Incrementing the count for each covers the case where the addresses
+ * cross entries.
*/
if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1;
@@ -585,8 +712,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
}
pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1;
pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD;
+ pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE;
- total = p4d_size + pud_size + pmd_size;
+ total = p4d_size + pud_size + pmd_size + pte_size;
/*
* Now calculate the added pagetable structures needed to populate
@@ -610,29 +738,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
return total;
}
-void __init sme_encrypt_kernel(void)
+void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp)
{
unsigned long workarea_start, workarea_end, workarea_len;
unsigned long execute_start, execute_end, execute_len;
unsigned long kernel_start, kernel_end, kernel_len;
+ unsigned long initrd_start, initrd_end, initrd_len;
+ struct sme_populate_pgd_data ppd;
unsigned long pgtable_area_len;
- unsigned long paddr, pmd_flags;
unsigned long decrypted_base;
- void *pgtable_area;
- pgd_t *pgd;
if (!sme_active())
return;
/*
- * Prepare for encrypting the kernel by building new pagetables with
- * the necessary attributes needed to encrypt the kernel in place.
+ * Prepare for encrypting the kernel and initrd by building new
+ * pagetables with the necessary attributes needed to encrypt the
+ * kernel in place.
*
* One range of virtual addresses will map the memory occupied
- * by the kernel as encrypted.
+ * by the kernel and initrd as encrypted.
*
* Another range of virtual addresses will map the memory occupied
- * by the kernel as decrypted and write-protected.
+ * by the kernel and initrd as decrypted and write-protected.
*
* The use of write-protect attribute will prevent any of the
* memory from being cached.
@@ -643,6 +771,20 @@ void __init sme_encrypt_kernel(void)
kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE);
kernel_len = kernel_end - kernel_start;
+ initrd_start = 0;
+ initrd_end = 0;
+ initrd_len = 0;
+#ifdef CONFIG_BLK_DEV_INITRD
+ initrd_len = (unsigned long)bp->hdr.ramdisk_size |
+ ((unsigned long)bp->ext_ramdisk_size << 32);
+ if (initrd_len) {
+ initrd_start = (unsigned long)bp->hdr.ramdisk_image |
+ ((unsigned long)bp->ext_ramdisk_image << 32);
+ initrd_end = PAGE_ALIGN(initrd_start + initrd_len);
+ initrd_len = initrd_end - initrd_start;
+ }
+#endif
+
/* Set the encryption workarea to be immediately after the kernel */
workarea_start = kernel_end;
@@ -665,16 +807,21 @@ void __init sme_encrypt_kernel(void)
*/
pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD;
pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2;
+ if (initrd_len)
+ pgtable_area_len += sme_pgtable_calc(initrd_len) * 2;
/* PUDs and PMDs needed in the current pagetables for the workarea */
pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len);
/*
* The total workarea includes the executable encryption area and
- * the pagetable area.
+ * the pagetable area. The start of the workarea is already 2MB
+ * aligned, align the end of the workarea on a 2MB boundary so that
+ * we don't try to create/allocate PTE entries from the workarea
+ * before it is mapped.
*/
workarea_len = execute_len + pgtable_area_len;
- workarea_end = workarea_start + workarea_len;
+ workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE);
/*
* Set the address to the start of where newly created pagetable
@@ -683,45 +830,30 @@ void __init sme_encrypt_kernel(void)
* pagetables and when the new encrypted and decrypted kernel
* mappings are populated.
*/
- pgtable_area = (void *)execute_end;
+ ppd.pgtable_area = (void *)execute_end;
/*
* Make sure the current pagetable structure has entries for
* addressing the workarea.
*/
- pgd = (pgd_t *)native_read_cr3_pa();
- paddr = workarea_start;
- while (paddr < workarea_end) {
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr,
- paddr + PMD_FLAGS);
-
- paddr += PMD_PAGE_SIZE;
- }
+ ppd.pgd = (pgd_t *)native_read_cr3_pa();
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start;
+ ppd.vaddr_end = workarea_end;
+ sme_map_range_decrypted(&ppd);
/* Flush the TLB - no globals so cr3 is enough */
native_write_cr3(__native_read_cr3());
/*
* A new pagetable structure is being built to allow for the kernel
- * to be encrypted. It starts with an empty PGD that will then be
- * populated with new PUDs and PMDs as the encrypted and decrypted
- * kernel mappings are created.
+ * and initrd to be encrypted. It starts with an empty PGD that will
+ * then be populated with new PUDs and PMDs as the encrypted and
+ * decrypted kernel mappings are created.
*/
- pgd = pgtable_area;
- memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD);
- pgtable_area += sizeof(*pgd) * PTRS_PER_PGD;
-
- /* Add encrypted kernel (identity) mappings */
- pmd_flags = PMD_FLAGS | _PAGE_ENC;
- paddr = kernel_start;
- while (paddr < kernel_end) {
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr,
- paddr + pmd_flags);
-
- paddr += PMD_PAGE_SIZE;
- }
+ ppd.pgd = ppd.pgtable_area;
+ memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD);
+ ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD;
/*
* A different PGD index/entry must be used to get different
@@ -730,47 +862,79 @@ void __init sme_encrypt_kernel(void)
* the base of the mapping.
*/
decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1);
+ if (initrd_len) {
+ unsigned long check_base;
+
+ check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1);
+ decrypted_base = max(decrypted_base, check_base);
+ }
decrypted_base <<= PGDIR_SHIFT;
+ /* Add encrypted kernel (identity) mappings */
+ ppd.paddr = kernel_start;
+ ppd.vaddr = kernel_start;
+ ppd.vaddr_end = kernel_end;
+ sme_map_range_encrypted(&ppd);
+
/* Add decrypted, write-protected kernel (non-identity) mappings */
- pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT);
- paddr = kernel_start;
- while (paddr < kernel_end) {
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr + decrypted_base,
- paddr + pmd_flags);
-
- paddr += PMD_PAGE_SIZE;
+ ppd.paddr = kernel_start;
+ ppd.vaddr = kernel_start + decrypted_base;
+ ppd.vaddr_end = kernel_end + decrypted_base;
+ sme_map_range_decrypted_wp(&ppd);
+
+ if (initrd_len) {
+ /* Add encrypted initrd (identity) mappings */
+ ppd.paddr = initrd_start;
+ ppd.vaddr = initrd_start;
+ ppd.vaddr_end = initrd_end;
+ sme_map_range_encrypted(&ppd);
+ /*
+ * Add decrypted, write-protected initrd (non-identity) mappings
+ */
+ ppd.paddr = initrd_start;
+ ppd.vaddr = initrd_start + decrypted_base;
+ ppd.vaddr_end = initrd_end + decrypted_base;
+ sme_map_range_decrypted_wp(&ppd);
}
/* Add decrypted workarea mappings to both kernel mappings */
- paddr = workarea_start;
- while (paddr < workarea_end) {
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr,
- paddr + PMD_FLAGS);
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start;
+ ppd.vaddr_end = workarea_end;
+ sme_map_range_decrypted(&ppd);
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr + decrypted_base,
- paddr + PMD_FLAGS);
-
- paddr += PMD_PAGE_SIZE;
- }
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start + decrypted_base;
+ ppd.vaddr_end = workarea_end + decrypted_base;
+ sme_map_range_decrypted(&ppd);
/* Perform the encryption */
sme_encrypt_execute(kernel_start, kernel_start + decrypted_base,
- kernel_len, workarea_start, (unsigned long)pgd);
+ kernel_len, workarea_start, (unsigned long)ppd.pgd);
+
+ if (initrd_len)
+ sme_encrypt_execute(initrd_start, initrd_start + decrypted_base,
+ initrd_len, workarea_start,
+ (unsigned long)ppd.pgd);
/*
* At this point we are running encrypted. Remove the mappings for
* the decrypted areas - all that is needed for this is to remove
* the PGD entry/entries.
*/
- sme_clear_pgd(pgd, kernel_start + decrypted_base,
- kernel_end + decrypted_base);
+ ppd.vaddr = kernel_start + decrypted_base;
+ ppd.vaddr_end = kernel_end + decrypted_base;
+ sme_clear_pgd(&ppd);
+
+ if (initrd_len) {
+ ppd.vaddr = initrd_start + decrypted_base;
+ ppd.vaddr_end = initrd_end + decrypted_base;
+ sme_clear_pgd(&ppd);
+ }
- sme_clear_pgd(pgd, workarea_start + decrypted_base,
- workarea_end + decrypted_base);
+ ppd.vaddr = workarea_start + decrypted_base;
+ ppd.vaddr_end = workarea_end + decrypted_base;
+ sme_clear_pgd(&ppd);
/* Flush the TLB - no globals so cr3 is enough */
native_write_cr3(__native_read_cr3());
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 730e6d541df1..01f682cf77a8 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute)
/*
* Entry parameters:
- * RDI - virtual address for the encrypted kernel mapping
- * RSI - virtual address for the decrypted kernel mapping
- * RDX - length of kernel
+ * RDI - virtual address for the encrypted mapping
+ * RSI - virtual address for the decrypted mapping
+ * RDX - length to encrypt
* RCX - virtual address of the encryption workarea, including:
* - stack page (PAGE_SIZE)
* - encryption routine page (PAGE_SIZE)
@@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute)
addq $PAGE_SIZE, %rax /* Workarea encryption routine */
push %r12
- movq %rdi, %r10 /* Encrypted kernel */
- movq %rsi, %r11 /* Decrypted kernel */
- movq %rdx, %r12 /* Kernel length */
+ movq %rdi, %r10 /* Encrypted area */
+ movq %rsi, %r11 /* Decrypted area */
+ movq %rdx, %r12 /* Area length */
/* Copy encryption routine into the workarea */
movq %rax, %rdi /* Workarea encryption routine */
@@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute)
rep movsb
/* Setup registers for call */
- movq %r10, %rdi /* Encrypted kernel */
- movq %r11, %rsi /* Decrypted kernel */
+ movq %r10, %rdi /* Encrypted area */
+ movq %r11, %rsi /* Decrypted area */
movq %r8, %rdx /* Pagetables used for encryption */
- movq %r12, %rcx /* Kernel length */
+ movq %r12, %rcx /* Area length */
movq %rax, %r8 /* Workarea encryption routine */
addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */
@@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute)
ENTRY(__enc_copy)
/*
- * Routine used to encrypt kernel.
+ * Routine used to encrypt memory in place.
* This routine must be run outside of the kernel proper since
* the kernel will be encrypted during the process. So this
* routine is defined here and then copied to an area outside
@@ -79,19 +79,19 @@ ENTRY(__enc_copy)
* during execution.
*
* On entry the registers must be:
- * RDI - virtual address for the encrypted kernel mapping
- * RSI - virtual address for the decrypted kernel mapping
+ * RDI - virtual address for the encrypted mapping
+ * RSI - virtual address for the decrypted mapping
* RDX - address of the pagetables to use for encryption
- * RCX - length of kernel
+ * RCX - length of area
* R8 - intermediate copy buffer
*
* RAX - points to this routine
*
- * The kernel will be encrypted by copying from the non-encrypted
- * kernel space to an intermediate buffer and then copying from the
- * intermediate buffer back to the encrypted kernel space. The physical
- * addresses of the two kernel space mappings are the same which
- * results in the kernel being encrypted "in place".
+ * The area will be encrypted by copying from the non-encrypted
+ * memory space to an intermediate buffer and then copying from the
+ * intermediate buffer back to the encrypted memory space. The physical
+ * addresses of the two mappings are the same which results in the area
+ * being encrypted "in place".
*/
/* Enable the new page tables */
mov %rdx, %cr3
@@ -103,47 +103,55 @@ ENTRY(__enc_copy)
orq $X86_CR4_PGE, %rdx
mov %rdx, %cr4
+ push %r15
+ push %r12
+
+ movq %rcx, %r9 /* Save area length */
+ movq %rdi, %r10 /* Save encrypted area address */
+ movq %rsi, %r11 /* Save decrypted area address */
+
/* Set the PAT register PA5 entry to write-protect */
- push %rcx
movl $MSR_IA32_CR_PAT, %ecx
rdmsr
- push %rdx /* Save original PAT value */
+ mov %rdx, %r15 /* Save original PAT value */
andl $0xffff00ff, %edx /* Clear PA5 */
orl $0x00000500, %edx /* Set PA5 to WP */
wrmsr
- pop %rdx /* RDX contains original PAT value */
- pop %rcx
-
- movq %rcx, %r9 /* Save kernel length */
- movq %rdi, %r10 /* Save encrypted kernel address */
- movq %rsi, %r11 /* Save decrypted kernel address */
wbinvd /* Invalidate any cache entries */
- /* Copy/encrypt 2MB at a time */
+ /* Copy/encrypt up to 2MB at a time */
+ movq $PMD_PAGE_SIZE, %r12
1:
- movq %r11, %rsi /* Source - decrypted kernel */
+ cmpq %r12, %r9
+ jnb 2f
+ movq %r9, %r12
+
+2:
+ movq %r11, %rsi /* Source - decrypted area */
movq %r8, %rdi /* Dest - intermediate copy buffer */
- movq $PMD_PAGE_SIZE, %rcx /* 2MB length */
+ movq %r12, %rcx
rep movsb
movq %r8, %rsi /* Source - intermediate copy buffer */
- movq %r10, %rdi /* Dest - encrypted kernel */
- movq $PMD_PAGE_SIZE, %rcx /* 2MB length */
+ movq %r10, %rdi /* Dest - encrypted area */
+ movq %r12, %rcx
rep movsb
- addq $PMD_PAGE_SIZE, %r11
- addq $PMD_PAGE_SIZE, %r10
- subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */
+ addq %r12, %r11
+ addq %r12, %r10
+ subq %r12, %r9 /* Kernel length decrement */
jnz 1b /* Kernel length not zero? */
/* Restore PAT register */
- push %rdx /* Save original PAT value */
movl $MSR_IA32_CR_PAT, %ecx
rdmsr
- pop %rdx /* Restore original PAT value */
+ mov %r15, %rdx /* Restore original PAT value */
wrmsr
+ pop %r12
+ pop %r15
+
ret
.L__enc_copy_end:
ENDPROC(__enc_copy)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 96d456a94b03..004abf9ebf12 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -355,14 +355,15 @@ static inline void _pgd_free(pgd_t *pgd)
kmem_cache_free(pgd_cache, pgd);
}
#else
+
static inline pgd_t *_pgd_alloc(void)
{
- return (pgd_t *)__get_free_page(PGALLOC_GFP);
+ return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
}
static inline void _pgd_free(pgd_t *pgd)
{
- free_page((unsigned long)pgd);
+ free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
}
#endif /* CONFIG_X86_PAE */
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 6b9bf023a700..c3c5274410a9 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -10,6 +10,7 @@
#include <linux/pagemap.h>
#include <linux/spinlock.h>
+#include <asm/cpu_entry_area.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/fixmap.h>
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
new file mode 100644
index 000000000000..ce38f165489b
--- /dev/null
+++ b/arch/x86/mm/pti.c
@@ -0,0 +1,368 @@
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * This code is based in part on work published here:
+ *
+ * https://github.com/IAIK/KAISER
+ *
+ * The original work was written by and and signed off by for the Linux
+ * kernel by:
+ *
+ * Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at>
+ * Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at>
+ * Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at>
+ * Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at>
+ *
+ * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com>
+ * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and
+ * Andy Lutomirsky <luto@amacapital.net>
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+
+#include <asm/cpufeature.h>
+#include <asm/hypervisor.h>
+#include <asm/vsyscall.h>
+#include <asm/cmdline.h>
+#include <asm/pti.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/desc.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt
+
+/* Backporting helper */
+#ifndef __GFP_NOTRACK
+#define __GFP_NOTRACK 0
+#endif
+
+static void __init pti_print_if_insecure(const char *reason)
+{
+ if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ pr_info("%s\n", reason);
+}
+
+static void __init pti_print_if_secure(const char *reason)
+{
+ if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ pr_info("%s\n", reason);
+}
+
+void __init pti_check_boottime_disable(void)
+{
+ char arg[5];
+ int ret;
+
+ if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
+ pti_print_if_insecure("disabled on XEN PV.");
+ return;
+ }
+
+ ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
+ if (ret > 0) {
+ if (ret == 3 && !strncmp(arg, "off", 3)) {
+ pti_print_if_insecure("disabled on command line.");
+ return;
+ }
+ if (ret == 2 && !strncmp(arg, "on", 2)) {
+ pti_print_if_secure("force enabled on command line.");
+ goto enable;
+ }
+ if (ret == 4 && !strncmp(arg, "auto", 4))
+ goto autosel;
+ }
+
+ if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+ pti_print_if_insecure("disabled on command line.");
+ return;
+ }
+
+autosel:
+ if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ return;
+enable:
+ setup_force_cpu_cap(X86_FEATURE_PTI);
+}
+
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ /*
+ * Changes to the high (kernel) portion of the kernelmode page
+ * tables are not automatically propagated to the usermode tables.
+ *
+ * Users should keep in mind that, unlike the kernelmode tables,
+ * there is no vmalloc_fault equivalent for the usermode tables.
+ * Top-level entries added to init_mm's usermode pgd after boot
+ * will not be automatically propagated to other mms.
+ */
+ if (!pgdp_maps_userspace(pgdp))
+ return pgd;
+
+ /*
+ * The user page tables get the full PGD, accessible from
+ * userspace:
+ */
+ kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd;
+
+ /*
+ * If this is normal user memory, make it NX in the kernel
+ * pagetables so that, if we somehow screw up and return to
+ * usermode with the kernel CR3 loaded, we'll get a page fault
+ * instead of allowing user code to execute with the wrong CR3.
+ *
+ * As exceptions, we don't set NX if:
+ * - _PAGE_USER is not set. This could be an executable
+ * EFI runtime mapping or something similar, and the kernel
+ * may execute from it
+ * - we don't have NX support
+ * - we're clearing the PGD (i.e. the new pgd is not present).
+ */
+ if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) &&
+ (__supported_pte_mask & _PAGE_NX))
+ pgd.pgd |= _PAGE_NX;
+
+ /* return the copy of the PGD we want the kernel to use: */
+ return pgd;
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a P4D on success, or NULL on failure.
+ */
+static __init p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
+{
+ pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address));
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+
+ if (address < PAGE_OFFSET) {
+ WARN_ONCE(1, "attempt to walk user address\n");
+ return NULL;
+ }
+
+ if (pgd_none(*pgd)) {
+ unsigned long new_p4d_page = __get_free_page(gfp);
+ if (!new_p4d_page)
+ return NULL;
+
+ set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
+ }
+ BUILD_BUG_ON(pgd_large(*pgd) != 0);
+
+ return p4d_offset(pgd, address);
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a PMD on success, or NULL on failure.
+ */
+static __init pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
+{
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+ pud_t *pud;
+
+ BUILD_BUG_ON(p4d_large(*p4d) != 0);
+ if (p4d_none(*p4d)) {
+ unsigned long new_pud_page = __get_free_page(gfp);
+ if (!new_pud_page)
+ return NULL;
+
+ set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
+ }
+
+ pud = pud_offset(p4d, address);
+ /* The user page tables do not use large mappings: */
+ if (pud_large(*pud)) {
+ WARN_ON(1);
+ return NULL;
+ }
+ if (pud_none(*pud)) {
+ unsigned long new_pmd_page = __get_free_page(gfp);
+ if (!new_pmd_page)
+ return NULL;
+
+ set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+ }
+
+ return pmd_offset(pud, address);
+}
+
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+/*
+ * Walk the shadow copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down. Does not support large pages.
+ *
+ * Note: this is only used when mapping *new* kernel data into the
+ * user/shadow page tables. It is never used for userspace data.
+ *
+ * Returns a pointer to a PTE on success, or NULL on failure.
+ */
+static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+{
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+ pte_t *pte;
+
+ /* We can't do anything sensible if we hit a large mapping. */
+ if (pmd_large(*pmd)) {
+ WARN_ON(1);
+ return NULL;
+ }
+
+ if (pmd_none(*pmd)) {
+ unsigned long new_pte_page = __get_free_page(gfp);
+ if (!new_pte_page)
+ return NULL;
+
+ set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+ }
+
+ pte = pte_offset_kernel(pmd, address);
+ if (pte_flags(*pte) & _PAGE_USER) {
+ WARN_ONCE(1, "attempt to walk to user pte\n");
+ return NULL;
+ }
+ return pte;
+}
+
+static void __init pti_setup_vsyscall(void)
+{
+ pte_t *pte, *target_pte;
+ unsigned int level;
+
+ pte = lookup_address(VSYSCALL_ADDR, &level);
+ if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
+ return;
+
+ target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR);
+ if (WARN_ON(!target_pte))
+ return;
+
+ *target_pte = *pte;
+ set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir));
+}
+#else
+static void __init pti_setup_vsyscall(void) { }
+#endif
+
+static void __init
+pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+{
+ unsigned long addr;
+
+ /*
+ * Clone the populated PMDs which cover start to end. These PMD areas
+ * can have holes.
+ */
+ for (addr = start; addr < end; addr += PMD_SIZE) {
+ pmd_t *pmd, *target_pmd;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+
+ pgd = pgd_offset_k(addr);
+ if (WARN_ON(pgd_none(*pgd)))
+ return;
+ p4d = p4d_offset(pgd, addr);
+ if (WARN_ON(p4d_none(*p4d)))
+ return;
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ continue;
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ continue;
+
+ target_pmd = pti_user_pagetable_walk_pmd(addr);
+ if (WARN_ON(!target_pmd))
+ return;
+
+ /*
+ * Copy the PMD. That is, the kernelmode and usermode
+ * tables will share the last-level page tables of this
+ * address range
+ */
+ *target_pmd = pmd_clear_flags(*pmd, clear);
+ }
+}
+
+/*
+ * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
+ * next-level entry on 5-level systems.
+ */
+static void __init pti_clone_p4d(unsigned long addr)
+{
+ p4d_t *kernel_p4d, *user_p4d;
+ pgd_t *kernel_pgd;
+
+ user_p4d = pti_user_pagetable_walk_p4d(addr);
+ kernel_pgd = pgd_offset_k(addr);
+ kernel_p4d = p4d_offset(kernel_pgd, addr);
+ *user_p4d = *kernel_p4d;
+}
+
+/*
+ * Clone the CPU_ENTRY_AREA into the user space visible page table.
