summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig45
-rw-r--r--arch/alpha/include/asm/uaccess.h19
-rw-r--r--arch/arc/Kconfig6
-rw-r--r--arch/arc/Makefile7
-rw-r--r--arch/arc/boot/dts/abilis_tb100_dvk.dts1
-rw-r--r--arch/arc/boot/dts/abilis_tb101_dvk.dts1
-rw-r--r--arch/arc/boot/dts/axs101.dts1
-rw-r--r--arch/arc/boot/dts/axs103.dts1
-rw-r--r--arch/arc/boot/dts/axs103_idu.dts1
-rw-r--r--arch/arc/boot/dts/nsim_700.dts1
-rw-r--r--arch/arc/boot/dts/nsim_hs.dts1
-rw-r--r--arch/arc/boot/dts/nsim_hs_idu.dts1
-rw-r--r--arch/arc/boot/dts/nsimosci.dts1
-rw-r--r--arch/arc/boot/dts/nsimosci_hs.dts1
-rw-r--r--arch/arc/boot/dts/nsimosci_hs_idu.dts1
-rw-r--r--arch/arc/boot/dts/vdk_hs38.dts1
-rw-r--r--arch/arc/boot/dts/vdk_hs38_smp.dts1
-rw-r--r--arch/arc/boot/dts/zebu_hs.dts69
-rw-r--r--arch/arc/boot/dts/zebu_hs_idu.dts85
-rw-r--r--arch/arc/configs/axs101_defconfig3
-rw-r--r--arch/arc/configs/axs103_defconfig3
-rw-r--r--arch/arc/configs/axs103_smp_defconfig3
-rw-r--r--arch/arc/configs/nsim_hs_defconfig5
-rw-r--r--arch/arc/configs/nsim_hs_smp_defconfig3
-rw-r--r--arch/arc/configs/zebu_hs_defconfig86
-rw-r--r--arch/arc/configs/zebu_hs_smp_defconfig89
-rw-r--r--arch/arc/include/asm/arcregs.h10
-rw-r--r--arch/arc/include/asm/atomic.h263
-rw-r--r--arch/arc/include/asm/cache.h2
-rw-r--r--arch/arc/include/asm/dwarf.h38
-rw-r--r--arch/arc/include/asm/elf.h3
-rw-r--r--arch/arc/include/asm/irqflags-arcv2.h2
-rw-r--r--arch/arc/include/asm/linkage.h12
-rw-r--r--arch/arc/include/asm/perf_event.h3
-rw-r--r--arch/arc/include/asm/uaccess.h11
-rw-r--r--arch/arc/kernel/ctx_sw_asm.S3
-rw-r--r--arch/arc/kernel/entry.S24
-rw-r--r--arch/arc/kernel/intc-arcv2.c2
-rw-r--r--arch/arc/kernel/module.c19
-rw-r--r--arch/arc/kernel/perf_event.c6
-rw-r--r--arch/arc/kernel/setup.c5
-rw-r--r--arch/arc/kernel/unwind.c24
-rw-r--r--arch/arc/kernel/vmlinux.lds.S21
-rw-r--r--arch/arc/lib/memcmp.S4
-rw-r--r--arch/arc/lib/memcpy-700.S4
-rw-r--r--arch/arc/lib/memcpy-archs.S4
-rw-r--r--arch/arc/lib/memset-archs.S8
-rw-r--r--arch/arc/lib/memset.S8
-rw-r--r--arch/arc/lib/strchr-700.S4
-rw-r--r--arch/arc/lib/strcmp-archs.S4
-rw-r--r--arch/arc/lib/strcmp.S4
-rw-r--r--arch/arc/lib/strcpy-700.S4
-rw-r--r--arch/arc/lib/strlen.S4
-rw-r--r--arch/arc/mm/cache.c23
-rw-r--r--arch/arc/mm/ioremap.c2
-rw-r--r--arch/arc/plat-sim/platform.c1
-rw-r--r--arch/arm/Kconfig2
-rw-r--r--arch/arm/boot/compressed/head.S2
-rw-r--r--arch/arm/boot/dts/am335x-baltos.dtsi2
-rw-r--r--arch/arm/boot/dts/am335x-igep0033.dtsi2
-rw-r--r--arch/arm/boot/dts/am335x-phycore-som.dtsi2
-rw-r--r--arch/arm/boot/dts/armada-388-clearfog.dts8
-rw-r--r--arch/arm/boot/dts/bcm2835-rpi.dtsi1
-rw-r--r--arch/arm/boot/dts/bcm283x.dtsi3
-rw-r--r--arch/arm/boot/dts/exynos5410-odroidxu.dts3
-rw-r--r--arch/arm/boot/dts/imx6qdl.dtsi2
-rw-r--r--arch/arm/boot/dts/imx6sx-sabreauto.dts2
-rw-r--r--arch/arm/boot/dts/imx7d-sdb.dts2
-rw-r--r--arch/arm/boot/dts/kirkwood-ib62x0.dts2
-rw-r--r--arch/arm/boot/dts/kirkwood-openrd.dtsi4
-rw-r--r--arch/arm/boot/dts/logicpd-som-lv.dtsi11
-rw-r--r--arch/arm/boot/dts/logicpd-torpedo-som.dtsi1
-rw-r--r--arch/arm/boot/dts/omap3-overo-base.dtsi4
-rw-r--r--arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi2
-rw-r--r--arch/arm/boot/dts/omap3-overo-tobi-common.dtsi2
-rw-r--r--arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi3
-rw-r--r--arch/arm/boot/dts/stih407-family.dtsi10
-rw-r--r--arch/arm/boot/dts/stih410.dtsi12
-rw-r--r--arch/arm/boot/dts/stm32f429.dtsi8
-rw-r--r--arch/arm/boot/dts/sun5i-a13.dtsi2
-rw-r--r--arch/arm/boot/dts/tegra114-dalmore.dts2
-rw-r--r--arch/arm/boot/dts/tegra114-roth.dts2
-rw-r--r--arch/arm/boot/dts/tegra114-tn7.dts2
-rw-r--r--arch/arm/boot/dts/tegra124-jetson-tk1.dts4
-rw-r--r--arch/arm/common/bL_switcher_dummy_if.c14
-rw-r--r--arch/arm/common/locomo.c5
-rw-r--r--arch/arm/common/sa1111.c32
-rw-r--r--arch/arm/configs/exynos_defconfig2
-rw-r--r--arch/arm/configs/keystone_defconfig1
-rw-r--r--arch/arm/configs/multi_v7_defconfig4
-rw-r--r--arch/arm/crypto/aes-ce-glue.c2
-rw-r--r--arch/arm/include/asm/arch_gicv3.h6
-rw-r--r--arch/arm/include/asm/clocksource.h8
-rw-r--r--arch/arm/include/asm/dma-mapping.h2
-rw-r--r--arch/arm/include/asm/pgtable-2level-hwdef.h1
-rw-r--r--arch/arm/include/asm/pgtable-3level-hwdef.h1
-rw-r--r--arch/arm/kernel/devtree.c14
-rw-r--r--arch/arm/kernel/ftrace.c2
-rw-r--r--arch/arm/kernel/hyp-stub.S13
-rw-r--r--arch/arm/kernel/perf_event_v7.c47
-rw-r--r--arch/arm/kernel/vdso.c2
-rw-r--r--arch/arm/kvm/arm.c2
-rw-r--r--arch/arm/kvm/mmu.c4
-rw-r--r--arch/arm/mach-exynos/suspend.c6
-rw-r--r--arch/arm/mach-imx/mach-imx6ul.c1
-rw-r--r--arch/arm/mach-imx/pm-imx6.c4
-rw-r--r--arch/arm/mach-omap2/cm33xx.c6
-rw-r--r--arch/arm/mach-omap2/cminst44xx.c6
-rw-r--r--arch/arm/mach-omap2/omap-wakeupgen.c35
-rw-r--r--arch/arm/mach-omap2/omap_hwmod.c8
-rw-r--r--arch/arm/mach-omap2/omap_hwmod.h4
-rw-r--r--arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c2
-rw-r--r--arch/arm/mach-omap2/omap_hwmod_3xxx_data.c12
-rw-r--r--arch/arm/mach-pxa/lubbock.c14
-rw-r--r--arch/arm/mach-sa1100/clock.c5
-rw-r--r--arch/arm/mach-sa1100/generic.c4
-rw-r--r--arch/arm/mach-sa1100/generic.h2
-rw-r--r--arch/arm/mach-shmobile/platsmp-scu.c26
-rw-r--r--arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c62
-rw-r--r--arch/arm/mm/mmu.c2
-rw-r--r--arch/arm/mm/proc-v7.S1
-rw-r--r--arch/arm/xen/enlighten.c7
-rw-r--r--arch/arm64/Kconfig34
-rw-r--r--arch/arm64/Kconfig.debug10
-rw-r--r--arch/arm64/Kconfig.platforms2
-rw-r--r--arch/arm64/Makefile10
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi8
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi8
-rw-r--r--arch/arm64/boot/dts/apm/apm-storm.dtsi8
l---------arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi1
-rw-r--r--arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts4
-rw-r--r--arch/arm64/boot/dts/broadcom/bcm2837.dtsi2
l---------arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi1
l---------arch/arm64/boot/dts/broadcom/bcm283x.dtsi1
-rw-r--r--arch/arm64/boot/dts/broadcom/ns2.dtsi8
-rw-r--r--arch/arm64/boot/dts/cavium/thunder-88xx.dtsi8
-rw-r--r--arch/arm64/boot/dts/exynos/exynos7.dtsi8
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi8
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi8
-rw-r--r--arch/arm64/boot/dts/marvell/armada-ap806.dtsi8
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi8
-rw-r--r--arch/arm64/boot/dts/xilinx/zynqmp.dtsi8
-rw-r--r--arch/arm64/crypto/aes-glue.c2
-rw-r--r--arch/arm64/include/asm/Kbuild5
-rw-r--r--arch/arm64/include/asm/acpi.h8
-rw-r--r--arch/arm64/include/asm/alternative.h70
-rw-r--r--arch/arm64/include/asm/arch_gicv3.h6
-rw-r--r--arch/arm64/include/asm/arch_timer.h82
-rw-r--r--arch/arm64/include/asm/assembler.h53
-rw-r--r--arch/arm64/include/asm/atomic_lse.h64
-rw-r--r--arch/arm64/include/asm/barrier.h3
-rw-r--r--arch/arm64/include/asm/cacheflush.h3
-rw-r--r--arch/arm64/include/asm/clocksource.h8
-rw-r--r--arch/arm64/include/asm/cmpxchg.h4
-rw-r--r--arch/arm64/include/asm/cpufeature.h42
-rw-r--r--arch/arm64/include/asm/cputype.h6
-rw-r--r--arch/arm64/include/asm/dcc.h14
-rw-r--r--arch/arm64/include/asm/debug-monitors.h2
-rw-r--r--arch/arm64/include/asm/esr.h84
-rw-r--r--arch/arm64/include/asm/hw_breakpoint.h15
-rw-r--r--arch/arm64/include/asm/insn.h11
-rw-r--r--arch/arm64/include/asm/io.h19
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h10
-rw-r--r--arch/arm64/include/asm/memory.h8
-rw-r--r--arch/arm64/include/asm/mmu_context.h36
-rw-r--r--arch/arm64/include/asm/percpu.h8
-rw-r--r--arch/arm64/include/asm/pgtable-hwdef.h1
-rw-r--r--arch/arm64/include/asm/pgtable-prot.h5
-rw-r--r--arch/arm64/include/asm/pgtable.h20
-rw-r--r--arch/arm64/include/asm/processor.h2
-rw-r--r--arch/arm64/include/asm/sections.h30
-rw-r--r--arch/arm64/include/asm/spinlock.h37
-rw-r--r--arch/arm64/include/asm/suspend.h3
-rw-r--r--arch/arm64/include/asm/sysreg.h44
-rw-r--r--arch/arm64/include/asm/system_misc.h6
-rw-r--r--arch/arm64/include/asm/thread_info.h3
-rw-r--r--arch/arm64/include/asm/tlbflush.h34
-rw-r--r--arch/arm64/include/asm/traps.h6
-rw-r--r--arch/arm64/include/asm/virt.h15
-rw-r--r--arch/arm64/kernel/Makefile2
-rw-r--r--arch/arm64/kernel/acpi.c11
-rw-r--r--arch/arm64/kernel/acpi_numa.c4
-rw-r--r--arch/arm64/kernel/alternative.c28
-rw-r--r--arch/arm64/kernel/asm-offsets.c2
-rw-r--r--arch/arm64/kernel/cacheinfo.c8
-rw-r--r--arch/arm64/kernel/cpu_errata.c26
-rw-r--r--arch/arm64/kernel/cpu_ops.c3
-rw-r--r--arch/arm64/kernel/cpufeature.c137
-rw-r--r--arch/arm64/kernel/cpuinfo.c2
-rw-r--r--arch/arm64/kernel/debug-monitors.c48
-rw-r--r--arch/arm64/kernel/entry-ftrace.S2
-rw-r--r--arch/arm64/kernel/entry.S24
-rw-r--r--arch/arm64/kernel/fpsimd.c22
-rw-r--r--arch/arm64/kernel/ftrace.c2
-rw-r--r--arch/arm64/kernel/head.S200
-rw-r--r--arch/arm64/kernel/hibernate-asm.S6
-rw-r--r--arch/arm64/kernel/hibernate.c118
-rw-r--r--arch/arm64/kernel/hw_breakpoint.c48
-rw-r--r--arch/arm64/kernel/insn.c15
-rw-r--r--arch/arm64/kernel/kaslr.c3
-rw-r--r--arch/arm64/kernel/kgdb.c36
-rw-r--r--arch/arm64/kernel/perf_event.c100
-rw-r--r--arch/arm64/kernel/probes/decode-insn.c48
-rw-r--r--arch/arm64/kernel/probes/kprobes.c36
-rw-r--r--arch/arm64/kernel/process.c14
-rw-r--r--arch/arm64/kernel/relocate_kernel.S2
-rw-r--r--arch/arm64/kernel/setup.c11
-rw-r--r--arch/arm64/kernel/signal.c36
-rw-r--r--arch/arm64/kernel/sleep.S29
-rw-r--r--arch/arm64/kernel/smp.c28
-rw-r--r--arch/arm64/kernel/smp_spin_table.c3
-rw-r--r--arch/arm64/kernel/stacktrace.c26
-rw-r--r--arch/arm64/kernel/suspend.c10
-rw-r--r--arch/arm64/kernel/sys_compat.c2
-rw-r--r--arch/arm64/kernel/traps.c97
-rw-r--r--arch/arm64/kernel/vdso.c36
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S19
-rw-r--r--arch/arm64/kvm/hyp.S6
-rw-r--r--arch/arm64/kvm/sys_regs.c31
-rw-r--r--arch/arm64/kvm/sys_regs_generic_v8.c6
-rw-r--r--arch/arm64/lib/copy_page.S13
-rw-r--r--arch/arm64/mm/cache.S82
-rw-r--r--arch/arm64/mm/dma-mapping.c9
-rw-r--r--arch/arm64/mm/extable.c2
-rw-r--r--arch/arm64/mm/fault.c7
-rw-r--r--arch/arm64/mm/flush.c2
-rw-r--r--arch/arm64/mm/init.c15
-rw-r--r--arch/arm64/mm/mm.h2
-rw-r--r--arch/arm64/mm/mmu.c15
-rw-r--r--arch/arm64/mm/numa.c115
-rw-r--r--arch/arm64/mm/pageattr.c41
-rw-r--r--arch/arm64/mm/pgd.c2
-rw-r--r--arch/arm64/mm/proc.S13
-rw-r--r--arch/avr32/include/asm/uaccess.h11
-rw-r--r--arch/avr32/kernel/avr32_ksyms.c2
-rw-r--r--arch/avr32/lib/copy_user.S8
-rw-r--r--arch/blackfin/include/asm/uaccess.h9
-rw-r--r--arch/blackfin/kernel/ftrace-entry.S4
-rw-r--r--arch/blackfin/kernel/ftrace.c2
-rw-r--r--arch/blackfin/mach-bf561/coreb.c13
-rw-r--r--arch/cris/include/asm/uaccess.h71
-rw-r--r--arch/frv/include/asm/uaccess.h12
-rw-r--r--arch/hexagon/include/asm/uaccess.h3
-rw-r--r--arch/ia64/include/asm/thread_info.h2
-rw-r--r--arch/ia64/include/asm/uaccess.h33
-rw-r--r--arch/ia64/kernel/acpi.c2
-rw-r--r--arch/ia64/kernel/mca.c36
-rw-r--r--arch/m32r/include/asm/uaccess.h2
-rw-r--r--arch/m68k/amiga/config.c2
-rw-r--r--arch/m68k/atari/config.c2
-rw-r--r--arch/m68k/configs/amiga_defconfig3
-rw-r--r--arch/m68k/configs/apollo_defconfig3
-rw-r--r--arch/m68k/configs/atari_defconfig3
-rw-r--r--arch/m68k/configs/bvme6000_defconfig3
-rw-r--r--arch/m68k/configs/hp300_defconfig3
-rw-r--r--arch/m68k/configs/mac_defconfig3
-rw-r--r--arch/m68k/configs/multi_defconfig3
-rw-r--r--arch/m68k/configs/mvme147_defconfig3
-rw-r--r--arch/m68k/configs/mvme16x_defconfig3
-rw-r--r--arch/m68k/configs/q40_defconfig3
-rw-r--r--arch/m68k/configs/sun3_defconfig3
-rw-r--r--arch/m68k/configs/sun3x_defconfig3
-rw-r--r--arch/m68k/kernel/setup_mm.c2
-rw-r--r--arch/m68k/kernel/signal.c2
-rw-r--r--arch/m68k/mac/config.c2
-rw-r--r--arch/m68k/q40/config.c2
-rw-r--r--arch/metag/include/asm/uaccess.h3
-rw-r--r--arch/microblaze/include/asm/uaccess.h11
-rw-r--r--arch/microblaze/kernel/ftrace.c2
-rw-r--r--arch/mips/Kconfig1
-rw-r--r--arch/mips/Kconfig.debug36
-rw-r--r--arch/mips/Makefile4
-rw-r--r--arch/mips/ath79/clock.c2
-rw-r--r--arch/mips/cavium-octeon/octeon-irq.c6
-rw-r--r--arch/mips/cavium-octeon/octeon-platform.c2
-rw-r--r--arch/mips/cavium-octeon/smp.c24
-rw-r--r--arch/mips/dec/int-handler.S40
-rw-r--r--arch/mips/include/asm/asmmacro.h1
-rw-r--r--arch/mips/include/asm/mach-cavium-octeon/mangle-port.h4
-rw-r--r--arch/mips/include/asm/mach-paravirt/kernel-entry-init.h2
-rw-r--r--arch/mips/include/asm/mips-cm.h11
-rw-r--r--arch/mips/include/asm/mipsregs.h2
-rw-r--r--arch/mips/include/asm/uaccess.h3
-rw-r--r--arch/mips/include/asm/uprobes.h1
-rw-r--r--arch/mips/kernel/cpu-probe.c53
-rw-r--r--arch/mips/kernel/ftrace.c4
-rw-r--r--arch/mips/kernel/genex.S3
-rw-r--r--arch/mips/kernel/mips-r2-to-r6-emul.c2
-rw-r--r--arch/mips/kernel/process.c8
-rw-r--r--arch/mips/kernel/setup.c9
-rw-r--r--arch/mips/kernel/smp-cps.c2
-rw-r--r--arch/mips/kernel/smp.c7
-rw-r--r--arch/mips/kernel/uprobes.c27
-rw-r--r--arch/mips/kernel/vdso.c8
-rw-r--r--arch/mips/loongson64/loongson-3/smp.c34
-rw-r--r--arch/mips/math-emu/dsemul.c1
-rw-r--r--arch/mips/mm/c-r4k.c2
-rw-r--r--arch/mips/mm/init.c16
-rw-r--r--arch/mips/mti-malta/malta-setup.c8
-rw-r--r--arch/mn10300/include/asm/uaccess.h1
-rw-r--r--arch/mn10300/lib/usercopy.c4
-rwxr-xr-xarch/nios2/boot/dts/10m50_devboard.dts1
-rw-r--r--arch/nios2/include/asm/uaccess.h13
-rw-r--r--arch/openrisc/include/asm/uaccess.h35
-rw-r--r--arch/parisc/include/asm/uaccess.h5
-rw-r--r--arch/parisc/kernel/ftrace.c2
-rw-r--r--arch/powerpc/include/asm/cpu_has_feature.h2
-rw-r--r--arch/powerpc/include/asm/uaccess.h38
-rw-r--r--arch/powerpc/kernel/ftrace.c3
-rw-r--r--arch/powerpc/kernel/idle_book3s.S10
-rw-r--r--arch/powerpc/lib/checksum_32.S7
-rw-r--r--arch/powerpc/mm/mmu_context_nohash.c56
-rw-r--r--arch/powerpc/mm/slb_low.S7
-rw-r--r--arch/powerpc/platforms/powermac/smp.c50
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda.c55
-rw-r--r--arch/powerpc/platforms/pseries/setup.c2
-rw-r--r--arch/powerpc/sysdev/xics/icp-opal.c12
-rw-r--r--arch/s390/include/asm/uaccess.h8
-rw-r--r--arch/s390/kernel/ftrace.c3
-rw-r--r--arch/s390/kvm/kvm-s390.c10
-rw-r--r--arch/s390/kvm/vsie.c2
-rw-r--r--arch/s390/mm/fault.c30
-rw-r--r--arch/score/include/asm/uaccess.h46
-rw-r--r--arch/sh/include/asm/atomic-llsc.h2
-rw-r--r--arch/sh/include/asm/uaccess.h5
-rw-r--r--arch/sh/include/asm/uaccess_64.h1
-rw-r--r--arch/sh/kernel/cpu/sh4a/smp-shx3.c26
-rw-r--r--arch/sh/kernel/ftrace.c2
-rw-r--r--arch/sparc/Kconfig1
-rw-r--r--arch/sparc/include/asm/ftrace.h4
-rw-r--r--arch/sparc/include/asm/page_64.h1
-rw-r--r--arch/sparc/include/asm/smp_64.h2
-rw-r--r--arch/sparc/include/asm/uaccess_32.h13
-rw-r--r--arch/sparc/include/asm/uaccess_64.h7
-rw-r--r--arch/sparc/kernel/ftrace.c2
-rw-r--r--arch/sparc/kernel/setup_64.c26
-rw-r--r--arch/sparc/kernel/smp_32.c2
-rw-r--r--arch/sparc/kernel/smp_64.c14
-rw-r--r--arch/sparc/mm/fault_64.c1
-rw-r--r--arch/sparc/mm/init_64.c22
-rw-r--r--arch/sparc/mm/tlb.c35
-rw-r--r--arch/sparc/mm/tsb.c18
-rw-r--r--arch/tile/kernel/ftrace.c2
-rw-r--r--arch/um/drivers/harddog_kern.c25
-rw-r--r--arch/um/kernel/skas/syscall.c10
-rw-r--r--arch/x86/Kconfig18
-rw-r--r--arch/x86/boot/compressed/eboot.c174
-rw-r--r--arch/x86/boot/compressed/head_32.S6
-rw-r--r--arch/x86/boot/compressed/head_64.S8
-rw-r--r--arch/x86/entry/common.c24
-rw-r--r--arch/x86/entry/entry_32.S68
-rw-r--r--arch/x86/entry/entry_64.S155
-rw-r--r--arch/x86/entry/vdso/vdso2c.h2
-rw-r--r--arch/x86/entry/vdso/vma.c175
-rw-r--r--arch/x86/events/amd/core.c4
-rw-r--r--arch/x86/events/amd/uncore.c22
-rw-r--r--arch/x86/events/core.c60
-rw-r--r--arch/x86/events/intel/bts.c126
-rw-r--r--arch/x86/events/intel/core.c46
-rw-r--r--arch/x86/events/intel/cqm.c9
-rw-r--r--arch/x86/events/intel/ds.c127
-rw-r--r--arch/x86/events/intel/lbr.c70
-rw-r--r--arch/x86/events/intel/pt.c42
-rw-r--r--arch/x86/events/intel/pt.h5
-rw-r--r--arch/x86/events/intel/rapl.c4
-rw-r--r--arch/x86/events/intel/uncore.c11
-rw-r--r--arch/x86/events/intel/uncore.h7
-rw-r--r--arch/x86/events/intel/uncore_snb.c2
-rw-r--r--arch/x86/events/intel/uncore_snbep.c626
-rw-r--r--arch/x86/events/perf_event.h13
-rw-r--r--arch/x86/ia32/ia32_signal.c2
-rw-r--r--arch/x86/include/asm/alternative.h8
-rw-r--r--arch/x86/include/asm/apic.h5
-rw-r--r--arch/x86/include/asm/cmpxchg.h44
-rw-r--r--arch/x86/include/asm/compat.h8
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/desc.h2
-rw-r--r--arch/x86/include/asm/e820.h6
-rw-r--r--arch/x86/include/asm/efi.h29
-rw-r--r--arch/x86/include/asm/fpu/signal.h6
-rw-r--r--arch/x86/include/asm/fpu/xstate.h3
-rw-r--r--arch/x86/include/asm/ftrace.h3
-rw-r--r--arch/x86/include/asm/hypervisor.h4
-rw-r--r--arch/x86/include/asm/intel-family.h4
-rw-r--r--arch/x86/include/asm/intel-mid.h2
-rw-r--r--arch/x86/include/asm/intel_scu_ipc.h2
-rw-r--r--arch/x86/include/asm/kaslr.h1
-rw-r--r--arch/x86/include/asm/kdebug.h2
-rw-r--r--arch/x86/include/asm/mce.h66
-rw-r--r--arch/x86/include/asm/mpspec.h3
-rw-r--r--arch/x86/include/asm/paravirt.h22
-rw-r--r--arch/x86/include/asm/paravirt_types.h8
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h4
-rw-r--r--arch/x86/include/asm/pmem.h5
-rw-r--r--arch/x86/include/asm/processor.h25
-rw-r--r--arch/x86/include/asm/realmode.h2
-rw-r--r--arch/x86/include/asm/rwsem.h2
-rw-r--r--arch/x86/include/asm/signal.h4
-rw-r--r--arch/x86/include/asm/smp.h3
-rw-r--r--arch/x86/include/asm/special_insns.h22
-rw-r--r--arch/x86/include/asm/spinlock.h174
-rw-r--r--arch/x86/include/asm/spinlock_types.h13
-rw-r--r--arch/x86/include/asm/stacktrace.h120
-rw-r--r--arch/x86/include/asm/string_64.h19
-rw-r--r--arch/x86/include/asm/switch_to.h164
-rw-r--r--arch/x86/include/asm/syscall.h20
-rw-r--r--arch/x86/include/asm/thread_info.h71
-rw-r--r--arch/x86/include/asm/traps.h6
-rw-r--r--arch/x86/include/asm/uaccess.h10
-rw-r--r--arch/x86/include/asm/unwind.h73
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h45
-rw-r--r--arch/x86/include/asm/vdso.h2
-rw-r--r--arch/x86/include/uapi/asm/mce.h2
-rw-r--r--arch/x86/include/uapi/asm/prctl.h6
-rw-r--r--arch/x86/kernel/Makefile6
-rw-r--r--arch/x86/kernel/acpi/Makefile1
-rw-r--r--arch/x86/kernel/acpi/boot.c35
-rw-r--r--arch/x86/kernel/acpi/cppc_msr.c58
-rw-r--r--arch/x86/kernel/acpi/sleep.c2
-rw-r--r--arch/x86/kernel/apic/apic.c97
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c22
-rw-r--r--arch/x86/kernel/apic/apic_noop.c2
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c5
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c4
-rw-r--r--arch/x86/kernel/apic/msi.c2
-rw-r--r--arch/x86/kernel/apic/probe_32.c6
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c40
-rw-r--r--arch/x86/kernel/asm-offsets.c7
-rw-r--r--arch/x86/kernel/asm-offsets_32.c5
-rw-r--r--arch/x86/kernel/asm-offsets_64.c5
-rw-r--r--arch/x86/kernel/cpu/common.c41
-rw-r--r--arch/x86/kernel/cpu/hypervisor.c11
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c44
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c204
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c13
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c52
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c4
-rw-r--r--arch/x86/kernel/cpu/mtrr/mtrr.h2
-rw-r--r--arch/x86/kernel/dumpstack.c258
-rw-r--r--arch/x86/kernel/dumpstack_32.c154
-rw-r--r--arch/x86/kernel/dumpstack_64.c318
-rw-r--r--arch/x86/kernel/e820.c155
-rw-r--r--arch/x86/kernel/early-quirks.c2
-rw-r--r--arch/x86/kernel/fpu/init.c1
-rw-r--r--arch/x86/kernel/ftrace.c2
-rw-r--r--arch/x86/kernel/head_32.S8
-rw-r--r--arch/x86/kernel/head_64.S12
-rw-r--r--arch/x86/kernel/hpet.c94
-rw-r--r--arch/x86/kernel/irq_64.c3
-rw-r--r--arch/x86/kernel/kexec-bzimage64.c4
-rw-r--r--arch/x86/kernel/kgdb.c8
-rw-r--r--arch/x86/kernel/kprobes/core.c2
-rw-r--r--arch/x86/kernel/kprobes/opt.c2
-rw-r--r--arch/x86/kernel/ksysfs.c2
-rw-r--r--arch/x86/kernel/kvm.c288
-rw-r--r--arch/x86/kernel/kvmclock.c3
-rw-r--r--arch/x86/kernel/mpparse.c3
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c7
-rw-r--r--arch/x86/kernel/paravirt.c3
-rw-r--r--arch/x86/kernel/paravirt_patch_32.c4
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c4
-rw-r--r--arch/x86/kernel/process.c42
-rw-r--r--arch/x86/kernel/process_32.c33
-rw-r--r--arch/x86/kernel/process_64.c52
-rw-r--r--arch/x86/kernel/ptrace.c14
-rw-r--r--arch/x86/kernel/quirks.c31
-rw-r--r--arch/x86/kernel/reboot.c2
-rw-r--r--arch/x86/kernel/resource.c4
-rw-r--r--arch/x86/kernel/setup.c37
-rw-r--r--arch/x86/kernel/setup_percpu.c4
-rw-r--r--arch/x86/kernel/signal.c22
-rw-r--r--arch/x86/kernel/signal_compat.c34
-rw-r--r--arch/x86/kernel/smpboot.c73
-rw-r--r--arch/x86/kernel/stacktrace.c79
-rw-r--r--arch/x86/kernel/tboot.c8
-rw-r--r--arch/x86/kernel/traps.c61
-rw-r--r--arch/x86/kernel/tsc.c12
-rw-r--r--arch/x86/kernel/unwind_frame.c93
-rw-r--r--arch/x86/kernel/unwind_guess.c43
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c2
-rw-r--r--arch/x86/kernel/x86_init.c6
-rw-r--r--arch/x86/kvm/ioapic.c8
-rw-r--r--arch/x86/kvm/pmu_amd.c4
-rw-r--r--arch/x86/kvm/svm.c2
-rw-r--r--arch/x86/kvm/vmx.c2
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--arch/x86/lib/memcpy_64.S6
-rw-r--r--arch/x86/mm/amdtopology.c22
-rw-r--r--arch/x86/mm/extable.c2
-rw-r--r--arch/x86/mm/fault.c34
-rw-r--r--arch/x86/mm/init.c4
-rw-r--r--arch/x86/mm/kaslr.c26
-rw-r--r--arch/x86/mm/numa.c27
-rw-r--r--arch/x86/mm/pageattr.c21
-rw-r--r--arch/x86/mm/pat.c17
-rw-r--r--arch/x86/mm/pat_rbtree.c4
-rw-r--r--arch/x86/mm/tlb.c15
-rw-r--r--arch/x86/oprofile/backtrace.c49
-rw-r--r--arch/x86/pci/fixup.c20
-rw-r--r--arch/x86/pci/pcbios.c7
-rw-r--r--arch/x86/platform/Makefile1
-rw-r--r--arch/x86/platform/atom/punit_atom_debug.c2
-rw-r--r--arch/x86/platform/efi/efi-bgrt.c13
-rw-r--r--arch/x86/platform/efi/efi.c200
-rw-r--r--arch/x86/platform/efi/efi_64.c25
-rw-r--r--arch/x86/platform/efi/quirks.c127
-rw-r--r--arch/x86/platform/intel-mid/device_libs/Makefile4
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c95
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c47
-rw-r--r--arch/x86/platform/intel-mid/intel-mid.c5
-rw-r--r--arch/x86/platform/intel-mid/pwr.c76
-rw-r--r--arch/x86/platform/mellanox/Makefile1
-rw-r--r--arch/x86/platform/mellanox/mlx-platform.c266
-rw-r--r--arch/x86/platform/uv/bios_uv.c7
-rw-r--r--arch/x86/platform/uv/tlb_uv.c184
-rw-r--r--arch/x86/power/cpu.c2
-rw-r--r--arch/x86/ras/mce_amd_inj.c54
-rw-r--r--arch/x86/um/ptrace_32.c11
-rw-r--r--arch/x86/um/ptrace_64.c4
-rw-r--r--arch/x86/xen/enlighten.c41
-rw-r--r--arch/x86/xen/setup.c2
-rw-r--r--arch/x86/xen/spinlock.c250
525 files changed, 7538 insertions, 4823 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index e9c9334507dd..180ea33164dc 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -336,17 +336,6 @@ config HAVE_ARCH_SECCOMP_FILTER
results in the system call being skipped immediately.
- seccomp syscall wired up
- For best performance, an arch should use seccomp_phase1 and
- seccomp_phase2 directly. It should call seccomp_phase1 for all
- syscalls if TIF_SECCOMP is set, but seccomp_phase1 does not
- need to be called from a ptrace-safe context. It must then
- call seccomp_phase2 if seccomp_phase1 returns anything other
- than SECCOMP_PHASE1_OK or SECCOMP_PHASE1_SKIP.
-
- As an additional optimization, an arch may provide seccomp_data
- directly to seccomp_phase1; this avoids multiple calls
- to the syscall_xyz helpers for every syscall.
-
config SECCOMP_FILTER
def_bool y
depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
@@ -707,4 +696,38 @@ config ARCH_NO_COHERENT_DMA_MMAP
config CPU_NO_EFFICIENT_FFS
def_bool n
+config HAVE_ARCH_VMAP_STACK
+ def_bool n
+ help
+ An arch should select this symbol if it can support kernel stacks
+ in vmalloc space. This means:
+
+ - vmalloc space must be large enough to hold many kernel stacks.
+ This may rule out many 32-bit architectures.
+
+ - Stacks in vmalloc space need to work reliably. For example, if
+ vmap page tables are created on demand, either this mechanism
+ needs to work while the stack points to a virtual address with
+ unpopulated page tables or arch code (switch_to() and switch_mm(),
+ most likely) needs to ensure that the stack's page table entries
+ are populated before running on a possibly unpopulated stack.
+
+ - If the stack overflows into a guard page, something reasonable
+ should happen. The definition of "reasonable" is flexible, but
+ instantly rebooting without logging anything would be unfriendly.
+
+config VMAP_STACK
+ default y
+ bool "Use a virtually-mapped stack"
+ depends on HAVE_ARCH_VMAP_STACK && !KASAN
+ ---help---
+ Enable this if you want the use virtually-mapped kernel stacks
+ with guard pages. This causes kernel stack overflows to be
+ caught immediately rather than causing difficult-to-diagnose
+ corruption.
+
+ This is presently incompatible with KASAN because KASAN expects
+ the stack to map directly to the KASAN shadow map using a formula
+ that is incorrect if the stack is in vmalloc space.
+
source "kernel/gcov/Kconfig"
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index c419b43c461d..466e42e96bfa 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -371,14 +371,6 @@ __copy_tofrom_user_nocheck(void *to, const void *from, long len)
return __cu_len;
}
-extern inline long
-__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate)
-{
- if (__access_ok((unsigned long)validate, len, get_fs()))
- len = __copy_tofrom_user_nocheck(to, from, len);
- return len;
-}
-
#define __copy_to_user(to, from, n) \
({ \
__chk_user_ptr(to); \
@@ -393,17 +385,22 @@ __copy_tofrom_user(void *to, const void *from, long len, const void __user *vali
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
-
extern inline long
copy_to_user(void __user *to, const void *from, long n)
{
- return __copy_tofrom_user((__force void *)to, from, n, to);
+ if (likely(__access_ok((unsigned long)to, n, get_fs())))
+ n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
+ return n;
}
extern inline long
copy_from_user(void *to, const void __user *from, long n)
{
- return __copy_tofrom_user(to, (__force void *)from, n, from);
+ if (likely(__access_ok((unsigned long)from, n, get_fs())))
+ n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
+ else
+ memset(to, 0, n);
+ return n;
}
extern void __do_clear_user(void);
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 0d3e59f56974..ecd12379e2cd 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -13,7 +13,7 @@ config ARC
select CLKSRC_OF
select CLONE_BACKWARDS
select COMMON_CLK
- select GENERIC_ATOMIC64
+ select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC)
select GENERIC_CLOCKEVENTS
select GENERIC_FIND_FIRST_BIT
# for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP
@@ -353,8 +353,8 @@ endchoice
config NODES_SHIFT
int "Maximum NUMA Nodes (as a power of 2)"
- default "1" if !DISCONTIGMEM
- default "2" if DISCONTIGMEM
+ default "0" if !DISCONTIGMEM
+ default "1" if DISCONTIGMEM
depends on NEED_MULTIPLE_NODES
---help---
Accessing memory beyond 1GB (with or w/o PAE) requires 2 memory
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 601ed173080b..aa82d13d4213 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -47,7 +47,6 @@ endif
upto_gcc44 := $(call cc-ifversion, -le, 0404, y)
atleast_gcc44 := $(call cc-ifversion, -ge, 0404, y)
-atleast_gcc48 := $(call cc-ifversion, -ge, 0408, y)
cflags-$(atleast_gcc44) += -fsection-anchors
@@ -66,10 +65,8 @@ endif
endif
-# By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok
-ifeq ($(atleast_gcc48),y)
-cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2
-endif
+cfi := $(call as-instr,.cfi_startproc\n.cfi_endproc,-DARC_DW2_UNWIND_AS_CFI)
+cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables $(cfi)
ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
# Generic build system uses -O2, we want -O3
diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts
index 3dd6ed941464..3acf04db8030 100644
--- a/arch/arc/boot/dts/abilis_tb100_dvk.dts
+++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts
@@ -24,6 +24,7 @@
/include/ "abilis_tb100.dtsi"
/ {
+ model = "abilis,tb100";
chosen {
bootargs = "earlycon=uart8250,mmio32,0xff100000,9600n8 console=ttyS0,9600n8";
};
diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts
index 1cf51c280f28..37d88c5dd181 100644
--- a/arch/arc/boot/dts/abilis_tb101_dvk.dts
+++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts
@@ -24,6 +24,7 @@
/include/ "abilis_tb101.dtsi"
/ {
+ model = "abilis,tb101";
chosen {
bootargs = "earlycon=uart8250,mmio32,0xff100000,9600n8 console=ttyS0,9600n8";
};
diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts
index 3f9b0582e734..d9b9b9dcfc4c 100644
--- a/arch/arc/boot/dts/axs101.dts
+++ b/arch/arc/boot/dts/axs101.dts
@@ -13,6 +13,7 @@
/include/ "axs10x_mb.dtsi"
/ {
+ model = "snps,axs101";
compatible = "snps,axs101", "snps,arc-sdp";
chosen {
diff --git a/arch/arc/boot/dts/axs103.dts b/arch/arc/boot/dts/axs103.dts
index e6d0e31ea299..ec7fb277a067 100644
--- a/arch/arc/boot/dts/axs103.dts
+++ b/arch/arc/boot/dts/axs103.dts
@@ -16,6 +16,7 @@
/include/ "axs10x_mb.dtsi"
/ {
+ model = "snps,axs103";
compatible = "snps,axs103", "snps,arc-sdp";
chosen {
diff --git a/arch/arc/boot/dts/axs103_idu.dts b/arch/arc/boot/dts/axs103_idu.dts
index f999fef5a60a..070c29782216 100644
--- a/arch/arc/boot/dts/axs103_idu.dts
+++ b/arch/arc/boot/dts/axs103_idu.dts
@@ -16,6 +16,7 @@
/include/ "axs10x_mb.dtsi"
/ {
+ model = "snps,axs103-smp";
compatible = "snps,axs103", "snps,arc-sdp";
chosen {
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index 63970513e4ae..ce0ccd20b5bf 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -10,6 +10,7 @@
/include/ "skeleton.dtsi"
/ {
+ model = "snps,nsim";
compatible = "snps,nsim";
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts
index bf05fe5f67b0..3772c40c245e 100644
--- a/arch/arc/boot/dts/nsim_hs.dts
+++ b/arch/arc/boot/dts/nsim_hs.dts
@@ -10,6 +10,7 @@
/include/ "skeleton_hs.dtsi"
/ {
+ model = "snps,nsim_hs";
compatible = "snps,nsim_hs";
#address-cells = <2>;
#size-cells = <2>;
diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts
index 99eabe1a2bf6..48434d7c4498 100644
--- a/arch/arc/boot/dts/nsim_hs_idu.dts
+++ b/arch/arc/boot/dts/nsim_hs_idu.dts
@@ -10,6 +10,7 @@
/include/ "skeleton_hs_idu.dtsi"
/ {
+ model = "snps,nsim_hs-smp";
compatible = "snps,nsim_hs";
interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index e659a340ca8a..bcf603142a33 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -10,6 +10,7 @@
/include/ "skeleton.dtsi"
/ {
+ model = "snps,nsimosci";
compatible = "snps,nsimosci";
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 16ce5d65cfde..14a727cbf4c9 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -10,6 +10,7 @@
/include/ "skeleton_hs.dtsi"
/ {
+ model = "snps,nsimosci_hs";
compatible = "snps,nsimosci_hs";
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index ce8dfbc30c4d..cbf65b6cc7c6 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -10,6 +10,7 @@
/include/ "skeleton_hs_idu.dtsi"
/ {
+ model = "snps,nsimosci_hs-smp";
compatible = "snps,nsimosci_hs";
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arc/boot/dts/vdk_hs38.dts b/arch/arc/boot/dts/vdk_hs38.dts
index 5d803dd2de59..3c51103f0cd0 100644
--- a/arch/arc/boot/dts/vdk_hs38.dts
+++ b/arch/arc/boot/dts/vdk_hs38.dts
@@ -13,6 +13,7 @@
/include/ "vdk_axs10x_mb.dtsi"
/ {
+ model = "snps,vdk_archs";
compatible = "snps,axs103";
chosen {
diff --git a/arch/arc/boot/dts/vdk_hs38_smp.dts b/arch/arc/boot/dts/vdk_hs38_smp.dts
index 2ba60c399d99..6be68001a6f0 100644
--- a/arch/arc/boot/dts/vdk_hs38_smp.dts
+++ b/arch/arc/boot/dts/vdk_hs38_smp.dts
@@ -13,6 +13,7 @@
/include/ "vdk_axs10x_mb.dtsi"
/ {
+ model = "snps,vdk_archs-smp";
compatible = "snps,axs103";
chosen {
diff --git a/arch/arc/boot/dts/zebu_hs.dts b/arch/arc/boot/dts/zebu_hs.dts
new file mode 100644
index 000000000000..1c1324e84965
--- /dev/null
+++ b/arch/arc/boot/dts/zebu_hs.dts
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2016-2014 Synopsys, Inc. (www.synopsys.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.
+ */
+/dts-v1/;
+
+/include/ "skeleton_hs.dtsi"
+
+/ {
+ model = "snps,zebu_hs";
+ compatible = "snps,zebu_hs";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ interrupt-parent = <&core_intc>;
+
+ memory {
+ device_type = "memory";
+ reg = <0x80000000 0x20000000>; /* 512 */
+ };
+
+ chosen {
+ bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
+ };
+
+ aliases {
+ serial0 = &uart0;
+ };
+
+ fpga {
+ compatible = "simple-bus";
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ /* child and parent address space 1:1 mapped */
+ ranges;
+
+ core_clk: core_clk {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ clock-frequency = <50000000>;
+ };
+
+ core_intc: interrupt-controller {
+ compatible = "snps,archs-intc";
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ };
+
+ uart0: serial@f0000000 {
+ compatible = "ns8250";
+ reg = <0xf0000000 0x2000>;
+ interrupts = <24>;
+ clock-frequency = <50000000>;
+ baud = <115200>;
+ reg-shift = <2>;
+ reg-io-width = <4>;
+ no-loopback-test = <1>;
+ };
+
+ arcpct0: pct {
+ compatible = "snps,archs-pct";
+ #interrupt-cells = <1>;
+ interrupts = <20>;
+ };
+ };
+};
diff --git a/arch/arc/boot/dts/zebu_hs_idu.dts b/arch/arc/boot/dts/zebu_hs_idu.dts
new file mode 100644
index 000000000000..65204b4c0f13
--- /dev/null
+++ b/arch/arc/boot/dts/zebu_hs_idu.dts
@@ -0,0 +1,85 @@
+/*
+ * Copyright (C) 2016-2014 Synopsys, Inc. (www.synopsys.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.
+ */
+/dts-v1/;
+
+/include/ "skeleton_hs_idu.dtsi"
+
+/ {
+ model = "snps,zebu_hs-smp";
+ compatible = "snps,zebu_hs";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ interrupt-parent = <&core_intc>;
+
+ memory {
+ device_type = "memory";
+ reg = <0x80000000 0x20000000>; /* 512 */
+ };
+
+ chosen {
+ bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug";
+ };
+
+ aliases {
+ serial0 = &uart0;
+ };
+
+ fpga {
+ compatible = "simple-bus";
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ /* child and parent address space 1:1 mapped */
+ ranges;
+
+ core_clk: core_clk {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ clock-frequency = <50000000>; /* 50 MHZ */
+ };
+
+ core_intc: interrupt-controller {
+ compatible = "snps,archs-intc";
+ interrupt-controller;
+ #interrupt-cells = <1>;
+/* interrupts = <16 17 18 19 20 21 22 23 24 25>; */
+ };
+
+ idu_intc: idu-interrupt-controller {
+ compatible = "snps,archs-idu-intc";
+ interrupt-controller;
+ interrupt-parent = <&core_intc>;
+ /* <hwirq distribution>
+ distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 */
+ #interrupt-cells = <2>;
+ interrupts = <24 25 26 27 28 29 30 31>;
+
+ };
+
+ uart0: serial@f0000000 {
+ /* compatible = "ns8250"; Doesn't use FIFOs */
+ compatible = "ns16550a";
+ reg = <0xf0000000 0x2000>;
+ interrupt-parent = <&idu_intc>;
+ /* interrupts = <0 1>; DEST=1*/
+ /* interrupts = <0 2>; DEST=2*/
+ interrupts = <0 0>; /* RR*/
+ clock-frequency = <50000000>;
+ baud = <115200>;
+ reg-shift = <2>;
+ reg-io-width = <4>;
+ no-loopback-test = <1>;
+ };
+
+ arcpct0: pct {
+ compatible = "snps,archs-pct";
+ #interrupt-cells = <1>;
+ interrupts = <20>;
+ };
+ };
+};
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 6cdffea3a914..0a0eaf09aac7 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -18,6 +18,9 @@ CONFIG_PERF_EVENTS=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_ARC_PLAT_AXS10X=y
CONFIG_AXS101=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 491b3b5f22bd..2233f5777a71 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -18,6 +18,9 @@ CONFIG_PERF_EVENTS=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_ARC_PLAT_AXS10X=y
CONFIG_AXS103=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index b25ee73b2e79..110874705085 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -18,6 +18,9 @@ CONFIG_PERF_EVENTS=y
# CONFIG_COMPAT_BRK is not set
CONFIG_SLAB=y
CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_ARC_PLAT_AXS10X=y
CONFIG_AXS103=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index a99dc7a3f0af..65ab9fbf83f2 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -11,13 +11,16 @@ CONFIG_NAMESPACES=y
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
+CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
# CONFIG_LBDAF is not set
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_IOSCHED_DEADLINE is not set
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 59f221fc9a41..3b3990cddbe1 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -16,6 +16,9 @@ CONFIG_EMBEDDED=y
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
# CONFIG_LBDAF is not set
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_IOSCHED_DEADLINE is not set
diff --git a/arch/arc/configs/zebu_hs_defconfig b/arch/arc/configs/zebu_hs_defconfig
new file mode 100644
index 000000000000..9f6166be7145
--- /dev/null
+++ b/arch/arc/configs/zebu_hs_defconfig
@@ -0,0 +1,86 @@
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ISA_ARCV2=y
+CONFIG_ARC_BUILTIN_DTB_NAME="zebu_hs"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_DEBUG_MEMORY_INIT=y
+# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/zebu_hs_smp_defconfig b/arch/arc/configs/zebu_hs_smp_defconfig
new file mode 100644
index 000000000000..44e9693f4257
--- /dev/null
+++ b/arch/arc/configs/zebu_hs_smp_defconfig
@@ -0,0 +1,89 @@
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+CONFIG_ARC_BUILTIN_DTB_NAME="zebu_hs_idu"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_LOCKUP_DETECTOR=y
+# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 7fbaea00a336..db25c65155cb 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -95,7 +95,7 @@
/* Auxiliary registers */
#define AUX_IDENTITY 4
#define AUX_INTR_VEC_BASE 0x25
-#define AUX_NON_VOL 0x5e
+#define AUX_VOL 0x5e
/*
* Floating Pt Registers
@@ -240,14 +240,6 @@ struct bcr_extn_xymem {
#endif
};
-struct bcr_perip {
-#ifdef CONFIG_CPU_BIG_ENDIAN
- unsigned int start:8, pad2:8, sz:8, ver:8;
-#else
- unsigned int ver:8, sz:8, pad2:8, start:8;
-#endif
-};
-
struct bcr_iccm_arcompact {
#ifdef CONFIG_CPU_BIG_ENDIAN
unsigned int base:16, pad:5, sz:3, ver:8;
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 4e3c1b6b0806..b65930a49589 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -20,6 +20,7 @@
#ifndef CONFIG_ARC_PLAT_EZNPS
#define atomic_read(v) READ_ONCE((v)->counter)
+#define ATOMIC_INIT(i) { (i) }
#ifdef CONFIG_ARC_HAS_LLSC
@@ -284,6 +285,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \
ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
#define atomic_sub(i, v) atomic_add(-(i), (v))
#define atomic_sub_return(i, v) atomic_add_return(-(i), (v))
+#define atomic_fetch_sub(i, v) atomic_fetch_add(-(i), (v))
#undef ATOMIC_OPS
#define ATOMIC_OPS(op, c_op, asm_op) \
@@ -292,6 +294,7 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
#define atomic_andnot(mask, v) atomic_and(~(mask), (v))
+#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v))
ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
@@ -343,10 +346,266 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-#define ATOMIC_INIT(i) { (i) }
+
+#ifdef CONFIG_GENERIC_ATOMIC64
#include <asm-generic/atomic64.h>
-#endif
+#else /* Kconfig ensures this is only enabled with needed h/w assist */
+
+/*
+ * ARCv2 supports 64-bit exclusive load (LLOCKD) / store (SCONDD)
+ * - The address HAS to be 64-bit aligned
+ * - There are 2 semantics involved here:
+ * = exclusive implies no interim update between load/store to same addr
+ * = both words are observed/updated together: this is guaranteed even
+ * for regular 64-bit load (LDD) / store (STD). Thus atomic64_set()
+ * is NOT required to use LLOCKD+SCONDD, STD suffices
+ */
+
+typedef struct {
+ aligned_u64 counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(a) { (a) }
+
+static inline long long atomic64_read(const atomic64_t *v)
+{
+ unsigned long long val;
+
+ __asm__ __volatile__(
+ " ldd %0, [%1] \n"
+ : "=r"(val)
+ : "r"(&v->counter));
+
+ return val;
+}
+
+static inline void atomic64_set(atomic64_t *v, long long a)
+{
+ /*
+ * This could have been a simple assignment in "C" but would need
+ * explicit volatile. Otherwise gcc optimizers could elide the store
+ * which borked atomic64 self-test
+ * In the inline asm version, memory clobber needed for exact same
+ * reason, to tell gcc about the store.
+ *
+ * This however is not needed for sibling atomic64_add() etc since both
+ * load/store are explicitly done in inline asm. As long as API is used
+ * for each access, gcc has no way to optimize away any load/store
+ */
+ __asm__ __volatile__(
+ " std %0, [%1] \n"
+ :
+ : "r"(a), "r"(&v->counter)
+ : "memory");
+}
+
+#define ATOMIC64_OP(op, op1, op2) \
+static inline void atomic64_##op(long long a, atomic64_t *v) \
+{ \
+ unsigned long long val; \
+ \
+ __asm__ __volatile__( \
+ "1: \n" \
+ " llockd %0, [%1] \n" \
+ " " #op1 " %L0, %L0, %L2 \n" \
+ " " #op2 " %H0, %H0, %H2 \n" \
+ " scondd %0, [%1] \n" \
+ " bnz 1b \n" \
+ : "=&r"(val) \
+ : "r"(&v->counter), "ir"(a) \
+ : "cc"); \
+} \
+
+#define ATOMIC64_OP_RETURN(op, op1, op2) \
+static inline long long atomic64_##op##_return(long long a, atomic64_t *v) \
+{ \
+ unsigned long long val; \
+ \
+ smp_mb(); \
+ \
+ __asm__ __volatile__( \
+ "1: \n" \
+ " llockd %0, [%1] \n" \
+ " " #op1 " %L0, %L0, %L2 \n" \
+ " " #op2 " %H0, %H0, %H2 \n" \
+ " scondd %0, [%1] \n" \
+ " bnz 1b \n" \
+ : [val] "=&r"(val) \
+ : "r"(&v->counter), "ir"(a) \
+ : "cc"); /* memory clobber comes from smp_mb() */ \
+ \
+ smp_mb(); \
+ \
+ return val; \
+}
+
+#define ATOMIC64_FETCH_OP(op, op1, op2) \
+static inline long long atomic64_fetch_##op(long long a, atomic64_t *v) \
+{ \
+ unsigned long long val, orig; \
+ \
+ smp_mb(); \
+ \
+ __asm__ __volatile__( \
+ "1: \n" \
+ " llockd %0, [%2] \n" \
+ " " #op1 " %L1, %L0, %L3 \n" \
+ " " #op2 " %H1, %H0, %H3 \n" \
+ " scondd %1, [%2] \n" \
+ " bnz 1b \n" \
+ : "=&r"(orig), "=&r"(val) \
+ : "r"(&v->counter), "ir"(a) \
+ : "cc"); /* memory clobber comes from smp_mb() */ \
+ \
+ smp_mb(); \
+ \
+ return orig; \
+}
+
+#define ATOMIC64_OPS(op, op1, op2) \
+ ATOMIC64_OP(op, op1, op2) \
+ ATOMIC64_OP_RETURN(op, op1, op2) \
+ ATOMIC64_FETCH_OP(op, op1, op2)
+
+#define atomic64_andnot atomic64_andnot
+
+ATOMIC64_OPS(add, add.f, adc)
+ATOMIC64_OPS(sub, sub.f, sbc)
+ATOMIC64_OPS(and, and, and)
+ATOMIC64_OPS(andnot, bic, bic)
+ATOMIC64_OPS(or, or, or)
+ATOMIC64_OPS(xor, xor, xor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+static inline long long
+atomic64_cmpxchg(atomic64_t *ptr, long long expected, long long new)
+{
+ long long prev;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "1: llockd %0, [%1] \n"
+ " brne %L0, %L2, 2f \n"
+ " brne %H0, %H2, 2f \n"
+ " scondd %3, [%1] \n"
+ " bnz 1b \n"
+ "2: \n"
+ : "=&r"(prev)
+ : "r"(ptr), "ir"(expected), "r"(new)
+ : "cc"); /* memory clobber comes from smp_mb() */
+
+ smp_mb();
+
+ return prev;
+}
+
+static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
+{
+ long long prev;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "1: llockd %0, [%1] \n"
+ " scondd %2, [%1] \n"
+ " bnz 1b \n"
+ "2: \n"
+ : "=&r"(prev)
+ : "r"(ptr), "r"(new)
+ : "cc"); /* memory clobber comes from smp_mb() */
+
+ smp_mb();
+
+ return prev;
+}
+
+/**
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic64_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic variable, v, was not decremented.
+ */
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+ long long val;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "1: llockd %0, [%1] \n"
+ " sub.f %L0, %L0, 1 # w0 - 1, set C on borrow\n"
+ " sub.c %H0, %H0, 1 # if C set, w1 - 1\n"
+ " brlt %H0, 0, 2f \n"
+ " scondd %0, [%1] \n"
+ " bnz 1b \n"
+ "2: \n"
+ : "=&r"(val)
+ : "r"(&v->counter)
+ : "cc"); /* memory clobber comes from smp_mb() */
+
+ smp_mb();
+
+ return val;
+}
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * if (v != u) { v += a; ret = 1} else {ret = 0}
+ * Returns 1 iff @v was not @u (i.e. if add actually happened)
+ */
+static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+{
+ long long val;
+ int op_done;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "1: llockd %0, [%2] \n"
+ " mov %1, 1 \n"
+ " brne %L0, %L4, 2f # continue to add since v != u \n"
+ " breq.d %H0, %H4, 3f # return since v == u \n"
+ " mov %1, 0 \n"
+ "2: \n"
+ " add.f %L0, %L0, %L3 \n"
+ " adc %H0, %H0, %H3 \n"
+ " scondd %0, [%2] \n"
+ " bnz 1b \n"
+ "3: \n"
+ : "=&r"(val), "=&r" (op_done)
+ : "r"(&v->counter), "r"(a), "r"(u)
+ : "cc"); /* memory clobber comes from smp_mb() */
+
+ smp_mb();
+
+ return op_done;
+}
+
+#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
+#define atomic64_inc(v) atomic64_add(1LL, (v))
+#define atomic64_inc_return(v) atomic64_add_return(1LL, (v))
+#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
+#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
+#define atomic64_dec(v) atomic64_sub(1LL, (v))
+#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v))
+#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)
+
+#endif /* !CONFIG_GENERIC_ATOMIC64 */
+
+#endif /* !__ASSEMBLY__ */
#endif
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 23706c635c30..fb781e34f322 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -54,7 +54,7 @@ extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
extern void read_decode_cache_bcr(void);
extern int ioc_exists;
-extern unsigned long perip_base;
+extern unsigned long perip_base, perip_end;
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/dwarf.h b/arch/arc/include/asm/dwarf.h
new file mode 100644
index 000000000000..bb7bdbc59a44
--- /dev/null
+++ b/arch/arc/include/asm/dwarf.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2016-17 Synopsys, Inc. (www.synopsys.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.
+ */
+
+#ifndef _ASM_ARC_DWARF_H
+#define _ASM_ARC_DWARF_H
+
+#ifdef __ASSEMBLY__
+
+#ifdef ARC_DW2_UNWIND_AS_CFI
+
+#define CFI_STARTPROC .cfi_startproc
+#define CFI_ENDPROC .cfi_endproc
+#define CFI_DEF_CFA .cfi_def_cfa
+#define CFI_REGISTER .cfi_register
+#define CFI_REL_OFFSET .cfi_rel_offset
+#define CFI_UNDEFINED .cfi_undefined
+
+#else
+
+#define CFI_IGNORE #
+
+#define CFI_STARTPROC CFI_IGNORE
+#define CFI_ENDPROC CFI_IGNORE
+#define CFI_DEF_CFA CFI_IGNORE
+#define CFI_REGISTER CFI_IGNORE
+#define CFI_REL_OFFSET CFI_IGNORE
+#define CFI_UNDEFINED CFI_IGNORE
+
+#endif /* !ARC_DW2_UNWIND_AS_CFI */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_ARC_DWARF_H */
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index 51a99e25fe33..7096f97a1434 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -23,8 +23,7 @@
/* ARC Relocations (kernel Modules only) */
#define R_ARC_32 0x4
#define R_ARC_32_ME 0x1B
-#define R_ARC_S25H_PCREL 0x10
-#define R_ARC_S25W_PCREL 0x11
+#define R_ARC_32_PCREL 0x31
/*to set parameters in the core dumps */
#define ELF_ARCH EM_ARCOMPACT
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index d1ec7f6b31e0..e880dfa3fcd3 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -112,7 +112,7 @@ static inline long arch_local_save_flags(void)
*/
temp = (1 << 5) |
((!!(temp & STATUS_IE_MASK)) << CLRI_STATUS_IE_BIT) |
- (temp & CLRI_STATUS_E_MASK);
+ ((temp >> 1) & CLRI_STATUS_E_MASK);
return temp;
}
diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
index 5faad17118b4..b29f1a9fd6f7 100644
--- a/arch/arc/include/asm/linkage.h
+++ b/arch/arc/include/asm/linkage.h
@@ -9,6 +9,8 @@
#ifndef __ASM_LINKAGE_H
#define __ASM_LINKAGE_H
+#include <asm/dwarf.h>
+
#ifdef __ASSEMBLY__
#define ASM_NL ` /* use '`' to mark new line in macro */
@@ -32,6 +34,16 @@
#endif
.endm
+#define ENTRY_CFI(name) \
+ .globl name ASM_NL \
+ ALIGN ASM_NL \
+ name: ASM_NL \
+ CFI_STARTPROC ASM_NL
+
+#define END_CFI(name) \
+ CFI_ENDPROC ASM_NL \
+ .size name, .-name
+
#else /* !__ASSEMBLY__ */
#ifdef CONFIG_ARC_HAS_ICCM
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 5f071762fb1c..9185541035cc 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -118,6 +118,9 @@ static const char * const arc_pmu_ev_hw_map[] = {
[PERF_COUNT_ARC_ICM] = "icm", /* I-cache Miss */
[PERF_COUNT_ARC_EDTLB] = "edtlb", /* D-TLB Miss */
[PERF_COUNT_ARC_EITLB] = "eitlb", /* I-TLB Miss */
+
+ [PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc", /* Instr: mem read cached */
+ [PERF_COUNT_HW_CACHE_MISSES] = "dclm", /* D-cache Load Miss */
};
#define C(_x) PERF_COUNT_HW_CACHE_##_x
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index a78d5670884f..41faf17cd28d 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -83,7 +83,10 @@
"2: ;nop\n" \
" .section .fixup, \"ax\"\n" \
" .align 4\n" \
- "3: mov %0, %3\n" \
+ "3: # return -EFAULT\n" \
+ " mov %0, %3\n" \
+ " # zero out dst ptr\n" \
+ " mov %1, 0\n" \
" j 2b\n" \
" .previous\n" \
" .section __ex_table, \"a\"\n" \
@@ -101,7 +104,11 @@
"2: ;nop\n" \
" .section .fixup, \"ax\"\n" \
" .align 4\n" \
- "3: mov %0, %3\n" \
+ "3: # return -EFAULT\n" \
+ " mov %0, %3\n" \
+ " # zero out dst ptr\n" \
+ " mov %1, 0\n" \
+ " mov %R1, 0\n" \
" j 2b\n" \
" .previous\n" \
" .section __ex_table, \"a\"\n" \
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
index e6890b1f8650..7c1f365ef3d2 100644
--- a/arch/arc/kernel/ctx_sw_asm.S
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -23,6 +23,7 @@
.global __switch_to
.type __switch_to, @function
__switch_to:
+ CFI_STARTPROC
/* Save regs on kernel mode stack of task */
st.a blink, [sp, -4]
@@ -59,4 +60,4 @@ __switch_to:
ld.ab blink, [sp, 4]
j [blink]
-END(__switch_to)
+END_CFI(__switch_to)
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 2efb0625331d..1eea99beecc3 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -35,7 +35,7 @@ ENTRY(sys_clone_wrapper)
btst r10, TIF_SYSCALL_TRACE
bnz tracesys_exit
- b ret_from_system_call
+ b .Lret_from_system_call
END(sys_clone_wrapper)
ENTRY(ret_from_fork)
@@ -61,18 +61,6 @@ ENTRY(ret_from_fork)
b ret_from_exception
END(ret_from_fork)
-#ifdef CONFIG_ARC_DW2_UNWIND
-; Workaround for bug 94179 (STAR ):
-; Despite -fasynchronous-unwind-tables, linker is not making dwarf2 unwinder
-; section (.debug_frame) as loadable. So we force it here.
-; This also fixes STAR 9000487933 where the prev-workaround (objcopy --setflag)
-; would not work after a clean build due to kernel build system dependencies.
-.section .debug_frame, "wa",@progbits
-
-; Reset to .text as this file is included in entry-<isa>.S
-.section .text, "ax",@progbits
-#endif
-
;################### Non TLB Exception Handling #############################
; ---------------------------------------------
@@ -260,20 +248,18 @@ ENTRY(EV_Trap)
; syscall num shd not exceed the total system calls avail
cmp r8, NR_syscalls
mov.hi r0, -ENOSYS
- bhi ret_from_system_call
+ bhi .Lret_from_system_call
; Offset into the syscall_table and call handler
ld.as r9,[sys_call_table, r8]
jl [r9] ; Entry into Sys Call Handler
- ; fall through to ret_from_system_call
-END(EV_Trap)
-
-ENTRY(ret_from_system_call)
+.Lret_from_system_call:
st r0, [sp, PT_r0] ; sys call return value in pt_regs
- ; fall through yet again to ret_from_exception
+ ; fall through to ret_from_exception
+END(EV_Trap)
;############# Return from Intr/Excp/Trap (Linux Specifics) ##############
;
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 6c24faf48b16..62b59409a5d9 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -74,7 +74,7 @@ void arc_init_IRQ(void)
tmp = read_aux_reg(0xa);
tmp |= STATUS_AD_MASK | (irq_prio << 1);
tmp &= ~STATUS_IE_MASK;
- asm volatile("flag %0 \n"::"r"(tmp));
+ asm volatile("kflag %0 \n"::"r"(tmp));
}
static void arcv2_irq_mask(struct irq_data *data)
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
index 376e04622962..9a2849756022 100644
--- a/arch/arc/kernel/module.c
+++ b/arch/arc/kernel/module.c
@@ -22,13 +22,9 @@ static inline void arc_write_me(unsigned short *addr, unsigned long value)
*(addr + 1) = (value & 0xffff);
}
-/* ARC specific section quirks - before relocation loop in generic loader
- *
- * For dwarf unwinding out of modules, this needs to
- * 1. Ensure the .debug_frame is allocatable (ARC Linker bug: despite
- * -fasynchronous-unwind-tables it doesn't).
- * 2. Since we are iterating thru sec hdr tbl anyways, make a note of
- * the exact section index, for later use.
+/*
+ * This gets called before relocation loop in generic loader
+ * Make a note of the section index of unwinding section
*/
int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
char *secstr, struct module *mod)
@@ -40,8 +36,7 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
mod->arch.unw_info = NULL;
for (i = 1; i < hdr->e_shnum; i++) {
- if (strcmp(secstr+sechdrs[i].sh_name, ".debug_frame") == 0) {
- sechdrs[i].sh_flags |= SHF_ALLOC;
+ if (strcmp(secstr+sechdrs[i].sh_name, ".eh_frame") == 0) {
mod->arch.unw_sec_idx = i;
break;
}
@@ -106,10 +101,12 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
*/
relo_type = ELF32_R_TYPE(rel_entry[i].r_info);
- if (likely(R_ARC_32_ME == relo_type))
+ if (likely(R_ARC_32_ME == relo_type)) /* ME ( S + A ) */
arc_write_me((unsigned short *)location, relocation);
- else if (R_ARC_32 == relo_type)
+ else if (R_ARC_32 == relo_type) /* ( S + A ) */
*((Elf32_Addr *) location) = relocation;
+ else if (R_ARC_32_PCREL == relo_type) /* ( S + A ) - PDATA ) */
+ *((Elf32_Addr *) location) = relocation - location;
else
goto relo_err;
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 08f03d9b5b3e..2ce24e74f879 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -179,8 +179,8 @@ static int arc_pmu_event_init(struct perf_event *event)
if (arc_pmu->ev_hw_idx[event->attr.config] < 0)
return -ENOENT;
hwc->config |= arc_pmu->ev_hw_idx[event->attr.config];
- pr_debug("init event %d with h/w %d \'%s\'\n",
- (int) event->attr.config, (int) hwc->config,
+ pr_debug("init event %d with h/w %08x \'%s\'\n",
+ (int)event->attr.config, (int)hwc->config,
arc_pmu_ev_hw_map[event->attr.config]);
return 0;
@@ -189,6 +189,8 @@ static int arc_pmu_event_init(struct perf_event *event)
if (ret < 0)
return ret;
hwc->config |= arc_pmu->ev_hw_idx[ret];
+ pr_debug("init cache event with h/w %08x \'%s\'\n",
+ (int)hwc->config, arc_pmu_ev_hw_map[ret]);
return 0;
default:
return -ENOENT;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index f52a0d0dc462..3df7f9c72f42 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -171,6 +171,7 @@ static const struct cpuinfo_data arc_cpu_tbl[] = {
#else
{ {0x50, "ARC HS38 R2.0"}, 0x51},
{ {0x52, "ARC HS38 R2.1"}, 0x52},
+ { {0x53, "ARC HS38 R3.0"}, 0x53},
#endif
{ {0x00, NULL } }
};
@@ -272,8 +273,8 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
FIX_PTR(cpu);
n += scnprintf(buf + n, len - n,
- "Vector Table\t: %#x\nUncached Base\t: %#lx\n",
- cpu->vec_base, perip_base);
+ "Vector Table\t: %#x\nPeripherals\t: %#lx:%#lx\n",
+ cpu->vec_base, perip_base, perip_end);
if (cpu->extn.fpu_sp || cpu->extn.fpu_dp)
n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 0587bf121d11..61fd1ce63c56 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -111,6 +111,8 @@ UNW_REGISTER_INFO};
#define DW_EH_PE_indirect 0x80
#define DW_EH_PE_omit 0xff
+#define CIE_ID 0
+
typedef unsigned long uleb128_t;
typedef signed long sleb128_t;
@@ -232,6 +234,7 @@ void __init arc_unwind_init(void)
static const u32 bad_cie, not_fde;
static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *);
+static const u32 *__cie_for_fde(const u32 *fde);
static signed fde_pointer_type(const u32 *cie);
struct eh_frame_hdr_table_entry {
@@ -338,10 +341,9 @@ static void init_unwind_hdr(struct unwind_table *table,
for (fde = table->address, tableSize = table->size, n = 0;
tableSize;
tableSize -= sizeof(*fde) + *fde, fde += 1 + *fde / sizeof(*fde)) {
- /* const u32 *cie = fde + 1 - fde[1] / sizeof(*fde); */
- const u32 *cie = (const u32 *)(fde[1]);
+ const u32 *cie = __cie_for_fde(fde);
- if (fde[1] == 0xffffffff)
+ if (fde[1] == CIE_ID)
continue; /* this is a CIE */
ptr = (const u8 *)(fde + 2);
header->table[n].start = read_pointer(&ptr,
@@ -504,6 +506,15 @@ static sleb128_t get_sleb128(const u8 **pcur, const u8 *end)
return value;
}
+static const u32 *__cie_for_fde(const u32 *fde)
+{
+ const u32 *cie;
+
+ cie = fde + 1 - fde[1] / sizeof(*fde);
+
+ return cie;
+}
+
static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *table)
{
const u32 *cie;
@@ -511,19 +522,18 @@ static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *table)
if (!*fde || (*fde & (sizeof(*fde) - 1)))
return &bad_cie;
- if (fde[1] == 0xffffffff)
+ if (fde[1] == CIE_ID)
return &not_fde; /* this is a CIE */
if ((fde[1] & (sizeof(*fde) - 1)))
/* || fde[1] > (unsigned long)(fde + 1) - (unsigned long)table->address) */
return NULL; /* this is not a valid FDE */
- /* cie = fde + 1 - fde[1] / sizeof(*fde); */
- cie = (u32 *) fde[1];
+ cie = __cie_for_fde(fde);
if (*cie <= sizeof(*cie) + 4 || *cie >= fde[1] - sizeof(*fde)
|| (*cie & (sizeof(*cie) - 1))
- || (cie[1] != 0xffffffff))
+ || (cie[1] != CIE_ID))
return NULL; /* this is not a (valid) CIE */
return cie;
}
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 894e696bddaa..36611072305f 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -82,14 +82,6 @@ SECTIONS
PERCPU_SECTION(L1_CACHE_BYTES)
- /*
- * .exit.text is discard at runtime, not link time, to deal with
- * references from .debug_frame
- * It will be init freed, being inside [__init_start : __init_end]
- */
- .exit.text : { EXIT_TEXT }
- .exit.data : { EXIT_DATA }
-
. = ALIGN(PAGE_SIZE);
__init_end = .;
@@ -120,18 +112,13 @@ SECTIONS
#ifdef CONFIG_ARC_DW2_UNWIND
. = ALIGN(PAGE_SIZE);
- .debug_frame : {
+ .eh_frame : {
__start_unwind = .;
- *(.debug_frame)
+ *(.eh_frame)
__end_unwind = .;
}
- /*
- * gcc 4.8 generates this for -fasynchonous-unwind-tables,
- * while we still use the .debug_frame based unwinder
- */
- /DISCARD/ : { *(.eh_frame) }
#else
- /DISCARD/ : { *(.debug_frame) }
+ /DISCARD/ : { *(.eh_frame) }
#endif
NOTES
@@ -148,7 +135,7 @@ SECTIONS
}
#ifndef CONFIG_DEBUG_INFO
- /* open-coded because we need .debug_frame seperately for unwinding */
+ /DISCARD/ : { *(.debug_frame) }
/DISCARD/ : { *(.debug_aranges) }
/DISCARD/ : { *(.debug_pubnames) }
/DISCARD/ : { *(.debug_info) }
diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S
index a4015e7d9ab7..21a103044b70 100644
--- a/arch/arc/lib/memcmp.S
+++ b/arch/arc/lib/memcmp.S
@@ -16,7 +16,7 @@
#define SHIFT r2
#endif
-ENTRY(memcmp)
+ENTRY_CFI(memcmp)
or r12,r0,r1
asl_s r12,r12,30
sub r3,r2,1
@@ -149,4 +149,4 @@ ENTRY(memcmp)
.Lnil:
j_s.d [blink]
mov r0,0
-END(memcmp)
+END_CFI(memcmp)
diff --git a/arch/arc/lib/memcpy-700.S b/arch/arc/lib/memcpy-700.S
index 3222573e50de..ba0beccdaafd 100644
--- a/arch/arc/lib/memcpy-700.S
+++ b/arch/arc/lib/memcpy-700.S
@@ -8,7 +8,7 @@
#include <linux/linkage.h>
-ENTRY(memcpy)
+ENTRY_CFI(memcpy)
or r3,r0,r1
asl_s r3,r3,30
mov_s r5,r0
@@ -63,4 +63,4 @@ ENTRY(memcpy)
.Lendbloop:
j_s.d [blink]
stb r12,[r5,0]
-END(memcpy)
+END_CFI(memcpy)
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
index f96c75edf30a..d61044dd8b58 100644
--- a/arch/arc/lib/memcpy-archs.S
+++ b/arch/arc/lib/memcpy-archs.S
@@ -40,7 +40,7 @@
# define ZOLAND 0xF
#endif
-ENTRY(memcpy)
+ENTRY_CFI(memcpy)
prefetch [r1] ; Prefetch the read location
prefetchw [r0] ; Prefetch the write location
mov.f 0, r2
@@ -233,4 +233,4 @@ ENTRY(memcpy)
.Lcopybytewise_3:
j [blink]
-END(memcpy)
+END_CFI(memcpy)
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index 365b18364815..62ad4bcb841a 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -10,7 +10,7 @@
#undef PREALLOC_NOT_AVAIL
-ENTRY(memset)
+ENTRY_CFI(memset)
prefetchw [r0] ; Prefetch the write location
mov.f 0, r2
;;; if size is zero
@@ -112,11 +112,11 @@ ENTRY(memset)
j [blink]
-END(memset)
+END_CFI(memset)
-ENTRY(memzero)
+ENTRY_CFI(memzero)
; adjust bzero args to memset args
mov r2, r1
b.d memset ;tail call so need to tinker with blink
mov r1, 0
-END(memzero)
+END_CFI(memzero)
diff --git a/arch/arc/lib/memset.S b/arch/arc/lib/memset.S
index d36bd43fc98d..cf736f9aa403 100644
--- a/arch/arc/lib/memset.S
+++ b/arch/arc/lib/memset.S
@@ -10,7 +10,7 @@
#define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */
-ENTRY(memset)
+ENTRY_CFI(memset)
mov_s r4,r0
or r12,r0,r2
bmsk.f r12,r12,1
@@ -46,14 +46,14 @@ ENTRY(memset)
stb.ab r1,[r4,1]
.Ltiny_end:
j_s [blink]
-END(memset)
+END_CFI(memset)
; memzero: @r0 = mem, @r1 = size_t
; memset: @r0 = mem, @r1 = char, @r2 = size_t
-ENTRY(memzero)
+ENTRY_CFI(memzero)
; adjust bzero args to memset args
mov r2, r1
mov r1, 0
b memset ;tail call so need to tinker with blink
-END(memzero)
+END_CFI(memzero)
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S
index b725d5862107..2d300daae2ae 100644
--- a/arch/arc/lib/strchr-700.S
+++ b/arch/arc/lib/strchr-700.S
@@ -13,7 +13,7 @@
#include <linux/linkage.h>
-ENTRY(strchr)
+ENTRY_CFI(strchr)
extb_s r1,r1
asl r5,r1,8
bmsk r2,r0,1
@@ -130,4 +130,4 @@ ENTRY(strchr)
j_s.d [blink]
mov.mi r0,0
#endif /* ENDIAN */
-END(strchr)
+END_CFI(strchr)
diff --git a/arch/arc/lib/strcmp-archs.S b/arch/arc/lib/strcmp-archs.S
index 4f338eec3365..fae9e82a09eb 100644
--- a/arch/arc/lib/strcmp-archs.S
+++ b/arch/arc/lib/strcmp-archs.S
@@ -8,7 +8,7 @@
#include <linux/linkage.h>
-ENTRY(strcmp)
+ENTRY_CFI(strcmp)
or r2, r0, r1
bmsk_s r2, r2, 1
brne r2, 0, @.Lcharloop
@@ -75,4 +75,4 @@ ENTRY(strcmp)
.Lcmpend:
j_s.d [blink]
sub r0, r2, r3
-END(strcmp)
+END_CFI(strcmp)
diff --git a/arch/arc/lib/strcmp.S b/arch/arc/lib/strcmp.S
index 3544600fefe6..fb20096e5008 100644
--- a/arch/arc/lib/strcmp.S
+++ b/arch/arc/lib/strcmp.S
@@ -15,7 +15,7 @@
#include <linux/linkage.h>
-ENTRY(strcmp)
+ENTRY_CFI(strcmp)
or r2,r0,r1
bmsk_s r2,r2,1
brne r2,0,.Lcharloop
@@ -93,4 +93,4 @@ ENTRY(strcmp)
.Lcmpend:
j_s.d [blink]
sub r0,r2,r3
-END(strcmp)
+END_CFI(strcmp)
diff --git a/arch/arc/lib/strcpy-700.S b/arch/arc/lib/strcpy-700.S
index 8422f38e1218..6a6c1553807d 100644
--- a/arch/arc/lib/strcpy-700.S
+++ b/arch/arc/lib/strcpy-700.S
@@ -18,7 +18,7 @@
#include <linux/linkage.h>
-ENTRY(strcpy)
+ENTRY_CFI(strcpy)
or r2,r0,r1
bmsk_s r2,r2,1
brne.d r2,0,charloop
@@ -67,4 +67,4 @@ charloop:
brne.d r3,0,charloop
stb.ab r3,[r10,1]
j [blink]
-END(strcpy)
+END_CFI(strcpy)
diff --git a/arch/arc/lib/strlen.S b/arch/arc/lib/strlen.S
index 53cfd5685a5f..839b44b8d055 100644
--- a/arch/arc/lib/strlen.S
+++ b/arch/arc/lib/strlen.S
@@ -8,7 +8,7 @@
#include <linux/linkage.h>
-ENTRY(strlen)
+ENTRY_CFI(strlen)
or r3,r0,7
ld r2,[r3,-7]
ld.a r6,[r3,-3]
@@ -80,4 +80,4 @@ ENTRY(strlen)
.Learly_end:
b.d .Lend
sub_s.ne r1,r1,r1
-END(strlen)
+END_CFI(strlen)
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 0b10efe3a6a7..97dddbefb86a 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -25,6 +25,7 @@ static int l2_line_sz;
int ioc_exists;
volatile int slc_enable = 1, ioc_enable = 1;
unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
+unsigned long perip_end = 0xFFFFFFFF; /* legacy value */
void (*_cache_line_loop_ic_fn)(phys_addr_t paddr, unsigned long vaddr,
unsigned long sz, const int cacheop);
@@ -76,7 +77,6 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
static void read_decode_cache_bcr_arcv2(int cpu)
{
struct cpuinfo_arc_cache *p_slc = &cpuinfo_arc700[cpu].slc;
- struct bcr_generic uncached_space;
struct bcr_generic sbcr;
struct bcr_slc_cfg {
@@ -95,6 +95,15 @@ static void read_decode_cache_bcr_arcv2(int cpu)
#endif
} cbcr;
+ struct bcr_volatile {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ unsigned int start:4, limit:4, pad:22, order:1, disable:1;
+#else
+ unsigned int disable:1, order:1, pad:22, limit:4, start:4;
+#endif
+ } vol;
+
+
READ_BCR(ARC_REG_SLC_BCR, sbcr);
if (sbcr.ver) {
READ_BCR(ARC_REG_SLC_CFG, slc_cfg);
@@ -107,10 +116,14 @@ static void read_decode_cache_bcr_arcv2(int cpu)
if (cbcr.c && ioc_enable)
ioc_exists = 1;
- /* Legacy Data Uncached BCR is deprecated from v3 onwards */
- READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
- if (uncached_space.ver > 2)
- perip_base = read_aux_reg(AUX_NON_VOL) & 0xF0000000;
+ /* HS 2.0 didn't have AUX_VOL */
+ if (cpuinfo_arc700[cpu].core.family > 0x51) {
+ READ_BCR(AUX_VOL, vol);
+ perip_base = vol.start << 28;
+ /* HS 3.0 has limit and strict-ordering fields */
+ if (cpuinfo_arc700[cpu].core.family > 0x52)
+ perip_end = (vol.limit << 28) - 1;
+ }
}
void read_decode_cache_bcr(void)
diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c
index f52b7db67fd3..9881bd740ccc 100644
--- a/arch/arc/mm/ioremap.c
+++ b/arch/arc/mm/ioremap.c
@@ -19,7 +19,7 @@ static inline bool arc_uncached_addr_space(phys_addr_t paddr)
if (is_isa_arcompact()) {
if (paddr >= ARC_UNCACHED_ADDR_SPACE)
return true;
- } else if (paddr >= perip_base && paddr <= 0xFFFFFFFF) {
+ } else if (paddr >= perip_base && paddr <= perip_end) {
return true;
}
diff --git a/arch/arc/plat-sim/platform.c b/arch/arc/plat-sim/platform.c
index e4fe51456808..aea87389e44b 100644
--- a/arch/arc/plat-sim/platform.c
+++ b/arch/arc/plat-sim/platform.c
@@ -24,6 +24,7 @@ static const char *simulation_compat[] __initconst = {
"snps,nsim_hs",
"snps,nsimosci",
"snps,nsimosci_hs",
+ "snps,zebu_hs",
NULL,
};
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a9c4e48bb7ec..3cd9042fbb62 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1,6 +1,7 @@
config ARM
bool
default y
+ select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
@@ -878,6 +879,7 @@ config ARCH_STM32
select CLKSRC_STM32
select PINCTRL
select RESET_CONTROLLER
+ select STM32_EXTI
help
Support for STMicroelectronics STM32 processors.