+ */
+static void __init pti_clone_user_shared(void)
+{
+ pti_clone_p4d(CPU_ENTRY_AREA_BASE);
+}
+
+/*
+ * Clone the ESPFIX P4D into the user space visinble page table
+ */
+static void __init pti_setup_espfix64(void)
+{
+#ifdef CONFIG_X86_ESPFIX64
+ pti_clone_p4d(ESPFIX_BASE_ADDR);
+#endif
+}
+
+/*
+ * Clone the populated PMDs of the entry and irqentry text and force it RO.
+ */
+static void __init pti_clone_entry_text(void)
+{
+ pti_clone_pmds((unsigned long) __entry_text_start,
+ (unsigned long) __irqentry_text_end,
+ _PAGE_RW | _PAGE_GLOBAL);
+}
+
+/*
+ * Initialize kernel page table isolation
+ */
+void __init pti_init(void)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ pr_info("enabled\n");
+
+ pti_clone_user_shared();
+ pti_clone_entry_text();
+ pti_setup_espfix64();
+ pti_setup_vsyscall();
+}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 3118392cdf75..5bfe61a5e8e3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -28,6 +28,38 @@
* Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
*/
+/*
+ * We get here when we do something requiring a TLB invalidation
+ * but could not go invalidate all of the contexts. We do the
+ * necessary invalidation by clearing out the 'ctx_id' which
+ * forces a TLB flush when the context is loaded.
+ */
+void clear_asid_other(void)
+{
+ u16 asid;
+
+ /*
+ * This is only expected to be set if we have disabled
+ * kernel _PAGE_GLOBAL pages.
+ */
+ if (!static_cpu_has(X86_FEATURE_PTI)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
+ /* Do not need to flush the current asid */
+ if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid))
+ continue;
+ /*
+ * Make sure the next time we go to switch to
+ * this asid, we do a flush:
+ */
+ this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0);
+ }
+ this_cpu_write(cpu_tlbstate.invalidate_other, false);
+}
+
atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
@@ -42,6 +74,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
return;
}
+ if (this_cpu_read(cpu_tlbstate.invalidate_other))
+ clear_asid_other();
+
for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) !=
next->context.ctx_id)
@@ -65,6 +100,25 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
*need_flush = true;
}
+static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush)
+{
+ unsigned long new_mm_cr3;
+
+ if (need_flush) {
+ invalidate_user_asid(new_asid);
+ new_mm_cr3 = build_cr3(pgdir, new_asid);
+ } else {
+ new_mm_cr3 = build_cr3_noflush(pgdir, new_asid);
+ }
+
+ /*
+ * Caution: many callers of this function expect
+ * that load_cr3() is serializing and orders TLB
+ * fills with respect to the mm_cpumask writes.
+ */
+ write_cr3(new_mm_cr3);
+}
+
void leave_mm(int cpu)
{
struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
@@ -97,6 +151,34 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
local_irq_restore(flags);
}
+static void sync_current_stack_to_mm(struct mm_struct *mm)
+{
+ unsigned long sp = current_stack_pointer;
+ pgd_t *pgd = pgd_offset(mm, sp);
+
+ if (CONFIG_PGTABLE_LEVELS > 4) {
+ if (unlikely(pgd_none(*pgd))) {
+ pgd_t *pgd_ref = pgd_offset_k(sp);
+
+ set_pgd(pgd, *pgd_ref);
+ }
+ } else {
+ /*
+ * "pgd" is faked. The top level entries are "p4d"s, so sync
+ * the p4d. This compiles to approximately the same code as
+ * the 5-level case.
+ */
+ p4d_t *p4d = p4d_offset(pgd, sp);
+
+ if (unlikely(p4d_none(*p4d))) {
+ pgd_t *pgd_ref = pgd_offset_k(sp);
+ p4d_t *p4d_ref = p4d_offset(pgd_ref, sp);
+
+ set_p4d(p4d, *p4d_ref);
+ }
+ }
+}
+
void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
@@ -128,7 +210,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* isn't free.
*/
#ifdef CONFIG_DEBUG_VM
- if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) {
+ if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) {
/*
* If we were to BUG here, we'd be very likely to kill
* the system so hard that we don't see the call trace.
@@ -172,11 +254,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* mapped in the new pgd, we'll double-fault. Forcibly
* map it.
*/
- unsigned int index = pgd_index(current_stack_pointer);
- pgd_t *pgd = next->pgd + index;
-
- if (unlikely(pgd_none(*pgd)))
- set_pgd(pgd, init_mm.pgd[index]);
+ sync_current_stack_to_mm(next);
}
/* Stop remote flushes for the previous mm */
@@ -195,7 +273,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (need_flush) {
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- write_cr3(build_cr3(next, new_asid));
+ load_new_mm_cr3(next->pgd, new_asid, true);
/*
* NB: This gets called via leave_mm() in the idle path
@@ -208,7 +286,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
- write_cr3(build_cr3_noflush(next, new_asid));
+ load_new_mm_cr3(next->pgd, new_asid, false);
/* See above wrt _rcuidle. */
trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
@@ -288,7 +366,7 @@ void initialize_tlbstate_and_flush(void)
!(cr4_read_shadow() & X86_CR4_PCIDE));
/* Force ASID 0 and force a TLB flush. */
- write_cr3(build_cr3(mm, 0));
+ write_cr3(build_cr3(mm->pgd, 0));
/* Reinitialize tlbstate. */
this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
@@ -551,7 +629,7 @@ static void do_kernel_range_flush(void *info)
/* flush range by one by one 'invlpg' */
for (addr = f->start; addr < f->end; addr += PAGE_SIZE)
- __flush_tlb_single(addr);
+ __flush_tlb_one(addr);
}
void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
index bb461cfd01ab..526536c81ddc 100644
--- a/arch/x86/pci/broadcom_bus.c
+++ b/arch/x86/pci/broadcom_bus.c
@@ -97,7 +97,7 @@ static int __init broadcom_postcore_init(void)
* We should get host bridge information from ACPI unless the BIOS
* doesn't support it.
*/
- if (acpi_os_get_root_pointer())
+ if (!acpi_disabled && acpi_os_get_root_pointer())
return 0;
#endif
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 7a5350d08cef..563049c483a1 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -594,6 +594,11 @@ char *__init pcibios_setup(char *str)
} else if (!strcmp(str, "nocrs")) {
pci_probe |= PCI_ROOT_NO_CRS;
return NULL;
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ } else if (!strcmp(str, "big_root_window")) {
+ pci_probe |= PCI_BIG_ROOT_WINDOW;
+ return NULL;
+#endif
} else if (!strcmp(str, "earlydump")) {
pci_early_dump_regs = 1;
return NULL;
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 1e996df687a3..54ef19e90705 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -662,9 +662,23 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid);
*/
static void pci_amd_enable_64bit_bar(struct pci_dev *dev)
{
- unsigned i;
- u32 base, limit, high;
+ static const char *name = "PCI Bus 0000:00";
struct resource *res, *conflict;
+ u32 base, limit, high;
+ struct pci_dev *other;
+ unsigned i;
+
+ if (!(pci_probe & PCI_BIG_ROOT_WINDOW))
+ return;
+
+ /* Check that we are the only device of that type */
+ other = pci_get_device(dev->vendor, dev->device, NULL);
+ if (other != dev ||
+ (other = pci_get_device(dev->vendor, dev->device, other))) {
+ /* This is a multi-socket system, don't touch it for now */
+ pci_dev_put(other);
+ return;
+ }
for (i = 0; i < 8; i++) {
pci_read_config_dword(dev, AMD_141b_MMIO_BASE(i), &base);
@@ -689,17 +703,30 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev)
if (!res)
return;
- res->name = "PCI Bus 0000:00";
+ /*
+ * Allocate a 256GB window directly below the 0xfd00000000 hardware
+ * limit (see AMD Family 15h Models 30h-3Fh BKDG, sec 2.4.6).
+ */
+ res->name = name;
res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM |
IORESOURCE_MEM_64 | IORESOURCE_WINDOW;
- res->start = 0x100000000ull;
+ res->start = 0xbd00000000ull;
res->end = 0xfd00000000ull - 1;
- /* Just grab the free area behind system memory for this */
- while ((conflict = request_resource_conflict(&iomem_resource, res)))
- res->start = conflict->end + 1;
+ conflict = request_resource_conflict(&iomem_resource, res);
+ if (conflict) {
+ kfree(res);
+ if (conflict->name != name)
+ return;
- dev_info(&dev->dev, "adding root bus resource %pR\n", res);
+ /* We are resuming from suspend; just reenable the window */
+ res = conflict;
+ } else {
+ dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n",
+ res);
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+ pci_bus_add_resource(dev->bus, res, 0);
+ }
base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) |
AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK;
@@ -711,13 +738,16 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev)
pci_write_config_dword(dev, AMD_141b_MMIO_HIGH(i), high);
pci_write_config_dword(dev, AMD_141b_MMIO_LIMIT(i), limit);
pci_write_config_dword(dev, AMD_141b_MMIO_BASE(i), base);
-
- pci_bus_add_resource(dev->bus, res, 0);
}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
#endif
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 511921045312..43867bc85368 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -300,6 +300,7 @@ int __init intel_mid_pci_init(void)
pci_root_ops = intel_mid_pci_ops;
pci_soc_mode = 1;
/* Continue with standard init */
+ acpi_noirq_set();
return 1;
}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6a151ce70e86..c310a8284358 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -25,7 +25,6 @@
#include <linux/spinlock.h>
#include <linux/bootmem.h>
#include <linux/ioport.h>
-#include <linux/init.h>
#include <linux/mc146818rtc.h>
#include <linux/efi.h>
#include <linux/uaccess.h>
@@ -135,7 +134,9 @@ pgd_t * __init efi_call_phys_prolog(void)
pud[j] = *pud_offset(p4d_k, vaddr);
}
}
+ pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX;
}
+
out:
__flush_tlb_all();
@@ -196,6 +197,9 @@ static pgd_t *efi_pgd;
* because we want to avoid inserting EFI region mappings (EFI_VA_END
* to EFI_VA_START) into the standard kernel page tables. Everything
* else can be shared, see efi_sync_low_kernel_mappings().
+ *
+ * We don't want the pgd on the pgd_list and cannot use pgd_alloc() for the
+ * allocation.
*/
int __init efi_alloc_page_tables(void)
{
@@ -208,7 +212,7 @@ int __init efi_alloc_page_tables(void)
return 0;
gfp_mask = GFP_KERNEL | __GFP_ZERO;
- efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
+ efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
if (!efi_pgd)
return -ENOMEM;
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 8a99a2e96537..5b513ccffde4 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -592,7 +592,18 @@ static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff,
/*
* Update the first page pointer to skip over the CSH header.
*/
- cap_info->pages[0] += csh->headersize;
+ cap_info->phys[0] += csh->headersize;
+
+ /*
+ * cap_info->capsule should point at a virtual mapping of the entire
+ * capsule, starting at the capsule header. Our image has the Quark
+ * security header prepended, so we cannot rely on the default vmap()
+ * mapping created by the generic capsule code.
+ * Given that the Quark firmware does not appear to care about the
+ * virtual mapping, let's just point cap_info->capsule at our copy
+ * of the capsule header.
+ */
+ cap_info->capsule = &cap_info->header;
return 1;
}
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
index dc036e511f48..5a0483e7bf66 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
@@ -60,7 +60,7 @@ static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata)
return 0;
}
-static const struct bt_sfi_data tng_bt_sfi_data __initdata = {
+static struct bt_sfi_data tng_bt_sfi_data __initdata = {
.setup = tng_bt_sfi_setup,
};
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 86676cec99a1..2c67bae6bb53 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -194,7 +194,7 @@ void __init x86_intel_mid_early_setup(void)
x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
- x86_init.pci.init = intel_mid_pci_init;
+ x86_init.pci.arch_init = intel_mid_pci_init;
x86_init.pci.fixup_irqs = x86_init_noop;
legacy_pic = &null_legacy_pic;
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 19b43e3a9f0f..7be1e1fe9ae3 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -96,8 +96,7 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table)
pentry->freq_hz, pentry->irq);
mp_irq.type = MP_INTSRC;
mp_irq.irqtype = mp_INT;
- /* triggering mode edge bit 2-3, active high polarity bit 0-1 */
- mp_irq.irqflag = 5;
+ mp_irq.irqflag = MP_IRQTRIG_EDGE | MP_IRQPOL_ACTIVE_HIGH;
mp_irq.srcbus = MP_BUS_ISA;
mp_irq.srcbusirq = pentry->irq; /* IRQ */
mp_irq.dstapic = MP_APIC_ALL;
@@ -168,7 +167,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
totallen, (u32)pentry->phys_addr, pentry->irq);
mp_irq.type = MP_INTSRC;
mp_irq.irqtype = mp_INT;
- mp_irq.irqflag = 0xf; /* level trigger and active low */
+ mp_irq.irqflag = MP_IRQTRIG_LEVEL | MP_IRQPOL_ACTIVE_LOW;
mp_irq.srcbus = MP_BUS_ISA;
mp_irq.srcbusirq = pentry->irq; /* IRQ */
mp_irq.dstapic = MP_APIC_ALL;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index f44c0bc95aa2..c2e9285d1bf1 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp,
local_flush_tlb();
stat->d_alltlb++;
} else {
- __flush_tlb_one(msg->address);
+ __flush_tlb_single(msg->address);
stat->d_onetlb++;
}
stat->d_requestee++;
@@ -1751,7 +1751,8 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
uv1 = 1;
/* the 14-bit pnode */
- write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));
+ write_mmr_descriptor_base(pnode,
+ (n << UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT | m));
/*
* Initializing all 8 (ITEMS_PER_DESC) descriptors for each
* cpu even though we only use the first one; one descriptor can
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 5f6fd860820a..e4cb9f4cde8a 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -128,7 +128,7 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
* on the specified blade to allow the sending of MSIs to the specified CPU.
*/
static int uv_domain_activate(struct irq_domain *domain,
- struct irq_data *irq_data, bool early)
+ struct irq_data *irq_data, bool reserve)
{
uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
return 0;
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index c34bd8233f7c..5f64f30873e2 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -905,7 +905,7 @@ static inline void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
/*
* UV NMI handler
*/
-int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
+static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
{
struct uv_hub_nmi_s *hub_nmi = uv_hub_nmi;
int cpu = smp_processor_id();
@@ -1013,7 +1013,7 @@ void uv_nmi_init(void)
}
/* Setup HUB NMI info */
-void __init uv_nmi_setup_common(bool hubbed)
+static void __init uv_nmi_setup_common(bool hubbed)
{
int size = sizeof(void *) * (1 << NODES_SHIFT);
int cpu;
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 84fcfde53f8f..a7d966964c6f 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -82,12 +82,8 @@ static void __save_processor_state(struct saved_context *ctxt)
/*
* descriptor tables
*/
-#ifdef CONFIG_X86_32
store_idt(&ctxt->idt);
-#else
-/* CONFIG_X86_64 */
- store_idt((struct desc_ptr *)&ctxt->idt_limit);
-#endif
+
/*
* We save it here, but restore it only in the hibernate case.
* For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit
@@ -103,22 +99,18 @@ static void __save_processor_state(struct saved_context *ctxt)
/*
* segment registers
*/
-#ifdef CONFIG_X86_32
- savesegment(es, ctxt->es);
- savesegment(fs, ctxt->fs);
+#ifdef CONFIG_X86_32_LAZY_GS
savesegment(gs, ctxt->gs);
- savesegment(ss, ctxt->ss);
-#else
-/* CONFIG_X86_64 */
- asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
- asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
- asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
- asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
- asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
+#endif
+#ifdef CONFIG_X86_64
+ savesegment(gs, ctxt->gs);
+ savesegment(fs, ctxt->fs);
+ savesegment(ds, ctxt->ds);
+ savesegment(es, ctxt->es);
rdmsrl(MSR_FS_BASE, ctxt->fs_base);
- rdmsrl(MSR_GS_BASE, ctxt->gs_base);
- rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+ rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+ rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
mtrr_save_fixed_ranges(NULL);
rdmsrl(MSR_EFER, ctxt->efer);
@@ -160,17 +152,19 @@ static void do_fpu_end(void)
static void fix_processor_context(void)
{
int cpu = smp_processor_id();
- struct tss_struct *t = &per_cpu(cpu_tss, cpu);
#ifdef CONFIG_X86_64
struct desc_struct *desc = get_cpu_gdt_rw(cpu);
tss_desc tss;
#endif
- set_tss_desc(cpu, t); /*
- * This just modifies memory; should not be
- * necessary. But... This is necessary, because
- * 386 hardware has concept of busy TSS or some
- * similar stupidity.
- */
+
+ /*
+ * We need to reload TR, which requires that we change the
+ * GDT entry to indicate "available" first.
+ *
+ * XXX: This could probably all be replaced by a call to
+ * force_reload_TR().
+ */
+ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
#ifdef CONFIG_X86_64
memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc));
@@ -178,6 +172,9 @@ static void fix_processor_context(void)
write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS);
syscall_init(); /* This sets MSR_*STAR and related */
+#else
+ if (boot_cpu_has(X86_FEATURE_SEP))
+ enable_sep_cpu();
#endif
load_TR_desc(); /* This does ltr */
load_mm_ldt(current->active_mm); /* This does lldt */
@@ -190,9 +187,12 @@ static void fix_processor_context(void)
}
/**
- * __restore_processor_state - restore the contents of CPU registers saved
- * by __save_processor_state()
- * @ctxt - structure to load the registers contents from
+ * __restore_processor_state - restore the contents of CPU registers saved
+ * by __save_processor_state()
+ * @ctxt - structure to load the registers contents from
+ *
+ * The asm code that gets us here will have restored a usable GDT, although
+ * it will be pointing to the wrong alias.
*/
static void notrace __restore_processor_state(struct saved_context *ctxt)
{
@@ -215,46 +215,52 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
write_cr2(ctxt->cr2);
write_cr0(ctxt->cr0);
+ /* Restore the IDT. */
+ load_idt(&ctxt->idt);
+
/*
- * now restore the descriptor tables to their proper values
- * ltr is done i fix_processor_context().
+ * Just in case the asm code got us here with the SS, DS, or ES
+ * out of sync with the GDT, update them.
*/
-#ifdef CONFIG_X86_32
- load_idt(&ctxt->idt);
+ loadsegment(ss, __KERNEL_DS);
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+
+ /*
+ * Restore percpu access. Percpu access can happen in exception
+ * handlers or in complicated helpers like load_gs_index().
+ */
+#ifdef CONFIG_X86_64
+ wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
#else
-/* CONFIG_X86_64 */
- load_idt((const struct desc_ptr *)&ctxt->idt_limit);
+ loadsegment(fs, __KERNEL_PERCPU);
+ loadsegment(gs, __KERNEL_STACK_CANARY);
#endif
+ /* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */
+ fix_processor_context();
+
/*
- * segment registers
+ * Now that we have descriptor tables fully restored and working
+ * exception handling, restore the usermode segments.
*/
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_64
+ loadsegment(ds, ctxt->es);
loadsegment(es, ctxt->es);
loadsegment(fs, ctxt->fs);
- loadsegment(gs, ctxt->gs);
- loadsegment(ss, ctxt->ss);
+ load_gs_index(ctxt->gs);
/*
- * sysenter MSRs
+ * Restore FSBASE and GSBASE after restoring the selectors, since
+ * restoring the selectors clobbers the bases. Keep in mind
+ * that MSR_KERNEL_GS_BASE is horribly misnamed.
*/
- if (boot_cpu_has(X86_FEATURE_SEP))
- enable_sep_cpu();
-#else
-/* CONFIG_X86_64 */
- asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
- asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
- asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
- load_gs_index(ctxt->gs);
- asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
-
wrmsrl(MSR_FS_BASE, ctxt->fs_base);
- wrmsrl(MSR_GS_BASE, ctxt->gs_base);
- wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+ wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
+#elif defined(CONFIG_X86_32_LAZY_GS)
+ loadsegment(gs, ctxt->gs);
#endif
- fix_processor_context();
-
do_fpu_end();
tsc_verify_tsc_adjust(true);
x86_platform.restore_sched_clock_state();
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index 972b8e8d939c..09af7ff53044 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -13,28 +13,28 @@ else
posttest_64bit = -n
endif
-distill_awk = $(srctree)/arch/x86/tools/distill.awk
+reformatter = $(srctree)/arch/x86/tools/objdump_reformat.awk
chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk
quiet_cmd_posttest = TEST $@
- cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(distill_awk) | $(obj)/test_get_len $(posttest_64bit) $(posttest_verbose)
+ cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(reformatter) | $(obj)/insn_decoder_test $(posttest_64bit) $(posttest_verbose)
quiet_cmd_sanitytest = TEST $@
cmd_sanitytest = $(obj)/insn_sanity $(posttest_64bit) -m 1000000
-posttest: $(obj)/test_get_len vmlinux $(obj)/insn_sanity
+posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity
$(call cmd,posttest)
$(call cmd,sanitytest)
-hostprogs-y += test_get_len insn_sanity
+hostprogs-y += insn_decoder_test insn_sanity
# -I needed for generated C source and C source which in the kernel tree.
-HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
+HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
# Dependencies are also needed.
-$(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_decoder_test.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
$(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/insn_decoder_test.c
index ecf31e0358c8..a3b4fd954931 100644
--- a/arch/x86/tools/test_get_len.c
+++ b/arch/x86/tools/insn_decoder_test.c
@@ -9,10 +9,6 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
* Copyright (C) IBM Corporation, 2009
*/
@@ -21,6 +17,7 @@
#include <string.h>
#include <assert.h>
#include <unistd.h>
+#include <stdarg.h>
#define unlikely(cond) (cond)
@@ -33,7 +30,7 @@
* particular. See if insn_get_length() and the disassembler agree
* on the length of each instruction in an elf disassembly.
*
- * Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
+ * Usage: objdump -d a.out | awk -f objdump_reformat.awk | ./insn_decoder_test
*/
const char *prog;
@@ -42,8 +39,8 @@ static int x86_64;
static void usage(void)
{
- fprintf(stderr, "Usage: objdump -d a.out | awk -f distill.awk |"
- " %s [-y|-n] [-v]\n", prog);
+ fprintf(stderr, "Usage: objdump -d a.out | awk -f objdump_reformat.awk"
+ " | %s [-y|-n] [-v]\n", prog);
fprintf(stderr, "\t-y 64bit mode\n");
fprintf(stderr, "\t-n 32bit mode\n");
fprintf(stderr, "\t-v verbose mode\n");
@@ -52,10 +49,21 @@ static void usage(void)
static void malformed_line(const char *line, int line_nr)
{
- fprintf(stderr, "%s: malformed line %d:\n%s", prog, line_nr, line);
+ fprintf(stderr, "%s: error: malformed line %d:\n%s",
+ prog, line_nr, line);
exit(3);
}
+static void pr_warn(const char *fmt, ...)