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index af11c2f8f3b7..fc6d541549a2 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -779,7 +779,7 @@ __armv7_mmu_cache_on:
orrne r0, r0, #1 @ MMU enabled
movne r1, #0xfffffffd @ domain 0 = client
bic r6, r6, #1 << 31 @ 32-bit translation system
- bic r6, r6, #3 << 0 @ use only ttbr0
+ bic r6, r6, #(7 << 0) | (1 << 4) @ use only ttbr0
mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer
mcrne p15, 0, r1, c3, c0, 0 @ load domain access control
mcrne p15, 0, r6, c2, c0, 2 @ load ttb control
diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi
index c8609d8d2c55..b689172632ef 100644
--- a/arch/arm/boot/dts/am335x-baltos.dtsi
+++ b/arch/arm/boot/dts/am335x-baltos.dtsi
@@ -226,7 +226,7 @@
#address-cells = <1>;
#size-cells = <1>;
- elm_id = <&elm>;
+ ti,elm-id = <&elm>;
};
};
diff --git a/arch/arm/boot/dts/am335x-igep0033.dtsi b/arch/arm/boot/dts/am335x-igep0033.dtsi
index df63484ef9b3..e7d9ca1305fa 100644
--- a/arch/arm/boot/dts/am335x-igep0033.dtsi
+++ b/arch/arm/boot/dts/am335x-igep0033.dtsi
@@ -161,7 +161,7 @@
#address-cells = <1>;
#size-cells = <1>;
- elm_id = <&elm>;
+ ti,elm-id = <&elm>;
/* MTD partition table */
partition@0 {
diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi
index 86f773165d5c..1263c9d4cba3 100644
--- a/arch/arm/boot/dts/am335x-phycore-som.dtsi
+++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi
@@ -197,7 +197,7 @@
gpmc,wr-access-ns = <30>;
gpmc,wr-data-mux-bus-ns = <0>;
- elm_id = <&elm>;
+ ti,elm-id = <&elm>;
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm/boot/dts/armada-388-clearfog.dts b/arch/arm/boot/dts/armada-388-clearfog.dts
index 2e0556af6e5e..d3e6bd805006 100644
--- a/arch/arm/boot/dts/armada-388-clearfog.dts
+++ b/arch/arm/boot/dts/armada-388-clearfog.dts
@@ -390,12 +390,12 @@
port@0 {
reg = <0>;
- label = "lan1";
+ label = "lan5";
};
port@1 {
reg = <1>;
- label = "lan2";
+ label = "lan4";
};
port@2 {
@@ -405,12 +405,12 @@
port@3 {
reg = <3>;
- label = "lan4";
+ label = "lan2";
};
port@4 {
reg = <4>;
- label = "lan5";
+ label = "lan1";
};
port@5 {
diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi
index caf2707680c1..e9b47b2bbc33 100644
--- a/arch/arm/boot/dts/bcm2835-rpi.dtsi
+++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi
@@ -2,6 +2,7 @@
/ {
memory {
+ device_type = "memory";
reg = <0 0x10000000>;
};
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index b98252232d20..445624a1a1de 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -2,7 +2,6 @@
#include <dt-bindings/clock/bcm2835.h>
#include <dt-bindings/clock/bcm2835-aux.h>
#include <dt-bindings/gpio/gpio.h>
-#include "skeleton.dtsi"
/* This include file covers the common peripherals and configuration between
* bcm2835 and bcm2836 implementations, leaving the CPU configuration to
@@ -13,6 +12,8 @@
compatible = "brcm,bcm2835";
model = "BCM2835";
interrupt-parent = <&intc>;
+ #address-cells = <1>;
+ #size-cells = <1>;
chosen {
bootargs = "earlyprintk console=ttyAMA0";
diff --git a/arch/arm/boot/dts/exynos5410-odroidxu.dts b/arch/arm/boot/dts/exynos5410-odroidxu.dts
index d9499310a301..f6d135245a4b 100644
--- a/arch/arm/boot/dts/exynos5410-odroidxu.dts
+++ b/arch/arm/boot/dts/exynos5410-odroidxu.dts
@@ -447,14 +447,11 @@
samsung,dw-mshc-ciu-div = <3>;
samsung,dw-mshc-sdr-timing = <0 4>;
samsung,dw-mshc-ddr-timing = <0 2>;
- samsung,dw-mshc-hs400-timing = <0 2>;
- samsung,read-strobe-delay = <90>;
pinctrl-names = "default";
pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus1 &sd0_bus4 &sd0_bus8 &sd0_cd>;
bus-width = <8>;
cap-mmc-highspeed;
mmc-hs200-1_8v;
- mmc-hs400-1_8v;
vmmc-supply = <&ldo20_reg>;
vqmmc-supply = <&ldo11_reg>;
};
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index b620ac884cfd..b13b0b2db881 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -243,7 +243,7 @@
clocks = <&clks IMX6QDL_CLK_SPDIF_GCLK>, <&clks IMX6QDL_CLK_OSC>,
<&clks IMX6QDL_CLK_SPDIF>, <&clks IMX6QDL_CLK_ASRC>,
<&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_ESAI_EXTAL>,
- <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_MLB>,
+ <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_DUMMY>,
<&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_SPBA>;
clock-names = "core", "rxtx0",
"rxtx1", "rxtx2",
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index 96ea936eeeb0..240a2864d044 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -64,7 +64,7 @@
cd-gpios = <&gpio7 11 GPIO_ACTIVE_LOW>;
no-1-8-v;
keep-power-in-suspend;
- enable-sdio-wakup;
+ wakeup-source;
status = "okay";
};
diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts
index 95ee268ed510..2f33c463cbce 100644
--- a/arch/arm/boot/dts/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/imx7d-sdb.dts
@@ -131,7 +131,7 @@
ti,y-min = /bits/ 16 <0>;
ti,y-max = /bits/ 16 <0>;
ti,pressure-max = /bits/ 16 <0>;
- ti,x-plat-ohms = /bits/ 16 <400>;
+ ti,x-plate-ohms = /bits/ 16 <400>;
wakeup-source;
};
};
diff --git a/arch/arm/boot/dts/kirkwood-ib62x0.dts b/arch/arm/boot/dts/kirkwood-ib62x0.dts
index ef84d8699a76..5bf62897014c 100644
--- a/arch/arm/boot/dts/kirkwood-ib62x0.dts
+++ b/arch/arm/boot/dts/kirkwood-ib62x0.dts
@@ -113,7 +113,7 @@
partition@e0000 {
label = "u-boot environment";
- reg = <0xe0000 0x100000>;
+ reg = <0xe0000 0x20000>;
};
partition@100000 {
diff --git a/arch/arm/boot/dts/kirkwood-openrd.dtsi b/arch/arm/boot/dts/kirkwood-openrd.dtsi
index e4ecab112601..7175511a92da 100644
--- a/arch/arm/boot/dts/kirkwood-openrd.dtsi
+++ b/arch/arm/boot/dts/kirkwood-openrd.dtsi
@@ -116,6 +116,10 @@
};
};
+&pciec {
+ status = "okay";
+};
+
&pcie0 {
status = "okay";
};
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index 365f39ff58bb..0ff1c2de95bf 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -35,10 +35,15 @@
ranges = <0 0 0x00000000 0x1000000>; /* CS0: 16MB for NAND */
nand@0,0 {
- linux,mtd-name = "micron,mt29f4g16abbda3w";
+ compatible = "ti,omap2-nand";
reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
+ interrupt-parent = <&gpmc>;
+ interrupts = <0 IRQ_TYPE_NONE>, /* fifoevent */
+ <1 IRQ_TYPE_NONE>; /* termcount */
+ linux,mtd-name = "micron,mt29f4g16abbda3w";
nand-bus-width = <16>;
ti,nand-ecc-opt = "bch8";
+ rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */
gpmc,sync-clk-ps = <0>;
gpmc,cs-on-ns = <0>;
gpmc,cs-rd-off-ns = <44>;
@@ -54,10 +59,6 @@
gpmc,wr-access-ns = <40>;
gpmc,wr-data-mux-bus-ns = <0>;
gpmc,device-width = <2>;
-
- gpmc,page-burst-access-ns = <5>;
- gpmc,cycle2cycle-delay-ns = <50>;
-
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 5e9a13c0eaf7..1c2c74655416 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -46,6 +46,7 @@
linux,mtd-name = "micron,mt29f4g16abbda3w";
nand-bus-width = <16>;
ti,nand-ecc-opt = "bch8";
+ rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */
gpmc,sync-clk-ps = <0>;
gpmc,cs-on-ns = <0>;
gpmc,cs-rd-off-ns = <44>;
diff --git a/arch/arm/boot/dts/omap3-overo-base.dtsi b/arch/arm/boot/dts/omap3-overo-base.dtsi
index de256fa8da48..3e946cac55f3 100644
--- a/arch/arm/boot/dts/omap3-overo-base.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-base.dtsi
@@ -223,7 +223,9 @@
};
&gpmc {
- ranges = <0 0 0x00000000 0x20000000>;
+ ranges = <0 0 0x30000000 0x1000000>, /* CS0 */
+ <4 0 0x2b000000 0x1000000>, /* CS4 */
+ <5 0 0x2c000000 0x1000000>; /* CS5 */
nand@0,0 {
compatible = "ti,omap2-nand";
diff --git a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
index 7df27926ead2..4f4c6efbd518 100644
--- a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
@@ -55,8 +55,6 @@
#include "omap-gpmc-smsc9221.dtsi"
&gpmc {
- ranges = <5 0 0x2c000000 0x1000000>; /* CS5 */
-
ethernet@gpmc {
reg = <5 0 0xff>;
interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
index 9e24b6a1d07b..1b304e2f1bd2 100644
--- a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
@@ -27,8 +27,6 @@
#include "omap-gpmc-smsc9221.dtsi"
&gpmc {
- ranges = <5 0 0x2c000000 0x1000000>; /* CS5 */
-
ethernet@gpmc {
reg = <5 0 0xff>;
interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
index 334109e14613..82e98ee3023a 100644
--- a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
@@ -15,9 +15,6 @@
#include "omap-gpmc-smsc9221.dtsi"
&gpmc {
- ranges = <4 0 0x2b000000 0x1000000>, /* CS4 */
- <5 0 0x2c000000 0x1000000>; /* CS5 */
-
smsc1: ethernet@gpmc {
reg = <5 0 0xff>;
interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index d294e82447a2..8b063ab10c19 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -550,8 +550,9 @@
interrupt-names = "mmcirq";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mmc0>;
- clock-names = "mmc";
- clocks = <&clk_s_c0_flexgen CLK_MMC_0>;
+ clock-names = "mmc", "icn";
+ clocks = <&clk_s_c0_flexgen CLK_MMC_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
bus-width = <8>;
non-removable;
};
@@ -565,8 +566,9 @@
interrupt-names = "mmcirq";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_sd1>;
- clock-names = "mmc";
- clocks = <&clk_s_c0_flexgen CLK_MMC_1>;
+ clock-names = "mmc", "icn";
+ clocks = <&clk_s_c0_flexgen CLK_MMC_1>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
resets = <&softreset STIH407_MMC1_SOFTRESET>;
bus-width = <4>;
};
diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi
index 18ed1ad10d32..40318869c733 100644
--- a/arch/arm/boot/dts/stih410.dtsi
+++ b/arch/arm/boot/dts/stih410.dtsi
@@ -41,7 +41,8 @@
compatible = "st,st-ohci-300x";
reg = <0x9a03c00 0x100>;
interrupts = <GIC_SPI 180 IRQ_TYPE_NONE>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
<&softreset STIH407_USB2_PORT0_SOFTRESET>;
reset-names = "power", "softreset";
@@ -57,7 +58,8 @@
interrupts = <GIC_SPI 151 IRQ_TYPE_NONE>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb0>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
<&softreset STIH407_USB2_PORT0_SOFTRESET>;
reset-names = "power", "softreset";
@@ -71,7 +73,8 @@
compatible = "st,st-ohci-300x";
reg = <0x9a83c00 0x100>;
interrupts = <GIC_SPI 181 IRQ_TYPE_NONE>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
<&softreset STIH407_USB2_PORT1_SOFTRESET>;
reset-names = "power", "softreset";
@@ -87,7 +90,8 @@
interrupts = <GIC_SPI 153 IRQ_TYPE_NONE>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb1>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
<&softreset STIH407_USB2_PORT1_SOFTRESET>;
reset-names = "power", "softreset";
diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi
index 35df462559ca..1a189d44ad38 100644
--- a/arch/arm/boot/dts/stm32f429.dtsi
+++ b/arch/arm/boot/dts/stm32f429.dtsi
@@ -176,6 +176,14 @@
reg = <0x40013800 0x400>;
};
+ exti: interrupt-controller@40013c00 {
+ compatible = "st,stm32-exti";
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ reg = <0x40013C00 0x400>;
+ interrupts = <1>, <2>, <3>, <6>, <7>, <8>, <9>, <10>, <23>, <40>, <41>, <42>, <62>, <76>;
+ };
+
pin-controller {
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index e012890e0cf2..a17ba0243db3 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -84,7 +84,7 @@
trips {
cpu_alert0: cpu_alert0 {
/* milliCelsius */
- temperature = <850000>;
+ temperature = <85000>;
hysteresis = <2000>;
type = "passive";
};
diff --git a/arch/arm/boot/dts/tegra114-dalmore.dts b/arch/arm/boot/dts/tegra114-dalmore.dts
index 1dfc492cc004..1444fbd543e7 100644
--- a/arch/arm/boot/dts/tegra114-dalmore.dts
+++ b/arch/arm/boot/dts/tegra114-dalmore.dts
@@ -897,7 +897,7 @@
palmas: tps65913@58 {
compatible = "ti,palmas";
reg = <0x58>;
- interrupts = <0 86 IRQ_TYPE_LEVEL_LOW>;
+ interrupts = <0 86 IRQ_TYPE_LEVEL_HIGH>;
#interrupt-cells = <2>;
interrupt-controller;
diff --git a/arch/arm/boot/dts/tegra114-roth.dts b/arch/arm/boot/dts/tegra114-roth.dts
index 70cf40996c3f..966a7fc044af 100644
--- a/arch/arm/boot/dts/tegra114-roth.dts
+++ b/arch/arm/boot/dts/tegra114-roth.dts
@@ -802,7 +802,7 @@
palmas: pmic@58 {
compatible = "ti,palmas";
reg = <0x58>;
- interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>;
+ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
#interrupt-cells = <2>;
interrupt-controller;
diff --git a/arch/arm/boot/dts/tegra114-tn7.dts b/arch/arm/boot/dts/tegra114-tn7.dts
index 17dd14545862..a161fa1dfb61 100644
--- a/arch/arm/boot/dts/tegra114-tn7.dts
+++ b/arch/arm/boot/dts/tegra114-tn7.dts
@@ -63,7 +63,7 @@
palmas: pmic@58 {
compatible = "ti,palmas";
reg = <0x58>;
- interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>;
+ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
#interrupt-cells = <2>;
interrupt-controller;
diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
index 6403e0de540e..e52b82449a79 100644
--- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts
+++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
@@ -1382,7 +1382,7 @@
* Pin 41: BR_UART1_TXD
* Pin 44: BR_UART1_RXD
*/
- serial@0,70006000 {
+ serial@70006000 {
compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart";
status = "okay";
};
@@ -1394,7 +1394,7 @@
* Pin 71: UART2_CTS_L
* Pin 74: UART2_RTS_L
*/
- serial@0,70006040 {
+ serial@70006040 {
compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart";
status = "okay";
};
diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c
index 3f47f1203c6b..6053f64c3752 100644
--- a/arch/arm/common/bL_switcher_dummy_if.c
+++ b/arch/arm/common/bL_switcher_dummy_if.c
@@ -56,16 +56,4 @@ static struct miscdevice bL_switcher_device = {
"b.L_switcher",
&bL_switcher_fops
};
-
-static int __init bL_switcher_dummy_if_init(void)
-{
- return misc_register(&bL_switcher_device);
-}
-
-static void __exit bL_switcher_dummy_if_exit(void)
-{
- misc_deregister(&bL_switcher_device);
-}
-
-module_init(bL_switcher_dummy_if_init);
-module_exit(bL_switcher_dummy_if_exit);
+module_misc_device(bL_switcher_device);
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 0e97b4b871f9..6c7b06854fce 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -140,7 +140,7 @@ static struct locomo_dev_info locomo_devices[] = {
static void locomo_handler(struct irq_desc *desc)
{
- struct locomo *lchip = irq_desc_get_chip_data(desc);
+ struct locomo *lchip = irq_desc_get_handler_data(desc);
int req, i;
/* Acknowledge the parent IRQ */
@@ -200,8 +200,7 @@ static void locomo_setup_irq(struct locomo *lchip)
* Install handler for IRQ_LOCOMO_HW.
*/
irq_set_irq_type(lchip->irq, IRQ_TYPE_EDGE_FALLING);
- irq_set_chip_data(lchip->irq, lchip);
- irq_set_chained_handler(lchip->irq, locomo_handler);
+ irq_set_chained_handler_and_data(lchip->irq, locomo_handler, lchip);
/* Install handlers for IRQ_LOCOMO_* */
for ( ; irq <= lchip->irq_base + 3; irq++) {
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index fb0a0a4dfea4..2e076c492005 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -472,8 +472,8 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
* specifies that S0ReadyInt and S1ReadyInt should be '1'.
*/
sa1111_writel(0, irqbase + SA1111_INTPOL0);
- sa1111_writel(SA1111_IRQMASK_HI(IRQ_S0_READY_NINT) |
- SA1111_IRQMASK_HI(IRQ_S1_READY_NINT),
+ sa1111_writel(BIT(IRQ_S0_READY_NINT & 31) |
+ BIT(IRQ_S1_READY_NINT & 31),
irqbase + SA1111_INTPOL1);
/* clear all IRQs */
@@ -754,7 +754,7 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq)
if (sachip->irq != NO_IRQ) {
ret = sa1111_setup_irq(sachip, pd->irq_base);
if (ret)
- goto err_unmap;
+ goto err_clk;
}
#ifdef CONFIG_ARCH_SA1100
@@ -799,6 +799,8 @@ static int __sa1111_probe(struct device *me, struct resource *mem, int irq)
return 0;
+ err_clk:
+ clk_disable(sachip->clk);
err_unmap:
iounmap(sachip->base);
err_clk_unprep:
@@ -869,9 +871,9 @@ struct sa1111_save_data {
#ifdef CONFIG_PM
-static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
+static int sa1111_suspend_noirq(struct device *dev)
{
- struct sa1111 *sachip = platform_get_drvdata(dev);
+ struct sa1111 *sachip = dev_get_drvdata(dev);
struct sa1111_save_data *save;
unsigned long flags;
unsigned int val;
@@ -934,9 +936,9 @@ static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
* restored by their respective drivers, and must be called
* via LDM after this function.
*/
-static int sa1111_resume(struct platform_device *dev)
+static int sa1111_resume_noirq(struct device *dev)
{
- struct sa1111 *sachip = platform_get_drvdata(dev);
+ struct sa1111 *sachip = dev_get_drvdata(dev);
struct sa1111_save_data *save;
unsigned long flags, id;
void __iomem *base;
@@ -952,7 +954,7 @@ static int sa1111_resume(struct platform_device *dev)
id = sa1111_readl(sachip->base + SA1111_SKID);
if ((id & SKID_ID_MASK) != SKID_SA1111_ID) {
__sa1111_remove(sachip);
- platform_set_drvdata(dev, NULL);
+ dev_set_drvdata(dev, NULL);
kfree(save);
return 0;
}
@@ -1003,8 +1005,8 @@ static int sa1111_resume(struct platform_device *dev)
}
#else
-#define sa1111_suspend NULL
-#define sa1111_resume NULL
+#define sa1111_suspend_noirq NULL
+#define sa1111_resume_noirq NULL
#endif
static int sa1111_probe(struct platform_device *pdev)
@@ -1017,7 +1019,7 @@ static int sa1111_probe(struct platform_device *pdev)
return -EINVAL;
irq = platform_get_irq(pdev, 0);
if (irq < 0)
- return -ENXIO;
+ return irq;
return __sa1111_probe(&pdev->dev, mem, irq);
}
@@ -1038,6 +1040,11 @@ static int sa1111_remove(struct platform_device *pdev)
return 0;
}
+static struct dev_pm_ops sa1111_pm_ops = {
+ .suspend_noirq = sa1111_suspend_noirq,
+ .resume_noirq = sa1111_resume_noirq,
+};
+
/*
* Not sure if this should be on the system bus or not yet.
* We really want some way to register a system device at
@@ -1050,10 +1057,9 @@ static int sa1111_remove(struct platform_device *pdev)
static struct platform_driver sa1111_device_driver = {
.probe = sa1111_probe,
.remove = sa1111_remove,
- .suspend = sa1111_suspend,
- .resume = sa1111_resume,
.driver = {
.name = "sa1111",
+ .pm = &sa1111_pm_ops,
},
};
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 01986deef7c5..36cc7cc012f9 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -28,7 +28,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
CONFIG_CPU_FREQ_GOV_POWERSAVE=m
CONFIG_CPU_FREQ_GOV_USERSPACE=m
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
-CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m
+CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
CONFIG_CPUFREQ_DT=y
CONFIG_CPU_IDLE=y
CONFIG_ARM_EXYNOS_CPUIDLE=y
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index 71b42e66488a..78cd2f197e01 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -161,6 +161,7 @@ CONFIG_USB_MON=y
CONFIG_USB_XHCI_HCD=y
CONFIG_USB_STORAGE=y
CONFIG_USB_DWC3=y
+CONFIG_NOP_USB_XCEIV=y
CONFIG_KEYSTONE_USB_PHY=y
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 2c8665cd9dc5..58459105cadc 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -135,7 +135,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
CONFIG_CPU_FREQ_GOV_POWERSAVE=m
CONFIG_CPU_FREQ_GOV_USERSPACE=m
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
-CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m
+CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
CONFIG_QORIQ_CPUFREQ=y
CONFIG_CPU_IDLE=y
CONFIG_ARM_CPUIDLE=y
@@ -781,7 +781,7 @@ CONFIG_MXS_DMA=y
CONFIG_DMA_BCM2835=y
CONFIG_DMA_OMAP=y
CONFIG_QCOM_BAM_DMA=y
-CONFIG_XILINX_VDMA=y
+CONFIG_XILINX_DMA=y
CONFIG_DMA_SUN6I=y
CONFIG_STAGING=y
CONFIG_SENSORS_ISL29018=y
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index da3c0428507b..aef022a87c53 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -284,7 +284,7 @@ static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
err = blkcipher_walk_done(desc, &walk,
walk.nbytes % AES_BLOCK_SIZE);
}
- if (nbytes) {
+ if (walk.nbytes % AES_BLOCK_SIZE) {
u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
u8 __aligned(8) tail[AES_BLOCK_SIZE];
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index e08d15184056..dfe4002812da 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -34,6 +34,7 @@
#define ICC_CTLR __ACCESS_CP15(c12, 0, c12, 4)
#define ICC_SRE __ACCESS_CP15(c12, 0, c12, 5)
#define ICC_IGRPEN1 __ACCESS_CP15(c12, 0, c12, 7)
+#define ICC_BPR1 __ACCESS_CP15(c12, 0, c12, 3)
#define ICC_HSRE __ACCESS_CP15(c12, 4, c9, 5)
@@ -157,6 +158,11 @@ static inline void gic_write_sre(u32 val)
isb();
}
+static inline void gic_write_bpr1(u32 val)
+{
+ asm volatile("mcr " __stringify(ICC_BPR1) : : "r" (val));
+}
+
/*
* Even in 32bit systems that use LPAE, there is no guarantee that the I/O
* interface provides true 64bit atomic accesses, so using strd/ldrd doesn't
diff --git a/arch/arm/include/asm/clocksource.h b/arch/arm/include/asm/clocksource.h
new file mode 100644
index 000000000000..0b350a7e26f3
--- /dev/null
+++ b/arch/arm/include/asm/clocksource.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+struct arch_clocksource_data {
+ bool vdso_direct; /* Usable for direct VDSO access? */
+};
+
+#endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index d009f7911ffc..bf02dbd9ccda 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -111,7 +111,7 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
/* The ARM override for dma_max_pfn() */
static inline unsigned long dma_max_pfn(struct device *dev)
{
- return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask);
+ return dma_to_pfn(dev, *dev->dma_mask);
}
#define dma_max_pfn(dev) dma_max_pfn(dev)
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index d0131ee6f6af..3f82e9da7cec 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -47,6 +47,7 @@
#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_CACHE_MASK (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2))
/*
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
index f8f1cff62065..4cd664abfcd3 100644
--- a/arch/arm/include/asm/pgtable-3level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -62,6 +62,7 @@
#define PMD_SECT_WT (_AT(pmdval_t, 2) << 2) /* normal inner write-through */
#define PMD_SECT_WB (_AT(pmdval_t, 3) << 2) /* normal inner write-back */
#define PMD_SECT_WBWA (_AT(pmdval_t, 7) << 2) /* normal inner write-alloc */
+#define PMD_SECT_CACHE_MASK (_AT(pmdval_t, 7) << 2)
/*
* + Level 3 descriptor (PTE)
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 40ecd5f514a2..f676febbb270 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -88,6 +88,8 @@ void __init arm_dt_init_cpu_maps(void)
return;
for_each_child_of_node(cpus, cpu) {
+ const __be32 *cell;
+ int prop_bytes;
u32 hwid;
if (of_node_cmp(cpu->type, "cpu"))
@@ -99,7 +101,8 @@ void __init arm_dt_init_cpu_maps(void)
* properties is considered invalid to build the
* cpu_logical_map.
*/
- if (of_property_read_u32(cpu, "reg", &hwid)) {
+ cell = of_get_property(cpu, "reg", &prop_bytes);
+ if (!cell || prop_bytes < sizeof(*cell)) {
pr_debug(" * %s missing reg property\n",
cpu->full_name);
of_node_put(cpu);
@@ -107,10 +110,15 @@ void __init arm_dt_init_cpu_maps(void)
}
/*
- * 8 MSBs must be set to 0 in the DT since the reg property
+ * Bits n:24 must be set to 0 in the DT since the reg property
* defines the MPIDR[23:0].
*/
- if (hwid & ~MPIDR_HWID_BITMASK) {
+ do {
+ hwid = be32_to_cpu(*cell++);
+ prop_bytes -= sizeof(*cell);
+ } while (!hwid && prop_bytes > 0);
+
+ if (prop_bytes || (hwid & ~MPIDR_HWID_BITMASK)) {
of_node_put(cpu);
return;
}
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 709ee1d6d4df..3f1759411d51 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -218,7 +218,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
}
err = ftrace_push_return_trace(old, self_addr, &trace.depth,
- frame_pointer);
+ frame_pointer, NULL);
if (err == -EBUSY) {
*parent = old;
return;
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 0b1e4a93d67e..15d073ae5da2 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -142,6 +142,19 @@ ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE
and r7, #0x1f @ Preserve HPMN
mcr p15, 4, r7, c1, c1, 1 @ HDCR
+ @ Make sure NS-SVC is initialised appropriately
+ mrc p15, 0, r7, c1, c0, 0 @ SCTLR
+ orr r7, #(1 << 5) @ CP15 barriers enabled
+ bic r7, #(3 << 7) @ Clear SED/ITD for v8 (RES0 for v7)
+ bic r7, #(3 << 19) @ WXN and UWXN disabled
+ mcr p15, 0, r7, c1, c0, 0 @ SCTLR
+
+ mrc p15, 0, r7, c0, c0, 0 @ MIDR
+ mcr p15, 4, r7, c0, c0, 0 @ VPIDR
+
+ mrc p15, 0, r7, c0, c0, 5 @ MPIDR
+ mcr p15, 4, r7, c0, c0, 5 @ VMPIDR
+
#if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER)
@ make CNTP_* and CNTPCT accessible from PL1
mrc p15, 0, r7, c0, c1, 1 @ ID_PFR1
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 15063851cd10..b9423491b9d7 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -596,12 +596,6 @@ static struct attribute_group armv7_pmuv1_events_attr_group = {
.attrs = armv7_pmuv1_event_attrs,
};
-static const struct attribute_group *armv7_pmuv1_attr_groups[] = {
- &armv7_pmuv1_events_attr_group,
- &armv7_pmu_format_attr_group,
- NULL,
-};
-
ARMV7_EVENT_ATTR(mem_access, ARMV7_PERFCTR_MEM_ACCESS);
ARMV7_EVENT_ATTR(l1i_cache, ARMV7_PERFCTR_L1_ICACHE_ACCESS);
ARMV7_EVENT_ATTR(l1d_cache_wb, ARMV7_PERFCTR_L1_DCACHE_WB);
@@ -653,12 +647,6 @@ static struct attribute_group armv7_pmuv2_events_attr_group = {
.attrs = armv7_pmuv2_event_attrs,
};
-static const struct attribute_group *armv7_pmuv2_attr_groups[] = {
- &armv7_pmuv2_events_attr_group,
- &armv7_pmu_format_attr_group,
- NULL,
-};
-
/*
* Perf Events' indices
*/
@@ -1208,7 +1196,10 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a8";
cpu_pmu->map_event = armv7_a8_map_event;
- cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv1_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1217,7 +1208,10 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a9";
cpu_pmu->map_event = armv7_a9_map_event;
- cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv1_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1226,7 +1220,10 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a5";
cpu_pmu->map_event = armv7_a5_map_event;
- cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv1_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1236,7 +1233,10 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->name = "armv7_cortex_a15";
cpu_pmu->map_event = armv7_a15_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
- cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv2_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1246,7 +1246,10 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->name = "armv7_cortex_a7";
cpu_pmu->map_event = armv7_a7_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
- cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv2_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1256,7 +1259,10 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->name = "armv7_cortex_a12";
cpu_pmu->map_event = armv7_a12_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
- cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv2_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1264,7 +1270,10 @@ static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
{
int ret = armv7_a12_pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a17";
- cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv2_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return ret;
}
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 994e971a8538..a0affd14086a 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -270,7 +270,7 @@ static bool tk_is_cntvct(const struct timekeeper *tk)
if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER))
return false;
- if (strcmp(tk->tkr_mono.clock->name, "arch_sys_counter") != 0)
+ if (!tk->tkr_mono.clock->archdata.vdso_direct)
return false;
return true;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 75f130ef6504..c94b90d43772 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -158,8 +158,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
{
int i;
- kvm_free_stage2_pgd(kvm);
-
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
if (kvm->vcpus[i]) {
kvm_arch_vcpu_free(kvm->vcpus[i]);
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 29d0b23af2a9..e9a5c0e0c115 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1714,7 +1714,8 @@ int kvm_mmu_init(void)
kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
- hyp_idmap_start < kern_hyp_va(~0UL)) {
+ hyp_idmap_start < kern_hyp_va(~0UL) &&
+ hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
/*
* The idmap page is intersecting with the VA space,
* it is not safe to continue further.
@@ -1893,6 +1894,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
+ kvm_free_stage2_pgd(kvm);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index 3750575c73c5..06332f626565 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -255,6 +255,12 @@ static int __init exynos_pmu_irq_init(struct device_node *node,
return -ENOMEM;
}
+ /*
+ * Clear the OF_POPULATED flag set in of_irq_init so that
+ * later the Exynos PMU platform device won't be skipped.
+ */
+ of_node_clear_flag(node, OF_POPULATED);
+
return 0;
}
diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c
index 5d9bfab279dd..6bb7d9cf1e38 100644
--- a/arch/arm/mach-imx/mach-imx6ul.c
+++ b/arch/arm/mach-imx/mach-imx6ul.c
@@ -64,6 +64,7 @@ static void __init imx6ul_init_machine(void)
if (parent == NULL)
pr_warn("failed to initialize soc device\n");
+ of_platform_default_populate(NULL, NULL, parent);
imx6ul_enet_init();
imx_anatop_init();
imx6ul_pm_init();
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index 58924b3844df..fe708e26d021 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -295,7 +295,7 @@ int imx6_set_lpm(enum mxc_cpu_pwr_mode mode)
val &= ~BM_CLPCR_SBYOS;
if (cpu_is_imx6sl())
val |= BM_CLPCR_BYPASS_PMIC_READY;
- if (cpu_is_imx6sl() || cpu_is_imx6sx())
+ if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul())
val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS;
else
val |= BM_CLPCR_BYP_MMDC_CH1_LPM_HS;
@@ -310,7 +310,7 @@ int imx6_set_lpm(enum mxc_cpu_pwr_mode mode)
val |= 0x3 << BP_CLPCR_STBY_COUNT;
val |= BM_CLPCR_VSTBY;
val |= BM_CLPCR_SBYOS;
- if (cpu_is_imx6sl())
+ if (cpu_is_imx6sl() || cpu_is_imx6sx())
val |= BM_CLPCR_BYPASS_PMIC_READY;
if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul())
val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS;
diff --git a/arch/arm/mach-omap2/cm33xx.c b/arch/arm/mach-omap2/cm33xx.c
index c073fb57dd13..6f2d0aec0513 100644
--- a/arch/arm/mach-omap2/cm33xx.c
+++ b/arch/arm/mach-omap2/cm33xx.c
@@ -220,9 +220,6 @@ static int am33xx_cm_wait_module_ready(u8 part, s16 inst, u16 clkctrl_offs,
{
int i = 0;
- if (!clkctrl_offs)
- return 0;
-
omap_test_timeout(_is_module_ready(inst, clkctrl_offs),
MAX_MODULE_READY_TIME, i);
@@ -246,9 +243,6 @@ static int am33xx_cm_wait_module_idle(u8 part, s16 inst, u16 clkctrl_offs,
{
int i = 0;
- if (!clkctrl_offs)
- return 0;
-
omap_test_timeout((_clkctrl_idlest(inst, clkctrl_offs) ==
CLKCTRL_IDLEST_DISABLED),
MAX_MODULE_READY_TIME, i);
diff --git a/arch/arm/mach-omap2/cminst44xx.c b/arch/arm/mach-omap2/cminst44xx.c
index 2c0e07ed6b99..2ab27ade136a 100644
--- a/arch/arm/mach-omap2/cminst44xx.c
+++ b/arch/arm/mach-omap2/cminst44xx.c
@@ -278,9 +278,6 @@ static int omap4_cminst_wait_module_ready(u8 part, s16 inst, u16 clkctrl_offs,
{
int i = 0;
- if (!clkctrl_offs)
- return 0;
-
omap_test_timeout(_is_module_ready(part, inst, clkctrl_offs),
MAX_MODULE_READY_TIME, i);
@@ -304,9 +301,6 @@ static int omap4_cminst_wait_module_idle(u8 part, s16 inst, u16 clkctrl_offs,
{
int i = 0;
- if (!clkctrl_offs)
- return 0;
-
omap_test_timeout((_clkctrl_idlest(part, inst, clkctrl_offs) ==
CLKCTRL_IDLEST_DISABLED),
MAX_MODULE_DISABLE_TIME, i);
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index 0c4754386532..369f95a703ac 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -322,34 +322,25 @@ static void irq_save_secure_context(void)
#endif
#ifdef CONFIG_HOTPLUG_CPU
-static int irq_cpu_hotplug_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
+static int omap_wakeupgen_cpu_online(unsigned int cpu)
{
- unsigned int cpu = (unsigned int)hcpu;
-
- /*
- * Corresponding FROZEN transitions do not have to be handled,
- * they are handled by at a higher level
- * (drivers/cpuidle/coupled.c).
- */
- switch (action) {
- case CPU_ONLINE:
- wakeupgen_irqmask_all(cpu, 0);
- break;
- case CPU_DEAD:
- wakeupgen_irqmask_all(cpu, 1);
- break;
- }
- return NOTIFY_OK;
+ wakeupgen_irqmask_all(cpu, 0);
+ return 0;
}
-static struct notifier_block irq_hotplug_notifier = {
- .notifier_call = irq_cpu_hotplug_notify,
-};
+static int omap_wakeupgen_cpu_dead(unsigned int cpu)
+{
+ wakeupgen_irqmask_all(cpu, 1);
+ return 0;
+}
static void __init irq_hotplug_init(void)
{
- register_hotcpu_notifier(&irq_hotplug_notifier);
+ cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "arm/omap-wake:online",
+ omap_wakeupgen_cpu_online, NULL);
+ cpuhp_setup_state_nocalls(CPUHP_ARM_OMAP_WAKE_DEAD,
+ "arm/omap-wake:dead", NULL,
+ omap_wakeupgen_cpu_dead);
}
#else
static void __init irq_hotplug_init(void)
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 5b709383381c..1052b29697b8 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1053,6 +1053,10 @@ static int _omap4_wait_target_disable(struct omap_hwmod *oh)
if (oh->flags & HWMOD_NO_IDLEST)
return 0;
+ if (!oh->prcm.omap4.clkctrl_offs &&
+ !(oh->prcm.omap4.flags & HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET))
+ return 0;
+
return omap_cm_wait_module_idle(oh->clkdm->prcm_partition,
oh->clkdm->cm_inst,
oh->prcm.omap4.clkctrl_offs, 0);
@@ -2971,6 +2975,10 @@ static int _omap4_wait_target_ready(struct omap_hwmod *oh)
if (!_find_mpu_rt_port(oh))
return 0;
+ if (!oh->prcm.omap4.clkctrl_offs &&
+ !(oh->prcm.omap4.flags & HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET))
+ return 0;
+
/* XXX check module SIDLEMODE, hardreset status */
return omap_cm_wait_module_ready(oh->clkdm->prcm_partition,
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index 4041bad79a9a..78904017f18c 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -443,8 +443,12 @@ struct omap_hwmod_omap2_prcm {
* HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT: Some IP blocks don't have a PRCM
* module-level context loss register associated with them; this
* flag bit should be set in those cases
+ * HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET: Some IP blocks have a valid CLKCTRL
+ * offset of zero; this flag bit should be set in those cases to
+ * distinguish from hwmods that have no clkctrl offset.
*/
#define HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT (1 << 0)
+#define HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET (1 << 1)
/**
* struct omap_hwmod_omap4_prcm - OMAP4-specific PRCM data
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
index 55c5878577f4..e2d84aa7f595 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
@@ -29,6 +29,7 @@
#define CLKCTRL(oh, clkctrl) ((oh).prcm.omap4.clkctrl_offs = (clkctrl))
#define RSTCTRL(oh, rstctrl) ((oh).prcm.omap4.rstctrl_offs = (rstctrl))
#define RSTST(oh, rstst) ((oh).prcm.omap4.rstst_offs = (rstst))
+#define PRCM_FLAGS(oh, flag) ((oh).prcm.omap4.flags = (flag))
/*
* 'l3' class
@@ -1296,6 +1297,7 @@ static void omap_hwmod_am33xx_clkctrl(void)
CLKCTRL(am33xx_i2c1_hwmod, AM33XX_CM_WKUP_I2C0_CLKCTRL_OFFSET);
CLKCTRL(am33xx_wd_timer1_hwmod, AM33XX_CM_WKUP_WDT1_CLKCTRL_OFFSET);
CLKCTRL(am33xx_rtc_hwmod, AM33XX_CM_RTC_RTC_CLKCTRL_OFFSET);
+ PRCM_FLAGS(am33xx_rtc_hwmod, HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET);
CLKCTRL(am33xx_mmc2_hwmod, AM33XX_CM_PER_MMC2_CLKCTRL_OFFSET);
CLKCTRL(am33xx_gpmc_hwmod, AM33XX_CM_PER_GPMC_CLKCTRL_OFFSET);
CLKCTRL(am33xx_l4_ls_hwmod, AM33XX_CM_PER_L4LS_CLKCTRL_OFFSET);
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index d72ee6185d5e..1cc4a6f3954e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -722,8 +722,20 @@ static struct omap_hwmod omap3xxx_dss_dispc_hwmod = {
* display serial interface controller
*/
+static struct omap_hwmod_class_sysconfig omap3xxx_dsi_sysc = {
+ .rev_offs = 0x0000,
+ .sysc_offs = 0x0010,
+ .syss_offs = 0x0014,
+ .sysc_flags = (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+ SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
+ SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+ .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+ .sysc_fields = &omap_hwmod_sysc_type1,
+};
+
static struct omap_hwmod_class omap3xxx_dsi_hwmod_class = {
.name = "dsi",
+ .sysc = &omap3xxx_dsi_sysc,
};
static struct omap_hwmod_irq_info omap3xxx_dsi1_irqs[] = {
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index 7245f3359564..d6159f8ef0c2 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -137,6 +137,18 @@ static struct pxa2xx_udc_mach_info udc_info __initdata = {
// no D+ pullup; lubbock can't connect/disconnect in software
};
+static void lubbock_init_pcmcia(void)
+{
+ struct clk *clk;
+
+ /* Add an alias for the SA1111 PCMCIA clock */
+ clk = clk_get_sys("pxa2xx-pcmcia", NULL);
+ if (!IS_ERR(clk)) {
+ clkdev_create(clk, NULL, "1800");
+ clk_put(clk);
+ }
+}
+
static struct resource sa1111_resources[] = {
[0] = {
.start = 0x10000000,
@@ -467,6 +479,8 @@ static void __init lubbock_init(void)
pxa_set_btuart_info(NULL);
pxa_set_stuart_info(NULL);
+ lubbock_init_pcmcia();
+
clk_add_alias("SA1111_CLK", NULL, "GPIO11_CLK", NULL);
pxa_set_udc_info(&udc_info);
pxa_set_fb_info(NULL, &sharp_lm8v31);
diff --git a/arch/arm/mach-sa1100/clock.c b/arch/arm/mach-sa1100/clock.c
index cbf53bb9c814..0db46895c82a 100644
--- a/arch/arm/mach-sa1100/clock.c
+++ b/arch/arm/mach-sa1100/clock.c
@@ -125,6 +125,8 @@ static unsigned long clk_36864_get_rate(struct clk *clk)
}
static struct clkops clk_36864_ops = {
+ .enable = clk_cpu_enable,
+ .disable = clk_cpu_disable,
.get_rate = clk_36864_get_rate,
};
@@ -140,9 +142,8 @@ static struct clk_lookup sa11xx_clkregs[] = {
CLKDEV_INIT(NULL, "OSTIMER0", &clk_36864),
};
-static int __init sa11xx_clk_init(void)
+int __init sa11xx_clk_init(void)
{
clkdev_add_table(sa11xx_clkregs, ARRAY_SIZE(sa11xx_clkregs));
return 0;
}
-core_initcall(sa11xx_clk_init);
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index 345e63f4eb71..3e09beddb6e8 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -34,6 +34,7 @@
#include <mach/hardware.h>
#include <mach/irqs.h>
+#include <mach/reset.h>
#include "generic.h"
#include <clocksource/pxa.h>
@@ -95,6 +96,8 @@ static void sa1100_power_off(void)
void sa11x0_restart(enum reboot_mode mode, const char *cmd)
{
+ clear_reset_status(RESET_STATUS_ALL);
+
if (mode == REBOOT_SOFT) {
/* Jump into ROM at address 0 */
soft_restart(0);
@@ -388,6 +391,7 @@ void __init sa1100_init_irq(void)
sa11x0_init_irq_nodt(IRQ_GPIO0_SC, irq_resource.start);
sa1100_init_gpio();
+ sa11xx_clk_init();
}
/*
diff --git a/arch/arm/mach-sa1100/generic.h b/arch/arm/mach-sa1100/generic.h
index 0d92e119b36b..68199b603ff7 100644
--- a/arch/arm/mach-sa1100/generic.h
+++ b/arch/arm/mach-sa1100/generic.h
@@ -44,3 +44,5 @@ int sa11x0_pm_init(void);
#else
static inline int sa11x0_pm_init(void) { return 0; }
#endif
+
+int sa11xx_clk_init(void);
diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c
index 8d478f1da265..d1ecaf37d142 100644
--- a/arch/arm/mach-shmobile/platsmp-scu.c
+++ b/arch/arm/mach-shmobile/platsmp-scu.c
@@ -21,26 +21,14 @@
static phys_addr_t shmobile_scu_base_phys;
static void __iomem *shmobile_scu_base;
-static int shmobile_smp_scu_notifier_call(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+static int shmobile_scu_cpu_prepare(unsigned int cpu)
{
- unsigned int cpu = (long)hcpu;
-
- switch (action) {
- case CPU_UP_PREPARE:
- /* For this particular CPU register SCU SMP boot vector */
- shmobile_smp_hook(cpu, virt_to_phys(shmobile_boot_scu),
- shmobile_scu_base_phys);
- break;
- };
-
- return NOTIFY_OK;
+ /* For this particular CPU register SCU SMP boot vector */
+ shmobile_smp_hook(cpu, virt_to_phys(shmobile_boot_scu),
+ shmobile_scu_base_phys);
+ return 0;
}
-static struct notifier_block shmobile_smp_scu_notifier = {
- .notifier_call = shmobile_smp_scu_notifier_call,
-};
-
void __init shmobile_smp_scu_prepare_cpus(phys_addr_t scu_base_phys,
unsigned int max_cpus)
{
@@ -54,7 +42,9 @@ void __init shmobile_smp_scu_prepare_cpus(phys_addr_t scu_base_phys,
scu_power_mode(shmobile_scu_base, SCU_PM_NORMAL);
/* Use CPU notifier for reset vector control */
- register_cpu_notifier(&shmobile_smp_scu_notifier);
+ cpuhp_setup_state_nocalls(CPUHP_ARM_SHMOBILE_SCU_PREPARE,
+ "arm/shmobile-scu:prepare",
+ shmobile_scu_cpu_prepare, NULL);
}
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
index 62437b57813e..73e3adbc1330 100644
--- a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
@@ -41,39 +41,26 @@
#define REGULATOR_IRQ_MASK BIT(2) /* IRQ2, active low */
-static void __iomem *irqc;
-
-static const u8 da9063_mask_regs[] = {
- DA9063_REG_IRQ_MASK_A,
- DA9063_REG_IRQ_MASK_B,
- DA9063_REG_IRQ_MASK_C,
- DA9063_REG_IRQ_MASK_D,
-};
-
-/* DA9210 System Control and Event Registers */
+/* start of DA9210 System Control and Event Registers */
#define DA9210_REG_MASK_A 0x54
-#define DA9210_REG_MASK_B 0x55
-
-static const u8 da9210_mask_regs[] = {
- DA9210_REG_MASK_A,
- DA9210_REG_MASK_B,
-};
-
-static void da9xxx_mask_irqs(struct i2c_client *client, const u8 regs[],
- unsigned int nregs)
-{
- unsigned int i;
- dev_info(&client->dev, "Masking %s interrupt sources\n", client->name);
+static void __iomem *irqc;
- for (i = 0; i < nregs; i++) {
- int error = i2c_smbus_write_byte_data(client, regs[i], ~0);
- if (error) {
- dev_err(&client->dev, "i2c error %d\n", error);
- return;
- }
- }
-}
+/* first byte sets the memory pointer, following are consecutive reg values */
+static u8 da9063_irq_clr[] = { DA9063_REG_IRQ_MASK_A, 0xff, 0xff, 0xff, 0xff };
+static u8 da9210_irq_clr[] = { DA9210_REG_MASK_A, 0xff, 0xff };
+
+static struct i2c_msg da9xxx_msgs[2] = {
+ {
+ .addr = 0x58,
+ .len = ARRAY_SIZE(da9063_irq_clr),
+ .buf = da9063_irq_clr,
+ }, {
+ .addr = 0x68,
+ .len = ARRAY_SIZE(da9210_irq_clr),
+ .buf = da9210_irq_clr,
+ },
+};
static int regulator_quirk_notify(struct notifier_block *nb,
unsigned long action, void *data)
@@ -93,12 +80,15 @@ static int regulator_quirk_notify(struct notifier_block *nb,
client = to_i2c_client(dev);
dev_dbg(dev, "Detected %s\n", client->name);
- if ((client->addr == 0x58 && !strcmp(client->name, "da9063")))
- da9xxx_mask_irqs(client, da9063_mask_regs,
- ARRAY_SIZE(da9063_mask_regs));
- else if (client->addr == 0x68 && !strcmp(client->name, "da9210"))
- da9xxx_mask_irqs(client, da9210_mask_regs,
- ARRAY_SIZE(da9210_mask_regs));
+ if ((client->addr == 0x58 && !strcmp(client->name, "da9063")) ||
+ (client->addr == 0x68 && !strcmp(client->name, "da9210"))) {
+ int ret;
+
+ dev_info(&client->dev, "clearing da9063/da9210 interrupts\n");
+ ret = i2c_transfer(client->adapter, da9xxx_msgs, ARRAY_SIZE(da9xxx_msgs));
+ if (ret != ARRAY_SIZE(da9xxx_msgs))
+ dev_err(&client->dev, "i2c error %d\n", ret);
+ }
mon = ioread32(irqc + IRQC_MONITOR);
if (mon & REGULATOR_IRQ_MASK)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6344913f0804..30fe03f95c85 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -137,7 +137,7 @@ void __init init_default_cache_policy(unsigned long pmd)
initial_pmd_value = pmd;
- pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE;
+ pmd &= PMD_SECT_CACHE_MASK;
for (i = 0; i < ARRAY_SIZE(cache_policies); i++)
if (cache_policies[i].pmd == pmd) {
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index a7123b4e129d..d00d52c9de3e 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -16,6 +16,7 @@
#include <asm/hwcap.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
+#include <asm/memory.h>
#include "proc-macros.S"
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 3d2cef6488ea..f193414d0f6f 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -170,9 +170,6 @@ static int xen_starting_cpu(unsigned int cpu)
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
- /* Direct vCPU id mapping for ARM guests. */
- per_cpu(xen_vcpu_id, cpu) = cpu;
-
info.mfn = virt_to_gfn(vcpup);
info.offset = xen_offset_in_page(vcpup);
@@ -330,6 +327,7 @@ static int __init xen_guest_init(void)
{
struct xen_add_to_physmap xatp;
struct shared_info *shared_info_page = NULL;
+ int cpu;
if (!xen_domain())
return 0;
@@ -380,7 +378,8 @@ static int __init xen_guest_init(void)
return -ENOMEM;
/* Direct vCPU id mapping for ARM guests. */
- per_cpu(xen_vcpu_id, 0) = 0;
+ for_each_possible_cpu(cpu)
+ per_cpu(xen_vcpu_id, cpu) = cpu;
xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index bc3f00f586f1..7d6bcf6339e1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -4,6 +4,8 @@ config ARM64
select ACPI_GENERIC_GSI if ACPI
select ACPI_REDUCED_HARDWARE_ONLY if ACPI
select ACPI_MCFG if ACPI
+ select ACPI_SPCR_TABLE if ACPI
+ select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -102,10 +104,8 @@ config ARM64
select NO_BOOTMEM
select OF
select OF_EARLY_FLATTREE
- select OF_NUMA if NUMA && OF
select OF_RESERVED_MEM
select PCI_ECAM if ACPI
- select PERF_USE_VMALLOC
select POWER_RESET
select POWER_SUPPLY
select SPARSE_IRQ
@@ -122,6 +122,9 @@ config ARCH_PHYS_ADDR_T_64BIT
config MMU
def_bool y
+config DEBUG_RODATA
+ def_bool y
+
config ARM64_PAGE_SHIFT
int
default 16 if ARM64_64K_PAGES
@@ -415,18 +418,13 @@ config ARM64_ERRATUM_845719
config ARM64_ERRATUM_843419
bool "Cortex-A53: 843419: A load or store might access an incorrect address"
- depends on MODULES
default y
- select ARM64_MODULE_CMODEL_LARGE
+ select ARM64_MODULE_CMODEL_LARGE if MODULES
help
- This option builds kernel modules using the large memory model in
- order to avoid the use of the ADRP instruction, which can cause
- a subsequent memory access to use an incorrect address on Cortex-A53
- parts up to r0p4.
-
- Note that the kernel itself must be linked with a version of ld
- which fixes potentially affected ADRP instructions through the
- use of veneers.
+ This option links the kernel with '--fix-cortex-a53-843419' and
+ builds modules using the large memory model in order to avoid the use
+ of the ADRP instruction, which can cause a subsequent memory access
+ to use an incorrect address on Cortex-A53 parts up to r0p4.
If unsure, say Y.
@@ -582,7 +580,8 @@ config HOTPLUG_CPU
# Common NUMA Features
config NUMA
bool "Numa Memory Allocation and Scheduler Support"
- depends on SMP
+ select ACPI_NUMA if ACPI
+ select OF_NUMA
help
Enable NUMA (Non Uniform Memory Access) support.
@@ -603,11 +602,18 @@ config USE_PERCPU_NUMA_NODE_ID
def_bool y
depends on NUMA
+config HAVE_SETUP_PER_CPU_AREA
+ def_bool y
+ depends on NUMA
+
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+ def_bool y
+ depends on NUMA
+
source kernel/Kconfig.preempt
source kernel/Kconfig.hz
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
- depends on !HIBERNATION
def_bool y
config ARCH_HAS_HOLES_MEMORYMODEL
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 0cc758cdd0dc..b661fe742615 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -49,16 +49,6 @@ config DEBUG_SET_MODULE_RONX
If in doubt, say Y.
-config DEBUG_RODATA
- bool "Make kernel text and rodata read-only"
- default y
- help
- If this is set, kernel text and rodata will be made read-only. This
- is to help catch accidental or malicious attempts to change the
- kernel's executable code.
-
- If in doubt, say Y.
-
config DEBUG_ALIGN_RODATA
depends on DEBUG_RODATA
bool "Align linker sections up to SECTION_SIZE"
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index be5d824ebdba..a8c77c72a831 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -93,6 +93,7 @@ config ARCH_MVEBU
select ARMADA_CP110_SYSCON
select ARMADA_37XX_CLK
select MVEBU_ODMI
+ select MVEBU_PIC
help
This enables support for Marvell EBU familly, including:
- Armada 3700 SoC Family
@@ -159,7 +160,6 @@ config ARCH_TEGRA
select CLKSRC_MMIO
select CLKSRC_OF
select GENERIC_CLOCKEVENTS
- select HAVE_CLK
select PINCTRL
select RESET_CONTROLLER
help
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 5b54f8c021d8..ab51aed6b6c1 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -18,6 +18,14 @@ ifneq ($(CONFIG_RELOCATABLE),)
LDFLAGS_vmlinux += -pie -Bsymbolic
endif
+ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
+ ifeq ($(call ld-option, --fix-cortex-a53-843419),)
+$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum)
+ else
+LDFLAGS_vmlinux += --fix-cortex-a53-843419
+ endif
+endif
+
KBUILD_DEFCONFIG := defconfig
# Check for binutils support for specific extensions
@@ -38,10 +46,12 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
KBUILD_CPPFLAGS += -mbig-endian
AS += -EB
LD += -EB
+UTS_MACHINE := aarch64_be
else
KBUILD_CPPFLAGS += -mlittle-endian
AS += -EL
LD += -EL
+UTS_MACHINE := aarch64
endif
CHECKFLAGS += -D__aarch64__
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 445aa678f914..c2b9bcb0ef61 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -255,10 +255,10 @@
/* Local timer */
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
};
timer0: timer0@ffc03000 {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index e502c24b0ac7..bf6c8d051002 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -102,13 +102,13 @@
timer {
compatible = "arm,armv8-timer";
interrupts = <GIC_PPI 13
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 14
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 11
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 10
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>;
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>;
};
xtal: xtal-clk {
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index f1c2c713f9b0..c29dab9d1834 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -110,10 +110,10 @@
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 0 0xff01>, /* Secure Phys IRQ */
- <1 13 0xff01>, /* Non-secure Phys IRQ */
- <1 14 0xff01>, /* Virt IRQ */
- <1 15 0xff01>; /* Hyp IRQ */
+ interrupts = <1 0 0xff08>, /* Secure Phys IRQ */
+ <1 13 0xff08>, /* Non-secure Phys IRQ */
+ <1 14 0xff08>, /* Virt IRQ */
+ <1 15 0xff08>; /* Hyp IRQ */
clock-frequency = <50000000>;
};
diff --git a/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi b/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi
new file mode 120000
index 000000000000..3937b77cb310
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/bcm2835-rpi.dtsi
@@ -0,0 +1 @@
+../../../../arm/boot/dts/bcm2835-rpi.dtsi \ No newline at end of file
diff --git a/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts b/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts
index 6f47dd2bb1db..7841b724e340 100644
--- a/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts
+++ b/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts
@@ -1,7 +1,7 @@
/dts-v1/;
#include "bcm2837.dtsi"
-#include "../../../../arm/boot/dts/bcm2835-rpi.dtsi"
-#include "../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi"
+#include "bcm2835-rpi.dtsi"
+#include "bcm283x-rpi-smsc9514.dtsi"
/ {
compatible = "raspberrypi,3-model-b", "brcm,bcm2837";
diff --git a/arch/arm64/boot/dts/broadcom/bcm2837.dtsi b/arch/arm64/boot/dts/broadcom/bcm2837.dtsi
index f2a31d06845d..8216bbb29fe0 100644
--- a/arch/arm64/boot/dts/broadcom/bcm2837.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm2837.dtsi
@@ -1,4 +1,4 @@
-#include "../../../../arm/boot/dts/bcm283x.dtsi"
+#include "bcm283x.dtsi"
/ {
compatible = "brcm,bcm2836";
diff --git a/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi b/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi
new file mode 120000
index 000000000000..dca7c057d5a5
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/bcm283x-rpi-smsc9514.dtsi
@@ -0,0 +1 @@
+../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi \ No newline at end of file
diff --git a/arch/arm64/boot/dts/broadcom/bcm283x.dtsi b/arch/arm64/boot/dts/broadcom/bcm283x.dtsi
new file mode 120000
index 000000000000..5f54e4cab99b
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/bcm283x.dtsi
@@ -0,0 +1 @@
+../../../../arm/boot/dts/bcm283x.dtsi \ No newline at end of file
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index f53b0955bfd3..d4a12fad8afd 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -88,13 +88,13 @@
timer {
compatible = "arm,armv8-timer";
interrupts = <GIC_PPI 13 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 14 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 11 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 10 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>;
+ IRQ_TYPE_LEVEL_LOW)>;
};
pmu {
diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
index 2eb9b225f0bc..04dc8a8d1539 100644
--- a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
@@ -354,10 +354,10 @@
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xff01>,
- <1 14 0xff01>,
- <1 11 0xff01>,
- <1 10 0xff01>;
+ interrupts = <1 13 4>,
+ <1 14 4>,
+ <1 11 4>,
+ <1 10 4>;
};
pmu {
diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi
index ca663dfe5189..162831546e18 100644
--- a/arch/arm64/boot/dts/exynos/exynos7.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi
@@ -473,10 +473,10 @@
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xff01>,
- <1 14 0xff01>,
- <1 11 0xff01>,
- <1 10 0xff01>;
+ interrupts = <1 13 0xff08>,
+ <1 14 0xff08>,
+ <1 11 0xff08>,
+ <1 10 0xff08>;
};
pmu_system_controller: system-controller@105c0000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index e669fbd7f9c3..a67e210e2019 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -119,10 +119,10 @@
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0x1>, /* Physical Secure PPI */
- <1 14 0x1>, /* Physical Non-Secure PPI */
- <1 11 0x1>, /* Virtual PPI */
- <1 10 0x1>; /* Hypervisor PPI */
+ interrupts = <1 13 0xf08>, /* Physical Secure PPI */
+ <1 14 0xf08>, /* Physical Non-Secure PPI */
+ <1 11 0xf08>, /* Virtual PPI */
+ <1 10 0xf08>; /* Hypervisor PPI */
};
pmu {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index 21023a388c29..e3b6034ea5d9 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -191,10 +191,10 @@
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0x8>, /* Physical Secure PPI, active-low */
- <1 14 0x8>, /* Physical Non-Secure PPI, active-low */
- <1 11 0x8>, /* Virtual PPI, active-low */
- <1 10 0x8>; /* Hypervisor PPI, active-low */
+ interrupts = <1 13 4>, /* Physical Secure PPI, active-low */
+ <1 14 4>, /* Physical Non-Secure PPI, active-low */
+ <1 11 4>, /* Virtual PPI, active-low */
+ <1 10 4>; /* Hypervisor PPI, active-low */
};
pmu {
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index eab1a42fb934..c2a6745f168c 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -122,10 +122,10 @@
timer {
compatible = "arm,armv8-timer";
- interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>;
+ interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
};
odmi: odmi@300000 {
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
index c223915f0907..d73bdc8c9115 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
@@ -129,10 +129,10 @@
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 4>,
+ <1 14 4>,
+ <1 11 4>,
+ <1 10 4>;
};
soc {
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index e595f22e7e4b..3e2e51fbd2bc 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -65,10 +65,10 @@
timer {
compatible = "arm,armv8-timer";
interrupt-parent = <&gic>;
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
};
amba_apu {
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 5c888049d061..6b2aa0fd6cd0 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -216,7 +216,7 @@ static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
err = blkcipher_walk_done(desc, &walk,
walk.nbytes % AES_BLOCK_SIZE);
}
- if (nbytes) {
+ if (walk.nbytes % AES_BLOCK_SIZE) {
u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
u8 __aligned(8) tail[AES_BLOCK_SIZE];
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index f43d2c44c765..44e1d7f10add 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,4 +1,3 @@
-generic-y += bug.h
generic-y += bugs.h
generic-y += clkdev.h
generic-y += cputime.h
@@ -10,7 +9,6 @@ generic-y += dma-contiguous.h
generic-y += early_ioremap.h
generic-y += emergency-restart.h
generic-y += errno.h
-generic-y += ftrace.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
@@ -27,12 +25,10 @@ generic-y += mman.h
generic-y += msgbuf.h
generic-y += msi.h
generic-y += mutex.h
-generic-y += pci.h
generic-y += poll.h
generic-y += preempt.h
generic-y += resource.h
generic-y += rwsem.h
-generic-y += sections.h
generic-y += segment.h
generic-y += sembuf.h
generic-y += serial.h
@@ -45,7 +41,6 @@ generic-y += swab.h
generic-y += switch_to.h
generic-y += termbits.h
generic-y += termios.h
-generic-y += topology.h
generic-y += trace_clock.h
generic-y += types.h
generic-y += unaligned.h
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 5420cb0fcb3e..e517088d635f 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -12,7 +12,7 @@
#ifndef _ASM_ACPI_H
#define _ASM_ACPI_H
-#include <linux/mm.h>
+#include <linux/memblock.h>
#include <linux/psci.h>
#include <asm/cputype.h>
@@ -32,7 +32,11 @@
static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
acpi_size size)
{
- if (!page_is_ram(phys >> PAGE_SHIFT))
+ /*
+ * EFI's reserve_regions() call adds memory with the WB attribute
+ * to memblock via early_init_dt_add_memory_arch().
+ */
+ if (!memblock_is_memory(phys))
return ioremap(phys, size);
return ioremap_cache(phys, size);
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 8746ff6abd77..55101bd86b98 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -2,6 +2,7 @@
#define __ASM_ALTERNATIVE_H
#include <asm/cpufeature.h>
+#include <asm/insn.h>
#ifndef __ASSEMBLY__
@@ -90,34 +91,55 @@ void apply_alternatives(void *start, size_t length);
.endm
/*
- * Begin an alternative code sequence.
+ * Alternative sequences
+ *
+ * The code for the case where the capability is not present will be
+ * assembled and linked as normal. There are no restrictions on this
+ * code.
+ *
+ * The code for the case where the capability is present will be
+ * assembled into a special section to be used for dynamic patching.
+ * Code for that case must:
+ *
+ * 1. Be exactly the same length (in bytes) as the default code
+ * sequence.
*
- * The code that follows this macro will be assembled and linked as
- * normal. There are no restrictions on this code.
+ * 2. Not contain a branch target that is used outside of the
+ * alternative sequence it is defined in (branches into an
+ * alternative sequence are not fixed up).
+ */
+
+/*
+ * Begin an alternative code sequence.
*/
.macro alternative_if_not cap
+ .set .Lasm_alt_mode, 0
.pushsection .altinstructions, "a"
altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
.popsection
661:
.endm
+.macro alternative_if cap
+ .set .Lasm_alt_mode, 1
+ .pushsection .altinstructions, "a"
+ altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
+ .popsection
+ .pushsection .altinstr_replacement, "ax"
+ .align 2 /* So GAS knows label 661 is suitably aligned */
+661:
+.endm
+
/*
- * Provide the alternative code sequence.
- *
- * The code that follows this macro is assembled into a special
- * section to be used for dynamic patching. Code that follows this
- * macro must:
- *
- * 1. Be exactly the same length (in bytes) as the default code
- * sequence.
- *
- * 2. Not contain a branch target that is used outside of the
- * alternative sequence it is defined in (branches into an
- * alternative sequence are not fixed up).
+ * Provide the other half of the alternative code sequence.
*/
.macro alternative_else
-662: .pushsection .altinstr_replacement, "ax"
+662:
+ .if .Lasm_alt_mode==0
+ .pushsection .altinstr_replacement, "ax"
+ .else
+ .popsection
+ .endif
663:
.endm
@@ -125,11 +147,25 @@ void apply_alternatives(void *start, size_t length);
* Complete an alternative code sequence.
*/
.macro alternative_endif
-664: .popsection
+664:
+ .if .Lasm_alt_mode==0
+ .popsection
+ .endif
.org . - (664b-663b) + (662b-661b)
.org . - (662b-661b) + (664b-663b)
.endm
+/*
+ * Provides a trivial alternative or default sequence consisting solely
+ * of NOPs. The number of NOPs is chosen automatically to match the
+ * previous case.
+ */
+.macro alternative_else_nop_endif
+alternative_else
+ nops (662b-661b) / AARCH64_INSN_SIZE
+alternative_endif
+.endm
+
#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \
alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 8ec88e5b290f..fc2a0cb47b2c 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -28,6 +28,7 @@
#define ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
#define ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
#define ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+#define ICC_BPR1_EL1 sys_reg(3, 0, 12, 12, 3)
#define ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5)
@@ -165,6 +166,11 @@ static inline void gic_write_sre(u32 val)
isb();
}
+static inline void gic_write_bpr1(u32 val)
+{
+ asm volatile("msr_s " __stringify(ICC_BPR1_EL1) ", %0" : : "r" (val));
+}
+
#define gic_read_typer(c) readq_relaxed(c)
#define gic_write_irouter(v, c) writeq_relaxed(v, c)
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index fbe0ca31a99c..eaa5bbe3fa87 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -20,13 +20,55 @@
#define __ASM_ARCH_TIMER_H
#include <asm/barrier.h>
+#include <asm/sysreg.h>
#include <linux/bug.h>
#include <linux/init.h>
+#include <linux/jump_label.h>
#include <linux/types.h>
#include <clocksource/arm_arch_timer.h>
+#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585)
+extern struct static_key_false arch_timer_read_ool_enabled;
+#define needs_fsl_a008585_workaround() \
+ static_branch_unlikely(&arch_timer_read_ool_enabled)
+#else
+#define needs_fsl_a008585_workaround() false
+#endif
+
+u32 __fsl_a008585_read_cntp_tval_el0(void);
+u32 __fsl_a008585_read_cntv_tval_el0(void);
+u64 __fsl_a008585_read_cntvct_el0(void);
+
+/*
+ * The number of retries is an arbitrary value well beyond the highest number
+ * of iterations the loop has been observed to take.
+ */
+#define __fsl_a008585_read_reg(reg) ({ \
+ u64 _old, _new; \
+ int _retries = 200; \
+ \
+ do { \
+ _old = read_sysreg(reg); \
+ _new = read_sysreg(reg); \
+ _retries--; \
+ } while (unlikely(_old != _new) && _retries); \
+ \
+ WARN_ON_ONCE(!_retries); \
+ _new; \
+})
+
+#define arch_timer_reg_read_stable(reg) \
+({ \
+ u64 _val; \
+ if (needs_fsl_a008585_workaround()) \
+ _val = __fsl_a008585_read_##reg(); \
+ else \
+ _val = read_sysreg(reg); \
+ _val; \
+})
+
/*
* These register accessors are marked inline so the compiler can
* nicely work out which register we want, and chuck away the rest of
@@ -38,19 +80,19 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("msr cntp_ctl_el0, %0" : : "r" (val));
+ write_sysreg(val, cntp_ctl_el0);
break;
case ARCH_TIMER_REG_TVAL:
- asm volatile("msr cntp_tval_el0, %0" : : "r" (val));
+ write_sysreg(val, cntp_tval_el0);
break;
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("msr cntv_ctl_el0, %0" : : "r" (val));
+ write_sysreg(val, cntv_ctl_el0);
break;
case ARCH_TIMER_REG_TVAL:
- asm volatile("msr cntv_tval_el0, %0" : : "r" (val));
+ write_sysreg(val, cntv_tval_el0);
break;
}
}
@@ -61,48 +103,38 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
static __always_inline
u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
{
- u32 val;
-
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("mrs %0, cntp_ctl_el0" : "=r" (val));
- break;
+ return read_sysreg(cntp_ctl_el0);
case ARCH_TIMER_REG_TVAL:
- asm volatile("mrs %0, cntp_tval_el0" : "=r" (val));
- break;
+ return arch_timer_reg_read_stable(cntp_tval_el0);
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("mrs %0, cntv_ctl_el0" : "=r" (val));
- break;
+ return read_sysreg(cntv_ctl_el0);
case ARCH_TIMER_REG_TVAL:
- asm volatile("mrs %0, cntv_tval_el0" : "=r" (val));
- break;
+ return arch_timer_reg_read_stable(cntv_tval_el0);
}
}
- return val;
+ BUG();
}
static inline u32 arch_timer_get_cntfrq(void)
{
- u32 val;
- asm volatile("mrs %0, cntfrq_el0" : "=r" (val));
- return val;
+ return read_sysreg(cntfrq_el0);
}
static inline u32 arch_timer_get_cntkctl(void)
{
- u32 cntkctl;
- asm volatile("mrs %0, cntkctl_el1" : "=r" (cntkctl));
- return cntkctl;
+ return read_sysreg(cntkctl_el1);
}
static inline void arch_timer_set_cntkctl(u32 cntkctl)
{
- asm volatile("msr cntkctl_el1, %0" : : "r" (cntkctl));
+ write_sysreg(cntkctl, cntkctl_el1);
}
static inline u64 arch_counter_get_cntpct(void)
@@ -116,12 +148,8 @@ static inline u64 arch_counter_get_cntpct(void)
static inline u64 arch_counter_get_cntvct(void)
{
- u64 cval;
-
isb();
- asm volatile("mrs %0, cntvct_el0" : "=r" (cval));
-
- return cval;
+ return arch_timer_reg_read_stable(cntvct_el0);
}
static inline int arch_timer_arch_init(void)
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index d5025c69ca81..28bfe6132eb6 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -87,6 +87,15 @@
.endm
/*
+ * NOP sequence
+ */
+ .macro nops, num
+ .rept \num
+ nop
+ .endr
+ .endm
+
+/*
* Emit an entry into the exception table
*/
.macro _asm_extable, from, to
@@ -216,11 +225,26 @@ lr .req x30 // link register
.macro mmid, rd, rn
ldr \rd, [\rn, #MM_CONTEXT_ID]
.endm
+/*
+ * read_ctr - read CTR_EL0. If the system has mismatched
+ * cache line sizes, provide the system wide safe value
+ * from arm64_ftr_reg_ctrel0.sys_val
+ */
+ .macro read_ctr, reg
+alternative_if_not ARM64_MISMATCHED_CACHE_LINE_SIZE
+ mrs \reg, ctr_el0 // read CTR
+ nop
+alternative_else
+ ldr_l \reg, arm64_ftr_reg_ctrel0 + ARM64_FTR_SYSVAL
+alternative_endif
+ .endm
+
/*
- * dcache_line_size - get the minimum D-cache line size from the CTR register.
+ * raw_dcache_line_size - get the minimum D-cache line size on this CPU
+ * from the CTR register.
*/
- .macro dcache_line_size, reg, tmp
+ .macro raw_dcache_line_size, reg, tmp
mrs \tmp, ctr_el0 // read CTR
ubfm \tmp, \tmp, #16, #19 // cache line size encoding
mov \reg, #4 // bytes per word
@@ -228,9 +252,20 @@ lr .req x30 // link register
.endm
/*
- * icache_line_size - get the minimum I-cache line size from the CTR register.
+ * dcache_line_size - get the safe D-cache line size across all CPUs
*/
- .macro icache_line_size, reg, tmp
+ .macro dcache_line_size, reg, tmp
+ read_ctr \tmp
+ ubfm \tmp, \tmp, #16, #19 // cache line size encoding
+ mov \reg, #4 // bytes per word
+ lsl \reg, \reg, \tmp // actual cache line size
+ .endm
+
+/*
+ * raw_icache_line_size - get the minimum I-cache line size on this CPU
+ * from the CTR register.
+ */
+ .macro raw_icache_line_size, reg, tmp
mrs \tmp, ctr_el0 // read CTR
and \tmp, \tmp, #0xf // cache line size encoding
mov \reg, #4 // bytes per word
@@ -238,6 +273,16 @@ lr .req x30 // link register
.endm
/*
+ * icache_line_size - get the safe I-cache line size across all CPUs
+ */
+ .macro icache_line_size, reg, tmp
+ read_ctr \tmp
+ and \tmp, \tmp, #0xf // cache line size encoding
+ mov \reg, #4 // bytes per word
+ lsl \reg, \reg, \tmp // actual cache line size
+ .endm
+
+/*
* tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
*/
.macro tcr_set_idmap_t0sz, valreg, tmpreg
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index b5890be8f257..7457ce082b5f 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -86,8 +86,8 @@ static inline int atomic_add_return##name(int i, atomic_t *v) \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC(add_return##name), \
+ __LL_SC_ATOMIC(add_return##name) \
+ __nops(1), \
/* LSE atomics */ \
" ldadd" #mb " %w[i], w30, %[v]\n" \
" add %w[i], %w[i], w30") \
@@ -112,8 +112,8 @@ static inline void atomic_and(int i, atomic_t *v)
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC(and),
+ __LL_SC_ATOMIC(and)
+ __nops(1),
/* LSE atomics */
" mvn %w[i], %w[i]\n"
" stclr %w[i], %[v]")
@@ -130,8 +130,8 @@ static inline int atomic_fetch_and##name(int i, atomic_t *v) \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC(fetch_and##name), \
+ __LL_SC_ATOMIC(fetch_and##name) \
+ __nops(1), \
/* LSE atomics */ \
" mvn %w[i], %w[i]\n" \
" ldclr" #mb " %w[i], %w[i], %[v]") \
@@ -156,8 +156,8 @@ static inline void atomic_sub(int i, atomic_t *v)
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC(sub),
+ __LL_SC_ATOMIC(sub)
+ __nops(1),
/* LSE atomics */
" neg %w[i], %w[i]\n"
" stadd %w[i], %[v]")
@@ -174,9 +174,8 @@ static inline int atomic_sub_return##name(int i, atomic_t *v) \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
__LL_SC_ATOMIC(sub_return##name) \
- " nop", \
+ __nops(2), \
/* LSE atomics */ \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], w30, %[v]\n" \
@@ -203,8 +202,8 @@ static inline int atomic_fetch_sub##name(int i, atomic_t *v) \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC(fetch_sub##name), \
+ __LL_SC_ATOMIC(fetch_sub##name) \
+ __nops(1), \
/* LSE atomics */ \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], %w[i], %[v]") \
@@ -284,8 +283,8 @@ static inline long atomic64_add_return##name(long i, atomic64_t *v) \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC64(add_return##name), \
+ __LL_SC_ATOMIC64(add_return##name) \
+ __nops(1), \
/* LSE atomics */ \
" ldadd" #mb " %[i], x30, %[v]\n" \
" add %[i], %[i], x30") \
@@ -310,8 +309,8 @@ static inline void atomic64_and(long i, atomic64_t *v)
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC64(and),
+ __LL_SC_ATOMIC64(and)
+ __nops(1),
/* LSE atomics */
" mvn %[i], %[i]\n"
" stclr %[i], %[v]")
@@ -328,8 +327,8 @@ static inline long atomic64_fetch_and##name(long i, atomic64_t *v) \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC64(fetch_and##name), \
+ __LL_SC_ATOMIC64(fetch_and##name) \
+ __nops(1), \
/* LSE atomics */ \
" mvn %[i], %[i]\n" \
" ldclr" #mb " %[i], %[i], %[v]") \
@@ -354,8 +353,8 @@ static inline void atomic64_sub(long i, atomic64_t *v)
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC64(sub),
+ __LL_SC_ATOMIC64(sub)
+ __nops(1),
/* LSE atomics */
" neg %[i], %[i]\n"
" stadd %[i], %[v]")
@@ -372,9 +371,8 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v) \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
__LL_SC_ATOMIC64(sub_return##name) \
- " nop", \
+ __nops(2), \
/* LSE atomics */ \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], x30, %[v]\n" \
@@ -401,8 +399,8 @@ static inline long atomic64_fetch_sub##name(long i, atomic64_t *v) \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC64(fetch_sub##name), \
+ __LL_SC_ATOMIC64(fetch_sub##name) \
+ __nops(1), \
/* LSE atomics */ \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], %[i], %[v]") \
@@ -426,13 +424,8 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
__LL_SC_ATOMIC64(dec_if_positive)
- " nop\n"
- " nop\n"
- " nop\n"
- " nop\n"
- " nop",
+ __nops(6),
/* LSE atomics */
"1: ldr x30, %[v]\n"
" subs %[ret], x30, #1\n"
@@ -464,9 +457,8 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_CMPXCHG(name) \
- " nop", \
+ __LL_SC_CMPXCHG(name) \
+ __nops(2), \
/* LSE atomics */ \
" mov " #w "30, %" #w "[old]\n" \
" cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n" \
@@ -517,10 +509,8 @@ static inline long __cmpxchg_double##name(unsigned long old1, \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- " nop\n" \
- " nop\n" \
- __LL_SC_CMPXCHG_DBL(name), \
+ __LL_SC_CMPXCHG_DBL(name) \
+ __nops(3), \
/* LSE atomics */ \
" casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
" eor %[old1], %[old1], %[oldval1]\n" \
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 4eea7f618dce..4e0497f581a0 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -20,6 +20,9 @@
#ifndef __ASSEMBLY__
+#define __nops(n) ".rept " #n "\nnop\n.endr\n"
+#define nops(n) asm volatile(__nops(n))
+
#define sev() asm volatile("sev" : : : "memory")
#define wfe() asm volatile("wfe" : : : "memory")
#define wfi() asm volatile("wfi" : : : "memory")
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index c64268dbff64..2e5fb976a572 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -68,6 +68,7 @@
extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void flush_icache_range(unsigned long start, unsigned long end);
extern void __flush_dcache_area(void *addr, size_t len);
+extern void __clean_dcache_area_poc(void *addr, size_t len);
extern void __clean_dcache_area_pou(void *addr, size_t len);
extern long __flush_cache_user_range(unsigned long start, unsigned long end);
@@ -85,7 +86,7 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
*/
extern void __dma_map_area(const void *, size_t, int);
extern void __dma_unmap_area(const void *, size_t, int);
-extern void __dma_flush_range(const void *, const void *);
+extern void __dma_flush_area(const void *, size_t);
/*
* Copy user data from/to a page which is mapped into a different
diff --git a/arch/arm64/include/asm/clocksource.h b/arch/arm64/include/asm/clocksource.h
new file mode 100644
index 000000000000..0b350a7e26f3
--- /dev/null
+++ b/arch/arm64/include/asm/clocksource.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+struct arch_clocksource_data {
+ bool vdso_direct; /* Usable for direct VDSO access? */
+};
+
+#endif
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index bd86a79491bc..91b26d26af8a 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -43,10 +43,8 @@ static inline unsigned long __xchg_case_##name(unsigned long x, \
" cbnz %w1, 1b\n" \
" " #mb, \
/* LSE atomics */ \
- " nop\n" \
- " nop\n" \
" swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \
- " nop\n" \
+ __nops(3) \
" " #nop_lse) \
: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) \
: "r" (x) \
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 7099f26e3702..758d74fedfad 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -9,6 +9,8 @@
#ifndef __ASM_CPUFEATURE_H
#define __ASM_CPUFEATURE_H
+#include <linux/jump_label.h>
+
#include <asm/hwcap.h>
#include <asm/sysreg.h>
@@ -37,8 +39,9 @@
#define ARM64_WORKAROUND_CAVIUM_27456 12
#define ARM64_HAS_32BIT_EL0 13
#define ARM64_HYP_OFFSET_LOW 14
+#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15
-#define ARM64_NCAPS 15
+#define ARM64_NCAPS 16
#ifndef __ASSEMBLY__
@@ -63,7 +66,7 @@ struct arm64_ftr_bits {
enum ftr_type type;
u8 shift;
u8 width;
- s64 safe_val; /* safe value for discrete features */
+ s64 safe_val; /* safe value for FTR_EXACT features */
};
/*
@@ -72,13 +75,14 @@ struct arm64_ftr_bits {
* @sys_val Safe value across the CPUs (system view)
*/
struct arm64_ftr_reg {
- u32 sys_id;
- const char *name;
- u64 strict_mask;
- u64 sys_val;
- struct arm64_ftr_bits *ftr_bits;
+ const char *name;
+ u64 strict_mask;
+ u64 sys_val;
+ const struct arm64_ftr_bits *ftr_bits;
};
+extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
+
/* scope of capability check */
enum {
SCOPE_SYSTEM,
@@ -109,6 +113,7 @@ struct arm64_cpu_capabilities {
};
extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
bool this_cpu_has_cap(unsigned int cap);
@@ -121,16 +126,21 @@ static inline bool cpus_have_cap(unsigned int num)
{
if (num >= ARM64_NCAPS)
return false;
- return test_bit(num, cpu_hwcaps);
+ if (__builtin_constant_p(num))
+ return static_branch_unlikely(&cpu_hwcap_keys[num]);
+ else
+ return test_bit(num, cpu_hwcaps);
}
static inline void cpus_set_cap(unsigned int num)
{
- if (num >= ARM64_NCAPS)
+ if (num >= ARM64_NCAPS) {
pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
num, ARM64_NCAPS);
- else
+ } else {
__set_bit(num, cpu_hwcaps);
+ static_branch_enable(&cpu_hwcap_keys[num]);
+ }
}
static inline int __attribute_const__
@@ -157,7 +167,7 @@ cpuid_feature_extract_unsigned_field(u64 features, int field)
return cpuid_feature_extract_unsigned_field_width(features, field, 4);
}
-static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
+static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
{
return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
}
@@ -170,7 +180,7 @@ cpuid_feature_extract_field(u64 features, int field, bool sign)
cpuid_feature_extract_unsigned_field(features, field);
}
-static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
+static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val)
{
return (s64)cpuid_feature_extract_field(val, ftrp->shift, ftrp->sign);
}
@@ -193,11 +203,11 @@ void __init setup_cpu_features(void);
void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
const char *info);
void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps);
-void check_local_cpu_errata(void);
-void __init enable_errata_workarounds(void);
+void check_local_cpu_capabilities(void);
-void verify_local_cpu_errata(void);
-void verify_local_cpu_capabilities(void);
+void update_cpu_errata_workarounds(void);
+void __init enable_errata_workarounds(void);
+void verify_local_cpu_errata_workarounds(void);
u64 read_system_reg(u32 id);
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 9d9fd4b9a72e..26a68ddb11c1 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -93,11 +93,7 @@
#include <asm/sysreg.h>
-#define read_cpuid(reg) ({ \
- u64 __val; \
- asm("mrs_s %0, " __stringify(SYS_ ## reg) : "=r" (__val)); \
- __val; \
-})
+#define read_cpuid(reg) read_sysreg_s(SYS_ ## reg)
/*
* The CPU ID never changes at run time, so we might as well tell the
diff --git a/arch/arm64/include/asm/dcc.h b/arch/arm64/include/asm/dcc.h
index 65e0190e97c8..836b05630003 100644
--- a/arch/arm64/include/asm/dcc.h
+++ b/arch/arm64/include/asm/dcc.h
@@ -21,21 +21,16 @@
#define __ASM_DCC_H
#include <asm/barrier.h>
+#include <asm/sysreg.h>
static inline u32 __dcc_getstatus(void)
{
- u32 ret;
-
- asm volatile("mrs %0, mdccsr_el0" : "=r" (ret));
-
- return ret;
+ return read_sysreg(mdccsr_el0);
}
static inline char __dcc_getchar(void)
{
- char c;
-
- asm volatile("mrs %0, dbgdtrrx_el0" : "=r" (c));
+ char c = read_sysreg(dbgdtrrx_el0);
isb();
return c;
@@ -47,8 +42,7 @@ static inline void __dcc_putchar(char c)
* The typecast is to make absolutely certain that 'c' is
* zero-extended.