+{
+ va_list ap;
+
+ fprintf(stderr, "%s: warning: ", prog);
+ va_start(ap, fmt);
+ vfprintf(stderr, fmt, ap);
+ va_end(ap);
+}
+
static void dump_field(FILE *fp, const char *name, const char *indent,
struct insn_field *field)
{
@@ -153,21 +161,20 @@ int main(int argc, char **argv)
insn_get_length(&insn);
if (insn.length != nb) {
warnings++;
- fprintf(stderr, "Warning: %s found difference at %s\n",
- prog, sym);
- fprintf(stderr, "Warning: %s", line);
- fprintf(stderr, "Warning: objdump says %d bytes, but "
- "insn_get_length() says %d\n", nb,
- insn.length);
+ pr_warn("Found an x86 instruction decoder bug, "
+ "please report this.\n", sym);
+ pr_warn("%s", line);
+ pr_warn("objdump says %d bytes, but insn_get_length() "
+ "says %d\n", nb, insn.length);
if (verbose)
dump_insn(stderr, &insn);
}
}
if (warnings)
- fprintf(stderr, "Warning: decoded and checked %d"
- " instructions with %d warnings\n", insns, warnings);
+ pr_warn("Decoded and checked %d instructions with %d "
+ "failures\n", insns, warnings);
else
- fprintf(stdout, "Success: decoded and checked %d"
- " instructions\n", insns);
+ fprintf(stdout, "%s: success: Decoded and checked %d"
+ " instructions\n", prog, insns);
return 0;
}
diff --git a/arch/x86/tools/distill.awk b/arch/x86/tools/objdump_reformat.awk
index e0edeccc1429..f418c91b71f0 100644
--- a/arch/x86/tools/distill.awk
+++ b/arch/x86/tools/objdump_reformat.awk
@@ -1,7 +1,7 @@
#!/bin/awk -f
# SPDX-License-Identifier: GPL-2.0
-# Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
-# Distills the disassembly as follows:
+# Usage: objdump -d a.out | awk -f objdump_reformat.awk | ./insn_decoder_test
+# Reformats the disassembly as follows:
# - Removes all lines except the disassembled instructions.
# - For instructions that exceed 1 line (7 bytes), crams all the hex bytes
# into a single line.
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 6b830d4cb4c8..de58533d3664 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -57,7 +57,7 @@ static u32 xen_apic_read(u32 reg)
return 0;
if (reg == APIC_LVR)
- return 0x10;
+ return 0x14;
#ifdef CONFIG_X86_32
if (reg == APIC_LDR)
return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d669e9d89001..c9081c6671f0 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1,8 +1,12 @@
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+#include <linux/bootmem.h>
+#endif
#include <linux/cpu.h>
#include <linux/kexec.h>
#include <xen/features.h>
#include <xen/page.h>
+#include <xen/interface/memory.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
@@ -331,3 +335,80 @@ void xen_arch_unregister_cpu(int num)
}
EXPORT_SYMBOL(xen_arch_unregister_cpu);
#endif
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+void __init arch_xen_balloon_init(struct resource *hostmem_resource)
+{
+ struct xen_memory_map memmap;
+ int rc;
+ unsigned int i, last_guest_ram;
+ phys_addr_t max_addr = PFN_PHYS(max_pfn);
+ struct e820_table *xen_e820_table;
+ const struct e820_entry *entry;
+ struct resource *res;
+
+ if (!xen_initial_domain())
+ return;
+
+ xen_e820_table = kmalloc(sizeof(*xen_e820_table), GFP_KERNEL);
+ if (!xen_e820_table)
+ return;
+
+ memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries);
+ set_xen_guest_handle(memmap.buffer, xen_e820_table->entries);
+ rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap);
+ if (rc) {
+ pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc);
+ goto out;
+ }
+
+ last_guest_ram = 0;
+ for (i = 0; i < memmap.nr_entries; i++) {
+ if (xen_e820_table->entries[i].addr >= max_addr)
+ break;
+ if (xen_e820_table->entries[i].type == E820_TYPE_RAM)
+ last_guest_ram = i;
+ }
+
+ entry = &xen_e820_table->entries[last_guest_ram];
+ if (max_addr >= entry->addr + entry->size)
+ goto out; /* No unallocated host RAM. */
+
+ hostmem_resource->start = max_addr;
+ hostmem_resource->end = entry->addr + entry->size;
+
+ /*
+ * Mark non-RAM regions between the end of dom0 RAM and end of host RAM
+ * as unavailable. The rest of that region can be used for hotplug-based
+ * ballooning.
+ */
+ for (; i < memmap.nr_entries; i++) {
+ entry = &xen_e820_table->entries[i];
+
+ if (entry->type == E820_TYPE_RAM)
+ continue;
+
+ if (entry->addr >= hostmem_resource->end)
+ break;
+
+ res = kzalloc(sizeof(*res), GFP_KERNEL);
+ if (!res)
+ goto out;
+
+ res->name = "Unavailable host RAM";
+ res->start = entry->addr;
+ res->end = (entry->addr + entry->size < hostmem_resource->end) ?
+ entry->addr + entry->size : hostmem_resource->end;
+ rc = insert_resource(hostmem_resource, res);
+ if (rc) {
+ pr_warn("%s: Can't insert [%llx - %llx) (%d)\n",
+ __func__, res->start, res->end, rc);
+ kfree(res);
+ goto out;
+ }
+ }
+
+ out:
+ kfree(xen_e820_table);
+}
+#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5b2b3f3f6531..c047f42552e1 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -88,6 +88,8 @@
#include "multicalls.h"
#include "pmu.h"
+#include "../kernel/cpu/cpu.h" /* get_cpu_cap() */
+
void *xen_initial_gdt;
static int xen_cpu_up_prepare_pv(unsigned int cpu);
@@ -622,7 +624,7 @@ static struct trap_array_entry trap_array[] = {
{ simd_coprocessor_error, xen_simd_coprocessor_error, false },
};
-static bool get_trap_addr(void **addr, unsigned int ist)
+static bool __ref get_trap_addr(void **addr, unsigned int ist)
{
unsigned int nr;
bool ist_okay = false;
@@ -644,6 +646,14 @@ static bool get_trap_addr(void **addr, unsigned int ist)
}
}
+ if (nr == ARRAY_SIZE(trap_array) &&
+ *addr >= (void *)early_idt_handler_array[0] &&
+ *addr < (void *)early_idt_handler_array[NUM_EXCEPTION_VECTORS]) {
+ nr = (*addr - (void *)early_idt_handler_array[0]) /
+ EARLY_IDT_HANDLER_SIZE;
+ *addr = (void *)xen_early_idt_handler_array[nr];
+ }
+
if (WARN_ON(ist != 0 && !ist_okay))
return false;
@@ -818,7 +828,7 @@ static void xen_load_sp0(unsigned long sp0)
mcs = xen_mc_entry(0);
MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
xen_mc_issue(PARAVIRT_LAZY_CPU);
- this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+ this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
}
void xen_set_iopl_mask(unsigned mask)
@@ -1250,6 +1260,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
/* Work out if we support NX */
+ get_cpu_cap(&boot_cpu_data);
x86_configure_nx();
/* Get mfn list */
@@ -1262,6 +1273,21 @@ asmlinkage __visible void __init xen_start_kernel(void)
xen_setup_gdt(0);
xen_init_irq_ops();
+
+ /* Let's presume PV guests always boot on vCPU with id 0. */
+ per_cpu(xen_vcpu_id, 0) = 0;
+
+ /*
+ * Setup xen_vcpu early because idt_setup_early_handler needs it for
+ * local_irq_disable(), irqs_disabled().
+ *
+ * Don't do the full vcpu_info placement stuff until we have
+ * the cpu_possible_mask and a non-dummy shared_info.
+ */
+ xen_vcpu_info_reset(0);
+
+ idt_setup_early_handler();
+
xen_init_capabilities();
#ifdef CONFIG_X86_LOCAL_APIC
@@ -1295,18 +1321,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
*/
acpi_numa = -1;
#endif
- /* Let's presume PV guests always boot on vCPU with id 0. */
- per_cpu(xen_vcpu_id, 0) = 0;
-
- /*
- * Setup xen_vcpu early because start_kernel needs it for
- * local_irq_disable(), irqs_disabled().
- *
- * Don't do the full vcpu_info placement stuff until we have
- * the cpu_possible_mask and a non-dummy shared_info.
- */
- xen_vcpu_info_reset(0);
-
WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
local_irq_disable();
diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c
index 2cfcfe4f6b2a..dd2ad82eee80 100644
--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -75,6 +75,6 @@ void __init xen_hvm_init_mmu_ops(void)
if (is_pagetable_dying_supported())
pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
#ifdef CONFIG_PROC_VMCORE
- register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
+ WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram));
#endif
}
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index fc048ec686e7..d85076223a69 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1325,20 +1325,18 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
{
struct {
struct mmuext_op op;
-#ifdef CONFIG_SMP
- DECLARE_BITMAP(mask, num_processors);
-#else
DECLARE_BITMAP(mask, NR_CPUS);
-#endif
} *args;
struct multicall_space mcs;
+ const size_t mc_entry_size = sizeof(args->op) +
+ sizeof(args->mask[0]) * BITS_TO_LONGS(num_possible_cpus());
trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end);
if (cpumask_empty(cpus))
return; /* nothing to do */
- mcs = xen_mc_entry(sizeof(*args));
+ mcs = xen_mc_entry(mc_entry_size);
args = mcs.args;
args->op.arg2.vcpumask = to_cpumask(args->mask);
@@ -1902,6 +1900,18 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
/* Graft it onto L4[511][510] */
copy_page(level2_kernel_pgt, l2);
+ /*
+ * Zap execute permission from the ident map. Due to the sharing of
+ * L1 entries we need to do this in the L2.
+ */
+ if (__supported_pte_mask & _PAGE_NX) {
+ for (i = 0; i < PTRS_PER_PMD; ++i) {
+ if (pmd_none(level2_ident_pgt[i]))
+ continue;
+ level2_ident_pgt[i] = pmd_set_flags(level2_ident_pgt[i], _PAGE_NX);
+ }
+ }
+
/* Copy the initial P->M table mappings if necessary. */
i = pgd_index(xen_start_info->mfn_list);
if (i && i < pgd_index(__START_KERNEL_map))
@@ -2261,7 +2271,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
switch (idx) {
case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
- case FIX_RO_IDT:
#ifdef CONFIG_X86_32
case FIX_WP_TEST:
# ifdef CONFIG_HIGHMEM
@@ -2272,7 +2281,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
#endif
case FIX_TEXT_POKE0:
case FIX_TEXT_POKE1:
- case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END:
/* All local page mappings */
pte = pfn_pte(phys, prot);
break;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index c114ca767b3b..6e0d2086eacb 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -808,7 +808,6 @@ char * __init xen_memory_setup(void)
addr = xen_e820_table.entries[0].addr;
size = xen_e820_table.entries[0].size;
while (i < xen_e820_table.nr_entries) {
- bool discard = false;
chunk_size = size;
type = xen_e820_table.entries[i].type;
@@ -824,11 +823,10 @@ char * __init xen_memory_setup(void)
xen_add_extra_mem(pfn_s, n_pfns);
xen_max_p2m_pfn = pfn_s + n_pfns;
} else
- discard = true;
+ type = E820_TYPE_UNUSABLE;
}
- if (!discard)
- xen_align_and_add_e820_region(addr, chunk_size, type);
+ xen_align_and_add_e820_region(addr, chunk_size, type);
addr += chunk_size;
size -= chunk_size;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 02f3445a2b5f..cd97a62394e7 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -23,8 +23,6 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
static DEFINE_PER_CPU(char *, irq_name);
static bool xen_pvspin = true;
-#include <asm/qspinlock.h>
-
static void xen_qlock_kick(int cpu)
{
int irq = per_cpu(lock_kicker_irq, cpu);
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 8a10c9a9e2b5..417b339e5c8e 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -15,6 +15,7 @@
#include <xen/interface/xen.h>
+#include <linux/init.h>
#include <linux/linkage.h>
.macro xen_pv_trap name
@@ -54,6 +55,19 @@ xen_pv_trap entry_INT80_compat
#endif
xen_pv_trap hypervisor_callback
+ __INIT
+ENTRY(xen_early_idt_handler_array)
+ i = 0
+ .rept NUM_EXCEPTION_VECTORS
+ pop %rcx
+ pop %r11
+ jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
+ i = i + 1
+ .fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
+ .endr
+END(xen_early_idt_handler_array)
+ __FINIT
+
hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
/*
* Xen64 iret frame:
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 75011b80660f..3b34745d0a52 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -72,7 +72,7 @@ u64 xen_clocksource_read(void);
void xen_setup_cpu_clockevents(void);
void xen_save_time_memory_area(void);
void xen_restore_time_memory_area(void);
-void __init xen_init_time_ops(void);
+void __ref xen_init_time_ops(void);
void __init xen_hvm_init_time_ops(void);
irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 8bc52f749f20..c921e8bccdc8 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -15,6 +15,9 @@ config XTENSA
select GENERIC_IRQ_SHOW
select GENERIC_PCI_IOMAP
select GENERIC_SCHED_CLOCK
+ select GENERIC_STRNCPY_FROM_USER if KASAN
+ select HAVE_ARCH_KASAN if MMU
+ select HAVE_CC_STACKPROTECTOR
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
@@ -79,6 +82,10 @@ config VARIANT_IRQ_SWITCH
config HAVE_XTENSA_GPIO32
def_bool n
+config KASAN_SHADOW_OFFSET
+ hex
+ default 0x6e400000
+
menu "Processor type and features"
choice
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 7ee02fe4a63d..3a934b72a272 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -42,10 +42,11 @@ export PLATFORM
# temporarily until string.h is fixed
KBUILD_CFLAGS += -ffreestanding -D__linux__
-
-KBUILD_CFLAGS += -pipe -mlongcalls
-
+KBUILD_CFLAGS += -pipe -mlongcalls -mtext-section-literals
KBUILD_CFLAGS += $(call cc-option,-mforce-no-pic,)
+KBUILD_CFLAGS += $(call cc-option,-mno-serialize-volatile,)
+
+KBUILD_AFLAGS += -mlongcalls -mtext-section-literals
ifneq ($(CONFIG_LD_NO_RELAX),)
LDFLAGS := --no-relax
diff --git a/arch/xtensa/boot/boot-redboot/bootstrap.S b/arch/xtensa/boot/boot-redboot/bootstrap.S
index bf7fabe6310d..bbf3b4b080cd 100644
--- a/arch/xtensa/boot/boot-redboot/bootstrap.S
+++ b/arch/xtensa/boot/boot-redboot/bootstrap.S
@@ -42,6 +42,7 @@ __start_a0:
.align 4
.section .text, "ax"
+ .literal_position
.begin literal_prefix .text
/* put literals in here! */
diff --git a/arch/xtensa/boot/lib/Makefile b/arch/xtensa/boot/lib/Makefile
index d2a7f48564a4..355127faade1 100644
--- a/arch/xtensa/boot/lib/Makefile
+++ b/arch/xtensa/boot/lib/Makefile
@@ -15,6 +15,12 @@ CFLAGS_REMOVE_inftrees.o = -pg
CFLAGS_REMOVE_inffast.o = -pg
endif
+KASAN_SANITIZE := n
+
+CFLAGS_REMOVE_inflate.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_zmem.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_inftrees.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_inffast.o += -fstack-protector -fstack-protector-strong
quiet_cmd_copy_zlib = COPY $@
cmd_copy_zlib = cat $< > $@
diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig
index 8d16925765cb..2bf964df37ba 100644
--- a/arch/xtensa/configs/audio_kc705_defconfig
+++ b/arch/xtensa/configs/audio_kc705_defconfig
@@ -1,7 +1,6 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig
index f2d3094aa1d1..3221b7053fa3 100644
--- a/arch/xtensa/configs/cadence_csp_defconfig
+++ b/arch/xtensa/configs/cadence_csp_defconfig
@@ -1,7 +1,6 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_USELIB=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig
index 744adeaf2945..985fa8546e4e 100644
--- a/arch/xtensa/configs/generic_kc705_defconfig
+++ b/arch/xtensa/configs/generic_kc705_defconfig
@@ -1,7 +1,6 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig
index 78c2529d0459..624f9b3a3878 100644
--- a/arch/xtensa/configs/nommu_kc705_defconfig
+++ b/arch/xtensa/configs/nommu_kc705_defconfig
@@ -1,7 +1,6 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 14e3ca353ac8..11fed6c06a7c 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -1,7 +1,6 @@
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_FHANDLE=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/include/asm/asmmacro.h b/arch/xtensa/include/asm/asmmacro.h
index 746dcc8b5abc..7f2ae5872151 100644
--- a/arch/xtensa/include/asm/asmmacro.h
+++ b/arch/xtensa/include/asm/asmmacro.h
@@ -150,5 +150,45 @@
__endl \ar \as
.endm
+/* Load or store instructions that may cause exceptions use the EX macro. */
+
+#define EX(handler) \
+ .section __ex_table, "a"; \
+ .word 97f, handler; \
+ .previous \
+97:
+
+
+/*
+ * Extract unaligned word that is split between two registers w0 and w1
+ * into r regardless of machine endianness. SAR must be loaded with the
+ * starting bit of the word (see __ssa8).
+ */
+
+ .macro __src_b r, w0, w1
+#ifdef __XTENSA_EB__
+ src \r, \w0, \w1
+#else
+ src \r, \w1, \w0
+#endif
+ .endm
+
+/*
+ * Load 2 lowest address bits of r into SAR for __src_b to extract unaligned
+ * word starting at r from two registers loaded from consecutive aligned
+ * addresses covering r regardless of machine endianness.
+ *
+ * r 0 1 2 3
+ * LE SAR 0 8 16 24
+ * BE SAR 32 24 16 8
+ */
+
+ .macro __ssa8 r
+#ifdef __XTENSA_EB__
+ ssa8b \r
+#else
+ ssa8l \r
+#endif
+ .endm
#endif /* _XTENSA_ASMMACRO_H */
diff --git a/arch/xtensa/include/asm/current.h b/arch/xtensa/include/asm/current.h
index 47e46dcf5d49..5d98a7ad4251 100644
--- a/arch/xtensa/include/asm/current.h
+++ b/arch/xtensa/include/asm/current.h
@@ -11,6 +11,8 @@
#ifndef _XTENSA_CURRENT_H
#define _XTENSA_CURRENT_H
+#include <asm/thread_info.h>
+
#ifndef __ASSEMBLY__
#include <linux/thread_info.h>
@@ -26,8 +28,6 @@ static inline struct task_struct *get_current(void)
#else
-#define CURRENT_SHIFT 13
-
#define GET_CURRENT(reg,sp) \
GET_THREAD_INFO(reg,sp); \
l32i reg, reg, TI_TASK \
diff --git a/arch/xtensa/include/asm/fixmap.h b/arch/xtensa/include/asm/fixmap.h
index 0d30403b6c95..7e25c1b50ac0 100644
--- a/arch/xtensa/include/asm/fixmap.h
+++ b/arch/xtensa/include/asm/fixmap.h
@@ -44,7 +44,7 @@ enum fixed_addresses {
__end_of_fixed_addresses
};
-#define FIXADDR_TOP (VMALLOC_START - PAGE_SIZE)
+#define FIXADDR_TOP (XCHAL_KSEG_CACHED_VADDR - PAGE_SIZE)
#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
#define FIXADDR_START ((FIXADDR_TOP - FIXADDR_SIZE) & PMD_MASK)
@@ -63,7 +63,7 @@ static __always_inline unsigned long fix_to_virt(const unsigned int idx)
* table.
*/
BUILD_BUG_ON(FIXADDR_START <
- XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE);
+ TLBTEMP_BASE_1 + TLBTEMP_SIZE);
BUILD_BUG_ON(idx >= __end_of_fixed_addresses);
return __fix_to_virt(idx);
}
diff --git a/arch/xtensa/include/asm/futex.h b/arch/xtensa/include/asm/futex.h
index eaaf1ebcc7a4..5bfbc1c401d4 100644
--- a/arch/xtensa/include/asm/futex.h
+++ b/arch/xtensa/include/asm/futex.h
@@ -92,7 +92,6 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
u32 oldval, u32 newval)
{
int ret = 0;
- u32 prev;
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
@@ -103,26 +102,24 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
__asm__ __volatile__ (
" # futex_atomic_cmpxchg_inatomic\n"
- "1: l32i %1, %3, 0\n"
- " mov %0, %5\n"
- " wsr %1, scompare1\n"
- "2: s32c1i %0, %3, 0\n"
- "3:\n"
+ " wsr %5, scompare1\n"
+ "1: s32c1i %1, %4, 0\n"
+ " s32i %1, %6, 0\n"
+ "2:\n"
" .section .fixup,\"ax\"\n"
" .align 4\n"
- "4: .long 3b\n"
- "5: l32r %1, 4b\n"
- " movi %0, %6\n"
+ "3: .long 2b\n"
+ "4: l32r %1, 3b\n"
+ " movi %0, %7\n"
" jx %1\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .long 1b,5b,2b,5b\n"
+ " .long 1b,4b\n"
" .previous\n"
- : "+r" (ret), "=&r" (prev), "+m" (*uaddr)
- : "r" (uaddr), "r" (oldval), "r" (newval), "I" (-EFAULT)
+ : "+r" (ret), "+r" (newval), "+m" (*uaddr), "+m" (*uval)
+ : "r" (uaddr), "r" (oldval), "r" (uval), "I" (-EFAULT)
: "memory");
- *uval = prev;
return ret;
}
diff --git a/arch/xtensa/include/asm/highmem.h b/arch/xtensa/include/asm/highmem.h
index 6e070db1022e..04e9340eac4b 100644
--- a/arch/xtensa/include/asm/highmem.h
+++ b/arch/xtensa/include/asm/highmem.h
@@ -72,7 +72,7 @@ static inline void *kmap(struct page *page)
* page table.
*/
BUILD_BUG_ON(PKMAP_BASE <
- XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE);
+ TLBTEMP_BASE_1 + TLBTEMP_SIZE);
BUG_ON(in_interrupt());
if (!PageHighMem(page))
return page_address(page);
diff --git a/arch/xtensa/include/asm/kasan.h b/arch/xtensa/include/asm/kasan.h
new file mode 100644
index 000000000000..54be80876e57
--- /dev/null
+++ b/arch/xtensa/include/asm/kasan.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_KASAN
+
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <asm/kmem_layout.h>
+
+/* Start of area covered by KASAN */
+#define KASAN_START_VADDR __XTENSA_UL_CONST(0x90000000)
+/* Start of the shadow map */
+#define KASAN_SHADOW_START (XCHAL_PAGE_TABLE_VADDR + XCHAL_PAGE_TABLE_SIZE)
+/* Size of the shadow map */
+#define KASAN_SHADOW_SIZE (-KASAN_START_VADDR >> KASAN_SHADOW_SCALE_SHIFT)
+/* Offset for mem to shadow address transformation */
+#define KASAN_SHADOW_OFFSET __XTENSA_UL_CONST(CONFIG_KASAN_SHADOW_OFFSET)
+
+void __init kasan_early_init(void);
+void __init kasan_init(void);
+
+#else
+
+static inline void kasan_early_init(void)
+{
+}
+
+static inline void kasan_init(void)
+{
+}
+
+#endif
+#endif
+#endif
diff --git a/arch/xtensa/include/asm/kmem_layout.h b/arch/xtensa/include/asm/kmem_layout.h
index 561f8729bcde..2317c835a4db 100644
--- a/arch/xtensa/include/asm/kmem_layout.h
+++ b/arch/xtensa/include/asm/kmem_layout.h
@@ -71,4 +71,11 @@
#endif
+#ifndef CONFIG_KASAN
+#define KERNEL_STACK_SHIFT 13
+#else
+#define KERNEL_STACK_SHIFT 15
+#endif
+#define KERNEL_STACK_SIZE (1 << KERNEL_STACK_SHIFT)
+
#endif
diff --git a/arch/xtensa/include/asm/linkage.h b/arch/xtensa/include/asm/linkage.h
new file mode 100644
index 000000000000..0ba9973235d9
--- /dev/null
+++ b/arch/xtensa/include/asm/linkage.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#define __ALIGN .align 4
+#define __ALIGN_STR ".align 4"
+
+#endif
diff --git a/arch/xtensa/include/asm/mmu_context.h b/arch/xtensa/include/asm/mmu_context.h
index f7e186dfc4e4..de5e6cbbafe4 100644
--- a/arch/xtensa/include/asm/mmu_context.h
+++ b/arch/xtensa/include/asm/mmu_context.h
@@ -52,6 +52,7 @@ DECLARE_PER_CPU(unsigned long, asid_cache);
#define ASID_INSERT(x) (0x03020001 | (((x) & ASID_MASK) << 8))
void init_mmu(void);
+void init_kio(void);
static inline void set_rasid_register (unsigned long val)
{
diff --git a/arch/xtensa/include/asm/nommu_context.h b/arch/xtensa/include/asm/nommu_context.h
index 2cebdbbdb633..37251b2ef871 100644
--- a/arch/xtensa/include/asm/nommu_context.h
+++ b/arch/xtensa/include/asm/nommu_context.h
@@ -3,6 +3,10 @@ static inline void init_mmu(void)
{
}
+static inline void init_kio(void)
+{
+}
+
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
}
diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h
index 4ddbfd57a7c8..5d69c11c01b8 100644
--- a/arch/xtensa/include/asm/page.h
+++ b/arch/xtensa/include/asm/page.h
@@ -36,8 +36,6 @@
#define MAX_LOW_PFN PHYS_PFN(0xfffffffful)
#endif
-#define PGTABLE_START 0x80000000
-
/*
* Cache aliasing:
*
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 30dd5b2e4ad5..38802259978f 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -12,9 +12,9 @@
#define _XTENSA_PGTABLE_H
#define __ARCH_USE_5LEVEL_HACK
-#include <asm-generic/pgtable-nopmd.h>
#include <asm/page.h>
#include <asm/kmem_layout.h>
+#include <asm-generic/pgtable-nopmd.h>
/*
* We only use two ring levels, user and kernel space.
@@ -170,6 +170,7 @@
#define PAGE_SHARED_EXEC \
__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_WRITABLE | _PAGE_HW_EXEC)
#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_HW_WRITE)
+#define PAGE_KERNEL_RO __pgprot(_PAGE_PRESENT)
#define PAGE_KERNEL_EXEC __pgprot(_PAGE_PRESENT|_PAGE_HW_WRITE|_PAGE_HW_EXEC)
#if (DCACHE_WAY_SIZE > PAGE_SIZE)
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index e2d9c5eb10bd..3a5c5918aea3 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -10,6 +10,7 @@
#ifndef _XTENSA_PTRACE_H
#define _XTENSA_PTRACE_H
+#include <asm/kmem_layout.h>
#include <uapi/asm/ptrace.h>
/*
@@ -38,20 +39,6 @@
* +-----------------------+ --------
*/
-#define KERNEL_STACK_SIZE (2 * PAGE_SIZE)
-
-/* Offsets for exception_handlers[] (3 x 64-entries x 4-byte tables). */
-
-#define EXC_TABLE_KSTK 0x004 /* Kernel Stack */
-#define EXC_TABLE_DOUBLE_SAVE 0x008 /* Double exception save area for a0 */
-#define EXC_TABLE_FIXUP 0x00c /* Fixup handler */
-#define EXC_TABLE_PARAM 0x010 /* For passing a parameter to fixup */
-#define EXC_TABLE_SYSCALL_SAVE 0x014 /* For fast syscall handler */
-#define EXC_TABLE_FAST_USER 0x100 /* Fast user exception handler */
-#define EXC_TABLE_FAST_KERNEL 0x200 /* Fast kernel exception handler */
-#define EXC_TABLE_DEFAULT 0x300 /* Default C-Handler */
-#define EXC_TABLE_SIZE 0x400
-
#ifndef __ASSEMBLY__
#include <asm/coprocessor.h>
diff --git a/arch/xtensa/include/asm/regs.h b/arch/xtensa/include/asm/regs.h
index 881a1134a4b4..477594e5817f 100644
--- a/arch/xtensa/include/asm/regs.h
+++ b/arch/xtensa/include/asm/regs.h
@@ -76,6 +76,7 @@
#define EXCCAUSE_COPROCESSOR5_DISABLED 37
#define EXCCAUSE_COPROCESSOR6_DISABLED 38
#define EXCCAUSE_COPROCESSOR7_DISABLED 39
+#define EXCCAUSE_N 64
/* PS register fields. */
diff --git a/arch/xtensa/include/asm/stackprotector.h b/arch/xtensa/include/asm/stackprotector.h
new file mode 100644
index 000000000000..e368f94fd2af
--- /dev/null
+++ b/arch/xtensa/include/asm/stackprotector.h
@@ -0,0 +1,40 @@
+/*
+ * GCC stack protector support.
+ *
+ * (This is directly adopted from the ARM implementation)
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function. The pattern is called stack canary
+ * and gcc expects it to be defined by a global variable called
+ * "__stack_chk_guard" on Xtensa. This unfortunately means that on SMP
+ * we cannot have a different canary value per task.
+ */
+
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+ unsigned long canary;
+
+ /* Try to get a semi random initial value. */
+ get_random_bytes(&canary, sizeof(canary));
+ canary ^= LINUX_VERSION_CODE;
+
+ current->stack_canary = canary;
+ __stack_chk_guard = current->stack_canary;
+}
+
+#endif /* _ASM_STACKPROTECTOR_H */
diff --git a/arch/xtensa/include/asm/string.h b/arch/xtensa/include/asm/string.h
index 8d5d9dfadb09..89b51a0c752f 100644
--- a/arch/xtensa/include/asm/string.h
+++ b/arch/xtensa/include/asm/string.h
@@ -53,7 +53,7 @@ static inline char *strncpy(char *__dest, const char *__src, size_t __n)
"bne %1, %5, 1b\n"
"2:"
: "=r" (__dest), "=r" (__src), "=&r" (__dummy)
- : "0" (__dest), "1" (__src), "r" (__src+__n)
+ : "0" (__dest), "1" (__src), "r" ((uintptr_t)__src+__n)
: "memory");
return __xdest;
@@ -101,21 +101,40 @@ static inline int strncmp(const char *__cs, const char *__ct, size_t __n)
"2:\n\t"
"sub %2, %2, %3"
: "=r" (__cs), "=r" (__ct), "=&r" (__res), "=&r" (__dummy)
- : "0" (__cs), "1" (__ct), "r" (__cs+__n));
+ : "0" (__cs), "1" (__ct), "r" ((uintptr_t)__cs+__n));
return __res;
}
#define __HAVE_ARCH_MEMSET
extern void *memset(void *__s, int __c, size_t __count);
+extern void *__memset(void *__s, int __c, size_t __count);
#define __HAVE_ARCH_MEMCPY
extern void *memcpy(void *__to, __const__ void *__from, size_t __n);
+extern void *__memcpy(void *__to, __const__ void *__from, size_t __n);
#define __HAVE_ARCH_MEMMOVE
extern void *memmove(void *__dest, __const__ void *__src, size_t __n);
+extern void *__memmove(void *__dest, __const__ void *__src, size_t __n);
/* Don't build bcopy at all ... */
#define __HAVE_ARCH_BCOPY
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+#endif
+
#endif /* _XTENSA_STRING_H */
diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h
index 7be2400f745a..2bd19ae61e47 100644
--- a/arch/xtensa/include/asm/thread_info.h
+++ b/arch/xtensa/include/asm/thread_info.h
@@ -11,7 +11,9 @@
#ifndef _XTENSA_THREAD_INFO_H
#define _XTENSA_THREAD_INFO_H
-#ifdef __KERNEL__
+#include <asm/kmem_layout.h>
+
+#define CURRENT_SHIFT KERNEL_STACK_SHIFT
#ifndef __ASSEMBLY__
# include <asm/processor.h>
@@ -77,14 +79,11 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
/* how to get the thread information struct from C */
static inline struct thread_info *current_thread_info(void)
{
struct thread_info *ti;
- __asm__("extui %0,a1,0,13\n\t"
+ __asm__("extui %0, a1, 0, "__stringify(CURRENT_SHIFT)"\n\t"
"xor %0, a1, %0" : "=&r" (ti) : );
return ti;
}
@@ -93,7 +92,7 @@ static inline struct thread_info *current_thread_info(void)
/* how to get the thread information struct from ASM */
#define GET_THREAD_INFO(reg,sp) \
- extui reg, sp, 0, 13; \
+ extui reg, sp, 0, CURRENT_SHIFT; \
xor reg, sp, reg
#endif
@@ -130,8 +129,7 @@ static inline struct thread_info *current_thread_info(void)
*/
#define TS_USEDFPU 0x0001 /* FPU was used by this task this quantum (SMP) */
-#define THREAD_SIZE 8192 //(2*PAGE_SIZE)
-#define THREAD_SIZE_ORDER 1
+#define THREAD_SIZE KERNEL_STACK_SIZE
+#define THREAD_SIZE_ORDER (KERNEL_STACK_SHIFT - PAGE_SHIFT)
-#endif /* __KERNEL__ */
#endif /* _XTENSA_THREAD_INFO */
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 2e69aa4b843f..f5cd7a7e65e0 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -13,12 +13,47 @@
#include <asm/ptrace.h>
/*
+ * Per-CPU exception handling data structure.
+ * EXCSAVE1 points to it.
+ */
+struct exc_table {
+ /* Kernel Stack */
+ void *kstk;
+ /* Double exception save area for a0 */
+ unsigned long double_save;
+ /* Fixup handler */
+ void *fixup;
+ /* For passing a parameter to fixup */
+ void *fixup_param;
+ /* For fast syscall handler */
+ unsigned long syscall_save;
+ /* Fast user exception handlers */
+ void *fast_user_handler[EXCCAUSE_N];
+ /* Fast kernel exception handlers */
+ void *fast_kernel_handler[EXCCAUSE_N];
+ /* Default C-Handlers */
+ void *default_handler[EXCCAUSE_N];
+};
+
+/*
* handler must be either of the following:
* void (*)(struct pt_regs *regs);
* void (*)(struct pt_regs *regs, unsigned long exccause);
*/
extern void * __init trap_set_handler(int cause, void *handler);
extern void do_unhandled(struct pt_regs *regs, unsigned long exccause);
+void fast_second_level_miss(void);
+
+/* Initialize minimal exc_table structure sufficient for basic paging */
+static inline void __init early_trap_init(void)
+{
+ static struct exc_table exc_table __initdata = {
+ .fast_kernel_handler[EXCCAUSE_DTLB_MISS] =
+ fast_second_level_miss,
+ };
+ __asm__ __volatile__("wsr %0, excsave1\n" : : "a" (&exc_table));
+}
+
void secondary_trap_init(void);
static inline void spill_registers(void)
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index b8f152b6aaa5..f1158b4c629c 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -44,6 +44,8 @@
#define __access_ok(addr, size) (__kernel_ok || __user_ok((addr), (size)))
#define access_ok(type, addr, size) __access_ok((unsigned long)(addr), (size))
+#define user_addr_max() (uaccess_kernel() ? ~0UL : TASK_SIZE)
+
/*
* These are the main single-value transfer routines. They
* automatically use the right size if we just have the right pointer
@@ -261,7 +263,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
static inline unsigned long
__xtensa_clear_user(void *addr, unsigned long size)
{
- if ( ! memset(addr, 0, size) )
+ if (!__memset(addr, 0, size))
return size;
return 0;
}
@@ -277,6 +279,8 @@ clear_user(void *addr, unsigned long size)
#define __clear_user __xtensa_clear_user
+#ifndef CONFIG_GENERIC_STRNCPY_FROM_USER
+
extern long __strncpy_user(char *, const char *, long);
static inline long
@@ -286,6 +290,9 @@ strncpy_from_user(char *dst, const char *src, long count)
return __strncpy_user(dst, src, count);
return -EFAULT;
}
+#else
+long strncpy_from_user(char *dst, const char *src, long count);
+#endif
/*
* Return the size of a string (including the ending 0!)
diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild
index a5bcdfb890f1..837d4dd76785 100644
--- a/arch/xtensa/include/uapi/asm/Kbuild
+++ b/arch/xtensa/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile
index bb8d55775a97..91907590d183 100644
--- a/arch/xtensa/kernel/Makefile
+++ b/arch/xtensa/kernel/Makefile
@@ -17,9 +17,6 @@ obj-$(CONFIG_XTENSA_VARIANT_HAVE_PERF_EVENTS) += perf_event.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_S32C1I_SELFTEST) += s32c1i_selftest.o
-AFLAGS_head.o += -mtext-section-literals
-AFLAGS_mxhead.o += -mtext-section-literals
-
# In the Xtensa architecture, assembly generates literals which must always
# precede the L32R instruction with a relative offset less than 256 kB.
# Therefore, the .text and .literal section must be combined in parenthesis
diff --git a/arch/xtensa/kernel/align.S b/arch/xtensa/kernel/align.S
index 890004af03a9..9301452e521e 100644
--- a/arch/xtensa/kernel/align.S
+++ b/arch/xtensa/kernel/align.S
@@ -19,6 +19,7 @@
#include <linux/linkage.h>
#include <asm/current.h>
#include <asm/asm-offsets.h>
+#include <asm/asmmacro.h>
#include <asm/processor.h>
#if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION
@@ -66,8 +67,6 @@
#define INSN_T 24
#define INSN_OP1 16
-.macro __src_b r, w0, w1; src \r, \w0, \w1; .endm
-.macro __ssa8 r; ssa8b \r; .endm
.macro __ssa8r r; ssa8l \r; .endm
.macro __sh r, s; srl \r, \s; .endm
.macro __sl r, s; sll \r, \s; .endm
@@ -81,8 +80,6 @@
#define INSN_T 4
#define INSN_OP1 12
-.macro __src_b r, w0, w1; src \r, \w1, \w0; .endm
-.macro __ssa8 r; ssa8l \r; .endm
.macro __ssa8r r; ssa8b \r; .endm
.macro __sh r, s; sll \r, \s; .endm
.macro __sl r, s; srl \r, \s; .endm
@@ -155,7 +152,7 @@
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
*/
-
+ .literal_position
ENTRY(fast_unaligned)
/* Note: We don't expect the address to be aligned on a word
diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c
index bcb5beb81177..022cf918ec20 100644
--- a/arch/xtensa/kernel/asm-offsets.c
+++ b/arch/xtensa/kernel/asm-offsets.c
@@ -76,6 +76,9 @@ int main(void)
DEFINE(TASK_PID, offsetof (struct task_struct, pid));
DEFINE(TASK_THREAD, offsetof (struct task_struct, thread));
DEFINE(TASK_THREAD_INFO, offsetof (struct task_struct, stack));
+#ifdef CONFIG_CC_STACKPROTECTOR
+ DEFINE(TASK_STACK_CANARY, offsetof(struct task_struct, stack_canary));
+#endif
DEFINE(TASK_STRUCT_SIZE, sizeof (struct task_struct));
/* offsets in thread_info struct */
@@ -129,5 +132,18 @@ int main(void)
offsetof(struct debug_table, icount_level_save));
#endif
+ /* struct exc_table */
+ DEFINE(EXC_TABLE_KSTK, offsetof(struct exc_table, kstk));
+ DEFINE(EXC_TABLE_DOUBLE_SAVE, offsetof(struct exc_table, double_save));
+ DEFINE(EXC_TABLE_FIXUP, offsetof(struct exc_table, fixup));
+ DEFINE(EXC_TABLE_PARAM, offsetof(struct exc_table, fixup_param));
+ DEFINE(EXC_TABLE_SYSCALL_SAVE,
+ offsetof(struct exc_table, syscall_save));
+ DEFINE(EXC_TABLE_FAST_USER,
+ offsetof(struct exc_table, fast_user_handler));
+ DEFINE(EXC_TABLE_FAST_KERNEL,
+ offsetof(struct exc_table, fast_kernel_handler));
+ DEFINE(EXC_TABLE_DEFAULT, offsetof(struct exc_table, default_handler));
+
return 0;
}
diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S
index 3a98503ad11a..4f8b52d575a2 100644
--- a/arch/xtensa/kernel/coprocessor.S
+++ b/arch/xtensa/kernel/coprocessor.S
@@ -212,8 +212,7 @@ ENDPROC(coprocessor_restore)
ENTRY(fast_coprocessor_double)
wsr a0, excsave1
- movi a0, unrecoverable_exception
- callx0 a0
+ call0 unrecoverable_exception
ENDPROC(fast_coprocessor_double)
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 37a239556889..5caff0744f3c 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -14,6 +14,7 @@
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
+#include <asm/asmmacro.h>
#include <asm/processor.h>
#include <asm/coprocessor.h>
#include <asm/thread_info.h>
@@ -125,6 +126,7 @@
*
* Note: _user_exception might be at an odd address. Don't use call0..call12
*/
+ .literal_position
ENTRY(user_exception)
@@ -475,8 +477,7 @@ common_exception_return:
1:
irq_save a2, a3
#ifdef CONFIG_TRACE_IRQFLAGS
- movi a4, trace_hardirqs_off
- callx4 a4
+ call4 trace_hardirqs_off
#endif
/* Jump if we are returning from kernel exceptions. */
@@ -503,24 +504,20 @@ common_exception_return:
/* Call do_signal() */
#ifdef CONFIG_TRACE_IRQFLAGS
- movi a4, trace_hardirqs_on
- callx4 a4
+ call4 trace_hardirqs_on
#endif
rsil a2, 0
- movi a4, do_notify_resume # int do_notify_resume(struct pt_regs*)
mov a6, a1
- callx4 a4
+ call4 do_notify_resume # int do_notify_resume(struct pt_regs*)
j 1b
3: /* Reschedule */
#ifdef CONFIG_TRACE_IRQFLAGS
- movi a4, trace_hardirqs_on
- callx4 a4
+ call4 trace_hardirqs_on
#endif
rsil a2, 0
- movi a4, schedule # void schedule (void)
- callx4 a4
+ call4 schedule # void schedule (void)
j 1b
#ifdef CONFIG_PREEMPT
@@ -531,8 +528,7 @@ common_exception_return:
l32i a4, a2, TI_PRE_COUNT
bnez a4, 4f
- movi a4, preempt_schedule_irq
- callx4 a4
+ call4 preempt_schedule_irq
j 1b
#endif
@@ -545,23 +541,20 @@ common_exception_return:
5:
#ifdef CONFIG_HAVE_HW_BREAKPOINT
_bbci.l a4, TIF_DB_DISABLED, 7f
- movi a4, restore_dbreak
- callx4 a4
+ call4 restore_dbreak
7:
#endif
#ifdef CONFIG_DEBUG_TLB_SANITY
l32i a4, a1, PT_DEPC
bgeui a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 4f
- movi a4, check_tlb_sanity
- callx4 a4
+ call4 check_tlb_sanity
#endif
6:
4:
#ifdef CONFIG_TRACE_IRQFLAGS
extui a4, a3, PS_INTLEVEL_SHIFT, PS_INTLEVEL_WIDTH
bgei a4, LOCKLEVEL, 1f
- movi a4, trace_hardirqs_on
- callx4 a4
+ call4 trace_hardirqs_on
1:
#endif
/* Restore optional registers. */
@@ -777,6 +770,8 @@ ENDPROC(kernel_exception)
* When we get here, a0 is trashed and saved to excsave[debuglevel]
*/
+ .literal_position
+
ENTRY(debug_exception)
rsr a0, SREG_EPS + XCHAL_DEBUGLEVEL
@@ -916,6 +911,8 @@ ENDPROC(debug_exception)
unrecoverable_text:
.ascii "Unrecoverable error in exception handler\0"
+ .literal_position
+
ENTRY(unrecoverable_exception)
movi a0, 1
@@ -933,10 +930,8 @@ ENTRY(unrecoverable_exception)
movi a0, 0
addi a1, a1, PT_REGS_OFFSET
- movi a4, panic
movi a6, unrecoverable_text
-
- callx4 a4
+ call4 panic
1: j 1b
@@ -1073,8 +1068,7 @@ ENTRY(fast_syscall_unrecoverable)
xsr a2, depc # restore a2, depc
wsr a0, excsave1
- movi a0, unrecoverable_exception
- callx0 a0
+ call0 unrecoverable_exception
ENDPROC(fast_syscall_unrecoverable)
@@ -1101,32 +1095,11 @@ ENDPROC(fast_syscall_unrecoverable)
* < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
*
* Note: we don't have to save a2; a2 holds the return value
- *
- * We use the two macros TRY and CATCH:
- *
- * TRY adds an entry to the __ex_table fixup table for the immediately
- * following instruction.