*/
- asm volatile("msr dbgdtrtx_el0, %0"
- : : "r" ((unsigned long)(unsigned char)c));
+ write_sysreg((unsigned char)c, dbgdtrtx_el0);
isb();
}
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 4b6b3f72a215..b71420a12f26 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -61,8 +61,6 @@
#define AARCH64_BREAK_KGDB_DYN_DBG \
(AARCH64_BREAK_MON | (KGDB_DYN_DBG_BRK_IMM << 5))
-#define KGDB_DYN_BRK_INS_BYTE(x) \
- ((AARCH64_BREAK_KGDB_DYN_DBG >> (8 * (x))) & 0xff)
#define CACHE_FLUSH_IS_SAFE 1
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index f772e15c4766..d14c478976d0 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -78,6 +78,23 @@
#define ESR_ELx_IL (UL(1) << 25)
#define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1)
+
+/* ISS field definitions shared by different classes */
+#define ESR_ELx_WNR (UL(1) << 6)
+
+/* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_EA (UL(1) << 9)
+#define ESR_ELx_S1PTW (UL(1) << 7)
+
+/* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */
+#define ESR_ELx_FSC (0x3F)
+#define ESR_ELx_FSC_TYPE (0x3C)
+#define ESR_ELx_FSC_EXTABT (0x10)
+#define ESR_ELx_FSC_ACCESS (0x08)
+#define ESR_ELx_FSC_FAULT (0x04)
+#define ESR_ELx_FSC_PERM (0x0C)
+
+/* ISS field definitions for Data Aborts */
#define ESR_ELx_ISV (UL(1) << 24)
#define ESR_ELx_SAS_SHIFT (22)
#define ESR_ELx_SAS (UL(3) << ESR_ELx_SAS_SHIFT)
@@ -86,16 +103,9 @@
#define ESR_ELx_SRT_MASK (UL(0x1F) << ESR_ELx_SRT_SHIFT)
#define ESR_ELx_SF (UL(1) << 15)
#define ESR_ELx_AR (UL(1) << 14)
-#define ESR_ELx_EA (UL(1) << 9)
#define ESR_ELx_CM (UL(1) << 8)
-#define ESR_ELx_S1PTW (UL(1) << 7)
-#define ESR_ELx_WNR (UL(1) << 6)
-#define ESR_ELx_FSC (0x3F)
-#define ESR_ELx_FSC_TYPE (0x3C)
-#define ESR_ELx_FSC_EXTABT (0x10)
-#define ESR_ELx_FSC_ACCESS (0x08)
-#define ESR_ELx_FSC_FAULT (0x04)
-#define ESR_ELx_FSC_PERM (0x0C)
+
+/* ISS field definitions for exceptions taken in to Hyp */
#define ESR_ELx_CV (UL(1) << 24)
#define ESR_ELx_COND_SHIFT (20)
#define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT)
@@ -109,6 +119,62 @@
((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL | \
((imm) & 0xffff))
+/* ISS field definitions for System instruction traps */
+#define ESR_ELx_SYS64_ISS_RES0_SHIFT 22
+#define ESR_ELx_SYS64_ISS_RES0_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_RES0_SHIFT)
+#define ESR_ELx_SYS64_ISS_DIR_MASK 0x1
+#define ESR_ELx_SYS64_ISS_DIR_READ 0x1
+#define ESR_ELx_SYS64_ISS_DIR_WRITE 0x0
+
+#define ESR_ELx_SYS64_ISS_RT_SHIFT 5
+#define ESR_ELx_SYS64_ISS_RT_MASK (UL(0x1f) << ESR_ELx_SYS64_ISS_RT_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRM_SHIFT 1
+#define ESR_ELx_SYS64_ISS_CRM_MASK (UL(0xf) << ESR_ELx_SYS64_ISS_CRM_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRN_SHIFT 10
+#define ESR_ELx_SYS64_ISS_CRN_MASK (UL(0xf) << ESR_ELx_SYS64_ISS_CRN_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP1_SHIFT 14
+#define ESR_ELx_SYS64_ISS_OP1_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_OP1_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP2_SHIFT 17
+#define ESR_ELx_SYS64_ISS_OP2_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_OP2_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP0_SHIFT 20
+#define ESR_ELx_SYS64_ISS_OP0_MASK (UL(0x3) << ESR_ELx_SYS64_ISS_OP0_SHIFT)
+#define ESR_ELx_SYS64_ISS_SYS_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \
+ ESR_ELx_SYS64_ISS_OP1_MASK | \
+ ESR_ELx_SYS64_ISS_OP2_MASK | \
+ ESR_ELx_SYS64_ISS_CRN_MASK | \
+ ESR_ELx_SYS64_ISS_CRM_MASK)
+#define ESR_ELx_SYS64_ISS_SYS_VAL(op0, op1, op2, crn, crm) \
+ (((op0) << ESR_ELx_SYS64_ISS_OP0_SHIFT) | \
+ ((op1) << ESR_ELx_SYS64_ISS_OP1_SHIFT) | \
+ ((op2) << ESR_ELx_SYS64_ISS_OP2_SHIFT) | \
+ ((crn) << ESR_ELx_SYS64_ISS_CRN_SHIFT) | \
+ ((crm) << ESR_ELx_SYS64_ISS_CRM_SHIFT))
+
+#define ESR_ELx_SYS64_ISS_SYS_OP_MASK (ESR_ELx_SYS64_ISS_SYS_MASK | \
+ ESR_ELx_SYS64_ISS_DIR_MASK)
+/*
+ * User space cache operations have the following sysreg encoding
+ * in System instructions.
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 14 }, WRITE (L=0)
+ */
+#define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC 14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAU 11
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAC 10
+#define ESR_ELx_SYS64_ISS_CRM_IC_IVAU 5
+
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \
+ ESR_ELx_SYS64_ISS_OP1_MASK | \
+ ESR_ELx_SYS64_ISS_OP2_MASK | \
+ ESR_ELx_SYS64_ISS_CRN_MASK | \
+ ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \
+ (ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_WRITE)
+
+#define ESR_ELx_SYS64_ISS_SYS_CTR ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0)
+#define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
+
#ifndef __ASSEMBLY__
#include <asm/types.h>
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 115ea2a64520..9510ace570e2 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -18,6 +18,7 @@
#include <asm/cputype.h>
#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
#include <asm/virt.h>
#ifdef __KERNEL__
@@ -98,18 +99,18 @@ static inline void decode_ctrl_reg(u32 reg,
#define AARCH64_DBG_REG_WCR (AARCH64_DBG_REG_WVR + ARM_MAX_WRP)
/* Debug register names. */
-#define AARCH64_DBG_REG_NAME_BVR "bvr"
-#define AARCH64_DBG_REG_NAME_BCR "bcr"
-#define AARCH64_DBG_REG_NAME_WVR "wvr"
-#define AARCH64_DBG_REG_NAME_WCR "wcr"
+#define AARCH64_DBG_REG_NAME_BVR bvr
+#define AARCH64_DBG_REG_NAME_BCR bcr
+#define AARCH64_DBG_REG_NAME_WVR wvr
+#define AARCH64_DBG_REG_NAME_WCR wcr
/* Accessor macros for the debug registers. */
#define AARCH64_DBG_READ(N, REG, VAL) do {\
- asm volatile("mrs %0, dbg" REG #N "_el1" : "=r" (VAL));\
+ VAL = read_sysreg(dbg##REG##N##_el1);\
} while (0)
#define AARCH64_DBG_WRITE(N, REG, VAL) do {\
- asm volatile("msr dbg" REG #N "_el1, %0" :: "r" (VAL));\
+ write_sysreg(VAL, dbg##REG##N##_el1);\
} while (0)
struct task_struct;
@@ -141,8 +142,6 @@ static inline void ptrace_hw_copy_thread(struct task_struct *task)
}
#endif
-extern struct pmu perf_ops_bp;
-
/* Determine number of BRP registers available. */
static inline int get_num_brps(void)
{
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 1dbaa901d7e5..bc853663dd51 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -246,7 +246,8 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
{ return (val); }
-__AARCH64_INSN_FUNCS(adr_adrp, 0x1F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adr, 0x9F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000)
__AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000)
__AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800)
__AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800)
@@ -318,6 +319,11 @@ __AARCH64_INSN_FUNCS(msr_reg, 0xFFF00000, 0xD5100000)
bool aarch64_insn_is_nop(u32 insn);
bool aarch64_insn_is_branch_imm(u32 insn);
+static inline bool aarch64_insn_is_adr_adrp(u32 insn)
+{
+ return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn);
+}
+
int aarch64_insn_read(void *addr, u32 *insnp);
int aarch64_insn_write(void *addr, u32 insn);
enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
@@ -398,6 +404,9 @@ int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
+s32 aarch64_insn_adrp_get_offset(u32 insn);
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset);
+
bool aarch32_insn_is_wide(u32 insn);
#define A32_RN_OFFSET 16
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 9b6e408cfa51..0bba427bb4c2 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -40,25 +40,25 @@
#define __raw_writeb __raw_writeb
static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
{
- asm volatile("strb %w0, [%1]" : : "r" (val), "r" (addr));
+ asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writew __raw_writew
static inline void __raw_writew(u16 val, volatile void __iomem *addr)
{
- asm volatile("strh %w0, [%1]" : : "r" (val), "r" (addr));
+ asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writel __raw_writel
static inline void __raw_writel(u32 val, volatile void __iomem *addr)
{
- asm volatile("str %w0, [%1]" : : "r" (val), "r" (addr));
+ asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writeq __raw_writeq
static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
{
- asm volatile("str %0, [%1]" : : "r" (val), "r" (addr));
+ asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_readb __raw_readb
@@ -184,17 +184,6 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
#define iowrite64be(v,p) ({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p) __va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p) p
-
#include <asm-generic/io.h>
/*
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index b6bb83400cd8..dff109871f2a 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -99,14 +99,10 @@
.macro kern_hyp_va reg
alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
and \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK
-alternative_else
- nop
-alternative_endif
-alternative_if_not ARM64_HYP_OFFSET_LOW
- nop
-alternative_else
+alternative_else_nop_endif
+alternative_if ARM64_HYP_OFFSET_LOW
and \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK
-alternative_endif
+alternative_else_nop_endif
.endm
#else
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 31b73227b41f..ba62df8c6e35 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -214,7 +214,7 @@ static inline void *phys_to_virt(phys_addr_t x)
#ifndef CONFIG_SPARSEMEM_VMEMMAP
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
#else
#define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
#define __page_to_voff(kaddr) (((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
@@ -222,11 +222,15 @@ static inline void *phys_to_virt(phys_addr_t x)
#define page_to_virt(page) ((void *)((__page_to_voff(page)) | PAGE_OFFSET))
#define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
-#define virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
+#define _virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
+ PHYS_OFFSET) >> PAGE_SHIFT)
#endif
#endif
+#define _virt_addr_is_linear(kaddr) (((u64)(kaddr)) >= PAGE_OFFSET)
+#define virt_addr_valid(kaddr) (_virt_addr_is_linear(kaddr) && \
+ _virt_addr_valid(kaddr))
+
#include <asm-generic/memory_model.h>
#endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index b1892a0dbcb0..a50185375f09 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -27,22 +27,17 @@
#include <asm-generic/mm_hooks.h>
#include <asm/cputype.h>
#include <asm/pgtable.h>
+#include <asm/sysreg.h>
#include <asm/tlbflush.h>
-#ifdef CONFIG_PID_IN_CONTEXTIDR
-static inline void contextidr_thread_switch(struct task_struct *next)
-{
- asm(
- " msr contextidr_el1, %0\n"
- " isb"
- :
- : "r" (task_pid_nr(next)));
-}
-#else
static inline void contextidr_thread_switch(struct task_struct *next)
{
+ if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR))
+ return;
+
+ write_sysreg(task_pid_nr(next), contextidr_el1);
+ isb();
}
-#endif
/*
* Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0.
@@ -51,11 +46,8 @@ static inline void cpu_set_reserved_ttbr0(void)
{
unsigned long ttbr = virt_to_phys(empty_zero_page);
- asm(
- " msr ttbr0_el1, %0 // set TTBR0\n"
- " isb"
- :
- : "r" (ttbr));
+ write_sysreg(ttbr, ttbr0_el1);
+ isb();
}
/*
@@ -81,13 +73,11 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
if (!__cpu_uses_extended_idmap())
return;
- asm volatile (
- " mrs %0, tcr_el1 ;"
- " bfi %0, %1, %2, %3 ;"
- " msr tcr_el1, %0 ;"
- " isb"
- : "=&r" (tcr)
- : "r"(t0sz), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH));
+ tcr = read_sysreg(tcr_el1);
+ tcr &= ~TCR_T0SZ_MASK;
+ tcr |= t0sz << TCR_T0SZ_OFFSET;
+ write_sysreg(tcr, tcr_el1);
+ isb();
}
#define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS))
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 0a456bef8c79..2fee2f59288c 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -199,19 +199,19 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
#define _percpu_read(pcp) \
({ \
typeof(pcp) __retval; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
__retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), \
sizeof(pcp)); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
__retval; \
})
#define _percpu_write(pcp, val) \
do { \
- preempt_disable(); \
+ preempt_disable_notrace(); \
__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), \
sizeof(pcp)); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
} while(0) \
#define _pcp_protect(operation, pcp, val) \
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index c3ae239db3ee..eb0c2bd90de9 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -208,6 +208,7 @@
#define TCR_T1SZ(x) ((UL(64) - (x)) << TCR_T1SZ_OFFSET)
#define TCR_TxSZ(x) (TCR_T0SZ(x) | TCR_T1SZ(x))
#define TCR_TxSZ_WIDTH 6
+#define TCR_T0SZ_MASK (((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
#define TCR_IRGN0_SHIFT 8
#define TCR_IRGN0_MASK (UL(3) << TCR_IRGN0_SHIFT)
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 39f5252673f7..2142c7726e76 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -70,12 +70,13 @@
#define PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
#define __P000 PAGE_NONE
#define __P001 PAGE_READONLY
#define __P010 PAGE_COPY
#define __P011 PAGE_COPY
-#define __P100 PAGE_READONLY_EXEC
+#define __P100 PAGE_EXECONLY
#define __P101 PAGE_READONLY_EXEC
#define __P110 PAGE_COPY_EXEC
#define __P111 PAGE_COPY_EXEC
@@ -84,7 +85,7 @@
#define __S001 PAGE_READONLY
#define __S010 PAGE_SHARED
#define __S011 PAGE_SHARED
-#define __S100 PAGE_READONLY_EXEC
+#define __S100 PAGE_EXECONLY
#define __S101 PAGE_READONLY_EXEC
#define __S110 PAGE_SHARED_EXEC
#define __S111 PAGE_SHARED_EXEC
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e20bd431184a..ffbb9a520563 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -73,7 +73,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE))
#define pte_exec(pte) (!(pte_val(pte) & PTE_UXN))
#define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT))
-#define pte_user(pte) (!!(pte_val(pte) & PTE_USER))
+#define pte_ng(pte) (!!(pte_val(pte) & PTE_NG))
#ifdef CONFIG_ARM64_HW_AFDBM
#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -84,8 +84,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte))
#define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_not_user(pte) \
- ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
+#define pte_valid_global(pte) \
+ ((pte_val(pte) & (PTE_VALID | PTE_NG)) == PTE_VALID)
#define pte_valid_young(pte) \
((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
@@ -155,6 +155,16 @@ static inline pte_t pte_mknoncont(pte_t pte)
return clear_pte_bit(pte, __pgprot(PTE_CONT));
}
+static inline pte_t pte_clear_rdonly(pte_t pte)
+{
+ return clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+}
+
+static inline pte_t pte_mkpresent(pte_t pte)
+{
+ return set_pte_bit(pte, __pgprot(PTE_VALID));
+}
+
static inline pmd_t pmd_mkcont(pmd_t pmd)
{
return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
@@ -168,7 +178,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
* Only if the new pte is valid and kernel, otherwise TLB maintenance
* or update_mmu_cache() have the necessary barriers.
*/
- if (pte_valid_not_user(pte)) {
+ if (pte_valid_global(pte)) {
dsb(ishst);
isb();
}
@@ -202,7 +212,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_val(pte) &= ~PTE_RDONLY;
else
pte_val(pte) |= PTE_RDONLY;
- if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+ if (pte_ng(pte) && pte_exec(pte) && !pte_special(pte))
__sync_icache_dcache(pte, addr);
}
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ace0a96e7d6e..df2e53d3a969 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -37,7 +37,6 @@
#include <asm/ptrace.h>
#include <asm/types.h>
-#ifdef __KERNEL__
#define STACK_TOP_MAX TASK_SIZE_64
#ifdef CONFIG_COMPAT
#define AARCH32_VECTORS_BASE 0xffff0000
@@ -49,7 +48,6 @@
extern phys_addr_t arm64_dma_phys_limit;
#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1)
-#endif /* __KERNEL__ */
struct debug_info {
/* Have we suspended stepping by a debugger? */
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
new file mode 100644
index 000000000000..4e7e7067afdb
--- /dev/null
+++ b/arch/arm64/include/asm/sections.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2016 ARM Limited
+ *
+ * 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/>.
+ */
+#ifndef __ASM_SECTIONS_H
+#define __ASM_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern char __alt_instructions[], __alt_instructions_end[];
+extern char __exception_text_start[], __exception_text_end[];
+extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
+extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
+extern char __hyp_text_start[], __hyp_text_end[];
+extern char __idmap_text_start[], __idmap_text_end[];
+extern char __irqentry_text_start[], __irqentry_text_end[];
+extern char __mmuoff_data_start[], __mmuoff_data_end[];
+
+#endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index e875a5a551d7..cae331d553f8 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -66,8 +66,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
" stxr %w1, %w0, %2\n"
-" nop\n"
-" nop\n",
+ __nops(2),
/* LSE atomics */
" mov %w1, %w0\n"
" cas %w0, %w0, %2\n"
@@ -99,9 +98,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
/* LSE atomics */
" mov %w2, %w5\n"
" ldadda %w2, %w0, %3\n"
-" nop\n"
-" nop\n"
-" nop\n"
+ __nops(3)
)
/* Did we get the lock? */
@@ -165,8 +162,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
" stlrh %w1, %0",
/* LSE atomics */
" mov %w1, #1\n"
- " nop\n"
- " staddlh %w1, %0")
+ " staddlh %w1, %0\n"
+ __nops(1))
: "=Q" (lock->owner), "=&r" (tmp)
:
: "memory");
@@ -212,7 +209,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
" cbnz %w0, 1b\n"
" stxr %w0, %w2, %1\n"
" cbnz %w0, 2b\n"
- " nop",
+ __nops(1),
/* LSE atomics */
"1: mov %w0, wzr\n"
"2: casa %w0, %w2, %1\n"
@@ -241,8 +238,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
/* LSE atomics */
" mov %w0, wzr\n"
" casa %w0, %w2, %1\n"
- " nop\n"
- " nop")
+ __nops(2))
: "=&r" (tmp), "+Q" (rw->lock)
: "r" (0x80000000)
: "memory");
@@ -290,8 +286,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
" add %w0, %w0, #1\n"
" tbnz %w0, #31, 1b\n"
" stxr %w1, %w0, %2\n"
- " nop\n"
- " cbnz %w1, 2b",
+ " cbnz %w1, 2b\n"
+ __nops(1),
/* LSE atomics */
"1: wfe\n"
"2: ldxr %w0, %2\n"
@@ -317,9 +313,8 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
" cbnz %w1, 1b",
/* LSE atomics */
" movn %w0, #0\n"
- " nop\n"
- " nop\n"
- " staddl %w0, %2")
+ " staddl %w0, %2\n"
+ __nops(2))
: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
:
: "memory");
@@ -344,7 +339,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
" tbnz %w1, #31, 1f\n"
" casa %w0, %w1, %2\n"
" sbc %w1, %w1, %w0\n"
- " nop\n"
+ __nops(1)
"1:")
: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
:
@@ -363,4 +358,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
#define arch_read_relax(lock) cpu_relax()
#define arch_write_relax(lock) cpu_relax()
+/*
+ * Accesses appearing in program order before a spin_lock() operation
+ * can be reordered with accesses inside the critical section, by virtue
+ * of arch_spin_lock being constructed using acquire semantics.
+ *
+ * In cases where this is problematic (e.g. try_to_wake_up), an
+ * smp_mb__before_spinlock() can restore the required ordering.
+ */
+#define smp_mb__before_spinlock() smp_mb()
+
#endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index 024d623f662e..b8a313fd7a09 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -47,4 +47,7 @@ int swsusp_arch_resume(void);
int arch_hibernation_header_save(void *addr, unsigned int max_size);
int arch_hibernation_header_restore(void *addr);
+/* Used to resume on the CPU we hibernated on */
+int hibernate_resume_nonboot_cpu_disable(void);
+
#endif
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cc06794b7346..e8d46e8e6079 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -100,6 +100,7 @@
/* SCTLR_EL1 specific flags. */
#define SCTLR_EL1_UCI (1 << 26)
#define SCTLR_EL1_SPAN (1 << 23)
+#define SCTLR_EL1_UCT (1 << 15)
#define SCTLR_EL1_SED (1 << 8)
#define SCTLR_EL1_CP15BEN (1 << 5)
@@ -253,16 +254,6 @@ asm(
" .endm\n"
);
-static inline void config_sctlr_el1(u32 clear, u32 set)
-{
- u32 val;
-
- asm volatile("mrs %0, sctlr_el1" : "=r" (val));
- val &= ~clear;
- val |= set;
- asm volatile("msr sctlr_el1, %0" : : "r" (val));
-}
-
/*
* Unlike read_cpuid, calls to read_sysreg are never expected to be
* optimized away or replaced with synthetic values.
@@ -273,12 +264,41 @@ static inline void config_sctlr_el1(u32 clear, u32 set)
__val; \
})
+/*
+ * The "Z" constraint normally means a zero immediate, but when combined with
+ * the "%x0" template means XZR.
+ */
#define write_sysreg(v, r) do { \
u64 __val = (u64)v; \
- asm volatile("msr " __stringify(r) ", %0" \
- : : "r" (__val)); \
+ asm volatile("msr " __stringify(r) ", %x0" \
+ : : "rZ" (__val)); \
+} while (0)
+
+/*
+ * For registers without architectural names, or simply unsupported by
+ * GAS.
+ */
+#define read_sysreg_s(r) ({ \
+ u64 __val; \
+ asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val)); \
+ __val; \
+})
+
+#define write_sysreg_s(v, r) do { \
+ u64 __val = (u64)v; \
+ asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val)); \
} while (0)
+static inline void config_sctlr_el1(u32 clear, u32 set)
+{
+ u32 val;
+
+ val = read_sysreg(sctlr_el1);
+ val &= ~clear;
+ val |= set;
+ write_sysreg(val, sctlr_el1);
+}
+
#endif
#endif /* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 57f110bea6a8..bc812435bc76 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -56,12 +56,6 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
__show_ratelimited; \
})
-#define UDBG_UNDEFINED (1 << 0)
-#define UDBG_SYSCALL (1 << 1)
-#define UDBG_BADABORT (1 << 2)
-#define UDBG_SEGV (1 << 3)
-#define UDBG_BUS (1 << 4)
-
#endif /* __ASSEMBLY__ */
#endif /* __ASM_SYSTEM_MISC_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index abd64bd1f6d9..e9ea5a6bd449 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -75,6 +75,9 @@ static inline struct thread_info *current_thread_info(void) __attribute_const__;
/*
* struct thread_info can be accessed directly via sp_el0.
+ *
+ * We don't use read_sysreg() as we want the compiler to cache the value where
+ * possible.
*/
static inline struct thread_info *current_thread_info(void)
{
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index b460ae28e346..deab52374119 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -25,6 +25,24 @@
#include <asm/cputype.h>
/*
+ * Raw TLBI operations.
+ *
+ * Where necessary, use the __tlbi() macro to avoid asm()
+ * boilerplate. Drivers and most kernel code should use the TLB
+ * management routines in preference to the macro below.
+ *
+ * The macro can be used as __tlbi(op) or __tlbi(op, arg), depending
+ * on whether a particular TLBI operation takes an argument or
+ * not. The macros handles invoking the asm with or without the
+ * register argument as appropriate.
+ */
+#define __TLBI_0(op, arg) asm ("tlbi " #op)
+#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0" : : "r" (arg))
+#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
+
+#define __tlbi(op, ...) __TLBI_N(op, ##__VA_ARGS__, 1, 0)
+
+/*
* TLB Management
* ==============
*
@@ -66,7 +84,7 @@
static inline void local_flush_tlb_all(void)
{
dsb(nshst);
- asm("tlbi vmalle1");
+ __tlbi(vmalle1);
dsb(nsh);
isb();
}
@@ -74,7 +92,7 @@ static inline void local_flush_tlb_all(void)
static inline void flush_tlb_all(void)
{
dsb(ishst);
- asm("tlbi vmalle1is");
+ __tlbi(vmalle1is);
dsb(ish);
isb();
}
@@ -84,7 +102,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
unsigned long asid = ASID(mm) << 48;
dsb(ishst);
- asm("tlbi aside1is, %0" : : "r" (asid));
+ __tlbi(aside1is, asid);
dsb(ish);
}
@@ -94,7 +112,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48);
dsb(ishst);
- asm("tlbi vale1is, %0" : : "r" (addr));
+ __tlbi(vale1is, addr);
dsb(ish);
}
@@ -122,9 +140,9 @@ 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)
- asm("tlbi vale1is, %0" : : "r"(addr));
+ __tlbi(vale1is, addr);
else
- asm("tlbi vae1is, %0" : : "r"(addr));
+ __tlbi(vae1is, addr);
}
dsb(ish);
}
@@ -149,7 +167,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
dsb(ishst);
for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
- asm("tlbi vaae1is, %0" : : "r"(addr));
+ __tlbi(vaae1is, addr);
dsb(ish);
isb();
}
@@ -163,7 +181,7 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
{
unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
- asm("tlbi vae1is, %0" : : "r" (addr));
+ __tlbi(vae1is, addr);
dsb(ish);
}
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 9cd03f3e812f..02e9035b0685 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/sections.h>
struct pt_regs;
@@ -39,9 +40,6 @@ void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
- extern char __irqentry_text_start[];
- extern char __irqentry_text_end[];
-
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
@@ -54,8 +52,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
static inline int in_exception_text(unsigned long ptr)
{
- extern char __exception_text_start[];
- extern char __exception_text_end[];
int in;
in = ptr >= (unsigned long)&__exception_text_start &&
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 1788545f25bc..fea10736b11f 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -45,6 +45,8 @@
#ifndef __ASSEMBLY__
#include <asm/ptrace.h>
+#include <asm/sections.h>
+#include <asm/sysreg.h>
/*
* __boot_cpu_mode records what mode CPUs were booted in.
@@ -75,10 +77,7 @@ static inline bool is_hyp_mode_mismatched(void)
static inline bool is_kernel_in_hyp_mode(void)
{
- u64 el;
-
- asm("mrs %0, CurrentEL" : "=r" (el));
- return el == CurrentEL_EL2;
+ return read_sysreg(CurrentEL) == CurrentEL_EL2;
}
#ifdef CONFIG_ARM64_VHE
@@ -87,14 +86,6 @@ extern void verify_cpu_run_el(void);
static inline void verify_cpu_run_el(void) {}
#endif
-/* The section containing the hypervisor idmap text */
-extern char __hyp_idmap_text_start[];
-extern char __hyp_idmap_text_end[];
-
-/* The section containing the hypervisor text */
-extern char __hyp_text_start[];
-extern char __hyp_text_end[];
-
#endif /* __ASSEMBLY__ */
#endif /* ! __ASM__VIRT_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 14f7b651c787..7d66bbaafc0c 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -10,6 +10,8 @@ CFLAGS_REMOVE_ftrace.o = -pg
CFLAGS_REMOVE_insn.o = -pg
CFLAGS_REMOVE_return_address.o = -pg
+CFLAGS_setup.o = -DUTS_MACHINE='"$(UTS_MACHINE)"'
+
# Object file lists.
arm64-obj-y := debug-monitors.o entry.o irq.o fpsimd.o \
entry-fpsimd.o process.o ptrace.o setup.o signal.o \
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 3e4f1a45b125..252a6d9c1da5 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -24,6 +24,7 @@
#include <linux/memblock.h>
#include <linux/of_fdt.h>
#include <linux/smp.h>
+#include <linux/serial_core.h>
#include <asm/cputype.h>
#include <asm/cpu_ops.h>
@@ -206,7 +207,7 @@ void __init acpi_boot_table_init(void)
if (param_acpi_off ||
(!param_acpi_on && !param_acpi_force &&
of_scan_flat_dt(dt_scan_depth1_nodes, NULL)))
- return;
+ goto done;
/*
* ACPI is disabled at this point. Enable it in order to parse
@@ -226,6 +227,14 @@ void __init acpi_boot_table_init(void)
if (!param_acpi_force)
disable_acpi();
}
+
+done:
+ if (acpi_disabled) {
+ if (earlycon_init_is_deferred)
+ early_init_dt_scan_chosen_stdout();
+ } else {
+ parse_spcr(earlycon_init_is_deferred);
+ }
}
#ifdef CONFIG_ACPI_APEI
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
index f85149cc7c71..f01fab637dab 100644
--- a/arch/arm64/kernel/acpi_numa.c
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -105,8 +105,10 @@ int __init arm64_acpi_numa_init(void)
int ret;
ret = acpi_numa_init();
- if (ret)
+ if (ret) {
+ pr_info("Failed to initialise from firmware\n");
return ret;
+ }
return srat_disabled() ? -EINVAL : 0;
}
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d2ee1b21a10d..06d650f61da7 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -25,14 +25,13 @@
#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/insn.h>
+#include <asm/sections.h>
#include <linux/stop_machine.h>
#define __ALT_PTR(a,f) (u32 *)((void *)&(a)->f + (a)->f)
#define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset)
#define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset)
-extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
-
struct alt_region {
struct alt_instr *begin;
struct alt_instr *end;
@@ -59,6 +58,8 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
BUG();
}
+#define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
+
static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
{
u32 insn;
@@ -80,6 +81,25 @@ static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
offset = target - (unsigned long)insnptr;
insn = aarch64_set_branch_offset(insn, offset);
}
+ } else if (aarch64_insn_is_adrp(insn)) {
+ s32 orig_offset, new_offset;
+ unsigned long target;
+
+ /*
+ * If we're replacing an adrp instruction, which uses PC-relative
+ * immediate addressing, adjust the offset to reflect the new
+ * PC. adrp operates on 4K aligned addresses.
+ */
+ orig_offset = aarch64_insn_adrp_get_offset(insn);
+ target = align_down(altinsnptr, SZ_4K) + orig_offset;
+ new_offset = target - align_down(insnptr, SZ_4K);
+ insn = aarch64_insn_adrp_set_offset(insn, new_offset);
+ } else if (aarch64_insn_uses_literal(insn)) {
+ /*
+ * Disallow patching unhandled instructions using PC relative
+ * literal addresses
+ */
+ BUG();
}
return insn;
@@ -124,8 +144,8 @@ static int __apply_alternatives_multi_stop(void *unused)
{
static int patched = 0;
struct alt_region region = {
- .begin = __alt_instructions,
- .end = __alt_instructions_end,
+ .begin = (struct alt_instr *)__alt_instructions,
+ .end = (struct alt_instr *)__alt_instructions_end,
};
/* We always have a CPU 0 at this point (__init) */
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 05070b72fc28..4a2f0f0fef32 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -23,6 +23,7 @@
#include <linux/dma-mapping.h>
#include <linux/kvm_host.h>
#include <linux/suspend.h>
+#include <asm/cpufeature.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
#include <asm/smp_plat.h>
@@ -145,5 +146,6 @@ int main(void)
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));
return 0;
}
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index b8629d52fba9..9617301f76b5 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -39,7 +39,7 @@ static inline enum cache_type get_cache_type(int level)
if (level > MAX_CACHE_LEVEL)
return CACHE_TYPE_NOCACHE;
- asm volatile ("mrs %x0, clidr_el1" : "=r" (clidr));
+ clidr = read_sysreg(clidr_el1);
return CLIDR_CTYPE(clidr, level);
}
@@ -55,11 +55,9 @@ u64 __attribute_const__ cache_get_ccsidr(u64 csselr)
WARN_ON(preemptible());
- /* Put value into CSSELR */
- asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
+ write_sysreg(csselr, csselr_el1);
isb();
- /* Read result out of CCSIDR */
- asm volatile("mrs %x0, ccsidr_el1" : "=r" (ccsidr));
+ ccsidr = read_sysreg(ccsidr_el1);
return ccsidr;
}
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 82b0fc2e637b..0150394f4cab 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -30,6 +30,21 @@ is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
entry->midr_range_max);
}
+static bool
+has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
+ int scope)
+{
+ WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+ return (read_cpuid_cachetype() & arm64_ftr_reg_ctrel0.strict_mask) !=
+ (arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
+}
+
+static void cpu_enable_trap_ctr_access(void *__unused)
+{
+ /* Clear SCTLR_EL1.UCT */
+ config_sctlr_el1(SCTLR_EL1_UCT, 0);
+}
+
#define MIDR_RANGE(model, min, max) \
.def_scope = SCOPE_LOCAL_CPU, \
.matches = is_affected_midr_range, \
@@ -108,6 +123,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
},
#endif
{
+ .desc = "Mismatched cache line size",
+ .capability = ARM64_MISMATCHED_CACHE_LINE_SIZE,
+ .matches = has_mismatched_cache_line_size,
+ .def_scope = SCOPE_LOCAL_CPU,
+ .enable = cpu_enable_trap_ctr_access,
+ },
+ {
}
};
@@ -116,7 +138,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
* and the related information is freed soon after. If the new CPU requires
* an errata not detected at boot, fail this CPU.
*/
-void verify_local_cpu_errata(void)
+void verify_local_cpu_errata_workarounds(void)
{
const struct arm64_cpu_capabilities *caps = arm64_errata;
@@ -131,7 +153,7 @@ void verify_local_cpu_errata(void)
}
}
-void check_local_cpu_errata(void)
+void update_cpu_errata_workarounds(void)
{
update_cpu_capabilities(arm64_errata, "enabling workaround for");
}
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index c7cfb8fe06f9..e137ceaf5016 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -17,6 +17,7 @@
*/
#include <linux/acpi.h>
+#include <linux/cache.h>
#include <linux/errno.h>
#include <linux/of.h>
#include <linux/string.h>
@@ -28,7 +29,7 @@ extern const struct cpu_operations smp_spin_table_ops;
extern const struct cpu_operations acpi_parking_protocol_ops;
extern const struct cpu_operations cpu_psci_ops;
-const struct cpu_operations *cpu_ops[NR_CPUS];
+const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = {
&smp_spin_table_ops,
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 62272eac1352..d577f263cc4a 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -46,6 +46,9 @@ unsigned int compat_elf_hwcap2 __read_mostly;
DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
+EXPORT_SYMBOL(cpu_hwcap_keys);
+
#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
{ \
.sign = SIGNED, \
@@ -74,7 +77,7 @@ static bool __maybe_unused
cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused);
-static struct arm64_ftr_bits ftr_id_aa64isar0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0),
@@ -87,7 +90,7 @@ static struct arm64_ftr_bits ftr_id_aa64isar0[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0),
@@ -101,7 +104,7 @@ static struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
@@ -119,7 +122,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
@@ -130,7 +133,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
@@ -139,7 +142,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_ctr[] = {
+static const struct arm64_ftr_bits ftr_ctr[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */
@@ -147,15 +150,21 @@ static struct arm64_ftr_bits ftr_ctr[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */
/*
* Linux can handle differing I-cache policies. Userspace JITs will
- * make use of *minLine
+ * make use of *minLine.
+ * If we have differing I-cache policies, report it as the weakest - AIVIVT.
*/
- ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0), /* L1Ip */
+ ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_AIVIVT), /* L1Ip */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_mmfr0[] = {
+struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
+ .name = "SYS_CTR_EL0",
+ .ftr_bits = ftr_ctr
+};
+
+static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0xf), /* InnerShr */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), /* FCSE */
ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */
@@ -167,7 +176,7 @@ static struct arm64_ftr_bits ftr_id_mmfr0[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
@@ -178,14 +187,14 @@ static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_mvfr2[] = {
+static const struct arm64_ftr_bits ftr_mvfr2[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* FPMisc */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* SIMDMisc */
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_dczid[] = {
+static const struct arm64_ftr_bits ftr_dczid[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 5, 27, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 1, 1), /* DZP */
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* BS */
@@ -193,7 +202,7 @@ static struct arm64_ftr_bits ftr_dczid[] = {
};
-static struct arm64_ftr_bits ftr_id_isar5[] = {
+static const struct arm64_ftr_bits ftr_id_isar5[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 20, 4, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0),
@@ -204,14 +213,14 @@ static struct arm64_ftr_bits ftr_id_isar5[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_mmfr4[] = {
+static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* ac2 */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* RAZ */
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_pfr0[] = {
+static const struct arm64_ftr_bits ftr_id_pfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 16, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0), /* State3 */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0), /* State2 */
@@ -220,7 +229,7 @@ static struct arm64_ftr_bits ftr_id_pfr0[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_dfr0[] = {
+static const struct arm64_ftr_bits ftr_id_dfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
@@ -238,7 +247,7 @@ static struct arm64_ftr_bits ftr_id_dfr0[] = {
* 0. Covers the following 32bit registers:
* id_isar[0-4], id_mmfr[1-3], id_pfr1, mvfr[0-1]
*/
-static struct arm64_ftr_bits ftr_generic_32bits[] = {
+static const struct arm64_ftr_bits ftr_generic_32bits[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
@@ -250,29 +259,32 @@ static struct arm64_ftr_bits ftr_generic_32bits[] = {
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_generic[] = {
+static const struct arm64_ftr_bits ftr_generic[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0),
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_generic32[] = {
+static const struct arm64_ftr_bits ftr_generic32[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 32, 0),
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_aa64raz[] = {
+static const struct arm64_ftr_bits ftr_aa64raz[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0),
ARM64_FTR_END,
};
-#define ARM64_FTR_REG(id, table) \
- { \
- .sys_id = id, \
+#define ARM64_FTR_REG(id, table) { \
+ .sys_id = id, \
+ .reg = &(struct arm64_ftr_reg){ \
.name = #id, \
.ftr_bits = &((table)[0]), \
- }
+ }}
-static struct arm64_ftr_reg arm64_ftr_regs[] = {
+static const struct __ftr_reg_entry {
+ u32 sys_id;
+ struct arm64_ftr_reg *reg;
+} arm64_ftr_regs[] = {
/* Op1 = 0, CRn = 0, CRm = 1 */
ARM64_FTR_REG(SYS_ID_PFR0_EL1, ftr_id_pfr0),
@@ -315,7 +327,7 @@ static struct arm64_ftr_reg arm64_ftr_regs[] = {
ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
/* Op1 = 3, CRn = 0, CRm = 0 */
- ARM64_FTR_REG(SYS_CTR_EL0, ftr_ctr),
+ { SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
/* Op1 = 3, CRn = 14, CRm = 0 */
@@ -324,7 +336,7 @@ static struct arm64_ftr_reg arm64_ftr_regs[] = {
static int search_cmp_ftr_reg(const void *id, const void *regp)
{
- return (int)(unsigned long)id - (int)((const struct arm64_ftr_reg *)regp)->sys_id;
+ return (int)(unsigned long)id - (int)((const struct __ftr_reg_entry *)regp)->sys_id;
}
/*
@@ -339,14 +351,20 @@ static int search_cmp_ftr_reg(const void *id, const void *regp)
*/
static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
{
- return bsearch((const void *)(unsigned long)sys_id,
+ const struct __ftr_reg_entry *ret;
+
+ ret = bsearch((const void *)(unsigned long)sys_id,
arm64_ftr_regs,
ARRAY_SIZE(arm64_ftr_regs),
sizeof(arm64_ftr_regs[0]),
search_cmp_ftr_reg);
+ if (ret)
+ return ret->reg;
+ return NULL;
}
-static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val)
+static u64 arm64_ftr_set_value(const struct arm64_ftr_bits *ftrp, s64 reg,
+ s64 ftr_val)
{
u64 mask = arm64_ftr_mask(ftrp);
@@ -355,7 +373,8 @@ static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val
return reg;
}
-static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur)
+static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new,
+ s64 cur)
{
s64 ret = 0;
@@ -376,27 +395,13 @@ static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur)
return ret;
}
-static int __init sort_cmp_ftr_regs(const void *a, const void *b)
-{
- return ((const struct arm64_ftr_reg *)a)->sys_id -
- ((const struct arm64_ftr_reg *)b)->sys_id;
-}
-
-static void __init swap_ftr_regs(void *a, void *b, int size)
-{
- struct arm64_ftr_reg tmp = *(struct arm64_ftr_reg *)a;
- *(struct arm64_ftr_reg *)a = *(struct arm64_ftr_reg *)b;
- *(struct arm64_ftr_reg *)b = tmp;
-}
-
static void __init sort_ftr_regs(void)
{
- /* Keep the array sorted so that we can do the binary search */
- sort(arm64_ftr_regs,
- ARRAY_SIZE(arm64_ftr_regs),
- sizeof(arm64_ftr_regs[0]),
- sort_cmp_ftr_regs,
- swap_ftr_regs);
+ int i;
+
+ /* Check that the array is sorted so that we can do the binary search */
+ for (i = 1; i < ARRAY_SIZE(arm64_ftr_regs); i++)
+ BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id);
}
/*
@@ -407,7 +412,7 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
{
u64 val = 0;
u64 strict_mask = ~0x0ULL;
- struct arm64_ftr_bits *ftrp;
+ const struct arm64_ftr_bits *ftrp;
struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg);
BUG_ON(!reg);
@@ -464,7 +469,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
{
- struct arm64_ftr_bits *ftrp;
+ const struct arm64_ftr_bits *ftrp;
for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
s64 ftr_cur = arm64_ftr_value(ftrp, reg->sys_val);
@@ -1004,23 +1009,33 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
* cannot do anything to fix it up and could cause unexpected failures. So
* we park the CPU.
*/
-void verify_local_cpu_capabilities(void)
+static void verify_local_cpu_capabilities(void)
{
+ verify_local_cpu_errata_workarounds();
+ verify_local_cpu_features(arm64_features);
+ verify_local_elf_hwcaps(arm64_elf_hwcaps);
+ if (system_supports_32bit_el0())
+ verify_local_elf_hwcaps(compat_elf_hwcaps);
+}
+void check_local_cpu_capabilities(void)
+{
+ /*
+ * All secondary CPUs should conform to the early CPU features
+ * in use by the kernel based on boot CPU.
+ */
check_early_cpu_features();
/*
- * If we haven't computed the system capabilities, there is nothing
- * to verify.
+ * If we haven't finalised the system capabilities, this CPU gets
+ * a chance to update the errata work arounds.
+ * Otherwise, this CPU should verify that it has all the system
+ * advertised capabilities.
*/
if (!sys_caps_initialised)
- return;
-
- verify_local_cpu_errata();
- verify_local_cpu_features(arm64_features);
- verify_local_elf_hwcaps(arm64_elf_hwcaps);
- if (system_supports_32bit_el0())
- verify_local_elf_hwcaps(compat_elf_hwcaps);
+ update_cpu_errata_workarounds();
+ else
+ verify_local_cpu_capabilities();
}
static void __init setup_feature_capabilities(void)
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index ed1b84fe6925..b3d5b3e8fbcb 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -363,8 +363,6 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
}
cpuinfo_detect_icache_policy(info);
-
- check_local_cpu_errata();
}
void cpuinfo_store_cpu(void)
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 91fff48d0f57..73ae90ef434c 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -46,16 +46,14 @@ static void mdscr_write(u32 mdscr)
{
unsigned long flags;
local_dbg_save(flags);
- asm volatile("msr mdscr_el1, %0" :: "r" (mdscr));
+ write_sysreg(mdscr, mdscr_el1);
local_dbg_restore(flags);
}
NOKPROBE_SYMBOL(mdscr_write);
static u32 mdscr_read(void)
{
- u32 mdscr;
- asm volatile("mrs %0, mdscr_el1" : "=r" (mdscr));
- return mdscr;
+ return read_sysreg(mdscr_el1);
}
NOKPROBE_SYMBOL(mdscr_read);
@@ -132,36 +130,18 @@ NOKPROBE_SYMBOL(disable_debug_monitors);
/*
* OS lock clearing.
*/
-static void clear_os_lock(void *unused)
+static int clear_os_lock(unsigned int cpu)
{
- asm volatile("msr oslar_el1, %0" : : "r" (0));
-}
-
-static int os_lock_notify(struct notifier_block *self,
- unsigned long action, void *data)
-{
- if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
- clear_os_lock(NULL);
- return NOTIFY_OK;
+ write_sysreg(0, oslar_el1);
+ isb();
+ return 0;
}
-static struct notifier_block os_lock_nb = {
- .notifier_call = os_lock_notify,
-};
-
static int debug_monitors_init(void)
{
- cpu_notifier_register_begin();
-
- /* Clear the OS lock. */
- on_each_cpu(clear_os_lock, NULL, 1);
- isb();
-
- /* Register hotplug handler. */
- __register_cpu_notifier(&os_lock_nb);
-
- cpu_notifier_register_done();
- return 0;
+ return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
+ "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING",
+ clear_os_lock, NULL);
}
postcore_initcall(debug_monitors_init);
@@ -254,7 +234,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
return 0;
if (user_mode(regs)) {
- send_user_sigtrap(TRAP_HWBKPT);
+ send_user_sigtrap(TRAP_TRACE);
/*
* ptrace will disable single step unless explicitly
@@ -382,7 +362,7 @@ NOKPROBE_SYMBOL(aarch32_break_handler);
static int __init debug_traps_init(void)
{
hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP,
- TRAP_HWBKPT, "single-step handler");
+ TRAP_TRACE, "single-step handler");
hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP,
TRAP_BRKPT, "ptrace BRK handler");
return 0;
@@ -435,8 +415,10 @@ NOKPROBE_SYMBOL(kernel_active_single_step);
/* ptrace API */
void user_enable_single_step(struct task_struct *task)
{
- set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
- set_regs_spsr_ss(task_pt_regs(task));
+ struct thread_info *ti = task_thread_info(task);
+
+ if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP))
+ set_regs_spsr_ss(task_pt_regs(task));
}
NOKPROBE_SYMBOL(user_enable_single_step);
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 0f03a8fe2314..aef02d2af3b5 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -219,7 +219,7 @@ ENDPROC(ftrace_graph_caller)
*
* Run ftrace_return_to_handler() before going back to parent.
* @fp is checked against the value passed by ftrace_graph_caller()
- * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
+ * only when HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
*/
ENTRY(return_to_handler)
save_return_regs
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 441420ca7d08..223d54a4d66b 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -104,7 +104,7 @@
str x20, [sp, #S_ORIG_ADDR_LIMIT]
mov x20, #TASK_SIZE_64
str x20, [tsk, #TI_ADDR_LIMIT]
- ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+ /* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
.endif /* \el == 0 */
mrs x22, elr_el1
mrs x23, spsr_el1
@@ -150,13 +150,7 @@
ldr x23, [sp, #S_SP] // load return stack pointer
msr sp_el0, x23
#ifdef CONFIG_ARM64_ERRATUM_845719
-alternative_if_not ARM64_WORKAROUND_845719
- nop
- nop
-#ifdef CONFIG_PID_IN_CONTEXTIDR
- nop
-#endif
-alternative_else
+alternative_if ARM64_WORKAROUND_845719
tbz x22, #4, 1f
#ifdef CONFIG_PID_IN_CONTEXTIDR
mrs x29, contextidr_el1
@@ -165,7 +159,7 @@ alternative_else
msr contextidr_el1, xzr
#endif
1:
-alternative_endif
+alternative_else_nop_endif
#endif
.endif
msr elr_el1, x21 // set up the return data
@@ -707,18 +701,13 @@ ret_fast_syscall_trace:
* Ok, we need to do extra processing, enter the slow path.
*/
work_pending:
- tbnz x1, #TIF_NEED_RESCHED, work_resched
- /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
mov x0, sp // 'regs'
- enable_irq // enable interrupts for do_notify_resume()
bl do_notify_resume
- b ret_to_user
-work_resched:
#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_off // the IRQs are off here, inform the tracing code
+ bl trace_hardirqs_on // enabled while in userspace
#endif
- bl schedule
-
+ ldr x1, [tsk, #TI_FLAGS] // re-check for single-step
+ b finish_ret_to_user
/*
* "slow" syscall return path.
*/
@@ -727,6 +716,7 @@ ret_to_user:
ldr x1, [tsk, #TI_FLAGS]
and x2, x1, #_TIF_WORK_MASK
cbnz x2, work_pending
+finish_ret_to_user:
enable_step_tsk x1, x2
kernel_exit 0
ENDPROC(ret_to_user)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 975b274ee7b5..394c61db5566 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -299,28 +299,16 @@ static inline void fpsimd_pm_init(void) { }
#endif /* CONFIG_CPU_PM */
#ifdef CONFIG_HOTPLUG_CPU
-static int fpsimd_cpu_hotplug_notifier(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
+static int fpsimd_cpu_dead(unsigned int cpu)
{
- unsigned int cpu = (long)hcpu;
-
- switch (action) {
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- per_cpu(fpsimd_last_state, cpu) = NULL;
- break;
- }
- return NOTIFY_OK;
+ per_cpu(fpsimd_last_state, cpu) = NULL;
+ return 0;
}
-static struct notifier_block fpsimd_cpu_hotplug_notifier_block = {
- .notifier_call = fpsimd_cpu_hotplug_notifier,
-};
-
static inline void fpsimd_hotplug_init(void)
{
- register_cpu_notifier(&fpsimd_cpu_hotplug_notifier_block);
+ cpuhp_setup_state_nocalls(CPUHP_ARM64_FPSIMD_DEAD, "arm64/fpsimd:dead",
+ NULL, fpsimd_cpu_dead);
}
#else
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index ebecf9aa33d1..40ad08ac569a 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -138,7 +138,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
return;
err = ftrace_push_return_trace(old, self_addr, &trace.depth,
- frame_pointer);
+ frame_pointer, NULL);
if (err == -EBUSY)
return;
else
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 3e7b050e99dc..427f6d3f084c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -208,13 +208,23 @@ efi_header_end:
__INIT
+ /*
+ * The following callee saved general purpose registers are used on the
+ * primary lowlevel boot path:
+ *
+ * Register Scope Purpose
+ * x21 stext() .. start_kernel() FDT pointer passed at boot in x0
+ * x23 stext() .. start_kernel() physical misalignment/KASLR offset
+ * x28 __create_page_tables() callee preserved temp register
+ * x19/x20 __primary_switch() callee preserved temp registers
+ */
ENTRY(stext)
bl preserve_boot_args
- bl el2_setup // Drop to EL1, w20=cpu_boot_mode
- adrp x24, __PHYS_OFFSET
- and x23, x24, MIN_KIMG_ALIGN - 1 // KASLR offset, defaults to 0
+ bl el2_setup // Drop to EL1, w0=cpu_boot_mode
+ adrp x23, __PHYS_OFFSET
+ and x23, x23, MIN_KIMG_ALIGN - 1 // KASLR offset, defaults to 0
bl set_cpu_boot_mode_flag
- bl __create_page_tables // x25=TTBR0, x26=TTBR1
+ bl __create_page_tables
/*
* The following calls CPU setup code, see arch/arm64/mm/proc.S for
* details.
@@ -222,9 +232,7 @@ ENTRY(stext)
* the TCR will have been set.
*/
bl __cpu_setup // initialise processor
- adr_l x27, __primary_switch // address to jump to after
- // MMU has been enabled
- b __enable_mmu
+ b __primary_switch
ENDPROC(stext)
/*
@@ -311,23 +319,21 @@ ENDPROC(preserve_boot_args)
* been enabled
*/
__create_page_tables:
- adrp x25, idmap_pg_dir
- adrp x26, swapper_pg_dir
mov x28, lr
/*
* Invalidate the idmap and swapper page tables to avoid potential
* dirty cache lines being evicted.
*/
- mov x0, x25
- add x1, x26, #SWAPPER_DIR_SIZE
+ adrp x0, idmap_pg_dir
+ adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE
bl __inval_cache_range
/*
* Clear the idmap and swapper page tables.
*/
- mov x0, x25
- add x6, x26, #SWAPPER_DIR_SIZE
+ adrp x0, idmap_pg_dir
+ adrp x6, swapper_pg_dir + SWAPPER_DIR_SIZE
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
@@ -340,7 +346,7 @@ __create_page_tables:
/*
* Create the identity mapping.
*/
- mov x0, x25 // idmap_pg_dir
+ adrp x0, idmap_pg_dir
adrp x3, __idmap_text_start // __pa(__idmap_text_start)
#ifndef CONFIG_ARM64_VA_BITS_48
@@ -390,7 +396,7 @@ __create_page_tables:
/*
* Map the kernel image (starting with PHYS_OFFSET).
*/
- mov x0, x26 // swapper_pg_dir
+ 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
@@ -405,8 +411,8 @@ __create_page_tables:
* accesses (MMU disabled), invalidate the idmap and swapper page
* tables again to remove any speculatively loaded cache lines.
*/
- mov x0, x25
- add x1, x26, #SWAPPER_DIR_SIZE
+ adrp x0, idmap_pg_dir
+ adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE
dmb sy
bl __inval_cache_range
@@ -416,14 +422,27 @@ ENDPROC(__create_page_tables)
/*
* The following fragment of code is executed with the MMU enabled.
+ *
+ * x0 = __PHYS_OFFSET
*/
- .set initial_sp, init_thread_union + THREAD_START_SP
__primary_switched:
- mov x28, lr // preserve LR
+ adrp x4, init_thread_union
+ add sp, x4, #THREAD_SIZE
+ msr sp_el0, x4 // Save thread_info
+
adr_l x8, vectors // load VBAR_EL1 with virtual
msr vbar_el1, x8 // vector table address
isb
+ stp xzr, x30, [sp, #-16]!
+ mov x29, sp
+
+ str_l x21, __fdt_pointer, x5 // Save FDT pointer
+
+ ldr_l x4, kimage_vaddr // Save the offset between
+ sub x4, x4, x0 // the kernel virtual and
+ str_l x4, kimage_voffset, x5 // physical mappings
+
// Clear BSS
adr_l x0, __bss_start
mov x1, xzr
@@ -432,17 +451,6 @@ __primary_switched:
bl __pi_memset
dsb ishst // Make zero page visible to PTW
- adr_l sp, initial_sp, x4
- mov x4, sp
- and x4, x4, #~(THREAD_SIZE - 1)
- msr sp_el0, x4 // Save thread_info
- str_l x21, __fdt_pointer, x5 // Save FDT pointer
-
- ldr_l x4, kimage_vaddr // Save the offset between
- sub x4, x4, x24 // the kernel virtual and
- str_l x4, kimage_voffset, x5 // physical mappings
-
- mov x29, #0
#ifdef CONFIG_KASAN
bl kasan_early_init
#endif
@@ -454,8 +462,8 @@ __primary_switched:
bl kaslr_early_init // parse FDT for KASLR options
cbz x0, 0f // KASLR disabled? just proceed
orr x23, x23, x0 // record KASLR offset
- ret x28 // we must enable KASLR, return
- // to __enable_mmu()
+ ldp x29, x30, [sp], #16 // we must enable KASLR, return
+ ret // to __primary_switch()
0:
#endif
b start_kernel
@@ -465,7 +473,7 @@ ENDPROC(__primary_switched)
* end early head section, begin head code that is also used for
* hotplug and needs to have the same protections as the text region
*/
- .section ".text","ax"
+ .section ".idmap.text","ax"
ENTRY(kimage_vaddr)
.quad _text - TEXT_OFFSET
@@ -490,7 +498,7 @@ CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2
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
msr sctlr_el1, x0
- mov w20, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1
+ mov w0, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1
isb
ret
@@ -586,7 +594,7 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems
cbz x2, install_el2_stub
- mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
+ mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
isb
ret
@@ -601,7 +609,7 @@ install_el2_stub:
PSR_MODE_EL1h)
msr spsr_el2, x0
msr elr_el2, lr
- mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
+ mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
eret
ENDPROC(el2_setup)
@@ -611,27 +619,39 @@ ENDPROC(el2_setup)
*/
set_cpu_boot_mode_flag:
adr_l x1, __boot_cpu_mode
- cmp w20, #BOOT_CPU_MODE_EL2
+ cmp w0, #BOOT_CPU_MODE_EL2
b.ne 1f
add x1, x1, #4
-1: str w20, [x1] // This CPU has booted in EL1
+1: str w0, [x1] // This CPU has booted in EL1
dmb sy
dc ivac, x1 // Invalidate potentially stale cache line
ret
ENDPROC(set_cpu_boot_mode_flag)
/*
+ * These values are written with the MMU off, but read with the MMU on.
+ * Writers will invalidate the corresponding address, discarding up to a
+ * 'Cache Writeback Granule' (CWG) worth of data. The linker script ensures
+ * sufficient alignment that the CWG doesn't overlap another section.
+ */
+ .pushsection ".mmuoff.data.write", "aw"
+/*
* We need to find out the CPU boot mode long after boot, so we need to
* store it in a writable variable.
*
* This is not in .bss, because we set it sufficiently early that the boot-time
* zeroing of .bss would clobber it.
*/
- .pushsection .data..cacheline_aligned
- .align L1_CACHE_SHIFT
ENTRY(__boot_cpu_mode)
.long BOOT_CPU_MODE_EL2
.long BOOT_CPU_MODE_EL1
+/*
+ * The booting CPU updates the failed status @__early_cpu_boot_status,
+ * with MMU turned off.
+ */
+ENTRY(__early_cpu_boot_status)
+ .long 0
+
.popsection
/*
@@ -639,7 +659,7 @@ ENTRY(__boot_cpu_mode)
* cores are held until we're ready for them to initialise.
*/
ENTRY(secondary_holding_pen)
- bl el2_setup // Drop to EL1, w20=cpu_boot_mode
+ bl el2_setup // Drop to EL1, w0=cpu_boot_mode
bl set_cpu_boot_mode_flag
mrs x0, mpidr_el1
mov_q x1, MPIDR_HWID_BITMASK
@@ -666,12 +686,10 @@ secondary_startup:
/*
* Common entry point for secondary CPUs.
*/
- adrp x25, idmap_pg_dir
- adrp x26, swapper_pg_dir
bl __cpu_setup // initialise processor
-
- adr_l x27, __secondary_switch // address to jump to after enabling the MMU
- b __enable_mmu
+ bl __enable_mmu
+ ldr x8, =__secondary_switched
+ br x8
ENDPROC(secondary_startup)
__secondary_switched:
@@ -706,33 +724,27 @@ ENDPROC(__secondary_switched)
dc ivac, \tmp1 // Invalidate potentially stale cache line
.endm
- .pushsection .data..cacheline_aligned
- .align L1_CACHE_SHIFT
-ENTRY(__early_cpu_boot_status)
- .long 0
- .popsection
-
/*
* Enable the MMU.
*
* x0 = SCTLR_EL1 value for turning on the MMU.
- * x27 = *virtual* address to jump to upon completion
*
- * Other registers depend on the function called upon completion.
+ * Returns to the caller via x30/lr. This requires the caller to be covered
+ * by the .idmap.text section.
*
* Checks if the selected granule size is supported by the CPU.
* If it isn't, park the CPU
*/
- .section ".idmap.text", "ax"
ENTRY(__enable_mmu)
- mrs x22, sctlr_el1 // preserve old SCTLR_EL1 value
mrs x1, ID_AA64MMFR0_EL1
ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
b.ne __no_granule_support
update_early_cpu_boot_status 0, x1, x2
- msr ttbr0_el1, x25 // load TTBR0
- msr ttbr1_el1, x26 // load TTBR1
+ adrp x1, idmap_pg_dir
+ adrp x2, swapper_pg_dir
+ msr ttbr0_el1, x1 // load TTBR0
+ msr ttbr1_el1, x2 // load TTBR1
isb
msr sctlr_el1, x0
isb
@@ -744,29 +756,7 @@ ENTRY(__enable_mmu)
ic iallu
dsb nsh
isb
-#ifdef CONFIG_RANDOMIZE_BASE
- mov x19, x0 // preserve new SCTLR_EL1 value
- blr x27
-
- /*
- * If we return here, we have a KASLR displacement in x23 which we need
- * to take into account by discarding the current kernel mapping and
- * creating a new one.
- */
- msr sctlr_el1, x22 // disable the MMU
- isb
- bl __create_page_tables // recreate kernel mapping
-
- tlbi vmalle1 // Remove any stale TLB entries
- dsb nsh
-
- msr sctlr_el1, x19 // re-enable the MMU
- isb
- ic iallu // flush instructions fetched
- dsb nsh // via old mapping
- isb
-#endif
- br x27
+ ret
ENDPROC(__enable_mmu)
__no_granule_support:
@@ -775,11 +765,11 @@ __no_granule_support:
1:
wfe
wfi
- b 1b
+ b 1b
ENDPROC(__no_granule_support)
-__primary_switch:
#ifdef CONFIG_RELOCATABLE
+__relocate_kernel:
/*
* Iterate over each entry in the relocation table, and apply the
* relocations in place.
@@ -801,14 +791,46 @@ __primary_switch:
add x13, x13, x23 // relocate
str x13, [x11, x23]
b 0b
+1: ret
+ENDPROC(__relocate_kernel)
+#endif
-1:
+__primary_switch:
+#ifdef CONFIG_RANDOMIZE_BASE
+ mov x19, x0 // preserve new SCTLR_EL1 value
+ mrs x20, sctlr_el1 // preserve old SCTLR_EL1 value
#endif
+
+ bl __enable_mmu
+#ifdef CONFIG_RELOCATABLE
+ bl __relocate_kernel
+#ifdef CONFIG_RANDOMIZE_BASE
ldr x8, =__primary_switched
- br x8
-ENDPROC(__primary_switch)
+ adrp x0, __PHYS_OFFSET
+ blr x8
-__secondary_switch:
- ldr x8, =__secondary_switched
+ /*
+ * If we return here, we have a KASLR displacement in x23 which we need
+ * to take into account by discarding the current kernel mapping and
+ * creating a new one.
+ */
+ msr sctlr_el1, x20 // disable the MMU
+ isb
+ bl __create_page_tables // recreate kernel mapping
+
+ tlbi vmalle1 // Remove any stale TLB entries
+ dsb nsh
+
+ msr sctlr_el1, x19 // re-enable the MMU
+ isb
+ ic iallu // flush instructions fetched
+ dsb nsh // via old mapping
+ isb
+
+ bl __relocate_kernel
+#endif
+#endif
+ ldr x8, =__primary_switched
+ adrp x0, __PHYS_OFFSET
br x8
-ENDPROC(__secondary_switch)
+ENDPROC(__primary_switch)
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 46f29b6560ec..e56d848b6466 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -36,8 +36,8 @@
.macro break_before_make_ttbr_switch zero_page, page_table
msr ttbr1_el1, \zero_page
isb
- tlbi vmalle1is
- dsb ish
+ tlbi vmalle1
+ dsb nsh
msr ttbr1_el1, \page_table
isb
.endm
@@ -96,7 +96,7 @@ ENTRY(swsusp_arch_suspend_exit)
add x1, x10, #PAGE_SIZE
/* Clean the copied page to PoU - based on flush_icache_range() */
- dcache_line_size x2, x3
+ raw_dcache_line_size x2, x3
sub x3, x2, #1
bic x4, x10, x3
2: dc cvau, x4 /* clean D line / unified line */
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 65d81f965e74..d55a7b09959b 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -15,9 +15,9 @@
* License terms: GNU General Public License (GPL) version 2
*/
#define pr_fmt(x) "hibernate: " x
+#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <linux/mm.h>
-#include <linux/notifier.h>
#include <linux/pm.h>
#include <linux/sched.h>
#include <linux/suspend.h>
@@ -26,6 +26,7 @@
#include <asm/barrier.h>
#include <asm/cacheflush.h>
+#include <asm/cputype.h>
#include <asm/irqflags.h>
#include <asm/memory.h>
#include <asm/mmu_context.h>
@@ -34,6 +35,7 @@
#include <asm/pgtable-hwdef.h>
#include <asm/sections.h>
#include <asm/smp.h>
+#include <asm/smp_plat.h>
#include <asm/suspend.h>
#include <asm/sysreg.h>
#include <asm/virt.h>
@@ -54,12 +56,6 @@ extern int in_suspend;
/* Do we need to reset el2? */
#define el2_reset_needed() (is_hyp_mode_available() && !is_kernel_in_hyp_mode())
-/*
- * Start/end of the hibernate exit code, this must be copied to a 'safe'
- * location in memory, and executed from there.
- */
-extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
-
/* temporary el2 vectors in the __hibernate_exit_text section. */
extern char hibernate_el2_vectors[];
@@ -67,6 +63,12 @@ extern char hibernate_el2_vectors[];
extern char __hyp_stub_vectors[];
/*
+ * The logical cpu number we should resume on, initialised to a non-cpu
+ * number.
+ */
+static int sleep_cpu = -EINVAL;
+
+/*
* Values that may not change over hibernate/resume. We put the build number
* and date in here so that we guarantee not to resume with a different
* kernel.
@@ -88,6 +90,8 @@ static struct arch_hibernate_hdr {
* re-configure el2.
*/
phys_addr_t __hyp_stub_vectors;
+
+ u64 sleep_cpu_mpidr;
} resume_hdr;
static inline void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i)
@@ -130,12 +134,22 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
else
hdr->__hyp_stub_vectors = 0;
+ /* Save the mpidr of the cpu we called cpu_suspend() on... */
+ if (sleep_cpu < 0) {
+ pr_err("Failing to hibernate on an unkown CPU.\n");
+ return -ENODEV;
+ }
+ hdr->sleep_cpu_mpidr = cpu_logical_map(sleep_cpu);
+ pr_info("Hibernating on CPU %d [mpidr:0x%llx]\n", sleep_cpu,
+ hdr->sleep_cpu_mpidr);
+
return 0;
}
EXPORT_SYMBOL(arch_hibernation_header_save);
int arch_hibernation_header_restore(void *addr)
{
+ int ret;
struct arch_hibernate_hdr_invariants invariants;
struct arch_hibernate_hdr *hdr = addr;
@@ -145,6 +159,24 @@ int arch_hibernation_header_restore(void *addr)
return -EINVAL;
}
+ sleep_cpu = get_logical_index(hdr->sleep_cpu_mpidr);
+ pr_info("Hibernated on CPU %d [mpidr:0x%llx]\n", sleep_cpu,
+ hdr->sleep_cpu_mpidr);
+ if (sleep_cpu < 0) {
+ pr_crit("Hibernated on a CPU not known to this kernel!\n");
+ sleep_cpu = -EINVAL;
+ return -EINVAL;
+ }
+ if (!cpu_online(sleep_cpu)) {
+ pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n");
+ ret = cpu_up(sleep_cpu);
+ if (ret) {
+ pr_err("Failed to bring hibernate-CPU up!\n");
+ sleep_cpu = -EINVAL;
+ return ret;
+ }
+ }
+
resume_hdr = *hdr;
return 0;
@@ -241,6 +273,7 @@ out:
return rc;
}
+#define dcache_clean_range(start, end) __flush_dcache_area(start, (end - start))
int swsusp_arch_suspend(void)
{
@@ -256,10 +289,16 @@ int swsusp_arch_suspend(void)
local_dbg_save(flags);
if (__cpu_suspend_enter(&state)) {
+ sleep_cpu = smp_processor_id();
ret = swsusp_save();
} else {
- /* Clean kernel to PoC for secondary core startup */
- __flush_dcache_area(LMADDR(KERNEL_START), KERNEL_END - KERNEL_START);
+ /* Clean kernel core startup/idle code to PoC*/
+ dcache_clean_range(__mmuoff_data_start, __mmuoff_data_end);
+ dcache_clean_range(__idmap_text_start, __idmap_text_end);
+
+ /* Clean kvm setup code to PoC? */
+ if (el2_reset_needed())
+ dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
/*
* Tell the hibernation core that we've just restored
@@ -267,6 +306,7 @@ int swsusp_arch_suspend(void)
*/
in_suspend = 0;
+ sleep_cpu = -EINVAL;
__cpu_suspend_exit();
}
@@ -275,6 +315,33 @@ int swsusp_arch_suspend(void)
return ret;
}
+static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
+{
+ pte_t pte = *src_pte;
+
+ if (pte_valid(pte)) {
+ /*
+ * Resume will overwrite areas that may be marked
+ * read only (code, rodata). Clear the RDONLY bit from
+ * the temporary mappings we use during restore.
+ */
+ set_pte(dst_pte, pte_clear_rdonly(pte));
+ } else if (debug_pagealloc_enabled() && !pte_none(pte)) {
+ /*
+ * debug_pagealloc will removed the PTE_VALID bit if
+ * the page isn't in use by the resume kernel. It may have
+ * been in use by the original kernel, in which case we need
+ * to put it back in our copy to do the restore.
+ *
+ * Before marking this entry valid, check the pfn should
+ * be mapped.
+ */
+ BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+ set_pte(dst_pte, pte_mkpresent(pte_clear_rdonly(pte)));
+ }
+}
+
static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start,
unsigned long end)
{
@@ -290,13 +357,7 @@ static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start,
src_pte = pte_offset_kernel(src_pmd, start);
do {
- if (!pte_none(*src_pte))
- /*
- * Resume will overwrite areas that may be marked
- * read only (code, rodata). Clear the RDONLY bit from
- * the temporary mappings we use during restore.
- */
- set_pte(dst_pte, __pte(pte_val(*src_pte) & ~PTE_RDONLY));
+ _copy_pte(dst_pte, src_pte, addr);
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
return 0;
@@ -483,27 +544,12 @@ out:
return rc;
}
-static int check_boot_cpu_online_pm_callback(struct notifier_block *nb,
- unsigned long action, void *ptr)
+int hibernate_resume_nonboot_cpu_disable(void)
{
- if (action == PM_HIBERNATION_PREPARE &&
- cpumask_first(cpu_online_mask) != 0) {
- pr_warn("CPU0 is offline.\n");
- return notifier_from_errno(-ENODEV);
+ if (sleep_cpu < 0) {
+ pr_err("Failing to resume from hibernate on an unkown CPU.\n");
+ return -ENODEV;
}
- return NOTIFY_OK;
-}
-
-static int __init check_boot_cpu_online_init(void)
-{
- /*
- * Set this pm_notifier callback with a lower priority than
- * cpu_hotplug_pm_callback, so that cpu_hotplug_pm_callback will be
- * called earlier to disable cpu hotplug before the cpu online check.
- */
- pm_notifier(check_boot_cpu_online_pm_callback, -INT_MAX);
-
- return 0;
+ return freeze_secondary_cpus(sleep_cpu);
}
-core_initcall(check_boot_cpu_online_init);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 26a6bf77d272..948b73148d56 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -857,7 +857,7 @@ void hw_breakpoint_thread_switch(struct task_struct *next)
/*
* CPU initialisation.
*/
-static void hw_breakpoint_reset(void *unused)
+static int hw_breakpoint_reset(unsigned int cpu)
{
int i;
struct perf_event **slots;
@@ -888,28 +888,14 @@ static void hw_breakpoint_reset(void *unused)
write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
}
}
-}
-static int hw_breakpoint_reset_notify(struct notifier_block *self,
- unsigned long action,
- void *hcpu)
-{
- if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) {
- local_irq_disable();
- hw_breakpoint_reset(NULL);
- local_irq_enable();
- }
- return NOTIFY_OK;
+ return 0;
}
-static struct notifier_block hw_breakpoint_reset_nb = {
- .notifier_call = hw_breakpoint_reset_notify,
-};
-
#ifdef CONFIG_CPU_PM
-extern void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *));
+extern void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int));
#else
-static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+static inline void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int))
{
}
#endif
@@ -919,36 +905,34 @@ static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
*/
static int __init arch_hw_breakpoint_init(void)
{
+ int ret;
+
core_num_brps = get_num_brps();
core_num_wrps = get_num_wrps();
pr_info("found %d breakpoint and %d watchpoint registers.\n",
core_num_brps, core_num_wrps);
- cpu_notifier_register_begin();
-
- /*
- * Reset the breakpoint resources. We assume that a halting
- * debugger will leave the world in a nice state for us.
- */
- smp_call_function(hw_breakpoint_reset, NULL, 1);
- hw_breakpoint_reset(NULL);
-
/* Register debug fault handlers. */
hook_debug_fault_code(DBG_ESR_EVT_HWBP, breakpoint_handler, SIGTRAP,
TRAP_HWBKPT, "hw-breakpoint handler");
hook_debug_fault_code(DBG_ESR_EVT_HWWP, watchpoint_handler, SIGTRAP,
TRAP_HWBKPT, "hw-watchpoint handler");
- /* Register hotplug notifier. */
- __register_cpu_notifier(&hw_breakpoint_reset_nb);
-
- cpu_notifier_register_done();
+ /*
+ * Reset the breakpoint resources. We assume that a halting
+ * debugger will leave the world in a nice state for us.
+ */
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
+ "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING",
+ hw_breakpoint_reset, NULL);
+ if (ret)
+ pr_err("failed to register CPU hotplug notifier: %d\n", ret);
/* Register cpu_suspend hw breakpoint restore hook */
cpu_suspend_set_dbg_restorer(hw_breakpoint_reset);
- return 0;
+ return ret;
}
arch_initcall(arch_hw_breakpoint_init);
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 63f9432d05e8..6f2ac4fc66ca 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -96,7 +96,7 @@ static void __kprobes *patch_map(void *addr, int fixmap)
if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX))
page = vmalloc_to_page(addr);
- else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA))
+ else if (!module)
page = pfn_to_page(PHYS_PFN(__pa(addr)));
else
return addr;
@@ -1202,6 +1202,19 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset)
BUG();
}
+s32 aarch64_insn_adrp_get_offset(u32 insn)
+{
+ BUG_ON(!aarch64_insn_is_adrp(insn));
+ return aarch64_insn_decode_immediate(AARCH64_INSN_IMM_ADR, insn) << 12;
+}
+
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset)
+{
+ BUG_ON(!aarch64_insn_is_adrp(insn));
+ return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn,
+ offset >> 12);
+}
+
/*
* Extract the Op/CR data from a msr/mrs instruction.
*/
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index b05469173ba5..769f24ef628c 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -6,6 +6,7 @@
* published by the Free Software Foundation.
*/
+#include <linux/cache.h>
#include <linux/crc32.h>
#include <linux/init.h>
#include <linux/libfdt.h>
@@ -20,7 +21,7 @@
#include <asm/pgtable.h>
#include <asm/sections.h>
-u64 __read_mostly module_alloc_base;
+u64 __ro_after_init module_alloc_base;
u16 __initdata memstart_offset_seed;
static __init u64 get_kaslr_seed(void *fdt)
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 8c57f6496e56..e017a9493b92 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -19,10 +19,13 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/bug.h>
#include <linux/irq.h>
#include <linux/kdebug.h>
#include <linux/kgdb.h>
#include <linux/kprobes.h>
+#include <asm/debug-monitors.h>
+#include <asm/insn.h>
#include <asm/traps.h>
struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
@@ -338,15 +341,24 @@ void kgdb_arch_exit(void)
unregister_die_notifier(&kgdb_notifier);
}
-/*
- * ARM instructions are always in LE.
- * Break instruction is encoded in LE format
- */
-struct kgdb_arch arch_kgdb_ops = {
- .gdb_bpt_instr = {
- KGDB_DYN_BRK_INS_BYTE(0),
- KGDB_DYN_BRK_INS_BYTE(1),
- KGDB_DYN_BRK_INS_BYTE(2),
- KGDB_DYN_BRK_INS_BYTE(3),
- }
-};
+struct kgdb_arch arch_kgdb_ops;
+
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+ int err;
+
+ BUILD_BUG_ON(AARCH64_INSN_SIZE != BREAK_INSTR_SIZE);
+
+ err = aarch64_insn_read((void *)bpt->bpt_addr, (u32 *)bpt->saved_instr);
+ if (err)
+ return err;
+
+ return aarch64_insn_write((void *)bpt->bpt_addr,
+ (u32)AARCH64_BREAK_KGDB_DYN_DBG);
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+ return aarch64_insn_write((void *)bpt->bpt_addr,
+ *(u32 *)bpt->saved_instr);
+}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 838ccf123307..a9310a69fffd 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -24,6 +24,7 @@
#include <asm/sysreg.h>
#include <asm/virt.h>
+#include <linux/acpi.h>
#include <linux/of.h>
#include <linux/perf/arm_pmu.h>
#include <linux/platform_device.h>
@@ -190,13 +191,23 @@
#define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS 0xED
/* PMUv3 HW events mapping. */
+
+/*
+ * ARMv8 Architectural defined events, not all of these may
+ * be supported on any given implementation. Undefined events will
+ * be disabled at run-time.
+ */
static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
PERF_MAP_ALL_UNSUPPORTED,
[PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED,
[PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
[PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
+ [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
};
/* ARM Cortex-A53 HW events mapping. */
@@ -258,6 +269,15 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
+ [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE,
+ [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
+
+ [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL,
+ [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB,
+
+ [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
+ [C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB,
+
[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
[C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
@@ -523,12 +543,6 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
.attrs = armv8_pmuv3_format_attrs,
};
-static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
- &armv8_pmuv3_events_attr_group,
- &armv8_pmuv3_format_attr_group,
- NULL,
-};
-
/*
* Perf Events' indices
*/
@@ -905,9 +919,22 @@ static void armv8pmu_reset(void *info)
static int armv8_pmuv3_map_event(struct perf_event *event)
{
- return armpmu_map_event(event, &armv8_pmuv3_perf_map,
- &armv8_pmuv3_perf_cache_map,
- ARMV8_PMU_EVTYPE_EVENT);
+ int hw_event_id;
+ struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+
+ hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map,
+ &armv8_pmuv3_perf_cache_map,
+ ARMV8_PMU_EVTYPE_EVENT);
+ if (hw_event_id < 0)
+ return hw_event_id;
+
+ /* disable micro/arch events not supported by this PMU */
+ if ((hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) &&
+ !test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
+ return -EOPNOTSUPP;
+ }
+
+ return hw_event_id;
}
static int armv8_a53_map_event(struct perf_event *event)
@@ -985,7 +1012,10 @@ static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_pmuv3";
cpu_pmu->map_event = armv8_pmuv3_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -994,7 +1024,10 @@ static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_cortex_a53";
cpu_pmu->map_event = armv8_a53_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1003,7 +1036,10 @@ static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_cortex_a57";
cpu_pmu->map_event = armv8_a57_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1012,7 +1048,10 @@ static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_cortex_a72";
cpu_pmu->map_event = armv8_a57_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1021,7 +1060,10 @@ static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_cavium_thunder";
cpu_pmu->map_event = armv8_thunder_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1030,7 +1072,10 @@ static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_brcm_vulcan";
cpu_pmu->map_event = armv8_vulcan_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1044,21 +1089,32 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
{},
};
+/*
+ * Non DT systems have their micro/arch events probed at run-time.