- *
- * CATCH catches any exception that occurred at one of the preceding TRY
- * statements and continues from there
- *
- * Usage TRY l32i a0, a1, 0
- * <other code>
- * done: rfe
- * CATCH <set return code>
- * j done
*/
-#ifdef CONFIG_FAST_SYSCALL_XTENSA
-
-#define TRY \
- .section __ex_table, "a"; \
- .word 66f, 67f; \
- .text; \
-66:
+ .literal_position
-#define CATCH \
-67:
+#ifdef CONFIG_FAST_SYSCALL_XTENSA
ENTRY(fast_syscall_xtensa)
@@ -1141,9 +1114,9 @@ ENTRY(fast_syscall_xtensa)
.Lswp: /* Atomic compare and swap */
-TRY l32i a0, a3, 0 # read old value
+EX(.Leac) l32i a0, a3, 0 # read old value
bne a0, a4, 1f # same as old value? jump
-TRY s32i a5, a3, 0 # different, modify value
+EX(.Leac) s32i a5, a3, 0 # different, modify value
l32i a7, a2, PT_AREG7 # restore a7
l32i a0, a2, PT_AREG0 # restore a0
movi a2, 1 # and return 1
@@ -1156,12 +1129,12 @@ TRY s32i a5, a3, 0 # different, modify value
.Lnswp: /* Atomic set, add, and exg_add. */
-TRY l32i a7, a3, 0 # orig
+EX(.Leac) l32i a7, a3, 0 # orig
addi a6, a6, -SYS_XTENSA_ATOMIC_SET
add a0, a4, a7 # + arg
moveqz a0, a4, a6 # set
addi a6, a6, SYS_XTENSA_ATOMIC_SET
-TRY s32i a0, a3, 0 # write new value
+EX(.Leac) s32i a0, a3, 0 # write new value
mov a0, a2
mov a2, a7
@@ -1169,7 +1142,6 @@ TRY s32i a0, a3, 0 # write new value
l32i a0, a0, PT_AREG0 # restore a0
rfe
-CATCH
.Leac: l32i a7, a2, PT_AREG7 # restore a7
l32i a0, a2, PT_AREG0 # restore a0
movi a2, -EFAULT
@@ -1411,14 +1383,12 @@ ENTRY(fast_syscall_spill_registers)
rsync
movi a6, SIGSEGV
- movi a4, do_exit
- callx4 a4
+ call4 do_exit
/* shouldn't return, so panic */
wsr a0, excsave1
- movi a0, unrecoverable_exception
- callx0 a0 # should not return
+ call0 unrecoverable_exception # should not return
1: j 1b
@@ -1564,8 +1534,8 @@ ENDPROC(fast_syscall_spill_registers)
ENTRY(fast_second_level_miss_double_kernel)
-1: movi a0, unrecoverable_exception
- callx0 a0 # should not return
+1:
+ call0 unrecoverable_exception # should not return
1: j 1b
ENDPROC(fast_second_level_miss_double_kernel)
@@ -1887,6 +1857,7 @@ ENDPROC(fast_store_prohibited)
* void system_call (struct pt_regs* regs, int exccause)
* a2 a3
*/
+ .literal_position
ENTRY(system_call)
@@ -1896,9 +1867,8 @@ ENTRY(system_call)
l32i a3, a2, PT_AREG2
mov a6, a2
- movi a4, do_syscall_trace_enter
s32i a3, a2, PT_SYSCALL
- callx4 a4
+ call4 do_syscall_trace_enter
mov a3, a6
/* syscall = sys_call_table[syscall_nr] */
@@ -1930,9 +1900,8 @@ ENTRY(system_call)
1: /* regs->areg[2] = return_value */
s32i a6, a2, PT_AREG2
- movi a4, do_syscall_trace_leave
mov a6, a2
- callx4 a4
+ call4 do_syscall_trace_leave
retw
ENDPROC(system_call)
@@ -2002,6 +1971,12 @@ ENTRY(_switch_to)
s32i a1, a2, THREAD_SP # save stack pointer
#endif
+#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
+ movi a6, __stack_chk_guard
+ l32i a8, a3, TASK_STACK_CANARY
+ s32i a8, a6, 0
+#endif
+
/* Disable ints while we manipulate the stack pointer. */
irq_save a14, a3
@@ -2048,12 +2023,10 @@ ENTRY(ret_from_fork)
/* void schedule_tail (struct task_struct *prev)
* Note: prev is still in a6 (return value from fake call4 frame)
*/
- movi a4, schedule_tail
- callx4 a4
+ call4 schedule_tail
- movi a4, do_syscall_trace_leave
mov a6, a1
- callx4 a4
+ call4 do_syscall_trace_leave
j common_exception_return
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index 23ce62e60435..9c4e9433e536 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -264,11 +264,8 @@ ENTRY(_startup)
/* init_arch kick-starts the linux kernel */
- movi a4, init_arch
- callx4 a4
-
- movi a4, start_kernel
- callx4 a4
+ call4 init_arch
+ call4 start_kernel
should_never_return:
j should_never_return
@@ -294,8 +291,7 @@ should_never_return:
movi a6, 0
wsr a6, excsave1
- movi a4, secondary_start_kernel
- callx4 a4
+ call4 secondary_start_kernel
j should_never_return
#endif /* CONFIG_SMP */
diff --git a/arch/xtensa/kernel/module.c b/arch/xtensa/kernel/module.c
index b715237bae61..902845ddacb7 100644
--- a/arch/xtensa/kernel/module.c
+++ b/arch/xtensa/kernel/module.c
@@ -22,8 +22,6 @@
#include <linux/kernel.h>
#include <linux/cache.h>
-#undef DEBUG_RELOCATE
-
static int
decode_calln_opcode (unsigned char *location)
{
@@ -58,10 +56,9 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
unsigned char *location;
uint32_t value;
-#ifdef DEBUG_RELOCATE
- printk("Applying relocate section %u to %u\n", relsec,
- sechdrs[relsec].sh_info);
-#endif
+ pr_debug("Applying relocate section %u to %u\n", relsec,
+ sechdrs[relsec].sh_info);
+
for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
location = (char *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ rela[i].r_offset;
@@ -87,7 +84,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
value -= ((unsigned long)location & -4) + 4;
if ((value & 3) != 0 ||
((value + (1 << 19)) >> 20) != 0) {
- printk("%s: relocation out of range, "
+ pr_err("%s: relocation out of range, "
"section %d reloc %d "
"sym '%s'\n",
mod->name, relsec, i,
@@ -111,7 +108,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
value -= (((unsigned long)location + 3) & -4);
if ((value & 3) != 0 ||
(signed int)value >> 18 != -1) {
- printk("%s: relocation out of range, "
+ pr_err("%s: relocation out of range, "
"section %d reloc %d "
"sym '%s'\n",
mod->name, relsec, i,
@@ -156,7 +153,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
case R_XTENSA_SLOT12_OP:
case R_XTENSA_SLOT13_OP:
case R_XTENSA_SLOT14_OP:
- printk("%s: unexpected FLIX relocation: %u\n",
+ pr_err("%s: unexpected FLIX relocation: %u\n",
mod->name,
ELF32_R_TYPE(rela[i].r_info));
return -ENOEXEC;
@@ -176,13 +173,13 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
case R_XTENSA_SLOT12_ALT:
case R_XTENSA_SLOT13_ALT:
case R_XTENSA_SLOT14_ALT:
- printk("%s: unexpected ALT relocation: %u\n",
+ pr_err("%s: unexpected ALT relocation: %u\n",
mod->name,
ELF32_R_TYPE(rela[i].r_info));
return -ENOEXEC;
default:
- printk("%s: unexpected relocation: %u\n",
+ pr_err("%s: unexpected relocation: %u\n",
mod->name,
ELF32_R_TYPE(rela[i].r_info));
return -ENOEXEC;
diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c
index 903963ee495d..d981f01c8d89 100644
--- a/arch/xtensa/kernel/pci.c
+++ b/arch/xtensa/kernel/pci.c
@@ -29,14 +29,6 @@
#include <asm/pci-bridge.h>
#include <asm/platform.h>
-#undef DEBUG
-
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
/* PCI Controller */
@@ -101,8 +93,8 @@ pcibios_enable_resources(struct pci_dev *dev, int mask)
for(idx=0; idx<6; idx++) {
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));
+ pr_err("PCI: Device %s not available because "
+ "of resource collisions\n", pci_name(dev));
return -EINVAL;
}
if (r->flags & IORESOURCE_IO)
@@ -113,7 +105,7 @@ pcibios_enable_resources(struct pci_dev *dev, int mask)
if (dev->resource[PCI_ROM_RESOURCE].start)
cmd |= PCI_COMMAND_MEMORY;
if (cmd != old_cmd) {
- printk("PCI: Enabling device %s (%04x -> %04x)\n",
+ pr_info("PCI: Enabling device %s (%04x -> %04x)\n",
pci_name(dev), old_cmd, cmd);
pci_write_config_word(dev, PCI_COMMAND, cmd);
}
@@ -144,8 +136,8 @@ static void __init pci_controller_apertures(struct pci_controller *pci_ctrl,
res = &pci_ctrl->io_resource;
if (!res->flags) {
if (io_offset)
- printk (KERN_ERR "I/O resource not set for host"
- " bridge %d\n", pci_ctrl->index);
+ pr_err("I/O resource not set for host bridge %d\n",
+ pci_ctrl->index);
res->start = 0;
res->end = IO_SPACE_LIMIT;
res->flags = IORESOURCE_IO;
@@ -159,8 +151,8 @@ static void __init pci_controller_apertures(struct pci_controller *pci_ctrl,
if (!res->flags) {
if (i > 0)
continue;
- printk(KERN_ERR "Memory resource not set for "
- "host bridge %d\n", pci_ctrl->index);
+ pr_err("Memory resource not set for host bridge %d\n",
+ pci_ctrl->index);
res->start = 0;
res->end = ~0U;
res->flags = IORESOURCE_MEM;
@@ -176,7 +168,7 @@ static int __init pcibios_init(void)
struct pci_bus *bus;
int next_busno = 0, ret;
- printk("PCI: Probing PCI hardware\n");
+ pr_info("PCI: Probing PCI hardware\n");
/* Scan all of the recorded PCI controllers. */
for (pci_ctrl = pci_ctrl_head; pci_ctrl; pci_ctrl = pci_ctrl->next) {
@@ -232,7 +224,7 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
for (idx=0; idx<6; idx++) {
r = &dev->resource[idx];
if (!r->start && r->end) {
- printk(KERN_ERR "PCI: Device %s not available because "
+ pr_err("PCI: Device %s not available because "
"of resource collisions\n", pci_name(dev));
return -EINVAL;
}
@@ -242,8 +234,8 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
cmd |= PCI_COMMAND_MEMORY;
}
if (cmd != old_cmd) {
- printk("PCI: Enabling device %s (%04x -> %04x)\n",
- pci_name(dev), old_cmd, cmd);
+ pr_info("PCI: Enabling device %s (%04x -> %04x)\n",
+ pci_name(dev), old_cmd, cmd);
pci_write_config_word(dev, PCI_COMMAND, cmd);
}
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index ff4f0ecb03dd..8dd0593fb2c4 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -58,6 +58,12 @@ void (*pm_power_off)(void) = NULL;
EXPORT_SYMBOL(pm_power_off);
+#ifdef CONFIG_CC_STACKPROTECTOR
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
#if XTENSA_HAVE_COPROCESSORS
void coprocessor_release_all(struct thread_info *ti)
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index e2461968efb2..c0845cb1cbb9 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -278,7 +278,6 @@ static void ptrace_hbptriggered(struct perf_event *bp,
struct pt_regs *regs)
{
int i;
- siginfo_t info;
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
if (bp->attr.bp_type & HW_BREAKPOINT_X) {
@@ -293,12 +292,7 @@ static void ptrace_hbptriggered(struct perf_event *bp,
i = (i << 1) | 1;
}
- info.si_signo = SIGTRAP;
- info.si_errno = i;
- info.si_code = TRAP_HWBKPT;
- info.si_addr = (void __user *)bkpt->address;
-
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_ptrace_errno_trap(i, (void __user *)bkpt->address);
}
static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 08175df7a69e..a931af9075f2 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -36,6 +36,7 @@
#endif
#include <asm/bootparam.h>
+#include <asm/kasan.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
@@ -156,7 +157,7 @@ static int __init parse_bootparam(const bp_tag_t* tag)
/* Boot parameters must start with a BP_TAG_FIRST tag. */
if (tag->id != BP_TAG_FIRST) {
- printk(KERN_WARNING "Invalid boot parameters!\n");
+ pr_warn("Invalid boot parameters!\n");
return 0;
}
@@ -165,15 +166,14 @@ static int __init parse_bootparam(const bp_tag_t* tag)
/* Parse all tags. */
while (tag != NULL && tag->id != BP_TAG_LAST) {
- for (t = &__tagtable_begin; t < &__tagtable_end; t++) {
+ for (t = &__tagtable_begin; t < &__tagtable_end; t++) {
if (tag->id == t->tag) {
t->parse(tag);
break;
}
}
if (t == &__tagtable_end)
- printk(KERN_WARNING "Ignoring tag "
- "0x%08x\n", tag->id);
+ pr_warn("Ignoring tag 0x%08x\n", tag->id);
tag = (bp_tag_t*)((unsigned long)(tag + 1) + tag->size);
}
@@ -208,6 +208,8 @@ static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
/* round down to nearest 256MB boundary */
xtensa_kio_paddr &= 0xf0000000;
+ init_kio();
+
return 1;
}
#else
@@ -246,6 +248,14 @@ void __init early_init_devtree(void *params)
void __init init_arch(bp_tag_t *bp_start)
{
+ /* Initialize MMU. */
+
+ init_mmu();
+
+ /* Initialize initial KASAN shadow map */
+
+ kasan_early_init();
+
/* Parse boot parameters */
if (bp_start)
@@ -263,10 +273,6 @@ void __init init_arch(bp_tag_t *bp_start)
/* Early hook for platforms */
platform_init(bp_start);
-
- /* Initialize MMU. */
-
- init_mmu();
}
/*
@@ -277,13 +283,13 @@ extern char _end[];
extern char _stext[];
extern char _WindowVectors_text_start;
extern char _WindowVectors_text_end;
-extern char _DebugInterruptVector_literal_start;
+extern char _DebugInterruptVector_text_start;
extern char _DebugInterruptVector_text_end;
-extern char _KernelExceptionVector_literal_start;
+extern char _KernelExceptionVector_text_start;
extern char _KernelExceptionVector_text_end;
-extern char _UserExceptionVector_literal_start;
+extern char _UserExceptionVector_text_start;
extern char _UserExceptionVector_text_end;
-extern char _DoubleExceptionVector_literal_start;
+extern char _DoubleExceptionVector_text_start;
extern char _DoubleExceptionVector_text_end;
#if XCHAL_EXCM_LEVEL >= 2
extern char _Level2InterruptVector_text_start;
@@ -317,6 +323,13 @@ static inline int mem_reserve(unsigned long start, unsigned long end)
void __init setup_arch(char **cmdline_p)
{
+ pr_info("config ID: %08x:%08x\n",
+ get_sr(SREG_EPC), get_sr(SREG_EXCSAVE));
+ if (get_sr(SREG_EPC) != XCHAL_HW_CONFIGID0 ||
+ get_sr(SREG_EXCSAVE) != XCHAL_HW_CONFIGID1)
+ pr_info("built for config ID: %08x:%08x\n",
+ XCHAL_HW_CONFIGID0, XCHAL_HW_CONFIGID1);
+
*cmdline_p = command_line;
platform_setup(cmdline_p);
strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
@@ -339,16 +352,16 @@ void __init setup_arch(char **cmdline_p)
mem_reserve(__pa(&_WindowVectors_text_start),
__pa(&_WindowVectors_text_end));
- mem_reserve(__pa(&_DebugInterruptVector_literal_start),
+ mem_reserve(__pa(&_DebugInterruptVector_text_start),
__pa(&_DebugInterruptVector_text_end));
- mem_reserve(__pa(&_KernelExceptionVector_literal_start),
+ mem_reserve(__pa(&_KernelExceptionVector_text_start),
__pa(&_KernelExceptionVector_text_end));
- mem_reserve(__pa(&_UserExceptionVector_literal_start),
+ mem_reserve(__pa(&_UserExceptionVector_text_start),
__pa(&_UserExceptionVector_text_end));
- mem_reserve(__pa(&_DoubleExceptionVector_literal_start),
+ mem_reserve(__pa(&_DoubleExceptionVector_text_start),
__pa(&_DoubleExceptionVector_text_end));
#if XCHAL_EXCM_LEVEL >= 2
@@ -380,7 +393,7 @@ void __init setup_arch(char **cmdline_p)
#endif
parse_early_param();
bootmem_init();
-
+ kasan_init();
unflatten_and_copy_device_tree();
#ifdef CONFIG_SMP
@@ -582,12 +595,14 @@ c_show(struct seq_file *f, void *slot)
"model\t\t: Xtensa " XCHAL_HW_VERSION_NAME "\n"
"core ID\t\t: " XCHAL_CORE_ID "\n"
"build ID\t: 0x%x\n"
+ "config ID\t: %08x:%08x\n"
"byte order\t: %s\n"
"cpu MHz\t\t: %lu.%02lu\n"
"bogomips\t: %lu.%02lu\n",
num_online_cpus(),
cpumask_pr_args(cpu_online_mask),
XCHAL_BUILD_UNIQUE_ID,
+ get_sr(SREG_EPC), get_sr(SREG_EXCSAVE),
XCHAL_HAVE_BE ? "big" : "little",
ccount_freq/1000000,
(ccount_freq/10000) % 100,
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index d427e784ab44..f88e7a0b232c 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -28,8 +28,6 @@
#include <asm/coprocessor.h>
#include <asm/unistd.h>
-#define DEBUG_SIG 0
-
extern struct task_struct *coproc_owners[];
struct rt_sigframe
@@ -399,10 +397,8 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
regs->areg[8] = (unsigned long) &frame->uc;
regs->threadptr = tp;
-#if DEBUG_SIG
- printk("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08x\n",
- current->comm, current->pid, sig, frame, regs->pc);
-#endif
+ pr_debug("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08lx\n",
+ current->comm, current->pid, sig, frame, regs->pc);
return 0;
}
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index bae697a06a98..32c5207f1226 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -33,6 +33,7 @@
#include <linux/kallsyms.h>
#include <linux/delay.h>
#include <linux/hardirq.h>
+#include <linux/ratelimit.h>
#include <asm/stacktrace.h>
#include <asm/ptrace.h>
@@ -158,8 +159,7 @@ COPROCESSOR(7),
* 2. it is a temporary memory buffer for the exception handlers.
*/
-DEFINE_PER_CPU(unsigned long, exc_table[EXC_TABLE_SIZE/4]);
-
+DEFINE_PER_CPU(struct exc_table, exc_table);
DEFINE_PER_CPU(struct debug_table, debug_table);
void die(const char*, struct pt_regs*, long);
@@ -178,13 +178,14 @@ __die_if_kernel(const char *str, struct pt_regs *regs, long err)
void do_unhandled(struct pt_regs *regs, unsigned long exccause)
{
__die_if_kernel("Caught unhandled exception - should not happen",
- regs, SIGKILL);
+ regs, SIGKILL);
/* If in user mode, send SIGILL signal to current process */
- printk("Caught unhandled exception in '%s' "
- "(pid = %d, pc = %#010lx) - should not happen\n"
- "\tEXCCAUSE is %ld\n",
- current->comm, task_pid_nr(current), regs->pc, exccause);
+ pr_info_ratelimited("Caught unhandled exception in '%s' "
+ "(pid = %d, pc = %#010lx) - should not happen\n"
+ "\tEXCCAUSE is %ld\n",
+ current->comm, task_pid_nr(current), regs->pc,
+ exccause);
force_sig(SIGILL, current);
}
@@ -305,8 +306,8 @@ do_illegal_instruction(struct pt_regs *regs)
/* If in user mode, send SIGILL signal to current process. */
- printk("Illegal Instruction in '%s' (pid = %d, pc = %#010lx)\n",
- current->comm, task_pid_nr(current), regs->pc);
+ pr_info_ratelimited("Illegal Instruction in '%s' (pid = %d, pc = %#010lx)\n",
+ current->comm, task_pid_nr(current), regs->pc);
force_sig(SIGILL, current);
}
@@ -325,13 +326,14 @@ do_unaligned_user (struct pt_regs *regs)
siginfo_t info;
__die_if_kernel("Unhandled unaligned exception in kernel",
- regs, SIGKILL);
+ regs, SIGKILL);
current->thread.bad_vaddr = regs->excvaddr;
current->thread.error_code = -3;
- printk("Unaligned memory access to %08lx in '%s' "
- "(pid = %d, pc = %#010lx)\n",
- regs->excvaddr, current->comm, task_pid_nr(current), regs->pc);
+ pr_info_ratelimited("Unaligned memory access to %08lx in '%s' "
+ "(pid = %d, pc = %#010lx)\n",
+ regs->excvaddr, current->comm,
+ task_pid_nr(current), regs->pc);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRALN;
@@ -365,28 +367,28 @@ do_debug(struct pt_regs *regs)
}
-static void set_handler(int idx, void *handler)
-{
- unsigned int cpu;
-
- for_each_possible_cpu(cpu)
- per_cpu(exc_table, cpu)[idx] = (unsigned long)handler;
-}
+#define set_handler(type, cause, handler) \
+ do { \
+ unsigned int cpu; \
+ \
+ for_each_possible_cpu(cpu) \
+ per_cpu(exc_table, cpu).type[cause] = (handler);\
+ } while (0)
/* Set exception C handler - for temporary use when probing exceptions */
void * __init trap_set_handler(int cause, void *handler)
{
- void *previous = (void *)per_cpu(exc_table, 0)[
- EXC_TABLE_DEFAULT / 4 + cause];
- set_handler(EXC_TABLE_DEFAULT / 4 + cause, handler);
+ void *previous = per_cpu(exc_table, 0).default_handler[cause];
+
+ set_handler(default_handler, cause, handler);
return previous;
}
static void trap_init_excsave(void)
{
- unsigned long excsave1 = (unsigned long)this_cpu_ptr(exc_table);
+ unsigned long excsave1 = (unsigned long)this_cpu_ptr(&exc_table);
__asm__ __volatile__("wsr %0, excsave1\n" : : "a" (excsave1));
}
@@ -418,10 +420,10 @@ void __init trap_init(void)
/* Setup default vectors. */
- for(i = 0; i < 64; i++) {
- set_handler(EXC_TABLE_FAST_USER/4 + i, user_exception);
- set_handler(EXC_TABLE_FAST_KERNEL/4 + i, kernel_exception);
- set_handler(EXC_TABLE_DEFAULT/4 + i, do_unhandled);
+ for (i = 0; i < EXCCAUSE_N; i++) {
+ set_handler(fast_user_handler, i, user_exception);
+ set_handler(fast_kernel_handler, i, kernel_exception);
+ set_handler(default_handler, i, do_unhandled);
}
/* Setup specific handlers. */
@@ -433,11 +435,11 @@ void __init trap_init(void)
void *handler = dispatch_init_table[i].handler;
if (fast == 0)
- set_handler (EXC_TABLE_DEFAULT/4 + cause, handler);
+ set_handler(default_handler, cause, handler);
if (fast && fast & USER)
- set_handler (EXC_TABLE_FAST_USER/4 + cause, handler);
+ set_handler(fast_user_handler, cause, handler);
if (fast && fast & KRNL)
- set_handler (EXC_TABLE_FAST_KERNEL/4 + cause, handler);
+ set_handler(fast_kernel_handler, cause, handler);
}
/* Initialize EXCSAVE_1 to hold the address of the exception table. */
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index 332e9d635fb6..841503d3307c 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -205,9 +205,6 @@ ENDPROC(_KernelExceptionVector)
*/
.section .DoubleExceptionVector.text, "ax"
- .begin literal_prefix .DoubleExceptionVector
- .globl _DoubleExceptionVector_WindowUnderflow
- .globl _DoubleExceptionVector_WindowOverflow
ENTRY(_DoubleExceptionVector)
@@ -217,8 +214,12 @@ ENTRY(_DoubleExceptionVector)
/* Check for kernel double exception (usually fatal). */
rsr a2, ps
- _bbci.l a2, PS_UM_BIT, .Lksp
+ _bbsi.l a2, PS_UM_BIT, 1f
+ j .Lksp
+ .align 4
+ .literal_position
+1:
/* Check if we are currently handling a window exception. */
/* Note: We don't need to indicate that we enter a critical section. */
@@ -304,8 +305,7 @@ _DoubleExceptionVector_WindowUnderflow:
.Lunrecoverable:
rsr a3, excsave1
wsr a0, excsave1
- movi a0, unrecoverable_exception
- callx0 a0
+ call0 unrecoverable_exception
.Lfixup:/* Check for a fixup handler or if we were in a critical section. */
@@ -475,11 +475,8 @@ _DoubleExceptionVector_handle_exception:
rotw -3
j 1b
-
ENDPROC(_DoubleExceptionVector)
- .end literal_prefix
-
.text
/*
* Fixup handler for TLB miss in double exception handler for window owerflow.
@@ -508,6 +505,8 @@ ENDPROC(_DoubleExceptionVector)
* a3: exctable, original value in excsave1
*/
+ .literal_position
+
ENTRY(window_overflow_restore_a0_fixup)
rsr a0, ps
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index 162c77e53ca8..70b731edc7b8 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -45,24 +45,16 @@ jiffies = jiffies_64;
LONG(sym ## _end); \
LONG(LOADADDR(section))
-/* Macro to define a section for a vector.
- *
- * Use of the MIN function catches the types of errors illustrated in
- * the following example:
- *
- * Assume the section .DoubleExceptionVector.literal is completely
- * full. Then a programmer adds code to .DoubleExceptionVector.text
- * that produces another literal. The final literal position will
- * overlay onto the first word of the adjacent code section
- * .DoubleExceptionVector.text. (In practice, the literals will
- * overwrite the code, and the first few instructions will be
- * garbage.)
+/*
+ * Macro to define a section for a vector. When CONFIG_VECTORS_OFFSET is
+ * defined code for every vector is located with other init data. At startup
+ * time head.S copies code for every vector to its final position according
+ * to description recorded in the corresponding RELOCATE_ENTRY.
*/
#ifdef CONFIG_VECTORS_OFFSET
-#define SECTION_VECTOR(sym, section, addr, max_prevsec_size, prevsec) \
- section addr : AT((MIN(LOADADDR(prevsec) + max_prevsec_size, \
- LOADADDR(prevsec) + SIZEOF(prevsec)) + 3) & ~ 3) \
+#define SECTION_VECTOR(sym, section, addr, prevsec) \
+ section addr : AT(((LOADADDR(prevsec) + SIZEOF(prevsec)) + 3) & ~ 3) \
{ \
. = ALIGN(4); \
sym ## _start = ABSOLUTE(.); \
@@ -112,26 +104,19 @@ SECTIONS
#if XCHAL_EXCM_LEVEL >= 6
SECTION_VECTOR (.Level6InterruptVector.text, INTLEVEL6_VECTOR_VADDR)
#endif
- SECTION_VECTOR (.DebugInterruptVector.literal, DEBUG_VECTOR_VADDR - 4)
SECTION_VECTOR (.DebugInterruptVector.text, DEBUG_VECTOR_VADDR)
- SECTION_VECTOR (.KernelExceptionVector.literal, KERNEL_VECTOR_VADDR - 4)
SECTION_VECTOR (.KernelExceptionVector.text, KERNEL_VECTOR_VADDR)
- SECTION_VECTOR (.UserExceptionVector.literal, USER_VECTOR_VADDR - 4)
SECTION_VECTOR (.UserExceptionVector.text, USER_VECTOR_VADDR)
- SECTION_VECTOR (.DoubleExceptionVector.literal, DOUBLEEXC_VECTOR_VADDR - 20)
SECTION_VECTOR (.DoubleExceptionVector.text, DOUBLEEXC_VECTOR_VADDR)
#endif
+ IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
+ ENTRY_TEXT
TEXT_TEXT
- VMLINUX_SYMBOL(__sched_text_start) = .;
- *(.sched.literal .sched.text)
- VMLINUX_SYMBOL(__sched_text_end) = .;
- VMLINUX_SYMBOL(__cpuidle_text_start) = .;
- *(.cpuidle.literal .cpuidle.text)
- VMLINUX_SYMBOL(__cpuidle_text_end) = .;
- VMLINUX_SYMBOL(__lock_text_start) = .;
- *(.spinlock.literal .spinlock.text)
- VMLINUX_SYMBOL(__lock_text_end) = .;
+ SCHED_TEXT
+ CPUIDLE_TEXT
+ LOCK_TEXT
}
_etext = .;
@@ -196,8 +181,6 @@ SECTIONS
.KernelExceptionVector.text);
RELOCATE_ENTRY(_UserExceptionVector_text,
.UserExceptionVector.text);
- RELOCATE_ENTRY(_DoubleExceptionVector_literal,
- .DoubleExceptionVector.literal);
RELOCATE_ENTRY(_DoubleExceptionVector_text,
.DoubleExceptionVector.text);
RELOCATE_ENTRY(_DebugInterruptVector_text,
@@ -230,25 +213,19 @@ SECTIONS
SECTION_VECTOR (_WindowVectors_text,
.WindowVectors.text,
- WINDOW_VECTORS_VADDR, 4,
+ WINDOW_VECTORS_VADDR,
.dummy)
- SECTION_VECTOR (_DebugInterruptVector_literal,
- .DebugInterruptVector.literal,
- DEBUG_VECTOR_VADDR - 4,
- SIZEOF(.WindowVectors.text),
- .WindowVectors.text)
SECTION_VECTOR (_DebugInterruptVector_text,
.DebugInterruptVector.text,
DEBUG_VECTOR_VADDR,
- 4,
- .DebugInterruptVector.literal)
+ .WindowVectors.text)
#undef LAST
#define LAST .DebugInterruptVector.text
#if XCHAL_EXCM_LEVEL >= 2
SECTION_VECTOR (_Level2InterruptVector_text,
.Level2InterruptVector.text,
INTLEVEL2_VECTOR_VADDR,
- SIZEOF(LAST), LAST)
+ LAST)
# undef LAST
# define LAST .Level2InterruptVector.text
#endif
@@ -256,7 +233,7 @@ SECTIONS
SECTION_VECTOR (_Level3InterruptVector_text,
.Level3InterruptVector.text,
INTLEVEL3_VECTOR_VADDR,
- SIZEOF(LAST), LAST)
+ LAST)
# undef LAST
# define LAST .Level3InterruptVector.text
#endif
@@ -264,7 +241,7 @@ SECTIONS
SECTION_VECTOR (_Level4InterruptVector_text,
.Level4InterruptVector.text,
INTLEVEL4_VECTOR_VADDR,
- SIZEOF(LAST), LAST)
+ LAST)
# undef LAST
# define LAST .Level4InterruptVector.text
#endif
@@ -272,7 +249,7 @@ SECTIONS
SECTION_VECTOR (_Level5InterruptVector_text,
.Level5InterruptVector.text,
INTLEVEL5_VECTOR_VADDR,
- SIZEOF(LAST), LAST)
+ LAST)
# undef LAST
# define LAST .Level5InterruptVector.text
#endif
@@ -280,40 +257,23 @@ SECTIONS
SECTION_VECTOR (_Level6InterruptVector_text,
.Level6InterruptVector.text,
INTLEVEL6_VECTOR_VADDR,
- SIZEOF(LAST), LAST)
+ LAST)
# undef LAST
# define LAST .Level6InterruptVector.text
#endif
- SECTION_VECTOR (_KernelExceptionVector_literal,
- .KernelExceptionVector.literal,
- KERNEL_VECTOR_VADDR - 4,
- SIZEOF(LAST), LAST)
-#undef LAST
SECTION_VECTOR (_KernelExceptionVector_text,
.KernelExceptionVector.text,
KERNEL_VECTOR_VADDR,
- 4,
- .KernelExceptionVector.literal)
- SECTION_VECTOR (_UserExceptionVector_literal,
- .UserExceptionVector.literal,
- USER_VECTOR_VADDR - 4,
- SIZEOF(.KernelExceptionVector.text),
- .KernelExceptionVector.text)
+ LAST)
+#undef LAST
SECTION_VECTOR (_UserExceptionVector_text,
.UserExceptionVector.text,
USER_VECTOR_VADDR,
- 4,
- .UserExceptionVector.literal)
- SECTION_VECTOR (_DoubleExceptionVector_literal,
- .DoubleExceptionVector.literal,
- DOUBLEEXC_VECTOR_VADDR - 20,
- SIZEOF(.UserExceptionVector.text),
- .UserExceptionVector.text)
+ .KernelExceptionVector.text)
SECTION_VECTOR (_DoubleExceptionVector_text,
.DoubleExceptionVector.text,
DOUBLEEXC_VECTOR_VADDR,
- 20,
- .DoubleExceptionVector.literal)
+ .UserExceptionVector.text)
. = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3;
@@ -323,7 +283,6 @@ SECTIONS
SECTION_VECTOR (_SecondaryResetVector_text,
.SecondaryResetVector.text,
RESET_VECTOR1_VADDR,
- SIZEOF(.DoubleExceptionVector.text),
.DoubleExceptionVector.text)
. = LOADADDR(.SecondaryResetVector.text)+SIZEOF(.SecondaryResetVector.text);
@@ -373,5 +332,4 @@ SECTIONS
/* Sections to be discarded */
DISCARDS
- /DISCARD/ : { *(.exit.literal) }
}
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 672391003e40..04f19de46700 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -41,7 +41,12 @@
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(__memmove);
+#ifndef CONFIG_GENERIC_STRNCPY_FROM_USER
EXPORT_SYMBOL(__strncpy_user);
+#endif
EXPORT_SYMBOL(clear_page);
EXPORT_SYMBOL(copy_page);
diff --git a/arch/xtensa/lib/checksum.S b/arch/xtensa/lib/checksum.S
index 4eb573d2720e..528fe0dd9339 100644
--- a/arch/xtensa/lib/checksum.S
+++ b/arch/xtensa/lib/checksum.S
@@ -14,9 +14,10 @@
* 2 of the License, or (at your option) any later version.
*/
-#include <asm/errno.h>
+#include <linux/errno.h>
#include <linux/linkage.h>
#include <variant/core.h>
+#include <asm/asmmacro.h>
/*
* computes a partial checksum, e.g. for TCP/UDP fragments
@@ -175,23 +176,8 @@ ENDPROC(csum_partial)
/*
* Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for each access type.
*/
-#define SRC(y...) \
- 9999: y; \
- .section __ex_table, "a"; \
- .long 9999b, 6001f ; \
- .previous
-
-#define DST(y...) \
- 9999: y; \
- .section __ex_table, "a"; \
- .long 9999b, 6002f ; \
- .previous
-
/*
unsigned int csum_partial_copy_generic (const char *src, char *dst, int len,
int sum, int *src_err_ptr, int *dst_err_ptr)
@@ -244,28 +230,28 @@ ENTRY(csum_partial_copy_generic)
add a10, a10, a2 /* a10 = end of last 32-byte src chunk */
.Loop5:
#endif
-SRC( l32i a9, a2, 0 )
-SRC( l32i a8, a2, 4 )
-DST( s32i a9, a3, 0 )
-DST( s32i a8, a3, 4 )
+EX(10f) l32i a9, a2, 0
+EX(10f) l32i a8, a2, 4
+EX(11f) s32i a9, a3, 0
+EX(11f) s32i a8, a3, 4
ONES_ADD(a5, a9)
ONES_ADD(a5, a8)
-SRC( l32i a9, a2, 8 )
-SRC( l32i a8, a2, 12 )
-DST( s32i a9, a3, 8 )
-DST( s32i a8, a3, 12 )
+EX(10f) l32i a9, a2, 8
+EX(10f) l32i a8, a2, 12
+EX(11f) s32i a9, a3, 8
+EX(11f) s32i a8, a3, 12
ONES_ADD(a5, a9)
ONES_ADD(a5, a8)
-SRC( l32i a9, a2, 16 )
-SRC( l32i a8, a2, 20 )
-DST( s32i a9, a3, 16 )
-DST( s32i a8, a3, 20 )
+EX(10f) l32i a9, a2, 16
+EX(10f) l32i a8, a2, 20
+EX(11f) s32i a9, a3, 16
+EX(11f) s32i a8, a3, 20
ONES_ADD(a5, a9)
ONES_ADD(a5, a8)
-SRC( l32i a9, a2, 24 )
-SRC( l32i a8, a2, 28 )
-DST( s32i a9, a3, 24 )
-DST( s32i a8, a3, 28 )
+EX(10f) l32i a9, a2, 24
+EX(10f) l32i a8, a2, 28
+EX(11f) s32i a9, a3, 24
+EX(11f) s32i a8, a3, 28
ONES_ADD(a5, a9)
ONES_ADD(a5, a8)
addi a2, a2, 32
@@ -284,8 +270,8 @@ DST( s32i a8, a3, 28 )
add a10, a10, a2 /* a10 = end of last 4-byte src chunk */
.Loop6:
#endif
-SRC( l32i a9, a2, 0 )
-DST( s32i a9, a3, 0 )
+EX(10f) l32i a9, a2, 0
+EX(11f) s32i a9, a3, 0
ONES_ADD(a5, a9)
addi a2, a2, 4
addi a3, a3, 4
@@ -315,8 +301,8 @@ DST( s32i a9, a3, 0 )
add a10, a10, a2 /* a10 = end of last 2-byte src chunk */
.Loop7:
#endif
-SRC( l16ui a9, a2, 0 )
-DST( s16i a9, a3, 0 )
+EX(10f) l16ui a9, a2, 0
+EX(11f) s16i a9, a3, 0
ONES_ADD(a5, a9)
addi a2, a2, 2
addi a3, a3, 2
@@ -326,8 +312,8 @@ DST( s16i a9, a3, 0 )
4:
/* This section processes a possible trailing odd byte. */
_bbci.l a4, 0, 8f /* 1-byte chunk */
-SRC( l8ui a9, a2, 0 )
-DST( s8i a9, a3, 0 )
+EX(10f) l8ui a9, a2, 0
+EX(11f) s8i a9, a3, 0
#ifdef __XTENSA_EB__
slli a9, a9, 8 /* shift byte to bits 8..15 */
#endif
@@ -350,10 +336,10 @@ DST( s8i a9, a3, 0 )
add a10, a10, a2 /* a10 = end of last odd-aligned, 2-byte src chunk */
.Loop8:
#endif
-SRC( l8ui a9, a2, 0 )
-SRC( l8ui a8, a2, 1 )
-DST( s8i a9, a3, 0 )
-DST( s8i a8, a3, 1 )
+EX(10f) l8ui a9, a2, 0
+EX(10f) l8ui a8, a2, 1
+EX(11f) s8i a9, a3, 0
+EX(11f) s8i a8, a3, 1
#ifdef __XTENSA_EB__
slli a9, a9, 8 /* combine into a single 16-bit value */
#else /* for checksum computation */
@@ -381,7 +367,7 @@ ENDPROC(csum_partial_copy_generic)
a12 = original dst for exception handling
*/
-6001:
+10:
_movi a2, -EFAULT
s32i a2, a6, 0 /* src_err_ptr */
@@ -403,7 +389,7 @@ ENDPROC(csum_partial_copy_generic)
2:
retw
-6002:
+11:
movi a2, -EFAULT
s32i a2, a7, 0 /* dst_err_ptr */
movi a2, 0
diff --git a/arch/xtensa/lib/memcopy.S b/arch/xtensa/lib/memcopy.S
index b1c219acabe7..c0f6981719d6 100644
--- a/arch/xtensa/lib/memcopy.S
+++ b/arch/xtensa/lib/memcopy.S
@@ -9,23 +9,9 @@
* Copyright (C) 2002 - 2012 Tensilica Inc.
*/
+#include <linux/linkage.h>
#include <variant/core.h>
-
- .macro src_b r, w0, w1
-#ifdef __XTENSA_EB__
- src \r, \w0, \w1
-#else
- src \r, \w1, \w0
-#endif
- .endm
-
- .macro ssa8 r
-#ifdef __XTENSA_EB__
- ssa8b \r
-#else
- ssa8l \r
-#endif
- .endm
+#include <asm/asmmacro.h>
/*
* void *memcpy(void *dst, const void *src, size_t len);
@@ -123,10 +109,8 @@
addi a5, a5, 2
j .Ldstaligned # dst is now aligned, return to main algorithm
- .align 4
- .global memcpy
- .type memcpy,@function
-memcpy:
+ENTRY(__memcpy)
+WEAK(memcpy)
entry sp, 16 # minimal stack frame
# a2/ dst, a3/ src, a4/ len
@@ -209,7 +193,7 @@ memcpy:
.Lsrcunaligned:
_beqz a4, .Ldone # avoid loading anything for zero-length copies
# copy 16 bytes per iteration for word-aligned dst and unaligned src
- ssa8 a3 # set shift amount from byte offset
+ __ssa8 a3 # set shift amount from byte offset
/* set to 1 when running on ISS (simulator) with the
lint or ferret client, or 0 to save a few cycles */
@@ -229,16 +213,16 @@ memcpy:
.Loop2:
l32i a7, a3, 4
l32i a8, a3, 8
- src_b a6, a6, a7
+ __src_b a6, a6, a7
s32i a6, a5, 0
l32i a9, a3, 12
- src_b a7, a7, a8
+ __src_b a7, a7, a8
s32i a7, a5, 4
l32i a6, a3, 16
- src_b a8, a8, a9
+ __src_b a8, a8, a9
s32i a8, a5, 8
addi a3, a3, 16
- src_b a9, a9, a6
+ __src_b a9, a9, a6
s32i a9, a5, 12
addi a5, a5, 16
#if !XCHAL_HAVE_LOOPS
@@ -249,10 +233,10 @@ memcpy:
# copy 8 bytes
l32i a7, a3, 4
l32i a8, a3, 8
- src_b a6, a6, a7
+ __src_b a6, a6, a7
s32i a6, a5, 0
addi a3, a3, 8
- src_b a7, a7, a8
+ __src_b a7, a7, a8
s32i a7, a5, 4
addi a5, a5, 8
mov a6, a8
@@ -261,7 +245,7 @@ memcpy:
# copy 4 bytes
l32i a7, a3, 4
addi a3, a3, 4
- src_b a6, a6, a7
+ __src_b a6, a6, a7
s32i a6, a5, 0
addi a5, a5, 4
mov a6, a7
@@ -288,14 +272,14 @@ memcpy:
s8i a6, a5, 0
retw
+ENDPROC(__memcpy)
/*
* void bcopy(const void *src, void *dest, size_t n);
*/
- .align 4
- .global bcopy
- .type bcopy,@function
-bcopy:
+
+ENTRY(bcopy)
+
entry sp, 16 # minimal stack frame
# a2=src, a3=dst, a4=len
mov a5, a3
@@ -303,6 +287,8 @@ bcopy:
mov a2, a5
j .Lmovecommon # go to common code for memmove+bcopy
+ENDPROC(bcopy)
+
/*
* void *memmove(void *dst, const void *src, size_t len);
*
@@ -391,10 +377,8 @@ bcopy:
j .Lbackdstaligned # dst is now aligned,
# return to main algorithm
- .align 4
- .global memmove
- .type memmove,@function
-memmove:
+ENTRY(__memmove)
+WEAK(memmove)
entry sp, 16 # minimal stack frame
# a2/ dst, a3/ src, a4/ len
@@ -485,7 +469,7 @@ memmove:
.Lbacksrcunaligned:
_beqz a4, .Lbackdone # avoid loading anything for zero-length copies
# copy 16 bytes per iteration for word-aligned dst and unaligned src
- ssa8 a3 # set shift amount from byte offset
+ __ssa8 a3 # set shift amount from byte offset
#define SIM_CHECKS_ALIGNMENT 1 /* set to 1 when running on ISS with
* the lint or ferret client, or 0
* to save a few cycles */
@@ -506,15 +490,15 @@ memmove:
l32i a7, a3, 12
l32i a8, a3, 8
addi a5, a5, -16
- src_b a6, a7, a6
+ __src_b a6, a7, a6
s32i a6, a5, 12
l32i a9, a3, 4
- src_b a7, a8, a7
+ __src_b a7, a8, a7
s32i a7, a5, 8
l32i a6, a3, 0
- src_b a8, a9, a8
+ __src_b a8, a9, a8
s32i a8, a5, 4
- src_b a9, a6, a9
+ __src_b a9, a6, a9
s32i a9, a5, 0
#if !XCHAL_HAVE_LOOPS
bne a3, a10, .backLoop2 # continue loop if a3:src != a10:src_start
@@ -526,9 +510,9 @@ memmove:
l32i a7, a3, 4
l32i a8, a3, 0
addi a5, a5, -8
- src_b a6, a7, a6
+ __src_b a6, a7, a6
s32i a6, a5, 4
- src_b a7, a8, a7
+ __src_b a7, a8, a7
s32i a7, a5, 0
mov a6, a8
.Lback12:
@@ -537,7 +521,7 @@ memmove:
addi a3, a3, -4
l32i a7, a3, 0
addi a5, a5, -4
- src_b a6, a7, a6
+ __src_b a6, a7, a6
s32i a6, a5, 0
mov a6, a7
.Lback13:
@@ -566,11 +550,4 @@ memmove:
s8i a6, a5, 0
retw
-
-/*
- * Local Variables:
- * mode:fundamental
- * comment-start: "# "
- * comment-start-skip: "# *"
- * End:
- */
+ENDPROC(__memmove)
diff --git a/arch/xtensa/lib/memset.S b/arch/xtensa/lib/memset.S
index 10b8c400f175..276747dec300 100644
--- a/arch/xtensa/lib/memset.S
+++ b/arch/xtensa/lib/memset.S
@@ -11,7 +11,9 @@
* Copyright (C) 2002 Tensilica Inc.