+ * A fairly complete list of generic events are provided and ones that
+ * aren't supported by the current PMU are disabled.
+ */
+static const struct pmu_probe_info armv8_pmu_probe_table[] = {
+ PMU_PROBE(0, 0, armv8_pmuv3_init), /* enable all defined counters */
+ { /* sentinel value */ }
+};
+
static int armv8_pmu_device_probe(struct platform_device *pdev)
{
- return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
+ if (acpi_disabled)
+ return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
+ NULL);
+
+ return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
+ armv8_pmu_probe_table);
}
static struct platform_driver armv8_pmu_driver = {
.driver = {
- .name = "armv8-pmu",
+ .name = ARMV8_PMU_PDEV_NAME,
.of_match_table = armv8_pmu_of_device_ids,
},
.probe = armv8_pmu_device_probe,
};
-static int __init register_armv8_pmu_driver(void)
-{
- return platform_driver_register(&armv8_pmu_driver);
-}
-device_initcall(register_armv8_pmu_driver);
+builtin_platform_driver(armv8_pmu_driver);
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index 37e47a9d617e..d1731bf977ef 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -16,6 +16,7 @@
#include <linux/kernel.h>
#include <linux/kprobes.h>
#include <linux/module.h>
+#include <linux/kallsyms.h>
#include <asm/kprobes.h>
#include <asm/insn.h>
#include <asm/sections.h>
@@ -122,7 +123,7 @@ arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
static bool __kprobes
is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end)
{
- while (scan_start > scan_end) {
+ while (scan_start >= scan_end) {
/*
* atomic region starts from exclusive load and ends with
* exclusive store.
@@ -142,33 +143,30 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
{
enum kprobe_insn decoded;
kprobe_opcode_t insn = le32_to_cpu(*addr);
- kprobe_opcode_t *scan_start = addr - 1;
- kprobe_opcode_t *scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
-#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
- struct module *mod;
-#endif
-
- if (addr >= (kprobe_opcode_t *)_text &&
- scan_end < (kprobe_opcode_t *)_text)
- scan_end = (kprobe_opcode_t *)_text;
-#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
- else {
- preempt_disable();
- mod = __module_address((unsigned long)addr);
- if (mod && within_module_init((unsigned long)addr, mod) &&
- !within_module_init((unsigned long)scan_end, mod))
- scan_end = (kprobe_opcode_t *)mod->init_layout.base;
- else if (mod && within_module_core((unsigned long)addr, mod) &&
- !within_module_core((unsigned long)scan_end, mod))
- scan_end = (kprobe_opcode_t *)mod->core_layout.base;
- preempt_enable();
+ kprobe_opcode_t *scan_end = NULL;
+ unsigned long size = 0, offset = 0;
+
+ /*
+ * If there's a symbol defined in front of and near enough to
+ * the probe address assume it is the entry point to this
+ * code and use it to further limit how far back we search
+ * when determining if we're in an atomic sequence. If we could
+ * not find any symbol skip the atomic test altogether as we
+ * could otherwise end up searching irrelevant text/literals.
+ * KPROBES depends on KALLSYMS so this last case should never
+ * happen.
+ */
+ if (kallsyms_lookup_size_offset((unsigned long) addr, &size, &offset)) {
+ if (offset < (MAX_ATOMIC_CONTEXT_SIZE*sizeof(kprobe_opcode_t)))
+ scan_end = addr - (offset / sizeof(kprobe_opcode_t));
+ else
+ scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
}
-#endif
decoded = arm_probe_decode_insn(insn, asi);
- if (decoded == INSN_REJECTED ||
- is_probed_address_atomic(scan_start, scan_end))
- return INSN_REJECTED;
+ if (decoded != INSN_REJECTED && scan_end)
+ if (is_probed_address_atomic(addr - 1, scan_end))
+ return INSN_REJECTED;
return decoded;
}
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index c6b0f40620d8..f5077ea7af6d 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -19,7 +19,7 @@
#include <linux/kasan.h>
#include <linux/kernel.h>
#include <linux/kprobes.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/slab.h>
#include <linux/stop_machine.h>
#include <linux/stringify.h>
@@ -31,7 +31,7 @@
#include <asm/insn.h>
#include <asm/uaccess.h>
#include <asm/irq.h>
-#include <asm-generic/sections.h>
+#include <asm/sections.h>
#include "decode-insn.h"
@@ -166,13 +166,18 @@ static void __kprobes set_current_kprobe(struct kprobe *p)
}
/*
- * The D-flag (Debug mask) is set (masked) upon debug exception entry.
- * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive
- * probe i.e. when probe hit from kprobe handler context upon
- * executing the pre/post handlers. In this case we return with
- * D-flag clear so that single-stepping can be carried-out.
- *
- * Leave D-flag set in all other cases.
+ * When PSTATE.D is set (masked), then software step exceptions can not be
+ * generated.
+ * SPSR's D bit shows the value of PSTATE.D immediately before the
+ * exception was taken. PSTATE.D is set while entering into any exception
+ * mode, however software clears it for any normal (none-debug-exception)
+ * mode in the exception entry. Therefore, when we are entering into kprobe
+ * breakpoint handler from any normal mode then SPSR.D bit is already
+ * cleared, however it is set when we are entering from any debug exception
+ * mode.
+ * Since we always need to generate single step exception after a kprobe
+ * breakpoint exception therefore we need to clear it unconditionally, when
+ * we become sure that the current breakpoint exception is for kprobe.
*/
static void __kprobes
spsr_set_debug_flag(struct pt_regs *regs, int mask)
@@ -245,10 +250,7 @@ static void __kprobes setup_singlestep(struct kprobe *p,
set_ss_context(kcb, slot); /* mark pending ss */
- if (kcb->kprobe_status == KPROBE_REENTER)
- spsr_set_debug_flag(regs, 0);
- else
- WARN_ON(regs->pstate & PSR_D_BIT);
+ spsr_set_debug_flag(regs, 0);
/* IRQs and single stepping do not mix well. */
kprobes_save_local_irqflag(kcb, regs);
@@ -333,8 +335,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
BUG();
kernel_disable_single_step();
- if (kcb->kprobe_status == KPROBE_REENTER)
- spsr_set_debug_flag(regs, 1);
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
@@ -457,9 +457,6 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
kprobes_restore_local_irqflag(kcb, regs);
kernel_disable_single_step();
- if (kcb->kprobe_status == KPROBE_REENTER)
- spsr_set_debug_flag(regs, 1);
-
post_kprobe_handler(kcb, regs);
}
@@ -543,9 +540,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
bool arch_within_kprobe_blacklist(unsigned long addr)
{
- extern char __idmap_text_start[], __idmap_text_end[];
- extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
-
if ((addr >= (unsigned long)__kprobes_text_start &&
addr < (unsigned long)__kprobes_text_end) ||
(addr >= (unsigned long)__entry_text_start &&
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 6cd2612236dc..a4f5f766af08 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -202,7 +202,7 @@ void show_regs(struct pt_regs * regs)
static void tls_thread_flush(void)
{
- asm ("msr tpidr_el0, xzr");
+ write_sysreg(0, tpidr_el0);
if (is_compat_task()) {
current->thread.tp_value = 0;
@@ -213,7 +213,7 @@ static void tls_thread_flush(void)
* with a stale shadow state during context switch.
*/
barrier();
- asm ("msr tpidrro_el0, xzr");
+ write_sysreg(0, tpidrro_el0);
}
}
@@ -253,7 +253,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
* Read the current TLS pointer from tpidr_el0 as it may be
* out-of-sync with the saved value.
*/
- asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p)));
+ *task_user_tls(p) = read_sysreg(tpidr_el0);
if (stack_start) {
if (is_compat_thread(task_thread_info(p)))
@@ -289,17 +289,15 @@ static void tls_thread_switch(struct task_struct *next)
{
unsigned long tpidr, tpidrro;
- asm("mrs %0, tpidr_el0" : "=r" (tpidr));
+ tpidr = read_sysreg(tpidr_el0);
*task_user_tls(current) = tpidr;
tpidr = *task_user_tls(next);
tpidrro = is_compat_thread(task_thread_info(next)) ?
next->thread.tp_value : 0;
- asm(
- " msr tpidr_el0, %0\n"
- " msr tpidrro_el0, %1"
- : : "r" (tpidr), "r" (tpidrro));
+ write_sysreg(tpidr, tpidr_el0);
+ write_sysreg(tpidrro, tpidrro_el0);
}
/* Restore the UAO state depending on next's addr_limit */
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index 51b73cdde287..ce704a4aeadd 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -34,7 +34,7 @@ ENTRY(arm64_relocate_new_kernel)
/* Setup the list loop variables. */
mov x17, x1 /* x17 = kimage_start */
mov x16, x0 /* x16 = kimage_head */
- dcache_line_size x15, x0 /* x15 = dcache line size */
+ raw_dcache_line_size x15, x0 /* x15 = dcache line size */
mov x14, xzr /* x14 = entry ptr */
mov x13, xzr /* x13 = copy dest */
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 536dce22fe76..f534f492a268 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -206,10 +206,15 @@ static void __init request_standard_resources(void)
for_each_memblock(memory, region) {
res = alloc_bootmem_low(sizeof(*res));
- res->name = "System RAM";
+ if (memblock_is_nomap(region)) {
+ res->name = "reserved";
+ res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ } else {
+ res->name = "System RAM";
+ res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ }
res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
- res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
request_resource(&iomem_resource, res);
@@ -228,7 +233,7 @@ void __init setup_arch(char **cmdline_p)
{
pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id());
- sprintf(init_utsname()->machine, ELF_PLATFORM);
+ sprintf(init_utsname()->machine, UTS_MACHINE);
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index a8eafdbc7cb8..404dd67080b9 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -402,15 +402,31 @@ static void do_signal(struct pt_regs *regs)
asmlinkage void do_notify_resume(struct pt_regs *regs,
unsigned int thread_flags)
{
- if (thread_flags & _TIF_SIGPENDING)
- do_signal(regs);
-
- if (thread_flags & _TIF_NOTIFY_RESUME) {
- clear_thread_flag(TIF_NOTIFY_RESUME);
- tracehook_notify_resume(regs);
- }
-
- if (thread_flags & _TIF_FOREIGN_FPSTATE)
- fpsimd_restore_current_state();
+ /*
+ * The assembly code enters us with IRQs off, but it hasn't
+ * informed the tracing code of that for efficiency reasons.
+ * Update the trace code with the current status.
+ */
+ trace_hardirqs_off();
+ do {
+ if (thread_flags & _TIF_NEED_RESCHED) {
+ schedule();
+ } else {
+ local_irq_enable();
+
+ if (thread_flags & _TIF_SIGPENDING)
+ do_signal(regs);
+
+ if (thread_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ }
+
+ if (thread_flags & _TIF_FOREIGN_FPSTATE)
+ fpsimd_restore_current_state();
+ }
+ local_irq_disable();
+ thread_flags = READ_ONCE(current_thread_info()->flags);
+ } while (thread_flags & _TIF_WORK_MASK);
}
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index ccf79d849e0a..b8799e7c79de 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -73,10 +73,9 @@ ENTRY(__cpu_suspend_enter)
str x2, [x0, #SLEEP_STACK_DATA_SYSTEM_REGS + CPU_CTX_SP]
/* find the mpidr_hash */
- ldr x1, =sleep_save_stash
- ldr x1, [x1]
+ ldr_l x1, sleep_save_stash
mrs x7, mpidr_el1
- ldr x9, =mpidr_hash
+ adr_l x9, mpidr_hash
ldr x10, [x9, #MPIDR_HASH_MASK]
/*
* Following code relies on the struct mpidr_hash
@@ -95,36 +94,30 @@ ENTRY(__cpu_suspend_enter)
mov x0, #1
ret
ENDPROC(__cpu_suspend_enter)
- .ltorg
+ .pushsection ".idmap.text", "ax"
ENTRY(cpu_resume)
bl el2_setup // if in EL2 drop to EL1 cleanly
+ bl __cpu_setup
/* enable the MMU early - so we can access sleep_save_stash by va */
- adr_l lr, __enable_mmu /* __cpu_setup will return here */
- adr_l x27, _resume_switched /* __enable_mmu will branch here */
- adrp x25, idmap_pg_dir
- adrp x26, swapper_pg_dir
- b __cpu_setup
-ENDPROC(cpu_resume)
-
- .pushsection ".idmap.text", "ax"
-_resume_switched:
+ bl __enable_mmu
ldr x8, =_cpu_resume
br x8
-ENDPROC(_resume_switched)
+ENDPROC(cpu_resume)
.ltorg
.popsection
ENTRY(_cpu_resume)
mrs x1, mpidr_el1
- adrp x8, mpidr_hash
- add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
- /* retrieve mpidr_hash members to compute the hash */
+ adr_l x8, mpidr_hash // x8 = struct mpidr_hash virt address
+
+ /* retrieve mpidr_hash members to compute the hash */
ldr x2, [x8, #MPIDR_HASH_MASK]
ldp w3, w4, [x8, #MPIDR_HASH_SHIFTS]
ldp w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
- /* x7 contains hash index, let's use it to grab context pointer */
+
+ /* x7 contains hash index, let's use it to grab context pointer */
ldr_l x0, sleep_save_stash
ldr x0, [x0, x7, lsl #3]
add x29, x0, #SLEEP_STACK_DATA_CALLEE_REGS
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d93d43352504..d3f151cfd4a1 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -201,12 +201,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
return ret;
}
-static void smp_store_cpu_info(unsigned int cpuid)
-{
- store_cpu_topology(cpuid);
- numa_store_cpu_info(cpuid);
-}
-
/*
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
@@ -239,7 +233,7 @@ asmlinkage void secondary_start_kernel(void)
* this CPU ticks all of those. If it doesn't, the CPU will
* fail to come online.
*/
- verify_local_cpu_capabilities();
+ check_local_cpu_capabilities();
if (cpu_ops[cpu]->cpu_postboot)
cpu_ops[cpu]->cpu_postboot();
@@ -254,7 +248,7 @@ asmlinkage void secondary_start_kernel(void)
*/
notify_cpu_starting(cpu);
- smp_store_cpu_info(cpu);
+ store_cpu_topology(cpu);
/*
* OK, now it's safe to let the boot CPU continue. Wait for
@@ -437,8 +431,19 @@ void __init smp_cpus_done(unsigned int max_cpus)
void __init smp_prepare_boot_cpu(void)
{
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+ /*
+ * Initialise the static keys early as they may be enabled by the
+ * cpufeature code.
+ */
+ jump_label_init();
cpuinfo_store_boot_cpu();
save_boot_cpu_run_el();
+ /*
+ * Run the errata work around checks on the boot CPU, once we have
+ * initialised the cpu feature infrastructure from
+ * cpuinfo_store_boot_cpu() above.
+ */
+ update_cpu_errata_workarounds();
}
static u64 __init of_get_cpu_mpidr(struct device_node *dn)
@@ -619,6 +624,7 @@ static void __init of_parse_and_init_cpus(void)
}
bootcpu_valid = true;
+ early_map_cpu_to_node(0, of_node_to_nid(dn));
/*
* cpu_logical_map has already been
@@ -689,10 +695,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
{
int err;
unsigned int cpu;
+ unsigned int this_cpu;
init_cpu_topology();
- smp_store_cpu_info(smp_processor_id());
+ this_cpu = smp_processor_id();
+ store_cpu_topology(this_cpu);
+ numa_store_cpu_info(this_cpu);
/*
* If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set
@@ -719,6 +728,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
continue;
set_cpu_present(cpu, true);
+ numa_store_cpu_info(cpu);
}
}
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 18a71bcd26ee..9a00eee9acc8 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -29,7 +29,8 @@
#include <asm/smp_plat.h>
extern void secondary_holding_pen(void);
-volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
+volatile unsigned long __section(".mmuoff.data.read")
+secondary_holding_pen_release = INVALID_HWID;
static phys_addr_t cpu_release_addr[NR_CPUS];
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d9751a4769e7..c2efddfca18c 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -43,6 +43,9 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
unsigned long fp = frame->fp;
unsigned long irq_stack_ptr;
+ if (!tsk)
+ tsk = current;
+
/*
* Switching between stacks is valid when tracing current and in
* non-preemptible context.
@@ -67,7 +70,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- if (tsk && tsk->ret_stack &&
+ if (tsk->ret_stack &&
(frame->pc == (unsigned long)return_to_handler)) {
/*
* This is a case where function graph tracer has
@@ -152,6 +155,27 @@ static int save_trace(struct stackframe *frame, void *d)
return trace->nr_entries >= trace->max_entries;
}
+void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+ struct stack_trace_data data;
+ struct stackframe frame;
+
+ data.trace = trace;
+ data.skip = trace->skip;
+ data.no_sched_functions = 0;
+
+ frame.fp = regs->regs[29];
+ frame.sp = regs->sp;
+ frame.pc = regs->pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ frame.graph = current->curr_ret_stack;
+#endif
+
+ walk_stackframe(current, &frame, save_trace, &data);
+ if (trace->nr_entries < trace->max_entries)
+ trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
struct stack_trace_data data;
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index b616e365cee3..ad734142070d 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -23,8 +23,8 @@ unsigned long *sleep_save_stash;
* time the notifier runs debug exceptions might have been enabled already,
* with HW breakpoints registers content still in an unknown state.
*/
-static void (*hw_breakpoint_restore)(void *);
-void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+static int (*hw_breakpoint_restore)(unsigned int);
+void __init cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int))
{
/* Prevent multiple restore hook initializations */
if (WARN_ON(hw_breakpoint_restore))
@@ -34,6 +34,8 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
void notrace __cpu_suspend_exit(void)
{
+ unsigned int cpu = smp_processor_id();
+
/*
* We are resuming from reset with the idmap active in TTBR0_EL1.
* We must uninstall the idmap and restore the expected MMU
@@ -45,7 +47,7 @@ void notrace __cpu_suspend_exit(void)
* Restore per-cpu offset before any kernel
* subsystem relying on it has a chance to run.
*/
- set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+ set_my_cpu_offset(per_cpu_offset(cpu));
/*
* Restore HW breakpoint registers to sane values
@@ -53,7 +55,7 @@ void notrace __cpu_suspend_exit(void)
* through local_dbg_restore.
*/
if (hw_breakpoint_restore)
- hw_breakpoint_restore(NULL);
+ hw_breakpoint_restore(cpu);
}
/*
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 28c511b06edf..abaf582fc7a8 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -94,7 +94,7 @@ long compat_arm_syscall(struct pt_regs *regs)
* See comment in tls_thread_flush.
*/
barrier();
- asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0]));
+ write_sysreg(regs->regs[0], tpidrro_el0);
return 0;
default:
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index e04f83873af7..5ff020f8fb7f 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -142,6 +142,11 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
unsigned long irq_stack_ptr;
int skip;
+ pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
+
+ if (!tsk)
+ tsk = current;
+
/*
* Switching between stacks is valid when tracing current and in
* non-preemptible context.
@@ -151,11 +156,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
else
irq_stack_ptr = 0;
- pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
-
- if (!tsk)
- tsk = current;
-
if (tsk == current) {
frame.fp = (unsigned long)__builtin_frame_address(0);
frame.sp = current_stack_pointer;
@@ -447,36 +447,29 @@ void cpu_enable_cache_maint_trap(void *__unused)
: "=r" (res) \
: "r" (address), "i" (-EFAULT) )
-asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
{
unsigned long address;
- int ret;
-
- /* if this is a write with: Op0=1, Op2=1, Op1=3, CRn=7 */
- if ((esr & 0x01fffc01) == 0x0012dc00) {
- int rt = (esr >> 5) & 0x1f;
- int crm = (esr >> 1) & 0x0f;
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
+ int ret = 0;
- address = (rt == 31) ? 0 : regs->regs[rt];
+ address = (rt == 31) ? 0 : regs->regs[rt];
- switch (crm) {
- case 11: /* DC CVAU, gets promoted */
- __user_cache_maint("dc civac", address, ret);
- break;
- case 10: /* DC CVAC, gets promoted */
- __user_cache_maint("dc civac", address, ret);
- break;
- case 14: /* DC CIVAC */
- __user_cache_maint("dc civac", address, ret);
- break;
- case 5: /* IC IVAU */
- __user_cache_maint("ic ivau", address, ret);
- break;
- default:
- force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
- return;
- }
- } else {
+ switch (crm) {
+ case ESR_ELx_SYS64_ISS_CRM_DC_CVAU: /* DC CVAU, gets promoted */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case ESR_ELx_SYS64_ISS_CRM_DC_CVAC: /* DC CVAC, gets promoted */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case ESR_ELx_SYS64_ISS_CRM_DC_CIVAC: /* DC CIVAC */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case ESR_ELx_SYS64_ISS_CRM_IC_IVAU: /* IC IVAU */
+ __user_cache_maint("ic ivau", address, ret);
+ break;
+ default:
force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
return;
}
@@ -487,6 +480,48 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
regs->pc += 4;
}
+static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+ regs->regs[rt] = arm64_ftr_reg_ctrel0.sys_val;
+ regs->pc += 4;
+}
+
+struct sys64_hook {
+ unsigned int esr_mask;
+ unsigned int esr_val;
+ void (*handler)(unsigned int esr, struct pt_regs *regs);
+};
+
+static struct sys64_hook sys64_hooks[] = {
+ {
+ .esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL,
+ .handler = user_cache_maint_handler,
+ },
+ {
+ /* Trap read access to CTR_EL0 */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ,
+ .handler = ctr_read_handler,
+ },
+ {},
+};
+
+asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+{
+ struct sys64_hook *hook;
+
+ for (hook = sys64_hooks; hook->handler; hook++)
+ if ((hook->esr_mask & esr) == hook->esr_val) {
+ hook->handler(esr, regs);
+ return;
+ }
+
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
+}
+
long compat_arm_syscall(struct pt_regs *regs);
asmlinkage long do_ni_syscall(struct pt_regs *regs)
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 076312b17d4f..a2c2478e7d78 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -18,12 +18,13 @@
* Author: Will Deacon <will.deacon@arm.com>
*/
-#include <linux/kernel.h>
+#include <linux/cache.h>
#include <linux/clocksource.h>
#include <linux/elf.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/gfp.h>
+#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/signal.h>
@@ -37,8 +38,7 @@
#include <asm/vdso_datapage.h>
extern char vdso_start, vdso_end;
-static unsigned long vdso_pages;
-static struct page **vdso_pagelist;
+static unsigned long vdso_pages __ro_after_init;
/*
* The vDSO data page.
@@ -53,9 +53,9 @@ struct vdso_data *vdso_data = &vdso_data_store.data;
/*
* Create and map the vectors page for AArch32 tasks.
*/
-static struct page *vectors_page[1];
+static struct page *vectors_page[1] __ro_after_init;
-static int alloc_vectors_page(void)
+static int __init alloc_vectors_page(void)
{
extern char __kuser_helper_start[], __kuser_helper_end[];
extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
@@ -88,7 +88,7 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
unsigned long addr = AARCH32_VECTORS_BASE;
- static struct vm_special_mapping spec = {
+ static const struct vm_special_mapping spec = {
.name = "[vectors]",
.pages = vectors_page,
@@ -110,11 +110,19 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
}
#endif /* CONFIG_COMPAT */
-static struct vm_special_mapping vdso_spec[2];
+static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
+ {
+ .name = "[vvar]",
+ },
+ {
+ .name = "[vdso]",
+ },
+};
static int __init vdso_init(void)
{
int i;
+ struct page **vdso_pagelist;
if (memcmp(&vdso_start, "\177ELF", 4)) {
pr_err("vDSO is not a valid ELF object!\n");
@@ -138,16 +146,8 @@ static int __init vdso_init(void)
for (i = 0; i < vdso_pages; i++)
vdso_pagelist[i + 1] = pfn_to_page(PHYS_PFN(__pa(&vdso_start)) + i);
- /* Populate the special mapping structures */
- vdso_spec[0] = (struct vm_special_mapping) {
- .name = "[vvar]",
- .pages = vdso_pagelist,
- };
-
- vdso_spec[1] = (struct vm_special_mapping) {
- .name = "[vdso]",
- .pages = &vdso_pagelist[1],
- };
+ vdso_spec[0].pages = &vdso_pagelist[0];
+ vdso_spec[1].pages = &vdso_pagelist[1];
return 0;
}
@@ -201,7 +201,7 @@ up_fail:
*/
void update_vsyscall(struct timekeeper *tk)
{
- u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter");
+ u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
++vdso_data->tb_seq_count;
smp_wmb();
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 659963d40bb4..5ce9b2929e0d 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -185,6 +185,25 @@ SECTIONS
_data = .;
_sdata = .;
RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+
+ /*
+ * Data written with the MMU off but read with the MMU on requires
+ * cache lines to be invalidated, discarding up to a Cache Writeback
+ * Granule (CWG) of data from the cache. Keep the section that
+ * requires this type of maintenance to be in its own Cache Writeback
+ * Granule (CWG) area so the cache maintenance operations don't
+ * interfere with adjacent data.
+ */
+ .mmuoff.data.write : ALIGN(SZ_2K) {
+ __mmuoff_data_start = .;
+ *(.mmuoff.data.write)
+ }
+ . = ALIGN(SZ_2K);
+ .mmuoff.data.read : {
+ *(.mmuoff.data.read)
+ __mmuoff_data_end = .;
+ }
+
PECOFF_EDATA_PADDING
_edata = .;
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 7ce931565151..2726635dceba 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -46,10 +46,6 @@ alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
hvc #0
ldr lr, [sp], #16
ret
-alternative_else
+alternative_else_nop_endif
b __vhe_hyp_call
- nop
- nop
- nop
-alternative_endif
ENDPROC(__kvm_call_hyp)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e51367d159d0..f302fdb3a030 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -36,6 +36,7 @@
#include <asm/kvm_host.h>
#include <asm/kvm_mmu.h>
#include <asm/perf_event.h>
+#include <asm/sysreg.h>
#include <trace/events/kvm.h>
@@ -67,11 +68,9 @@ static u32 get_ccsidr(u32 csselr)
/* Make sure noone else changes CSSELR during this! */
local_irq_disable();
- /* Put value into CSSELR */
- asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
+ write_sysreg(csselr, csselr_el1);
isb();
- /* Read result out of CCSIDR */
- asm volatile("mrs %0, ccsidr_el1" : "=r" (ccsidr));
+ ccsidr = read_sysreg(ccsidr_el1);
local_irq_enable();
return ccsidr;
@@ -174,9 +173,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
if (p->is_write) {
return ignore_write(vcpu, p);
} else {
- u32 val;
- asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
- p->regval = val;
+ p->regval = read_sysreg(dbgauthstatus_el1);
return true;
}
}
@@ -429,10 +426,7 @@ static void reset_wcr(struct kvm_vcpu *vcpu,
static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
- u64 amair;
-
- asm volatile("mrs %0, amair_el1\n" : "=r" (amair));
- vcpu_sys_reg(vcpu, AMAIR_EL1) = amair;
+ vcpu_sys_reg(vcpu, AMAIR_EL1) = read_sysreg(amair_el1);
}
static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
@@ -456,8 +450,9 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 pmcr, val;
- asm volatile("mrs %0, pmcr_el0\n" : "=r" (pmcr));
- /* Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) is reset to UNKNOWN
+ pmcr = read_sysreg(pmcr_el0);
+ /*
+ * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
* except PMCR.E resetting to zero.
*/
val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
@@ -557,9 +552,9 @@ static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
return false;
if (!(p->Op2 & 1))
- asm volatile("mrs %0, pmceid0_el0\n" : "=r" (pmceid));
+ pmceid = read_sysreg(pmceid0_el0);
else
- asm volatile("mrs %0, pmceid1_el0\n" : "=r" (pmceid));
+ pmceid = read_sysreg(pmceid1_el0);
p->regval = pmceid;
@@ -1833,11 +1828,7 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
static void get_##reg(struct kvm_vcpu *v, \
const struct sys_reg_desc *r) \
{ \
- u64 val; \
- \
- asm volatile("mrs %0, " __stringify(reg) "\n" \
- : "=r" (val)); \
- ((struct sys_reg_desc *)r)->val = val; \
+ ((struct sys_reg_desc *)r)->val = read_sysreg(reg); \
}
FUNCTION_INVARIANT(midr_el1)
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index ed90578fa120..46af7186bca6 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -26,6 +26,7 @@
#include <asm/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
+#include <asm/sysreg.h>
#include <linux/init.h>
#include "sys_regs.h"
@@ -43,10 +44,7 @@ static bool access_actlr(struct kvm_vcpu *vcpu,
static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
- u64 actlr;
-
- asm volatile("mrs %0, actlr_el1\n" : "=r" (actlr));
- vcpu_sys_reg(vcpu, ACTLR_EL1) = actlr;
+ vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1);
}
/*
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index 4c1e700840b6..c3cd65e31814 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -29,14 +29,11 @@
* x1 - src
*/
ENTRY(copy_page)
-alternative_if_not ARM64_HAS_NO_HW_PREFETCH
- nop
- nop
-alternative_else
+alternative_if ARM64_HAS_NO_HW_PREFETCH
# Prefetch two cache lines ahead.
prfm pldl1strm, [x1, #128]
prfm pldl1strm, [x1, #256]
-alternative_endif
+alternative_else_nop_endif
ldp x2, x3, [x1]
ldp x4, x5, [x1, #16]
@@ -52,11 +49,9 @@ alternative_endif
1:
subs x18, x18, #128
-alternative_if_not ARM64_HAS_NO_HW_PREFETCH
- nop
-alternative_else
+alternative_if ARM64_HAS_NO_HW_PREFETCH
prfm pldl1strm, [x1, #384]
-alternative_endif
+alternative_else_nop_endif
stnp x2, x3, [x0]
ldp x2, x3, [x1]
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 07d7352d7c38..58b5a906ff78 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -105,19 +105,20 @@ ENTRY(__clean_dcache_area_pou)
ENDPROC(__clean_dcache_area_pou)
/*
- * __inval_cache_range(start, end)
- * - start - start address of region
- * - end - end address of region
+ * __dma_inv_area(start, size)
+ * - start - virtual start address of region
+ * - size - size in question
*/
-ENTRY(__inval_cache_range)
+__dma_inv_area:
+ add x1, x1, x0
/* FALLTHROUGH */
/*
- * __dma_inv_range(start, end)
- * - start - virtual start address of region
- * - end - virtual end address of region
+ * __inval_cache_range(start, end)
+ * - start - start address of region
+ * - end - end address of region
*/
-__dma_inv_range:
+ENTRY(__inval_cache_range)
dcache_line_size x2, x3
sub x3, x2, #1
tst x1, x3 // end cache line aligned?
@@ -136,46 +137,43 @@ __dma_inv_range:
dsb sy
ret
ENDPIPROC(__inval_cache_range)
-ENDPROC(__dma_inv_range)
+ENDPROC(__dma_inv_area)
+
+/*
+ * __clean_dcache_area_poc(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are cleaned to the PoC.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
+ */
+ENTRY(__clean_dcache_area_poc)
+ /* FALLTHROUGH */
/*
- * __dma_clean_range(start, end)
+ * __dma_clean_area(start, size)
* - start - virtual start address of region
- * - end - virtual end address of region
+ * - size - size in question
*/
-__dma_clean_range:
- dcache_line_size x2, x3
- sub x3, x2, #1
- bic x0, x0, x3
-1:
-alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
- dc cvac, x0
-alternative_else
- dc civac, x0
-alternative_endif
- add x0, x0, x2
- cmp x0, x1
- b.lo 1b
- dsb sy
+__dma_clean_area:
+ dcache_by_line_op cvac, sy, x0, x1, x2, x3
ret
-ENDPROC(__dma_clean_range)
+ENDPIPROC(__clean_dcache_area_poc)
+ENDPROC(__dma_clean_area)
/*
- * __dma_flush_range(start, end)
+ * __dma_flush_area(start, size)
+ *
+ * clean & invalidate D / U line
+ *
* - start - virtual start address of region
- * - end - virtual end address of region
+ * - size - size in question
*/
-ENTRY(__dma_flush_range)
- dcache_line_size x2, x3
- sub x3, x2, #1
- bic x0, x0, x3
-1: dc civac, x0 // clean & invalidate D / U line
- add x0, x0, x2
- cmp x0, x1
- b.lo 1b
- dsb sy
+ENTRY(__dma_flush_area)
+ dcache_by_line_op civac, sy, x0, x1, x2, x3
ret
-ENDPIPROC(__dma_flush_range)
+ENDPIPROC(__dma_flush_area)
/*
* __dma_map_area(start, size, dir)
@@ -184,10 +182,9 @@ ENDPIPROC(__dma_flush_range)
* - dir - DMA direction
*/
ENTRY(__dma_map_area)
- add x1, x1, x0
cmp w2, #DMA_FROM_DEVICE
- b.eq __dma_inv_range
- b __dma_clean_range
+ b.eq __dma_inv_area
+ b __dma_clean_area
ENDPIPROC(__dma_map_area)
/*
@@ -197,8 +194,7 @@ ENDPIPROC(__dma_map_area)
* - dir - DMA direction
*/
ENTRY(__dma_unmap_area)
- add x1, x1, x0
cmp w2, #DMA_TO_DEVICE
- b.ne __dma_inv_range
+ b.ne __dma_inv_area
ret
ENDPIPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index c4284c432ae8..bdacead5b802 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -20,6 +20,7 @@
#include <linux/gfp.h>
#include <linux/acpi.h>
#include <linux/bootmem.h>
+#include <linux/cache.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/genalloc.h>
@@ -30,7 +31,7 @@
#include <asm/cacheflush.h>
-static int swiotlb __read_mostly;
+static int swiotlb __ro_after_init;
static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
bool coherent)
@@ -168,7 +169,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
return ptr;
/* remove any dirty cache lines on the kernel alias */
- __dma_flush_range(ptr, ptr + size);
+ __dma_flush_area(ptr, size);
/* create a coherent mapping */
page = virt_to_page(ptr);
@@ -387,7 +388,7 @@ static int __init atomic_pool_init(void)
void *page_addr = page_address(page);
memset(page_addr, 0, atomic_pool_size);
- __dma_flush_range(page_addr, page_addr + atomic_pool_size);
+ __dma_flush_area(page_addr, atomic_pool_size);
atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
if (!atomic_pool)
@@ -548,7 +549,7 @@ fs_initcall(dma_debug_do_init);
/* Thankfully, all cache ops are by VA so we can ignore phys here */
static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
{
- __dma_flush_range(virt, virt + PAGE_SIZE);
+ __dma_flush_area(virt, PAGE_SIZE);
}
static void *__iommu_alloc_attrs(struct device *dev, size_t size,
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
index 81acd4706878..c9f118cd812b 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -2,7 +2,7 @@
* Based on arch/arm/mm/extable.c
*/
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/uaccess.h>
int fixup_exception(struct pt_regs *regs)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 05d2bd776c69..53d9159662fe 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -18,7 +18,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
@@ -251,8 +251,7 @@ static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
good_area:
/*
* Check that the permissions on the VMA allow for the fault which
- * occurred. If we encountered a write or exec fault, we must have
- * appropriate permissions, otherwise we allow any permission.
+ * occurred.
*/
if (!(vma->vm_flags & vm_flags)) {
fault = VM_FAULT_BADACCESS;
@@ -288,7 +287,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
+ unsigned long vm_flags = VM_READ | VM_WRITE;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (notify_page_fault(regs, esr))
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 43a76b07eb32..8377329d8c97 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -25,8 +25,6 @@
#include <asm/cachetype.h>
#include <asm/tlbflush.h>
-#include "mm.h"
-
void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index bbb7ee76e319..21c489bdeb4e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -23,6 +23,7 @@
#include <linux/swap.h>
#include <linux/init.h>
#include <linux/bootmem.h>
+#include <linux/cache.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>
@@ -34,6 +35,7 @@
#include <linux/dma-contiguous.h>
#include <linux/efi.h>
#include <linux/swiotlb.h>
+#include <linux/vmalloc.h>
#include <asm/boot.h>
#include <asm/fixmap.h>
@@ -47,16 +49,14 @@
#include <asm/tlb.h>
#include <asm/alternative.h>
-#include "mm.h"
-
/*
* We need to be able to catch inadvertent references to memstart_addr
* that occur (potentially in generic code) before arm64_memblock_init()
* executes, which assigns it its actual value. So use a default value
* that cannot be mistaken for a real physical address.
*/
-s64 memstart_addr __read_mostly = -1;
-phys_addr_t arm64_dma_phys_limit __read_mostly;
+s64 memstart_addr __ro_after_init = -1;
+phys_addr_t arm64_dma_phys_limit __ro_after_init;
#ifdef CONFIG_BLK_DEV_INITRD
static int __init early_initrd(char *p)
@@ -485,7 +485,12 @@ void free_initmem(void)
{
free_reserved_area(__va(__pa(__init_begin)), __va(__pa(__init_end)),
0, "unused kernel");
- fixup_init();
+ /*
+ * Unmap the __init region but leave the VM area in place. This
+ * prevents the region from being reused for kernel modules, which
+ * is not supported by kallsyms.
+ */
+ unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
}
#ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/arm64/mm/mm.h b/arch/arm64/mm/mm.h
deleted file mode 100644
index 71fe98985455..000000000000
--- a/arch/arm64/mm/mm.h
+++ /dev/null
@@ -1,2 +0,0 @@
-
-void fixup_init(void);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 4989948d1feb..05615a3fdc6f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/cache.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/errno.h>
@@ -42,11 +43,9 @@
#include <asm/memblock.h>
#include <asm/mmu_context.h>
-#include "mm.h"
-
u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
-u64 kimage_voffset __read_mostly;
+u64 kimage_voffset __ro_after_init;
EXPORT_SYMBOL(kimage_voffset);
/*
@@ -399,16 +398,6 @@ void mark_rodata_ro(void)
section_size, PAGE_KERNEL_RO);
}
-void fixup_init(void)
-{
- /*
- * Unmap the __init region but leave the VM area in place. This
- * prevents the region from being reused for kernel modules, which
- * is not supported by kallsyms.
- */
- unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
-}
-
static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
pgprot_t prot, struct vm_struct *vma)
{
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 5bb15eab6f00..778a985c8a70 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -17,6 +17,8 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#define pr_fmt(fmt) "NUMA: " fmt
+
#include <linux/acpi.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
@@ -24,6 +26,7 @@
#include <linux/of.h>
#include <asm/acpi.h>
+#include <asm/sections.h>
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
@@ -38,10 +41,9 @@ static __init int numa_parse_early_param(char *opt)
{
if (!opt)
return -EINVAL;
- if (!strncmp(opt, "off", 3)) {
- pr_info("%s\n", "NUMA turned off");
+ if (!strncmp(opt, "off", 3))
numa_off = true;
- }
+
return 0;
}
early_param("numa", numa_parse_early_param);
@@ -93,7 +95,6 @@ void numa_clear_node(unsigned int cpu)
*/
static void __init setup_node_to_cpumask_map(void)
{
- unsigned int cpu;
int node;
/* setup nr_node_ids if not done yet */
@@ -106,11 +107,8 @@ static void __init setup_node_to_cpumask_map(void)
cpumask_clear(node_to_cpumask_map[node]);
}
- for_each_possible_cpu(cpu)
- set_cpu_numa_node(cpu, NUMA_NO_NODE);
-
/* cpumask_of_node() will now work */
- pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids);
+ pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
}
/*
@@ -118,18 +116,77 @@ static void __init setup_node_to_cpumask_map(void)
*/
void numa_store_cpu_info(unsigned int cpu)
{
- map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
+ map_cpu_to_node(cpu, cpu_to_node_map[cpu]);
}
void __init early_map_cpu_to_node(unsigned int cpu, int nid)
{
/* fallback to node 0 */
- if (nid < 0 || nid >= MAX_NUMNODES)
+ if (nid < 0 || nid >= MAX_NUMNODES || numa_off)
nid = 0;
cpu_to_node_map[cpu] = nid;
+
+ /*
+ * We should set the numa node of cpu0 as soon as possible, because it
+ * has already been set up online before. cpu_to_node(0) will soon be
+ * called.
+ */
+ if (!cpu)
+ set_cpu_numa_node(cpu, nid);
+}
+
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static int __init early_cpu_to_node(int cpu)
+{
+ return cpu_to_node_map[cpu];
+}
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+ return node_distance(from, to);
}
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
+ size_t align)
+{
+ int nid = early_cpu_to_node(cpu);
+
+ return memblock_virt_alloc_try_nid(size, align,
+ __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+ memblock_free_early(__pa(ptr), size);
+}
+
+void __init setup_per_cpu_areas(void)
+{
+ unsigned long delta;
+ unsigned int cpu;
+ int rc;
+
+ /*
+ * Always reserve area for module percpu variables. That's
+ * what the legacy allocator did.
+ */
+ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+ PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+ pcpu_cpu_distance,
+ pcpu_fc_alloc, pcpu_fc_free);
+ if (rc < 0)
+ panic("Failed to initialize percpu areas.");
+
+ delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+ for_each_possible_cpu(cpu)
+ __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+}
+#endif
+
/**
* numa_add_memblk - Set node id to memblk
* @nid: NUMA node ID of the new memblk
@@ -145,13 +202,13 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
if (ret < 0) {
- pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
+ pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n",
start, (end - 1), nid);
return ret;
}
node_set(nid, numa_nodes_parsed);
- pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
+ pr_info("Adding memblock [0x%llx - 0x%llx] on node %d\n",
start, (end - 1), nid);
return ret;
}
@@ -166,19 +223,18 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
void *nd;
int tnid;
- pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
- nid, start_pfn << PAGE_SHIFT,
- (end_pfn << PAGE_SHIFT) - 1);
+ pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+ nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
nd = __va(nd_pa);
/* report and initialize */
- pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n",
+ pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n",
nd_pa, nd_pa + nd_size - 1);
tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
if (tnid != nid)
- pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid);
+ pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
node_data[nid] = nd;
memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
@@ -235,8 +291,7 @@ static int __init numa_alloc_distance(void)
numa_distance[i * numa_distance_cnt + j] = i == j ?
LOCAL_DISTANCE : REMOTE_DISTANCE;
- pr_debug("NUMA: Initialized distance table, cnt=%d\n",
- numa_distance_cnt);
+ pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt);
return 0;
}
@@ -257,20 +312,20 @@ static int __init numa_alloc_distance(void)
void __init numa_set_distance(int from, int to, int distance)
{
if (!numa_distance) {
- pr_warn_once("NUMA: Warning: distance table not allocated yet\n");
+ pr_warn_once("Warning: distance table not allocated yet\n");
return;
}
if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
from < 0 || to < 0) {
- pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+ pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
if ((u8)distance != distance ||
(from == to && distance != LOCAL_DISTANCE)) {
- pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+ pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
@@ -297,7 +352,7 @@ static int __init numa_register_nodes(void)
/* Check that valid nid is set to memblks */
for_each_memblock(memory, mblk)
if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) {
- pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+ pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
mblk->nid, mblk->base,
mblk->base + mblk->size - 1);
return -EINVAL;
@@ -335,8 +390,10 @@ static int __init numa_init(int (*init_func)(void))
if (ret < 0)
return ret;
- if (nodes_empty(numa_nodes_parsed))
+ if (nodes_empty(numa_nodes_parsed)) {
+ pr_info("No NUMA configuration found\n");
return -EINVAL;
+ }
ret = numa_register_nodes();
if (ret < 0)
@@ -344,10 +401,6 @@ static int __init numa_init(int (*init_func)(void))
setup_node_to_cpumask_map();
- /* init boot processor */
- cpu_to_node_map[0] = 0;
- map_cpu_to_node(0, 0);
-
return 0;
}
@@ -367,10 +420,8 @@ static int __init dummy_numa_init(void)
if (numa_off)
pr_info("NUMA disabled\n"); /* Forced off on command line. */
- else
- pr_info("No NUMA configuration found\n");
- pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
- 0LLU, PFN_PHYS(max_pfn) - 1);
+ pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
+ 0LLU, PFN_PHYS(max_pfn) - 1);
for_each_memblock(memory, mblk) {
ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index ca6d268e3313..8def55e7249b 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -139,4 +139,43 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
__pgprot(0),
__pgprot(PTE_VALID));
}
-#endif
+#ifdef CONFIG_HIBERNATION
+/*
+ * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
+ * is used to determine if a linear map page has been marked as not-valid by
+ * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit.
+ * This is based on kern_addr_valid(), which almost does what we need.
+ *
+ * Because this is only called on the kernel linear map, p?d_sect() implies
+ * p?d_present(). When debug_pagealloc is enabled, sections mappings are
+ * disabled.
+ */
+bool kernel_page_present(struct page *page)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ unsigned long addr = (unsigned long)page_address(page);
+
+ pgd = pgd_offset_k(addr);
+ if (pgd_none(*pgd))
+ return false;
+
+ pud = pud_offset(pgd, addr);
+ if (pud_none(*pud))
+ return false;
+ if (pud_sect(*pud))
+ return true;
+
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ return false;
+ if (pmd_sect(*pmd))
+ return true;
+
+ pte = pte_offset_kernel(pmd, addr);
+ return pte_valid(*pte);
+}
+#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index ae11d4e03d0e..371c5f03a170 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -26,8 +26,6 @@
#include <asm/page.h>
#include <asm/tlbflush.h>
-#include "mm.h"
-
static struct kmem_cache *pgd_cache;
pgd_t *pgd_alloc(struct mm_struct *mm)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 9d37e967fa19..352c73b6a59e 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -83,6 +83,7 @@ ENDPROC(cpu_do_suspend)
*
* x0: Address of context pointer
*/
+ .pushsection ".idmap.text", "ax"
ENTRY(cpu_do_resume)
ldp x2, x3, [x0]
ldp x4, x5, [x0, #16]
@@ -120,6 +121,7 @@ ENTRY(cpu_do_resume)
isb
ret
ENDPROC(cpu_do_resume)
+ .popsection
#endif
/*
@@ -134,17 +136,12 @@ ENTRY(cpu_do_switch_mm)
bfi x0, x1, #48, #16 // set the ASID
msr ttbr0_el1, x0 // set TTBR0
isb
-alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
- ret
- nop
- nop
- nop
-alternative_else
+alternative_if ARM64_WORKAROUND_CAVIUM_27456
ic iallu
dsb nsh
isb
+alternative_else_nop_endif
ret
-alternative_endif
ENDPROC(cpu_do_switch_mm)
.pushsection ".idmap.text", "ax"
@@ -181,6 +178,7 @@ ENDPROC(idmap_cpu_replace_ttbr1)
* Initialise the processor for turning the MMU on. Return in x0 the
* value of the SCTLR_EL1 register.
*/
+ .pushsection ".idmap.text", "ax"
ENTRY(__cpu_setup)
tlbi vmalle1 // Invalidate local TLB
dsb nsh
@@ -266,3 +264,4 @@ ENDPROC(__cpu_setup)
crval:
.word 0xfcffffff // clear
.word 0x34d5d91d // set
+ .popsection
diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h
index 68cf638faf48..b1ec1fa06463 100644
--- a/arch/avr32/include/asm/uaccess.h
+++ b/arch/avr32/include/asm/uaccess.h
@@ -74,7 +74,7 @@ extern __kernel_size_t __copy_user(void *to, const void *from,
extern __kernel_size_t copy_to_user(void __user *to, const void *from,
__kernel_size_t n);
-extern __kernel_size_t copy_from_user(void *to, const void __user *from,
+extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
__kernel_size_t n);
static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
@@ -88,6 +88,15 @@ static inline __kernel_size_t __copy_from_user(void *to,
{
return __copy_user(to, (const void __force *)from, n);
}
+static inline __kernel_size_t copy_from_user(void *to,
+ const void __user *from,
+ __kernel_size_t n)
+{
+ size_t res = ___copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
+}
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
diff --git a/arch/avr32/kernel/avr32_ksyms.c b/arch/avr32/kernel/avr32_ksyms.c
index d93ead02daed..7c6cf14f0985 100644
--- a/arch/avr32/kernel/avr32_ksyms.c
+++ b/arch/avr32/kernel/avr32_ksyms.c
@@ -36,7 +36,7 @@ EXPORT_SYMBOL(copy_page);
/*
* Userspace access stuff.
*/
-EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(___copy_from_user);
EXPORT_SYMBOL(copy_to_user);
EXPORT_SYMBOL(__copy_user);
EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/avr32/lib/copy_user.S b/arch/avr32/lib/copy_user.S
index ea59c04b07de..075373471da1 100644
--- a/arch/avr32/lib/copy_user.S
+++ b/arch/avr32/lib/copy_user.S
@@ -23,13 +23,13 @@
*/
.text
.align 1
- .global copy_from_user
- .type copy_from_user, @function
-copy_from_user:
+ .global ___copy_from_user
+ .type ___copy_from_user, @function
+___copy_from_user:
branch_if_kernel r8, __copy_user
ret_if_privileged r8, r11, r10, r10
rjmp __copy_user
- .size copy_from_user, . - copy_from_user
+ .size ___copy_from_user, . - ___copy_from_user
.global copy_to_user
.type copy_to_user, @function
diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h
index 12f5d6851bbc..0a2a70096d8b 100644
--- a/arch/blackfin/include/asm/uaccess.h
+++ b/arch/blackfin/include/asm/uaccess.h
@@ -171,11 +171,12 @@ static inline int bad_user_access_length(void)
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n))) {
memcpy(to, (const void __force *)from, n);
- else
- return n;
- return 0;
+ return 0;
+ }
+ memset(to, 0, n);
+ return n;
}
static inline unsigned long __must_check
diff --git a/arch/blackfin/kernel/ftrace-entry.S b/arch/blackfin/kernel/ftrace-entry.S
index 28d059540424..3b8bdcbb7da3 100644
--- a/arch/blackfin/kernel/ftrace-entry.S
+++ b/arch/blackfin/kernel/ftrace-entry.S
@@ -169,7 +169,7 @@ ENTRY(_ftrace_graph_caller)
r0 = sp; /* unsigned long *parent */
r1 = [sp]; /* unsigned long self_addr */
# endif
-# ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+# ifdef HAVE_FUNCTION_GRAPH_FP_TEST
r2 = fp; /* unsigned long frame_pointer */
# endif
r0 += 16; /* skip the 4 local regs on stack */
@@ -190,7 +190,7 @@ ENTRY(_return_to_handler)
[--sp] = r1;
/* get original return address */
-# ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+# ifdef HAVE_FUNCTION_GRAPH_FP_TEST
r0 = fp; /* Blackfin is sane, so omit this */
# endif
call _ftrace_return_to_handler;
diff --git a/arch/blackfin/kernel/ftrace.c b/arch/blackfin/kernel/ftrace.c
index 095de0fa044d..8dad7589b843 100644
--- a/arch/blackfin/kernel/ftrace.c
+++ b/arch/blackfin/kernel/ftrace.c
@@ -107,7 +107,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
return;
if (ftrace_push_return_trace(*parent, self_addr, &trace.depth,
- frame_pointer) == -EBUSY)
+ frame_pointer, NULL) == -EBUSY)
return;
trace.func = self_addr;
diff --git a/arch/blackfin/mach-bf561/coreb.c b/arch/blackfin/mach-bf561/coreb.c
index 78ecb50bafc8..8a2543c654b3 100644
--- a/arch/blackfin/mach-bf561/coreb.c
+++ b/arch/blackfin/mach-bf561/coreb.c
@@ -59,18 +59,7 @@ static struct miscdevice coreb_dev = {
.name = "coreb",
.fops = &coreb_fops,
};
-
-static int __init bf561_coreb_init(void)
-{
- return misc_register(&coreb_dev);
-}
-module_init(bf561_coreb_init);
-
-static void __exit bf561_coreb_exit(void)
-{
- misc_deregister(&coreb_dev);
-}
-module_exit(bf561_coreb_exit);
+module_misc_device(coreb_dev);
MODULE_AUTHOR("Bas Vermeulen <bvermeul@blackstar.xs4all.nl>");
MODULE_DESCRIPTION("BF561 Core B Support");
diff --git a/arch/cris/include/asm/uaccess.h b/arch/cris/include/asm/uaccess.h
index e3530d0f13ee..56c7d5750abd 100644
--- a/arch/cris/include/asm/uaccess.h
+++ b/arch/cris/include/asm/uaccess.h
@@ -194,30 +194,6 @@ extern unsigned long __copy_user(void __user *to, const void *from, unsigned lon
extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
extern unsigned long __do_clear_user(void __user *to, unsigned long n);
-static inline unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_user(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n))
- return __copy_user_zeroing(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_clear_user(void __user *to, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __do_clear_user(to, n);
- return n;
-}
-
static inline long
__strncpy_from_user(char *dst, const char __user *src, long count)
{
@@ -282,7 +258,7 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n)
else if (n == 24)
__asm_copy_from_user_24(to, from, ret);
else
- ret = __generic_copy_from_user(to, from, n);
+ ret = __copy_user_zeroing(to, from, n);
return ret;
}
@@ -333,7 +309,7 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n)
else if (n == 24)
__asm_copy_to_user_24(to, from, ret);
else
- ret = __generic_copy_to_user(to, from, n);
+ ret = __copy_user(to, from, n);
return ret;
}
@@ -366,26 +342,43 @@ __constant_clear_user(void __user *to, unsigned long n)
else if (n == 24)
__asm_clear_24(to, ret);
else
- ret = __generic_clear_user(to, n);
+ ret = __do_clear_user(to, n);
return ret;
}
-#define clear_user(to, n) \
- (__builtin_constant_p(n) ? \
- __constant_clear_user(to, n) : \
- __generic_clear_user(to, n))
+static inline size_t clear_user(void __user *to, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+ return n;
+ if (__builtin_constant_p(n))
+ return __constant_clear_user(to, n);
+ else
+ return __do_clear_user(to, n);
+}
-#define copy_from_user(to, from, n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_from_user(to, from, n) : \
- __generic_copy_from_user(to, from, n))
+static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_READ, from, n))) {
+ memset(to, 0, n);
+ return n;
+ }
+ if (__builtin_constant_p(n))
+ return __constant_copy_from_user(to, from, n);
+ else
+ return __copy_user_zeroing(to, from, n);
+}
-#define copy_to_user(to, from, n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_to_user(to, from, n) : \
- __generic_copy_to_user(to, from, n))
+static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+ return n;
+ if (__builtin_constant_p(n))
+ return __constant_copy_to_user(to, from, n);
+ else
+ return __copy_user(to, from, n);
+}
/* We let the __ versions of copy_from/to_user inline, because they're often
* used in fast paths and have only a small space overhead.
diff --git a/arch/frv/include/asm/uaccess.h b/arch/frv/include/asm/uaccess.h
index 3ac9a59d65d4..87d9e34c5df8 100644
--- a/arch/frv/include/asm/uaccess.h
+++ b/arch/frv/include/asm/uaccess.h
@@ -263,19 +263,25 @@ do { \
extern long __memset_user(void *dst, unsigned long count);
extern long __memcpy_user(void *dst, const void *src, unsigned long count);
-#define clear_user(dst,count) __memset_user(____force(dst), (count))
+#define __clear_user(dst,count) __memset_user(____force(dst), (count))
#define __copy_from_user_inatomic(to, from, n) __memcpy_user((to), ____force(from), (n))
#define __copy_to_user_inatomic(to, from, n) __memcpy_user(____force(to), (from), (n))
#else
-#define clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
+#define __clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
#define __copy_from_user_inatomic(to, from, n) (memcpy((to), ____force(from), (n)), 0)
#define __copy_to_user_inatomic(to, from, n) (memcpy(____force(to), (from), (n)), 0)
#endif
-#define __clear_user clear_user
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
+{
+ if (likely(__access_ok(to, n)))
+ n = __clear_user(to, n);
+ return n;
+}
static inline unsigned long __must_check
__copy_to_user(void __user *to, const void *from, unsigned long n)
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index f000a382bc7f..f61cfb28e9f2 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -103,7 +103,8 @@ static inline long hexagon_strncpy_from_user(char *dst, const char __user *src,
{
long res = __strnlen_user(src, n);
- /* return from strnlen can't be zero -- that would be rubbish. */
+ if (unlikely(!res))
+ return -EFAULT;
if (res > n) {
copy_from_user(dst, src, n);
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index 29bd59790d6c..c7026429816b 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -56,7 +56,7 @@ struct thread_info {
#define alloc_thread_stack_node(tsk, node) ((unsigned long *) 0)
#define task_thread_info(tsk) ((struct thread_info *) 0)
#endif
-#define free_thread_stack(ti) /* nothing */
+#define free_thread_stack(tsk) /* nothing */
#define task_stack_page(tsk) ((void *)(tsk))
#define __HAVE_THREAD_FUNCTIONS
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 465c70982f40..bfe13196f770 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -241,8 +241,7 @@ extern unsigned long __must_check __copy_user (void __user *to, const void __use
static inline unsigned long
__copy_to_user (void __user *to, const void *from, unsigned long count)
{
- if (!__builtin_constant_p(count))
- check_object_size(from, count, true);
+ check_object_size(from, count, true);
return __copy_user(to, (__force void __user *) from, count);
}
@@ -250,8 +249,7 @@ __copy_to_user (void __user *to, const void *from, unsigned long count)
static inline unsigned long
__copy_from_user (void *to, const void __user *from, unsigned long count)
{
- if (!__builtin_constant_p(count))
- check_object_size(to, count, false);
+ check_object_size(to, count, false);
return __copy_user((__force void __user *) to, from, count);
}
@@ -265,27 +263,22 @@ __copy_from_user (void *to, const void __user *from, unsigned long count)
long __cu_len = (n); \
\
if (__access_ok(__cu_to, __cu_len, get_fs())) { \
- if (!__builtin_constant_p(n)) \
- check_object_size(__cu_from, __cu_len, true); \
+ check_object_size(__cu_from, __cu_len, true); \
__cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \
} \
__cu_len; \
})
-#define copy_from_user(to, from, n) \
-({ \
- void *__cu_to = (to); \
- const void __user *__cu_from = (from); \
- long __cu_len = (n); \
- \
- __chk_user_ptr(__cu_from); \
- if (__access_ok(__cu_from, __cu_len, get_fs())) { \
- if (!__builtin_constant_p(n)) \
- check_object_size(__cu_to, __cu_len, false); \
- __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \
- } \
- __cu_len; \
-})
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ check_object_size(to, n, false);
+ if (likely(__access_ok(from, n, get_fs())))
+ n = __copy_user((__force void __user *) to, from, n);
+ else
+ memset(to, 0, n);
+ return n;
+}
#define __copy_in_user(to, from, size) __copy_user((to), (from), (size))
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 92b7bc956795..9273e034b730 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -796,7 +796,7 @@ int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi)
* ACPI based hotplug CPU support
*/
#ifdef CONFIG_ACPI_HOTPLUG_CPU
-static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
{
#ifdef CONFIG_ACPI_NUMA
/*
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index eb9220cde76c..9509cc73b9c6 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -986,7 +986,7 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
int cpu = smp_processor_id();
previous_current = curr_task(cpu);
- set_curr_task(cpu, current);
+ ia64_set_curr_task(cpu, current);
if ((p = strchr(current->comm, ' ')))
*p = '\0';
@@ -1360,14 +1360,14 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
cpumask_clear_cpu(i, &mca_cpu); /* wake next cpu */
while (monarch_cpu != -1)
cpu_relax(); /* spin until last cpu leaves */
- set_curr_task(cpu, previous_current);
+ ia64_set_curr_task(cpu, previous_current);
ia64_mc_info.imi_rendez_checkin[cpu]
= IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
return;
}
}
}
- set_curr_task(cpu, previous_current);
+ ia64_set_curr_task(cpu, previous_current);
ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
monarch_cpu = -1; /* This frees the slaves and previous monarchs */
}
@@ -1729,7 +1729,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
NOTIFY_INIT(DIE_INIT_SLAVE_LEAVE, regs, (long)&nd, 1);
mprintk("Slave on cpu %d returning to normal service.\n", cpu);
- set_curr_task(cpu, previous_current);
+ ia64_set_curr_task(cpu, previous_current);
ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
atomic_dec(&slaves);
return;
@@ -1756,7 +1756,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
mprintk("\nINIT dump complete. Monarch on cpu %d returning to normal service.\n", cpu);
atomic_dec(&monarchs);
- set_curr_task(cpu, previous_current);
+ ia64_set_curr_task(cpu, previous_current);
monarch_cpu = -1;
return;
}
@@ -1890,7 +1890,7 @@ ia64_mca_cpu_init(void *cpu_data)
PAGE_KERNEL)));
}
-static void ia64_mca_cmc_vector_adjust(void *dummy)
+static int ia64_mca_cpu_online(unsigned int cpu)
{
unsigned long flags;
@@ -1898,25 +1898,9 @@ static void ia64_mca_cmc_vector_adjust(void *dummy)
if (!cmc_polling_enabled)
ia64_mca_cmc_vector_enable(NULL);
local_irq_restore(flags);
+ return 0;
}
-static int mca_cpu_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
-{
- switch (action) {
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- ia64_mca_cmc_vector_adjust(NULL);
- break;
- }
- return NOTIFY_OK;
-}
-
-static struct notifier_block mca_cpu_notifier = {
- .notifier_call = mca_cpu_callback
-};
-
/*
* ia64_mca_init
*
@@ -2111,15 +2095,13 @@ ia64_mca_late_init(void)
if (!mca_init)
return 0;
- register_hotcpu_notifier(&mca_cpu_notifier);
-
/* Setup the CMCI/P vector and handler */
setup_timer(&cmc_poll_timer, ia64_mca_cmc_poll, 0UL);
/* Unmask/enable the vector */
cmc_polling_enabled = 0;
- schedule_work(&cmc_enable_work);
-
+ cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "ia64/mca:online",
+ ia64_mca_cpu_online, NULL);
IA64_MCA_DEBUG("%s: CMCI/P setup and enabled.\n", __func__);
#ifdef CONFIG_ACPI
diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h
index cac7014daef3..6f8982157a75 100644
--- a/arch/m32r/include/asm/uaccess.h
+++ b/arch/m32r/include/asm/uaccess.h
@@ -219,7 +219,7 @@ extern int fixup_exception(struct pt_regs *regs);
#define __get_user_nocheck(x, ptr, size) \
({ \
long __gu_err = 0; \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
might_fault(); \
__get_user_size(__gu_val, (ptr), (size), __gu_err); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index ec9cc1fdd237..ddb8192a3661 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -396,7 +396,7 @@ void __init config_amiga(void)
mach_max_dma_address = 0xffffffff;
mach_reset = amiga_reset;
-#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE)
+#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP)
mach_beep = amiga_mksound;
#endif
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index cbd5991fd49a..97a3c38cd1f5 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -211,7 +211,7 @@ void __init config_atari(void)
arch_gettimeoffset = atari_gettimeoffset;
mach_reset = atari_reset;
mach_max_dma_address = 0xffffff;
-#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE)
+#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP)
mach_beep = atari_mksound;
#endif
#ifdef CONFIG_HEARTBEAT
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 8f5b6f7dd136..55be7e3ff109 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -566,6 +566,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -584,6 +586,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 31bded9c83d4..365dda66b0e6 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -525,6 +525,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -543,6 +545,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 0d7739e04ae2..ce3cbfd16fcd 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -546,6 +546,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -564,6 +566,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 2cbb5c465fec..8db496a9797d 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -517,6 +517,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -535,6 +537,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 96102a42c156..8314156f7149 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -527,6 +527,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -545,6 +547,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 97d88f7dc5a7..6600270b9622 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -549,6 +549,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -567,6 +569,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index be25ef208f0f..90abfe9eabba 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -629,6 +629,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -647,6 +649,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index a008344360c9..0d502c2f73d5 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -517,6 +517,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -535,6 +537,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 6735a25f36d4..5930e91fc710 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -517,6 +517,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -535,6 +537,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 780c6e9f6cf9..74e3ad82eca9 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -540,6 +540,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -558,6 +560,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 44693cf361e5..4ba8606a4e69 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -518,6 +518,8 @@ CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -536,6 +538,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index ef0071d61158..c6f49726a6c9 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -519,6 +519,8 @@ CONFIG_TEST_UDELAY=m
CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_CRYPTD=m
@@ -537,6 +539,7 @@ CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 5b8ec4d5f8e8..50633c38f1e2 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -105,7 +105,7 @@ EXPORT_SYMBOL(mach_heartbeat);
#ifdef CONFIG_M68K_L2_CACHE
void (*mach_l2_flush) (int);
#endif
-#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE)
+#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP)
void (*mach_beep)(unsigned int, unsigned int);
EXPORT_SYMBOL(mach_beep);
#endif
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 9202f82dfce6..58507edbdf1d 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -42,7 +42,7 @@
#include <linux/personality.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/tracehook.h>
#include <asm/setup.h>
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 2f33a33001e5..e46895316eb0 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -162,7 +162,7 @@ void __init config_mac(void)
mach_halt = mac_poweroff;
mach_power_off = mac_poweroff;
mach_max_dma_address = 0xffffffff;
-#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE)
+#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP)
mach_beep = mac_mksound;
#endif
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index fcb7f05b60b6..ea89a24f4600 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -180,7 +180,7 @@ void __init config_q40(void)
mach_reset = q40_reset;
mach_get_model = q40_get_model;
-#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE)
+#if IS_ENABLED(CONFIG_INPUT_M68K_BEEP)
mach_beep = q40_mksound;
#endif
#ifdef CONFIG_HEARTBEAT
diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h
index 8282cbce7e39..273e61225c27 100644
--- a/arch/metag/include/asm/uaccess.h
+++ b/arch/metag/include/asm/uaccess.h
@@ -204,8 +204,9 @@ extern unsigned long __must_check __copy_user_zeroing(void *to,
static inline unsigned long
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n)))
return __copy_user_zeroing(to, from, n);
+ memset(to, 0, n);
return n;
}
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 331b0d35f89c..826676778094 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -227,7 +227,7 @@ extern long __user_bad(void);
#define __get_user(x, ptr) \
({ \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
/*unsigned long __gu_ptr = (unsigned long)(ptr);*/ \
long __gu_err; \
switch (sizeof(*(ptr))) { \
@@ -373,10 +373,13 @@ extern long __user_bad(void);
static inline long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
+ unsigned long res = n;
might_fault();
- if (access_ok(VERIFY_READ, from, n))
- return __copy_from_user(to, from, n);
- return n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
#define __copy_to_user(to, from, n) \
diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c
index fc7b48a52cd5..d57563c58a26 100644
--- a/arch/microblaze/kernel/ftrace.c
+++ b/arch/microblaze/kernel/ftrace.c
@@ -63,7 +63,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
return;
}
- err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0);
+ err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL);
if (err == -EBUSY) {
*parent = old;
return;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 26388562e300..212ff92920d2 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -65,6 +65,7 @@ config MIPS
select ARCH_CLOCKSOURCE_DATA
select HANDLE_DOMAIN_IRQ
select HAVE_EXIT_THREAD
+ select HAVE_REGS_AND_STACK_ACCESS_API
menu "Machine selection"
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index f0e314ceb8ba..7f975b20b20c 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -113,42 +113,6 @@ config SPINLOCK_TEST
help
Add several files to the debugfs to test spinlock speed.
-if CPU_MIPSR6
-
-choice
- prompt "Compact branch policy"
- default MIPS_COMPACT_BRANCHES_OPTIMAL
-
-config MIPS_COMPACT_BRANCHES_NEVER
- bool "Never (force delay slot branches)"
- help
- Pass the -mcompact-branches=never flag to the compiler in order to
- force it to always emit branches with delay slots, and make no use
- of the compact branch instructions introduced by MIPSr6. This is
- useful if you suspect there may be an issue with compact branches in
- either the compiler or the CPU.
-
-config MIPS_COMPACT_BRANCHES_OPTIMAL
- bool "Optimal (use where beneficial)"
- help
- Pass the -mcompact-branches=optimal flag to the compiler in order for
- it to make use of compact branch instructions where it deems them
- beneficial, and use branches with delay slots elsewhere. This is the
- default compiler behaviour, and should be used unless you have a
- reason to choose otherwise.
-
-config MIPS_COMPACT_BRANCHES_ALWAYS
- bool "Always (force compact branches)"
- help
- Pass the -mcompact-branches=always flag to the compiler in order to
- force it to always emit compact branches, making no use of branch
- instructions with delay slots. This can result in more compact code
- which may be beneficial in some scenarios.
-
-endchoice
-
-endif # CPU_MIPSR6
-
config SCACHE_DEBUGFS
bool "L2 cache debugfs entries"
depends on DEBUG_FS
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index efd7a9dc93c4..598ab2930fce 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -203,10 +203,6 @@ endif
toolchain-virt := $(call cc-option-yn,$(mips-cflags) -mvirt)
cflags-$(toolchain-virt) += -DTOOLCHAIN_SUPPORTS_VIRT
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_NEVER) += -mcompact-branches=never
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_OPTIMAL) += -mcompact-branches=optimal
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_ALWAYS) += -mcompact-branches=always
-
#
# Firmware support
#
diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index 2e7378467c5c..cc3a1e33a600 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -96,7 +96,7 @@ static struct clk * __init ath79_reg_ffclk(const char *name,
struct clk *clk;
clk = clk_register_fixed_factor(NULL, name, parent_name, 0, mult, div);
- if (!clk)
+ if (IS_ERR(clk))
panic("failed to allocate %s clock structure", name);
return clk;
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 5a9b87b7993e..c1eb1ff7c800 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1619,6 +1619,12 @@ static int __init octeon_irq_init_gpio(
return -ENOMEM;
}
+ /*
+ * Clear the OF_POPULATED flag that was set by of_irq_init()
+ * so that all GPIO devices will be probed.
+ */
+ of_node_clear_flag(gpio_node, OF_POPULATED);
+
return 0;
}
/*
diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index b31fbc9d6eae..37a932d9148c 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -1059,7 +1059,7 @@ static int __init octeon_publish_devices(void)
{
return of_platform_bus_probe(NULL, octeon_ids, NULL);
}
-device_initcall(octeon_publish_devices);
+arch_initcall(octeon_publish_devices);
MODULE_AUTHOR("David Daney <ddaney@caviumnetworks.com>");
MODULE_LICENSE("GPL");
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 4d457d602d3b..256fe6f65cf2 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -380,29 +380,11 @@ static int octeon_update_boot_vector(unsigned int cpu)
return 0;
}
-static int octeon_cpu_callback(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
-{
- unsigned int cpu = (unsigned long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- octeon_update_boot_vector(cpu);
- break;
- case CPU_ONLINE:
- pr_info("Cpu %d online\n", cpu);
- break;
- case CPU_DEAD:
- break;
- }
-
- return NOTIFY_OK;
-}
-
static int register_cavium_notifier(void)
{
- hotcpu_notifier(octeon_cpu_callback, 0);
- return 0;
+ return cpuhp_setup_state_nocalls(CPUHP_MIPS_SOC_PREPARE,
+ "mips/cavium:prepare",
+ octeon_update_boot_vector, NULL);
}
late_initcall(register_cavium_notifier);
diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S
index d7b99180c6e1..1910223a9c02 100644
--- a/arch/mips/dec/int-handler.S
+++ b/arch/mips/dec/int-handler.S
@@ -146,7 +146,25 @@
/*
* Find irq with highest priority
*/
- PTR_LA t1,cpu_mask_nr_tbl
+ # open coded PTR_LA t1, cpu_mask_nr_tbl
+#if (_MIPS_SZPTR == 32)
+ # open coded la t1, cpu_mask_nr_tbl
+ lui t1, %hi(cpu_mask_nr_tbl)
+ addiu t1, %lo(cpu_mask_nr_tbl)
+
+#endif
+#if (_MIPS_SZPTR == 64)
+ # open coded dla t1, cpu_mask_nr_tbl
+ .set push
+ .set noat
+ lui t1, %highest(cpu_mask_nr_tbl)
+ lui AT, %hi(cpu_mask_nr_tbl)
+ daddiu t1, t1, %higher(cpu_mask_nr_tbl)
+ daddiu AT, AT, %lo(cpu_mask_nr_tbl)
+ dsll t1, 32
+ daddu t1, t1, AT
+ .set pop
+#endif
1: lw t2,(t1)
nop
and t2,t0
@@ -195,7 +213,25 @@
/*
* Find irq with highest priority
*/
- PTR_LA t1,asic_mask_nr_tbl
+ # open coded PTR_LA t1,asic_mask_nr_tbl
+#if (_MIPS_SZPTR == 32)
+ # open coded la t1, asic_mask_nr_tbl
+ lui t1, %hi(asic_mask_nr_tbl)
+ addiu t1, %lo(asic_mask_nr_tbl)
+
+#endif
+#if (_MIPS_SZPTR == 64)
+ # open coded dla t1, asic_mask_nr_tbl
+ .set push
+ .set noat
+ lui t1, %highest(asic_mask_nr_tbl)
+ lui AT, %hi(asic_mask_nr_tbl)
+ daddiu t1, t1, %higher(asic_mask_nr_tbl)
+ daddiu AT, AT, %lo(asic_mask_nr_tbl)
+ dsll t1, 32
+ daddu t1, t1, AT
+ .set pop
+#endif
2: lw t2,(t1)
nop
and t2,t0
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 56584a659183..83054f79f72a 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -157,6 +157,7 @@
ldc1 $f28, THREAD_FPR28(\thread)
ldc1 $f30, THREAD_FPR30(\thread)
ctc1 \tmp, fcr31
+ .set pop
.endm
.macro fpu_restore_16odd thread
diff --git a/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h b/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h
index 0cf5ac1f7245..8ff2cbdf2c3e 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h
@@ -15,8 +15,8 @@
static inline bool __should_swizzle_bits(volatile void *a)
{
extern const bool octeon_should_swizzle_table[];
+ u64 did = ((u64)(uintptr_t)a >> 40) & 0xff;
- unsigned long did = ((unsigned long)a >> 40) & 0xff;
return octeon_should_swizzle_table[did];
}
@@ -29,7 +29,7 @@ static inline bool __should_swizzle_bits(volatile void *a)
#define __should_swizzle_bits(a) false
-static inline bool __should_swizzle_addr(unsigned long p)
+static inline bool __should_swizzle_addr(u64 p)
{
/* boot bus? */
return ((p >> 40) & 0xff) == 0;
diff --git a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
index 2f82bfa3a773..c9f5769dfc8f 100644
--- a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
@@ -11,11 +11,13 @@
#define CP0_EBASE $15, 1
.macro kernel_entry_setup
+#ifdef CONFIG_SMP
mfc0 t0, CP0_EBASE
andi t0, t0, 0x3ff # CPUNum
beqz t0, 1f
# CPUs other than zero goto smp_bootstrap
j smp_bootstrap
+#endif /* CONFIG_SMP */
1:
.endm
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index 58e7874e9347..4fafeefe65c2 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -458,10 +458,21 @@ static inline int mips_cm_revision(void)
static inline unsigned int mips_cm_max_vp_width(void)
{
extern int smp_num_siblings;
+ uint32_t cfg;
if (mips_cm_revision() >= CM_REV_CM3)
return read_gcr_sys_config2() & CM_GCR_SYS_CONFIG2_MAXVPW_MSK;
+ if (mips_cm_present()) {
+ /*
+ * We presume that all cores in the system will have the same
+ * number of VP(E)s, and if that ever changes then this will
+ * need revisiting.
+ */
+ cfg = read_gcr_cl_config() & CM_GCR_Cx_CONFIG_PVPE_MSK;
+ return (cfg >> CM_GCR_Cx_CONFIG_PVPE_SHF) + 1;
+ }
+
if (IS_ENABLED(CONFIG_SMP))
return smp_num_siblings;
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index def9d8d13f6e..7dd2dd47909a 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -660,8 +660,6 @@
#define MIPS_CONF7_IAR (_ULCAST_(1) << 10)
#define MIPS_CONF7_AR (_ULCAST_(1) << 16)
-/* FTLB probability bits for R6 */
-#define MIPS_CONF7_FTLBP_SHIFT (18)
/* WatchLo* register definitions */
#define MIPS_WATCHLO_IRW (_ULCAST_(0x7) << 0)
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 11b965f98d95..21a2aaba20d5 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -14,6 +14,7 @@
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/thread_info.h>
+#include <linux/string.h>
#include <asm/asm-eva.h>
/*
@@ -1170,6 +1171,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
__cu_len = __invoke_copy_from_user(__cu_to, \
__cu_from, \
__cu_len); \
+ } else { \
+ memset(__cu_to, 0, __cu_len); \
} \
} \
__cu_len; \
diff --git a/arch/mips/include/asm/uprobes.h b/arch/mips/include/asm/uprobes.h
index 34c325c674c4..70a4a2f173ff 100644
--- a/arch/mips/include/asm/uprobes.h
+++ b/arch/mips/include/asm/uprobes.h
@@ -36,7 +36,6 @@ struct arch_uprobe {
unsigned long resume_epc;
u32 insn[2];
u32 ixol[2];
- union mips_instruction orig_inst[MAX_UINSN_BYTES / 4];
};
struct arch_uprobe_task {
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index a88d44247cc8..dd3175442c9e 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -352,7 +352,12 @@ __setup("nohtw", htw_disable);
static int mips_ftlb_disabled;
static int mips_has_ftlb_configured;
-static int set_ftlb_enable(struct cpuinfo_mips *c, int enable);
+enum ftlb_flags {
+ FTLB_EN = 1 << 0,
+ FTLB_SET_PROB = 1 << 1,
+};
+
+static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags);
static int __init ftlb_disable(char *s)
{
@@ -371,8 +376,6 @@ static int __init ftlb_disable(char *s)
return 1;
}
- back_to_back_c0_hazard();
-
config4 = read_c0_config4();
/* Check that FTLB has been disabled */
@@ -531,7 +534,7 @@ static unsigned int calculate_ftlb_probability(struct cpuinfo_mips *c)
return 3;
}
-static int set_ftlb_enable(struct cpuinfo_mips *c, int enable)
+static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags)
{
unsigned int config;
@@ -542,33 +545,33 @@ static int set_ftlb_enable(struct cpuinfo_mips *c, int enable)
case CPU_P6600:
/* proAptiv & related cores use Config6 to enable the FTLB */
config = read_c0_config6();
- /* Clear the old probability value */
- config &= ~(3 << MIPS_CONF6_FTLBP_SHIFT);
- if (enable)
- /* Enable FTLB */
- write_c0_config6(config |
- (calculate_ftlb_probability(c)
- << MIPS_CONF6_FTLBP_SHIFT)
- | MIPS_CONF6_FTLBEN);
+
+ if (flags & FTLB_EN)
+ config |= MIPS_CONF6_FTLBEN;
else
- /* Disable FTLB */
- write_c0_config6(config & ~MIPS_CONF6_FTLBEN);
+ config &= ~MIPS_CONF6_FTLBEN;
+
+ if (flags & FTLB_SET_PROB) {
+ config &= ~(3 << MIPS_CONF6_FTLBP_SHIFT);
+ config |= calculate_ftlb_probability(c)
+ << MIPS_CONF6_FTLBP_SHIFT;
+ }
+
+ write_c0_config6(config);
+ back_to_back_c0_hazard();
break;
case CPU_I6400:
- /* I6400 & related cores use Config7 to configure FTLB */
- config = read_c0_config7();
- /* Clear the old probability value */
- config &= ~(3 << MIPS_CONF7_FTLBP_SHIFT);
- write_c0_config7(config | (calculate_ftlb_probability(c)
- << MIPS_CONF7_FTLBP_SHIFT));
- break;
+ /* There's no way to disable the FTLB */
+ if (!(flags & FTLB_EN))
+ return 1;
+ return 0;
case CPU_LOONGSON3:
/* Flush ITLB, DTLB, VTLB and FTLB */
write_c0_diag(LOONGSON_DIAG_ITLB | LOONGSON_DIAG_DTLB |
LOONGSON_DIAG_VTLB | LOONGSON_DIAG_FTLB);
/* Loongson-3 cores use Config6 to enable the FTLB */
config = read_c0_config6();
- if (enable)
+ if (flags & FTLB_EN)
/* Enable FTLB */
write_c0_config6(config & ~MIPS_CONF6_FTLBDIS);
else
@@ -788,6 +791,7 @@ static inline unsigned int decode_config4(struct cpuinfo_mips *c)
PAGE_SIZE, config4);
/* Switch FTLB off */
set_ftlb_enable(c, 0);
+ mips_ftlb_disabled = 1;
break;
}
c->tlbsizeftlbsets = 1 <<
@@ -852,7 +856,7 @@ static void decode_configs(struct cpuinfo_mips *c)
c->scache.flags = MIPS_CACHE_NOT_PRESENT;
/* Enable FTLB if present and not disabled */
- set_ftlb_enable(c, !mips_ftlb_disabled);
+ set_ftlb_enable(c, mips_ftlb_disabled ? 0 : FTLB_EN);
ok = decode_config0(c); /* Read Config registers. */
BUG_ON(!ok); /* Arch spec violation! */
@@ -902,6 +906,9 @@ static void decode_configs(struct cpuinfo_mips *c)
}
}
+ /* configure the FTLB write probability */
+ set_ftlb_enable(c, (mips_ftlb_disabled ? 0 : FTLB_EN) | FTLB_SET_PROB);
+
mips_probe_watch_registers(c);
#ifndef CONFIG_MIPS_CPS
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 937c54bc8ccc..30a3b75e88eb 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -382,8 +382,8 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra,
if (unlikely(faulted))
goto out;
- if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp)
- == -EBUSY) {
+ if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp,
+ NULL) == -EBUSY) {
*parent_ra_addr = old_parent_ra;
return;
}
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 17326a90d53c..dc0b29612891 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -142,9 +142,8 @@ LEAF(__r4k_wait)
PTR_LA k1, __r4k_wait
ori k0, 0x1f /* 32 byte rollback region */
xori k0, 0x1f
- bne k0, k1, 9f
+ bne k0, k1, \handler
MTC0 k0, CP0_EPC
-9:
.set pop
.endm
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index c3372cac6db2..0a7e10b5f9e3 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -1164,7 +1164,9 @@ fpu_emul:
regs->regs[31] = r31;
regs->cp0_epc = epc;
if (!used_math()) { /* First time FPU user. */
+ preempt_disable();
err = init_fpu();
+ preempt_enable();
set_used_math();
}
lose_fpu(1); /* Save FPU state for the emulator. */
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 7429ad09fbe3..d2d061520a23 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -605,14 +605,14 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
return -EOPNOTSUPP;
/* Avoid inadvertently triggering emulation */
- if ((value & PR_FP_MODE_FR) && cpu_has_fpu &&
- !(current_cpu_data.fpu_id & MIPS_FPIR_F64))
+ if ((value & PR_FP_MODE_FR) && raw_cpu_has_fpu &&
+ !(raw_current_cpu_data.fpu_id & MIPS_FPIR_F64))
return -EOPNOTSUPP;
- if ((value & PR_FP_MODE_FRE) && cpu_has_fpu && !cpu_has_fre)
+ if ((value & PR_FP_MODE_FRE) && raw_cpu_has_fpu && !cpu_has_fre)
return -EOPNOTSUPP;
/* FR = 0 not supported in MIPS R6 */
- if (!(value & PR_FP_MODE_FR) && cpu_has_fpu && cpu_has_mips_r6)
+ if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
return -EOPNOTSUPP;
/* Proceed with the mode switch */
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 36cf8d65c47d..0d57909d9026 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -87,6 +87,13 @@ void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type)
int x = boot_mem_map.nr_map;
int i;
+ /*
+ * If the region reaches the top of the physical address space, adjust
+ * the size slightly so that (start + size) doesn't overflow
+ */
+ if (start + size - 1 == (phys_addr_t)ULLONG_MAX)
+ --size;
+
/* Sanity check */
if (start + size < start) {
pr_warn("Trying to add an invalid memory region, skipped\n");
@@ -757,7 +764,6 @@ static void __init arch_mem_init(char **cmdline_p)
device_tree_init();
sparse_init();
plat_swiotlb_setup();
- paging_init();
dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
/* Tell bootmem about cma reserved memblock section */
@@ -870,6 +876,7 @@ void __init setup_arch(char **cmdline_p)
prefill_possible_map();
cpu_cache_init();
+ paging_init();
}
unsigned long kernelsp[NR_CPUS];
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index e9d9fc6c754c..6183ad84cc73 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -513,7 +513,7 @@ static void cps_cpu_die(unsigned int cpu)
* in which case the CPC will refuse to power down the core.