*/
+#include <linux/linkage.h>
#include <variant/core.h>
+#include <asm/asmmacro.h>
/*
* void *memset(void *dst, int c, size_t length)
@@ -28,20 +30,10 @@
* the alignment labels).
*/
-/* Load or store instructions that may cause exceptions use the EX macro. */
-
-#define EX(insn,reg1,reg2,offset,handler) \
-9: insn reg1, reg2, offset; \
- .section __ex_table, "a"; \
- .word 9b, handler; \
- .previous
-
-
.text
-.align 4
-.global memset
-.type memset,@function
-memset:
+ENTRY(__memset)
+WEAK(memset)
+
entry sp, 16 # minimal stack frame
# a2/ dst, a3/ c, a4/ length
extui a3, a3, 0, 8 # mask to just 8 bits
@@ -73,10 +65,10 @@ memset:
add a6, a6, a5 # a6 = end of last 16B chunk
#endif /* !XCHAL_HAVE_LOOPS */
.Loop1:
- EX(s32i, a3, a5, 0, memset_fixup)
- EX(s32i, a3, a5, 4, memset_fixup)
- EX(s32i, a3, a5, 8, memset_fixup)
- EX(s32i, a3, a5, 12, memset_fixup)
+EX(10f) s32i a3, a5, 0
+EX(10f) s32i a3, a5, 4
+EX(10f) s32i a3, a5, 8
+EX(10f) s32i a3, a5, 12
addi a5, a5, 16
#if !XCHAL_HAVE_LOOPS
blt a5, a6, .Loop1
@@ -84,23 +76,23 @@ memset:
.Loop1done:
bbci.l a4, 3, .L2
# set 8 bytes
- EX(s32i, a3, a5, 0, memset_fixup)
- EX(s32i, a3, a5, 4, memset_fixup)
+EX(10f) s32i a3, a5, 0
+EX(10f) s32i a3, a5, 4
addi a5, a5, 8
.L2:
bbci.l a4, 2, .L3
# set 4 bytes
- EX(s32i, a3, a5, 0, memset_fixup)
+EX(10f) s32i a3, a5, 0
addi a5, a5, 4
.L3:
bbci.l a4, 1, .L4
# set 2 bytes
- EX(s16i, a3, a5, 0, memset_fixup)
+EX(10f) s16i a3, a5, 0
addi a5, a5, 2
.L4:
bbci.l a4, 0, .L5
# set 1 byte
- EX(s8i, a3, a5, 0, memset_fixup)
+EX(10f) s8i a3, a5, 0
.L5:
.Lret1:
retw
@@ -114,7 +106,7 @@ memset:
bbci.l a5, 0, .L20 # branch if dst alignment half-aligned
# dst is only byte aligned
# set 1 byte
- EX(s8i, a3, a5, 0, memset_fixup)
+EX(10f) s8i a3, a5, 0
addi a5, a5, 1
addi a4, a4, -1
# now retest if dst aligned
@@ -122,7 +114,7 @@ memset:
.L20:
# dst half-aligned
# set 2 bytes
- EX(s16i, a3, a5, 0, memset_fixup)
+EX(10f) s16i a3, a5, 0
addi a5, a5, 2
addi a4, a4, -2
j .L0 # dst is now aligned, return to main algorithm
@@ -141,7 +133,7 @@ memset:
add a6, a5, a4 # a6 = ending address
#endif /* !XCHAL_HAVE_LOOPS */
.Lbyteloop:
- EX(s8i, a3, a5, 0, memset_fixup)
+EX(10f) s8i a3, a5, 0
addi a5, a5, 1
#if !XCHAL_HAVE_LOOPS
blt a5, a6, .Lbyteloop
@@ -149,12 +141,13 @@ memset:
.Lbytesetdone:
retw
+ENDPROC(__memset)
.section .fixup, "ax"
.align 4
/* We return zero if a failure occurred. */
-memset_fixup:
+10:
movi a2, 0
retw
diff --git a/arch/xtensa/lib/pci-auto.c b/arch/xtensa/lib/pci-auto.c
index 34d05abbd921..a2b558161d6d 100644
--- a/arch/xtensa/lib/pci-auto.c
+++ b/arch/xtensa/lib/pci-auto.c
@@ -49,17 +49,6 @@
*
*/
-
-/* define DEBUG to print some debugging messages. */
-
-#undef DEBUG
-
-#ifdef DEBUG
-# define DBG(x...) printk(x)
-#else
-# define DBG(x...)
-#endif
-
static int pciauto_upper_iospc;
static int pciauto_upper_memspc;
@@ -97,7 +86,7 @@ pciauto_setup_bars(struct pci_dev *dev, int bar_limit)
{
bar_size &= PCI_BASE_ADDRESS_IO_MASK;
upper_limit = &pciauto_upper_iospc;
- DBG("PCI Autoconfig: BAR %d, I/O, ", bar_nr);
+ pr_debug("PCI Autoconfig: BAR %d, I/O, ", bar_nr);
}
else
{
@@ -107,7 +96,7 @@ pciauto_setup_bars(struct pci_dev *dev, int bar_limit)
bar_size &= PCI_BASE_ADDRESS_MEM_MASK;
upper_limit = &pciauto_upper_memspc;
- DBG("PCI Autoconfig: BAR %d, Mem, ", bar_nr);
+ pr_debug("PCI Autoconfig: BAR %d, Mem, ", bar_nr);
}
/* Allocate a base address (bar_size is negative!) */
@@ -125,7 +114,8 @@ pciauto_setup_bars(struct pci_dev *dev, int bar_limit)
if (found_mem64)
pci_write_config_dword(dev, (bar+=4), 0x00000000);
- DBG("size=0x%x, address=0x%x\n", ~bar_size + 1, *upper_limit);
+ pr_debug("size=0x%x, address=0x%x\n",
+ ~bar_size + 1, *upper_limit);
}
}
@@ -150,7 +140,7 @@ pciauto_setup_irq(struct pci_controller* pci_ctrl,struct pci_dev *dev,int devfn)
if (irq == -1)
irq = 0;
- DBG("PCI Autoconfig: Interrupt %d, pin %d\n", irq, pin);
+ pr_debug("PCI Autoconfig: Interrupt %d, pin %d\n", irq, pin);
pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
}
@@ -289,8 +279,8 @@ int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
int iosave, memsave;
- DBG("PCI Autoconfig: Found P2P bridge, device %d\n",
- PCI_SLOT(pci_devfn));
+ pr_debug("PCI Autoconfig: Found P2P bridge, device %d\n",
+ PCI_SLOT(pci_devfn));
/* Allocate PCI I/O and/or memory space */
pciauto_setup_bars(dev, PCI_BASE_ADDRESS_1);
@@ -306,23 +296,6 @@ int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
}
-
-#if 0
- /* Skip legacy mode IDE controller */
-
- if ((pci_class >> 16) == PCI_CLASS_STORAGE_IDE) {
-
- unsigned char prg_iface;
- pci_read_config_byte(dev, PCI_CLASS_PROG, &prg_iface);
-
- if (!(prg_iface & PCIAUTO_IDE_MODE_MASK)) {
- DBG("PCI Autoconfig: Skipping legacy mode "
- "IDE controller\n");
- continue;
- }
- }
-#endif
-
/*
* Found a peripheral, enable some standard
* settings
@@ -337,8 +310,8 @@ int __init pciauto_bus_scan(struct pci_controller *pci_ctrl, int current_bus)
pci_write_config_byte(dev, PCI_LATENCY_TIMER, 0x80);
/* Allocate PCI I/O and/or memory space */
- DBG("PCI Autoconfig: Found Bus %d, Device %d, Function %d\n",
- current_bus, PCI_SLOT(pci_devfn), PCI_FUNC(pci_devfn) );
+ pr_debug("PCI Autoconfig: Found Bus %d, Device %d, Function %d\n",
+ current_bus, PCI_SLOT(pci_devfn), PCI_FUNC(pci_devfn));
pciauto_setup_bars(dev, PCI_BASE_ADDRESS_5);
pciauto_setup_irq(pci_ctrl, dev, pci_devfn);
diff --git a/arch/xtensa/lib/strncpy_user.S b/arch/xtensa/lib/strncpy_user.S
index 1ad0ecf45368..5fce16b67dca 100644
--- a/arch/xtensa/lib/strncpy_user.S
+++ b/arch/xtensa/lib/strncpy_user.S
@@ -11,16 +11,10 @@
* Copyright (C) 2002 Tensilica Inc.
*/
-#include <variant/core.h>
#include <linux/errno.h>
-
-/* Load or store instructions that may cause exceptions use the EX macro. */
-
-#define EX(insn,reg1,reg2,offset,handler) \
-9: insn reg1, reg2, offset; \
- .section __ex_table, "a"; \
- .word 9b, handler; \
- .previous
+#include <linux/linkage.h>
+#include <variant/core.h>
+#include <asm/asmmacro.h>
/*
* char *__strncpy_user(char *dst, const char *src, size_t len)
@@ -54,10 +48,8 @@
# a12/ tmp
.text
-.align 4
-.global __strncpy_user
-.type __strncpy_user,@function
-__strncpy_user:
+ENTRY(__strncpy_user)
+
entry sp, 16 # minimal stack frame
# a2/ dst, a3/ src, a4/ len
mov a11, a2 # leave dst in return value register
@@ -75,9 +67,9 @@ __strncpy_user:
j .Ldstunaligned
.Lsrc1mod2: # src address is odd
- EX(l8ui, a9, a3, 0, fixup_l) # get byte 0
+EX(11f) l8ui a9, a3, 0 # get byte 0
addi a3, a3, 1 # advance src pointer
- EX(s8i, a9, a11, 0, fixup_s) # store byte 0
+EX(10f) s8i a9, a11, 0 # store byte 0
beqz a9, .Lret # if byte 0 is zero
addi a11, a11, 1 # advance dst pointer
addi a4, a4, -1 # decrement len
@@ -85,16 +77,16 @@ __strncpy_user:
bbci.l a3, 1, .Lsrcaligned # if src is now word-aligned
.Lsrc2mod4: # src address is 2 mod 4
- EX(l8ui, a9, a3, 0, fixup_l) # get byte 0
+EX(11f) l8ui a9, a3, 0 # get byte 0
/* 1-cycle interlock */
- EX(s8i, a9, a11, 0, fixup_s) # store byte 0
+EX(10f) s8i a9, a11, 0 # store byte 0
beqz a9, .Lret # if byte 0 is zero
addi a11, a11, 1 # advance dst pointer
addi a4, a4, -1 # decrement len
beqz a4, .Lret # if len is zero
- EX(l8ui, a9, a3, 1, fixup_l) # get byte 0
+EX(11f) l8ui a9, a3, 1 # get byte 0
addi a3, a3, 2 # advance src pointer
- EX(s8i, a9, a11, 0, fixup_s) # store byte 0
+EX(10f) s8i a9, a11, 0 # store byte 0
beqz a9, .Lret # if byte 0 is zero
addi a11, a11, 1 # advance dst pointer
addi a4, a4, -1 # decrement len
@@ -117,12 +109,12 @@ __strncpy_user:
add a12, a12, a11 # a12 = end of last 4B chunck
#endif
.Loop1:
- EX(l32i, a9, a3, 0, fixup_l) # get word from src
+EX(11f) l32i a9, a3, 0 # get word from src
addi a3, a3, 4 # advance src pointer
bnone a9, a5, .Lz0 # if byte 0 is zero
bnone a9, a6, .Lz1 # if byte 1 is zero
bnone a9, a7, .Lz2 # if byte 2 is zero
- EX(s32i, a9, a11, 0, fixup_s) # store word to dst
+EX(10f) s32i a9, a11, 0 # store word to dst
bnone a9, a8, .Lz3 # if byte 3 is zero
addi a11, a11, 4 # advance dst pointer
#if !XCHAL_HAVE_LOOPS
@@ -132,7 +124,7 @@ __strncpy_user:
.Loop1done:
bbci.l a4, 1, .L100
# copy 2 bytes
- EX(l16ui, a9, a3, 0, fixup_l)
+EX(11f) l16ui a9, a3, 0
addi a3, a3, 2 # advance src pointer
#ifdef __XTENSA_EB__
bnone a9, a7, .Lz0 # if byte 2 is zero
@@ -141,13 +133,13 @@ __strncpy_user:
bnone a9, a5, .Lz0 # if byte 0 is zero
bnone a9, a6, .Lz1 # if byte 1 is zero
#endif
- EX(s16i, a9, a11, 0, fixup_s)
+EX(10f) s16i a9, a11, 0
addi a11, a11, 2 # advance dst pointer
.L100:
bbci.l a4, 0, .Lret
- EX(l8ui, a9, a3, 0, fixup_l)
+EX(11f) l8ui a9, a3, 0
/* slot */
- EX(s8i, a9, a11, 0, fixup_s)
+EX(10f) s8i a9, a11, 0
beqz a9, .Lret # if byte is zero
addi a11, a11, 1-3 # advance dst ptr 1, but also cancel
# the effect of adding 3 in .Lz3 code
@@ -161,14 +153,14 @@ __strncpy_user:
#ifdef __XTENSA_EB__
movi a9, 0
#endif /* __XTENSA_EB__ */
- EX(s8i, a9, a11, 0, fixup_s)
+EX(10f) s8i a9, a11, 0
sub a2, a11, a2 # compute strlen
retw
.Lz1: # byte 1 is zero
#ifdef __XTENSA_EB__
extui a9, a9, 16, 16
#endif /* __XTENSA_EB__ */
- EX(s16i, a9, a11, 0, fixup_s)
+EX(10f) s16i a9, a11, 0
addi a11, a11, 1 # advance dst pointer
sub a2, a11, a2 # compute strlen
retw
@@ -176,9 +168,9 @@ __strncpy_user:
#ifdef __XTENSA_EB__
extui a9, a9, 16, 16
#endif /* __XTENSA_EB__ */
- EX(s16i, a9, a11, 0, fixup_s)
+EX(10f) s16i a9, a11, 0
movi a9, 0
- EX(s8i, a9, a11, 2, fixup_s)
+EX(10f) s8i a9, a11, 2
addi a11, a11, 2 # advance dst pointer
sub a2, a11, a2 # compute strlen
retw
@@ -196,9 +188,9 @@ __strncpy_user:
add a12, a11, a4 # a12 = ending address
#endif /* XCHAL_HAVE_LOOPS */
.Lnextbyte:
- EX(l8ui, a9, a3, 0, fixup_l)
+EX(11f) l8ui a9, a3, 0
addi a3, a3, 1
- EX(s8i, a9, a11, 0, fixup_s)
+EX(10f) s8i a9, a11, 0
beqz a9, .Lunalignedend
addi a11, a11, 1
#if !XCHAL_HAVE_LOOPS
@@ -209,6 +201,7 @@ __strncpy_user:
sub a2, a11, a2 # compute strlen
retw
+ENDPROC(__strncpy_user)
.section .fixup, "ax"
.align 4
@@ -218,8 +211,7 @@ __strncpy_user:
* implementation in memset(). Thus, we differentiate between
* load/store fixups. */
-fixup_s:
-fixup_l:
+10:
+11:
movi a2, -EFAULT
retw
-
diff --git a/arch/xtensa/lib/strnlen_user.S b/arch/xtensa/lib/strnlen_user.S
index 4c03b1e581e9..0b956ce7f386 100644
--- a/arch/xtensa/lib/strnlen_user.S
+++ b/arch/xtensa/lib/strnlen_user.S
@@ -11,15 +11,9 @@
* Copyright (C) 2002 Tensilica Inc.