*/
do {
- mips_cm_lock_other(core, vpe_id);
+ mips_cm_lock_other(core, 0);
mips_cpc_lock_other(core);
stat = read_cpc_co_stat_conf();
stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK;
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index f95f094f36e4..b0baf48951fa 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -322,6 +322,9 @@ asmlinkage void start_secondary(void)
cpumask_set_cpu(cpu, &cpu_coherent_mask);
notify_cpu_starting(cpu);
+ cpumask_set_cpu(cpu, &cpu_callin_map);
+ synchronise_count_slave(cpu);
+
set_cpu_online(cpu, true);
set_cpu_sibling_map(cpu);
@@ -329,10 +332,6 @@ asmlinkage void start_secondary(void)
calculate_cpu_foreign_map();
- cpumask_set_cpu(cpu, &cpu_callin_map);
-
- synchronise_count_slave(cpu);
-
/*
* irq will be enabled in ->smp_finish(), enabling it too early
* is dangerous.
diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c
index 8452d933a645..4c7c1558944a 100644
--- a/arch/mips/kernel/uprobes.c
+++ b/arch/mips/kernel/uprobes.c
@@ -157,7 +157,6 @@ bool is_trap_insn(uprobe_opcode_t *insn)
int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs)
{
struct uprobe_task *utask = current->utask;
- union mips_instruction insn;
/*
* Now find the EPC where to resume after the breakpoint has been
@@ -168,10 +167,10 @@ int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs)
unsigned long epc;
epc = regs->cp0_epc;
- __compute_return_epc_for_insn(regs, insn);
+ __compute_return_epc_for_insn(regs,
+ (union mips_instruction) aup->insn[0]);
aup->resume_epc = regs->cp0_epc;
}
-
utask->autask.saved_trap_nr = current->thread.trap_nr;
current->thread.trap_nr = UPROBE_TRAP_NR;
regs->cp0_epc = current->utask->xol_vaddr;
@@ -222,7 +221,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self,
return NOTIFY_DONE;
switch (val) {
- case DIE_BREAK:
+ case DIE_UPROBE:
if (uprobe_pre_sstep_notifier(regs))
return NOTIFY_STOP;
break;
@@ -257,7 +256,7 @@ unsigned long arch_uretprobe_hijack_return_addr(
ra = regs->regs[31];
/* Replace the return address with the trampoline address */
- regs->regs[31] = ra;
+ regs->regs[31] = trampoline_vaddr;
return ra;
}
@@ -280,24 +279,6 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm,
return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
}
-/**
- * set_orig_insn - Restore the original instruction.
- * @mm: the probed process address space.
- * @auprobe: arch specific probepoint information.
- * @vaddr: the virtual address to insert the opcode.
- *
- * For mm @mm, restore the original opcode (opcode) at @vaddr.
- * Return 0 (success) or a negative errno.
- *
- * This overrides the weak version in kernel/events/uprobes.c.
- */
-int set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
- unsigned long vaddr)
-{
- return uprobe_write_opcode(mm, vaddr,
- *(uprobe_opcode_t *)&auprobe->orig_inst[0].word);
-}
-
void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
void *src, unsigned long len)
{
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index 9abe447a4b48..f9dbfb14af33 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -39,16 +39,16 @@ static struct vm_special_mapping vdso_vvar_mapping = {
static void __init init_vdso_image(struct mips_vdso_image *image)
{
unsigned long num_pages, i;
+ unsigned long data_pfn;
BUG_ON(!PAGE_ALIGNED(image->data));
BUG_ON(!PAGE_ALIGNED(image->size));
num_pages = image->size / PAGE_SIZE;
- for (i = 0; i < num_pages; i++) {
- image->mapping.pages[i] =
- virt_to_page(image->data + (i * PAGE_SIZE));
- }
+ data_pfn = __phys_to_pfn(__pa_symbol(image->data));
+ for (i = 0; i < num_pages; i++)
+ image->mapping.pages[i] = pfn_to_page(data_pfn + i);
}
static int __init init_vdso(void)
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 2fec6f753a35..99aab9f85904 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -677,7 +677,7 @@ void play_dead(void)
play_dead_at_ckseg1(state_addr);
}
-void loongson3_disable_clock(int cpu)
+static int loongson3_disable_clock(unsigned int cpu)
{
uint64_t core_id = cpu_data[cpu].core;
uint64_t package_id = cpu_data[cpu].package;
@@ -688,9 +688,10 @@ void loongson3_disable_clock(int cpu)
if (!(loongson_sysconf.workarounds & WORKAROUND_CPUHOTPLUG))
LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3));
}
+ return 0;
}
-void loongson3_enable_clock(int cpu)
+static int loongson3_enable_clock(unsigned int cpu)
{
uint64_t core_id = cpu_data[cpu].core;
uint64_t package_id = cpu_data[cpu].package;
@@ -701,34 +702,15 @@ void loongson3_enable_clock(int cpu)
if (!(loongson_sysconf.workarounds & WORKAROUND_CPUHOTPLUG))
LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3);
}
-}
-
-#define CPU_POST_DEAD_FROZEN (CPU_POST_DEAD | CPU_TASKS_FROZEN)
-static int loongson3_cpu_callback(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
-{
- unsigned int cpu = (unsigned long)hcpu;
-
- switch (action) {
- case CPU_POST_DEAD:
- case CPU_POST_DEAD_FROZEN:
- pr_info("Disable clock for CPU#%d\n", cpu);
- loongson3_disable_clock(cpu);
- break;
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- pr_info("Enable clock for CPU#%d\n", cpu);
- loongson3_enable_clock(cpu);
- break;
- }
-
- return NOTIFY_OK;
+ return 0;
}
static int register_loongson3_notifier(void)
{
- hotcpu_notifier(loongson3_cpu_callback, 0);
- return 0;
+ return cpuhp_setup_state_nocalls(CPUHP_MIPS_SOC_PREPARE,
+ "mips/loongson:prepare",
+ loongson3_enable_clock,
+ loongson3_disable_clock);
}
early_initcall(register_loongson3_notifier);
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index 72a4642eee2c..4a094f7acb3d 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -298,5 +298,6 @@ bool do_dsemulret(struct pt_regs *xcp)
/* Set EPC to return to post-branch instruction */
xcp->cp0_epc = current->thread.bd_emu_cont_pc;
pr_debug("dsemulret to 0x%08lx\n", xcp->cp0_epc);
+ MIPS_FPU_EMU_INC_STATS(ds_emul);
return true;
}
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index cd72805b64a7..fa7d8d3790bf 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -800,7 +800,7 @@ static void r4k_flush_icache_range(unsigned long start, unsigned long end)
* If address-based cache ops don't require an SMP call, then
* use them exclusively for small flushes.
*/
- size = start - end;
+ size = end - start;
cache_size = icache_size;
if (!cpu_has_ic_fills_f_dc) {
size *= 2;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index a5509e7dcad2..72f7478ee068 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -261,7 +261,6 @@ unsigned __weak platform_maar_init(unsigned num_pairs)
{
struct maar_config cfg[BOOT_MEM_MAP_MAX];
unsigned i, num_configured, num_cfg = 0;
- phys_addr_t skip;
for (i = 0; i < boot_mem_map.nr_map; i++) {
switch (boot_mem_map.map[i].type) {
@@ -272,14 +271,14 @@ unsigned __weak platform_maar_init(unsigned num_pairs)
continue;
}
- skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
-
+ /* Round lower up */
cfg[num_cfg].lower = boot_mem_map.map[i].addr;
- cfg[num_cfg].lower += skip;
+ cfg[num_cfg].lower = (cfg[num_cfg].lower + 0xffff) & ~0xffff;
- cfg[num_cfg].upper = cfg[num_cfg].lower;
- cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
- cfg[num_cfg].upper -= skip;
+ /* Round upper down */
+ cfg[num_cfg].upper = boot_mem_map.map[i].addr +
+ boot_mem_map.map[i].size;
+ cfg[num_cfg].upper = (cfg[num_cfg].upper & ~0xffff) - 1;
cfg[num_cfg].attrs = MIPS_MAAR_S;
num_cfg++;
@@ -441,6 +440,9 @@ static inline void mem_init_free_highmem(void)
#ifdef CONFIG_HIGHMEM
unsigned long tmp;
+ if (cpu_has_dc_aliases)
+ return;
+
for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) {
struct page *page = pfn_to_page(tmp);
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index ec5b21678fad..7e7364b0501e 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -39,6 +39,9 @@
#include <linux/console.h>
#endif
+#define ROCIT_CONFIG_GEN0 0x1f403000
+#define ROCIT_CONFIG_GEN0_PCI_IOCU BIT(7)
+
extern void malta_be_init(void);
extern int malta_be_handler(struct pt_regs *regs, int is_fixup);
@@ -107,6 +110,8 @@ static void __init fd_activate(void)
static int __init plat_enable_iocoherency(void)
{
int supported = 0;
+ u32 cfg;
+
if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO) {
if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
@@ -129,7 +134,8 @@ static int __init plat_enable_iocoherency(void)
} else if (mips_cm_numiocu() != 0) {
/* Nothing special needs to be done to enable coherency */
pr_info("CMP IOCU detected\n");
- if ((*(unsigned int *)0xbf403000 & 0x81) != 0x81) {
+ cfg = __raw_readl((u32 *)CKSEG1ADDR(ROCIT_CONFIG_GEN0));
+ if (!(cfg & ROCIT_CONFIG_GEN0_PCI_IOCU)) {
pr_crit("IOCU OPERATION DISABLED BY SWITCH - DEFAULTING TO SW IO COHERENCY\n");
return 0;
}
diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h
index 20f7bf6de384..d012e877a95a 100644
--- a/arch/mn10300/include/asm/uaccess.h
+++ b/arch/mn10300/include/asm/uaccess.h
@@ -166,6 +166,7 @@ struct __large_struct { unsigned long buf[100]; };
"2:\n" \
" .section .fixup,\"ax\"\n" \
"3:\n\t" \
+ " mov 0,%1\n" \
" mov %3,%0\n" \
" jmp 2b\n" \
" .previous\n" \
diff --git a/arch/mn10300/lib/usercopy.c b/arch/mn10300/lib/usercopy.c
index 7826e6c364e7..ce8899e5e171 100644
--- a/arch/mn10300/lib/usercopy.c
+++ b/arch/mn10300/lib/usercopy.c
@@ -9,7 +9,7 @@
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
unsigned long
__generic_copy_to_user(void *to, const void *from, unsigned long n)
@@ -24,6 +24,8 @@ __generic_copy_from_user(void *to, const void *from, unsigned long n)
{
if (access_ok(VERIFY_READ, from, n))
__copy_user_zeroing(to, from, n);
+ else
+ memset(to, 0, n);
return n;
}
diff --git a/arch/nios2/boot/dts/10m50_devboard.dts b/arch/nios2/boot/dts/10m50_devboard.dts
index 3e411c644824..f362b2224ee7 100755
--- a/arch/nios2/boot/dts/10m50_devboard.dts
+++ b/arch/nios2/boot/dts/10m50_devboard.dts
@@ -83,6 +83,7 @@
fifo-size = <32>;
reg-io-width = <4>;
reg-shift = <2>;
+ tx-threshold = <16>;
};
sysid: sysid@18001528 {
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index caa51ff85a3c..0ab82324c817 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -102,9 +102,12 @@ extern long __copy_to_user(void __user *to, const void *from, unsigned long n);
static inline long copy_from_user(void *to, const void __user *from,
unsigned long n)
{
- if (!access_ok(VERIFY_READ, from, n))
- return n;
- return __copy_from_user(to, from, n);
+ unsigned long res = n;
+ if (access_ok(VERIFY_READ, from, n))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline long copy_to_user(void __user *to, const void *from,
@@ -139,7 +142,7 @@ extern long strnlen_user(const char __user *s, long n);
#define __get_user_unknown(val, size, ptr, err) do { \
err = 0; \
- if (copy_from_user(&(val), ptr, size)) { \
+ if (__copy_from_user(&(val), ptr, size)) { \
err = -EFAULT; \
} \
} while (0)
@@ -166,7 +169,7 @@ do { \
({ \
long __gu_err = -EFAULT; \
const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
__get_user_common(__gu_val, sizeof(*(ptr)), __gu_ptr, __gu_err);\
(x) = (__force __typeof__(x))__gu_val; \
__gu_err; \
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index a6bd07ca3d6c..5cc6b4f1b795 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -273,28 +273,20 @@ __copy_tofrom_user(void *to, const void *from, unsigned long size);
static inline unsigned long
copy_from_user(void *to, const void *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_READ, from, n))
- return __copy_tofrom_user(to, from, n);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- return __copy_tofrom_user(to, from, n - over) + over;
- }
- return n;
+ unsigned long res = n;
+
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_tofrom_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline unsigned long
copy_to_user(void *to, const void *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_tofrom_user(to, from, n);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- return __copy_tofrom_user(to, from, n - over) + over;
- }
+ if (likely(access_ok(VERIFY_WRITE, to, n)))
+ n = __copy_tofrom_user(to, from, n);
return n;
}
@@ -303,13 +295,8 @@ extern unsigned long __clear_user(void *addr, unsigned long size);
static inline __must_check unsigned long
clear_user(void *addr, unsigned long size)
{
-
- if (access_ok(VERIFY_WRITE, addr, size))
- return __clear_user(addr, size);
- if ((unsigned long)addr < TASK_SIZE) {
- unsigned long over = (unsigned long)addr + size - TASK_SIZE;
- return __clear_user(addr, size - over) + over;
- }
+ if (likely(access_ok(VERIFY_WRITE, addr, size)))
+ size = __clear_user(addr, size);
return size;
}
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index e9150487e20d..482847865dac 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -10,6 +10,7 @@
#include <asm-generic/uaccess-unaligned.h>
#include <linux/bug.h>
+#include <linux/string.h>
#define VERIFY_READ 0
#define VERIFY_WRITE 1
@@ -221,7 +222,7 @@ static inline unsigned long __must_check copy_from_user(void *to,
unsigned long n)
{
int sz = __compiletime_object_size(to);
- int ret = -EFAULT;
+ unsigned long ret = n;
if (likely(sz == -1 || sz >= n))
ret = __copy_from_user(to, from, n);
@@ -230,6 +231,8 @@ static inline unsigned long __must_check copy_from_user(void *to,
else
__bad_copy_user();
+ if (unlikely(ret))
+ memset(to + (n - ret), 0, ret);
return ret;
}
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index a828a0adf52c..5a5506a35395 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -48,7 +48,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent,
return;
if (ftrace_push_return_trace(old, self_addr, &trace.depth,
- 0 ) == -EBUSY)
+ 0, NULL) == -EBUSY)
return;
/* activate parisc_return_to_handler() as return point */
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index 2ef55f8968a2..b312b152461b 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -15,7 +15,7 @@ static inline bool early_cpu_has_feature(unsigned long feature)
#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
#include <linux/jump_label.h>
-#define NUM_CPU_FTR_KEYS 64
+#define NUM_CPU_FTR_KEYS BITS_PER_LONG
extern struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS];
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index c1dc6c14deb8..c266227fdd5b 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -308,40 +308,21 @@ extern unsigned long __copy_tofrom_user(void __user *to,
static inline unsigned long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_READ, from, n)) {
- if (!__builtin_constant_p(n))
- check_object_size(to, n, false);
+ if (likely(access_ok(VERIFY_READ, from, n))) {
+ check_object_size(to, n, false);
return __copy_tofrom_user((__force void __user *)to, from, n);
}
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- if (!__builtin_constant_p(n - over))
- check_object_size(to, n - over, false);
- return __copy_tofrom_user((__force void __user *)to, from,
- n - over) + over;
- }
+ memset(to, 0, n);
return n;
}
static inline unsigned long copy_to_user(void __user *to,
const void *from, unsigned long n)
{
- unsigned long over;
-
if (access_ok(VERIFY_WRITE, to, n)) {
- if (!__builtin_constant_p(n))
- check_object_size(from, n, true);
+ check_object_size(from, n, true);
return __copy_tofrom_user(to, (__force void __user *)from, n);
}
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- if (!__builtin_constant_p(n))
- check_object_size(from, n - over, true);
- return __copy_tofrom_user(to, (__force void __user *)from,
- n - over) + over;
- }
return n;
}
@@ -383,8 +364,7 @@ static inline unsigned long __copy_from_user_inatomic(void *to,
return 0;
}
- if (!__builtin_constant_p(n))
- check_object_size(to, n, false);
+ check_object_size(to, n, false);
return __copy_tofrom_user((__force void __user *)to, from, n);
}
@@ -412,8 +392,8 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to,
if (ret == 0)
return 0;
}
- if (!__builtin_constant_p(n))
- check_object_size(from, n, true);
+
+ check_object_size(from, n, true);
return __copy_tofrom_user(to, (__force const void __user *)from, n);
}
@@ -439,10 +419,6 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size)
might_fault();
if (likely(access_ok(VERIFY_WRITE, addr, size)))
return __clear_user(addr, size);
- if ((unsigned long)addr < TASK_SIZE) {
- unsigned long over = (unsigned long)addr + size - TASK_SIZE;
- return __clear_user(addr, size - over) + over;
- }
return size;
}
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index cc52d9795f88..a95639b8d4ac 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -593,7 +593,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
if (!ftrace_graph_entry(&trace))
goto out;
- if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+ if (ftrace_push_return_trace(parent, ip, &trace.depth, 0,
+ NULL) == -EBUSY)
goto out;
parent = return_hooker;
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 2265c6398a17..bd739fed26e3 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -411,7 +411,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
*
* r13 - PACA
* cr3 - gt if waking up with partial/complete hypervisor state loss
- * cr4 - eq if waking up from complete hypervisor state loss.
+ * cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
_GLOBAL(pnv_wakeup_tb_loss)
ld r1,PACAR1(r13)
@@ -453,7 +453,7 @@ lwarx_loop2:
* At this stage
* cr2 - eq if first thread to wakeup in core
* cr3- gt if waking up with partial/complete hypervisor state loss
- * cr4 - eq if waking up from complete hypervisor state loss.
+ * cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
@@ -481,7 +481,7 @@ first_thread_in_subcore:
* If waking up from sleep, subcore state is not lost. Hence
* skip subcore state restore
*/
- bne cr4,subcore_state_restored
+ blt cr4,subcore_state_restored
/* Restore per-subcore state */
ld r4,_SDR1(r1)
@@ -526,7 +526,7 @@ timebase_resync:
* If waking up from sleep, per core state is not lost, skip to
* clear_lock.
*/
- bne cr4,clear_lock
+ blt cr4,clear_lock
/*
* First thread in the core to wake up and its waking up with
@@ -557,7 +557,7 @@ common_exit:
* If waking up from sleep, hypervisor state is not lost. Hence
* skip hypervisor state restore.
*/
- bne cr4,hypervisor_state_restored
+ blt cr4,hypervisor_state_restored
/* Waking up from winkle */
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 0a57fe6d49cc..aa8214f30c92 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -127,18 +127,19 @@ _GLOBAL(csum_partial_copy_generic)
stw r7,12(r1)
stw r8,8(r1)
- rlwinm r0,r4,3,0x8
- rlwnm r6,r6,r0,0,31 /* odd destination address: rotate one byte */
- cmplwi cr7,r0,0 /* is destination address even ? */
addic r12,r6,0
addi r6,r4,-4
neg r0,r4
addi r4,r3,-4
andi. r0,r0,CACHELINE_MASK /* # bytes to start of cache line */
+ crset 4*cr7+eq
beq 58f
cmplw 0,r5,r0 /* is this more than total to do? */
blt 63f /* if not much to do */
+ rlwinm r7,r6,3,0x8
+ rlwnm r12,r12,r7,0,31 /* odd destination address: rotate one byte */
+ cmplwi cr7,r7,0 /* is destination address even ? */
andi. r8,r0,3 /* get it word-aligned first */
mtctr r8
beq+ 61f
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 7d95bc402dba..c491f2c8f2b9 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -369,44 +369,34 @@ void destroy_context(struct mm_struct *mm)
}
#ifdef CONFIG_SMP
-
-static int mmu_context_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
+static int mmu_ctx_cpu_prepare(unsigned int cpu)
{
- unsigned int cpu = (unsigned int)(long)hcpu;
-
/* We don't touch CPU 0 map, it's allocated at aboot and kept
* around forever
*/
if (cpu == boot_cpuid)
- return NOTIFY_OK;
-
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu);
- stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL);
- break;
-#ifdef CONFIG_HOTPLUG_CPU
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu);
- kfree(stale_map[cpu]);
- stale_map[cpu] = NULL;
-
- /* We also clear the cpu_vm_mask bits of CPUs going away */
- clear_tasks_mm_cpumask(cpu);
- break;
-#endif /* CONFIG_HOTPLUG_CPU */
- }
- return NOTIFY_OK;
+ return 0;
+
+ pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu);
+ stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL);
+ return 0;
}
-static struct notifier_block mmu_context_cpu_nb = {
- .notifier_call = mmu_context_cpu_notify,
-};
+static int mmu_ctx_cpu_dead(unsigned int cpu)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ if (cpu == boot_cpuid)
+ return 0;
+
+ pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu);
+ kfree(stale_map[cpu]);
+ stale_map[cpu] = NULL;
+
+ /* We also clear the cpu_vm_mask bits of CPUs going away */
+ clear_tasks_mm_cpumask(cpu);
+#endif
+ return 0;
+}
#endif /* CONFIG_SMP */
@@ -469,7 +459,9 @@ void __init mmu_context_init(void)
#else
stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0);
- register_cpu_notifier(&mmu_context_cpu_nb);
+ cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE,
+ "powerpc/mmu/ctx:prepare",
+ mmu_ctx_cpu_prepare, mmu_ctx_cpu_dead);
#endif
printk(KERN_INFO
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index dfdb90cb4403..9f1983404e1a 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -113,7 +113,12 @@ BEGIN_FTR_SECTION
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
b slb_finish_load_1T
-0:
+0: /*
+ * For userspace addresses, make sure this is region 0.
+ */
+ cmpdi r9, 0
+ bne 8f
+
/* when using slices, we extract the psize off the slice bitmaps
* and then we need to get the sllp encoding off the mmu_psize_defs
* array.
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 834868b9fdc9..366e4f510fcf 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -852,37 +852,33 @@ static void smp_core99_setup_cpu(int cpu_nr)
#ifdef CONFIG_PPC64
#ifdef CONFIG_HOTPLUG_CPU
-static int smp_core99_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
+static unsigned int smp_core99_host_open;
+
+static int smp_core99_cpu_prepare(unsigned int cpu)
{
int rc;
- switch(action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- /* Open i2c bus if it was used for tb sync */
- if (pmac_tb_clock_chip_host) {
- rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1);
- if (rc) {
- pr_err("Failed to open i2c bus for time sync\n");
- return notifier_from_errno(rc);
- }
+ /* Open i2c bus if it was used for tb sync */
+ if (pmac_tb_clock_chip_host && !smp_core99_host_open) {
+ rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1);
+ if (rc) {
+ pr_err("Failed to open i2c bus for time sync\n");
+ return notifier_from_errno(rc);
}
- break;
- case CPU_ONLINE:
- case CPU_UP_CANCELED:
- /* Close i2c bus if it was used for tb sync */
- if (pmac_tb_clock_chip_host)
- pmac_i2c_close(pmac_tb_clock_chip_host);
- break;
- default:
- break;
+ smp_core99_host_open = 1;
}
- return NOTIFY_OK;
+ return 0;
}
-static struct notifier_block smp_core99_cpu_nb = {
- .notifier_call = smp_core99_cpu_notify,
-};
+static int smp_core99_cpu_online(unsigned int cpu)
+{
+ /* Close i2c bus if it was used for tb sync */
+ if (pmac_tb_clock_chip_host && smp_core99_host_open) {
+ pmac_i2c_close(pmac_tb_clock_chip_host);
+ smp_core99_host_open = 0;
+ }
+ return 0;
+}
#endif /* CONFIG_HOTPLUG_CPU */
static void __init smp_core99_bringup_done(void)
@@ -902,7 +898,11 @@ static void __init smp_core99_bringup_done(void)
g5_phy_disable_cpu1();
}
#ifdef CONFIG_HOTPLUG_CPU
- register_cpu_notifier(&smp_core99_cpu_nb);
+ cpuhp_setup_state_nocalls(CPUHP_POWERPC_PMAC_PREPARE,
+ "powerpc/pmac:prepare", smp_core99_cpu_prepare,
+ NULL);
+ cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "powerpc/pmac:online",
+ smp_core99_cpu_online, NULL);
#endif
if (ppc_md.progress)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 13218263e66e..38a5c657ffd3 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -124,6 +124,13 @@ static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
}
+static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags)
+{
+ unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);
+
+ return (resource_flags & flags) == flags;
+}
+
static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
{
phb->ioda.pe_array[pe_no].phb = phb;
@@ -162,11 +169,12 @@ static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
{
struct pnv_phb *phb = pe->phb;
+ unsigned int pe_num = pe->pe_number;
WARN_ON(pe->pdev);
memset(pe, 0, sizeof(struct pnv_ioda_pe));
- clear_bit(pe->pe_number, phb->ioda.pe_alloc);
+ clear_bit(pe_num, phb->ioda.pe_alloc);
}
/* The default M64 BAR is shared by all PEs */
@@ -2216,7 +2224,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
pnv_pci_link_table_and_group(phb->hose->node, num,
tbl, &pe->table_group);
- pnv_pci_phb3_tce_invalidate_pe(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
return 0;
}
@@ -2354,7 +2362,7 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
if (ret)
pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
else
- pnv_pci_phb3_tce_invalidate_pe(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
@@ -2870,7 +2878,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
res = &pdev->resource[i + PCI_IOV_RESOURCES];
if (!res->flags || res->parent)
continue;
- if (!pnv_pci_is_m64(phb, res)) {
+ if (!pnv_pci_is_m64_flags(res->flags)) {
dev_warn(&pdev->dev, "Don't support SR-IOV with"
" non M64 VF BAR%d: %pR. \n",
i, res);
@@ -3095,7 +3103,7 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
* alignment for any 64-bit resource, PCIe doesn't care and
* bridges only do 64-bit prefetchable anyway.
*/
- if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64))
+ if (phb->ioda.m64_segsize && pnv_pci_is_m64_flags(type))
return phb->ioda.m64_segsize;
if (type & IORESOURCE_MEM)
return phb->ioda.m32_segsize;
@@ -3402,12 +3410,6 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
struct pnv_phb *phb = pe->phb;
struct pnv_ioda_pe *slave, *tmp;
- /* Release slave PEs in compound PE */
- if (pe->flags & PNV_IODA_PE_MASTER) {
- list_for_each_entry_safe(slave, tmp, &pe->slaves, list)
- pnv_ioda_release_pe(slave);
- }
-
list_del(&pe->list);
switch (phb->type) {
case PNV_PHB_IODA1:
@@ -3422,7 +3424,26 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
pnv_ioda_release_pe_seg(pe);
pnv_ioda_deconfigure_pe(pe->phb, pe);
- pnv_ioda_free_pe(pe);
+
+ /* Release slave PEs in the compound PE */
+ if (pe->flags & PNV_IODA_PE_MASTER) {
+ list_for_each_entry_safe(slave, tmp, &pe->slaves, list) {
+ list_del(&slave->list);
+ pnv_ioda_free_pe(slave);
+ }
+ }
+
+ /*
+ * The PE for root bus can be removed because of hotplug in EEH
+ * recovery for fenced PHB error. We need to mark the PE dead so
+ * that it can be populated again in PCI hot add path. The PE
+ * shouldn't be destroyed as it's the global reserved resource.
+ */
+ if (phb->ioda.root_pe_populated &&
+ phb->ioda.root_pe_idx == pe->pe_number)
+ phb->ioda.root_pe_populated = false;
+ else
+ pnv_ioda_free_pe(pe);
}
static void pnv_pci_release_device(struct pci_dev *pdev)
@@ -3438,7 +3459,17 @@ static void pnv_pci_release_device(struct pci_dev *pdev)
if (!pdn || pdn->pe_number == IODA_INVALID_PE)
return;
+ /*
+ * PCI hotplug can happen as part of EEH error recovery. The @pdn
+ * isn't removed and added afterwards in this scenario. We should
+ * set the PE number in @pdn to an invalid one. Otherwise, the PE's
+ * device count is decreased on removing devices while failing to
+ * be increased on adding devices. It leads to unbalanced PE's device
+ * count and eventually make normal PCI hotplug path broken.
+ */
pe = &phb->ioda.pe_array[pdn->pe_number];
+ pdn->pe_number = IODA_INVALID_PE;
+
WARN_ON(--pe->device_count < 0);
if (pe->device_count == 0)
pnv_ioda_release_pe(pe);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 4ffcaa6f8670..a39d20e8623d 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -41,7 +41,6 @@
#include <linux/root_dev.h>
#include <linux/of.h>
#include <linux/of_pci.h>
-#include <linux/kexec.h>
#include <asm/mmu.h>
#include <asm/processor.h>
@@ -66,6 +65,7 @@
#include <asm/eeh.h>
#include <asm/reg.h>
#include <asm/plpar_wrappers.h>
+#include <asm/kexec.h>
#include "pseries.h"
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index 57d72f10a97f..9114243fa1b5 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -23,10 +23,10 @@
static void icp_opal_teardown_cpu(void)
{
- int cpu = smp_processor_id();
+ int hw_cpu = hard_smp_processor_id();
/* Clear any pending IPI */
- opal_int_set_mfrr(cpu, 0xff);
+ opal_int_set_mfrr(hw_cpu, 0xff);
}
static void icp_opal_flush_ipi(void)
@@ -101,14 +101,16 @@ static void icp_opal_eoi(struct irq_data *d)
static void icp_opal_cause_ipi(int cpu, unsigned long data)
{
- opal_int_set_mfrr(cpu, IPI_PRIORITY);
+ int hw_cpu = get_hard_smp_processor_id(cpu);
+
+ opal_int_set_mfrr(hw_cpu, IPI_PRIORITY);
}
static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
{
- int cpu = smp_processor_id();
+ int hw_cpu = hard_smp_processor_id();
- opal_int_set_mfrr(cpu, 0xff);
+ opal_int_set_mfrr(hw_cpu, 0xff);
return smp_ipi_demux();
}
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 95aefdba4be2..52d7c8709279 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -266,28 +266,28 @@ int __put_user_bad(void) __attribute__((noreturn));
__chk_user_ptr(ptr); \
switch (sizeof(*(ptr))) { \
case 1: { \
- unsigned char __x; \
+ unsigned char __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 2: { \
- unsigned short __x; \
+ unsigned short __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 4: { \
- unsigned int __x; \
+ unsigned int __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 8: { \
- unsigned long long __x; \
+ unsigned long long __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 0f7bfeba6da6..60a8a4e207ed 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -209,7 +209,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
/* Only trace if the calling function expects to. */
if (!ftrace_graph_entry(&trace))
goto out;
- if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+ if (ftrace_push_return_trace(parent, ip, &trace.depth, 0,
+ NULL) == -EBUSY)
goto out;
parent = (unsigned long) return_to_handler;
out:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f142215ed30d..607ec91966c7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2231,9 +2231,10 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
return -EINVAL;
current->thread.fpu.fpc = fpu->fpc;
if (MACHINE_HAS_VX)
- convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+ convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
+ (freg_t *) fpu->fprs);
else
- memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
+ memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
return 0;
}
@@ -2242,9 +2243,10 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
/* make sure we have the latest values */
save_fpu_regs();
if (MACHINE_HAS_VX)
- convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+ convert_vx_to_fp((freg_t *) fpu->fprs,
+ (__vector128 *) vcpu->run->s.regs.vrs);
else
- memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+ memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
fpu->fpc = current->thread.fpu.fpc;
return 0;
}
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index c106488b4137..d8673e243f13 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -584,7 +584,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
/* Validity 0x0044 will be checked by SIE */
if (rc)
goto unpin;
- scb_s->gvrd = hpa;
+ scb_s->riccbd = hpa;
}
return 0;
unpin:
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index a58bca62a93b..cbb73fabc91e 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -740,28 +740,21 @@ out:
put_task_struct(tsk);
}
-static int pfault_cpu_notify(struct notifier_block *self, unsigned long action,
- void *hcpu)
+static int pfault_cpu_dead(unsigned int cpu)
{
struct thread_struct *thread, *next;
struct task_struct *tsk;
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_DEAD:
- spin_lock_irq(&pfault_lock);
- list_for_each_entry_safe(thread, next, &pfault_list, list) {
- thread->pfault_wait = 0;
- list_del(&thread->list);
- tsk = container_of(thread, struct task_struct, thread);
- wake_up_process(tsk);
- put_task_struct(tsk);
- }
- spin_unlock_irq(&pfault_lock);
- break;
- default:
- break;
+ spin_lock_irq(&pfault_lock);
+ list_for_each_entry_safe(thread, next, &pfault_list, list) {
+ thread->pfault_wait = 0;
+ list_del(&thread->list);
+ tsk = container_of(thread, struct task_struct, thread);
+ wake_up_process(tsk);
+ put_task_struct(tsk);
}
- return NOTIFY_OK;
+ spin_unlock_irq(&pfault_lock);
+ return 0;
}
static int __init pfault_irq_init(void)
@@ -775,7 +768,8 @@ static int __init pfault_irq_init(void)
if (rc)
goto out_pfault;
irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
- hotcpu_notifier(pfault_cpu_notify, 0);
+ cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead",
+ NULL, pfault_cpu_dead);
return 0;
out_pfault:
diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h
index 20a3591225cc..01aec8ccde83 100644
--- a/arch/score/include/asm/uaccess.h
+++ b/arch/score/include/asm/uaccess.h
@@ -163,7 +163,7 @@ do { \
__get_user_asm(val, "lw", ptr); \
break; \
case 8: \
- if ((copy_from_user((void *)&val, ptr, 8)) == 0) \
+ if (__copy_from_user((void *)&val, ptr, 8) == 0) \
__gu_err = 0; \
else \
__gu_err = -EFAULT; \
@@ -188,6 +188,8 @@ do { \
\
if (likely(access_ok(VERIFY_READ, __gu_ptr, size))) \
__get_user_common((x), size, __gu_ptr); \
+ else \
+ (x) = 0; \
\
__gu_err; \
})
@@ -201,6 +203,7 @@ do { \
"2:\n" \
".section .fixup,\"ax\"\n" \
"3:li %0, %4\n" \
+ "li %1, 0\n" \
"j 2b\n" \
".previous\n" \
".section __ex_table,\"a\"\n" \
@@ -298,35 +301,34 @@ extern int __copy_tofrom_user(void *to, const void *from, unsigned long len);
static inline unsigned long
copy_from_user(void *to, const void *from, unsigned long len)
{
- unsigned long over;
+ unsigned long res = len;
- if (access_ok(VERIFY_READ, from, len))
- return __copy_tofrom_user(to, from, len);
+ if (likely(access_ok(VERIFY_READ, from, len)))
+ res = __copy_tofrom_user(to, from, len);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + len - TASK_SIZE;
- return __copy_tofrom_user(to, from, len - over) + over;
- }
- return len;
+ if (unlikely(res))
+ memset(to + (len - res), 0, res);
+
+ return res;
}
static inline unsigned long
copy_to_user(void *to, const void *from, unsigned long len)
{
- unsigned long over;
-
- if (access_ok(VERIFY_WRITE, to, len))
- return __copy_tofrom_user(to, from, len);
+ if (likely(access_ok(VERIFY_WRITE, to, len)))
+ len = __copy_tofrom_user(to, from, len);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + len - TASK_SIZE;
- return __copy_tofrom_user(to, from, len - over) + over;
- }
return len;
}
-#define __copy_from_user(to, from, len) \
- __copy_tofrom_user((to), (from), (len))
+static inline unsigned long
+__copy_from_user(void *to, const void *from, unsigned long len)
+{
+ unsigned long left = __copy_tofrom_user(to, from, len);
+ if (unlikely(left))
+ memset(to + (len - left), 0, left);
+ return left;
+}
#define __copy_to_user(to, from, len) \
__copy_tofrom_user((to), (from), (len))
@@ -340,17 +342,17 @@ __copy_to_user_inatomic(void *to, const void *from, unsigned long len)
static inline unsigned long
__copy_from_user_inatomic(void *to, const void *from, unsigned long len)
{
- return __copy_from_user(to, from, len);
+ return __copy_tofrom_user(to, from, len);
}
-#define __copy_in_user(to, from, len) __copy_from_user(to, from, len)
+#define __copy_in_user(to, from, len) __copy_tofrom_user(to, from, len)
static inline unsigned long
copy_in_user(void *to, const void *from, unsigned long len)
{
if (access_ok(VERIFY_READ, from, len) &&
access_ok(VERFITY_WRITE, to, len))
- return copy_from_user(to, from, len);
+ return __copy_tofrom_user(to, from, len);
}
/*
diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h
index caea2c45f6c2..1d159ce50f5a 100644
--- a/arch/sh/include/asm/atomic-llsc.h
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -60,7 +60,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \
" movco.l %0, @%3 \n" \
" bf 1b \n" \
" synco \n" \
- : "=&z" (temp), "=&z" (res) \
+ : "=&z" (temp), "=&r" (res) \
: "r" (i), "r" (&v->counter) \
: "t"); \
\
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index a49635c51266..92ade79ac427 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -151,7 +151,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
__kernel_size_t __copy_size = (__kernel_size_t) n;
if (__copy_size && __access_ok(__copy_from, __copy_size))
- return __copy_user(to, from, __copy_size);
+ __copy_size = __copy_user(to, from, __copy_size);
+
+ if (unlikely(__copy_size))
+ memset(to + (n - __copy_size), 0, __copy_size);
return __copy_size;
}
diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h
index c01376c76b86..ca5073dd4596 100644
--- a/arch/sh/include/asm/uaccess_64.h
+++ b/arch/sh/include/asm/uaccess_64.h
@@ -24,6 +24,7 @@
#define __get_user_size(x,ptr,size,retval) \
do { \
retval = 0; \
+ x = 0; \
switch (size) { \
case 1: \
retval = __get_user_asm_b((void *)&x, \
diff --git a/arch/sh/kernel/cpu/sh4a/smp-shx3.c b/arch/sh/kernel/cpu/sh4a/smp-shx3.c
index 839612c8a0a0..0d3637c494bf 100644
--- a/arch/sh/kernel/cpu/sh4a/smp-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/smp-shx3.c
@@ -122,32 +122,16 @@ static void shx3_update_boot_vector(unsigned int cpu)
__raw_writel(STBCR_RESET, STBCR_REG(cpu));
}
-static int
-shx3_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+static int shx3_cpu_prepare(unsigned int cpu)
{
- unsigned int cpu = (unsigned int)hcpu;
-
- switch (action) {
- case CPU_UP_PREPARE:
- shx3_update_boot_vector(cpu);
- break;
- case CPU_ONLINE:
- pr_info("CPU %u is now online\n", cpu);
- break;
- case CPU_DEAD:
- break;
- }
-
- return NOTIFY_OK;
+ shx3_update_boot_vector(cpu);
+ return 0;
}
-static struct notifier_block shx3_cpu_notifier = {
- .notifier_call = shx3_cpu_callback,
-};
-
static int register_shx3_cpu_notifier(void)
{
- register_hotcpu_notifier(&shx3_cpu_notifier);
+ cpuhp_setup_state_nocalls(CPUHP_SH_SH3X_PREPARE, "sh/shx3:prepare",
+ shx3_cpu_prepare, NULL);
return 0;
}
late_initcall(register_shx3_cpu_notifier);
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 38993e09ef03..95eccd49672f 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -382,7 +382,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
return;
}
- err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0);
+ err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL);
if (err == -EBUSY) {
__raw_writel(old, parent);
return;
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 59b09600dd32..f5d60f14a0bc 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -56,7 +56,6 @@ config SPARC64
def_bool 64BIT
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
- select HAVE_FUNCTION_GRAPH_FP_TEST
select HAVE_KRETPROBES
select HAVE_KPROBES
select HAVE_RCU_TABLE_FREE if SMP
diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h
index 3192a8e42fd6..62755a339a59 100644
--- a/arch/sparc/include/asm/ftrace.h
+++ b/arch/sparc/include/asm/ftrace.h
@@ -9,6 +9,10 @@
void _mcount(void);
#endif
+#endif /* CONFIG_MCOUNT */
+
+#if defined(CONFIG_SPARC64) && !defined(CC_USE_FENTRY)
+#define HAVE_FUNCTION_GRAPH_FP_TEST
#endif
#ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index 8c2a8c937540..c1263fc390db 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -25,6 +25,7 @@
#define HPAGE_MASK (~(HPAGE_SIZE - 1UL))
#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index 26d9e7726867..ce2233f7e662 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -43,6 +43,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask);
int hard_smp_processor_id(void);
#define raw_smp_processor_id() (current_thread_info()->cpu)
+void smp_fill_in_cpu_possible_map(void);
void smp_fill_in_sib_core_maps(void);
void cpu_play_dead(void);
@@ -72,6 +73,7 @@ void __cpu_die(unsigned int cpu);
#define smp_fill_in_sib_core_maps() do { } while (0)
#define smp_fetch_global_regs() do { } while (0)
#define smp_fetch_global_pmu() do { } while (0)
+#define smp_fill_in_cpu_possible_map() do { } while (0)
#endif /* !(CONFIG_SMP) */
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 341a5a133f48..ea55f86d7ccd 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -249,8 +249,7 @@ unsigned long __copy_user(void __user *to, const void __user *from, unsigned lon
static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
{
if (n && __access_ok((unsigned long) to, n)) {
- if (!__builtin_constant_p(n))
- check_object_size(from, n, true);
+ check_object_size(from, n, true);
return __copy_user(to, (__force void __user *) from, n);
} else
return n;
@@ -258,19 +257,19 @@ static inline unsigned long copy_to_user(void __user *to, const void *from, unsi
static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
{
- if (!__builtin_constant_p(n))
- check_object_size(from, n, true);
+ check_object_size(from, n, true);
return __copy_user(to, (__force void __user *) from, n);
}
static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
{
if (n && __access_ok((unsigned long) from, n)) {
- if (!__builtin_constant_p(n))
- check_object_size(to, n, false);
+ check_object_size(to, n, false);
return __copy_user((__force void __user *) to, from, n);
- } else
+ } else {
+ memset(to, 0, n);
return n;
+ }
}
static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index 8bda94fab8e8..37a315d0ddd4 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -212,8 +212,7 @@ copy_from_user(void *to, const void __user *from, unsigned long size)
{
unsigned long ret;
- if (!__builtin_constant_p(size))
- check_object_size(to, size, false);
+ check_object_size(to, size, false);
ret = ___copy_from_user(to, from, size);
if (unlikely(ret))
@@ -233,8 +232,8 @@ copy_to_user(void __user *to, const void *from, unsigned long size)
{
unsigned long ret;
- if (!__builtin_constant_p(size))
- check_object_size(from, size, true);
+ check_object_size(from, size, true);
+
ret = ___copy_to_user(to, from, size);
if (unlikely(ret))
ret = copy_to_user_fixup(to, from, size);
diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c
index 0a2d2ddff543..6bcff698069b 100644
--- a/arch/sparc/kernel/ftrace.c
+++ b/arch/sparc/kernel/ftrace.c
@@ -131,7 +131,7 @@ unsigned long prepare_ftrace_return(unsigned long parent,
return parent + 8UL;
if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
- frame_pointer) == -EBUSY)
+ frame_pointer, NULL) == -EBUSY)
return parent + 8UL;
trace.func = self_addr;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 599f1207eed2..6b7331d198e9 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -31,6 +31,7 @@
#include <linux/initrd.h>
#include <linux/module.h>
#include <linux/start_kernel.h>
+#include <linux/bootmem.h>
#include <asm/io.h>
#include <asm/processor.h>
@@ -50,6 +51,8 @@
#include <asm/elf.h>
#include <asm/mdesc.h>
#include <asm/cacheflush.h>
+#include <asm/dma.h>
+#include <asm/irq.h>
#ifdef CONFIG_IP_PNP
#include <net/ipconfig.h>
@@ -590,6 +593,22 @@ static void __init init_sparc64_elf_hwcap(void)
pause_patch();
}
+void __init alloc_irqstack_bootmem(void)
+{
+ unsigned int i, node;
+
+ for_each_possible_cpu(i) {
+ node = cpu_to_node(i);
+
+ softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
+ THREAD_SIZE,
+ THREAD_SIZE, 0);
+ hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
+ THREAD_SIZE,
+ THREAD_SIZE, 0);
+ }
+}
+
void __init setup_arch(char **cmdline_p)
{
/* Initialize PROM console and command line. */
@@ -650,6 +669,13 @@ void __init setup_arch(char **cmdline_p)
paging_init();
init_sparc64_elf_hwcap();
+ smp_fill_in_cpu_possible_map();
+ /*
+ * Once the OF device tree and MDESC have been setup and nr_cpus has
+ * been parsed, we know the list of possible cpus. Therefore we can
+ * allocate the IRQ stacks.
+ */
+ alloc_irqstack_bootmem();
}
extern int stop_a_enabled;
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index fb30e7c6a5b1..e80e6ba3d500 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -352,9 +352,7 @@ static void sparc_start_secondary(void *arg)
preempt_disable();
cpu = smp_processor_id();
- /* Invoke the CPU_STARTING notifier callbacks */
notify_cpu_starting(cpu);
-
arch_cpu_pre_online(arg);
/* Set the CPU in the cpu_online_mask */
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 8a6151a628ce..d3035ba6cd31 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1227,6 +1227,20 @@ void __init smp_setup_processor_id(void)
xcall_deliver_impl = hypervisor_xcall_deliver;
}
+void __init smp_fill_in_cpu_possible_map(void)
+{
+ int possible_cpus = num_possible_cpus();
+ int i;
+
+ if (possible_cpus > nr_cpu_ids)
+ possible_cpus = nr_cpu_ids;
+
+ for (i = 0; i < possible_cpus; i++)
+ set_cpu_possible(i, true);
+ for (; i < NR_CPUS; i++)
+ set_cpu_possible(i, false);
+}
+
void smp_fill_in_sib_core_maps(void)
{
unsigned int i;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index e16fdd28a931..3f291d8c57f7 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -484,6 +484,7 @@ good_area:
tsb_grow(mm, MM_TSB_BASE, mm_rss);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count;
+ mm_rss *= REAL_HPAGE_PER_HPAGE;
if (unlikely(mm_rss >
mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) {
if (mm->context.tsb_block[MM_TSB_HUGE].tsb)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 65457c9f1365..7ac6b62fb7c1 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1160,7 +1160,7 @@ int __node_distance(int from, int to)
return numa_latency[from][to];
}
-static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
+static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
{
int i;
@@ -1173,8 +1173,8 @@ static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
return i;
}
-static void find_numa_latencies_for_group(struct mdesc_handle *md, u64 grp,
- int index)
+static void __init find_numa_latencies_for_group(struct mdesc_handle *md,
+ u64 grp, int index)
{
u64 arc;
@@ -2081,7 +2081,6 @@ void __init paging_init(void)
{
unsigned long end_pfn, shift, phys_base;
unsigned long real_end, i;
- int node;
setup_page_offset();
@@ -2250,21 +2249,6 @@ void __init paging_init(void)
/* Setup bootmem... */
last_valid_pfn = end_pfn = bootmem_init(phys_base);
- /* Once the OF device tree and MDESC have been setup, we know
- * the list of possible cpus. Therefore we can allocate the
- * IRQ stacks.
- */
- for_each_possible_cpu(i) {
- node = cpu_to_node(i);
-
- softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
- THREAD_SIZE,
- THREAD_SIZE, 0);
- hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
- THREAD_SIZE,
- THREAD_SIZE, 0);
- }
-
kernel_physical_mapping_init();
{
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 3659d37b4d81..c56a195c9071 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -174,10 +174,25 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
return;
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
- if (pmd_val(pmd) & _PAGE_PMD_HUGE)
- mm->context.thp_pte_count++;
- else
- mm->context.thp_pte_count--;
+ /*
+ * Note that this routine only sets pmds for THP pages.
+ * Hugetlb pages are handled elsewhere. We need to check
+ * for huge zero page. Huge zero pages are like hugetlb
+ * pages in that there is no RSS, but there is the need
+ * for TSB entries. So, huge zero page counts go into
+ * hugetlb_pte_count.
+ */
+ if (pmd_val(pmd) & _PAGE_PMD_HUGE) {
+ if (is_huge_zero_page(pmd_page(pmd)))
+ mm->context.hugetlb_pte_count++;
+ else
+ mm->context.thp_pte_count++;
+ } else {
+ if (is_huge_zero_page(pmd_page(orig)))
+ mm->context.hugetlb_pte_count--;
+ else
+ mm->context.thp_pte_count--;
+ }
/* Do not try to allocate the TSB hash table if we
* don't have one already. We have various locks held
@@ -204,6 +219,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
}
}
+/*
+ * This routine is only called when splitting a THP
+ */
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
@@ -213,6 +231,15 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
set_pmd_at(vma->vm_mm, address, pmdp, entry);
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+ /*
+ * set_pmd_at() will not be called in a way to decrement
+ * thp_pte_count when splitting a THP, so do it now.
+ * Sanity check pmd before doing the actual decrement.
+ */
+ if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
+ !is_huge_zero_page(pmd_page(entry)))
+ (vma->vm_mm)->context.thp_pte_count--;
}
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 6725ed45580e..f2b77112e9d8 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -469,8 +469,10 @@ retry_tsb_alloc:
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
+ unsigned long mm_rss = get_mm_rss(mm);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- unsigned long total_huge_pte_count;
+ unsigned long saved_hugetlb_pte_count;
+ unsigned long saved_thp_pte_count;
#endif
unsigned int i;
@@ -483,10 +485,12 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
* will re-increment the counters as the parent PTEs are
* copied into the child address space.
*/
- total_huge_pte_count = mm->context.hugetlb_pte_count +
- mm->context.thp_pte_count;
+ saved_hugetlb_pte_count = mm->context.hugetlb_pte_count;
+ saved_thp_pte_count = mm->context.thp_pte_count;
mm->context.hugetlb_pte_count = 0;
mm->context.thp_pte_count = 0;
+
+ mm_rss -= saved_thp_pte_count * (HPAGE_SIZE / PAGE_SIZE);
#endif
/* copy_mm() copies over the parent's mm_struct before calling
@@ -499,11 +503,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
/* If this is fork, inherit the parent's TSB size. We would
* grow it to that size on the first page fault anyways.
*/
- tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
+ tsb_grow(mm, MM_TSB_BASE, mm_rss);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (unlikely(total_huge_pte_count))
- tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count);
+ if (unlikely(saved_hugetlb_pte_count + saved_thp_pte_count))
+ tsb_grow(mm, MM_TSB_HUGE,
+ (saved_hugetlb_pte_count + saved_thp_pte_count) *
+ REAL_HPAGE_PER_HPAGE);
#endif
if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))
diff --git a/arch/tile/kernel/ftrace.c b/arch/tile/kernel/ftrace.c
index 4a572088b270..b827a418b155 100644
--- a/arch/tile/kernel/ftrace.c
+++ b/arch/tile/kernel/ftrace.c
@@ -184,7 +184,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
*parent = return_hooker;
err = ftrace_push_return_trace(old, self_addr, &trace.depth,
- frame_pointer);
+ frame_pointer, NULL);
if (err == -EBUSY) {
*parent = old;
return;
diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c
index 2d0266d0254d..3282787bbcfb 100644
--- a/arch/um/drivers/harddog_kern.c
+++ b/arch/um/drivers/harddog_kern.c
@@ -175,27 +175,4 @@ static struct miscdevice harddog_miscdev = {
.name = "watchdog",
.fops = &harddog_fops,
};
-
-static char banner[] __initdata = KERN_INFO "UML Watchdog Timer\n";
-
-static int __init harddog_init(void)
-{
- int ret;
-
- ret = misc_register(&harddog_miscdev);
-
- if (ret)
- return ret;
-
- printk(banner);
-
- return 0;
-}
-
-static void __exit harddog_exit(void)
-{
- misc_deregister(&harddog_miscdev);
-}
-
-module_init(harddog_init);
-module_exit(harddog_exit);
+module_misc_device(harddog_miscdev);
diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c
index ef4b8f949b51..b783ac87d98a 100644
--- a/arch/um/kernel/skas/syscall.c
+++ b/arch/um/kernel/skas/syscall.c
@@ -21,21 +21,17 @@ void handle_syscall(struct uml_pt_regs *r)
PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS);
if (syscall_trace_enter(regs))
- return;
+ goto out;
/* Do the seccomp check after ptrace; failures should be fast. */
if (secure_computing(NULL) == -1)
- return;
+ goto out;
- /* Update the syscall number after orig_ax has potentially been updated
- * with ptrace.
- */
- UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
syscall = UPT_SYSCALL_NR(r);
-
if (syscall >= 0 && syscall <= __NR_syscall_max)
PT_REGS_SET_SYSCALL_RETURN(regs,
EXECUTE_SYSCALL(syscall, regs));
+out:
syscall_trace_leave(regs);
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2a1f0ce7c59a..9b2d50a73a11 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -93,6 +93,7 @@ config X86
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ARCH_WITHIN_STACK_FRAMES
select HAVE_EBPF_JIT if X86_64
+ select HAVE_ARCH_VMAP_STACK if X86_64
select HAVE_CC_STACKPROTECTOR
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
@@ -109,7 +110,6 @@ config X86
select HAVE_EXIT_THREAD
select HAVE_FENTRY if X86_64
select HAVE_FTRACE_MCOUNT_RECORD
- select HAVE_FUNCTION_GRAPH_FP_TEST
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
@@ -157,6 +157,7 @@ config X86
select SPARSE_IRQ
select SRCU
select SYSCTL_EXCEPTION_TRACE
+ select THREAD_INFO_IN_TASK
select USER_STACKTRACE_SUPPORT
select VIRT_TO_BUS
select X86_DEV_DMA_OPS if X86_64
@@ -549,6 +550,18 @@ config X86_INTEL_QUARK
Say Y here if you have a Quark based system such as the Arduino
compatible Intel Galileo.
+config MLX_PLATFORM
+ tristate "Mellanox Technologies platform support"
+ depends on X86_64
+ depends on X86_EXTENDED_PLATFORM
+ ---help---
+ This option enables system support for the Mellanox Technologies
+ platform.
+
+ Say Y here if you are building a kernel for Mellanox system.
+
+ Otherwise, say N.
+
config X86_INTEL_LPSS
bool "Intel Low Power Subsystem Support"
depends on X86 && ACPI
@@ -705,7 +718,6 @@ config PARAVIRT_DEBUG
config PARAVIRT_SPINLOCKS
bool "Paravirtualization layer for spinlocks"
depends on PARAVIRT && SMP
- select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS
---help---
Paravirtualized spinlocks allow a pvops backend to replace the
spinlock implementation with something virtualization-friendly
@@ -718,7 +730,7 @@ config PARAVIRT_SPINLOCKS
config QUEUED_LOCK_STAT
bool "Paravirt queued spinlock statistics"
- depends on PARAVIRT_SPINLOCKS && DEBUG_FS && QUEUED_SPINLOCKS
+ depends on PARAVIRT_SPINLOCKS && DEBUG_FS
---help---
Enable the collection of statistical data on the slowpath
behavior of paravirtualized queued spinlocks and report
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ff574dad95cc..cc69e37548db 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -29,22 +29,11 @@ __pure const struct efi_config *__efi_early(void)
static void setup_boot_services##bits(struct efi_config *c) \
{ \
efi_system_table_##bits##_t *table; \
- efi_boot_services_##bits##_t *bt; \
\
table = (typeof(table))sys_table; \
\
+ c->boot_services = table->boottime; \
c->text_output = table->con_out; \
- \
- bt = (typeof(bt))(unsigned long)(table->boottime); \
- \
- c->allocate_pool = bt->allocate_pool; \
- c->allocate_pages = bt->allocate_pages; \
- c->get_memory_map = bt->get_memory_map; \
- c->free_pool = bt->free_pool; \
- c->free_pages = bt->free_pages; \
- c->locate_handle = bt->locate_handle; \
- c->handle_protocol = bt->handle_protocol; \
- c->exit_boot_services = bt->exit_boot_services; \
}
BOOT_SERVICES(32);
BOOT_SERVICES(64);
@@ -286,29 +275,6 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
}
}
-static void find_bits(unsigned long mask, u8 *pos, u8 *size)
-{
- u8 first, len;
-
- first = 0;
- len = 0;
-
- if (mask) {
- while (!(mask & 0x1)) {
- mask = mask >> 1;
- first++;
- }
-
- while (mask & 0x1) {
- mask = mask >> 1;
- len++;
- }
- }
-
- *pos = first;
- *size = len;
-}
-
static efi_status_t
__setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
{
@@ -578,7 +544,7 @@ setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
unsigned long nr_ugas;
u32 *handles = (u32 *)uga_handle;;
- efi_status_t status;
+ efi_status_t status = EFI_INVALID_PARAMETER;
int i;
first_uga = NULL;
@@ -623,7 +589,7 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
unsigned long nr_ugas;
u64 *handles = (u64 *)uga_handle;;
- efi_status_t status;
+ efi_status_t status = EFI_INVALID_PARAMETER;
int i;
first_uga = NULL;
@@ -1004,79 +970,87 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
return status;
}
-static efi_status_t exit_boot(struct boot_params *boot_params,
- void *handle, bool is64)
-{
- struct efi_info *efi = &boot_params->efi_info;
- unsigned long map_sz, key, desc_size;
- efi_memory_desc_t *mem_map;
+struct exit_boot_struct {
+ struct boot_params *boot_params;
+ struct efi_info *efi;
struct setup_data *e820ext;
- const char *signature;
__u32 e820ext_size;
- __u32 nr_desc, prev_nr_desc;
- efi_status_t status;
- __u32 desc_version;
- bool called_exit = false;
- u8 nr_entries;
- int i;
-
- nr_desc = 0;
- e820ext = NULL;
- e820ext_size = 0;
-
-get_map:
- status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
- &desc_version, &key);
-
- if (status != EFI_SUCCESS)
- return status;
-
- prev_nr_desc = nr_desc;
- nr_desc = map_sz / desc_size;
- if (nr_desc > prev_nr_desc &&
- nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
- u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
-
- status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
- if (status != EFI_SUCCESS)
- goto free_mem_map;
+ bool is64;
+};
- efi_call_early(free_pool, mem_map);
- goto get_map; /* Allocated memory, get map again */
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv)
+{
+ static bool first = true;
+ const char *signature;
+ __u32 nr_desc;
+ efi_status_t status;
+ struct exit_boot_struct *p = priv;
+
+ if (first) {
+ nr_desc = *map->buff_size / *map->desc_size;
+ if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+ u32 nr_e820ext = nr_desc -
+ ARRAY_SIZE(p->boot_params->e820_map);
+
+ status = alloc_e820ext(nr_e820ext, &p->e820ext,
+ &p->e820ext_size);
+ if (status != EFI_SUCCESS)
+ return status;
+ }
+ first = false;
}
- signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
- memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
+ signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+ memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
- efi->efi_systab = (unsigned long)sys_table;
- efi->efi_memdesc_size = desc_size;
- efi->efi_memdesc_version = desc_version;
- efi->efi_memmap = (unsigned long)mem_map;
- efi->efi_memmap_size = map_sz;
+ p->efi->efi_systab = (unsigned long)sys_table_arg;
+ p->efi->efi_memdesc_size = *map->desc_size;
+ p->efi->efi_memdesc_version = *map->desc_ver;
+ p->efi->efi_memmap = (unsigned long)*map->map;
+ p->efi->efi_memmap_size = *map->map_size;
#ifdef CONFIG_X86_64
- efi->efi_systab_hi = (unsigned long)sys_table >> 32;
- efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+ p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
+ p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
#endif
+ return EFI_SUCCESS;
+}
+
+static efi_status_t exit_boot(struct boot_params *boot_params,
+ void *handle, bool is64)
+{
+ unsigned long map_sz, key, desc_size, buff_size;
+ efi_memory_desc_t *mem_map;
+ struct setup_data *e820ext;
+ __u32 e820ext_size;
+ efi_status_t status;
+ __u32 desc_version;
+ struct efi_boot_memmap map;
+ struct exit_boot_struct priv;
+
+ map.map = &mem_map;
+ map.map_size = &map_sz;
+ map.desc_size = &desc_size;
+ map.desc_ver = &desc_version;
+ map.key_ptr = &key;
+ map.buff_size = &buff_size;
+ priv.boot_params = boot_params;
+ priv.efi = &boot_params->efi_info;
+ priv.e820ext = NULL;
+ priv.e820ext_size = 0;
+ priv.is64 = is64;
+
/* Might as well exit boot services now */
- status = efi_call_early(exit_boot_services, handle, key);
- if (status != EFI_SUCCESS) {
- /*
- * ExitBootServices() will fail if any of the event
- * handlers change the memory map. In which case, we
- * must be prepared to retry, but only once so that
- * we're guaranteed to exit on repeated failures instead
- * of spinning forever.
- */
- if (called_exit)
- goto free_mem_map;
-
- called_exit = true;
- efi_call_early(free_pool, mem_map);
- goto get_map;
- }
+ status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+ exit_boot_func);
+ if (status != EFI_SUCCESS)
+ return status;
+ e820ext = priv.e820ext;
+ e820ext_size = priv.e820ext_size;
/* Historic? */
boot_params->alt_mem_k = 32 * 1024;
@@ -1085,10 +1059,6 @@ get_map:
return status;
return EFI_SUCCESS;
-
-free_mem_map:
- efi_call_early(free_pool, mem_map);
- return status;
}
/*
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 1038524270e7..fd0b6a272dd5 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -82,7 +82,7 @@ ENTRY(efi_pe_entry)
/* Relocate efi_config->call() */
leal efi32_config(%esi), %eax
- add %esi, 88(%eax)
+ add %esi, 32(%eax)
pushl %eax
call make_boot_params
@@ -108,7 +108,7 @@ ENTRY(efi32_stub_entry)
/* Relocate efi_config->call() */
leal efi32_config(%esi), %eax
- add %esi, 88(%eax)
+ add %esi, 32(%eax)
pushl %eax
2:
call efi_main
@@ -264,7 +264,7 @@ relocated:
#ifdef CONFIG_EFI_STUB
.data
efi32_config:
- .fill 11,8,0
+ .fill 4,8,0
.long efi_call_phys
.long 0
.byte 0
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 0d80a7ad65cd..efdfba21a5b2 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -265,7 +265,7 @@ ENTRY(efi_pe_entry)
/*
* Relocate efi_config->call().
*/
- addq %rbp, efi64_config+88(%rip)
+ addq %rbp, efi64_config+32(%rip)
movq %rax, %rdi
call make_boot_params
@@ -285,7 +285,7 @@ handover_entry:
* Relocate efi_config->call().
*/
movq efi_config(%rip), %rax
- addq %rbp, 88(%rax)
+ addq %rbp, 32(%rax)
2:
movq efi_config(%rip), %rdi
call efi_main
@@ -457,14 +457,14 @@ efi_config:
#ifdef CONFIG_EFI_MIXED
.global efi32_config
efi32_config:
- .fill 11,8,0
+ .fill 4,8,0
.quad efi64_thunk
.byte 0
#endif
.global efi64_config
efi64_config:
- .fill 11,8,0
+ .fill 4,8,0
.quad efi_call
.byte 1
#endif /* CONFIG_EFI_STUB */
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 1433f6b4607d..bdd9cc59d20f 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -31,13 +31,6 @@
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
-static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
-{
- unsigned long top_of_stack =
- (unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING;
- return (struct thread_info *)(top_of_stack - THREAD_SIZE);
-}
-
#ifdef CONFIG_CONTEXT_TRACKING
/* Called on entry from user mode with IRQs off. */
__visible inline void enter_from_user_mode(void)
@@ -71,7 +64,7 @@ static long syscall_trace_enter(struct pt_regs *regs)
{
u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
- struct thread_info *ti = pt_regs_to_thread_info(regs);
+ struct thread_info *ti = current_thread_info();
unsigned long ret = 0;
bool emulated = false;
u32 work;
@@ -173,18 +166,17 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
/* Disable IRQs and retry */
local_irq_disable();
- cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+ cached_flags = READ_ONCE(current_thread_info()->flags);
if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
break;
-
}
}
/* Called with IRQs disabled. */
__visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
{
- struct thread_info *ti = pt_regs_to_thread_info(regs);
+ struct thread_info *ti = current_thread_info();
u32 cached_flags;
if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
@@ -209,7 +201,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
* special case only applies after poking regs and before the
* very next return to user mode.
*/
- ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
+ current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
#endif
user_enter_irqoff();
@@ -247,7 +239,7 @@ static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags)
*/
__visible inline void syscall_return_slowpath(struct pt_regs *regs)
{
- struct thread_info *ti = pt_regs_to_thread_info(regs);
+ struct thread_info *ti = current_thread_info();
u32 cached_flags = READ_ONCE(ti->flags);
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
@@ -270,7 +262,7 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
#ifdef CONFIG_X86_64
__visible void do_syscall_64(struct pt_regs *regs)
{
- struct thread_info *ti = pt_regs_to_thread_info(regs);
+ struct thread_info *ti = current_thread_info();
unsigned long nr = regs->orig_ax;
enter_from_user_mode();
@@ -303,11 +295,11 @@ __visible void do_syscall_64(struct pt_regs *regs)
*/
static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
{
- struct thread_info *ti = pt_regs_to_thread_info(regs);
+ struct thread_info *ti = current_thread_info();
unsigned int nr = (unsigned int)regs->orig_ax;
#ifdef CONFIG_IA32_EMULATION
- ti->status |= TS_COMPAT;
+ current->thread.status |= TS_COMPAT;
#endif
if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) {
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 0b56666e6039..b75a8bcd2d23 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -204,34 +204,70 @@
POP_GS_EX
.endm
+/*
+ * %eax: prev task
+ * %edx: next task
+ */
+ENTRY(__switch_to_asm)
+ /*
+ * Save callee-saved registers
+ * This must match the order in struct inactive_task_frame
+ */
+ pushl %ebp
+ pushl %ebx
+ pushl %edi
+ pushl %esi
+
+ /* switch stack */
+ movl %esp, TASK_threadsp(%eax)
+ movl TASK_threadsp(%edx), %esp
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+ movl TASK_stack_canary(%edx), %ebx
+ movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
+#endif
+
+ /* restore callee-saved registers */
+ popl %esi
+ popl %edi
+ popl %ebx
+ popl %ebp
+
+ jmp __switch_to
+END(__switch_to_asm)
+
+/*
+ * A newly forked process directly context switches into this address.
+ *
+ * eax: prev task we switched from
+ * ebx: kernel thread func (NULL for user thread)
+ * edi: kernel thread arg
+ */
ENTRY(ret_from_fork)
pushl %eax
call schedule_tail
popl %eax
+ testl %ebx, %ebx
+ jnz 1f /* kernel threads are uncommon */
+
+2:
/* When we fork, we trace the syscall return in the child, too. */
movl %esp, %eax
call syscall_return_slowpath
jmp restore_all
-END(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
- pushl %eax
- call schedule_tail
- popl %eax
- movl PT_EBP(%esp), %eax
- call *PT_EBX(%esp)
- movl $0, PT_EAX(%esp)
+ /* kernel thread */
+1: movl %edi, %eax
+ call *%ebx
/*
- * Kernel threads return to userspace as if returning from a syscall.
- * We should check whether anything actually uses this path and, if so,
- * consider switching it over to ret_from_fork.
+ * A kernel thread is allowed to return here after successfully
+ * calling do_execve(). Exit to userspace to complete the execve()
+ * syscall.
*/
- movl %esp, %eax
- call syscall_return_slowpath
- jmp restore_all
-ENDPROC(ret_from_kernel_thread)
+ movl $0, PT_EAX(%esp)
+ jmp 2b
+END(ret_from_fork)
/*
* Return to user mode is not as complex as all this looks,
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d172c619c449..fee1d95902b5 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -179,7 +179,8 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
* If we need to do entry work or if we guess we'll need to do
* exit work, go straight to the slow path.
*/
- testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ movq PER_CPU_VAR(current_task), %r11
+ testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
jnz entry_SYSCALL64_slow_path
entry_SYSCALL_64_fastpath:
@@ -217,7 +218,8 @@ entry_SYSCALL_64_fastpath:
*/
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ movq PER_CPU_VAR(current_task), %r11
+ testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
jnz 1f
LOCKDEP_SYS_EXIT
@@ -351,8 +353,7 @@ ENTRY(stub_ptregs_64)
jmp entry_SYSCALL64_slow_path
1:
- /* Called from C */
- jmp *%rax /* called from C */
+ jmp *%rax /* Called from C */
END(stub_ptregs_64)
.macro ptregs_stub func
@@ -369,41 +370,73 @@ END(ptregs_\func)
#include <asm/syscalls_64.h>
/*
+ * %rdi: prev task
+ * %rsi: next task
+ */
+ENTRY(__switch_to_asm)
+ /*
+ * Save callee-saved registers
+ * This must match the order in inactive_task_frame
+ */
+ pushq %rbp
+ pushq %rbx
+ pushq %r12
+ pushq %r13
+ pushq %r14
+ pushq %r15
+
+ /* switch stack */
+ movq %rsp, TASK_threadsp(%rdi)
+ movq TASK_threadsp(%rsi), %rsp
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+ movq TASK_stack_canary(%rsi), %rbx
+ movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
+#endif
+
+ /* restore callee-saved registers */
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbx
+ popq %rbp
+
+ jmp __switch_to
+END(__switch_to_asm)
+
+/*
* A newly forked process directly context switches into this address.
*
- * rdi: prev task we switched from
+ * rax: prev task we switched from
+ * rbx: kernel thread func (NULL for user thread)
+ * r12: kernel thread arg
*/
ENTRY(ret_from_fork)
- LOCK ; btr $TIF_FORK, TI_flags(%r8)
-
+ movq %rax, %rdi
call schedule_tail /* rdi: 'prev' task parameter */
- testb $3, CS(%rsp) /* from kernel_thread? */
- jnz 1f
-
- /*
- * We came from kernel_thread. This code path is quite twisted, and
- * someone should clean it up.
- *
- * copy_thread_tls stashes the function pointer in RBX and the
- * parameter to be passed in RBP. The called function is permitted
- * to call do_execve and thereby jump to user mode.
- */
- movq RBP(%rsp), %rdi
- call *RBX(%rsp)
- movl $0, RAX(%rsp)
+ testq %rbx, %rbx /* from kernel_thread? */
+ jnz 1f /* kernel threads are uncommon */
- /*
- * Fall through as though we're exiting a syscall. This makes a
- * twisted sort of sense if we just called do_execve.
- */
-
-1:
+2:
movq %rsp, %rdi
call syscall_return_slowpath /* returns with IRQs disabled */
TRACE_IRQS_ON /* user mode is traced as IRQS on */
SWAPGS
jmp restore_regs_and_iret
+
+1:
+ /* kernel thread */
+ movq %r12, %rdi
+ call *%rbx
+ /*
+ * A kernel thread is allowed to return here after successfully
+ * calling do_execve(). Exit to userspace to complete the execve()
+ * syscall.
+ */
+ movq $0, RAX(%rsp)
+ jmp 2b
END(ret_from_fork)
/*
@@ -555,27 +588,69 @@ native_irq_return_iret:
#ifdef CONFIG_X86_ESPFIX64
native_irq_return_ldt:
- pushq %rax
- pushq %rdi
+ /*
+ * We are running with user GSBASE. All GPRs contain their user
+ * values. We have a percpu ESPFIX stack that is eight slots
+ * long (see ESPFIX_STACK_SIZE). espfix_waddr points to the bottom
+ * of the ESPFIX stack.
+ *
+ * We clobber RAX and RDI in this code. We stash RDI on the
+ * normal stack and RAX on the ESPFIX stack.
+ *
+ * The ESPFIX stack layout we set up looks like this:
+ *
+ * --- top of ESPFIX stack ---
+ * SS
+ * RSP
+ * RFLAGS
+ * CS
+ * RIP <-- RSP points here when we're done
+ * RAX <-- espfix_waddr points here
+ * --- bottom of ESPFIX stack ---
+ */
+
+ pushq %rdi /* Stash user RDI */
SWAPGS
movq PER_CPU_VAR(espfix_waddr), %rdi
- movq %rax, (0*8)(%rdi) /* RAX */
- movq (2*8)(%rsp), %rax /* RIP */
+ movq %rax, (0*8)(%rdi) /* user RAX */
+ movq (1*8)(%rsp), %rax /* user RIP */
movq %rax, (1*8)(%rdi)
- movq (3*8)(%rsp), %rax /* CS */
+ movq (2*8)(%rsp), %rax /* user CS */
movq %rax, (2*8)(%rdi)
- movq (4*8)(%rsp), %rax /* RFLAGS */
+ movq (3*8)(%rsp), %rax /* user RFLAGS */
movq %rax, (3*8)(%rdi)
- movq (6*8)(%rsp), %rax /* SS */
+ movq (5*8)(%rsp), %rax /* user SS */
movq %rax, (5*8)(%rdi)
- movq (5*8)(%rsp), %rax /* RSP */
+ movq (4*8)(%rsp), %rax /* user RSP */
movq %rax, (4*8)(%rdi)
- andl $0xffff0000, %eax
- popq %rdi
+ /* 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
+ * (espfix_stack | (X & 0xffff0000)) points to a read-only alias of
+ * espfix_waddr for any X. That is, there are 65536 RO aliases of
+ * the same page. Set up RSP so that RSP[31:16] contains the
+ * respective 16 bits of the /userspace/ RSP and RSP nonetheless
+ * still points to an RO alias of the ESPFIX stack.
+ */
orq PER_CPU_VAR(espfix_stack), %rax
SWAPGS
movq %rax, %rsp
- popq %rax
+
+ /*
+ * At this point, we cannot write to the stack any more, but we can
+ * still read.
+ */
+ popq %rax /* Restore user RAX */
+
+ /*
+ * RSP now points to an ordinary IRET frame, except that the page
+ * is read-only and RSP[31:16] are preloaded with the userspace
+ * values. We can now IRET back to userspace.
+ */
jmp native_irq_return_iret
#endif
END(common_interrupt)
@@ -1002,7 +1077,6 @@ ENTRY(error_entry)
testb $3, CS+8(%rsp)
jz .Lerror_kernelspace
-.Lerror_entry_from_usermode_swapgs:
/*
* We entered from user mode or we're pretending to have entered
* from user mode due to an IRET fault.
@@ -1045,7 +1119,8 @@ ENTRY(error_entry)
* gsbase and proceed. We'll fix up the exception and land in
* .Lgs_change's error handler with kernel gsbase.
*/
- jmp .Lerror_entry_from_usermode_swapgs
+ SWAPGS
+ jmp .Lerror_entry_done
.Lbstep_iret:
/* Fix truncated RIP */
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 4f741192846d..3dab75f2a673 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -22,7 +22,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff));
- if (hdr->e_type != ET_DYN)
+ if (GET_LE(&hdr->e_type) != ET_DYN)
fail("input is not a shared object\n");
/* Walk the segment table. */
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index f840766659a8..23c881caabd1 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -37,54 +37,6 @@ void __init init_vdso_image(const struct vdso_image *image)
struct linux_binprm;
-/*
- * Put the vdso above the (randomized) stack with another randomized
- * offset. This way there is no hole in the middle of address space.
- * To save memory make sure it is still in the same PTE as the stack
- * top. This doesn't give that many random bits.
- *
- * Note that this algorithm is imperfect: the distribution of the vdso
- * start address within a PMD is biased toward the end.
- *
- * Only used for the 64-bit and x32 vdsos.
- */
-static unsigned long vdso_addr(unsigned long start, unsigned len)
-{
-#ifdef CONFIG_X86_32
- return 0;
-#else
- unsigned long addr, end;
- unsigned offset;
-
- /*
- * Round up the start address. It can start out unaligned as a result
- * of stack start randomization.
- */
- start = PAGE_ALIGN(start);
-
- /* Round the lowest possible end address up to a PMD boundary. */
- end = (start + len + PMD_SIZE - 1) & PMD_MASK;
- if (end >= TASK_SIZE_MAX)
- end = TASK_SIZE_MAX;
- end -= len;
-
- if (end > start) {
- offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
- addr = start + (offset << PAGE_SHIFT);
- } else {
- addr = start;
- }
-
- /*
- * Forcibly align the final address in case we have a hardware
- * issue that requires alignment for performance reasons.
- */
- addr = align_vdso_addr(addr);
-
- return addr;
-#endif
-}
-
static int vdso_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
@@ -176,30 +128,28 @@ static int vvar_fault(const struct vm_special_mapping *sm,
return VM_FAULT_SIGBUS;
}
-static int map_vdso(const struct vdso_image *image, bool calculate_addr)
+static const struct vm_special_mapping vdso_mapping = {
+ .name = "[vdso]",
+ .fault = vdso_fault,
+ .mremap = vdso_mremap,
+};
+static const struct vm_special_mapping vvar_mapping = {
+ .name = "[vvar]",
+ .fault = vvar_fault,
+};
+
+/*
+ * Add vdso and vvar mappings to current process.
+ * @image - blob to map
+ * @addr - request a specific address (zero to map at free addr)
+ */
+static int map_vdso(const struct vdso_image *image, unsigned long addr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- unsigned long addr, text_start;
+ unsigned long text_start;
int ret = 0;
- static const struct vm_special_mapping vdso_mapping = {
- .name = "[vdso]",
- .fault = vdso_fault,
- .mremap = vdso_mremap,
- };
- static const struct vm_special_mapping vvar_mapping = {
- .name = "[vvar]",
- .fault = vvar_fault,
- };
-
- if (calculate_addr) {
- addr = vdso_addr(current->mm->start_stack,
- image->size - image->sym_vvar_start);
- } else {
- addr = 0;
- }
-
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
@@ -238,24 +188,104 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
- goto up_fail;
+ do_munmap(mm, text_start, image->size);
}
up_fail:
- if (ret)
+ if (ret) {
current->mm->context.vdso = NULL;
+ current->mm->context.vdso_image = NULL;
+ }
up_write(&mm->mmap_sem);
return ret;
}
+#ifdef CONFIG_X86_64
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset. This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top. This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
+static unsigned long vdso_addr(unsigned long start, unsigned len)
+{
+ unsigned long addr, end;
+ unsigned offset;
+
+ /*
+ * Round up the start address. It can start out unaligned as a result
+ * of stack start randomization.
+ */
+ start = PAGE_ALIGN(start);
+
+ /* Round the lowest possible end address up to a PMD boundary. */
+ end = (start + len + PMD_SIZE - 1) & PMD_MASK;
+ if (end >= TASK_SIZE_MAX)
+ end = TASK_SIZE_MAX;
+ end -= len;
+
+ if (end > start) {
+ offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+ addr = start + (offset << PAGE_SHIFT);
+ } else {
+ addr = start;
+ }
+
+ /*
+ * Forcibly align the final address in case we have a hardware
+ * issue that requires alignment for performance reasons.
+ */
+ addr = align_vdso_addr(addr);
+
+ return addr;
+}
+
+static int map_vdso_randomized(const struct vdso_image *image)
+{
+ unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start);
+
+ return map_vdso(image, addr);
+}
+#endif
+
+int map_vdso_once(const struct vdso_image *image, unsigned long addr)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+
+ down_write(&mm->mmap_sem);
+ /*
+ * Check if we have already mapped vdso blob - fail to prevent
+ * abusing from userspace install_speciall_mapping, which may
+ * not do accounting and rlimit right.
+ * We could search vma near context.vdso, but it's a slowpath,
+ * so let's explicitely check all VMAs to be completely sure.
+ */
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (vma_is_special_mapping(vma, &vdso_mapping) ||
+ vma_is_special_mapping(vma, &vvar_mapping)) {
+ up_write(&mm->mmap_sem);
+ return -EEXIST;
+ }
+ }
+ up_write(&mm->mmap_sem);
+
+ return map_vdso(image, addr);
+}
+
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
static int load_vdso32(void)
{
if (vdso32_enabled != 1) /* Other values all mean "disabled" */
return 0;
- return map_vdso(&vdso_image_32, false);
+ return map_vdso(&vdso_image_32, 0);
}
#endif
@@ -265,7 +295,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
if (!vdso64_enabled)
return 0;
- return map_vdso(&vdso_image_64, true);
+ return map_vdso_randomized(&vdso_image_64);
}
#ifdef CONFIG_COMPAT
@@ -276,8 +306,7 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
if (test_thread_flag(TIF_X32)) {
if (!vdso64_enabled)
return 0;
-
- return map_vdso(&vdso_image_x32, true);
+ return map_vdso_randomized(&vdso_image_x32);
}
#endif
#ifdef CONFIG_IA32_EMULATION
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index e07a22bb9308..f5f4b3fbbbc2 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -119,8 +119,8 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
{
[PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
[PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index e6131d4454e6..65577f081d07 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -29,6 +29,8 @@
#define COUNTER_SHIFT 16
+static HLIST_HEAD(uncore_unused_list);
+
struct amd_uncore {
int id;
int refcnt;
@@ -39,7 +41,7 @@ struct amd_uncore {
cpumask_t *active_mask;
struct pmu *pmu;
struct perf_event *events[MAX_COUNTERS];
- struct amd_uncore *free_when_cpu_online;
+ struct hlist_node node;
};
static struct amd_uncore * __percpu *amd_uncore_nb;
@@ -306,6 +308,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
uncore_nb->pmu = &amd_nb_pmu;
+ uncore_nb->id = -1;
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
@@ -319,6 +322,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
uncore_l2->active_mask = &amd_l2_active_mask;
uncore_l2->pmu = &amd_l2_pmu;
+ uncore_l2->id = -1;
*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
}
@@ -348,7 +352,7 @@ amd_uncore_find_online_sibling(struct amd_uncore *this,
continue;
if (this->id == that->id) {
- that->free_when_cpu_online = this;
+ hlist_add_head(&this->node, &uncore_unused_list);
this = that;
break;
}
@@ -388,13 +392,23 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
return 0;
}
+static void uncore_clean_online(void)
+{
+ struct amd_uncore *uncore;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
+ hlist_del(&uncore->node);
+ kfree(uncore);
+ }
+}
+
static void uncore_online(unsigned int cpu,
struct amd_uncore * __percpu *uncores)
{
struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
- kfree(uncore->free_when_cpu_online);
- uncore->free_when_cpu_online = NULL;
+ uncore_clean_online();
if (cpu == uncore->cpu)
cpumask_set_cpu(cpu, uncore->active_mask);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d0efb5cb1b00..d31735f37ed7 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -37,6 +37,7 @@
#include <asm/timer.h>
#include <asm/desc.h>
#include <asm/ldt.h>
+#include <asm/unwind.h>
#include "perf_event.h"
@@ -1201,6 +1202,9 @@ static int x86_pmu_add(struct perf_event *event, int flags)
* If group events scheduling transaction was started,
* skip the schedulability test here, it will be performed
* at commit time (->commit_txn) as a whole.
+ *
+ * If commit fails, we'll call ->del() on all events
+ * for which ->add() was called.
*/
if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
goto done_collect;
@@ -1223,6 +1227,14 @@ done_collect:
cpuc->n_added += n - n0;
cpuc->n_txn += n - n0;
+ if (x86_pmu.add) {
+ /*
+ * This is before x86_pmu_enable() will call x86_pmu_start(),
+ * so we enable LBRs before an event needs them etc..
+ */
+ x86_pmu.add(event);
+ }
+
ret = 0;
out:
return ret;
@@ -1346,7 +1358,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
/*
- * If we're called during a txn, we don't need to do anything.
+ * If we're called during a txn, we only need to undo x86_pmu.add.
* The events never got scheduled and ->cancel_txn will truncate
* the event_list.
*
@@ -1354,7 +1366,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
* an event added during that same TXN.
*/
if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
- return;
+ goto do_del;
/*
* Not a TXN, therefore cleanup properly.
@@ -1384,6 +1396,15 @@ static void x86_pmu_del(struct perf_event *event, int flags)
--cpuc->n_events;
perf_event_update_userpage(event);
+
+do_del:
+ if (x86_pmu.del) {
+ /*
+ * This is after x86_pmu_stop(); so we disable LBRs after any
+ * event can need them etc..
+ */
+ x86_pmu.del(event);
+ }
}
int x86_pmu_handle_irq(struct pt_regs *regs)
@@ -2247,39 +2268,26 @@ void arch_perf_update_userpage(struct perf_event *event,
cyc2ns_read_end(data);
}
-/*
- * callchain support
- */
-
-static int backtrace_stack(void *data, char *name)
-{
- return 0;
-}
-
-static int backtrace_address(void *data, unsigned long addr, int reliable)
-{
- struct perf_callchain_entry_ctx *entry = data;
-
- return perf_callchain_store(entry, addr);
-}
-
-static const struct stacktrace_ops backtrace_ops = {
- .stack = backtrace_stack,
- .address = backtrace_address,
- .walk_stack = print_context_stack_bp,
-};
-
void
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
+ struct unwind_state state;
+ unsigned long addr;
+
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
/* TODO: We don't support guest os callchain now */
return;
}
- perf_callchain_store(entry, regs->ip);
+ if (perf_callchain_store(entry, regs->ip))
+ return;
- dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
+ for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
+ unwind_next_frame(&state)) {
+ addr = unwind_get_return_address(&state);
+ if (!addr || perf_callchain_store(entry, addr))
+ return;
+ }
}
static inline int
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 0a6e393a2e62..982c9e31daca 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -31,7 +31,17 @@
struct bts_ctx {
struct perf_output_handle handle;
struct debug_store ds_back;
- int started;
+ int state;
+};
+
+/* BTS context states: */
+enum {
+ /* no ongoing AUX transactions */
+ BTS_STATE_STOPPED = 0,
+ /* AUX transaction is on, BTS tracing is disabled */
+ BTS_STATE_INACTIVE,
+ /* AUX transaction is on, BTS tracing is running */
+ BTS_STATE_ACTIVE,
};
static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
@@ -204,6 +214,15 @@ static void bts_update(struct bts_ctx *bts)
static int
bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+/*
+ * Ordering PMU callbacks wrt themselves and the PMI is done by means
+ * of bts::state, which:
+ * - is set when bts::handle::event is valid, that is, between
+ * perf_aux_output_begin() and perf_aux_output_end();
+ * - is zero otherwise;
+ * - is ordered against bts::handle::event with a compiler barrier.
+ */
+
static void __bts_event_start(struct perf_event *event)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
@@ -221,10 +240,13 @@ static void __bts_event_start(struct perf_event *event)
/*
* local barrier to make sure that ds configuration made it
- * before we enable BTS
+ * before we enable BTS and bts::state goes ACTIVE
*/
wmb();
+ /* INACTIVE/STOPPED -> ACTIVE */
+ WRITE_ONCE(bts->state, BTS_STATE_ACTIVE);
+
intel_pmu_enable_bts(config);
}
@@ -251,9 +273,6 @@ static void bts_event_start(struct perf_event *event, int flags)
__bts_event_start(event);
- /* PMI handler: this counter is running and likely generating PMIs */
- ACCESS_ONCE(bts->started) = 1;
-
return;
fail_end_stop:
@@ -263,30 +282,34 @@ fail_stop:
event->hw.state = PERF_HES_STOPPED;
}
-static void __bts_event_stop(struct perf_event *event)
+static void __bts_event_stop(struct perf_event *event, int state)
{
+ struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+
+ /* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
+ WRITE_ONCE(bts->state, state);
+
/*
* No extra synchronization is mandated by the documentation to have
* BTS data stores globally visible.
*/
intel_pmu_disable_bts();
-
- if (event->hw.state & PERF_HES_STOPPED)
- return;
-
- ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED;
}
static void bts_event_stop(struct perf_event *event, int flags)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
- struct bts_buffer *buf = perf_get_aux(&bts->handle);
+ struct bts_buffer *buf = NULL;
+ int state = READ_ONCE(bts->state);
- /* PMI handler: don't restart this counter */
- ACCESS_ONCE(bts->started) = 0;
+ if (state == BTS_STATE_ACTIVE)
+ __bts_event_stop(event, BTS_STATE_STOPPED);
- __bts_event_stop(event);
+ if (state != BTS_STATE_STOPPED)
+ buf = perf_get_aux(&bts->handle);
+
+ event->hw.state |= PERF_HES_STOPPED;
if (flags & PERF_EF_UPDATE) {
bts_update(bts);
@@ -296,6 +319,7 @@ static void bts_event_stop(struct perf_event *event, int flags)
bts->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
+
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
}
@@ -310,8 +334,20 @@ static void bts_event_stop(struct perf_event *event, int flags)
void intel_bts_enable_local(void)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+ int state = READ_ONCE(bts->state);
+
+ /*
+ * Here we transition from INACTIVE to ACTIVE;
+ * if we instead are STOPPED from the interrupt handler,
+ * stay that way. Can't be ACTIVE here though.
+ */
+ if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE))
+ return;
+
+ if (state == BTS_STATE_STOPPED)
+ return;
- if (bts->handle.event && bts->started)
+ if (bts->handle.event)
__bts_event_start(bts->handle.event);
}
@@ -319,8 +355,15 @@ void intel_bts_disable_local(void)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+ /*
+ * Here we transition from ACTIVE to INACTIVE;
+ * do nothing for STOPPED or INACTIVE.
+ */
+ if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE)
+ return;
+
if (bts->handle.event)
- __bts_event_stop(bts->handle.event);
+ __bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE);
}
static int
@@ -335,8 +378,6 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
return 0;
head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
- if (WARN_ON_ONCE(head != local_read(&buf->head)))
- return -EINVAL;
phys = &buf->buf[buf->cur_buf];
space = phys->offset + phys->displacement + phys->size - head;
@@ -403,22 +444,37 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
int intel_bts_interrupt(void)
{
+ struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
struct perf_event *event = bts->handle.event;
struct bts_buffer *buf;
s64 old_head;
- int err;
+ int err = -ENOSPC, handled = 0;
- if (!event || !bts->started)
- return 0;
+ /*
+ * The only surefire way of knowing if this NMI is ours is by checking
+ * the write ptr against the PMI threshold.
+ */
+ if (ds && (ds->bts_index >= ds->bts_interrupt_threshold))
+ handled = 1;
+
+ /*
+ * this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
+ * so we can only be INACTIVE or STOPPED
+ */
+ if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
+ return handled;
buf = perf_get_aux(&bts->handle);
+ if (!buf)
+ return handled;
+
/*
* Skip snapshot counters: they don't use the interrupt, but
* there's no other way of telling, because the pointer will
* keep moving
*/
- if (!buf || buf->snapshot)
+ if (buf->snapshot)
return 0;
old_head = local_read(&buf->head);
@@ -426,18 +482,27 @@ int intel_bts_interrupt(void)
/* no new data */
if (old_head == local_read(&buf->head))
- return 0;
+ return handled;
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
buf = perf_aux_output_begin(&bts->handle, event);
- if (!buf)
- return 1;
+ if (buf)
+ err = bts_buffer_reset(buf, &bts->handle);
+
+ if (err) {
+ WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
- err = bts_buffer_reset(buf, &bts->handle);
- if (err)
- perf_aux_output_end(&bts->handle, 0, false);
+ if (buf) {
+ /*
+ * BTS_STATE_STOPPED should be visible before
+ * cleared handle::event
+ */
+ barrier();
+ perf_aux_output_end(&bts->handle, 0, false);
+ }
+ }
return 1;
}
@@ -519,7 +584,8 @@ static __init int bts_init(void)
if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
return -ENODEV;
- bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE;
+ 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;
bts_pmu.event_init = bts_event_init;
bts_pmu.add = bts_event_add;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2cbde2f449aa..a3a9eb84b5cf 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1730,9 +1730,11 @@ static __initconst const u64 knl_hw_cache_extra_regs
* disabled state if called consecutively.
*
* During consecutive calls, the same disable value will be written to related
- * registers, so the PMU state remains unchanged. hw.state in
- * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
- * calls.
+ * registers, so the PMU state remains unchanged.
+ *
+ * intel_bts events don't coexist with intel PMU's BTS events because of
+ * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
+ * disabled around intel PMU's event batching etc, only inside the PMI handler.
*/
static void __intel_pmu_disable_all(void)
{
@@ -1742,8 +1744,6 @@ static void __intel_pmu_disable_all(void)
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
- else
- intel_bts_disable_local();
intel_pmu_pebs_disable_all();
}
@@ -1771,8 +1771,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
return;
intel_pmu_enable_bts(event->hw.config);
- } else
- intel_bts_enable_local();
+ }
}
static void intel_pmu_enable_all(int added)
@@ -1907,13 +1906,6 @@ static void intel_pmu_disable_event(struct perf_event *event)
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
cpuc->intel_cp_status &= ~(1ull << hwc->idx);
- /*
- * must disable before any actual event
- * because any event may be combined with LBR
- */
- if (needs_branch_stack(event))
- intel_pmu_lbr_disable(event);
-
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
@@ -1925,6 +1917,14 @@ static void intel_pmu_disable_event(struct perf_event *event)
intel_pmu_pebs_disable(event);
}
+static void intel_pmu_del_event(struct perf_event *event)
+{
+ if (needs_branch_stack(event))
+ intel_pmu_lbr_del(event);
+ if (event->attr.precise_ip)
+ intel_pmu_pebs_del(event);
+}
+
static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
{
int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
@@ -1968,12 +1968,6 @@ static void intel_pmu_enable_event(struct perf_event *event)
intel_pmu_enable_bts(hwc->config);
return;
}
- /*
- * must enabled before any actual event
- * because any event may be combined with LBR
- */
- if (needs_branch_stack(event))
- intel_pmu_lbr_enable(event);
if (event->attr.exclude_host)
cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@@ -1994,6 +1988,14 @@ static void intel_pmu_enable_event(struct perf_event *event)
__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
+static void intel_pmu_add_event(struct perf_event *event)
+{
+ if (event->attr.precise_ip)
+ intel_pmu_pebs_add(event);
+ if (needs_branch_stack(event))
+ intel_pmu_lbr_add(event);
+}
+
/*
* Save and restart an expired event. Called by NMI contexts,
* so it has to be careful about preempting normal event ops:
@@ -2073,6 +2075,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
*/
if (!x86_pmu.late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
+ intel_bts_disable_local();
__intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
handled += intel_bts_interrupt();
@@ -2172,6 +2175,7 @@ done:
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
if (cpuc->enabled)
__intel_pmu_enable_all(0, true);
+ intel_bts_enable_local();
/*
* Only unmask the NMI after the overflow counters
@@ -3290,6 +3294,8 @@ static __initconst const struct x86_pmu intel_pmu = {
.enable_all = intel_pmu_enable_all,
.enable = intel_pmu_enable_event,
.disable = intel_pmu_disable_event,
+ .add = intel_pmu_add_event,
+ .del = intel_pmu_del_event,
.hw_config = intel_pmu_hw_config,
.schedule_events = x86_schedule_events,
.eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 783c49ddef29..8f82b02934fa 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -458,6 +458,11 @@ static void __intel_cqm_event_count(void *info);
static void init_mbm_sample(u32 rmid, u32 evt_type);
static void __intel_mbm_event_count(void *info);
+static bool is_cqm_event(int e)
+{
+ return (e == QOS_L3_OCCUP_EVENT_ID);
+}
+
static bool is_mbm_event(int e)
{
return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
@@ -1366,6 +1371,10 @@ static int intel_cqm_event_init(struct perf_event *event)
(event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
return -EINVAL;
+ if ((is_cqm_event(event->attr.config) && !cqm_enabled) ||
+ (is_mbm_event(event->attr.config) && !mbm_enabled))
+ return -EINVAL;
+
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ce9f3f669e6..0319311dbdbb 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -806,9 +806,65 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
return &emptyconstraint;
}
-static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+/*
+ * We need the sched_task callback even for per-cpu events when we use
+ * the large interrupt threshold, such that we can provide PID and TID
+ * to PEBS samples.
+ */
+static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
+{
+ return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
+}
+
+static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
+{
+ struct debug_store *ds = cpuc->ds;
+ u64 threshold;
+
+ if (cpuc->n_pebs == cpuc->n_large_pebs) {
+ threshold = ds->pebs_absolute_maximum -
+ x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+ } else {
+ threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+ }
+
+ ds->pebs_interrupt_threshold = threshold;
+}
+
+static void
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
{
- return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+ /*
+ * Make sure we get updated with the first PEBS
+ * event. It will trigger also during removal, but
+ * that does not hurt:
+ */
+ bool update = cpuc->n_pebs == 1;
+
+ if (needed_cb != pebs_needs_sched_cb(cpuc)) {
+ if (!needed_cb)
+ perf_sched_cb_inc(pmu);
+ else
+ perf_sched_cb_dec(pmu);
+
+ update = true;
+ }
+
+ if (update)
+ pebs_update_threshold(cpuc);
+}
+
+void intel_pmu_pebs_add(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+ bool needed_cb = pebs_needs_sched_cb(cpuc);
+
+ cpuc->n_pebs++;
+ if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+ cpuc->n_large_pebs++;
+
+ pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
}
void intel_pmu_pebs_enable(struct perf_event *event)
@@ -816,12 +872,9 @@ void intel_pmu_pebs_enable(struct perf_event *event)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
struct debug_store *ds = cpuc->ds;
- bool first_pebs;
- u64 threshold;
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
- first_pebs = !pebs_is_enabled(cpuc);
cpuc->pebs_enabled |= 1ULL << hwc->idx;
if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
@@ -830,46 +883,34 @@ void intel_pmu_pebs_enable(struct perf_event *event)
cpuc->pebs_enabled |= 1ULL << 63;
/*
- * When the event is constrained enough we can use a larger
- * threshold and run the event with less frequent PMI.
+ * Use auto-reload if possible to save a MSR write in the PMI.
+ * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
*/
- if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
- threshold = ds->pebs_absolute_maximum -
- x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
-
- if (first_pebs)
- perf_sched_cb_inc(event->ctx->pmu);
- } else {
- threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
-
- /*
- * If not all events can use larger buffer,
- * roll back to threshold = 1
- */
- if (!first_pebs &&
- (ds->pebs_interrupt_threshold > threshold))
- perf_sched_cb_dec(event->ctx->pmu);
- }
-
- /* Use auto-reload if possible to save a MSR write in the PMI */
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
ds->pebs_event_reset[hwc->idx] =
(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
}
+}
+
+void intel_pmu_pebs_del(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+ bool needed_cb = pebs_needs_sched_cb(cpuc);
- if (first_pebs || ds->pebs_interrupt_threshold > threshold)
- ds->pebs_interrupt_threshold = threshold;
+ cpuc->n_pebs--;
+ if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+ cpuc->n_large_pebs--;
+
+ pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
}
void intel_pmu_pebs_disable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- struct debug_store *ds = cpuc->ds;
- bool large_pebs = ds->pebs_interrupt_threshold >
- ds->pebs_buffer_base + x86_pmu.pebs_record_size;
- if (large_pebs)
+ if (cpuc->n_pebs == cpuc->n_large_pebs)
intel_pmu_drain_pebs_buffer();
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -879,9 +920,6 @@ void intel_pmu_pebs_disable(struct perf_event *event)
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled &= ~(1ULL << 63);
- if (large_pebs && !pebs_is_enabled(cpuc))
- perf_sched_cb_dec(event->ctx->pmu);
-
if (cpuc->enabled)
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
@@ -1274,18 +1312,18 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
struct pebs_record_nhm *p = at;
u64 pebs_status;
- /* PEBS v3 has accurate status bits */
+ pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+ /* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&p->status,
- MAX_PEBS_EVENTS)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status,
+ x86_pmu.max_pebs_events)
counts[bit]++;
continue;
}
- pebs_status = p->status & cpuc->pebs_enabled;
- pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
-
/*
* On some CPUs the PEBS status can be zero when PEBS is
* racing with clearing of GLOBAL_STATUS.
@@ -1333,8 +1371,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
continue;
event = cpuc->events[bit];
- WARN_ON_ONCE(!event);
- WARN_ON_ONCE(!event->attr.precise_ip);
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
/* log dropped samples number */
if (error[bit])
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 707d358e0dff..fc6cf21c535e 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -380,7 +380,6 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
{
- struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct x86_perf_task_context *task_ctx;
/*
@@ -390,31 +389,21 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
*/
task_ctx = ctx ? ctx->task_ctx_data : NULL;
if (task_ctx) {
- if (sched_in) {
+ if (sched_in)
__intel_pmu_lbr_restore(task_ctx);
- cpuc->lbr_context = ctx;
- } else {
+ else
__intel_pmu_lbr_save(task_ctx);
- }
return;
}
/*
- * When sampling the branck stack in system-wide, it may be
- * necessary to flush the stack on context switch. This happens
- * when the branch stack does not tag its entries with the pid
- * of the current task. Otherwise it becomes impossible to
- * associate a branch entry with a task. This ambiguity is more
- * likely to appear when the branch stack supports priv level
- * filtering and the user sets it to monitor only at the user
- * level (which could be a useful measurement in system-wide
- * mode). In that case, the risk is high of having a branch
- * stack with branch from multiple tasks.
- */
- if (sched_in) {
+ * Since a context switch can flip the address space and LBR entries
+ * are not tagged with an identifier, we need to wipe the LBR, even for
+ * per-cpu events. You simply cannot resolve the branches from the old
+ * address space.
+ */
+ if (sched_in)
intel_pmu_lbr_reset();
- cpuc->lbr_context = ctx;
- }
}
static inline bool branch_user_callstack(unsigned br_sel)
@@ -422,7 +411,7 @@ static inline bool branch_user_callstack(unsigned br_sel)
return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
}
-void intel_pmu_lbr_enable(struct perf_event *event)
+void intel_pmu_lbr_add(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct x86_perf_task_context *task_ctx;
@@ -430,27 +419,38 @@ void intel_pmu_lbr_enable(struct perf_event *event)
if (!x86_pmu.lbr_nr)
return;
- /*
- * Reset the LBR stack if we changed task context to
- * avoid data leaks.
- */
- if (event->ctx->task && cpuc->lbr_context != event->ctx) {
- intel_pmu_lbr_reset();
- cpuc->lbr_context = event->ctx;
- }
cpuc->br_sel = event->hw.branch_reg.reg;
- if (branch_user_callstack(cpuc->br_sel) && event->ctx &&
- event->ctx->task_ctx_data) {
+ if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) {
task_ctx = event->ctx->task_ctx_data;
task_ctx->lbr_callstack_users++;
}
- cpuc->lbr_users++;
+ /*
+ * Request pmu::sched_task() callback, which will fire inside the
+ * regular perf event scheduling, so that call will:
+ *
+ * - restore or wipe; when LBR-callstack,
+ * - wipe; otherwise,
+ *
+ * when this is from __perf_event_task_sched_in().
+ *
+ * However, if this is from perf_install_in_context(), no such callback
+ * will follow and we'll need to reset the LBR here if this is the
+ * first LBR event.
+ *
+ * The problem is, we cannot tell these cases apart... but we can
+ * exclude the biggest chunk of cases by looking at
+ * event->total_time_running. An event that has accrued runtime cannot
+ * be 'new'. Conversely, a new event can get installed through the
+ * context switch path for the first time.
+ */
perf_sched_cb_inc(event->ctx->pmu);
+ if (!cpuc->lbr_users++ && !event->total_time_running)
+ intel_pmu_lbr_reset();
}
-void intel_pmu_lbr_disable(struct perf_event *event)
+void intel_pmu_lbr_del(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct x86_perf_task_context *task_ctx;
@@ -467,12 +467,6 @@ void intel_pmu_lbr_disable(struct perf_event *event)
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
perf_sched_cb_dec(event->ctx->pmu);
-
- if (cpuc->enabled && !cpuc->lbr_users) {
- __intel_pmu_lbr_disable();
- /* avoid stale pointer */
- cpuc->lbr_context = NULL;
- }
}
void intel_pmu_lbr_enable_all(bool pmi)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 04bb5fb5a8d7..c5047b8f777b 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -69,6 +69,8 @@ static struct pt_cap_desc {
PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)),
PT_CAP(ip_filtering, 0, CR_EBX, BIT(2)),
PT_CAP(mtc, 0, CR_EBX, BIT(3)),
+ PT_CAP(ptwrite, 0, CR_EBX, BIT(4)),
+ PT_CAP(power_event_trace, 0, CR_EBX, BIT(5)),
PT_CAP(topa_output, 0, CR_ECX, BIT(0)),
PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)),
PT_CAP(single_range_output, 0, CR_ECX, BIT(2)),
@@ -259,10 +261,16 @@ fail:
#define RTIT_CTL_MTC (RTIT_CTL_MTC_EN | \
RTIT_CTL_MTC_RANGE)
+#define RTIT_CTL_PTW (RTIT_CTL_PTW_EN | \
+ RTIT_CTL_FUP_ON_PTW)
+
#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | \
RTIT_CTL_DISRETC | \
RTIT_CTL_CYC_PSB | \
- RTIT_CTL_MTC)
+ RTIT_CTL_MTC | \
+ RTIT_CTL_PWR_EVT_EN | \
+ RTIT_CTL_FUP_ON_PTW | \
+ RTIT_CTL_PTW_EN)
static bool pt_event_valid(struct perf_event *event)
{
@@ -311,6 +319,20 @@ static bool pt_event_valid(struct perf_event *event)
return false;
}
+ if (config & RTIT_CTL_PWR_EVT_EN &&
+ !pt_cap_get(PT_CAP_power_event_trace))
+ return false;
+
+ if (config & RTIT_CTL_PTW) {
+ if (!pt_cap_get(PT_CAP_ptwrite))
+ return false;
+
+ /* FUPonPTW without PTW doesn't make sense */
+ if ((config & RTIT_CTL_FUP_ON_PTW) &&
+ !(config & RTIT_CTL_PTW_EN))
+ return false;
+ }
+
return true;
}
@@ -1074,6 +1096,11 @@ static void pt_addr_filters_fini(struct perf_event *event)
event->hw.addr_filters = NULL;
}
+static inline bool valid_kernel_ip(unsigned long ip)
+{
+ return virt_addr_valid(ip) && kernel_ip(ip);
+}
+
static int pt_event_addr_filters_validate(struct list_head *filters)
{
struct perf_addr_filter *filter;
@@ -1081,11 +1108,16 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
list_for_each_entry(filter, filters, entry) {
/* PT doesn't support single address triggers */
- if (!filter->range)
+ if (!filter->range || !filter->size)
return -EOPNOTSUPP;
- if (!filter->inode && !kernel_ip(filter->offset))
- return -EINVAL;
+ if (!filter->inode) {
+ if (!valid_kernel_ip(filter->offset))
+ return -EINVAL;
+
+ if (!valid_kernel_ip(filter->offset + filter->size))
+ return -EINVAL;
+ }
if (++range > pt_cap_get(PT_CAP_num_address_ranges))
return -EOPNOTSUPP;
@@ -1111,7 +1143,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
} else {
/* apply the offset */
msr_a = filter->offset + offs[range];
- msr_b = filter->size + msr_a;
+ msr_b = filter->size + msr_a - 1;
}
filters->filter[range].msr_a = msr_a;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index efffa4a09f68..53473c21b554 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -26,11 +26,14 @@
#define RTIT_CTL_CYCLEACC BIT(1)
#define RTIT_CTL_OS BIT(2)
#define RTIT_CTL_USR BIT(3)
+#define RTIT_CTL_PWR_EVT_EN BIT(4)
+#define RTIT_CTL_FUP_ON_PTW BIT(5)
#define RTIT_CTL_CR3EN BIT(7)
#define RTIT_CTL_TOPA BIT(8)
#define RTIT_CTL_MTC_EN BIT(9)
#define RTIT_CTL_TSC_EN BIT(10)
#define RTIT_CTL_DISRETC BIT(11)
+#define RTIT_CTL_PTW_EN BIT(12)
#define RTIT_CTL_BRANCH_EN BIT(13)
#define RTIT_CTL_MTC_RANGE_OFFSET 14
#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
@@ -91,6 +94,8 @@ enum pt_capabilities {
PT_CAP_psb_cyc,
PT_CAP_ip_filtering,
PT_CAP_mtc,
+ PT_CAP_ptwrite,
+ PT_CAP_power_event_trace,
PT_CAP_topa_output,
PT_CAP_topa_multiple_entries,
PT_CAP_single_range_output,
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 28865938aadf..b0f0e835a770 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -357,6 +357,8 @@ static int rapl_pmu_event_init(struct perf_event *event)
if (event->cpu < 0)
return -EINVAL;
+ event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
/*
* check event is known (determines counter)
*/
@@ -765,6 +767,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init),
+
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
{},
};
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 463dc7a5a6c3..d9844cc74486 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -664,6 +664,8 @@ static int uncore_pmu_event_init(struct perf_event *event)
event->cpu = box->cpu;
event->pmu_private = box;
+ event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
event->hw.idx = -1;
event->hw.last_tag = ~0ULL;
event->hw.extra_reg.idx = EXTRA_REG_NONE;
@@ -683,7 +685,8 @@ static int uncore_pmu_event_init(struct perf_event *event)
/* fixed counters have event field hardcoded to zero */
hwc->config = 0ULL;
} else {
- hwc->config = event->attr.config & pmu->type->event_mask;
+ hwc->config = event->attr.config &
+ (pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32));
if (pmu->type->ops->hw_config) {
ret = pmu->type->ops->hw_config(box, event);
if (ret)
@@ -1321,6 +1324,11 @@ static const struct intel_uncore_init_fun skl_uncore_init __initconst = {
.pci_init = skl_uncore_pci_init,
};
+static const struct intel_uncore_init_fun skx_uncore_init __initconst = {
+ .cpu_init = skx_uncore_cpu_init,
+ .pci_init = skx_uncore_pci_init,
+};
+
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
@@ -1343,6 +1351,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
{},
};
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 78b9c23e2d8d..ad986c1e29bc 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -44,6 +44,7 @@ struct intel_uncore_type {
unsigned perf_ctr;
unsigned event_ctl;
unsigned event_mask;
+ unsigned event_mask_ext;
unsigned fixed_ctr;
unsigned fixed_ctl;
unsigned box_ctl;
@@ -120,6 +121,7 @@ struct intel_uncore_box {
};
#define UNCORE_BOX_FLAG_INITIATED 0
+#define UNCORE_BOX_FLAG_CTL_OFFS8 1 /* event config registers are 8-byte apart */
struct uncore_event_desc {
struct kobj_attribute attr;
@@ -172,6 +174,9 @@ static inline unsigned uncore_pci_fixed_ctr(struct intel_uncore_box *box)
static inline
unsigned uncore_pci_event_ctl(struct intel_uncore_box *box, int idx)
{
+ if (test_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags))
+ return idx * 8 + box->pmu->type->event_ctl;
+
return idx * 4 + box->pmu->type->event_ctl;
}
@@ -377,6 +382,8 @@ int bdx_uncore_pci_init(void);
void bdx_uncore_cpu_init(void);
int knl_uncore_pci_init(void);
void knl_uncore_cpu_init(void);
+int skx_uncore_pci_init(void);
+void skx_uncore_cpu_init(void);
/* perf_event_intel_uncore_nhmex.c */
void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 9d35ec0cb8fc..5f845eef9a4d 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -388,6 +388,8 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
event->cpu = box->cpu;
event->pmu_private = box;
+ event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
event->hw.idx = -1;
event->hw.last_tag = ~0ULL;
event->hw.extra_reg.idx = EXTRA_REG_NONE;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 8aee83bcf71f..272427700d48 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1,6 +1,10 @@
/* SandyBridge-EP/IvyTown uncore support */
#include "uncore.h"
+/* SNB-EP pci bus to socket mapping */
+#define SNBEP_CPUNODEID 0x40
+#define SNBEP_GIDNIDMAP 0x54
+
/* SNB-EP Box level control */
#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0)
#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1)
@@ -264,15 +268,72 @@
SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+/* SKX pci bus to socket mapping */
+#define SKX_CPUNODEID 0xc0
+#define SKX_GIDNIDMAP 0xd4
+
+/* SKX CHA */
+#define SKX_CHA_MSR_PMON_BOX_FILTER_TID (0x1ffULL << 0)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_LINK (0xfULL << 9)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_STATE (0x3ffULL << 17)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_REM (0x1ULL << 32)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_LOC (0x1ULL << 33)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_ALL_OPC (0x1ULL << 35)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_NM (0x1ULL << 36)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_NOT_NM (0x1ULL << 37)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_OPC0 (0x3ffULL << 41)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_OPC1 (0x3ffULL << 51)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63)
+
+/* SKX IIO */
+#define SKX_IIO0_MSR_PMON_CTL0 0xa48
+#define SKX_IIO0_MSR_PMON_CTR0 0xa41
+#define SKX_IIO0_MSR_PMON_BOX_CTL 0xa40
+#define SKX_IIO_MSR_OFFSET 0x20
+
+#define SKX_PMON_CTL_TRESH_MASK (0xff << 24)
+#define SKX_PMON_CTL_TRESH_MASK_EXT (0xf)
+#define SKX_PMON_CTL_CH_MASK (0xff << 4)
+#define SKX_PMON_CTL_FC_MASK (0x7 << 12)
+#define SKX_IIO_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SKX_PMON_CTL_TRESH_MASK)
+#define SKX_IIO_PMON_RAW_EVENT_MASK_EXT (SKX_PMON_CTL_TRESH_MASK_EXT | \
+ SKX_PMON_CTL_CH_MASK | \
+ SKX_PMON_CTL_FC_MASK)
+
+/* SKX IRP */
+#define SKX_IRP0_MSR_PMON_CTL0 0xa5b
+#define SKX_IRP0_MSR_PMON_CTR0 0xa59
+#define SKX_IRP0_MSR_PMON_BOX_CTL 0xa58
+#define SKX_IRP_MSR_OFFSET 0x20
+
+/* SKX UPI */
+#define SKX_UPI_PCI_PMON_CTL0 0x350
+#define SKX_UPI_PCI_PMON_CTR0 0x318
+#define SKX_UPI_PCI_PMON_BOX_CTL 0x378
+#define SKX_PMON_CTL_UMASK_EXT 0xff
+
+/* SKX M2M */
+#define SKX_M2M_PCI_PMON_CTL0 0x228
+#define SKX_M2M_PCI_PMON_CTR0 0x200
+#define SKX_M2M_PCI_PMON_BOX_CTL 0x258
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-39");
DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(thresh9, thresh, "config:24-35");
DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29");
DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
@@ -280,6 +341,8 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31");
+DEFINE_UNCORE_FORMAT_ATTR(ch_mask, ch_mask, "config:36-43");
+DEFINE_UNCORE_FORMAT_ATTR(fc_mask, fc_mask, "config:44-46");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
@@ -288,18 +351,26 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link4, filter_link, "config1:9-12");
DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23");
DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state5, filter_state, "config1:17-26");
+DEFINE_UNCORE_FORMAT_ATTR(filter_rem, filter_rem, "config1:32");
+DEFINE_UNCORE_FORMAT_ATTR(filter_loc, filter_loc, "config1:33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nm, filter_nm, "config1:36");
+DEFINE_UNCORE_FORMAT_ATTR(filter_not_nm, filter_not_nm, "config1:37");
DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33");
DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35");
DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37");
DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc_0, filter_opc0, "config1:41-50");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc_1, filter_opc1, "config1:51-60");
DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62");
DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61");
DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63");
@@ -1153,7 +1224,7 @@ static struct pci_driver snbep_uncore_pci_driver = {
/*
* build pci bus to socket mapping
*/
-static int snbep_pci2phy_map_init(int devid)
+static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool reverse)
{
struct pci_dev *ubox_dev = NULL;
int i, bus, nodeid, segment;
@@ -1168,12 +1239,12 @@ static int snbep_pci2phy_map_init(int devid)
break;
bus = ubox_dev->bus->number;
/* get the Node ID of the local register */
- err = pci_read_config_dword(ubox_dev, 0x40, &config);
+ err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
if (err)
break;
nodeid = config;
/* get the Node ID mapping */
- err = pci_read_config_dword(ubox_dev, 0x54, &config);
+ err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
if (err)
break;
@@ -1207,11 +1278,20 @@ static int snbep_pci2phy_map_init(int devid)
raw_spin_lock(&pci2phy_map_lock);
list_for_each_entry(map, &pci2phy_map_head, list) {
i = -1;
- for (bus = 255; bus >= 0; bus--) {
- if (map->pbus_to_physid[bus] >= 0)
- i = map->pbus_to_physid[bus];
- else
- map->pbus_to_physid[bus] = i;
+ if (reverse) {
+ for (bus = 255; bus >= 0; bus--) {
+ if (map->pbus_to_physid[bus] >= 0)
+ i = map->pbus_to_physid[bus];
+ else
+ map->pbus_to_physid[bus] = i;
+ }
+ } else {
+ for (bus = 0; bus <= 255; bus++) {
+ if (map->pbus_to_physid[bus] >= 0)
+ i = map->pbus_to_physid[bus];
+ else
+ map->pbus_to_physid[bus] = i;
+ }
}
}
raw_spin_unlock(&pci2phy_map_lock);
@@ -1224,7 +1304,7 @@ static int snbep_pci2phy_map_init(int devid)
int snbep_uncore_pci_init(void)
{
- int ret = snbep_pci2phy_map_init(0x3ce0);
+ int ret = snbep_pci2phy_map_init(0x3ce0, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true);
if (ret)
return ret;
uncore_pci_uncores = snbep_pci_uncores;
@@ -1788,7 +1868,7 @@ static struct pci_driver ivbep_uncore_pci_driver = {
int ivbep_uncore_pci_init(void)
{
- int ret = snbep_pci2phy_map_init(0x0e1e);
+ int ret = snbep_pci2phy_map_init(0x0e1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true);
if (ret)
return ret;
uncore_pci_uncores = ivbep_pci_uncores;
@@ -2897,7 +2977,7 @@ static struct pci_driver hswep_uncore_pci_driver = {
int hswep_uncore_pci_init(void)
{
- int ret = snbep_pci2phy_map_init(0x2f1e);
+ int ret = snbep_pci2phy_map_init(0x2f1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true);
if (ret)
return ret;
uncore_pci_uncores = hswep_pci_uncores;
@@ -3186,7 +3266,7 @@ static struct pci_driver bdx_uncore_pci_driver = {
int bdx_uncore_pci_init(void)
{
- int ret = snbep_pci2phy_map_init(0x6f1e);
+ int ret = snbep_pci2phy_map_init(0x6f1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true);
if (ret)
return ret;
@@ -3196,3 +3276,525 @@ int bdx_uncore_pci_init(void)
}
/* end of BDX uncore support */
+
+/* SKX uncore support */
+
+static struct intel_uncore_type skx_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = HSWEP_U_MSR_PMON_CTR0,
+ .event_ctl = HSWEP_U_MSR_PMON_CTL0,
+ .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_ubox_format_group,
+};
+
+static struct attribute *skx_uncore_cha_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid4.attr,
+ &format_attr_filter_link4.attr,
+ &format_attr_filter_state5.attr,
+ &format_attr_filter_rem.attr,
+ &format_attr_filter_loc.attr,
+ &format_attr_filter_nm.attr,
+ &format_attr_filter_all_op.attr,
+ &format_attr_filter_not_nm.attr,
+ &format_attr_filter_opc_0.attr,
+ &format_attr_filter_opc_1.attr,
+ &format_attr_filter_nc.attr,
+ &format_attr_filter_c6.attr,
+ &format_attr_filter_isoc.attr,
+ NULL,
+};
+
+static struct attribute_group skx_uncore_chabox_format_group = {
+ .name = "format",
+ .attrs = skx_uncore_cha_formats_attr,
+};
+
+static struct event_constraint skx_uncore_chabox_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg skx_uncore_cha_extra_regs[] = {
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8134, 0xffff, 0x4),
+};
+
+static u64 skx_cha_filter_mask(int fields)
+{
+ u64 mask = 0;
+
+ if (fields & 0x1)
+ mask |= SKX_CHA_MSR_PMON_BOX_FILTER_TID;
+ if (fields & 0x2)
+ mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LINK;
+ if (fields & 0x4)
+ mask |= SKX_CHA_MSR_PMON_BOX_FILTER_STATE;
+ return mask;
+}
+
+static struct event_constraint *
+skx_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ return __snbep_cbox_get_constraint(box, event, skx_cha_filter_mask);
+}
+
+static int skx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct extra_reg *er;
+ int idx = 0;
+
+ for (er = skx_uncore_cha_extra_regs; er->msr; er++) {
+ if (er->event != (event->hw.config & er->config_mask))
+ continue;
+ idx |= er->idx;
+ }
+
+ if (idx) {
+ reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
+ HSWEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 & skx_cha_filter_mask(idx);
+ reg1->idx = idx;
+ }
+ return 0;
+}
+
+static struct intel_uncore_ops skx_uncore_chabox_ops = {
+ /* There is no frz_en for chabox ctl */
+ .init_box = ivbep_uncore_msr_init_box,
+ .disable_box = snbep_uncore_msr_disable_box,
+ .enable_box = snbep_uncore_msr_enable_box,
+ .disable_event = snbep_uncore_msr_disable_event,
+ .enable_event = hswep_cbox_enable_event,
+ .read_counter = uncore_msr_read_counter,
+ .hw_config = skx_cha_hw_config,
+ .get_constraint = skx_cha_get_constraint,
+ .put_constraint = snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type skx_uncore_chabox = {
+ .name = "cha",
+ .num_counters = 4,
+ .perf_ctr_bits = 48,
+ .event_ctl = HSWEP_C0_MSR_PMON_CTL0,
+ .perf_ctr = HSWEP_C0_MSR_PMON_CTR0,
+ .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL,
+ .msr_offset = HSWEP_CBO_MSR_OFFSET,
+ .num_shared_regs = 1,
+ .constraints = skx_uncore_chabox_constraints,
+ .ops = &skx_uncore_chabox_ops,
+ .format_group = &skx_uncore_chabox_format_group,
+};
+
+static struct attribute *skx_uncore_iio_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh9.attr,
+ &format_attr_ch_mask.attr,
+ &format_attr_fc_mask.attr,
+ NULL,
+};
+
+static struct attribute_group skx_uncore_iio_format_group = {
+ .name = "format",
+ .attrs = skx_uncore_iio_formats_attr,
+};
+
+static struct event_constraint skx_uncore_iio_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x83, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x88, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x95, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0xc0, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0xc5, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0xd4, 0xc),
+ EVENT_CONSTRAINT_END
+};
+
+static void skx_iio_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops skx_uncore_iio_ops = {
+ .init_box = ivbep_uncore_msr_init_box,
+ .disable_box = snbep_uncore_msr_disable_box,
+ .enable_box = snbep_uncore_msr_enable_box,
+ .disable_event = snbep_uncore_msr_disable_event,
+ .enable_event = skx_iio_enable_event,
+ .read_counter = uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type skx_uncore_iio = {
+ .name = "iio",
+ .num_counters = 4,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SKX_IIO0_MSR_PMON_CTL0,
+ .perf_ctr = SKX_IIO0_MSR_PMON_CTR0,
+ .event_mask = SKX_IIO_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SKX_IIO_PMON_RAW_EVENT_MASK_EXT,
+ .box_ctl = SKX_IIO0_MSR_PMON_BOX_CTL,
+ .msr_offset = SKX_IIO_MSR_OFFSET,
+ .constraints = skx_uncore_iio_constraints,
+ .ops = &skx_uncore_iio_ops,
+ .format_group = &skx_uncore_iio_format_group,
+};
+
+static struct attribute *skx_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute_group skx_uncore_format_group = {
+ .name = "format",
+ .attrs = skx_uncore_formats_attr,
+};
+
+static struct intel_uncore_type skx_uncore_irp = {
+ .name = "irp",
+ .num_counters = 2,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SKX_IRP0_MSR_PMON_CTL0,
+ .perf_ctr = SKX_IRP0_MSR_PMON_CTR0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SKX_IRP0_MSR_PMON_BOX_CTL,
+ .msr_offset = SKX_IRP_MSR_OFFSET,
+ .ops = &skx_uncore_iio_ops,
+ .format_group = &skx_uncore_format_group,
+};
+
+static struct intel_uncore_ops skx_uncore_pcu_ops = {
+ IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = hswep_pcu_hw_config,
+ .get_constraint = snbep_pcu_get_constraint,
+ .put_constraint = snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type skx_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0,
+ .event_ctl = HSWEP_PCU_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &skx_uncore_pcu_ops,
+ .format_group = &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *skx_msr_uncores[] = {
+ &skx_uncore_ubox,
+ &skx_uncore_chabox,
+ &skx_uncore_iio,
+ &skx_uncore_irp,
+ &skx_uncore_pcu,
+ NULL,
+};
+
+static int skx_count_chabox(void)
+{
+ struct pci_dev *chabox_dev = NULL;
+ int bus, count = 0;
+
+ while (1) {
+ chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev);
+ if (!chabox_dev)
+ break;
+ if (count == 0)
+ bus = chabox_dev->bus->number;
+ if (bus != chabox_dev->bus->number)
+ break;
+ count++;
+ }
+
+ pci_dev_put(chabox_dev);
+ return count;
+}
+
+void skx_uncore_cpu_init(void)
+{
+ skx_uncore_chabox.num_boxes = skx_count_chabox();
+ uncore_msr_uncores = skx_msr_uncores;
+}
+
+static struct intel_uncore_type skx_uncore_imc = {
+ .name = "imc",
+ .num_counters = 4,
+ .num_boxes = 6,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+ .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+ .event_descs = hswep_uncore_imc_events,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .ops = &ivbep_uncore_pci_ops,
+ .format_group = &skx_uncore_format_group,
+};
+
+static struct attribute *skx_upi_uncore_formats_attr[] = {
+ &format_attr_event_ext.attr,
+ &format_attr_umask_ext.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute_group skx_upi_uncore_format_group = {
+ .name = "format",
+ .attrs = skx_upi_uncore_formats_attr,
+};
+
+static void skx_upi_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+
+ __set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+ pci_write_config_dword(pdev, SKX_UPI_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static struct intel_uncore_ops skx_upi_uncore_pci_ops = {
+ .init_box = skx_upi_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_uncore_pci_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+};
+
+static struct intel_uncore_type skx_uncore_upi = {
+ .name = "upi",
+ .num_counters = 4,
+ .num_boxes = 3,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SKX_UPI_PCI_PMON_CTR0,
+ .event_ctl = SKX_UPI_PCI_PMON_CTL0,
+ .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SKX_PMON_CTL_UMASK_EXT,
+ .box_ctl = SKX_UPI_PCI_PMON_BOX_CTL,
+ .ops = &skx_upi_uncore_pci_ops,
+ .format_group = &skx_upi_uncore_format_group,
+};
+
+static void skx_m2m_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+
+ __set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+ pci_write_config_dword(pdev, SKX_M2M_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static struct intel_uncore_ops skx_m2m_uncore_pci_ops = {
+ .init_box = skx_m2m_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_uncore_pci_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+};
+
+static struct intel_uncore_type skx_uncore_m2m = {
+ .name = "m2m",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SKX_M2M_PCI_PMON_CTR0,
+ .event_ctl = SKX_M2M_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SKX_M2M_PCI_PMON_BOX_CTL,
+ .ops = &skx_m2m_uncore_pci_ops,
+ .format_group = &skx_uncore_format_group,
+};
+
+static struct event_constraint skx_uncore_m2pcie_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type skx_uncore_m2pcie = {
+ .name = "m2pcie",
+ .num_counters = 4,
+ .num_boxes = 4,
+ .perf_ctr_bits = 48,
+ .constraints = skx_uncore_m2pcie_constraints,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .ops = &ivbep_uncore_pci_ops,
+ .format_group = &skx_uncore_format_group,
+};
+
+static struct event_constraint skx_uncore_m3upi_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x1d, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x1e, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x40, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x4e, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x4f, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x50, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x51, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x52, 0x7),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type skx_uncore_m3upi = {
+ .name = "m3upi",
+ .num_counters = 3,
+ .num_boxes = 3,
+ .perf_ctr_bits = 48,
+ .constraints = skx_uncore_m3upi_constraints,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .ops = &ivbep_uncore_pci_ops,
+ .format_group = &skx_uncore_format_group,
+};
+
+enum {
+ SKX_PCI_UNCORE_IMC,
+ SKX_PCI_UNCORE_M2M,
+ SKX_PCI_UNCORE_UPI,
+ SKX_PCI_UNCORE_M2PCIE,
+ SKX_PCI_UNCORE_M3UPI,
+};
+
+static struct intel_uncore_type *skx_pci_uncores[] = {
+ [SKX_PCI_UNCORE_IMC] = &skx_uncore_imc,
+ [SKX_PCI_UNCORE_M2M] = &skx_uncore_m2m,
+ [SKX_PCI_UNCORE_UPI] = &skx_uncore_upi,
+ [SKX_PCI_UNCORE_M2PCIE] = &skx_uncore_m2pcie,
+ [SKX_PCI_UNCORE_M3UPI] = &skx_uncore_m3upi,
+ NULL,
+};
+
+static const struct pci_device_id skx_uncore_pci_ids[] = {
+ { /* MC0 Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2042),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(10, 2, SKX_PCI_UNCORE_IMC, 0),
+ },
+ { /* MC0 Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2046),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(10, 6, SKX_PCI_UNCORE_IMC, 1),
+ },
+ { /* MC0 Channel 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204a),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(11, 2, SKX_PCI_UNCORE_IMC, 2),
+ },
+ { /* MC1 Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2042),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 2, SKX_PCI_UNCORE_IMC, 3),
+ },
+ { /* MC1 Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2046),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 6, SKX_PCI_UNCORE_IMC, 4),
+ },
+ { /* MC1 Channel 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204a),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(13, 2, SKX_PCI_UNCORE_IMC, 5),
+ },
+ { /* M2M0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2066),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 0, SKX_PCI_UNCORE_M2M, 0),
+ },
+ { /* M2M1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2066),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 0, SKX_PCI_UNCORE_M2M, 1),
+ },
+ { /* UPI0 Link 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(14, 0, SKX_PCI_UNCORE_UPI, 0),
+ },
+ { /* UPI0 Link 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(15, 0, SKX_PCI_UNCORE_UPI, 1),
+ },
+ { /* UPI1 Link 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(16, 0, SKX_PCI_UNCORE_UPI, 2),
+ },
+ { /* M2PCIe 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 1, SKX_PCI_UNCORE_M2PCIE, 0),
+ },
+ { /* M2PCIe 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(22, 1, SKX_PCI_UNCORE_M2PCIE, 1),
+ },
+ { /* M2PCIe 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(23, 1, SKX_PCI_UNCORE_M2PCIE, 2),
+ },
+ { /* M2PCIe 3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
+ },
+ { /* M3UPI0 Link 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+ },
+ { /* M3UPI0 Link 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+ },
+ { /* M3UPI1 Link 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+ },
+ { /* end: all zeroes */ }
+};
+
+
+static struct pci_driver skx_uncore_pci_driver = {
+ .name = "skx_uncore",
+ .id_table = skx_uncore_pci_ids,
+};
+
+int skx_uncore_pci_init(void)
+{
+ /* need to double check pci address */
+ int ret = snbep_pci2phy_map_init(0x2014, SKX_CPUNODEID, SKX_GIDNIDMAP, false);
+
+ if (ret)
+ return ret;
+
+ uncore_pci_uncores = skx_pci_uncores;
+ uncore_pci_driver = &skx_uncore_pci_driver;
+ return 0;
+}
+
+/* end of SKX uncore support */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8c4a47706296..5874d8de1f8d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -194,12 +194,13 @@ struct cpu_hw_events {
*/
struct debug_store *ds;
u64 pebs_enabled;
+ int n_pebs;
+ int n_large_pebs;
/*
* Intel LBR bits
*/
int lbr_users;
- void *lbr_context;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
@@ -508,6 +509,8 @@ struct x86_pmu {
void (*enable_all)(int added);
void (*enable)(struct perf_event *);
void (*disable)(struct perf_event *);
+ void (*add)(struct perf_event *);
+ void (*del)(struct perf_event *);
int (*hw_config)(struct perf_event *event);
int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
unsigned eventsel;
@@ -888,6 +891,10 @@ extern struct event_constraint intel_skl_pebs_event_constraints[];
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
+void intel_pmu_pebs_add(struct perf_event *event);
+
+void intel_pmu_pebs_del(struct perf_event *event);
+
void intel_pmu_pebs_enable(struct perf_event *event);
void intel_pmu_pebs_disable(struct perf_event *event);
@@ -906,9 +913,9 @@ u64 lbr_from_signext_quirk_wr(u64 val);
void intel_pmu_lbr_reset(void);
-void intel_pmu_lbr_enable(struct perf_event *event);
+void intel_pmu_lbr_add(struct perf_event *event);
-void intel_pmu_lbr_disable(struct perf_event *event);
+void intel_pmu_lbr_del(struct perf_event *event);
void intel_pmu_lbr_enable_all(bool pmi);
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 2f29f4e407c3..cb13c0564ea7 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -378,7 +378,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);
} put_user_catch(err);
- err |= copy_siginfo_to_user32(&frame->info, &ksig->info);
+ err |= __copy_siginfo_to_user32(&frame->info, &ksig->info, false);
err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
regs, set->sig[0]);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e77a6443104f..1b020381ab38 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -217,10 +217,14 @@ static inline int alternatives_text_reserved(void *start, void *end)
*/
#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \
output, input...) \
+{ \
+ register void *__sp asm(_ASM_SP); \
asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
"call %P[new2]", feature2) \
- : output : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
- [new2] "i" (newfunc2), ## input)
+ : output, "+r" (__sp) \
+ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
+ [new2] "i" (newfunc2), ## input); \
+}
/*
* use this macro(s) if you need more than one output parameter
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 124357773ffa..f5aaf6c83222 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -650,8 +650,8 @@ static inline void entering_ack_irq(void)
static inline void ipi_entering_ack_irq(void)
{
- ack_APIC_irq();
irq_enter();
+ ack_APIC_irq();
}
static inline void exiting_irq(void)
@@ -661,9 +661,8 @@ static inline void exiting_irq(void)
static inline void exiting_ack_irq(void)
{
- irq_exit();
- /* Ack only at the end to avoid potential reentry */
ack_APIC_irq();
+ irq_exit();
}
extern void ioapic_zap_locks(void);
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 9733361fed6f..97848cdfcb1a 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -158,53 +158,9 @@ extern void __add_wrong_size(void)
* value of "*ptr".
*
* xadd() is locked when multiple CPUs are online
- * xadd_sync() is always locked
- * xadd_local() is never locked
*/
#define __xadd(ptr, inc, lock) __xchg_op((ptr), (inc), xadd, lock)
#define xadd(ptr, inc) __xadd((ptr), (inc), LOCK_PREFIX)
-#define xadd_sync(ptr, inc) __xadd((ptr), (inc), "lock; ")
-#define xadd_local(ptr, inc) __xadd((ptr), (inc), "")
-
-#define __add(ptr, inc, lock) \
- ({ \
- __typeof__ (*(ptr)) __ret = (inc); \
- switch (sizeof(*(ptr))) { \
- case __X86_CASE_B: \
- asm volatile (lock "addb %b1, %0\n" \
- : "+m" (*(ptr)) : "qi" (inc) \
- : "memory", "cc"); \
- break; \
- case __X86_CASE_W: \
- asm volatile (lock "addw %w1, %0\n" \
- : "+m" (*(ptr)) : "ri" (inc) \
- : "memory", "cc"); \
- break; \
- case __X86_CASE_L: \
- asm volatile (lock "addl %1, %0\n" \
- : "+m" (*(ptr)) : "ri" (inc) \
- : "memory", "cc"); \
- break; \
- case __X86_CASE_Q: \
- asm volatile (lock "addq %1, %0\n" \
- : "+m" (*(ptr)) : "ri" (inc) \
- : "memory", "cc"); \
- break; \
- default: \
- __add_wrong_size(); \
- } \
- __ret; \
- })
-
-/*
- * add_*() adds "inc" to "*ptr"
- *
- * __add() takes a lock prefix
- * add_smp() is locked when multiple CPUs are online
- * add_sync() is always locked
- */
-#define add_smp(ptr, inc) __add((ptr), (inc), LOCK_PREFIX)
-#define add_sync(ptr, inc) __add((ptr), (inc), "lock; ")
#define __cmpxchg_double(pfx, p1, p2, o1, o2, n1, n2) \
({ \
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index a18806165fe4..03d269bed941 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -275,10 +275,10 @@ struct compat_shmid64_ds {
#ifdef CONFIG_X86_X32_ABI
typedef struct user_regs_struct compat_elf_gregset_t;
-#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216)
-#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296)
-#define SET_PR_FPVALID(S,V) \
- do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \
+/* Full regset -- prstatus on x32, otherwise on ia32 */
+#define PRSTATUS_SIZE(S, R) (R != sizeof(S.pr_reg) ? 144 : 296)
+#define SET_PR_FPVALID(S, V, R) \
+ do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \
while (0)
#define COMPAT_USE_64BIT_TIME \
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 92a8308b96f6..1188bc849ee3 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -106,7 +106,6 @@
#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */
#define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 4e10d73cf018..12080d87da3b 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -36,7 +36,7 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
extern struct desc_ptr idt_descr;
extern gate_desc idt_table[];
-extern struct desc_ptr debug_idt_descr;
+extern const struct desc_ptr debug_idt_descr;
extern gate_desc debug_idt_table[];
struct gdt_page {
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 3ab0537872fb..476b574de99e 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -10,8 +10,8 @@
#include <uapi/asm/e820.h>
#ifndef __ASSEMBLY__
/* see comment in arch/x86/kernel/e820.c */
-extern struct e820map e820;
-extern struct e820map e820_saved;
+extern struct e820map *e820;
+extern struct e820map *e820_saved;
extern unsigned long pci_mem_start;
extern int e820_any_mapped(u64 start, u64 end, unsigned type);
@@ -53,6 +53,8 @@ extern void e820_reserve_resources_late(void);
extern void setup_memory_map(void);
extern char *default_machine_specific_memory_setup(void);
+extern void e820_reallocate_tables(void);
+
/*
* Returns true iff the specified range [s,e) is completely contained inside
* the ISA region.
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index d0bb76d81402..389d700b961e 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -117,7 +117,6 @@ extern int __init efi_memblock_x86_reserve_range(void);
extern pgd_t * __init efi_call_phys_prolog(void);
extern void __init efi_call_phys_epilog(pgd_t *save_pgd);
extern void __init efi_print_memmap(void);
-extern void __init efi_unmap_memmap(void);
extern void __init efi_memory_uc(u64 addr, unsigned long size);
extern void __init efi_map_region(efi_memory_desc_t *md);
extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
@@ -192,14 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map(
struct efi_config {
u64 image_handle;
u64 table;
- u64 allocate_pool;
- u64 allocate_pages;
- u64 get_memory_map;
- u64 free_pool;
- u64 free_pages;
- u64 locate_handle;
- u64 handle_protocol;
- u64 exit_boot_services;
+ u64 boot_services;
u64 text_output;
efi_status_t (*call)(unsigned long, ...);
bool is64;
@@ -207,14 +199,27 @@ struct efi_config {
__pure const struct efi_config *__efi_early(void);
+static inline bool efi_is_64bit(void)
+{
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return false;
+
+ if (!IS_ENABLED(CONFIG_EFI_MIXED))
+ return true;
+
+ return __efi_early()->is64;
+}
+
#define efi_call_early(f, ...) \
- __efi_early()->call(__efi_early()->f, __VA_ARGS__);
+ __efi_early()->call(efi_is_64bit() ? \
+ ((efi_boot_services_64_t *)(unsigned long) \
+ __efi_early()->boot_services)->f : \
+ ((efi_boot_services_32_t *)(unsigned long) \
+ __efi_early()->boot_services)->f, __VA_ARGS__)
#define __efi_call_early(f, ...) \
__efi_early()->call((unsigned long)f, __VA_ARGS__);
-#define efi_is_64bit() __efi_early()->is64
-
extern bool efi_reboot_required(void);
#else
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
index 0e970d00dfcd..20a1fbf7fe4e 100644
--- a/arch/x86/include/asm/fpu/signal.h
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -19,6 +19,12 @@ 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/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index ae55a43e09c0..d4957ac72b48 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -45,7 +45,8 @@
extern u64 xfeatures_mask;
extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
-extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
+extern void __init update_regset_xstate_info(unsigned int size,
+ u64 xstate_mask);
void fpu__xstate_clear_all_cpu_caps(void);
void *get_xsave_addr(struct xregs_state *xsave, int xstate);
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index a4820d4df617..eccd0ac6bc38 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -6,6 +6,7 @@
# define MCOUNT_ADDR ((unsigned long)(__fentry__))
#else
# define MCOUNT_ADDR ((unsigned long)(mcount))
+# define HAVE_FUNCTION_GRAPH_FP_TEST
#endif
#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */
@@ -13,6 +14,8 @@
#define ARCH_SUPPORTS_FTRACE_OPS 1
#endif
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
#ifndef __ASSEMBLY__
extern void mcount(void);
extern atomic_t modifying_ftrace_code;
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 055ea9941dd5..67942b6ad4b7 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -43,6 +43,9 @@ struct hypervisor_x86 {
/* X2APIC detection (run once per boot) */
bool (*x2apic_available)(void);
+
+ /* pin current vcpu to specified physical cpu (run rarely) */
+ void (*pin_vcpu)(int);
};
extern const struct hypervisor_x86 *x86_hyper;
@@ -56,6 +59,7 @@ extern const struct hypervisor_x86 x86_hyper_kvm;
extern void init_hypervisor(struct cpuinfo_x86 *c);
extern void init_hypervisor_platform(void);
extern bool hypervisor_x2apic_available(void);
+extern void hypervisor_pin_vcpu(int cpu);
#else
static inline void init_hypervisor(struct cpuinfo_x86 *c) { }
static inline void init_hypervisor_platform(void) { }
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 627719475457..9ae5ab80a497 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -56,8 +56,8 @@
#define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */
#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */
#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */
-#define INTEL_FAM6_ATOM_MERRIFIELD1 0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MERRIFIELD2 0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */
+#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C
#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 9d6b097aa73d..5b6753d1f7f4 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -18,6 +18,8 @@
extern int intel_mid_pci_init(void);
extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state);
+extern void intel_mid_pwr_power_off(void);
+
#define INTEL_MID_PWR_LSS_OFFSET 4
#define INTEL_MID_PWR_LSS_TYPE (1 << 7)
diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h
index 925b605eb5c6..4fb1d0abef95 100644
--- a/arch/x86/include/asm/intel_scu_ipc.h
+++ b/arch/x86/include/asm/intel_scu_ipc.h
@@ -3,6 +3,8 @@
#include <linux/notifier.h>
+#define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */
+
#define IPCMSG_WARM_RESET 0xF0
#define IPCMSG_COLD_RESET 0xF1
#define IPCMSG_SOFT_RESET 0xF2
diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h
index 2674ee3de748..1052a797d71d 100644
--- a/arch/x86/include/asm/kaslr.h
+++ b/arch/x86/include/asm/kaslr.h
@@ -6,6 +6,7 @@ unsigned long kaslr_get_random_long(const char *purpose);
#ifdef CONFIG_RANDOMIZE_MEMORY
extern unsigned long page_offset_base;
extern unsigned long vmalloc_base;
+extern unsigned long vmemmap_base;
void kernel_randomize_memory(void);
#else
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 1ef9d581b5d9..d31881188431 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -24,8 +24,6 @@ enum die_val {
extern void printk_address(unsigned long address);
extern void die(const char *, struct pt_regs *,long);
extern int __must_check __die(const char *, struct pt_regs *, long);
-extern void show_trace(struct task_struct *t, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp);
extern void show_stack_regs(struct pt_regs *regs);
extern void __show_regs(struct pt_regs *regs, int all);
extern unsigned long oops_begin(void);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 8bf766ef0e18..9bd7ff5ffbcc 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -40,9 +40,10 @@
#define MCI_STATUS_AR (1ULL<<55) /* Action required */
/* AMD-specific bits */
+#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */
+#define MCI_STATUS_SYNDV (1ULL<<53) /* synd reg. valid */
#define MCI_STATUS_DEFERRED (1ULL<<44) /* uncorrected error, deferred exception */
#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */
-#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */
/*
* McaX field if set indicates a given bank supports MCA extensions:
@@ -110,6 +111,7 @@
#define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003
#define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004
#define MSR_AMD64_SMCA_MC0_IPID 0xc0002005
+#define MSR_AMD64_SMCA_MC0_SYND 0xc0002006
#define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008
#define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009
#define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a
@@ -119,6 +121,7 @@
#define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_SYND(x) (MSR_AMD64_SMCA_MC0_SYND + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
@@ -334,44 +337,47 @@ extern void apei_mce_report_mem_error(int corrected,
* Scalable MCA.
*/
#ifdef CONFIG_X86_MCE_AMD
-enum amd_ip_types {
- SMCA_F17H_CORE = 0, /* Core errors */
- SMCA_DF, /* Data Fabric */
- SMCA_UMC, /* Unified Memory Controller */
- SMCA_PB, /* Parameter Block */
- SMCA_PSP, /* Platform Security Processor */
- SMCA_SMU, /* System Management Unit */
- N_AMD_IP_TYPES
-};
-
-struct amd_hwid {
- const char *name;
- unsigned int hwid;
-};
-
-extern struct amd_hwid amd_hwids[N_AMD_IP_TYPES];
-enum amd_core_mca_blocks {
+/* These may be used by multiple smca_hwid_mcatypes */
+enum smca_bank_types {
SMCA_LS = 0, /* Load Store */
SMCA_IF, /* Instruction Fetch */
- SMCA_L2_CACHE, /* L2 cache */
- SMCA_DE, /* Decoder unit */
- RES, /* Reserved */
- SMCA_EX, /* Execution unit */
+ SMCA_L2_CACHE, /* L2 Cache */
+ SMCA_DE, /* Decoder Unit */
+ SMCA_EX, /* Execution Unit */
SMCA_FP, /* Floating Point */
- SMCA_L3_CACHE, /* L3 cache */
- N_CORE_MCA_BLOCKS
+ SMCA_L3_CACHE, /* L3 Cache */
+ SMCA_CS, /* Coherent Slave */
+ SMCA_PIE, /* Power, Interrupts, etc. */
+ SMCA_UMC, /* Unified Memory Controller */
+ SMCA_PB, /* Parameter Block */
+ SMCA_PSP, /* Platform Security Processor */
+ SMCA_SMU, /* System Management Unit */
+ N_SMCA_BANK_TYPES
};
-extern const char * const amd_core_mcablock_names[N_CORE_MCA_BLOCKS];
+struct smca_bank_name {
+ const char *name; /* Short name for sysfs */
+ const char *long_name; /* Long name for pretty-printing */
+};
+
+extern struct smca_bank_name smca_bank_names[N_SMCA_BANK_TYPES];
+
+#define HWID_MCATYPE(hwid, mcatype) ((hwid << 16) | mcatype)
-enum amd_df_mca_blocks {
- SMCA_CS = 0, /* Coherent Slave */
- SMCA_PIE, /* Power management, Interrupts, etc */
- N_DF_BLOCKS
+struct smca_hwid_mcatype {
+ unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */
+ u32 hwid_mcatype; /* (hwid,mcatype) tuple */
+ u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */
};
-extern const char * const amd_df_mcablock_names[N_DF_BLOCKS];
+struct smca_bank_info {
+ struct smca_hwid_mcatype *type;
+ u32 type_instance;
+};
+
+extern struct smca_bank_info smca_banks[MAX_NR_BANKS];
+
#endif
#endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index b07233b64578..32007041ef8c 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -6,7 +6,6 @@
#include <asm/x86_init.h>
#include <asm/apicdef.h>
-extern int apic_version[];
extern int pic_mode;
#ifdef CONFIG_X86_32
@@ -40,6 +39,7 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES];
extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
extern unsigned int boot_cpu_physical_apicid;
+extern u8 boot_cpu_apic_version;
extern unsigned long mp_lapic_addr;
#ifdef CONFIG_X86_LOCAL_APIC
@@ -86,6 +86,7 @@ static inline void early_reserve_e820_mpc_new(void) { }
#endif
int generic_processor_info(int apicid, int version);
+int __generic_processor_info(int apicid, int version, bool enabled);
#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 2970d22d7766..ce932812f142 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -80,10 +80,6 @@ static inline unsigned long __read_cr4(void)
{
return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
}
-static inline unsigned long __read_cr4_safe(void)
-{
- return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
-}
static inline void __write_cr4(unsigned long x)
{
@@ -661,8 +657,6 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
-#ifdef CONFIG_QUEUED_SPINLOCKS
-
static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
u32 val)
{
@@ -684,22 +678,6 @@ static __always_inline void pv_kick(int cpu)
PVOP_VCALL1(pv_lock_ops.kick, cpu);
}
-#else /* !CONFIG_QUEUED_SPINLOCKS */
-
-static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
- __ticket_t ticket)
-{
- PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket);
-}
-
-static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
- __ticket_t ticket)
-{
- PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
-}
-
-#endif /* CONFIG_QUEUED_SPINLOCKS */
-
#endif /* SMP && PARAVIRT_SPINLOCKS */
#ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 7fa9e7740ba3..0f400c0e4979 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -108,7 +108,6 @@ struct pv_cpu_ops {
unsigned long (*read_cr0)(void);
void (*write_cr0)(unsigned long);
- unsigned long (*read_cr4_safe)(void);
unsigned long (*read_cr4)(void);
void (*write_cr4)(unsigned long);
@@ -301,23 +300,16 @@ struct pv_mmu_ops {
struct arch_spinlock;
#ifdef CONFIG_SMP
#include <asm/spinlock_types.h>
-#else
-typedef u16 __ticket_t;
#endif
struct qspinlock;
struct pv_lock_ops {
-#ifdef CONFIG_QUEUED_SPINLOCKS
void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
struct paravirt_callee_save queued_spin_unlock;
void (*wait)(u8 *ptr, u8 val);
void (*kick)(int cpu);
-#else /* !CONFIG_QUEUED_SPINLOCKS */
- struct paravirt_callee_save lock_spinning;
- void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
-#endif /* !CONFIG_QUEUED_SPINLOCKS */
};
/* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 6fdef9eef2d5..3a264200c62f 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -57,11 +57,13 @@ typedef struct { pteval_t pte; } pte_t;
#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
#define VMALLOC_SIZE_TB _AC(32, UL)
#define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
-#define VMEMMAP_START _AC(0xffffea0000000000, UL)
+#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
#ifdef CONFIG_RANDOMIZE_MEMORY
#define VMALLOC_START vmalloc_base
+#define VMEMMAP_START vmemmap_base
#else
#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)
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index 643eba42d620..2c1ebeb4d737 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -46,10 +46,7 @@ static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n)
static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
{
- if (static_cpu_has(X86_FEATURE_MCE_RECOVERY))
- return memcpy_mcsafe(dst, src, n);
- memcpy(dst, src, n);
- return 0;
+ return memcpy_mcsafe(dst, src, n);
}
/**
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 63def9537a2d..984a7bf17f6a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -389,9 +389,9 @@ struct thread_struct {
unsigned short fsindex;
unsigned short gsindex;
#endif
-#ifdef CONFIG_X86_32
- unsigned long ip;
-#endif
+
+ u32 status; /* thread synchronous flags */
+
#ifdef CONFIG_X86_64
unsigned long fsbase;
unsigned long gsbase;
@@ -438,6 +438,15 @@ struct thread_struct {
};
/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
+
+/*
* Set IOPL bits in EFLAGS from given mask
*/
static inline void native_set_iopl_mask(unsigned mask)
@@ -724,8 +733,6 @@ static inline void spin_lock_prefetch(const void *x)
.addr_limit = KERNEL_DS, \
}
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
/*
* TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack.
* This is necessary to guarantee that the entire "struct pt_regs"
@@ -776,17 +783,13 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
.addr_limit = KERNEL_DS, \
}
-/*
- * Return saved PC of a blocked thread.
- * What is this good for? it will be always the scheduler or ret_from_fork.
- */
-#define thread_saved_pc(t) READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8))
-
#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1)
extern unsigned long KSTK_ESP(struct task_struct *task);
#endif /* CONFIG_X86_64 */
+extern unsigned long thread_saved_pc(struct task_struct *tsk);
+
extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
unsigned long new_sp);
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index b2988c0ed829..230e1903acf0 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -44,9 +44,9 @@ struct trampoline_header {
extern struct real_mode_header *real_mode_header;
extern unsigned char real_mode_blob_end[];
-extern unsigned long init_rsp;
extern unsigned long initial_code;
extern unsigned long initial_gs;
+extern unsigned long initial_stack;
extern unsigned char real_mode_blob[];
extern unsigned char real_mode_relocs[];
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 8dbc762ad132..3d33a719f5c1 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -154,7 +154,7 @@ static inline bool __down_write_trylock(struct rw_semaphore *sem)
: "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
CC_OUT(e) (result)
: "er" (RWSEM_ACTIVE_WRITE_BIAS)
- : "memory", "cc");
+ : "memory");
return result;
}
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index dd1e7d6387ab..8af22be0fe61 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -23,6 +23,10 @@ typedef struct {
unsigned long sig[_NSIG_WORDS];
} sigset_t;
+/* non-uapi in-kernel SA_FLAGS for those indicates ABI for a signal frame */
+#define SA_IA32_ABI 0x02000000u
+#define SA_X32_ABI 0x01000000u
+
#ifndef CONFIG_COMPAT
typedef sigset_t compat_sigset_t;
#endif
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ebd0c164cd4e..19980b36f394 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -39,9 +39,6 @@ DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid);
#endif
-/* Static state in head.S used to set up a CPU */
-extern unsigned long stack_start; /* Initial stack pointer address */
-
struct task_struct;
struct smp_ops {
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 587d7914ea4b..19a2224f9e16 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -59,22 +59,19 @@ static inline void native_write_cr3(unsigned long val)
static inline unsigned long native_read_cr4(void)
{
unsigned long val;
- asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
- return val;
-}
-
-static inline unsigned long native_read_cr4_safe(void)
-{
- unsigned long val;
- /* This could fault if %cr4 does not exist. In x86_64, a cr4 always
- * exists, so it will never fail. */
#ifdef CONFIG_X86_32
+ /*
+ * This could fault if CR4 does not exist. Non-existent CR4
+ * is functionally equivalent to CR4 == 0. Keep it simple and pretend
+ * that CR4 == 0 on CPUs that don't have CR4.
+ */
asm volatile("1: mov %%cr4, %0\n"
"2:\n"
_ASM_EXTABLE(1b, 2b)
: "=r" (val), "=m" (__force_order) : "0" (0));
#else
- val = native_read_cr4();
+ /* CR4 always exists on x86_64. */
+ asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
#endif
return val;
}
@@ -182,11 +179,6 @@ static inline unsigned long __read_cr4(void)
return native_read_cr4();
}
-static inline unsigned long __read_cr4_safe(void)
-{
- return native_read_cr4_safe();
-}
-
static inline void __write_cr4(unsigned long x)
{
native_write_cr4(x);
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index be0a05913b91..921bea7a2708 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -20,187 +20,13 @@
* (the type definitions are in asm/spinlock_types.h)
*/
-#ifdef CONFIG_X86_32
-# define LOCK_PTR_REG "a"
-#else
-# define LOCK_PTR_REG "D"
-#endif
-
-#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE))
-/*
- * On PPro SMP, we use a locked operation to unlock
- * (PPro errata 66, 92)
- */
-# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
-#else
-# define UNLOCK_LOCK_PREFIX
-#endif
-
/* How long a lock should spin before we consider blocking */
#define SPIN_THRESHOLD (1 << 15)
extern struct static_key paravirt_ticketlocks_enabled;
static __always_inline bool static_key_false(struct static_key *key);
-#ifdef CONFIG_QUEUED_SPINLOCKS
#include <asm/qspinlock.h>
-#else
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-
-static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
-{
- set_bit(0, (volatile unsigned long *)&lock->tickets.head);
-}
-
-#else /* !CONFIG_PARAVIRT_SPINLOCKS */
-static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock,
- __ticket_t ticket)
-{
-}
-static inline void __ticket_unlock_kick(arch_spinlock_t *lock,
- __ticket_t ticket)
-{
-}
-
-#endif /* CONFIG_PARAVIRT_SPINLOCKS */
-static inline int __tickets_equal(__ticket_t one, __ticket_t two)
-{
- return !((one ^ two) & ~TICKET_SLOWPATH_FLAG);
-}
-
-static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock,
- __ticket_t head)
-{
- if (head & TICKET_SLOWPATH_FLAG) {
- arch_spinlock_t old, new;
-
- old.tickets.head = head;
- new.tickets.head = head & ~TICKET_SLOWPATH_FLAG;
- old.tickets.tail = new.tickets.head + TICKET_LOCK_INC;
- new.tickets.tail = old.tickets.tail;
-
- /* try to clear slowpath flag when there are no contenders */
- cmpxchg(&lock->head_tail, old.head_tail, new.head_tail);
- }
-}
-
-static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
-{
- return __tickets_equal(lock.tickets.head, lock.tickets.tail);
-}
-
-/*
- * Ticket locks are conceptually two parts, one indicating the current head of
- * the queue, and the other indicating the current tail. The lock is acquired
- * by atomically noting the tail and incrementing it by one (thus adding
- * ourself to the queue and noting our position), then waiting until the head
- * becomes equal to the the initial value of the tail.
- *
- * We use an xadd covering *both* parts of the lock, to increment the tail and
- * also load the position of the head, which takes care of memory ordering
- * issues and should be optimal for the uncontended case. Note the tail must be
- * in the high part, because a wide xadd increment of the low part would carry
- * up and contaminate the high part.
- */
-static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
-{
- register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC };
-
- inc = xadd(&lock->tickets, inc);
- if (likely(inc.head == inc.tail))
- goto out;
-
- for (;;) {
- unsigned count = SPIN_THRESHOLD;
-
- do {
- inc.head = READ_ONCE(lock->tickets.head);
- if (__tickets_equal(inc.head, inc.tail))
- goto clear_slowpath;
- cpu_relax();
- } while (--count);
- __ticket_lock_spinning(lock, inc.tail);
- }
-clear_slowpath:
- __ticket_check_and_clear_slowpath(lock, inc.head);
-out:
- barrier(); /* make sure nothing creeps before the lock is taken */
-}
-
-static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
-{
- arch_spinlock_t old, new;
-
- old.tickets = READ_ONCE(lock->tickets);
- if (!__tickets_equal(old.tickets.head, old.tickets.tail))
- return 0;
-
- new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT);
- new.head_tail &= ~TICKET_SLOWPATH_FLAG;
-
- /* cmpxchg is a full barrier, so nothing can move before it */
- return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail;
-}
-
-static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
- if (TICKET_SLOWPATH_FLAG &&
- static_key_false(&paravirt_ticketlocks_enabled)) {
- __ticket_t head;
-
- BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
-
- head = xadd(&lock->tickets.head, TICKET_LOCK_INC);
-
- if (unlikely(head & TICKET_SLOWPATH_FLAG)) {
- head &= ~TICKET_SLOWPATH_FLAG;
- __ticket_unlock_kick(lock, (head + TICKET_LOCK_INC));
- }
- } else
- __add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
-}
-
-static inline int arch_spin_is_locked(arch_spinlock_t *lock)
-{
- struct __raw_tickets tmp = READ_ONCE(lock->tickets);
-
- return !__tickets_equal(tmp.tail, tmp.head);
-}
-
-static inline int arch_spin_is_contended(arch_spinlock_t *lock)
-{
- struct __raw_tickets tmp = READ_ONCE(lock->tickets);
-
- tmp.head &= ~TICKET_SLOWPATH_FLAG;
- return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
-}
-#define arch_spin_is_contended arch_spin_is_contended
-
-static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
- unsigned long flags)
-{
- arch_spin_lock(lock);
-}
-
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
- __ticket_t head = READ_ONCE(lock->tickets.head);
-
- for (;;) {
- struct __raw_tickets tmp = READ_ONCE(lock->tickets);
- /*
- * We need to check "unlocked" in a loop, tmp.head == head
- * can be false positive because of overflow.