*/
+#include <linux/linkage.h>
#include <variant/core.h>
-
-/* Load or store instructions that may cause exceptions use the EX macro. */
-
-#define EX(insn,reg1,reg2,offset,handler) \
-9: insn reg1, reg2, offset; \
- .section __ex_table, "a"; \
- .word 9b, handler; \
- .previous
+#include <asm/asmmacro.h>
/*
* size_t __strnlen_user(const char *s, size_t len)
@@ -49,10 +43,8 @@
# a10/ tmp
.text
-.align 4
-.global __strnlen_user
-.type __strnlen_user,@function
-__strnlen_user:
+ENTRY(__strnlen_user)
+
entry sp, 16 # minimal stack frame
# a2/ s, a3/ len
addi a4, a2, -4 # because we overincrement at the end;
@@ -77,7 +69,7 @@ __strnlen_user:
add a10, a10, a4 # a10 = end of last 4B chunk
#endif /* XCHAL_HAVE_LOOPS */
.Loop:
- EX(l32i, a9, a4, 4, lenfixup) # get next word of string
+EX(10f) l32i a9, a4, 4 # get next word of string
addi a4, a4, 4 # advance string pointer
bnone a9, a5, .Lz0 # if byte 0 is zero
bnone a9, a6, .Lz1 # if byte 1 is zero
@@ -88,7 +80,7 @@ __strnlen_user:
#endif
.Ldone:
- EX(l32i, a9, a4, 4, lenfixup) # load 4 bytes for remaining checks
+EX(10f) l32i a9, a4, 4 # load 4 bytes for remaining checks
bbci.l a3, 1, .L100
# check two more bytes (bytes 0, 1 of word)
@@ -125,14 +117,14 @@ __strnlen_user:
retw
.L1mod2: # address is odd
- EX(l8ui, a9, a4, 4, lenfixup) # get byte 0
+EX(10f) l8ui a9, a4, 4 # get byte 0
addi a4, a4, 1 # advance string pointer
beqz a9, .Lz3 # if byte 0 is zero
bbci.l a4, 1, .Laligned # if string pointer is now word-aligned
.L2mod4: # address is 2 mod 4
addi a4, a4, 2 # advance ptr for aligned access
- EX(l32i, a9, a4, 0, lenfixup) # get word with first two bytes of string
+EX(10f) l32i a9, a4, 0 # get word with first two bytes of string
bnone a9, a7, .Lz2 # if byte 2 (of word, not string) is zero
bany a9, a8, .Laligned # if byte 3 (of word, not string) is nonzero
# byte 3 is zero
@@ -140,8 +132,10 @@ __strnlen_user:
sub a2, a4, a2 # subtract to get length
retw
+ENDPROC(__strnlen_user)
+
.section .fixup, "ax"
.align 4
-lenfixup:
+10:
movi a2, 0
retw
diff --git a/arch/xtensa/lib/usercopy.S b/arch/xtensa/lib/usercopy.S
index d9cd766bde3e..64ab1971324f 100644
--- a/arch/xtensa/lib/usercopy.S
+++ b/arch/xtensa/lib/usercopy.S
@@ -53,30 +53,13 @@
* a11/ original length
*/
+#include <linux/linkage.h>
#include <variant/core.h>
-
-#ifdef __XTENSA_EB__
-#define ALIGN(R, W0, W1) src R, W0, W1
-#define SSA8(R) ssa8b R
-#else
-#define ALIGN(R, W0, W1) src R, W1, W0
-#define SSA8(R) ssa8l R
-#endif
-
-/* Load or store instructions that may cause exceptions use the EX macro. */
-
-#define EX(insn,reg1,reg2,offset,handler) \
-9: insn reg1, reg2, offset; \
- .section __ex_table, "a"; \
- .word 9b, handler; \
- .previous
-
+#include <asm/asmmacro.h>
.text
- .align 4
- .global __xtensa_copy_user
- .type __xtensa_copy_user,@function
-__xtensa_copy_user:
+ENTRY(__xtensa_copy_user)
+
entry sp, 16 # minimal stack frame
# a2/ dst, a3/ src, a4/ len
mov a5, a2 # copy dst so that a2 is return value
@@ -89,7 +72,7 @@ __xtensa_copy_user:
# per iteration
movi a8, 3 # if source is also aligned,
bnone a3, a8, .Laligned # then use word copy
- SSA8( a3) # set shift amount from byte offset
+ __ssa8 a3 # set shift amount from byte offset
bnez a4, .Lsrcunaligned
movi a2, 0 # return success for len==0
retw
@@ -102,9 +85,9 @@ __xtensa_copy_user:
bltui a4, 7, .Lbytecopy # do short copies byte by byte
# copy 1 byte
- EX(l8ui, a6, a3, 0, fixup)
+EX(10f) l8ui a6, a3, 0
addi a3, a3, 1
- EX(s8i, a6, a5, 0, fixup)
+EX(10f) s8i a6, a5, 0
addi a5, a5, 1
addi a4, a4, -1
bbci.l a5, 1, .Ldstaligned # if dst is now aligned, then
@@ -112,11 +95,11 @@ __xtensa_copy_user:
.Ldst2mod4: # dst 16-bit aligned
# copy 2 bytes
bltui a4, 6, .Lbytecopy # do short copies byte by byte
- EX(l8ui, a6, a3, 0, fixup)
- EX(l8ui, a7, a3, 1, fixup)
+EX(10f) l8ui a6, a3, 0
+EX(10f) l8ui a7, a3, 1
addi a3, a3, 2
- EX(s8i, a6, a5, 0, fixup)
- EX(s8i, a7, a5, 1, fixup)
+EX(10f) s8i a6, a5, 0
+EX(10f) s8i a7, a5, 1
addi a5, a5, 2
addi a4, a4, -2
j .Ldstaligned # dst is now aligned, return to main algorithm
@@ -135,9 +118,9 @@ __xtensa_copy_user:
add a7, a3, a4 # a7 = end address for source
#endif /* !XCHAL_HAVE_LOOPS */
.Lnextbyte:
- EX(l8ui, a6, a3, 0, fixup)
+EX(10f) l8ui a6, a3, 0
addi a3, a3, 1
- EX(s8i, a6, a5, 0, fixup)
+EX(10f) s8i a6, a5, 0
addi a5, a5, 1
#if !XCHAL_HAVE_LOOPS
blt a3, a7, .Lnextbyte
@@ -161,15 +144,15 @@ __xtensa_copy_user:
add a8, a8, a3 # a8 = end of last 16B source chunk
#endif /* !XCHAL_HAVE_LOOPS */
.Loop1:
- EX(l32i, a6, a3, 0, fixup)
- EX(l32i, a7, a3, 4, fixup)
- EX(s32i, a6, a5, 0, fixup)
- EX(l32i, a6, a3, 8, fixup)
- EX(s32i, a7, a5, 4, fixup)
- EX(l32i, a7, a3, 12, fixup)
- EX(s32i, a6, a5, 8, fixup)
+EX(10f) l32i a6, a3, 0
+EX(10f) l32i a7, a3, 4
+EX(10f) s32i a6, a5, 0
+EX(10f) l32i a6, a3, 8
+EX(10f) s32i a7, a5, 4
+EX(10f) l32i a7, a3, 12
+EX(10f) s32i a6, a5, 8
addi a3, a3, 16
- EX(s32i, a7, a5, 12, fixup)
+EX(10f) s32i a7, a5, 12
addi a5, a5, 16
#if !XCHAL_HAVE_LOOPS
blt a3, a8, .Loop1
@@ -177,31 +160,31 @@ __xtensa_copy_user:
.Loop1done:
bbci.l a4, 3, .L2
# copy 8 bytes
- EX(l32i, a6, a3, 0, fixup)
- EX(l32i, a7, a3, 4, fixup)
+EX(10f) l32i a6, a3, 0
+EX(10f) l32i a7, a3, 4
addi a3, a3, 8
- EX(s32i, a6, a5, 0, fixup)
- EX(s32i, a7, a5, 4, fixup)
+EX(10f) s32i a6, a5, 0
+EX(10f) s32i a7, a5, 4
addi a5, a5, 8
.L2:
bbci.l a4, 2, .L3
# copy 4 bytes
- EX(l32i, a6, a3, 0, fixup)
+EX(10f) l32i a6, a3, 0
addi a3, a3, 4
- EX(s32i, a6, a5, 0, fixup)
+EX(10f) s32i a6, a5, 0
addi a5, a5, 4
.L3:
bbci.l a4, 1, .L4
# copy 2 bytes
- EX(l16ui, a6, a3, 0, fixup)
+EX(10f) l16ui a6, a3, 0
addi a3, a3, 2
- EX(s16i, a6, a5, 0, fixup)
+EX(10f) s16i a6, a5, 0
addi a5, a5, 2
.L4:
bbci.l a4, 0, .L5
# copy 1 byte
- EX(l8ui, a6, a3, 0, fixup)
- EX(s8i, a6, a5, 0, fixup)
+EX(10f) l8ui a6, a3, 0
+EX(10f) s8i a6, a5, 0
.L5:
movi a2, 0 # return success for len bytes copied
retw
@@ -217,7 +200,7 @@ __xtensa_copy_user:
# copy 16 bytes per iteration for word-aligned dst and unaligned src
and a10, a3, a8 # save unalignment offset for below
sub a3, a3, a10 # align a3 (to avoid sim warnings only; not needed for hardware)
- EX(l32i, a6, a3, 0, fixup) # load first word
+EX(10f) l32i a6, a3, 0 # load first word
#if XCHAL_HAVE_LOOPS
loopnez a7, .Loop2done
#else /* !XCHAL_HAVE_LOOPS */
@@ -226,19 +209,19 @@ __xtensa_copy_user:
add a12, a12, a3 # a12 = end of last 16B source chunk
#endif /* !XCHAL_HAVE_LOOPS */
.Loop2:
- EX(l32i, a7, a3, 4, fixup)
- EX(l32i, a8, a3, 8, fixup)
- ALIGN( a6, a6, a7)
- EX(s32i, a6, a5, 0, fixup)
- EX(l32i, a9, a3, 12, fixup)
- ALIGN( a7, a7, a8)
- EX(s32i, a7, a5, 4, fixup)
- EX(l32i, a6, a3, 16, fixup)
- ALIGN( a8, a8, a9)
- EX(s32i, a8, a5, 8, fixup)
+EX(10f) l32i a7, a3, 4
+EX(10f) l32i a8, a3, 8
+ __src_b a6, a6, a7
+EX(10f) s32i a6, a5, 0
+EX(10f) l32i a9, a3, 12
+ __src_b a7, a7, a8
+EX(10f) s32i a7, a5, 4
+EX(10f) l32i a6, a3, 16
+ __src_b a8, a8, a9
+EX(10f) s32i a8, a5, 8
addi a3, a3, 16
- ALIGN( a9, a9, a6)
- EX(s32i, a9, a5, 12, fixup)
+ __src_b a9, a9, a6
+EX(10f) s32i a9, a5, 12
addi a5, a5, 16
#if !XCHAL_HAVE_LOOPS
blt a3, a12, .Loop2
@@ -246,43 +229,44 @@ __xtensa_copy_user:
.Loop2done:
bbci.l a4, 3, .L12
# copy 8 bytes
- EX(l32i, a7, a3, 4, fixup)
- EX(l32i, a8, a3, 8, fixup)
- ALIGN( a6, a6, a7)
- EX(s32i, a6, a5, 0, fixup)
+EX(10f) l32i a7, a3, 4
+EX(10f) l32i a8, a3, 8
+ __src_b a6, a6, a7
+EX(10f) s32i a6, a5, 0
addi a3, a3, 8
- ALIGN( a7, a7, a8)
- EX(s32i, a7, a5, 4, fixup)
+ __src_b a7, a7, a8
+EX(10f) s32i a7, a5, 4
addi a5, a5, 8
mov a6, a8
.L12:
bbci.l a4, 2, .L13
# copy 4 bytes
- EX(l32i, a7, a3, 4, fixup)
+EX(10f) l32i a7, a3, 4
addi a3, a3, 4
- ALIGN( a6, a6, a7)
- EX(s32i, a6, a5, 0, fixup)
+ __src_b a6, a6, a7
+EX(10f) s32i a6, a5, 0
addi a5, a5, 4
mov a6, a7
.L13:
add a3, a3, a10 # readjust a3 with correct misalignment
bbci.l a4, 1, .L14
# copy 2 bytes
- EX(l8ui, a6, a3, 0, fixup)
- EX(l8ui, a7, a3, 1, fixup)
+EX(10f) l8ui a6, a3, 0
+EX(10f) l8ui a7, a3, 1
addi a3, a3, 2
- EX(s8i, a6, a5, 0, fixup)
- EX(s8i, a7, a5, 1, fixup)
+EX(10f) s8i a6, a5, 0
+EX(10f) s8i a7, a5, 1
addi a5, a5, 2
.L14:
bbci.l a4, 0, .L15
# copy 1 byte
- EX(l8ui, a6, a3, 0, fixup)
- EX(s8i, a6, a5, 0, fixup)
+EX(10f) l8ui a6, a3, 0
+EX(10f) s8i a6, a5, 0
.L15:
movi a2, 0 # return success for len bytes copied
retw
+ENDPROC(__xtensa_copy_user)
.section .fixup, "ax"
.align 4
@@ -294,7 +278,7 @@ __xtensa_copy_user:
*/
-fixup:
+10:
sub a2, a5, a2 /* a2 <-- bytes copied */
sub a2, a11, a2 /* a2 <-- bytes not copied */
retw
diff --git a/arch/xtensa/mm/Makefile b/arch/xtensa/mm/Makefile
index 0b3d296a016a..734888a00dc8 100644
--- a/arch/xtensa/mm/Makefile
+++ b/arch/xtensa/mm/Makefile
@@ -5,3 +5,8 @@
obj-y := init.o misc.o
obj-$(CONFIG_MMU) += cache.o fault.o ioremap.o mmu.o tlb.o
obj-$(CONFIG_HIGHMEM) += highmem.o
+obj-$(CONFIG_KASAN) += kasan_init.o
+
+KASAN_SANITIZE_fault.o := n
+KASAN_SANITIZE_kasan_init.o := n
+KASAN_SANITIZE_mmu.o := n
diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c
index 3c75c4e597da..57dc231a0709 100644
--- a/arch/xtensa/mm/cache.c
+++ b/arch/xtensa/mm/cache.c
@@ -33,9 +33,6 @@
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
-//#define printd(x...) printk(x)
-#define printd(x...) do { } while(0)
-
/*
* Note:
* The kernel provides one architecture bit PG_arch_1 in the page flags that
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index a14df5aa98c8..8b9b6f44bb06 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -25,8 +25,6 @@
DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST;
void bad_page_fault(struct pt_regs*, unsigned long, int);
-#undef DEBUG_PAGE_FAULT
-
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
@@ -68,10 +66,10 @@ void do_page_fault(struct pt_regs *regs)
exccause == EXCCAUSE_ITLB_MISS ||
exccause == EXCCAUSE_FETCH_CACHE_ATTRIBUTE) ? 1 : 0;
-#ifdef DEBUG_PAGE_FAULT
- printk("[%s:%d:%08x:%d:%08x:%s%s]\n", current->comm, current->pid,
- address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
-#endif
+ pr_debug("[%s:%d:%08x:%d:%08lx:%s%s]\n",
+ current->comm, current->pid,
+ address, exccause, regs->pc,
+ is_write ? "w" : "", is_exec ? "x" : "");
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
@@ -247,10 +245,8 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
/* Are we prepared to handle this kernel fault? */
if ((entry = search_exception_tables(regs->pc)) != NULL) {
-#ifdef DEBUG_PAGE_FAULT
- printk(KERN_DEBUG "%s: Exception at pc=%#010lx (%lx)\n",
- current->comm, regs->pc, entry->fixup);
-#endif
+ pr_debug("%s: Exception at pc=%#010lx (%lx)\n",
+ current->comm, regs->pc, entry->fixup);
current->thread.bad_uaddr = address;
regs->pc = entry->fixup;
return;
@@ -259,9 +255,9 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
/* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
- printk(KERN_ALERT "Unable to handle kernel paging request at virtual "
- "address %08lx\n pc = %08lx, ra = %08lx\n",
- address, regs->pc, regs->areg[0]);
+ pr_alert("Unable to handle kernel paging request at virtual "
+ "address %08lx\n pc = %08lx, ra = %08lx\n",
+ address, regs->pc, regs->areg[0]);
die("Oops", regs, sig);
do_exit(sig);
}
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 720fe4e8b497..d776ec0d7b22 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -100,29 +100,51 @@ void __init mem_init(void)
mem_init_print_info(NULL);
pr_info("virtual kernel memory layout:\n"
+#ifdef CONFIG_KASAN
+ " kasan : 0x%08lx - 0x%08lx (%5lu MB)\n"
+#endif
+#ifdef CONFIG_MMU
+ " vmalloc : 0x%08lx - 0x%08lx (%5lu MB)\n"
+#endif
#ifdef CONFIG_HIGHMEM
" pkmap : 0x%08lx - 0x%08lx (%5lu kB)\n"
" fixmap : 0x%08lx - 0x%08lx (%5lu kB)\n"
#endif
-#ifdef CONFIG_MMU
- " vmalloc : 0x%08lx - 0x%08lx (%5lu MB)\n"
+ " lowmem : 0x%08lx - 0x%08lx (%5lu MB)\n"
+ " .text : 0x%08lx - 0x%08lx (%5lu kB)\n"
+ " .rodata : 0x%08lx - 0x%08lx (%5lu kB)\n"
+ " .data : 0x%08lx - 0x%08lx (%5lu kB)\n"
+ " .init : 0x%08lx - 0x%08lx (%5lu kB)\n"
+ " .bss : 0x%08lx - 0x%08lx (%5lu kB)\n",
+#ifdef CONFIG_KASAN
+ KASAN_SHADOW_START, KASAN_SHADOW_START + KASAN_SHADOW_SIZE,
+ KASAN_SHADOW_SIZE >> 20,
#endif
- " lowmem : 0x%08lx - 0x%08lx (%5lu MB)\n",
+#ifdef CONFIG_MMU
+ VMALLOC_START, VMALLOC_END,
+ (VMALLOC_END - VMALLOC_START) >> 20,
#ifdef CONFIG_HIGHMEM
PKMAP_BASE, PKMAP_BASE + LAST_PKMAP * PAGE_SIZE,
(LAST_PKMAP*PAGE_SIZE) >> 10,
FIXADDR_START, FIXADDR_TOP,
(FIXADDR_TOP - FIXADDR_START) >> 10,
#endif
-#ifdef CONFIG_MMU
- VMALLOC_START, VMALLOC_END,
- (VMALLOC_END - VMALLOC_START) >> 20,
PAGE_OFFSET, PAGE_OFFSET +
(max_low_pfn - min_low_pfn) * PAGE_SIZE,
#else
min_low_pfn * PAGE_SIZE, max_low_pfn * PAGE_SIZE,
#endif
- ((max_low_pfn - min_low_pfn) * PAGE_SIZE) >> 20);
+ ((max_low_pfn - min_low_pfn) * PAGE_SIZE) >> 20,
+ (unsigned long)_text, (unsigned long)_etext,
+ (unsigned long)(_etext - _text) >> 10,
+ (unsigned long)__start_rodata, (unsigned long)_sdata,
+ (unsigned long)(_sdata - __start_rodata) >> 10,
+ (unsigned long)_sdata, (unsigned long)_edata,
+ (unsigned long)(_edata - _sdata) >> 10,
+ (unsigned long)__init_begin, (unsigned long)__init_end,
+ (unsigned long)(__init_end - __init_begin) >> 10,
+ (unsigned long)__bss_start, (unsigned long)__bss_stop,
+ (unsigned long)(__bss_stop - __bss_start) >> 10);
}
#ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c
new file mode 100644
index 000000000000..6b532b6bd785
--- /dev/null
+++ b/arch/xtensa/mm/kasan_init.c
@@ -0,0 +1,95 @@
+/*
+ * Xtensa KASAN shadow map initialization
+ *
+ * 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) 2017 Cadence Design Systems Inc.
+ */
+
+#include <linux/bootmem.h>
+#include <linux/init_task.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <asm/initialize_mmu.h>
+#include <asm/tlbflush.h>
+#include <asm/traps.h>
+
+void __init kasan_early_init(void)
+{
+ unsigned long vaddr = KASAN_SHADOW_START;
+ pgd_t *pgd = pgd_offset_k(vaddr);
+ pmd_t *pmd = pmd_offset(pgd, vaddr);
+ int i;
+
+ for (i = 0; i < PTRS_PER_PTE; ++i)
+ set_pte(kasan_zero_pte + i,
+ mk_pte(virt_to_page(kasan_zero_page), PAGE_KERNEL));
+
+ for (vaddr = 0; vaddr < KASAN_SHADOW_SIZE; vaddr += PMD_SIZE, ++pmd) {
+ BUG_ON(!pmd_none(*pmd));
+ set_pmd(pmd, __pmd((unsigned long)kasan_zero_pte));
+ }
+ early_trap_init();
+}
+
+static void __init populate(void *start, void *end)
+{
+ unsigned long n_pages = (end - start) / PAGE_SIZE;
+ unsigned long n_pmds = n_pages / PTRS_PER_PTE;
+ unsigned long i, j;
+ unsigned long vaddr = (unsigned long)start;
+ pgd_t *pgd = pgd_offset_k(vaddr);
+ pmd_t *pmd = pmd_offset(pgd, vaddr);
+ pte_t *pte = memblock_virt_alloc(n_pages * sizeof(pte_t), PAGE_SIZE);
+
+ pr_debug("%s: %p - %p\n", __func__, start, end);
+
+ for (i = j = 0; i < n_pmds; ++i) {
+ int k;
+
+ for (k = 0; k < PTRS_PER_PTE; ++k, ++j) {
+ phys_addr_t phys =
+ memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
+ MEMBLOCK_ALLOC_ANYWHERE);
+
+ set_pte(pte + j, pfn_pte(PHYS_PFN(phys), PAGE_KERNEL));
+ }
+ }
+
+ for (i = 0; i < n_pmds ; ++i, pte += PTRS_PER_PTE)
+ set_pmd(pmd + i, __pmd((unsigned long)pte));
+
+ local_flush_tlb_all();
+ memset(start, 0, end - start);
+}
+
+void __init kasan_init(void)
+{
+ int i;
+
+ BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_START -
+ (KASAN_START_VADDR >> KASAN_SHADOW_SCALE_SHIFT));
+ BUILD_BUG_ON(VMALLOC_START < KASAN_START_VADDR);
+
+ /*
+ * Replace shadow map pages that cover addresses from VMALLOC area
+ * start to the end of KSEG with clean writable pages.
+ */
+ populate(kasan_mem_to_shadow((void *)VMALLOC_START),
+ kasan_mem_to_shadow((void *)XCHAL_KSEG_BYPASS_VADDR));
+
+ /* Write protect kasan_zero_page and zero-initialize it again. */
+ for (i = 0; i < PTRS_PER_PTE; ++i)
+ set_pte(kasan_zero_pte + i,
+ mk_pte(virt_to_page(kasan_zero_page), PAGE_KERNEL_RO));
+
+ local_flush_tlb_all();
+ memset(kasan_zero_page, 0, PAGE_SIZE);
+
+ /* At this point kasan is fully initialized. Enable error messages. */
+ current->kasan_depth = 0;
+ pr_info("KernelAddressSanitizer initialized\n");
+}
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 358d748d9083..9d1ecfc53670 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -56,7 +56,6 @@ static void __init fixedrange_init(void)
void __init paging_init(void)
{
- memset(swapper_pg_dir, 0, PAGE_SIZE);
#ifdef CONFIG_HIGHMEM
fixedrange_init();
pkmap_page_table = init_pmd(PKMAP_BASE, LAST_PKMAP);
@@ -82,6 +81,23 @@ void init_mmu(void)
set_itlbcfg_register(0);
set_dtlbcfg_register(0);
#endif
+ init_kio();
+ local_flush_tlb_all();
+
+ /* Set rasid register to a known value. */
+
+ set_rasid_register(ASID_INSERT(ASID_USER_FIRST));
+
+ /* Set PTEVADDR special register to the start of the page
+ * table, which is in kernel mappable space (ie. not
+ * statically mapped). This register's value is undefined on
+ * reset.
+ */
+ set_ptevaddr_register(XCHAL_PAGE_TABLE_VADDR);
+}
+
+void init_kio(void)
+{
#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
/*
* Update the IO area mapping in case xtensa_kio_paddr has changed
@@ -95,17 +111,4 @@ void init_mmu(void)
write_itlb_entry(__pte(xtensa_kio_paddr + CA_BYPASS),
XCHAL_KIO_BYPASS_VADDR + 6);
#endif
-
- local_flush_tlb_all();
-
- /* Set rasid register to a known value. */
-
- set_rasid_register(ASID_INSERT(ASID_USER_FIRST));
-
- /* Set PTEVADDR special register to the start of the page
- * table, which is in kernel mappable space (ie. not
- * statically mapped). This register's value is undefined on
- * reset.
- */
- set_ptevaddr_register(PGTABLE_START);
}
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index 35c822286bbe..59153d0aa890 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -95,10 +95,8 @@ void local_flush_tlb_range(struct vm_area_struct *vma,
if (mm->context.asid[cpu] == NO_CONTEXT)
return;
-#if 0
- printk("[tlbrange<%02lx,%08lx,%08lx>]\n",
- (unsigned long)mm->context.asid[cpu], start, end);
-#endif
+ pr_debug("[tlbrange<%02lx,%08lx,%08lx>]\n",
+ (unsigned long)mm->context.asid[cpu], start, end);
local_irq_save(flags);
if (end-start + (PAGE_SIZE-1) <= _TLB_ENTRIES << PAGE_SHIFT) {
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 464c2684c4f1..92f567f9a21e 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -185,7 +185,7 @@ int __init rs_init(void)
serial_driver = alloc_tty_driver(SERIAL_MAX_NUM_LINES);
- printk ("%s %s\n", serial_name, serial_version);
+ pr_info("%s %s\n", serial_name, serial_version);
/* Initialize the tty_driver structure */
@@ -214,7 +214,7 @@ static __exit void rs_exit(void)
int error;
if ((error = tty_unregister_driver(serial_driver)))
- printk("ISS_SERIAL: failed to unregister serial driver (%d)\n",
+ pr_err("ISS_SERIAL: failed to unregister serial driver (%d)\n",
error);
put_tty_driver(serial_driver);
tty_port_destroy(&serial_port);
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 6363b18e5b8c..d027dddc41ca 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -16,6 +16,8 @@
*
*/
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
#include <linux/list.h>
#include <linux/irq.h>
#include <linux/spinlock.h>
@@ -606,8 +608,6 @@ struct iss_net_init {
* those fields. They will be later initialized in iss_net_init.
*/
-#define ERR KERN_ERR "iss_net_setup: "
-
static int __init iss_net_setup(char *str)
{
struct iss_net_private *device = NULL;
@@ -619,14 +619,14 @@ static int __init iss_net_setup(char *str)
end = strchr(str, '=');
if (!end) {
- printk(ERR "Expected '=' after device number\n");
+ pr_err("Expected '=' after device number\n");
return 1;
}
*end = 0;
rc = kstrtouint(str, 0, &n);
*end = '=';
if (rc < 0) {
- printk(ERR "Failed to parse '%s'\n", str);
+ pr_err("Failed to parse '%s'\n", str);
return 1;
}
str = end;
@@ -642,13 +642,13 @@ static int __init iss_net_setup(char *str)
spin_unlock(&devices_lock);
if (device && device->index == n) {
- printk(ERR "Device %u already configured\n", n);
+ pr_err("Device %u already configured\n", n);
return 1;
}
new = alloc_bootmem(sizeof(*new));
if (new == NULL) {
- printk(ERR "Alloc_bootmem failed\n");
+ pr_err("Alloc_bootmem failed\n");
return 1;
}
@@ -660,8 +660,6 @@ static int __init iss_net_setup(char *str)
return 1;
}
-#undef ERR
-
__setup("eth", iss_net_setup);
/*