- */
- if (__tickets_equal(tmp.head, tmp.tail) ||
- !__tickets_equal(tmp.head, head))
- break;
-
- cpu_relax();
- }
-}
-#endif /* CONFIG_QUEUED_SPINLOCKS */
/*
* Read-write spinlocks, allowing multiple readers
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 65c3e37f879a..25311ebb446c 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -23,20 +23,7 @@ typedef u32 __ticketpair_t;
#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
-#ifdef CONFIG_QUEUED_SPINLOCKS
#include <asm-generic/qspinlock_types.h>
-#else
-typedef struct arch_spinlock {
- union {
- __ticketpair_t head_tail;
- struct __raw_tickets {
- __ticket_t head, tail;
- } tickets;
- };
-} arch_spinlock_t;
-
-#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } }
-#endif /* CONFIG_QUEUED_SPINLOCKS */
#include <asm-generic/qrwlock_types.h>
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 0944218af9e2..37f2e0b377ad 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -8,86 +8,86 @@
#include <linux/uaccess.h>
#include <linux/ptrace.h>
+#include <asm/switch_to.h>
+
+enum stack_type {
+ STACK_TYPE_UNKNOWN,
+ STACK_TYPE_TASK,
+ STACK_TYPE_IRQ,
+ STACK_TYPE_SOFTIRQ,
+ STACK_TYPE_EXCEPTION,
+ STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
+};
-extern int kstack_depth_to_print;
-
-struct thread_info;
-struct stacktrace_ops;
-
-typedef unsigned long (*walk_stack_t)(struct task_struct *task,
- unsigned long *stack,
- unsigned long bp,
- const struct stacktrace_ops *ops,
- void *data,
- unsigned long *end,
- int *graph);
-
-extern unsigned long
-print_context_stack(struct task_struct *task,
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data,
- unsigned long *end, int *graph);
-
-extern unsigned long
-print_context_stack_bp(struct task_struct *task,
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data,
- unsigned long *end, int *graph);
-
-/* Generic stack tracer with callbacks */
-
-struct stacktrace_ops {
- int (*address)(void *data, unsigned long address, int reliable);
- /* On negative return stop dumping */
- int (*stack)(void *data, char *name);
- walk_stack_t walk_stack;
+struct stack_info {
+ enum stack_type type;
+ unsigned long *begin, *end, *next_sp;
};
-void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data);
+bool in_task_stack(unsigned long *stack, struct task_struct *task,
+ struct stack_info *info);
+
+int get_stack_info(unsigned long *stack, struct task_struct *task,
+ struct stack_info *info, unsigned long *visit_mask);
+
+void stack_type_str(enum stack_type type, const char **begin,
+ const char **end);
+
+static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
+{
+ void *begin = info->begin;
+ void *end = info->end;
+
+ return (info->type != STACK_TYPE_UNKNOWN &&
+ addr >= begin && addr < end &&
+ addr + len > begin && addr + len <= end);
+}
+
+extern int kstack_depth_to_print;
#ifdef CONFIG_X86_32
#define STACKSLOTS_PER_LINE 8
-#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
#else
#define STACKSLOTS_PER_LINE 4
-#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
#endif
#ifdef CONFIG_FRAME_POINTER
-static inline unsigned long
-stack_frame(struct task_struct *task, struct pt_regs *regs)
+static inline unsigned long *
+get_frame_pointer(struct task_struct *task, struct pt_regs *regs)
{
- unsigned long bp;
-
if (regs)
- return regs->bp;
+ return (unsigned long *)regs->bp;
- if (task == current) {
- /* Grab bp right from our regs */
- get_bp(bp);
- return bp;
- }
+ if (task == current)
+ return __builtin_frame_address(0);
- /* bp is the last reg pushed by switch_to */
- return *(unsigned long *)task->thread.sp;
+ return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp;
}
#else
-static inline unsigned long
-stack_frame(struct task_struct *task, struct pt_regs *regs)
+static inline unsigned long *
+get_frame_pointer(struct task_struct *task, struct pt_regs *regs)
{
- return 0;
+ return NULL;
+}
+#endif /* CONFIG_FRAME_POINTER */
+
+static inline unsigned long *
+get_stack_pointer(struct task_struct *task, struct pt_regs *regs)
+{
+ if (regs)
+ return (unsigned long *)kernel_stack_pointer(regs);
+
+ if (task == current)
+ return __builtin_frame_address(0);
+
+ return (unsigned long *)task->thread.sp;
}
-#endif
-extern void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp, char *log_lvl);
+void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+ unsigned long *stack, char *log_lvl);
-extern void
-show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp, char *log_lvl);
+void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+ unsigned long *sp, char *log_lvl);
extern unsigned int code_bytes;
@@ -106,7 +106,7 @@ static inline unsigned long caller_frame_pointer(void)
{
struct stack_frame *frame;
- get_bp(frame);
+ frame = __builtin_frame_address(0);
#ifdef CONFIG_FRAME_POINTER
frame = frame->next_frame;
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 90dbbd9666d4..a164862d77e3 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -2,6 +2,7 @@
#define _ASM_X86_STRING_64_H
#ifdef __KERNEL__
+#include <linux/jump_label.h>
/* Written 2002 by Andi Kleen */
@@ -78,6 +79,9 @@ int strcmp(const char *cs, const char *ct);
#define memset(s, c, n) __memset(s, c, n)
#endif
+__must_check int memcpy_mcsafe_unrolled(void *dst, const void *src, size_t cnt);
+DECLARE_STATIC_KEY_FALSE(mcsafe_key);
+
/**
* memcpy_mcsafe - copy memory with indication if a machine check happened
*
@@ -86,10 +90,23 @@ int strcmp(const char *cs, const char *ct);
* @cnt: number of bytes to copy
*
* Low level memory copy function that catches machine checks
+ * We only call into the "safe" function on systems that can
+ * actually do machine check recovery. Everyone else can just
+ * use memcpy().
*
* Return 0 for success, -EFAULT for fail
*/
-int memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+static __always_inline __must_check int
+memcpy_mcsafe(void *dst, const void *src, size_t cnt)
+{
+#ifdef CONFIG_X86_MCE
+ if (static_branch_unlikely(&mcsafe_key))
+ return memcpy_mcsafe_unrolled(dst, src, cnt);
+ else
+#endif
+ memcpy(dst, src, cnt);
+ return 0;
+}
#endif /* __KERNEL__ */
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 8f321a1b03a1..5cb436acd463 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -2,130 +2,66 @@
#define _ASM_X86_SWITCH_TO_H
struct task_struct; /* one of the stranger aspects of C forward declarations */
+
+struct task_struct *__switch_to_asm(struct task_struct *prev,
+ struct task_struct *next);
+
__visible struct task_struct *__switch_to(struct task_struct *prev,
- struct task_struct *next);
+ struct task_struct *next);
struct tss_struct;
void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
struct tss_struct *tss);
-#ifdef CONFIG_X86_32
+/* This runs runs on the previous thread's stack. */
+static inline void prepare_switch_to(struct task_struct *prev,
+ struct task_struct *next)
+{
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * If we switch to a stack that has a top-level paging entry
+ * that is not present in the current mm, the resulting #PF will
+ * will be promoted to a double-fault and we'll panic. Probe
+ * the new stack now so that vmalloc_fault can fix up the page
+ * tables if needed. This can only happen if we use a stack
+ * in vmap space.
+ *
+ * We assume that the stack is aligned so that it never spans
+ * more than one top-level paging entry.
+ *
+ * To minimize cache pollution, just follow the stack pointer.
+ */
+ READ_ONCE(*(unsigned char *)next->thread.sp);
+#endif
+}
+
+asmlinkage void ret_from_fork(void);
+
+/* data that is pointed to by thread.sp */
+struct inactive_task_frame {
+#ifdef CONFIG_X86_64
+ unsigned long r15;
+ unsigned long r14;
+ unsigned long r13;
+ unsigned long r12;
+#else
+ unsigned long si;
+ unsigned long di;
+#endif
+ unsigned long bx;
+ unsigned long bp;
+ unsigned long ret_addr;
+};
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary \
- "movl %P[task_canary](%[next]), %%ebx\n\t" \
- "movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
-#define __switch_canary_oparam \
- , [stack_canary] "=m" (stack_canary.canary)
-#define __switch_canary_iparam \
- , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else /* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif /* CC_STACKPROTECTOR */
+struct fork_frame {
+ struct inactive_task_frame frame;
+ struct pt_regs regs;
+};
-/*
- * Saving eflags is important. It switches not only IOPL between tasks,
- * it also protects other tasks from NT leaking through sysenter etc.
- */
#define switch_to(prev, next, last) \
do { \
- /* \
- * Context-switching clobbers all registers, so we clobber \
- * them explicitly, via unused output variables. \
- * (EAX and EBP is not listed because EBP is saved/restored \
- * explicitly for wchan access and EAX is the return value of \
- * __switch_to()) \
- */ \
- unsigned long ebx, ecx, edx, esi, edi; \
- \
- asm volatile("pushl %%ebp\n\t" /* save EBP */ \
- "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \
- "movl %[next_sp],%%esp\n\t" /* restore ESP */ \
- "movl $1f,%[prev_ip]\n\t" /* save EIP */ \
- "pushl %[next_ip]\n\t" /* restore EIP */ \
- __switch_canary \
- "jmp __switch_to\n" /* regparm call */ \
- "1:\t" \
- "popl %%ebp\n\t" /* restore EBP */ \
- \
- /* output parameters */ \
- : [prev_sp] "=m" (prev->thread.sp), \
- [prev_ip] "=m" (prev->thread.ip), \
- "=a" (last), \
- \
- /* clobbered output registers: */ \
- "=b" (ebx), "=c" (ecx), "=d" (edx), \
- "=S" (esi), "=D" (edi) \
- \
- __switch_canary_oparam \
- \
- /* input parameters: */ \
- : [next_sp] "m" (next->thread.sp), \
- [next_ip] "m" (next->thread.ip), \
- \
- /* regparm parameters for __switch_to(): */ \
- [prev] "a" (prev), \
- [next] "d" (next) \
+ prepare_switch_to(prev, next); \
\
- __switch_canary_iparam \
- \
- : /* reloaded segment registers */ \
- "memory"); \
+ ((last) = __switch_to_asm((prev), (next))); \
} while (0)
-#else /* CONFIG_X86_32 */
-
-/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
-
-#define __EXTRA_CLOBBER \
- , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
- "r12", "r13", "r14", "r15", "flags"
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary \
- "movq %P[task_canary](%%rsi),%%r8\n\t" \
- "movq %%r8,"__percpu_arg([gs_canary])"\n\t"
-#define __switch_canary_oparam \
- , [gs_canary] "=m" (irq_stack_union.stack_canary)
-#define __switch_canary_iparam \
- , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else /* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif /* CC_STACKPROTECTOR */
-
-/*
- * There is no need to save or restore flags, because flags are always
- * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL
- * has no effect.
- */
-#define switch_to(prev, next, last) \
- asm volatile(SAVE_CONTEXT \
- "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
- "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \
- "call __switch_to\n\t" \
- "movq "__percpu_arg([current_task])",%%rsi\n\t" \
- __switch_canary \
- "movq %P[thread_info](%%rsi),%%r8\n\t" \
- "movq %%rax,%%rdi\n\t" \
- "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \
- "jnz ret_from_fork\n\t" \
- RESTORE_CONTEXT \
- : "=a" (last) \
- __switch_canary_oparam \
- : [next] "S" (next), [prev] "D" (prev), \
- [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
- [ti_flags] "i" (offsetof(struct thread_info, flags)), \
- [_tif_fork] "i" (_TIF_FORK), \
- [thread_info] "i" (offsetof(struct task_struct, stack)), \
- [current_task] "m" (current_task) \
- __switch_canary_iparam \
- : "memory", "cc" __EXTRA_CLOBBER)
-
-#endif /* CONFIG_X86_32 */
-
#endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 4e23dd15c661..e3c95e8e61c5 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task,
* TS_COMPAT is set for 32-bit syscall entries and then
* remains set until we return to user mode.
*/
- if (task_thread_info(task)->status & (TS_COMPAT|TS_I386_REGS_POKED))
+ if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED))
/*
* Sign-extend the value so (int)-EFOO becomes (long)-EFOO
* and will match correctly in comparisons.
@@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
- if (task_thread_info(task)->status & TS_COMPAT)
+ if (task->thread.status & TS_COMPAT)
switch (i) {
case 0:
if (!n--) break;
@@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
const unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
- if (task_thread_info(task)->status & TS_COMPAT)
+ if (task->thread.status & TS_COMPAT)
switch (i) {
case 0:
if (!n--) break;
@@ -234,18 +234,8 @@ static inline void syscall_set_arguments(struct task_struct *task,
static inline int syscall_get_arch(void)
{
-#ifdef CONFIG_IA32_EMULATION
- /*
- * TS_COMPAT is set for 32-bit syscall entry and then
- * remains set until we return to user mode.
- *
- * x32 tasks should be considered AUDIT_ARCH_X86_64.
- */
- if (task_thread_info(current)->status & TS_COMPAT)
- return AUDIT_ARCH_I386;
-#endif
- /* Both x32 and x86_64 are considered "64-bit". */
- return AUDIT_ARCH_X86_64;
+ /* x32 tasks should be considered AUDIT_ARCH_X86_64. */
+ return in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
}
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8b7c8d8e0852..2aaca53c0974 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -52,21 +52,6 @@ struct task_struct;
#include <asm/cpufeature.h>
#include <linux/atomic.h>
-struct thread_info {
- struct task_struct *task; /* main task structure */
- __u32 flags; /* low level flags */
- __u32 status; /* thread synchronous flags */
- __u32 cpu; /* current CPU */
-};
-
-#define INIT_THREAD_INFO(tsk) \
-{ \
- .task = &tsk, \
- .flags = 0, \
- .cpu = 0, \
-}
-
-#define init_thread_info (init_thread_union.thread_info)
#define init_stack (init_thread_union.stack)
#else /* !__ASSEMBLY__ */
@@ -95,7 +80,6 @@ struct thread_info {
#define TIF_UPROBE 12 /* breakpointed or singlestepping */
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
#define TIF_IA32 17 /* IA32 compatibility process */
-#define TIF_FORK 18 /* ret_from_fork */
#define TIF_NOHZ 19 /* in adaptive nohz mode */
#define TIF_MEMDIE 20 /* is terminating due to OOM killer */
#define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */
@@ -119,7 +103,6 @@ struct thread_info {
#define _TIF_UPROBE (1 << TIF_UPROBE)
#define _TIF_NOTSC (1 << TIF_NOTSC)
#define _TIF_IA32 (1 << TIF_IA32)
-#define _TIF_FORK (1 << TIF_FORK)
#define _TIF_NOHZ (1 << TIF_NOHZ)
#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG)
#define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP)
@@ -160,11 +143,6 @@ struct thread_info {
*/
#ifndef __ASSEMBLY__
-static inline struct thread_info *current_thread_info(void)
-{
- return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE);
-}
-
static inline unsigned long current_stack_pointer(void)
{
unsigned long sp;
@@ -226,60 +204,19 @@ static inline int arch_within_stack_frames(const void * const stack,
# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
#endif
-/*
- * ASM operand which evaluates to a 'thread_info' address of
- * the current task, if it is known that "reg" is exactly "off"
- * bytes below the top of the stack currently.
- *
- * ( The kernel stack's size is known at build time, it is usually
- * 2 or 4 pages, and the bottom of the kernel stack contains
- * the thread_info structure. So to access the thread_info very
- * quickly from assembly code we can calculate down from the
- * top of the kernel stack to the bottom, using constant,
- * build-time calculations only. )
- *
- * For example, to fetch the current thread_info->flags value into %eax
- * on x86-64 defconfig kernels, in syscall entry code where RSP is
- * currently at exactly SIZEOF_PTREGS bytes away from the top of the
- * stack:
- *
- * mov ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS), %eax
- *
- * will translate to:
- *
- * 8b 84 24 b8 c0 ff ff mov -0x3f48(%rsp), %eax
- *
- * which is below the current RSP by almost 16K.
- */
-#define ASM_THREAD_INFO(field, reg, off) ((field)+(off)-THREAD_SIZE)(reg)
-
#endif
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
#ifdef CONFIG_COMPAT
#define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */
#endif
-
#ifndef __ASSEMBLY__
-static inline bool in_ia32_syscall(void)
-{
#ifdef CONFIG_X86_32
- return true;
-#endif
-#ifdef CONFIG_IA32_EMULATION
- if (current_thread_info()->status & TS_COMPAT)
- return true;
+#define in_ia32_syscall() true
+#else
+#define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \
+ current->thread.status & TS_COMPAT)
#endif
- return false;
-}
/*
* Force syscall return via IRET by making it look as if there was
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index c3496619740a..01fd0a7f48cd 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -117,6 +117,12 @@ extern void ist_exit(struct pt_regs *regs);
extern void ist_begin_non_atomic(struct pt_regs *regs);
extern void ist_end_non_atomic(void);
+#ifdef CONFIG_VMAP_STACK
+void __noreturn handle_stack_overflow(const char *message,
+ struct pt_regs *regs,
+ unsigned long fault_address);
+#endif
+
/* Interrupts/Exceptions */
enum {
X86_TRAP_DE = 0, /* 0, Divide-by-zero */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index c3f291195294..2131c4ce7d8a 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -433,7 +433,11 @@ do { \
#define __get_user_asm_ex(x, addr, itype, rtype, ltype) \
asm volatile("1: mov"itype" %1,%"rtype"0\n" \
"2:\n" \
- _ASM_EXTABLE_EX(1b, 2b) \
+ ".section .fixup,\"ax\"\n" \
+ "3:xor"itype" %"rtype"0,%"rtype"0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE_EX(1b, 3b) \
: ltype(x) : "m" (__m(addr)))
#define __put_user_nocheck(x, ptr, size) \
@@ -705,7 +709,7 @@ static inline void copy_user_overflow(int size, unsigned long count)
WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
}
-static inline unsigned long __must_check
+static __always_inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
int sz = __compiletime_object_size(to);
@@ -725,7 +729,7 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
return n;
}
-static inline unsigned long __must_check
+static __always_inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long n)
{
int sz = __compiletime_object_size(from);
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
new file mode 100644
index 000000000000..c4b6d1cafa46
--- /dev/null
+++ b/arch/x86/include/asm/unwind.h
@@ -0,0 +1,73 @@
+#ifndef _ASM_X86_UNWIND_H
+#define _ASM_X86_UNWIND_H
+
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+
+struct unwind_state {
+ struct stack_info stack_info;
+ unsigned long stack_mask;
+ struct task_struct *task;
+ int graph_idx;
+#ifdef CONFIG_FRAME_POINTER
+ unsigned long *bp;
+#else
+ unsigned long *sp;
+#endif
+};
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs, unsigned long *first_frame);
+
+bool unwind_next_frame(struct unwind_state *state);
+
+static inline bool unwind_done(struct unwind_state *state)
+{
+ return state->stack_info.type == STACK_TYPE_UNKNOWN;
+}
+
+static inline
+void unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs, unsigned long *first_frame)
+{
+ first_frame = first_frame ? : get_stack_pointer(task, regs);
+
+ __unwind_start(state, task, regs, first_frame);
+}
+
+#ifdef CONFIG_FRAME_POINTER
+
+static inline
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+ if (unwind_done(state))
+ return NULL;
+
+ return state->bp + 1;
+}
+
+unsigned long unwind_get_return_address(struct unwind_state *state);
+
+#else /* !CONFIG_FRAME_POINTER */
+
+static inline
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+ return NULL;
+}
+
+static inline
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+ if (unwind_done(state))
+ return 0;
+
+ return ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ *state->sp, state->sp);
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
+#endif /* _ASM_X86_UNWIND_H */
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index cc44d926c17e..57ab86d94d64 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -49,14 +49,12 @@
#define UV_NET_ENDPOINT_INTD (is_uv1_hub() ? \
UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD)
#define UV_DESC_PSHIFT 49
-#define UV_PAYLOADQ_PNODE_SHIFT 49
+#define UV_PAYLOADQ_GNODE_SHIFT 49
#define UV_PTC_BASENAME "sgi_uv/ptc_statistics"
#define UV_BAU_BASENAME "sgi_uv/bau_tunables"
#define UV_BAU_TUNABLES_DIR "sgi_uv"
#define UV_BAU_TUNABLES_FILE "bau_tunables"
#define WHITESPACE " \t\n"
-#define uv_mmask ((1UL << uv_hub_info->m_val) - 1)
-#define uv_physnodeaddr(x) ((__pa((unsigned long)(x)) & uv_mmask))
#define cpubit_isset(cpu, bau_local_cpumask) \
test_bit((cpu), (bau_local_cpumask).bits)
@@ -387,6 +385,17 @@ struct uv2_3_bau_msg_header {
/* bits 127:120 */
};
+/* Abstracted BAU functions */
+struct bau_operations {
+ unsigned long (*read_l_sw_ack)(void);
+ unsigned long (*read_g_sw_ack)(int pnode);
+ unsigned long (*bau_gpa_to_offset)(unsigned long vaddr);
+ void (*write_l_sw_ack)(unsigned long mmr);
+ void (*write_g_sw_ack)(int pnode, unsigned long mmr);
+ void (*write_payload_first)(int pnode, unsigned long mmr);
+ void (*write_payload_last)(int pnode, unsigned long mmr);
+};
+
/*
* The activation descriptor:
* The format of the message to send, plus all accompanying control
@@ -655,6 +664,16 @@ static inline void write_gmmr_activation(int pnode, unsigned long mmr_image)
write_gmmr(pnode, UVH_LB_BAU_SB_ACTIVATION_CONTROL, mmr_image);
}
+static inline void write_mmr_proc_payload_first(int pnode, unsigned long mmr_image)
+{
+ write_gmmr(pnode, UV4H_LB_PROC_INTD_QUEUE_FIRST, mmr_image);
+}
+
+static inline void write_mmr_proc_payload_last(int pnode, unsigned long mmr_image)
+{
+ write_gmmr(pnode, UV4H_LB_PROC_INTD_QUEUE_LAST, mmr_image);
+}
+
static inline void write_mmr_payload_first(int pnode, unsigned long mmr_image)
{
write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, mmr_image);
@@ -700,6 +719,26 @@ static inline unsigned long read_gmmr_sw_ack(int pnode)
return read_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
}
+static inline void write_mmr_proc_sw_ack(unsigned long mr)
+{
+ uv_write_local_mmr(UV4H_LB_PROC_INTD_SOFT_ACK_CLEAR, mr);
+}
+
+static inline void write_gmmr_proc_sw_ack(int pnode, unsigned long mr)
+{
+ write_gmmr(pnode, UV4H_LB_PROC_INTD_SOFT_ACK_CLEAR, mr);
+}
+
+static inline unsigned long read_mmr_proc_sw_ack(void)
+{
+ return read_lmmr(UV4H_LB_PROC_INTD_SOFT_ACK_PENDING);
+}
+
+static inline unsigned long read_gmmr_proc_sw_ack(int pnode)
+{
+ return read_gmmr(pnode, UV4H_LB_PROC_INTD_SOFT_ACK_PENDING);
+}
+
static inline void write_mmr_data_config(int pnode, unsigned long mr)
{
uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, mr);
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 43dc55be524e..2444189cbe28 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -41,6 +41,8 @@ extern const struct vdso_image vdso_image_32;
extern void __init init_vdso_image(const struct vdso_image *image);
+extern int map_vdso_once(const struct vdso_image *image, unsigned long addr);
+
#endif /* __ASSEMBLER__ */
#endif /* _ASM_X86_VDSO_H */
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 2184943341bf..69a6e07e3149 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -26,6 +26,8 @@ struct mce {
__u32 socketid; /* CPU socket ID */
__u32 apicid; /* CPU initial apic ID */
__u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */
+ __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */
+ __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */
};
#define MCE_GET_RECORD_LEN _IOR('M', 1, int)
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index 3ac5032fae09..ae135de547f5 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -6,4 +6,10 @@
#define ARCH_GET_FS 0x1003
#define ARCH_GET_GS 0x1004
+#ifdef CONFIG_CHECKPOINT_RESTORE
+# define ARCH_MAP_VDSO_X32 0x2001
+# define ARCH_MAP_VDSO_32 0x2002
+# define ARCH_MAP_VDSO_64 0x2003
+#endif
+
#endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0503f5bfb18d..45257cf84370 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -125,6 +125,12 @@ obj-$(CONFIG_EFI) += sysfb_efi.o
obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
obj-$(CONFIG_TRACING) += tracepoint.o
+ifdef CONFIG_FRAME_POINTER
+obj-y += unwind_frame.o
+else
+obj-y += unwind_guess.o
+endif
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index 3242e591fa82..26b78d86f25a 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -1,6 +1,7 @@
obj-$(CONFIG_ACPI) += boot.o
obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o
obj-$(CONFIG_ACPI_APEI) += apei.o
+obj-$(CONFIG_ACPI_CPPC_LIB) += cppc_msr.o
ifneq ($(CONFIG_ACPI_PROCESSOR),)
obj-y += cstate.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 90d84c3eee53..32a7d70913ac 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -176,15 +176,10 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
return -EINVAL;
}
- if (!enabled) {
- ++disabled_cpus;
- return -EINVAL;
- }
-
if (boot_cpu_physical_apicid != -1U)
- ver = apic_version[boot_cpu_physical_apicid];
+ ver = boot_cpu_apic_version;
- cpu = generic_processor_info(id, ver);
+ cpu = __generic_processor_info(id, ver, enabled);
if (cpu >= 0)
early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
@@ -282,6 +277,8 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
if (BAD_MADT_ENTRY(lapic_addr_ovr, end))
return -EINVAL;
+ acpi_table_print_madt_entry(header);
+
acpi_lapic_addr = lapic_addr_ovr->address;
return 0;
@@ -705,7 +702,7 @@ static void __init acpi_set_irq_model_ioapic(void)
#ifdef CONFIG_ACPI_HOTPLUG_CPU
#include <acpi/processor.h>
-static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
{
#ifdef CONFIG_ACPI_NUMA
int nid;
@@ -716,6 +713,7 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
numa_set_node(cpu, nid);
}
#endif
+ return 0;
}
int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu)
@@ -998,21 +996,6 @@ static int __init acpi_parse_madt_lapic_entries(void)
if (!boot_cpu_has(X86_FEATURE_APIC))
return -ENODEV;
- /*
- * Note that the LAPIC address is obtained from the MADT (32-bit value)
- * and (optionally) overridden by a LAPIC_ADDR_OVR entry (64-bit value).
- */
-
- count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE,
- acpi_parse_lapic_addr_ovr, 0);
- if (count < 0) {
- printk(KERN_ERR PREFIX
- "Error parsing LAPIC address override entry\n");
- return count;
- }
-
- register_lapic_address(acpi_lapic_addr);
-
count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
acpi_parse_sapic, MAX_LOCAL_APIC);
@@ -1031,8 +1014,8 @@ static int __init acpi_parse_madt_lapic_entries(void)
return ret;
}
- x2count = madt_proc[0].count;
- count = madt_proc[1].count;
+ count = madt_proc[0].count;
+ x2count = madt_proc[1].count;
}
if (!count && !x2count) {
printk(KERN_ERR PREFIX "No LAPIC entries present\n");
@@ -1513,7 +1496,7 @@ void __init acpi_boot_table_init(void)
* If acpi_disabled, bail out
*/
if (acpi_disabled)
- return;
+ return;
/*
* Initialize the ACPI boot-time table parser.
diff --git a/arch/x86/kernel/acpi/cppc_msr.c b/arch/x86/kernel/acpi/cppc_msr.c
new file mode 100644
index 000000000000..6fb478bf82fd
--- /dev/null
+++ b/arch/x86/kernel/acpi/cppc_msr.c
@@ -0,0 +1,58 @@
+/*
+ * cppc_msr.c: MSR Interface for CPPC
+ * Copyright (c) 2016, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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 <acpi/cppc_acpi.h>
+#include <asm/msr.h>
+
+/* Refer to drivers/acpi/cppc_acpi.c for the description of functions */
+
+bool cpc_ffh_supported(void)
+{
+ return true;
+}
+
+int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
+{
+ int err;
+
+ err = rdmsrl_safe_on_cpu(cpunum, reg->address, val);
+ if (!err) {
+ u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
+ reg->bit_offset);
+
+ *val &= mask;
+ *val >>= reg->bit_offset;
+ }
+ return err;
+}
+
+int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
+{
+ u64 rd_val;
+ int err;
+
+ err = rdmsrl_safe_on_cpu(cpunum, reg->address, &rd_val);
+ if (!err) {
+ u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
+ reg->bit_offset);
+
+ val <<= reg->bit_offset;
+ val &= mask;
+ rd_val &= ~mask;
+ rd_val |= val;
+ err = wrmsrl_safe_on_cpu(cpunum, reg->address, rd_val);
+ }
+ return err;
+}
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index adb3eaf8fe2a..48587335ede8 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -99,7 +99,7 @@ int x86_acpi_suspend_lowlevel(void)
saved_magic = 0x12345678;
#else /* CONFIG_64BIT */
#ifdef CONFIG_SMP
- stack_start = (unsigned long)temp_stack + sizeof(temp_stack);
+ initial_stack = (unsigned long)temp_stack + sizeof(temp_stack);
early_gdt_descr.address =
(unsigned long)get_cpu_gdt_table(smp_processor_id());
initial_gs = per_cpu_offset(smp_processor_id());
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 50c95af0f017..f266b8a92a9e 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -64,6 +64,8 @@ unsigned disabled_cpus;
unsigned int boot_cpu_physical_apicid = -1U;
EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
+u8 boot_cpu_apic_version;
+
/*
* The highest APIC ID seen during enumeration.
*/
@@ -1374,7 +1376,6 @@ void setup_local_APIC(void)
* Actually disabling the focus CPU check just makes the hang less
* frequent as it makes the interrupt distributon model be more
* like LRU than MRU (the short-term load is more even across CPUs).
- * See also the comment in end_level_ioapic_irq(). --macro
*/
/*
@@ -1816,8 +1817,7 @@ void __init init_apic_mappings(void)
* since smp_sanity_check is prepared for such a case
* and disable smp mode
*/
- apic_version[new_apicid] =
- GET_APIC_VERSION(apic_read(APIC_LVR));
+ boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
}
}
@@ -1828,17 +1828,14 @@ void __init register_lapic_address(unsigned long address)
if (!x2apic_mode) {
set_fixmap_nocache(FIX_APIC_BASE, address);
apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
- APIC_BASE, mp_lapic_addr);
+ APIC_BASE, address);
}
if (boot_cpu_physical_apicid == -1U) {
boot_cpu_physical_apicid = read_apic_id();
- apic_version[boot_cpu_physical_apicid] =
- GET_APIC_VERSION(apic_read(APIC_LVR));
+ boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
}
}
-int apic_version[MAX_LOCAL_APIC];
-
/*
* Local APIC interrupts
*/
@@ -2027,7 +2024,53 @@ void disconnect_bsp_APIC(int virt_wire_setup)
apic_write(APIC_LVT1, value);
}
-int generic_processor_info(int apicid, int version)
+/*
+ * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated
+ * contiguously, it equals to current allocated max logical CPU ID plus 1.
+ * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of
+ * nr_logical_cpuids is nr_cpu_ids.
+ *
+ * NOTE: Reserve 0 for BSP.
+ */
+static int nr_logical_cpuids = 1;
+
+/*
+ * Used to store mapping between logical CPU IDs and APIC IDs.
+ */
+static int cpuid_to_apicid[] = {
+ [0 ... NR_CPUS - 1] = -1,
+};
+
+/*
+ * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
+ * and cpuid_to_apicid[] synchronized.
+ */
+static int allocate_logical_cpuid(int apicid)
+{
+ int i;
+
+ /*
+ * cpuid <-> apicid mapping is persistent, so when a cpu is up,
+ * check if the kernel has allocated a cpuid for it.
+ */
+ for (i = 0; i < nr_logical_cpuids; i++) {
+ if (cpuid_to_apicid[i] == apicid)
+ return i;
+ }
+
+ /* Allocate a new cpuid. */
+ if (nr_logical_cpuids >= nr_cpu_ids) {
+ WARN_ONCE(1, "Only %d processors supported."
+ "Processor %d/0x%x and the rest are ignored.\n",
+ nr_cpu_ids - 1, nr_logical_cpuids, apicid);
+ return -1;
+ }
+
+ cpuid_to_apicid[nr_logical_cpuids] = apicid;
+ return nr_logical_cpuids++;
+}
+
+int __generic_processor_info(int apicid, int version, bool enabled)
{
int cpu, max = nr_cpu_ids;
bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
@@ -2093,7 +2136,6 @@ int generic_processor_info(int apicid, int version)
return -EINVAL;
}
- num_processors++;
if (apicid == boot_cpu_physical_apicid) {
/*
* x86_bios_cpu_apicid is required to have processors listed
@@ -2103,8 +2145,16 @@ int generic_processor_info(int apicid, int version)
* for BSP.
*/
cpu = 0;
- } else
- cpu = cpumask_next_zero(-1, cpu_present_mask);
+
+ /* Logical cpuid 0 is reserved for BSP. */
+ cpuid_to_apicid[0] = apicid;
+ } else {
+ cpu = allocate_logical_cpuid(apicid);
+ if (cpu < 0) {
+ disabled_cpus++;
+ return -EINVAL;
+ }
+ }
/*
* This can happen on physical hotplug. The sanity check at boot time
@@ -2116,6 +2166,7 @@ int generic_processor_info(int apicid, int version)
pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
thiscpu, apicid);
+
disabled_cpus++;
return -ENOSPC;
}
@@ -2128,14 +2179,12 @@ int generic_processor_info(int apicid, int version)
cpu, apicid);
version = 0x10;
}
- apic_version[apicid] = version;
- if (version != apic_version[boot_cpu_physical_apicid]) {
+ if (version != boot_cpu_apic_version) {
pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
- apic_version[boot_cpu_physical_apicid], cpu, version);
+ boot_cpu_apic_version, cpu, version);
}
- physid_set(apicid, phys_cpu_present_map);
if (apicid > max_physical_apicid)
max_physical_apicid = apicid;
@@ -2148,11 +2197,23 @@ int generic_processor_info(int apicid, int version)
apic->x86_32_early_logical_apicid(cpu);
#endif
set_cpu_possible(cpu, true);
- set_cpu_present(cpu, true);
+
+ if (enabled) {
+ num_processors++;
+ physid_set(apicid, phys_cpu_present_map);
+ set_cpu_present(cpu, true);
+ } else {
+ disabled_cpus++;
+ }
return cpu;
}
+int generic_processor_info(int apicid, int version)
+{
+ return __generic_processor_info(apicid, version, true);
+}
+
int hard_smp_processor_id(void)
{
return read_apic_id();
@@ -2275,7 +2336,7 @@ int __init APIC_init_uniprocessor(void)
* Complain if the BIOS pretends there is one.
*/
if (!boot_cpu_has(X86_FEATURE_APIC) &&
- APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+ APIC_INTEGRATED(boot_cpu_apic_version)) {
pr_err("BIOS bug, local APIC 0x%x not detected!...\n",
boot_cpu_physical_apicid);
return -1;
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 5b2ae106bd4a..a4d7ff20ed22 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -25,7 +25,7 @@
static struct apic apic_physflat;
static struct apic apic_flat;
-struct apic __read_mostly *apic = &apic_flat;
+struct apic *apic __ro_after_init = &apic_flat;
EXPORT_SYMBOL_GPL(apic);
static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
@@ -116,27 +116,17 @@ static void flat_send_IPI_all(int vector)
static unsigned int flat_get_apic_id(unsigned long x)
{
- unsigned int id;
-
- id = (((x)>>24) & 0xFFu);
-
- return id;
+ return (x >> 24) & 0xFF;
}
static unsigned long set_apic_id(unsigned int id)
{
- unsigned long x;
-
- x = ((id & 0xFFu)<<24);
- return x;
+ return (id & 0xFF) << 24;
}
static unsigned int read_xapic_id(void)
{
- unsigned int id;
-
- id = flat_get_apic_id(apic_read(APIC_ID));
- return id;
+ return flat_get_apic_id(apic_read(APIC_ID));
}
static int flat_apic_id_registered(void)
@@ -154,7 +144,7 @@ static int flat_probe(void)
return 1;
}
-static struct apic apic_flat = {
+static struct apic apic_flat __ro_after_init = {
.name = "flat",
.probe = flat_probe,
.acpi_madt_oem_check = flat_acpi_madt_oem_check,
@@ -248,7 +238,7 @@ static int physflat_probe(void)
return 0;
}
-static struct apic apic_physflat = {
+static struct apic apic_physflat __ro_after_init = {
.name = "physical flat",
.probe = physflat_probe,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index c05688b2deff..b109e4389c92 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -108,7 +108,7 @@ static void noop_apic_write(u32 reg, u32 v)
WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic);
}
-struct apic apic_noop = {
+struct apic apic_noop __ro_after_init = {
.name = "noop",
.probe = noop_probe,
.acpi_madt_oem_check = NULL,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 714d4fda0d52..e08fe2c8dd8c 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -40,10 +40,7 @@ static unsigned int numachip1_get_apic_id(unsigned long x)
static unsigned long numachip1_set_apic_id(unsigned int id)
{
- unsigned long x;
-
- x = ((id & 0xffU) << 24);
- return x;
+ return (id & 0xff) << 24;
}
static unsigned int numachip2_get_apic_id(unsigned long x)
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 06dbaa458bfe..56012010332c 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -142,7 +142,7 @@ static int probe_bigsmp(void)
return dmi_bigsmp;
}
-static struct apic apic_bigsmp = {
+static struct apic apic_bigsmp __ro_after_init = {
.name = "bigsmp",
.probe = probe_bigsmp,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7491f417a8e4..48e6d84f173e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1593,7 +1593,7 @@ void __init setup_ioapic_ids_from_mpc(void)
* no meaning without the serial APIC bus.
*/
if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
- || APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+ || APIC_XAPIC(boot_cpu_apic_version))
return;
setup_ioapic_ids_from_mpc_nocheck();
}
@@ -2423,7 +2423,7 @@ static int io_apic_get_unique_id(int ioapic, int apic_id)
static u8 io_apic_unique_id(int idx, u8 id)
{
if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
- !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+ !APIC_XAPIC(boot_cpu_apic_version))
return io_apic_get_unique_id(idx, id);
else
return id;
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index ade25320df96..015bbf30e3e3 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -269,7 +269,7 @@ static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
hpet_msi_write(irq_data_get_irq_handler_data(data), msg);
}
-static struct irq_chip hpet_msi_controller = {
+static struct irq_chip hpet_msi_controller __ro_after_init = {
.name = "HPET-MSI",
.irq_unmask = hpet_msi_unmask,
.irq_mask = hpet_msi_mask,
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 7c43e716c158..c48264e202fd 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -72,7 +72,7 @@ static int probe_default(void)
return 1;
}
-static struct apic apic_default = {
+static struct apic apic_default __ro_after_init = {
.name = "default",
.probe = probe_default,
@@ -126,7 +126,7 @@ static struct apic apic_default = {
apic_driver(apic_default);
-struct apic *apic = &apic_default;
+struct apic *apic __ro_after_init = &apic_default;
EXPORT_SYMBOL_GPL(apic);
static int cmdline_apic __initdata;
@@ -152,7 +152,7 @@ early_param("apic", parse_apic);
void __init default_setup_apic_routing(void)
{
- int version = apic_version[boot_cpu_physical_apicid];
+ int version = boot_cpu_apic_version;
if (num_possible_cpus() > 8) {
switch (boot_cpu_data.x86_vendor) {
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 54f35d988025..200af5ae9662 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -227,7 +227,7 @@ static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask,
cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu));
}
-static struct apic apic_x2apic_cluster = {
+static struct apic apic_x2apic_cluster __ro_after_init = {
.name = "cluster x2apic",
.probe = x2apic_cluster_probe,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 4f13f54f1b1f..ff111f05a314 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -98,7 +98,7 @@ static int x2apic_phys_probe(void)
return apic == &apic_x2apic_phys;
}
-static struct apic apic_x2apic_phys = {
+static struct apic apic_x2apic_phys __ro_after_init = {
.name = "physical x2apic",
.probe = x2apic_phys_probe,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index cb0673c1e940..aeef53ce93e1 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -533,11 +533,8 @@ static unsigned int x2apic_get_apic_id(unsigned long x)
static unsigned long set_apic_id(unsigned int id)
{
- unsigned long x;
-
- /* maskout x2apic_extra_bits ? */
- x = id;
- return x;
+ /* CHECKME: Do we need to mask out the xapic extra bits? */
+ return id;
}
static unsigned int uv_read_apic_id(void)
@@ -560,7 +557,7 @@ static int uv_probe(void)
return apic == &apic_x2apic_uv_x;
}
-static struct apic __refdata apic_x2apic_uv_x = {
+static struct apic apic_x2apic_uv_x __ro_after_init = {
.name = "UV large system",
.probe = uv_probe,
@@ -927,7 +924,7 @@ static void uv_heartbeat(unsigned long ignored)
mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
}
-static void uv_heartbeat_enable(int cpu)
+static int uv_heartbeat_enable(unsigned int cpu)
{
while (!uv_cpu_scir_info(cpu)->enabled) {
struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer;
@@ -941,43 +938,24 @@ static void uv_heartbeat_enable(int cpu)
/* also ensure that boot cpu is enabled */
cpu = 0;
}
+ return 0;
}
#ifdef CONFIG_HOTPLUG_CPU
-static void uv_heartbeat_disable(int cpu)
+static int uv_heartbeat_disable(unsigned int cpu)
{
if (uv_cpu_scir_info(cpu)->enabled) {
uv_cpu_scir_info(cpu)->enabled = 0;
del_timer(&uv_cpu_scir_info(cpu)->timer);
}
uv_set_cpu_scir_bits(cpu, 0xff);
-}
-
-/*
- * cpu hotplug notifier
- */
-static int uv_scir_cpu_notify(struct notifier_block *self, unsigned long action,
- void *hcpu)
-{
- long cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_DOWN_FAILED:
- case CPU_ONLINE:
- uv_heartbeat_enable(cpu);
- break;
- case CPU_DOWN_PREPARE:
- uv_heartbeat_disable(cpu);
- break;
- default:
- break;
- }
- return NOTIFY_OK;
+ return 0;
}
static __init void uv_scir_register_cpu_notifier(void)
{
- hotcpu_notifier(uv_scir_cpu_notify, 0);
+ cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/x2apic-uvx:online",
+ uv_heartbeat_enable, uv_heartbeat_disable);
}
#else /* !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 2bd5c6ff7ee7..c62e015b126c 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -29,10 +29,13 @@
void common(void) {
BLANK();
- OFFSET(TI_flags, thread_info, flags);
- OFFSET(TI_status, thread_info, status);
+ OFFSET(TASK_threadsp, task_struct, thread.sp);
+#ifdef CONFIG_CC_STACKPROTECTOR
+ OFFSET(TASK_stack_canary, task_struct, stack_canary);
+#endif
BLANK();
+ OFFSET(TASK_TI_flags, task_struct, thread_info.flags);
OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
BLANK();
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index ecdc1d217dc0..880aa093268d 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -57,6 +57,11 @@ void foo(void)
/* Size of SYSENTER_stack */
DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
+#ifdef CONFIG_CC_STACKPROTECTOR
+ BLANK();
+ OFFSET(stack_canary_offset, stack_canary, canary);
+#endif
+
#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
BLANK();
OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index d875f97d4e0b..210927ee2e74 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -56,6 +56,11 @@ int main(void)
OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
BLANK();
+#ifdef CONFIG_CC_STACKPROTECTOR
+ DEFINE(stack_canary_offset, offsetof(union irq_stack_union, stack_canary));
+ BLANK();
+#endif
+
DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
DEFINE(NR_syscalls, sizeof(syscalls_64));
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 809eda03c527..9bd910a7dd0a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -804,21 +804,20 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
identify_cpu_without_cpuid(c);
/* cyrix could have cpuid enabled via c_identify()*/
- if (!have_cpuid_p())
- return;
-
- cpu_detect(c);
- get_cpu_vendor(c);
- get_cpu_cap(c);
+ if (have_cpuid_p()) {
+ cpu_detect(c);
+ get_cpu_vendor(c);
+ get_cpu_cap(c);
- if (this_cpu->c_early_init)
- this_cpu->c_early_init(c);
+ if (this_cpu->c_early_init)
+ this_cpu->c_early_init(c);
- c->cpu_index = 0;
- filter_cpuid_features(c, false);
+ c->cpu_index = 0;
+ filter_cpuid_features(c, false);
- if (this_cpu->c_bsp_init)
- this_cpu->c_bsp_init(c);
+ if (this_cpu->c_bsp_init)
+ this_cpu->c_bsp_init(c);
+ }
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
fpu__init_system(c);
@@ -1265,9 +1264,14 @@ static __init int setup_disablecpuid(char *arg)
__setup("clearcpuid=", setup_disablecpuid);
#ifdef CONFIG_X86_64
-struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
-struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
- (unsigned long) debug_idt_table };
+struct desc_ptr idt_descr __ro_after_init = {
+ .size = NR_VECTORS * 16 - 1,
+ .address = (unsigned long) idt_table,
+};
+const struct desc_ptr debug_idt_descr = {
+ .size = NR_VECTORS * 16 - 1,
+ .address = (unsigned long) debug_idt_table,
+};
DEFINE_PER_CPU_FIRST(union irq_stack_union,
irq_stack_union) __aligned(PAGE_SIZE) __visible;
@@ -1281,7 +1285,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
EXPORT_PER_CPU_SYMBOL(current_task);
DEFINE_PER_CPU(char *, irq_stack_ptr) =
- init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
+ init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE;
DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
@@ -1305,11 +1309,6 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
/* May not be marked __init: used by software suspend */
void syscall_init(void)
{
- /*
- * LSTAR and STAR live in a bit strange symbiosis.
- * They both write to the same internal register. STAR allows to
- * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
- */
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 27e46658ebe3..35691a6b0d32 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -86,3 +86,14 @@ bool __init hypervisor_x2apic_available(void)
x86_hyper->x2apic_available &&
x86_hyper->x2apic_available();
}
+
+void hypervisor_pin_vcpu(int cpu)
+{
+ if (!x86_hyper)
+ return;
+
+ if (x86_hyper->pin_vcpu)
+ x86_hyper->pin_vcpu(cpu);
+ else
+ WARN_ONCE(1, "vcpu pinning requested but not supported!\n");
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 79d8ec849468..a7fdf453d895 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -41,6 +41,7 @@
#include <linux/debugfs.h>
#include <linux/irq_work.h>
#include <linux/export.h>
+#include <linux/jump_label.h>
#include <asm/processor.h>
#include <asm/traps.h>
@@ -292,6 +293,13 @@ static void print_mce(struct mce *m)
if (m->misc)
pr_cont("MISC %llx ", m->misc);
+ if (mce_flags.smca) {
+ if (m->synd)
+ pr_cont("SYND %llx ", m->synd);
+ if (m->ipid)
+ pr_cont("IPID %llx ", m->ipid);
+ }
+
pr_cont("\n");
/*
* Note this output is parsed by external tools and old fields
@@ -568,6 +576,7 @@ static void mce_read_aux(struct mce *m, int i)
{
if (m->status & MCI_STATUS_MISCV)
m->misc = mce_rdmsrl(msr_ops.misc(i));
+
if (m->status & MCI_STATUS_ADDRV) {
m->addr = mce_rdmsrl(msr_ops.addr(i));
@@ -579,6 +588,23 @@ static void mce_read_aux(struct mce *m, int i)
m->addr >>= shift;
m->addr <<= shift;
}
+
+ /*
+ * Extract [55:<lsb>] where lsb is the least significant
+ * *valid* bit of the address bits.
+ */
+ if (mce_flags.smca) {
+ u8 lsb = (m->addr >> 56) & 0x3f;
+
+ m->addr &= GENMASK_ULL(55, lsb);
+ }
+ }
+
+ if (mce_flags.smca) {
+ m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+
+ if (m->status & MCI_STATUS_SYNDV)
+ m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
}
}
@@ -1633,17 +1659,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
if (c->x86 == 6 && c->x86_model == 45)
quirk_no_way_out = quirk_sandybridge_ifu;
- /*
- * MCG_CAP.MCG_SER_P is necessary but not sufficient to know
- * whether this processor will actually generate recoverable
- * machine checks. Check to see if this is an E7 model Xeon.
- * We can't do a model number check because E5 and E7 use the
- * same model number. E5 doesn't support recovery, E7 does.
- */
- if (mca_cfg.recovery || (mca_cfg.ser &&
- !strncmp(c->x86_model_id,
- "Intel(R) Xeon(R) CPU E7-", 24)))
- set_cpu_cap(c, X86_FEATURE_MCE_RECOVERY);
}
if (cfg->monarch_timeout < 0)
cfg->monarch_timeout = 0;
@@ -2080,6 +2095,7 @@ void mce_disable_bank(int bank)
* mce=bootlog Log MCEs from before booting. Disabled by default on AMD.
* mce=nobootlog Don't log MCEs from before booting.
* mce=bios_cmci_threshold Don't program the CMCI threshold
+ * mce=recovery force enable memcpy_mcsafe()
*/
static int __init mcheck_enable(char *str)
{
@@ -2676,8 +2692,14 @@ static int __init mcheck_debugfs_init(void)
static int __init mcheck_debugfs_init(void) { return -EINVAL; }
#endif
+DEFINE_STATIC_KEY_FALSE(mcsafe_key);
+EXPORT_SYMBOL_GPL(mcsafe_key);
+
static int __init mcheck_late_init(void)
{
+ if (mca_cfg.recovery)
+ static_branch_inc(&mcsafe_key);
+
mcheck_debugfs_init();
/*
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 7b7f3be783d4..9b5403462936 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -20,6 +20,7 @@
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/smp.h>
+#include <linux/string.h>
#include <asm/amd_nb.h>
#include <asm/apic.h>
@@ -63,34 +64,71 @@ static const char * const th_names[] = {
"execution_unit",
};
-/* Define HWID to IP type mappings for Scalable MCA */
-struct amd_hwid amd_hwids[] = {
- [SMCA_F17H_CORE] = { "f17h_core", 0xB0 },
- [SMCA_DF] = { "data_fabric", 0x2E },
- [SMCA_UMC] = { "umc", 0x96 },
- [SMCA_PB] = { "param_block", 0x5 },
- [SMCA_PSP] = { "psp", 0xFF },
- [SMCA_SMU] = { "smu", 0x1 },
+static const char * const smca_umc_block_names[] = {
+ "dram_ecc",
+ "misc_umc"
};
-EXPORT_SYMBOL_GPL(amd_hwids);
-
-const char * const amd_core_mcablock_names[] = {
- [SMCA_LS] = "load_store",
- [SMCA_IF] = "insn_fetch",
- [SMCA_L2_CACHE] = "l2_cache",
- [SMCA_DE] = "decode_unit",
- [RES] = "",
- [SMCA_EX] = "execution_unit",
- [SMCA_FP] = "floating_point",
- [SMCA_L3_CACHE] = "l3_cache",
+
+struct smca_bank_name smca_bank_names[] = {
+ [SMCA_LS] = { "load_store", "Load Store Unit" },
+ [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" },
+ [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" },
+ [SMCA_DE] = { "decode_unit", "Decode Unit" },
+ [SMCA_EX] = { "execution_unit", "Execution Unit" },
+ [SMCA_FP] = { "floating_point", "Floating Point Unit" },
+ [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" },
+ [SMCA_CS] = { "coherent_slave", "Coherent Slave" },
+ [SMCA_PIE] = { "pie", "Power, Interrupts, etc." },
+ [SMCA_UMC] = { "umc", "Unified Memory Controller" },
+ [SMCA_PB] = { "param_block", "Parameter Block" },
+ [SMCA_PSP] = { "psp", "Platform Security Processor" },
+ [SMCA_SMU] = { "smu", "System Management Unit" },
};
-EXPORT_SYMBOL_GPL(amd_core_mcablock_names);
+EXPORT_SYMBOL_GPL(smca_bank_names);
+
+static struct smca_hwid_mcatype smca_hwid_mcatypes[] = {
+ /* { bank_type, hwid_mcatype, xec_bitmap } */
+
+ /* ZN Core (HWID=0xB0) MCA types */
+ { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF },
+ { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF },
+ { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF },
+ { SMCA_DE, HWID_MCATYPE(0xB0, 0x3), 0x1FF },
+ /* HWID 0xB0 MCATYPE 0x4 is Reserved */
+ { SMCA_EX, HWID_MCATYPE(0xB0, 0x5), 0x7FF },
+ { SMCA_FP, HWID_MCATYPE(0xB0, 0x6), 0x7F },
+ { SMCA_L3_CACHE, HWID_MCATYPE(0xB0, 0x7), 0xFF },
+
+ /* Data Fabric MCA types */
+ { SMCA_CS, HWID_MCATYPE(0x2E, 0x0), 0x1FF },
+ { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1), 0xF },
+
+ /* Unified Memory Controller MCA type */
+ { SMCA_UMC, HWID_MCATYPE(0x96, 0x0), 0x3F },
+
+ /* Parameter Block MCA type */
+ { SMCA_PB, HWID_MCATYPE(0x05, 0x0), 0x1 },
+
+ /* Platform Security Processor MCA type */
+ { SMCA_PSP, HWID_MCATYPE(0xFF, 0x0), 0x1 },
-const char * const amd_df_mcablock_names[] = {
- [SMCA_CS] = "coherent_slave",
- [SMCA_PIE] = "pie",
+ /* System Management Unit MCA type */
+ { SMCA_SMU, HWID_MCATYPE(0x01, 0x0), 0x1 },
};
-EXPORT_SYMBOL_GPL(amd_df_mcablock_names);
+
+struct smca_bank_info smca_banks[MAX_NR_BANKS];
+EXPORT_SYMBOL_GPL(smca_banks);
+
+/*
+ * In SMCA enabled processors, we can have multiple banks for a given IP type.
+ * So to define a unique name for each bank, we use a temp c-string to append
+ * the MCA_IPID[InstanceId] to type's name in get_name().
+ *
+ * InstanceId is 32 bits which is 8 characters. Make sure MAX_MCATYPE_NAME_LEN
+ * is greater than 8 plus 1 (for underscore) plus length of longest type name.
+ */
+#define MAX_MCATYPE_NAME_LEN 30
+static char buf_mcatype[MAX_MCATYPE_NAME_LEN];
static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
static DEFINE_PER_CPU(unsigned int, bank_map); /* see which banks are on */
@@ -108,6 +146,36 @@ void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
* CPU Initialization
*/
+static void get_smca_bank_info(unsigned int bank)
+{
+ unsigned int i, hwid_mcatype, cpu = smp_processor_id();
+ struct smca_hwid_mcatype *type;
+ u32 high, instanceId;
+ u16 hwid, mcatype;
+
+ /* Collect bank_info using CPU 0 for now. */
+ if (cpu)
+ return;
+
+ if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instanceId, &high)) {
+ pr_warn("Failed to read MCA_IPID for bank %d\n", bank);
+ return;
+ }
+
+ hwid = high & MCI_IPID_HWID;
+ mcatype = (high & MCI_IPID_MCATYPE) >> 16;
+ hwid_mcatype = HWID_MCATYPE(hwid, mcatype);
+
+ for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) {
+ type = &smca_hwid_mcatypes[i];
+ if (hwid_mcatype == type->hwid_mcatype) {
+ smca_banks[bank].type = type;
+ smca_banks[bank].type_instance = instanceId;
+ break;
+ }
+ }
+}
+
struct thresh_restart {
struct threshold_block *b;
int reset;
@@ -293,7 +361,7 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
wrmsr(MSR_CU_DEF_ERR, low, high);
}
-static u32 get_block_address(u32 current_addr, u32 low, u32 high,
+static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high,
unsigned int bank, unsigned int block)
{
u32 addr = 0, offset = 0;
@@ -309,13 +377,13 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
*/
u32 low, high;
- if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+ if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
return addr;
if (!(low & MCI_CONFIG_MCAX))
return addr;
- if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+ if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
(low & MASK_BLKPTR_LO))
addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
}
@@ -395,6 +463,20 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
*/
smca_high &= ~BIT(2);
+ /*
+ * SMCA sets the Deferred Error Interrupt type per bank.
+ *
+ * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us
+ * if the DeferredIntType bit field is available.
+ *
+ * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the
+ * high portion of the MSR). OS should set this to 0x1 to enable
+ * APIC based interrupt. First, check that no interrupt has been
+ * set.
+ */
+ if ((smca_low & BIT(5)) && !((smca_high >> 5) & 0x3))
+ smca_high |= BIT(5);
+
wrmsr(smca_addr, smca_low, smca_high);
}
@@ -421,12 +503,15 @@ out:
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
u32 low = 0, high = 0, address = 0;
- unsigned int bank, block;
+ unsigned int bank, block, cpu = smp_processor_id();
int offset = -1;
for (bank = 0; bank < mca_cfg.banks; ++bank) {
+ if (mce_flags.smca)
+ get_smca_bank_info(bank);
+
for (block = 0; block < NR_BLOCKS; ++block) {
- address = get_block_address(address, low, high, bank, block);
+ address = get_block_address(cpu, address, low, high, bank, block);
if (!address)
break;
@@ -476,9 +561,27 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
if (threshold_err)
m.misc = misc;
- if (m.status & MCI_STATUS_ADDRV)
+ if (m.status & MCI_STATUS_ADDRV) {
rdmsrl(msr_addr, m.addr);
+ /*
+ * Extract [55:<lsb>] where lsb is the least significant
+ * *valid* bit of the address bits.
+ */
+ if (mce_flags.smca) {
+ u8 lsb = (m.addr >> 56) & 0x3f;
+
+ m.addr &= GENMASK_ULL(55, lsb);
+ }
+ }
+
+ if (mce_flags.smca) {
+ rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m.ipid);
+
+ if (m.status & MCI_STATUS_SYNDV)
+ rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd);
+ }
+
mce_log(&m);
wrmsrl(msr_status, 0);
@@ -541,15 +644,14 @@ static void amd_deferred_error_interrupt(void)
static void amd_threshold_interrupt(void)
{
u32 low = 0, high = 0, address = 0;
- int cpu = smp_processor_id();
- unsigned int bank, block;
+ unsigned int bank, block, cpu = smp_processor_id();
/* assume first bank caused it */
for (bank = 0; bank < mca_cfg.banks; ++bank) {
if (!(per_cpu(bank_map, cpu) & (1 << bank)))
continue;
for (block = 0; block < NR_BLOCKS; ++block) {
- address = get_block_address(address, low, high, bank, block);
+ address = get_block_address(cpu, address, low, high, bank, block);
if (!address)
break;
@@ -713,6 +815,34 @@ static struct kobj_type threshold_ktype = {
.default_attrs = default_attrs,
};
+static const char *get_name(unsigned int bank, struct threshold_block *b)
+{
+ unsigned int bank_type;
+
+ if (!mce_flags.smca) {
+ if (b && bank == 4)
+ return bank4_names(b);
+
+ return th_names[bank];
+ }
+
+ if (!smca_banks[bank].type)
+ return NULL;
+
+ bank_type = smca_banks[bank].type->bank_type;
+
+ if (b && bank_type == SMCA_UMC) {
+ if (b->block < ARRAY_SIZE(smca_umc_block_names))
+ return smca_umc_block_names[b->block];
+ return NULL;
+ }
+
+ snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN,
+ "%s_%x", smca_bank_names[bank_type].name,
+ smca_banks[bank].type_instance);
+ return buf_mcatype;
+}
+
static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
unsigned int block, u32 address)
{
@@ -767,11 +897,11 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
err = kobject_init_and_add(&b->kobj, &threshold_ktype,
per_cpu(threshold_banks, cpu)[bank]->kobj,
- (bank == 4 ? bank4_names(b) : th_names[bank]));
+ get_name(bank, b));
if (err)
goto out_free;
recurse:
- address = get_block_address(address, low, high, bank, ++block);
+ address = get_block_address(cpu, address, low, high, bank, ++block);
if (!address)
return 0;
@@ -822,7 +952,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
struct device *dev = per_cpu(mce_device, cpu);
struct amd_northbridge *nb = NULL;
struct threshold_bank *b = NULL;
- const char *name = th_names[bank];
+ const char *name = get_name(bank, NULL);
int err = 0;
if (is_shared_bank(bank)) {
@@ -869,7 +999,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
}
}
- err = allocate_threshold_blocks(cpu, bank, 0, MSR_IA32_MCx_MISC(bank));
+ err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank));
if (!err)
goto out;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index b816971f5da4..620ab06bcf45 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -54,6 +54,7 @@ static LIST_HEAD(pcache);
*/
static u8 *container;
static size_t container_size;
+static bool ucode_builtin;
static u32 ucode_new_rev;
static u8 amd_ucode_patch[PATCH_MAX_SIZE];
@@ -281,18 +282,22 @@ static bool __init load_builtin_amd_microcode(struct cpio_data *cp,
void __init load_ucode_amd_bsp(unsigned int family)
{
struct cpio_data cp;
+ bool *builtin;
void **data;
size_t *size;
#ifdef CONFIG_X86_32
data = (void **)__pa_nodebug(&ucode_cpio.data);
size = (size_t *)__pa_nodebug(&ucode_cpio.size);
+ builtin = (bool *)__pa_nodebug(&ucode_builtin);
#else
data = &ucode_cpio.data;
size = &ucode_cpio.size;
+ builtin = &ucode_builtin;
#endif
- if (!load_builtin_amd_microcode(&cp, family))
+ *builtin = load_builtin_amd_microcode(&cp, family);
+ if (!*builtin)
cp = find_ucode_in_initrd();
if (!(cp.data && cp.size))
@@ -373,7 +378,8 @@ void load_ucode_amd_ap(void)
return;
/* Add CONFIG_RANDOMIZE_MEMORY offset. */
- cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+ if (!ucode_builtin)
+ cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
eax = cpuid_eax(0x00000001);
eq = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ);
@@ -439,7 +445,8 @@ int __init save_microcode_in_initrd_amd(void)
container = cont_va;
/* Add CONFIG_RANDOMIZE_MEMORY offset. */
- container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+ if (!ucode_builtin)
+ container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
eax = cpuid_eax(0x00000001);
eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index df04b2d033f6..5ce5155f0695 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -558,55 +558,36 @@ static struct syscore_ops mc_syscore_ops = {
.resume = mc_bp_resume,
};
-static int
-mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
+static int mc_cpu_online(unsigned int cpu)
{
- unsigned int cpu = (unsigned long)hcpu;
struct device *dev;
dev = get_cpu_device(cpu);
+ microcode_update_cpu(cpu);
+ pr_debug("CPU%d added\n", cpu);
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_ONLINE:
- microcode_update_cpu(cpu);
- pr_debug("CPU%d added\n", cpu);
- /*
- * "break" is missing on purpose here because we want to fall
- * through in order to create the sysfs group.
- */
-
- case CPU_DOWN_FAILED:
- if (sysfs_create_group(&dev->kobj, &mc_attr_group))
- pr_err("Failed to create group for CPU%d\n", cpu);
- break;
+ if (sysfs_create_group(&dev->kobj, &mc_attr_group))
+ pr_err("Failed to create group for CPU%d\n", cpu);
+ return 0;
+}
- case CPU_DOWN_PREPARE:
- /* Suspend is in progress, only remove the interface */
- sysfs_remove_group(&dev->kobj, &mc_attr_group);
- pr_debug("CPU%d removed\n", cpu);
- break;
+static int mc_cpu_down_prep(unsigned int cpu)
+{
+ struct device *dev;
+ dev = get_cpu_device(cpu);
+ /* Suspend is in progress, only remove the interface */
+ sysfs_remove_group(&dev->kobj, &mc_attr_group);
+ pr_debug("CPU%d removed\n", cpu);
/*
- * case CPU_DEAD:
- *
* When a CPU goes offline, don't free up or invalidate the copy of
* the microcode in kernel memory, so that we can reuse it when the
* CPU comes back online without unnecessarily requesting the userspace
* for it again.
*/
- }
-
- /* The CPU refused to come up during a system resume */
- if (action == CPU_UP_CANCELED_FROZEN)
- microcode_fini_cpu(cpu);
-
- return NOTIFY_OK;
+ return 0;
}
-static struct notifier_block mc_cpu_notifier = {
- .notifier_call = mc_cpu_callback,
-};
-
static struct attribute *cpu_root_microcode_attrs[] = {
&dev_attr_reload.attr,
NULL
@@ -665,7 +646,8 @@ int __init microcode_init(void)
goto out_ucode_group;
register_syscore_ops(&mc_syscore_ops);
- register_hotcpu_notifier(&mc_cpu_notifier);
+ cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
+ mc_cpu_online, mc_cpu_down_prep);
pr_info("Microcode Update Driver: v" MICROCODE_VERSION
" <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n");
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 28f1b54b7fad..24e87e74990d 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -72,14 +72,14 @@ static DEFINE_MUTEX(mtrr_mutex);
u64 size_or_mask, size_and_mask;
static bool mtrr_aps_delayed_init;
-static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM];
+static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM] __ro_after_init;
const struct mtrr_ops *mtrr_if;
static void set_mtrr(unsigned int reg, unsigned long base,
unsigned long size, mtrr_type type);
-void set_mtrr_ops(const struct mtrr_ops *ops)
+void __init set_mtrr_ops(const struct mtrr_ops *ops)
{
if (ops->vendor && ops->vendor < X86_VENDOR_NUM)
mtrr_ops[ops->vendor] = ops;
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 6c7ced07d16d..ad8bd763efa5 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -54,7 +54,7 @@ void fill_mtrr_var_range(unsigned int index,
bool get_mtrr_state(void);
void mtrr_bp_pat_init(void);
-extern void set_mtrr_ops(const struct mtrr_ops *ops);
+extern void __init set_mtrr_ops(const struct mtrr_ops *ops);
extern u64 size_or_mask, size_and_mask;
extern const struct mtrr_ops *mtrr_if;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 92e8f0a7159c..9b7cf5c28f5f 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -17,7 +17,7 @@
#include <linux/sysfs.h>
#include <asm/stacktrace.h>
-
+#include <asm/unwind.h>
int panic_on_unrecovered_nmi;
int panic_on_io_nmi;
@@ -25,11 +25,29 @@ unsigned int code_bytes = 64;
int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
static int die_counter;
+bool in_task_stack(unsigned long *stack, struct task_struct *task,
+ struct stack_info *info)
+{
+ unsigned long *begin = task_stack_page(task);
+ unsigned long *end = task_stack_page(task) + THREAD_SIZE;
+
+ if (stack < begin || stack >= end)
+ return false;
+
+ info->type = STACK_TYPE_TASK;
+ info->begin = begin;
+ info->end = end;
+ info->next_sp = NULL;
+
+ return true;
+}
+
static void printk_stack_address(unsigned long address, int reliable,
- void *data)
+ char *log_lvl)
{
+ touch_nmi_watchdog();
printk("%s [<%p>] %s%pB\n",
- (char *)data, (void *)address, reliable ? "" : "? ",
+ log_lvl, (void *)address, reliable ? "" : "? ",
(void *)address);
}
@@ -38,176 +56,120 @@ void printk_address(unsigned long address)
pr_cont(" [<%p>] %pS\n", (void *)address, (void *)address);
}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static void
-print_ftrace_graph_addr(unsigned long addr, void *data,
- const struct stacktrace_ops *ops,
- struct task_struct *task, int *graph)
+void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+ unsigned long *stack, char *log_lvl)
{
- unsigned long ret_addr;
- int index;
-
- if (addr != (unsigned long)return_to_handler)
- return;
-
- index = task->curr_ret_stack;
-
- if (!task->ret_stack || index < *graph)
- return;
-
- index -= *graph;
- ret_addr = task->ret_stack[index].ret;
-
- ops->address(data, ret_addr, 1);
+ struct unwind_state state;
+ struct stack_info stack_info = {0};
+ unsigned long visit_mask = 0;
+ int graph_idx = 0;
- (*graph)++;
-}
-#else
-static inline void
-print_ftrace_graph_addr(unsigned long addr, void *data,
- const struct stacktrace_ops *ops,
- struct task_struct *task, int *graph)
-{ }
-#endif
-
-/*
- * x86-64 can have up to three kernel stacks:
- * process stack
- * interrupt stack
- * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
- */
-
-static inline int valid_stack_ptr(struct task_struct *task,
- void *p, unsigned int size, void *end)
-{
- void *t = task_stack_page(task);
- if (end) {
- if (p < end && p >= (end-THREAD_SIZE))
- return 1;
- else
- return 0;
- }
- return p >= t && p < t + THREAD_SIZE - size;
-}
+ printk("%sCall Trace:\n", log_lvl);
-unsigned long
-print_context_stack(struct task_struct *task,
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data,
- unsigned long *end, int *graph)
-{
- struct stack_frame *frame = (struct stack_frame *)bp;
+ unwind_start(&state, task, regs, stack);
/*
- * If we overflowed the stack into a guard page, jump back to the
- * bottom of the usable stack.
+ * Iterate through the stacks, starting with the current stack pointer.
+ * Each stack has a pointer to the next one.
+ *
+ * x86-64 can have several stacks:
+ * - task stack
+ * - interrupt stack
+ * - HW exception stacks (double fault, nmi, debug, mce)
+ *
+ * x86-32 can have up to three stacks:
+ * - task stack
+ * - softirq stack
+ * - hardirq stack
*/
- if ((unsigned long)task_stack_page(task) - (unsigned long)stack <
- PAGE_SIZE)
- stack = (unsigned long *)task_stack_page(task);
-
- while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
- unsigned long addr;
-
- addr = *stack;
- if (__kernel_text_address(addr)) {
- if ((unsigned long) stack == bp + sizeof(long)) {
- ops->address(data, addr, 1);
- frame = frame->next_frame;
- bp = (unsigned long) frame;
- } else {
- ops->address(data, addr, 0);
- }
- print_ftrace_graph_addr(addr, data, ops, task, graph);
- }
- stack++;
- }
- return bp;
-}
-EXPORT_SYMBOL_GPL(print_context_stack);
-
-unsigned long
-print_context_stack_bp(struct task_struct *task,
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data,
- unsigned long *end, int *graph)
-{
- struct stack_frame *frame = (struct stack_frame *)bp;
- unsigned long *ret_addr = &frame->return_address;
+ for (; stack; stack = stack_info.next_sp) {
+ const char *str_begin, *str_end;
- while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) {
- unsigned long addr = *ret_addr;
+ /*
+ * 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 (!__kernel_text_address(addr))
+ if (get_stack_info(stack, task, &stack_info, &visit_mask))
break;
- if (ops->address(data, addr, 1))
- break;
- frame = frame->next_frame;
- ret_addr = &frame->return_address;
- print_ftrace_graph_addr(addr, data, ops, task, graph);
- }
-
- return (unsigned long)frame;
-}
-EXPORT_SYMBOL_GPL(print_context_stack_bp);
-
-static int print_trace_stack(void *data, char *name)
-{
- printk("%s <%s> ", (char *)data, name);
- return 0;
-}
-
-/*
- * Print one address/symbol entries per line.
- */
-static int print_trace_address(void *data, unsigned long addr, int reliable)
-{
- touch_nmi_watchdog();
- printk_stack_address(addr, reliable, data);
- return 0;
-}
-
-static const struct stacktrace_ops print_trace_ops = {
- .stack = print_trace_stack,
- .address = print_trace_address,
- .walk_stack = print_context_stack,
-};
-
-void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp, char *log_lvl)
-{
- printk("%sCall Trace:\n", log_lvl);
- dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-}
+ stack_type_str(stack_info.type, &str_begin, &str_end);
+ if (str_begin)
+ printk("%s <%s> ", log_lvl, str_begin);
+
+ /*
+ * Scan the stack, printing any text addresses we find. At the
+ * same time, follow proper stack frames with the unwinder.
+ *
+ * Addresses found during the scan which are not reported by
+ * the unwinder are considered to be additional clues which are
+ * sometimes useful for debugging and are prefixed with '?'.
+ * This also serves as a failsafe option in case the unwinder
+ * goes off in the weeds.
+ */
+ for (; stack < stack_info.end; stack++) {
+ unsigned long real_addr;
+ int reliable = 0;
+ unsigned long addr = *stack;
+ unsigned long *ret_addr_p =
+ unwind_get_return_address_ptr(&state);
+
+ if (!__kernel_text_address(addr))
+ continue;
+
+ if (stack == ret_addr_p)
+ reliable = 1;
+
+ /*
+ * When function graph tracing is enabled for a
+ * function, its return address on the stack is
+ * replaced with the address of an ftrace handler
+ * (return_to_handler). In that case, before printing
+ * the "real" address, we want to print the handler
+ * address as an "unreliable" hint that function graph
+ * tracing was involved.
+ */
+ real_addr = ftrace_graph_ret_addr(task, &graph_idx,
+ addr, stack);
+ if (real_addr != addr)
+ printk_stack_address(addr, 0, log_lvl);
+ printk_stack_address(real_addr, reliable, log_lvl);
+
+ if (!reliable)
+ continue;
+
+ /*
+ * Get the next frame from the unwinder. No need to
+ * check for an error: if anything goes wrong, the rest
+ * of the addresses will just be printed as unreliable.
+ */
+ unwind_next_frame(&state);
+ }
-void show_trace(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp)
-{
- show_trace_log_lvl(task, regs, stack, bp, "");
+ if (str_end)
+ printk("%s <%s> ", log_lvl, str_end);
+ }
}
void show_stack(struct task_struct *task, unsigned long *sp)
{
- unsigned long bp = 0;
- unsigned long stack;
+ task = task ? : current;
/*
* Stack frames below this one aren't interesting. Don't show them
* if we're printing for %current.
*/
- if (!sp && (!task || task == current)) {
- sp = &stack;
- bp = stack_frame(current, NULL);
- }
+ if (!sp && task == current)
+ sp = get_stack_pointer(current, NULL);
- show_stack_log_lvl(task, NULL, sp, bp, "");
+ show_stack_log_lvl(task, NULL, sp, "");
}
void show_stack_regs(struct pt_regs *regs)
{
- show_stack_log_lvl(current, regs, (unsigned long *)regs->sp, regs->bp, "");
+ show_stack_log_lvl(current, regs, NULL, "");
}
static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 09675712eba8..06eb322b5f9f 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -16,93 +16,121 @@
#include <asm/stacktrace.h>
-static void *is_irq_stack(void *p, void *irq)
+void stack_type_str(enum stack_type type, const char **begin, const char **end)
{
- if (p < irq || p >= (irq + THREAD_SIZE))
- return NULL;
- return irq + THREAD_SIZE;
+ switch (type) {
+ case STACK_TYPE_IRQ:
+ case STACK_TYPE_SOFTIRQ:
+ *begin = "IRQ";
+ *end = "EOI";
+ break;
+ default:
+ *begin = NULL;
+ *end = NULL;
+ }
}
-
-static void *is_hardirq_stack(unsigned long *stack, int cpu)
+static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
{
- void *irq = per_cpu(hardirq_stack, cpu);
+ unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack);
+ unsigned long *end = begin + (THREAD_SIZE / sizeof(long));
- return is_irq_stack(stack, irq);
-}
+ /*
+ * This is a software stack, so 'end' can be a valid stack pointer.
+ * It just means the stack is empty.
+ */
+ if (stack < begin || stack > end)
+ return false;
-static void *is_softirq_stack(unsigned long *stack, int cpu)
-{
- void *irq = per_cpu(softirq_stack, cpu);
+ info->type = STACK_TYPE_IRQ;
+ info->begin = begin;
+ info->end = end;
- return is_irq_stack(stack, irq);
+ /*
+ * See irq_32.c -- the next stack pointer is stored at the beginning of
+ * the stack.
+ */
+ info->next_sp = (unsigned long *)*begin;
+
+ return true;
}
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data)
+static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
{
- const unsigned cpu = get_cpu();
- int graph = 0;
- u32 *prev_esp;
+ unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack);
+ unsigned long *end = begin + (THREAD_SIZE / sizeof(long));
- if (!task)
- task = current;
+ /*
+ * This is a software stack, so 'end' can be a valid stack pointer.
+ * It just means the stack is empty.
+ */
+ if (stack < begin || stack > end)
+ return false;
- if (!stack) {
- unsigned long dummy;
+ info->type = STACK_TYPE_SOFTIRQ;
+ info->begin = begin;
+ info->end = end;
- stack = &dummy;
- if (task != current)
- stack = (unsigned long *)task->thread.sp;
- }
+ /*
+ * The next stack pointer is stored at the beginning of the stack.
+ * See irq_32.c.
+ */
+ info->next_sp = (unsigned long *)*begin;
- if (!bp)
- bp = stack_frame(task, regs);
+ return true;
+}
- for (;;) {
- void *end_stack;
+int get_stack_info(unsigned long *stack, struct task_struct *task,
+ struct stack_info *info, unsigned long *visit_mask)
+{
+ if (!stack)
+ goto unknown;
- end_stack = is_hardirq_stack(stack, cpu);
- if (!end_stack)
- end_stack = is_softirq_stack(stack, cpu);
+ task = task ? : current;
- bp = ops->walk_stack(task, stack, bp, ops, data,
- end_stack, &graph);
+ if (in_task_stack(stack, task, info))
+ goto recursion_check;
- /* Stop if not on irq stack */
- if (!end_stack)
- break;
+ if (task != current)
+ goto unknown;
- /* The previous esp is saved on the bottom of the stack */
- prev_esp = (u32 *)(end_stack - THREAD_SIZE);
- stack = (unsigned long *)*prev_esp;
- if (!stack)
- break;
+ if (in_hardirq_stack(stack, info))
+ goto recursion_check;
- if (ops->stack(data, "IRQ") < 0)
- break;
- touch_nmi_watchdog();
+ if (in_softirq_stack(stack, info))
+ goto recursion_check;
+
+ goto unknown;
+
+recursion_check:
+ /*
+ * Make sure we don't iterate through any given stack more than once.
+ * If it comes up a second time then there's something wrong going on:
+ * just break out and report an unknown stack type.
+ */
+ if (visit_mask) {
+ if (*visit_mask & (1UL << info->type))
+ goto unknown;
+ *visit_mask |= 1UL << info->type;
}
- put_cpu();
+
+ return 0;
+
+unknown:
+ info->type = STACK_TYPE_UNKNOWN;
+ return -EINVAL;
}
-EXPORT_SYMBOL(dump_trace);
-void
-show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp, char *log_lvl)
+void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+ unsigned long *sp, char *log_lvl)
{
unsigned long *stack;
int i;
- if (sp == NULL) {
- if (regs)
- sp = (unsigned long *)regs->sp;
- else if (task)
- sp = (unsigned long *)task->thread.sp;
- else
- sp = (unsigned long *)&sp;
- }
+ if (!try_get_task_stack(task))
+ return;
+
+ sp = sp ? : get_stack_pointer(task, regs);
stack = sp;
for (i = 0; i < kstack_depth_to_print; i++) {
@@ -117,7 +145,9 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
touch_nmi_watchdog();
}
pr_cont("\n");
- show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+ show_trace_log_lvl(task, regs, sp, log_lvl);
+
+ put_task_stack(task);
}
@@ -139,7 +169,7 @@ void show_regs(struct pt_regs *regs)
u8 *ip;
pr_emerg("Stack:\n");
- show_stack_log_lvl(NULL, regs, &regs->sp, 0, KERN_EMERG);
+ show_stack_log_lvl(current, regs, NULL, KERN_EMERG);
pr_emerg("Code:");
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 9ee4520ce83c..36cf1a498227 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -16,261 +16,145 @@
#include <asm/stacktrace.h>
+static char *exception_stack_names[N_EXCEPTION_STACKS] = {
+ [ DOUBLEFAULT_STACK-1 ] = "#DF",
+ [ NMI_STACK-1 ] = "NMI",
+ [ DEBUG_STACK-1 ] = "#DB",
+ [ MCE_STACK-1 ] = "#MC",
+};
-#define N_EXCEPTION_STACKS_END \
- (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
-
-static char x86_stack_ids[][8] = {
- [ DEBUG_STACK-1 ] = "#DB",
- [ NMI_STACK-1 ] = "NMI",
- [ DOUBLEFAULT_STACK-1 ] = "#DF",
- [ MCE_STACK-1 ] = "#MC",
-#if DEBUG_STKSZ > EXCEPTION_STKSZ
- [ N_EXCEPTION_STACKS ...
- N_EXCEPTION_STACKS_END ] = "#DB[?]"
-#endif
+static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
+ [DEBUG_STACK - 1] = DEBUG_STKSZ
};
-static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
- unsigned *usedp, char **idp)
+void stack_type_str(enum stack_type type, const char **begin, const char **end)
{
- unsigned k;
-
- /*
- * Iterate over all exception stacks, and figure out whether
- * 'stack' is in one of them:
- */
- for (k = 0; k < N_EXCEPTION_STACKS; k++) {
- unsigned long end = per_cpu(orig_ist, cpu).ist[k];
- /*
- * Is 'stack' above this exception frame's end?
- * If yes then skip to the next frame.
- */
- if (stack >= end)
- continue;
- /*
- * Is 'stack' above this exception frame's start address?
- * If yes then we found the right frame.
- */
- if (stack >= end - EXCEPTION_STKSZ) {
- /*
- * Make sure we only iterate through an exception
- * stack once. If it comes up for the second time
- * then there's something wrong going on - just
- * break out and return NULL:
- */
- if (*usedp & (1U << k))
- break;
- *usedp |= 1U << k;
- *idp = x86_stack_ids[k];
- return (unsigned long *)end;
- }
- /*
- * If this is a debug stack, and if it has a larger size than
- * the usual exception stacks, then 'stack' might still
- * be within the lower portion of the debug stack:
- */
-#if DEBUG_STKSZ > EXCEPTION_STKSZ
- if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) {
- unsigned j = N_EXCEPTION_STACKS - 1;
-
- /*
- * Black magic. A large debug stack is composed of
- * multiple exception stack entries, which we
- * iterate through now. Dont look:
- */
- do {
- ++j;
- end -= EXCEPTION_STKSZ;
- x86_stack_ids[j][4] = '1' +
- (j - N_EXCEPTION_STACKS);
- } while (stack < end - EXCEPTION_STKSZ);
- if (*usedp & (1U << j))
- break;
- *usedp |= 1U << j;
- *idp = x86_stack_ids[j];
- return (unsigned long *)end;
- }
-#endif
+ BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+
+ switch (type) {
+ case STACK_TYPE_IRQ:
+ *begin = "IRQ";
+ *end = "EOI";
+ break;
+ case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST:
+ *begin = exception_stack_names[type - STACK_TYPE_EXCEPTION];
+ *end = "EOE";
+ break;
+ default:
+ *begin = NULL;
+ *end = NULL;
}
- return NULL;
}
-static inline int
-in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
- unsigned long *irq_stack_end)
+static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
{
- return (stack >= irq_stack && stack < irq_stack_end);
-}
-
-static const unsigned long irq_stack_size =
- (IRQ_STACK_SIZE - 64) / sizeof(unsigned long);
-
-enum stack_type {
- STACK_IS_UNKNOWN,
- STACK_IS_NORMAL,
- STACK_IS_EXCEPTION,
- STACK_IS_IRQ,
-};
-
-static enum stack_type
-analyze_stack(int cpu, struct task_struct *task, unsigned long *stack,
- unsigned long **stack_end, unsigned long *irq_stack,
- unsigned *used, char **id)
-{
- unsigned long addr;
+ unsigned long *begin, *end;
+ struct pt_regs *regs;
+ unsigned k;
- addr = ((unsigned long)stack & (~(THREAD_SIZE - 1)));
- if ((unsigned long)task_stack_page(task) == addr)
- return STACK_IS_NORMAL;
+ BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
- *stack_end = in_exception_stack(cpu, (unsigned long)stack,
- used, id);
- if (*stack_end)
- return STACK_IS_EXCEPTION;
+ for (k = 0; k < N_EXCEPTION_STACKS; k++) {
+ end = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k];
+ begin = end - (exception_stack_sizes[k] / sizeof(long));
+ regs = (struct pt_regs *)end - 1;
- if (!irq_stack)
- return STACK_IS_NORMAL;
+ if (stack < begin || stack >= end)
+ continue;
- *stack_end = irq_stack;
- irq_stack = irq_stack - irq_stack_size;
+ info->type = STACK_TYPE_EXCEPTION + k;
+ info->begin = begin;
+ info->end = end;
+ info->next_sp = (unsigned long *)regs->sp;
- if (in_irq_stack(stack, irq_stack, *stack_end))
- return STACK_IS_IRQ;
+ return true;
+ }
- return STACK_IS_UNKNOWN;
+ return false;
}
-/*
- * x86-64 can have up to three kernel stacks:
- * process stack
- * interrupt stack
- * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
- */
-
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data)
+static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
{
- const unsigned cpu = get_cpu();
- unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
- unsigned long dummy;
- unsigned used = 0;
- int graph = 0;
- int done = 0;
-
- if (!task)
- task = current;
-
- if (!stack) {
- if (regs)
- stack = (unsigned long *)regs->sp;
- else if (task != current)
- stack = (unsigned long *)task->thread.sp;
- else
- stack = &dummy;
- }
+ unsigned long *end = (unsigned long *)this_cpu_read(irq_stack_ptr);
+ unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
- if (!bp)
- bp = stack_frame(task, regs);
/*
- * Print function call entries in all stacks, starting at the
- * current stack address. If the stacks consist of nested
- * exceptions
+ * This is a software stack, so 'end' can be a valid stack pointer.
+ * It just means the stack is empty.
*/
- while (!done) {
- unsigned long *stack_end;
- enum stack_type stype;
- char *id;
+ if (stack < begin || stack > end)
+ return false;
- stype = analyze_stack(cpu, task, stack, &stack_end,
- irq_stack, &used, &id);
+ info->type = STACK_TYPE_IRQ;
+ info->begin = begin;
+ info->end = end;
- /* Default finish unless specified to continue */
- done = 1;
+ /*
+ * The next stack pointer is the first thing pushed by the entry code
+ * after switching to the irq stack.
+ */
+ info->next_sp = (unsigned long *)*(end - 1);
- switch (stype) {
+ return true;
+}
- /* Break out early if we are on the thread stack */
- case STACK_IS_NORMAL:
- break;
+int get_stack_info(unsigned long *stack, struct task_struct *task,
+ struct stack_info *info, unsigned long *visit_mask)
+{
+ if (!stack)
+ goto unknown;
- case STACK_IS_EXCEPTION:
+ task = task ? : current;
- if (ops->stack(data, id) < 0)
- break;
+ if (in_task_stack(stack, task, info))
+ goto recursion_check;
- bp = ops->walk_stack(task, stack, bp, ops,
- data, stack_end, &graph);
- ops->stack(data, "<EOE>");
- /*
- * We link to the next stack via the
- * second-to-last pointer (index -2 to end) in the
- * exception stack:
- */
- stack = (unsigned long *) stack_end[-2];
- done = 0;
- break;
+ if (task != current)
+ goto unknown;
- case STACK_IS_IRQ:
+ if (in_exception_stack(stack, info))
+ goto recursion_check;
- if (ops->stack(data, "IRQ") < 0)
- break;
- bp = ops->walk_stack(task, stack, bp,
- ops, data, stack_end, &graph);
- /*
- * We link to the next stack (which would be
- * the process stack normally) the last
- * pointer (index -1 to end) in the IRQ stack:
- */
- stack = (unsigned long *) (stack_end[-1]);
- irq_stack = NULL;
- ops->stack(data, "EOI");
- done = 0;
- break;
+ if (in_irq_stack(stack, info))
+ goto recursion_check;
- case STACK_IS_UNKNOWN:
- ops->stack(data, "UNK");
- break;
- }
- }
+ goto unknown;
+recursion_check:
/*
- * This handles the process stack:
+ * Make sure we don't iterate through any given stack more than once.
+ * If it comes up a second time then there's something wrong going on:
+ * just break out and report an unknown stack type.
*/
- bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph);
- put_cpu();
+ if (visit_mask) {
+ if (*visit_mask & (1UL << info->type))
+ goto unknown;
+ *visit_mask |= 1UL << info->type;
+ }
+
+ return 0;
+
+unknown:
+ info->type = STACK_TYPE_UNKNOWN;
+ return -EINVAL;
}
-EXPORT_SYMBOL(dump_trace);
-void
-show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp, char *log_lvl)
+void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+ unsigned long *sp, char *log_lvl)
{
unsigned long *irq_stack_end;
unsigned long *irq_stack;
unsigned long *stack;
- int cpu;
int i;
- preempt_disable();
- cpu = smp_processor_id();
+ if (!try_get_task_stack(task))
+ return;
- irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
- irq_stack = (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
+ irq_stack_end = (unsigned long *)this_cpu_read(irq_stack_ptr);
+ irq_stack = irq_stack_end - (IRQ_STACK_SIZE / sizeof(long));
- /*
- * Debugging aid: "show_stack(NULL, NULL);" prints the
- * back trace for this cpu:
- */
- if (sp == NULL) {
- if (regs)
- sp = (unsigned long *)regs->sp;
- else if (task)
- sp = (unsigned long *)task->thread.sp;
- else
- sp = (unsigned long *)&sp;
- }
+ sp = sp ? : get_stack_pointer(task, regs);
stack = sp;
for (i = 0; i < kstack_depth_to_print; i++) {
@@ -299,18 +183,17 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
stack++;
touch_nmi_watchdog();
}
- preempt_enable();
pr_cont("\n");
- show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+ show_trace_log_lvl(task, regs, sp, log_lvl);
+
+ put_task_stack(task);
}
void show_regs(struct pt_regs *regs)
{
int i;
- unsigned long sp;
- sp = regs->sp;
show_regs_print_info(KERN_DEFAULT);
__show_regs(regs, 1);
@@ -325,8 +208,7 @@ void show_regs(struct pt_regs *regs)
u8 *ip;
printk(KERN_DEFAULT "Stack:\n");
- show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
- 0, KERN_DEFAULT);
+ show_stack_log_lvl(current, regs, NULL, KERN_DEFAULT);
printk(KERN_DEFAULT "Code: ");
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 621b501f8935..b85fe5f91c3f 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -40,8 +40,10 @@
* user can e.g. boot the original kernel with mem=1G while still booting the
* next kernel with full memory.
*/
-struct e820map e820;
-struct e820map e820_saved;
+static struct e820map initial_e820 __initdata;
+static struct e820map initial_e820_saved __initdata;
+struct e820map *e820 __refdata = &initial_e820;
+struct e820map *e820_saved __refdata = &initial_e820_saved;
/* For PCI or other memory-mapped resources */
unsigned long pci_mem_start = 0xaeedbabe;
@@ -58,8 +60,8 @@ e820_any_mapped(u64 start, u64 end, unsigned type)
{
int i;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ struct e820entry *ei = &e820->map[i];
if (type && ei->type != type)
continue;
@@ -81,8 +83,8 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type)
{
int i;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ struct e820entry *ei = &e820->map[i];
if (type && ei->type != type)
continue;
@@ -128,7 +130,7 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
void __init e820_add_region(u64 start, u64 size, int type)
{
- __e820_add_region(&e820, start, size, type);
+ __e820_add_region(e820, start, size, type);
}
static void __init e820_print_type(u32 type)
@@ -164,12 +166,12 @@ void __init e820_print_map(char *who)
{
int i;
- for (i = 0; i < e820.nr_map; i++) {
+ for (i = 0; i < e820->nr_map; i++) {
printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who,
- (unsigned long long) e820.map[i].addr,
+ (unsigned long long) e820->map[i].addr,
(unsigned long long)
- (e820.map[i].addr + e820.map[i].size - 1));
- e820_print_type(e820.map[i].type);
+ (e820->map[i].addr + e820->map[i].size - 1));
+ e820_print_type(e820->map[i].type);
printk(KERN_CONT "\n");
}
}
@@ -348,7 +350,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
* continue building up new bios map based on this
* information
*/
- if (current_type != last_type || current_type == E820_PRAM) {
+ if (current_type != last_type) {
if (last_type != 0) {
new_bios[new_bios_entry].size =
change_point[chgidx]->addr - last_addr;
@@ -388,11 +390,11 @@ static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
while (nr_map) {
u64 start = biosmap->addr;
u64 size = biosmap->size;
- u64 end = start + size;
+ u64 end = start + size - 1;
u32 type = biosmap->type;
/* Overflow in 64 bits? Ignore the memory map. */
- if (start > end)
+ if (start > end && likely(size))
return -1;
e820_add_region(start, size, type);
@@ -493,13 +495,13 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
unsigned new_type)
{
- return __e820_update_range(&e820, start, size, old_type, new_type);
+ return __e820_update_range(e820, start, size, old_type, new_type);
}
static u64 __init e820_update_range_saved(u64 start, u64 size,
unsigned old_type, unsigned new_type)
{
- return __e820_update_range(&e820_saved, start, size, old_type,
+ return __e820_update_range(e820_saved, start, size, old_type,
new_type);
}
@@ -521,8 +523,8 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
e820_print_type(old_type);
printk(KERN_CONT "\n");
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ struct e820entry *ei = &e820->map[i];
u64 final_start, final_end;
u64 ei_end;
@@ -566,15 +568,15 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
void __init update_e820(void)
{
- if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map))
+ if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map))
return;
printk(KERN_INFO "e820: modified physical RAM map:\n");
e820_print_map("modified");
}
static void __init update_e820_saved(void)
{
- sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map),
- &e820_saved.nr_map);
+ sanitize_e820_map(e820_saved->map, ARRAY_SIZE(e820_saved->map),
+ &e820_saved->nr_map);
}
#define MAX_GAP_END 0x100000000ull
/*
@@ -584,14 +586,14 @@ __init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
unsigned long start_addr, unsigned long long end_addr)
{
unsigned long long last;
- int i = e820.nr_map;
+ int i = e820->nr_map;
int found = 0;
last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END;
while (--i >= 0) {
- unsigned long long start = e820.map[i].addr;
- unsigned long long end = start + e820.map[i].size;
+ unsigned long long start = e820->map[i].addr;
+ unsigned long long end = start + e820->map[i].size;
if (end < start_addr)
continue;
@@ -649,6 +651,33 @@ __init void e820_setup_gap(void)
gapstart, gapstart + gapsize - 1);
}
+/*
+ * Called late during init, in free_initmem().
+ *
+ * Initial e820 and e820_saved are largish __initdata arrays.
+ * Copy them to (usually much smaller) dynamically allocated area.
+ * This is done after all tweaks we ever do to them:
+ * all functions which modify them are __init functions,
+ * they won't exist after this point.
+ */
+__init void e820_reallocate_tables(void)
+{
+ struct e820map *n;
+ int size;
+
+ size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820->nr_map;
+ n = kmalloc(size, GFP_KERNEL);
+ BUG_ON(!n);
+ memcpy(n, e820, size);
+ e820 = n;
+
+ size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820_saved->nr_map;
+ n = kmalloc(size, GFP_KERNEL);
+ BUG_ON(!n);
+ memcpy(n, e820_saved, size);
+ e820_saved = n;
+}
+
/**
* Because of the size limitation of struct boot_params, only first
* 128 E820 memory entries are passed to kernel via
@@ -665,7 +694,7 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len)
entries = sdata->len / sizeof(struct e820entry);
extmap = (struct e820entry *)(sdata->data);
__append_e820_map(extmap, entries);
- sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
early_memunmap(sdata, data_len);
printk(KERN_INFO "e820: extended physical RAM map:\n");
e820_print_map("extended");
@@ -686,8 +715,8 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn)
int i;
unsigned long pfn = 0;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ struct e820entry *ei = &e820->map[i];
if (pfn < PFN_UP(ei->addr))
register_nosave_region(pfn, PFN_UP(ei->addr));
@@ -712,8 +741,8 @@ static int __init e820_mark_nvs_memory(void)
{
int i;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ struct e820entry *ei = &e820->map[i];
if (ei->type == E820_NVS)
acpi_nvs_register(ei->addr, ei->size);
@@ -754,22 +783,18 @@ u64 __init early_reserve_e820(u64 size, u64 align)
/*
* Find the highest page frame number we have available
*/
-static unsigned long __init e820_end_pfn(unsigned long limit_pfn)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
{
int i;
unsigned long last_pfn = 0;
unsigned long max_arch_pfn = MAX_ARCH_PFN;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ struct e820entry *ei = &e820->map[i];
unsigned long start_pfn;
unsigned long end_pfn;
- /*
- * Persistent memory is accounted as ram for purposes of
- * establishing max_pfn and mem_map.
- */
- if (ei->type != E820_RAM && ei->type != E820_PRAM)
+ if (ei->type != type)
continue;
start_pfn = ei->addr >> PAGE_SHIFT;
@@ -794,15 +819,15 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn)
}
unsigned long __init e820_end_of_ram_pfn(void)
{
- return e820_end_pfn(MAX_ARCH_PFN);
+ return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
}
unsigned long __init e820_end_of_low_ram_pfn(void)
{
- return e820_end_pfn(1UL << (32-PAGE_SHIFT));
+ return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_RAM);
}
-static void early_panic(char *msg)
+static void __init early_panic(char *msg)
{
early_printk(msg);
panic(msg);
@@ -856,7 +881,7 @@ static int __init parse_memmap_one(char *p)
*/
saved_max_pfn = e820_end_of_ram_pfn();
#endif
- e820.nr_map = 0;
+ e820->nr_map = 0;
userdef = 1;
return 0;
}
@@ -903,8 +928,8 @@ early_param("memmap", parse_memmap_opt);
void __init finish_e820_parsing(void)
{
if (userdef) {
- if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map),
- &e820.nr_map) < 0)
+ if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map),
+ &e820->nr_map) < 0)
early_panic("Invalid user supplied memory map");
printk(KERN_INFO "e820: user-defined physical RAM map:\n");
@@ -912,7 +937,7 @@ void __init finish_e820_parsing(void)
}
}
-static const char *e820_type_to_string(int e820_type)
+static const char *__init e820_type_to_string(int e820_type)
{
switch (e820_type) {
case E820_RESERVED_KERN:
@@ -926,7 +951,7 @@ static const char *e820_type_to_string(int e820_type)
}
}
-static unsigned long e820_type_to_iomem_type(int e820_type)
+static unsigned long __init e820_type_to_iomem_type(int e820_type)
{
switch (e820_type) {
case E820_RESERVED_KERN:
@@ -942,7 +967,7 @@ static unsigned long e820_type_to_iomem_type(int e820_type)
}
}
-static unsigned long e820_type_to_iores_desc(int e820_type)
+static unsigned long __init e820_type_to_iores_desc(int e820_type)
{
switch (e820_type) {
case E820_ACPI:
@@ -961,7 +986,7 @@ static unsigned long e820_type_to_iores_desc(int e820_type)
}
}
-static bool do_mark_busy(u32 type, struct resource *res)
+static bool __init do_mark_busy(u32 type, struct resource *res)
{
/* this is the legacy bios/dos rom-shadow + mmio region */
if (res->start < (1ULL<<20))
@@ -991,35 +1016,35 @@ void __init e820_reserve_resources(void)
struct resource *res;
u64 end;
- res = alloc_bootmem(sizeof(struct resource) * e820.nr_map);
+ res = alloc_bootmem(sizeof(struct resource) * e820->nr_map);
e820_res = res;
- for (i = 0; i < e820.nr_map; i++) {
- end = e820.map[i].addr + e820.map[i].size - 1;
+ for (i = 0; i < e820->nr_map; i++) {
+ end = e820->map[i].addr + e820->map[i].size - 1;
if (end != (resource_size_t)end) {
res++;
continue;
}
- res->name = e820_type_to_string(e820.map[i].type);
- res->start = e820.map[i].addr;
+ res->name = e820_type_to_string(e820->map[i].type);
+ res->start = e820->map[i].addr;
res->end = end;
- res->flags = e820_type_to_iomem_type(e820.map[i].type);
- res->desc = e820_type_to_iores_desc(e820.map[i].type);
+ res->flags = e820_type_to_iomem_type(e820->map[i].type);
+ res->desc = e820_type_to_iores_desc(e820->map[i].type);
/*
* don't register the region that could be conflicted with
* pci device BAR resource and insert them later in
* pcibios_resource_survey()
*/
- if (do_mark_busy(e820.map[i].type, res)) {
+ if (do_mark_busy(e820->map[i].type, res)) {
res->flags |= IORESOURCE_BUSY;
insert_resource(&iomem_resource, res);
}
res++;
}
- for (i = 0; i < e820_saved.nr_map; i++) {
- struct e820entry *entry = &e820_saved.map[i];
+ for (i = 0; i < e820_saved->nr_map; i++) {
+ struct e820entry *entry = &e820_saved->map[i];
firmware_map_add_early(entry->addr,
entry->addr + entry->size,
e820_type_to_string(entry->type));
@@ -1027,7 +1052,7 @@ void __init e820_reserve_resources(void)
}
/* How much should we pad RAM ending depending on where it is? */
-static unsigned long ram_alignment(resource_size_t pos)
+static unsigned long __init ram_alignment(resource_size_t pos)
{
unsigned long mb = pos >> 20;
@@ -1051,7 +1076,7 @@ void __init e820_reserve_resources_late(void)
struct resource *res;
res = e820_res;
- for (i = 0; i < e820.nr_map; i++) {
+ for (i = 0; i < e820->nr_map; i++) {
if (!res->parent && res->end)
insert_resource_expand_to_fit(&iomem_resource, res);
res++;
@@ -1061,8 +1086,8 @@ void __init e820_reserve_resources_late(void)
* Try to bump up RAM regions to reasonable boundaries to
* avoid stolen RAM:
*/
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *entry = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ struct e820entry *entry = &e820->map[i];
u64 start, end;
if (entry->type != E820_RAM)
@@ -1110,7 +1135,7 @@ char *__init default_machine_specific_memory_setup(void)
who = "BIOS-e801";
}
- e820.nr_map = 0;
+ e820->nr_map = 0;
e820_add_region(0, LOWMEMSIZE(), E820_RAM);
e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
}
@@ -1124,7 +1149,7 @@ void __init setup_memory_map(void)
char *who;
who = x86_init.resources.memory_setup();
- memcpy(&e820_saved, &e820, sizeof(struct e820map));
+ memcpy(e820_saved, e820, sizeof(struct e820map));
printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n");
e820_print_map(who);
}
@@ -1141,8 +1166,8 @@ void __init memblock_x86_fill(void)
*/
memblock_allow_resize();
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ struct e820entry *ei = &e820->map[i];
end = ei->addr + ei->size;
if (end != (resource_size_t)end)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index de7501edb21c..18bb3a639197 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -555,7 +555,7 @@ intel_graphics_stolen(int num, int slot, int func,
/* Mark this space as reserved */
e820_add_region(base, size, E820_RESERVED);
- sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
}
static void __init intel_graphics_quirks(int num, int slot, int func)
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 93982aebb398..2f2b8c7ccb85 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -317,7 +317,6 @@ static void __init fpu__init_system_ctx_switch(void)
on_boot_cpu = 0;
WARN_ON_FPU(current->thread.fpu.fpstate_active);
- current_thread_info()->status = 0;
if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE)
eagerfpu = ENABLE;
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d036cfb4495d..8639bb2ae058 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -1029,7 +1029,7 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
}
if (ftrace_push_return_trace(old, self_addr, &trace.depth,
- frame_pointer) == -EBUSY) {
+ frame_pointer, parent) == -EBUSY) {
*parent = old;
return;
}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 6f8902b0d151..5f401262f12d 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -94,7 +94,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE)
*/
__HEAD
ENTRY(startup_32)
- movl pa(stack_start),%ecx
+ movl pa(initial_stack),%ecx
/* test KEEP_SEGMENTS flag to see if the bootloader is asking
us to not reload segments */
@@ -286,7 +286,7 @@ num_subarch_entries = (. - subarch_entries) / 4
* start_secondary().
*/
ENTRY(start_cpu0)
- movl stack_start, %ecx
+ movl initial_stack, %ecx
movl %ecx, %esp
jmp *(initial_code)
ENDPROC(start_cpu0)
@@ -307,7 +307,7 @@ ENTRY(startup_32_smp)
movl %eax,%es
movl %eax,%fs
movl %eax,%gs
- movl pa(stack_start),%ecx
+ movl pa(initial_stack),%ecx
movl %eax,%ss
leal -__PAGE_OFFSET(%ecx),%esp
@@ -703,7 +703,7 @@ ENTRY(initial_page_table)
.data
.balign 4
-ENTRY(stack_start)
+ENTRY(initial_stack)
.long init_thread_union+THREAD_SIZE
__INITRODATA
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 9f8efc9f0075..c98a559c346e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -66,7 +66,7 @@ startup_64:
*/
/*
- * Setup stack for verify_cpu(). "-8" because stack_start is defined
+ * Setup stack for verify_cpu(). "-8" because initial_stack is defined
* this way, see below. Our best guess is a NULL ptr for stack
* termination heuristics and we don't want to break anything which
* might depend on it (kgdb, ...).
@@ -226,7 +226,7 @@ ENTRY(secondary_startup_64)
movq %rax, %cr0
/* Setup a boot time stack */
- movq stack_start(%rip), %rsp
+ movq initial_stack(%rip), %rsp
/* zero EFLAGS after setting rsp */
pushq $0
@@ -310,7 +310,7 @@ ENDPROC(secondary_startup_64)
* start_secondary().
*/
ENTRY(start_cpu0)
- movq stack_start(%rip),%rsp
+ movq initial_stack(%rip),%rsp
movq initial_code(%rip),%rax
pushq $0 # fake return address to stop unwinder
pushq $__KERNEL_CS # set correct cs
@@ -319,17 +319,15 @@ ENTRY(start_cpu0)
ENDPROC(start_cpu0)
#endif
- /* SMP bootup changes these two */
+ /* Both SMP bootup and ACPI suspend change these variables */
__REFDATA
.balign 8
GLOBAL(initial_code)
.quad x86_64_start_kernel
GLOBAL(initial_gs)
.quad INIT_PER_CPU_VAR(irq_stack_union)
-
- GLOBAL(stack_start)
+ GLOBAL(initial_stack)
.quad init_thread_union+THREAD_SIZE-8
- .word 0
__FINITDATA
bad_address:
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index c6dfd801df97..274fab99169d 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -756,10 +756,104 @@ static void hpet_reserve_msi_timers(struct hpet_data *hd)
/*
* Clock source related code
*/
+#if defined(CONFIG_SMP) && defined(CONFIG_64BIT)
+/*
+ * Reading the HPET counter is a very slow operation. If a large number of
+ * CPUs are trying to access the HPET counter simultaneously, it can cause
+ * massive delay and slow down system performance dramatically. This may
+ * happen when HPET is the default clock source instead of TSC. For a
+ * really large system with hundreds of CPUs, the slowdown may be so
+ * severe that it may actually crash the system because of a NMI watchdog
+ * soft lockup, for example.
+ *
+ * If multiple CPUs are trying to access the HPET counter at the same time,
+ * we don't actually need to read the counter multiple times. Instead, the
+ * other CPUs can use the counter value read by the first CPU in the group.
+ *
+ * This special feature is only enabled on x86-64 systems. It is unlikely
+ * that 32-bit x86 systems will have enough CPUs to require this feature
+ * with its associated locking overhead. And we also need 64-bit atomic
+ * read.
+ *
+ * The lock and the hpet value are stored together and can be read in a
+ * single atomic 64-bit read. It is explicitly assumed that arch_spinlock_t
+ * is 32 bits in size.
+ */
+union hpet_lock {
+ struct {
+ arch_spinlock_t lock;
+ u32 value;
+ };
+ u64 lockval;
+};
+
+static union hpet_lock hpet __cacheline_aligned = {
+ { .lock = __ARCH_SPIN_LOCK_UNLOCKED, },
+};
+
+static cycle_t read_hpet(struct clocksource *cs)
+{
+ unsigned long flags;
+ union hpet_lock old, new;
+
+ BUILD_BUG_ON(sizeof(union hpet_lock) != 8);
+
+ /*
+ * Read HPET directly if in NMI.
+ */
+ if (in_nmi())
+ return (cycle_t)hpet_readl(HPET_COUNTER);
+
+ /*
+ * Read the current state of the lock and HPET value atomically.
+ */
+ old.lockval = READ_ONCE(hpet.lockval);
+
+ if (arch_spin_is_locked(&old.lock))
+ goto contended;
+
+ local_irq_save(flags);
+ if (arch_spin_trylock(&hpet.lock)) {
+ new.value = hpet_readl(HPET_COUNTER);
+ /*
+ * Use WRITE_ONCE() to prevent store tearing.
+ */
+ WRITE_ONCE(hpet.value, new.value);
+ arch_spin_unlock(&hpet.lock);
+ local_irq_restore(flags);
+ return (cycle_t)new.value;
+ }
+ local_irq_restore(flags);
+
+contended:
+ /*
+ * Contended case
+ * --------------
+ * Wait until the HPET value change or the lock is free to indicate
+ * its value is up-to-date.
+ *
+ * It is possible that old.value has already contained the latest
+ * HPET value while the lock holder was in the process of releasing
+ * the lock. Checking for lock state change will enable us to return
+ * the value immediately instead of waiting for the next HPET reader
+ * to come along.
+ */
+ do {
+ cpu_relax();
+ new.lockval = READ_ONCE(hpet.lockval);
+ } while ((new.value == old.value) && arch_spin_is_locked(&new.lock));
+
+ return (cycle_t)new.value;
+}
+#else
+/*
+ * For UP or 32-bit.
+ */
static cycle_t read_hpet(struct clocksource *cs)
{
return (cycle_t)hpet_readl(HPET_COUNTER);
}
+#endif
static struct clocksource clocksource_hpet = {
.name = "hpet",
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 4a7903714065..9ebd0b0e73d9 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -40,8 +40,7 @@ static inline void stack_overflow_check(struct pt_regs *regs)
if (user_mode(regs))
return;
- if (regs->sp >= curbase + sizeof(struct thread_info) +
- sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
+ if (regs->sp >= curbase + sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
regs->sp <= curbase + THREAD_SIZE)
return;
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index f2356bda2b05..3407b148c240 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -99,14 +99,14 @@ static int setup_e820_entries(struct boot_params *params)
{
unsigned int nr_e820_entries;
- nr_e820_entries = e820_saved.nr_map;
+ nr_e820_entries = e820_saved->nr_map;
/* TODO: Pass entries more than E820MAX in bootparams setup data */
if (nr_e820_entries > E820MAX)
nr_e820_entries = E820MAX;
params->e820_entries = nr_e820_entries;
- memcpy(&params->e820_map, &e820_saved.map,
+ memcpy(&params->e820_map, &e820_saved->map,
nr_e820_entries * sizeof(struct e820entry));
return 0;
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 04cde527d728..8e36f249646e 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -50,6 +50,7 @@
#include <asm/apicdef.h>
#include <asm/apic.h>
#include <asm/nmi.h>
+#include <asm/switch_to.h>
struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
{
@@ -166,21 +167,19 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
gdb_regs[GDB_DX] = 0;
gdb_regs[GDB_SI] = 0;
gdb_regs[GDB_DI] = 0;
- gdb_regs[GDB_BP] = *(unsigned long *)p->thread.sp;
+ gdb_regs[GDB_BP] = ((struct inactive_task_frame *)p->thread.sp)->bp;
#ifdef CONFIG_X86_32
gdb_regs[GDB_DS] = __KERNEL_DS;
gdb_regs[GDB_ES] = __KERNEL_DS;
gdb_regs[GDB_PS] = 0;
gdb_regs[GDB_CS] = __KERNEL_CS;
- gdb_regs[GDB_PC] = p->thread.ip;
gdb_regs[GDB_SS] = __KERNEL_DS;
gdb_regs[GDB_FS] = 0xFFFF;
gdb_regs[GDB_GS] = 0xFFFF;
#else
- gdb_regs32[GDB_PS] = *(unsigned long *)(p->thread.sp + 8);
+ gdb_regs32[GDB_PS] = 0;
gdb_regs32[GDB_CS] = __KERNEL_CS;
gdb_regs32[GDB_SS] = __KERNEL_DS;
- gdb_regs[GDB_PC] = 0;
gdb_regs[GDB_R8] = 0;
gdb_regs[GDB_R9] = 0;
gdb_regs[GDB_R10] = 0;
@@ -190,6 +189,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
gdb_regs[GDB_R14] = 0;
gdb_regs[GDB_R15] = 0;
#endif
+ gdb_regs[GDB_PC] = 0;
gdb_regs[GDB_SP] = p->thread.sp;
}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 7847e5c0e0b5..28cee019209c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -45,7 +45,7 @@
#include <linux/slab.h>
#include <linux/hardirq.h>
#include <linux/preempt.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/kallsyms.h>
#include <linux/ftrace.h>
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 4425f593f0ec..3bb4c5f021f6 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -24,7 +24,7 @@
#include <linux/slab.h>
#include <linux/hardirq.h>
#include <linux/preempt.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/kallsyms.h>
#include <linux/ftrace.h>
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index c2bedaea11f7..4afc67f5facc 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -184,7 +184,7 @@ out:
static struct kobj_attribute type_attr = __ATTR_RO(type);
-static struct bin_attribute data_attr = {
+static struct bin_attribute data_attr __ro_after_init = {
.attr = {
.name = "data",
.mode = S_IRUGO,
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 1726c4c12336..edbbfc854e39 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -423,12 +423,7 @@ static void __init kvm_smp_prepare_boot_cpu(void)
kvm_spinlock_init();
}
-static void kvm_guest_cpu_online(void *dummy)
-{
- kvm_guest_cpu_init();
-}
-
-static void kvm_guest_cpu_offline(void *dummy)
+static void kvm_guest_cpu_offline(void)
{
kvm_disable_steal_time();
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -437,29 +432,21 @@ static void kvm_guest_cpu_offline(void *dummy)
apf_task_wake_all();
}
-static int kvm_cpu_notify(struct notifier_block *self, unsigned long action,
- void *hcpu)
+static int kvm_cpu_online(unsigned int cpu)
{
- int cpu = (unsigned long)hcpu;
- switch (action) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
- case CPU_ONLINE_FROZEN:
- smp_call_function_single(cpu, kvm_guest_cpu_online, NULL, 0);
- break;
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- smp_call_function_single(cpu, kvm_guest_cpu_offline, NULL, 1);
- break;
- default:
- break;
- }
- return NOTIFY_OK;
+ local_irq_disable();
+ kvm_guest_cpu_init();
+ local_irq_enable();
+ return 0;
}
-static struct notifier_block kvm_cpu_notifier = {
- .notifier_call = kvm_cpu_notify,
-};
+static int kvm_cpu_down_prepare(unsigned int cpu)
+{
+ local_irq_disable();
+ kvm_guest_cpu_offline();
+ local_irq_enable();
+ return 0;
+}
#endif
static void __init kvm_apf_trap_init(void)
@@ -494,7 +481,9 @@ void __init kvm_guest_init(void)
#ifdef CONFIG_SMP
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
- register_cpu_notifier(&kvm_cpu_notifier);
+ if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
+ kvm_cpu_online, kvm_cpu_down_prepare) < 0)
+ pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
#else
kvm_guest_cpu_init();
#endif
@@ -575,9 +564,6 @@ static void kvm_kick_cpu(int cpu)
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}
-
-#ifdef CONFIG_QUEUED_SPINLOCKS
-
#include <asm/qspinlock.h>
static void kvm_wait(u8 *ptr, u8 val)
@@ -606,243 +592,6 @@ out:
local_irq_restore(flags);
}
-#else /* !CONFIG_QUEUED_SPINLOCKS */
-
-enum kvm_contention_stat {
- TAKEN_SLOW,
- TAKEN_SLOW_PICKUP,
- RELEASED_SLOW,
- RELEASED_SLOW_KICKED,
- NR_CONTENTION_STATS
-};
-
-#ifdef CONFIG_KVM_DEBUG_FS
-#define HISTO_BUCKETS 30
-
-static struct kvm_spinlock_stats
-{
- u32 contention_stats[NR_CONTENTION_STATS];
- u32 histo_spin_blocked[HISTO_BUCKETS+1];
- u64 time_blocked;
-} spinlock_stats;
-
-static u8 zero_stats;
-
-static inline void check_zero(void)
-{
- u8 ret;
- u8 old;
-
- old = READ_ONCE(zero_stats);
- if (unlikely(old)) {
- ret = cmpxchg(&zero_stats, old, 0);
- /* This ensures only one fellow resets the stat */
- if (ret == old)
- memset(&spinlock_stats, 0, sizeof(spinlock_stats));
- }
-}
-
-static inline void add_stats(enum kvm_contention_stat var, u32 val)
-{
- check_zero();
- spinlock_stats.contention_stats[var] += val;
-}
-
-
-static inline u64 spin_time_start(void)
-{
- return sched_clock();
-}
-
-static void __spin_time_accum(u64 delta, u32 *array)
-{
- unsigned index;
-
- index = ilog2(delta);
- check_zero();
-
- if (index < HISTO_BUCKETS)
- array[index]++;
- else
- array[HISTO_BUCKETS]++;
-}
-
-static inline void spin_time_accum_blocked(u64 start)
-{
- u32 delta;
-
- delta = sched_clock() - start;
- __spin_time_accum(delta, spinlock_stats.histo_spin_blocked);
- spinlock_stats.time_blocked += delta;
-}
-
-static struct dentry *d_spin_debug;
-static struct dentry *d_kvm_debug;
-
-static struct dentry *kvm_init_debugfs(void)
-{
- d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
- if (!d_kvm_debug)
- printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n");
-
- return d_kvm_debug;
-}
-
-static int __init kvm_spinlock_debugfs(void)
-{
- struct dentry *d_kvm;
-
- d_kvm = kvm_init_debugfs();
- if (d_kvm == NULL)
- return -ENOMEM;
-
- d_spin_debug = debugfs_create_dir("spinlocks", d_kvm);
-
- debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
-
- debugfs_create_u32("taken_slow", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[TAKEN_SLOW]);
- debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
-
- debugfs_create_u32("released_slow", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[RELEASED_SLOW]);
- debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
-
- debugfs_create_u64("time_blocked", 0444, d_spin_debug,
- &spinlock_stats.time_blocked);
-
- debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
- spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
-
- return 0;
-}
-fs_initcall(kvm_spinlock_debugfs);
-#else /* !CONFIG_KVM_DEBUG_FS */
-static inline void add_stats(enum kvm_contention_stat var, u32 val)
-{
-}
-
-static inline u64 spin_time_start(void)
-{
- return 0;
-}
-
-static inline void spin_time_accum_blocked(u64 start)
-{
-}
-#endif /* CONFIG_KVM_DEBUG_FS */
-
-struct kvm_lock_waiting {
- struct arch_spinlock *lock;
- __ticket_t want;
-};
-
-/* cpus 'waiting' on a spinlock to become available */
-static cpumask_t waiting_cpus;
-
-/* Track spinlock on which a cpu is waiting */
-static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting);
-
-__visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
-{
- struct kvm_lock_waiting *w;
- int cpu;
- u64 start;
- unsigned long flags;
- __ticket_t head;
-
- if (in_nmi())
- return;
-
- w = this_cpu_ptr(&klock_waiting);
- cpu = smp_processor_id();
- start = spin_time_start();
-
- /*
- * Make sure an interrupt handler can't upset things in a
- * partially setup state.
- */
- local_irq_save(flags);
-
- /*
- * The ordering protocol on this is that the "lock" pointer
- * may only be set non-NULL if the "want" ticket is correct.
- * If we're updating "want", we must first clear "lock".
- */
- w->lock = NULL;
- smp_wmb();
- w->want = want;
- smp_wmb();
- w->lock = lock;
-
- add_stats(TAKEN_SLOW, 1);
-
- /*
- * This uses set_bit, which is atomic but we should not rely on its
- * reordering gurantees. So barrier is needed after this call.
- */
- cpumask_set_cpu(cpu, &waiting_cpus);
-
- barrier();
-
- /*
- * Mark entry to slowpath before doing the pickup test to make
- * sure we don't deadlock with an unlocker.
- */
- __ticket_enter_slowpath(lock);
-
- /* make sure enter_slowpath, which is atomic does not cross the read */
- smp_mb__after_atomic();
-
- /*
- * check again make sure it didn't become free while
- * we weren't looking.
- */
- head = READ_ONCE(lock->tickets.head);
- if (__tickets_equal(head, want)) {
- add_stats(TAKEN_SLOW_PICKUP, 1);
- goto out;
- }
-
- /*
- * halt until it's our turn and kicked. Note that we do safe halt
- * for irq enabled case to avoid hang when lock info is overwritten
- * in irq spinlock slowpath and no spurious interrupt occur to save us.
- */
- if (arch_irqs_disabled_flags(flags))
- halt();
- else
- safe_halt();
-
-out:
- cpumask_clear_cpu(cpu, &waiting_cpus);
- w->lock = NULL;
- local_irq_restore(flags);
- spin_time_accum_blocked(start);
-}
-PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning);
-
-/* Kick vcpu waiting on @lock->head to reach value @ticket */
-static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
-{
- int cpu;
-
- add_stats(RELEASED_SLOW, 1);
- for_each_cpu(cpu, &waiting_cpus) {
- const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu);
- if (READ_ONCE(w->lock) == lock &&
- READ_ONCE(w->want) == ticket) {
- add_stats(RELEASED_SLOW_KICKED, 1);
- kvm_kick_cpu(cpu);
- break;
- }
- }
-}
-
-#endif /* !CONFIG_QUEUED_SPINLOCKS */
-
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
@@ -854,16 +603,11 @@ void __init kvm_spinlock_init(void)
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
-#ifdef CONFIG_QUEUED_SPINLOCKS
__pv_init_lock_hash();
pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = kvm_wait;
pv_lock_ops.kick = kvm_kick_cpu;
-#else /* !CONFIG_QUEUED_SPINLOCKS */
- pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
- pv_lock_ops.unlock_kick = kvm_unlock_kick;
-#endif
}
static __init int kvm_spinlock_init_jump(void)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1d39bfbd26bb..60b9949f1e65 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -29,7 +29,7 @@
#include <asm/x86_init.h>
#include <asm/reboot.h>
-static int kvmclock = 1;
+static int kvmclock __ro_after_init = 1;
static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
static cycle_t kvm_sched_clock_offset;
@@ -289,6 +289,7 @@ void __init kvmclock_init(void)
put_cpu();
x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+ x86_platform.calibrate_cpu = kvm_get_tsc_khz;
x86_platform.get_wallclock = kvm_get_wallclock;
x86_platform.set_wallclock = kvm_set_wallclock;
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 068c4a929de6..0f8d20497383 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -499,6 +499,9 @@ void __init default_get_smp_config(unsigned int early)
{
struct mpf_intel *mpf = mpf_found;
+ if (!smp_found_config)
+ return;
+
if (!mpf)
return;
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 1939a0269377..2c55a003b793 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -8,7 +8,6 @@
#include <asm/paravirt.h>
-#ifdef CONFIG_QUEUED_SPINLOCKS
__visible void __native_queued_spin_unlock(struct qspinlock *lock)
{
native_queued_spin_unlock(lock);
@@ -21,19 +20,13 @@ bool pv_is_native_spin_unlock(void)
return pv_lock_ops.queued_spin_unlock.func ==
__raw_callee_save___native_queued_spin_unlock;
}
-#endif
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
-#ifdef CONFIG_QUEUED_SPINLOCKS
.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
.wait = paravirt_nop,
.kick = paravirt_nop,
-#else /* !CONFIG_QUEUED_SPINLOCKS */
- .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
- .unlock_kick = paravirt_nop,
-#endif /* !CONFIG_QUEUED_SPINLOCKS */
#endif /* SMP */
};
EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1acfd76e3e26..bbf3d5933eaa 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -332,7 +332,6 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
.read_cr0 = native_read_cr0,
.write_cr0 = native_write_cr0,
.read_cr4 = native_read_cr4,
- .read_cr4_safe = native_read_cr4_safe,
.write_cr4 = native_write_cr4,
#ifdef CONFIG_X86_64
.read_cr8 = native_read_cr8,
@@ -389,7 +388,7 @@ NOKPROBE_SYMBOL(native_load_idt);
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
#endif
-struct pv_mmu_ops pv_mmu_ops = {
+struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
.read_cr2 = native_read_cr2,
.write_cr2 = native_write_cr2,
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 158dc0650d5d..920c6ae08592 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -10,7 +10,7 @@ DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
DEF_NATIVE(pv_cpu_ops, clts, "clts");
-#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
#endif
@@ -49,7 +49,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_mmu_ops, read_cr3);
PATCH_SITE(pv_mmu_ops, write_cr3);
PATCH_SITE(pv_cpu_ops, clts);
-#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
if (pv_is_native_spin_unlock()) {
start = start_pv_lock_ops_queued_spin_unlock;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index e70087a04cc8..bb3840cedb4f 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -19,7 +19,7 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
DEF_NATIVE(, mov32, "mov %edi, %eax");
DEF_NATIVE(, mov64, "mov %rdi, %rax");
-#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
#endif
@@ -61,7 +61,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_cpu_ops, clts);
PATCH_SITE(pv_mmu_ops, flush_tlb_single);
PATCH_SITE(pv_cpu_ops, wbinvd);
-#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
if (pv_is_native_spin_unlock()) {
start = start_pv_lock_ops_queued_spin_unlock;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 62c0b0ea2ce4..4002b475171c 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -32,6 +32,7 @@
#include <asm/tlbflush.h>
#include <asm/mce.h>
#include <asm/vm86.h>
+#include <asm/switch_to.h>
/*
* per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -513,6 +514,17 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
}
/*
+ * Return saved PC of a blocked thread.
+ * What is this good for? it will be always the scheduler or ret_from_fork.
+ */
+unsigned long thread_saved_pc(struct task_struct *tsk)
+{
+ struct inactive_task_frame *frame =
+ (struct inactive_task_frame *) READ_ONCE(tsk->thread.sp);
+ return READ_ONCE_NOCHECK(frame->ret_addr);
+}
+
+/*
* Called from fs/proc with a reference on @p to find the function
* which called into schedule(). This needs to be done carefully
* because the task might wake up and we might look at a stack
@@ -520,15 +532,18 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
*/
unsigned long get_wchan(struct task_struct *p)
{
- unsigned long start, bottom, top, sp, fp, ip;
+ unsigned long start, bottom, top, sp, fp, ip, ret = 0;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
+ if (!try_get_task_stack(p))
+ return 0;
+
start = (unsigned long)task_stack_page(p);
if (!start)
- return 0;
+ goto out;
/*
* Layout of the stack page:
@@ -537,9 +552,7 @@ unsigned long get_wchan(struct task_struct *p)
* PADDING
* ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
* stack
- * ----------- bottom = start + sizeof(thread_info)
- * thread_info
- * ----------- start
+ * ----------- bottom = start
*
* The tasks stack pointer points at the location where the
* framepointer is stored. The data on the stack is:
@@ -550,20 +563,25 @@ unsigned long get_wchan(struct task_struct *p)
*/
top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
top -= 2 * sizeof(unsigned long);
- bottom = start + sizeof(struct thread_info);
+ bottom = start;
sp = READ_ONCE(p->thread.sp);
if (sp < bottom || sp > top)
- return 0;
+ goto out;
- fp = READ_ONCE_NOCHECK(*(unsigned long *)sp);
+ fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp);
do {
if (fp < bottom || fp > top)
- return 0;
+ goto out;
ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long)));
- if (!in_sched_functions(ip))
- return ip;
+ if (!in_sched_functions(ip)) {
+ ret = ip;
+ goto out;
+ }
fp = READ_ONCE_NOCHECK(*(unsigned long *)fp);
} while (count++ < 16 && p->state != TASK_RUNNING);
- return 0;
+
+out:
+ put_task_stack(p);
+ return ret;
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index d86be29c38c7..bd7be8efdc4c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -55,17 +55,6 @@
#include <asm/switch_to.h>
#include <asm/vm86.h>
-asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
-
-/*
- * Return saved PC of a blocked thread.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
- return ((unsigned long *)tsk->thread.sp)[3];
-}
-
void __show_regs(struct pt_regs *regs, int all)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
@@ -101,7 +90,7 @@ void __show_regs(struct pt_regs *regs, int all)
cr0 = read_cr0();
cr2 = read_cr2();
cr3 = read_cr3();
- cr4 = __read_cr4_safe();
+ cr4 = __read_cr4();
printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
cr0, cr2, cr3, cr4);
@@ -133,35 +122,31 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
unsigned long arg, struct task_struct *p, unsigned long tls)
{
struct pt_regs *childregs = task_pt_regs(p);
+ struct fork_frame *fork_frame = container_of(childregs, struct fork_frame, regs);
+ struct inactive_task_frame *frame = &fork_frame->frame;
struct task_struct *tsk;
int err;
- p->thread.sp = (unsigned long) childregs;
+ frame->bp = 0;
+ frame->ret_addr = (unsigned long) ret_from_fork;
+ p->thread.sp = (unsigned long) fork_frame;
p->thread.sp0 = (unsigned long) (childregs+1);
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
- p->thread.ip = (unsigned long) ret_from_kernel_thread;
- task_user_gs(p) = __KERNEL_STACK_CANARY;
- childregs->ds = __USER_DS;
- childregs->es = __USER_DS;
- childregs->fs = __KERNEL_PERCPU;
- childregs->bx = sp; /* function */
- childregs->bp = arg;
- childregs->orig_ax = -1;
- childregs->cs = __KERNEL_CS | get_kernel_rpl();
- childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
+ frame->bx = sp; /* function */
+ frame->di = arg;
p->thread.io_bitmap_ptr = NULL;
return 0;
}
+ frame->bx = 0;
*childregs = *current_pt_regs();
childregs->ax = 0;
if (sp)
childregs->sp = sp;
- p->thread.ip = (unsigned long) ret_from_fork;
task_user_gs(p) = get_user_gs(current_pt_regs());
p->thread.io_bitmap_ptr = NULL;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 63236d8f84bf..ee944bd2310d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -49,8 +49,7 @@
#include <asm/debugreg.h>
#include <asm/switch_to.h>
#include <asm/xen/hypervisor.h>
-
-asmlinkage extern void ret_from_fork(void);
+#include <asm/vdso.h>
__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
@@ -141,12 +140,17 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
{
int err;
struct pt_regs *childregs;
+ struct fork_frame *fork_frame;
+ struct inactive_task_frame *frame;
struct task_struct *me = current;
p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
childregs = task_pt_regs(p);
- p->thread.sp = (unsigned long) childregs;
- set_tsk_thread_flag(p, TIF_FORK);
+ fork_frame = container_of(childregs, struct fork_frame, regs);
+ frame = &fork_frame->frame;
+ frame->bp = 0;
+ frame->ret_addr = (unsigned long) ret_from_fork;
+ p->thread.sp = (unsigned long) fork_frame;
p->thread.io_bitmap_ptr = NULL;
savesegment(gs, p->thread.gsindex);
@@ -160,15 +164,11 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
- childregs->sp = (unsigned long)childregs;
- childregs->ss = __KERNEL_DS;
- childregs->bx = sp; /* function */
- childregs->bp = arg;
- childregs->orig_ax = -1;
- childregs->cs = __KERNEL_CS | get_kernel_rpl();
- childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
+ frame->bx = sp; /* function */
+ frame->r12 = arg;
return 0;
}
+ frame->bx = 0;
*childregs = *current_pt_regs();
childregs->ax = 0;
@@ -511,7 +511,7 @@ void set_personality_ia32(bool x32)
current->personality &= ~READ_IMPLIES_EXEC;
/* in_compat_syscall() uses the presence of the x32
syscall bit flag to determine compat status */
- current_thread_info()->status &= ~TS_COMPAT;
+ current->thread.status &= ~TS_COMPAT;
} else {
set_thread_flag(TIF_IA32);
clear_thread_flag(TIF_X32);
@@ -519,11 +519,24 @@ void set_personality_ia32(bool x32)
current->mm->context.ia32_compat = TIF_IA32;
current->personality |= force_personality32;
/* Prepare the first "return" to user space */
- current_thread_info()->status |= TS_COMPAT;
+ current->thread.status |= TS_COMPAT;
}
}
EXPORT_SYMBOL_GPL(set_personality_ia32);
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
+{
+ int ret;
+
+ ret = map_vdso_once(image, addr);
+ if (ret)
+ return ret;
+
+ return (long)image->size;
+}
+#endif
+
long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
{
int ret = 0;
@@ -577,6 +590,19 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
break;
}
+#ifdef CONFIG_CHECKPOINT_RESTORE
+# ifdef CONFIG_X86_X32_ABI
+ case ARCH_MAP_VDSO_X32:
+ return prctl_map_vdso(&vdso_image_x32, addr);
+# endif
+# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+ case ARCH_MAP_VDSO_32:
+ return prctl_map_vdso(&vdso_image_32, addr);
+# endif
+ case ARCH_MAP_VDSO_64:
+ return prctl_map_vdso(&vdso_image_64, addr);
+#endif
+
default:
ret = -EINVAL;
break;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index f79576a541ff..0e63c0267f99 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -173,8 +173,8 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs)
return sp;
prev_esp = (u32 *)(context);
- if (prev_esp)
- return (unsigned long)prev_esp;
+ if (*prev_esp)
+ return (unsigned long)*prev_esp;
return (unsigned long)regs;
}
@@ -934,7 +934,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value)
*/
regs->orig_ax = value;
if (syscall_get_nr(child, regs) >= 0)
- task_thread_info(child)->status |= TS_I386_REGS_POKED;
+ child->thread.status |= TS_I386_REGS_POKED;
break;
case offsetof(struct user32, regs.eflags):
@@ -1250,7 +1250,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
#ifdef CONFIG_X86_64
-static struct user_regset x86_64_regsets[] __read_mostly = {
+static struct user_regset x86_64_regsets[] __ro_after_init = {
[REGSET_GENERAL] = {
.core_note_type = NT_PRSTATUS,
.n = sizeof(struct user_regs_struct) / sizeof(long),
@@ -1291,7 +1291,7 @@ static const struct user_regset_view user_x86_64_view = {
#endif /* CONFIG_X86_64 */
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-static struct user_regset x86_32_regsets[] __read_mostly = {
+static struct user_regset x86_32_regsets[] __ro_after_init = {
[REGSET_GENERAL] = {
.core_note_type = NT_PRSTATUS,
.n = sizeof(struct user_regs_struct32) / sizeof(u32),
@@ -1344,7 +1344,7 @@ static const struct user_regset_view user_x86_32_view = {
*/
u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
-void update_regset_xstate_info(unsigned int size, u64 xstate_mask)
+void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask)
{
#ifdef CONFIG_X86_64
x86_64_regsets[REGSET_XSTATE].n = size / sizeof(u64);
@@ -1358,7 +1358,7 @@ void update_regset_xstate_info(unsigned int size, u64 xstate_mask)
const struct user_regset_view *task_user_regset_view(struct task_struct *task)
{
#ifdef CONFIG_IA32_EMULATION
- if (test_tsk_thread_flag(task, TIF_IA32))
+ if (!user_64bit_mode(task_pt_regs(task)))
#endif
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
return &user_x86_32_view;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index cc457ff818ad..51402a7e4ca6 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -626,3 +626,34 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
amd_disable_seq_and_redirect_scrub);
#endif
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
+#include <linux/jump_label.h>
+#include <asm/string_64.h>
+
+/* Ivy Bridge, Haswell, Broadwell */
+static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev)
+{
+ u32 capid0;
+
+ pci_read_config_dword(pdev, 0x84, &capid0);
+
+ if (capid0 & 0x10)
+ static_branch_inc(&mcsafe_key);
+}
+
+/* Skylake */
+static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)
+{
+ u32 capid0;
+
+ pci_read_config_dword(pdev, 0x84, &capid0);
+
+ if ((capid0 & 0xc0) == 0xc0)
+ static_branch_inc(&mcsafe_key);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap);
+#endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 63bf27d972b7..e244c19a2451 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -705,7 +705,7 @@ static void native_machine_power_off(void)
tboot_shutdown(TB_SHUTDOWN_HALT);
}
-struct machine_ops machine_ops = {
+struct machine_ops machine_ops __ro_after_init = {
.power_off = native_machine_power_off,
.shutdown = native_machine_shutdown,
.emergency_restart = native_machine_emergency_restart,
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 80eab01c1a68..2408c1603438 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -27,8 +27,8 @@ static void remove_e820_regions(struct resource *avail)
int i;
struct e820entry *entry;
- for (i = 0; i < e820.nr_map; i++) {
- entry = &e820.map[i];
+ for (i = 0; i < e820->nr_map; i++) {
+ entry = &e820->map[i];
resource_clip(avail, entry->addr,
entry->addr + entry->size - 1);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0fa60f5f5a16..bbfbca5fea0c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -210,9 +210,9 @@ EXPORT_SYMBOL(boot_cpu_data);
#if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-__visible unsigned long mmu_cr4_features;
+__visible unsigned long mmu_cr4_features __ro_after_init;
#else
-__visible unsigned long mmu_cr4_features = X86_CR4_PAE;
+__visible unsigned long mmu_cr4_features __ro_after_init = X86_CR4_PAE;
#endif
/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
@@ -458,8 +458,8 @@ static void __init e820_reserve_setup_data(void)
early_memunmap(data, sizeof(*data));
}
- sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
- memcpy(&e820_saved, &e820, sizeof(struct e820map));
+ sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+ memcpy(e820_saved, e820, sizeof(struct e820map));
printk(KERN_INFO "extended physical RAM map:\n");
e820_print_map("reserve setup_data");
}
@@ -763,7 +763,7 @@ static void __init trim_bios_range(void)
*/
e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
- sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
}
/* called before trim_bios_range() to spare extra sanitize */
@@ -1032,7 +1032,7 @@ void __init setup_arch(char **cmdline_p)
if (ppro_with_ram_bug()) {
e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
E820_RESERVED);
- sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
printk(KERN_INFO "fixed physical RAM map:\n");
e820_print_map("bad_ppro");
}
@@ -1096,19 +1096,19 @@ void __init setup_arch(char **cmdline_p)
memblock_set_current_limit(ISA_END_ADDRESS);
memblock_x86_fill();
- if (efi_enabled(EFI_BOOT)) {
+ reserve_bios_regions();
+
+ if (efi_enabled(EFI_MEMMAP)) {
efi_fake_memmap();
efi_find_mirror();
- }
-
- reserve_bios_regions();
+ efi_esrt_init();
- /*
- * The EFI specification says that boot service code won't be called
- * after ExitBootServices(). This is, in fact, a lie.
- */
- if (efi_enabled(EFI_MEMMAP))
+ /*
+ * The EFI specification says that boot service code won't be
+ * called after ExitBootServices(). This is, in fact, a lie.
+ */
efi_reserve_boot_services();
+ }
/* preallocate 4k for mptable mpc */
early_reserve_e820_mpc_new();
@@ -1137,9 +1137,7 @@ void __init setup_arch(char **cmdline_p)
* auditing all the early-boot CR4 manipulation would be needed to
* rule it out.
*/
- if (boot_cpu_data.cpuid_level >= 0)
- /* A CPU has %cr4 if and only if it has CPUID. */
- mmu_cr4_features = __read_cr4();
+ mmu_cr4_features = __read_cr4();
memblock_set_current_limit(get_max_mapped());
@@ -1221,8 +1219,7 @@ void __init setup_arch(char **cmdline_p)
/*
* get boot-time SMP configuration:
*/
- if (smp_found_config)
- get_smp_config();
+ get_smp_config();
prefill_possible_map();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 7a40e068302d..2bbd27f89802 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -33,7 +33,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number);
DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
EXPORT_PER_CPU_SYMBOL(this_cpu_off);
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
};
EXPORT_SYMBOL(__per_cpu_offset);
@@ -246,7 +246,7 @@ void __init setup_per_cpu_areas(void)
#ifdef CONFIG_X86_64
per_cpu(irq_stack_ptr, cpu) =
per_cpu(irq_stack_union.irq_stack, cpu) +
- IRQ_STACK_SIZE - 64;
+ IRQ_STACK_SIZE;
#endif
#ifdef CONFIG_NUMA
per_cpu(x86_cpu_to_node_map, cpu) =
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 04cb3212db2d..763af1d0de64 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -42,6 +42,7 @@
#include <asm/syscalls.h>
#include <asm/sigframe.h>
+#include <asm/signal.h>
#define COPY(x) do { \
get_user_ex(regs->x, &sc->x); \
@@ -547,7 +548,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
return -EFAULT;
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
- if (copy_siginfo_to_user32(&frame->info, &ksig->info))
+ if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true))
return -EFAULT;
}
@@ -660,20 +661,21 @@ badframe:
return 0;
}
-static inline int is_ia32_compat_frame(void)
+static inline int is_ia32_compat_frame(struct ksignal *ksig)
{
return IS_ENABLED(CONFIG_IA32_EMULATION) &&
- test_thread_flag(TIF_IA32);
+ ksig->ka.sa.sa_flags & SA_IA32_ABI;
}
-static inline int is_ia32_frame(void)
+static inline int is_ia32_frame(struct ksignal *ksig)
{
- return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame();
+ return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig);
}
-static inline int is_x32_frame(void)
+static inline int is_x32_frame(struct ksignal *ksig)
{
- return IS_ENABLED(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+ return IS_ENABLED(CONFIG_X86_X32_ABI) &&
+ ksig->ka.sa.sa_flags & SA_X32_ABI;
}
static int
@@ -684,12 +686,12 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
compat_sigset_t *cset = (compat_sigset_t *) set;
/* Set up the stack frame */
- if (is_ia32_frame()) {
+ if (is_ia32_frame(ksig)) {
if (ksig->ka.sa.sa_flags & SA_SIGINFO)
return ia32_setup_rt_frame(usig, ksig, cset, regs);
else
return ia32_setup_frame(usig, ksig, cset, regs);
- } else if (is_x32_frame()) {
+ } else if (is_x32_frame(ksig)) {
return x32_setup_rt_frame(ksig, cset, regs);
} else {
return __setup_rt_frame(ksig->sig, ksig, set, regs);
@@ -783,7 +785,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
* than the tracee.
*/
#ifdef CONFIG_IA32_EMULATION
- if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED))
+ if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED))
return __NR_ia32_restart_syscall;
#endif
#ifdef CONFIG_X86_X32_ABI
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index b44564bf86a8..40df33753bae 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -1,5 +1,6 @@
#include <linux/compat.h>
#include <linux/uaccess.h>
+#include <linux/ptrace.h>
/*
* The compat_siginfo_t structure and handing code is very easy
@@ -92,10 +93,31 @@ static inline void signal_compat_build_tests(void)
/* any new si_fields should be added here */
}
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
+void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
+{
+ /* Don't leak in-kernel non-uapi flags to user-space */
+ if (oact)
+ oact->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
+
+ if (!act)
+ return;
+
+ /* Don't let flags to be set from userspace */
+ act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
+
+ if (user_64bit_mode(current_pt_regs()))
+ return;
+
+ if (in_ia32_syscall())
+ act->sa.sa_flags |= SA_IA32_ABI;
+ 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;
- bool ia32 = test_thread_flag(TIF_IA32);
signal_compat_build_tests();
@@ -146,7 +168,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
put_user_ex(from->si_arch, &to->si_arch);
break;
case __SI_CHLD >> 16:
- if (ia32) {
+ if (!x32_ABI) {
put_user_ex(from->si_utime, &to->si_utime);
put_user_ex(from->si_stime, &to->si_stime);
} else {
@@ -180,6 +202,12 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
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;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4296beb8fdd3..42a93621f5b0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -471,7 +471,7 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
return false;
}
-static struct sched_domain_topology_level numa_inside_package_topology[] = {
+static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
#endif
@@ -480,22 +480,23 @@ static struct sched_domain_topology_level numa_inside_package_topology[] = {
#endif
{ NULL, },
};
+
+static struct sched_domain_topology_level x86_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+ { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+ { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+ { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { NULL, },
+};
+
/*
- * set_sched_topology() sets the topology internal to a CPU. The
- * NUMA topologies are layered on top of it to build the full
- * system topology.
- *
- * If NUMA nodes are observed to occur within a CPU package, this
- * function should be called. It forces the sched domain code to
- * only use the SMT level for the CPU portion of the topology.
- * This essentially falls back to relying on NUMA information
- * from the SRAT table to describe the entire system topology
- * (except for hyperthreads).
+ * Set if a package/die has multiple NUMA nodes inside.
+ * AMD Magny-Cours and Intel Cluster-on-Die have this.
*/
-static void primarily_use_numa_for_topology(void)
-{
- set_sched_topology(numa_inside_package_topology);
-}
+static bool x86_has_numa_in_package;
void set_cpu_sibling_map(int cpu)
{
@@ -558,7 +559,7 @@ void set_cpu_sibling_map(int cpu)
c->booted_cores = cpu_data(i).booted_cores;
}
if (match_die(c, o) && !topology_same_node(c, o))
- primarily_use_numa_for_topology();
+ x86_has_numa_in_package = true;
}
threads = cpumask_weight(topology_sibling_cpumask(cpu));
@@ -690,7 +691,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
- if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+ if (APIC_INTEGRATED(boot_cpu_apic_version)) {
maxlvt = lapic_get_maxlvt();
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
@@ -717,7 +718,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
/*
* Be paranoid about clearing APIC errors.
*/
- if (APIC_INTEGRATED(apic_version[phys_apicid])) {
+ if (APIC_INTEGRATED(boot_cpu_apic_version)) {
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
@@ -756,7 +757,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
* Determine this based on the APIC version.
* If we don't have an integrated APIC, don't send the STARTUP IPIs.
*/
- if (APIC_INTEGRATED(apic_version[phys_apicid]))
+ if (APIC_INTEGRATED(boot_cpu_apic_version))
num_starts = 2;
else
num_starts = 0;
@@ -942,7 +943,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
per_cpu(cpu_current_top_of_stack, cpu) =
(unsigned long)task_stack_page(idle) + THREAD_SIZE;
#else
- clear_tsk_thread_flag(idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
#endif
}
@@ -969,7 +969,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
- stack_start = idle->thread.sp;
+ initial_stack = idle->thread.sp;
/*
* Enable the espfix hack for this CPU
@@ -994,7 +994,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
/*
* Be paranoid about clearing APIC errors.
*/
- if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+ if (APIC_INTEGRATED(boot_cpu_apic_version)) {
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
}
@@ -1115,17 +1115,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
common_cpu_up(cpu, tidle);
- /*
- * We have to walk the irq descriptors to setup the vector
- * space for the cpu which comes online. Prevent irq
- * alloc/free across the bringup.
- */
- irq_lock_sparse();
-
err = do_boot_cpu(apicid, cpu, tidle);
-
if (err) {
- irq_unlock_sparse();
pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
return -EIO;
}
@@ -1143,8 +1134,6 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
touch_nmi_watchdog();
}
- irq_unlock_sparse();
-
return 0;
}
@@ -1249,7 +1238,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
/*
* If we couldn't find a local APIC, then get out of here now!
*/
- if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
+ if (APIC_INTEGRATED(boot_cpu_apic_version) &&
!boot_cpu_has(X86_FEATURE_APIC)) {
if (!disable_apic) {
pr_err("BIOS bug, local APIC #%d not detected!...\n",
@@ -1304,6 +1293,16 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
+
+ /*
+ * Set 'default' x86 topology, this matches default_topology() in that
+ * it has NUMA nodes as a topology level. See also
+ * native_smp_cpus_done().
+ *
+ * Must be done before set_cpus_sibling_map() is ran.
+ */
+ set_sched_topology(x86_topology);
+
set_cpu_sibling_map(0);
switch (smp_sanity_check(max_cpus)) {
@@ -1323,14 +1322,13 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
break;
}
- default_setup_apic_routing();
-
if (read_apic_id() != boot_cpu_physical_apicid) {
panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
read_apic_id(), boot_cpu_physical_apicid);
/* Or can we switch back to PIC here? */
}
+ default_setup_apic_routing();
cpu0_logical_apicid = apic_bsp_setup(false);
pr_info("CPU%d: ", 0);
@@ -1370,6 +1368,9 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
{
pr_debug("Boot done\n");
+ if (x86_has_numa_in_package)
+ set_sched_topology(x86_numa_in_package_topology);
+
nmi_selftest();
impress_friends();
setup_ioapic_dest();
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 4738f5e0f2ab..0653788026e2 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -8,80 +8,69 @@
#include <linux/export.h>
#include <linux/uaccess.h>
#include <asm/stacktrace.h>
+#include <asm/unwind.h>
-static int save_stack_stack(void *data, char *name)
+static int save_stack_address(struct stack_trace *trace, unsigned long addr,
+ bool nosched)
{
- return 0;
-}
-
-static int
-__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched)
-{
- struct stack_trace *trace = data;
-#ifdef CONFIG_FRAME_POINTER
- if (!reliable)
- return 0;
-#endif
if (nosched && in_sched_functions(addr))
return 0;
+
if (trace->skip > 0) {
trace->skip--;
return 0;
}
- if (trace->nr_entries < trace->max_entries) {
- trace->entries[trace->nr_entries++] = addr;
- return 0;
- } else {
- return -1; /* no more room, stop walking the stack */
- }
-}
-static int save_stack_address(void *data, unsigned long addr, int reliable)
-{
- return __save_stack_address(data, addr, reliable, false);
+ if (trace->nr_entries >= trace->max_entries)
+ return -1;
+
+ trace->entries[trace->nr_entries++] = addr;
+ return 0;
}
-static int
-save_stack_address_nosched(void *data, unsigned long addr, int reliable)
+static void __save_stack_trace(struct stack_trace *trace,
+ struct task_struct *task, struct pt_regs *regs,
+ bool nosched)
{
- return __save_stack_address(data, addr, reliable, true);
-}
+ struct unwind_state state;
+ unsigned long addr;
-static const struct stacktrace_ops save_stack_ops = {
- .stack = save_stack_stack,
- .address = save_stack_address,
- .walk_stack = print_context_stack,
-};
+ if (regs)
+ save_stack_address(trace, regs->ip, nosched);
-static const struct stacktrace_ops save_stack_ops_nosched = {
- .stack = save_stack_stack,
- .address = save_stack_address_nosched,
- .walk_stack = print_context_stack,
-};
+ for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
+ unwind_next_frame(&state)) {
+ addr = unwind_get_return_address(&state);
+ if (!addr || save_stack_address(trace, addr, nosched))
+ break;
+ }
+
+ if (trace->nr_entries < trace->max_entries)
+ trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
/*
* Save stack-backtrace addresses into a stack_trace buffer.
*/
void save_stack_trace(struct stack_trace *trace)
{
- dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
+ __save_stack_trace(trace, current, NULL, false);
}
EXPORT_SYMBOL_GPL(save_stack_trace);
void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
{
- dump_trace(current, regs, NULL, 0, &save_stack_ops, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
+ __save_stack_trace(trace, current, regs, false);
}
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
- dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
+ if (!try_get_task_stack(tsk))
+ return;
+
+ __save_stack_trace(trace, tsk, NULL, true);
+
+ put_task_stack(tsk);
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 654f6c66fe45..8402907825b0 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -188,12 +188,12 @@ static int tboot_setup_sleep(void)
tboot->num_mac_regions = 0;
- for (i = 0; i < e820.nr_map; i++) {
- if ((e820.map[i].type != E820_RAM)
- && (e820.map[i].type != E820_RESERVED_KERN))
+ for (i = 0; i < e820->nr_map; i++) {
+ if ((e820->map[i].type != E820_RAM)
+ && (e820->map[i].type != E820_RESERVED_KERN))
continue;
- add_mac_region(e820.map[i].addr, e820.map[i].size);
+ add_mac_region(e820->map[i].addr, e820->map[i].size);
}
tboot->acpi_sinfo.kernel_s3_resume_vector =
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b70ca12dd389..bd4e3d4d3625 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -292,12 +292,30 @@ DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check)
+#ifdef CONFIG_VMAP_STACK
+__visible void __noreturn handle_stack_overflow(const char *message,
+ struct pt_regs *regs,
+ unsigned long fault_address)
+{
+ printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n",
+ (void *)fault_address, current->stack,
+ (char *)current->stack + THREAD_SIZE - 1);
+ die(message, regs, 0);
+
+ /* Be absolutely certain we don't return. */
+ panic(message);
+}
+#endif
+
#ifdef CONFIG_X86_64
/* Runs on IST stack */
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
{
static const char str[] = "double fault";
struct task_struct *tsk = current;
+#ifdef CONFIG_VMAP_STACK
+ unsigned long cr2;
+#endif
#ifdef CONFIG_X86_ESPFIX64
extern unsigned char native_irq_return_iret[];
@@ -332,6 +350,49 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_DF;
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * If we overflow the stack into a guard page, the CPU will fail
+ * to deliver #PF and will send #DF instead. Similarly, if we
+ * take any non-IST exception while too close to the bottom of
+ * the stack, the processor will get a page fault while
+ * delivering the exception and will generate a double fault.
+ *
+ * According to the SDM (footnote in 6.15 under "Interrupt 14 -
+ * Page-Fault Exception (#PF):
+ *
+ * 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
+ * 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
+ * double fault.
+ *
+ * The logic below has a small possibility of incorrectly diagnosing
+ * some errors as stack overflows. For example, if the IDT or GDT
+ * gets corrupted such that #GP delivery fails due to a bad descriptor
+ * causing #GP and we hit this condition while CR2 coincidentally
+ * points to the stack guard page, we'll think we overflowed the
+ * stack. Given that we're going to panic one way or another
+ * if this happens, this isn't necessarily worth fixing.
+ *
+ * If necessary, we could improve the test by only diagnosing
+ * a stack overflow if the saved RSP points within 47 bytes of
+ * the bottom of the stack: if RSP == tsk_stack + 48 and we
+ * take an exception, the stack is already aligned and there
+ * will be enough room SS, RSP, RFLAGS, CS, RIP, and a
+ * possible error code, so a stack overflow would *not* double
+ * fault. With any less space left, exception delivery could
+ * fail, and, as a practical matter, we've overflowed the
+ * stack even if the actual trigger for the double fault was
+ * something else.
+ */
+ cr2 = read_cr2();
+ if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE)
+ handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2);
+#endif
+
#ifdef CONFIG_DOUBLEFAULT
df_debug(regs, error_code);
#endif
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 78b9cb5a26af..46b2f41f8b05 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -23,6 +23,7 @@
#include <asm/x86_init.h>
#include <asm/geode.h>
#include <asm/apic.h>
+#include <asm/intel-family.h>
unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
@@ -686,11 +687,16 @@ unsigned long native_calibrate_tsc(void)
if (crystal_khz == 0) {
switch (boot_cpu_data.x86_model) {
- case 0x4E: /* SKL */
- case 0x5E: /* SKL */
+ case INTEL_FAM6_SKYLAKE_MOBILE:
+ case INTEL_FAM6_SKYLAKE_DESKTOP:
+ case INTEL_FAM6_KABYLAKE_MOBILE:
+ case INTEL_FAM6_KABYLAKE_DESKTOP:
crystal_khz = 24000; /* 24.0 MHz */
break;
- case 0x5C: /* BXT */
+ case INTEL_FAM6_SKYLAKE_X:
+ crystal_khz = 25000; /* 25.0 MHz */
+ break;
+ case INTEL_FAM6_ATOM_GOLDMONT:
crystal_khz = 19200; /* 19.2 MHz */
break;
}
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
new file mode 100644
index 000000000000..a2456d4d286a
--- /dev/null
+++ b/arch/x86/kernel/unwind_frame.c
@@ -0,0 +1,93 @@
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+#include <asm/bitops.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+#define FRAME_HEADER_SIZE (sizeof(long) * 2)
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+ unsigned long addr;
+ unsigned long *addr_p = unwind_get_return_address_ptr(state);
+
+ if (unwind_done(state))
+ return 0;
+
+ addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
+ addr_p);
+
+ return __kernel_text_address(addr) ? addr : 0;
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+static bool update_stack_state(struct unwind_state *state, void *addr,
+ size_t len)
+{
+ struct stack_info *info = &state->stack_info;
+
+ /*
+ * If addr 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 'addr' could
+ * be on a subsequent stack.
+ */
+ while (!on_stack(info, addr, len))
+ if (get_stack_info(info->next_sp, state->task, info,
+ &state->stack_mask))
+ return false;
+
+ return true;
+}
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+ unsigned long *next_bp;
+
+ if (unwind_done(state))
+ return false;
+
+ next_bp = (unsigned long *)*state->bp;
+
+ /* make sure the next frame's data is accessible */
+ if (!update_stack_state(state, next_bp, FRAME_HEADER_SIZE))
+ return false;
+
+ /* move to the next frame */
+ state->bp = next_bp;
+ return true;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs, unsigned long *first_frame)
+{
+ memset(state, 0, sizeof(*state));
+ state->task = task;
+
+ /* don't even attempt to start from user mode regs */
+ if (regs && user_mode(regs)) {
+ state->stack_info.type = STACK_TYPE_UNKNOWN;
+ return;
+ }
+
+ /* set up the starting stack frame */
+ state->bp = get_frame_pointer(task, regs);
+
+ /* initialize stack info and make sure the frame data is accessible */
+ get_stack_info(state->bp, state->task, &state->stack_info,
+ &state->stack_mask);
+ update_stack_state(state, state->bp, FRAME_HEADER_SIZE);
+
+ /*
+ * The caller can provide the address of the first frame directly
+ * (first_frame) or indirectly (regs->sp) to indicate which stack frame
+ * to start unwinding at. Skip ahead until we reach it.
+ */
+ while (!unwind_done(state) &&
+ (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
+ state->bp < first_frame))
+ unwind_next_frame(state);
+}
+EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
new file mode 100644
index 000000000000..b5a834c93065
--- /dev/null
+++ b/arch/x86/kernel/unwind_guess.c
@@ -0,0 +1,43 @@
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
+#include <asm/bitops.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+ struct stack_info *info = &state->stack_info;
+
+ if (unwind_done(state))
+ return false;
+
+ do {
+ for (state->sp++; state->sp < info->end; state->sp++)
+ if (__kernel_text_address(*state->sp))
+ return true;
+
+ state->sp = info->next_sp;
+
+ } while (!get_stack_info(state->sp, state->task, info,
+ &state->stack_mask));
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs, unsigned long *first_frame)
+{
+ memset(state, 0, sizeof(*state));
+
+ state->task = task;
+ state->sp = first_frame;
+
+ get_stack_info(first_frame, state->task, &state->stack_info,
+ &state->stack_mask);
+
+ if (!__kernel_text_address(*first_frame))
+ unwind_next_frame(state);
+}
+EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 95e49f6e4fc3..b2cee3d19477 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -38,7 +38,7 @@ EXPORT_SYMBOL(__copy_user_nocache);
EXPORT_SYMBOL(_copy_from_user);
EXPORT_SYMBOL(_copy_to_user);
-EXPORT_SYMBOL_GPL(memcpy_mcsafe);
+EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled);
EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(clear_page);
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 76c5e52436c4..0bd9f1287f39 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -91,7 +91,7 @@ struct x86_cpuinit_ops x86_cpuinit = {
static void default_nmi_init(void) { };
static int default_i8042_detect(void) { return 1; };
-struct x86_platform_ops x86_platform = {
+struct x86_platform_ops x86_platform __ro_after_init = {
.calibrate_cpu = native_calibrate_cpu,
.calibrate_tsc = native_calibrate_tsc,
.get_wallclock = mach_get_cmos_time,
@@ -108,7 +108,7 @@ struct x86_platform_ops x86_platform = {
EXPORT_SYMBOL_GPL(x86_platform);
#if defined(CONFIG_PCI_MSI)
-struct x86_msi_ops x86_msi = {
+struct x86_msi_ops x86_msi __ro_after_init = {
.setup_msi_irqs = native_setup_msi_irqs,
.teardown_msi_irq = native_teardown_msi_irq,
.teardown_msi_irqs = default_teardown_msi_irqs,
@@ -137,7 +137,7 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
}
#endif
-struct x86_io_apic_ops x86_io_apic_ops = {
+struct x86_io_apic_ops x86_io_apic_ops __ro_after_init = {
.read = native_io_apic_read,
.disable = native_disable_io_apic,
};
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 5f42d038fcb4..c7220ba94aa7 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -109,6 +109,7 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
{
bool new_val, old_val;
struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+ struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
union kvm_ioapic_redirect_entry *e;
e = &ioapic->redirtbl[RTC_GSI];
@@ -117,16 +118,17 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
return;
new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
- old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ old_val = test_bit(vcpu->vcpu_id, dest_map->map);
if (new_val == old_val)
return;
if (new_val) {
- __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ __set_bit(vcpu->vcpu_id, dest_map->map);
+ dest_map->vectors[vcpu->vcpu_id] = e->fields.vector;
ioapic->rtc_status.pending_eoi++;
} else {
- __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ __clear_bit(vcpu->vcpu_id, dest_map->map);
ioapic->rtc_status.pending_eoi--;
rtc_status_pending_eoi_check_valid(ioapic);
}
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 39b91127ef07..cd944435dfbd 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -23,8 +23,8 @@
static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
- [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
- [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+ [2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES },
+ [3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES },
[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index af523d84d102..1e6b84b96ea6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -4961,7 +4961,7 @@ static inline void avic_post_state_restore(struct kvm_vcpu *vcpu)
avic_handle_ldr_update(vcpu);
}
-static struct kvm_x86_ops svm_x86_ops = {
+static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.hardware_setup = svm_hardware_setup,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5cede40e2552..121fdf6e9ed0 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11177,7 +11177,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu)
~FEATURE_CONTROL_LMCE;
}
-static struct kvm_x86_ops vmx_x86_ops = {
+static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.hardware_setup = hardware_setup,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 19f9f9e05c2a..699f8726539a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2743,16 +2743,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (kvm_lapic_hv_timer_in_use(vcpu) &&
- kvm_x86_ops->set_hv_timer(vcpu,
- kvm_get_lapic_tscdeadline_msr(vcpu)))
- kvm_lapic_switch_to_sw_timer(vcpu);
if (check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_x86_ops->write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
}
+ if (kvm_lapic_hv_timer_in_use(vcpu) &&
+ kvm_x86_ops->set_hv_timer(vcpu,
+ kvm_get_lapic_tscdeadline_msr(vcpu)))
+ kvm_lapic_switch_to_sw_timer(vcpu);
/*
* On a host with synchronized TSC, there is no need to update
* kvmclock on vcpu->cpu migration
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 2ec0b0abbfaa..49e6ebac7e73 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -181,11 +181,11 @@ ENDPROC(memcpy_orig)
#ifndef CONFIG_UML
/*
- * memcpy_mcsafe - memory copy with machine check exception handling
+ * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
* Note that we only catch machine checks when reading the source addresses.
* Writes to target are posted and don't generate machine checks.
*/
-ENTRY(memcpy_mcsafe)
+ENTRY(memcpy_mcsafe_unrolled)
cmpl $8, %edx
/* Less than 8 bytes? Go to byte copy loop */
jb .L_no_whole_words
@@ -273,7 +273,7 @@ ENTRY(memcpy_mcsafe)
.L_done_memcpy_trap:
xorq %rax, %rax
ret
-ENDPROC(memcpy_mcsafe)
+ENDPROC(memcpy_mcsafe_unrolled)
.section .fixup, "ax"
/* Return -EFAULT for any failure */
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index ba47524f56e8..d1c7de095808 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -52,21 +52,6 @@ static __init int find_northbridge(void)
return -ENOENT;
}
-static __init void early_get_boot_cpu_id(void)
-{
- /*
- * need to get the APIC ID of the BSP so can use that to
- * create apicid_to_node in amd_scan_nodes()
- */
-#ifdef CONFIG_X86_MPPARSE
- /*
- * get boot-time SMP configuration:
- */
- if (smp_found_config)
- early_get_smp_config();
-#endif
-}
-
int __init amd_numa_init(void)
{
u64 start = PFN_PHYS(0);
@@ -180,8 +165,11 @@ int __init amd_numa_init(void)
cores = 1 << bits;
apicid_base = 0;
- /* get the APIC ID of the BSP early for systems with apicid lifting */
- early_get_boot_cpu_id();
+ /*
+ * get boot-time SMP configuration:
+ */
+ early_get_smp_config();
+
if (boot_cpu_physical_apicid > 0) {
pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
apicid_base = boot_cpu_physical_apicid;
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 832b98f822be..79ae939970d3 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/extable.h>
#include <asm/uaccess.h>
#include <asm/traps.h>
#include <asm/kdebug.h>
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index dc8023060456..1e525122cbe4 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -5,7 +5,7 @@
*/
#include <linux/sched.h> /* test_thread_flag(), ... */
#include <linux/kdebug.h> /* oops_begin/end, ... */
-#include <linux/module.h> /* search_exception_table */
+#include <linux/extable.h> /* search_exception_table */
#include <linux/bootmem.h> /* max_low_pfn */
#include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */
#include <linux/mmiotrace.h> /* kmmio_handler, ... */
@@ -753,6 +753,38 @@ no_context(struct pt_regs *regs, unsigned long error_code,
return;
}
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * Stack overflow? During boot, we can fault near the initial
+ * stack in the direct map, but that's not an overflow -- check
+ * that we're in vmalloc space to avoid this.
+ */
+ if (is_vmalloc_addr((void *)address) &&
+ (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
+ address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
+ register void *__sp asm("rsp");
+ unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
+ /*
+ * We're likely to be running with very little stack space
+ * left. It's plausible that we'd hit this condition but
+ * double-fault even before we get this far, in which case
+ * we're fine: the double-fault handler will deal with it.
+ *
+ * We don't want to make it all the way into the oops code
+ * and then double-fault, though, because we're likely to
+ * break the console driver and lose most of the stack dump.
+ */
+ asm volatile ("movq %[stack], %%rsp\n\t"
+ "call handle_stack_overflow\n\t"
+ "1: jmp 1b"
+ : "+r" (__sp)
+ : "D" ("kernel stack overflow (page fault)"),
+ "S" (regs), "d" (address),
+ [stack] "rm" (stack));
+ unreachable();
+ }
+#endif
+
/*
* 32-bit:
*
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d28a2d741f9e..22af912d66d2 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -699,8 +699,10 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
}
}
-void free_initmem(void)
+void __ref free_initmem(void)
{
+ e820_reallocate_tables();
+
free_init_pages("unused kernel",
(unsigned long)(&__init_begin),
(unsigned long)(&__init_end));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index bda8d5eef04d..ddd2661c4502 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -40,17 +40,26 @@
* 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
+ * 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.
*/
static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
-static const unsigned long vaddr_end = VMEMMAP_START;
+
+#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_START;
+#else
+static const unsigned long vaddr_end = __START_KERNEL_map;
+#endif
/* Default values */
unsigned long page_offset_base = __PAGE_OFFSET_BASE;
EXPORT_SYMBOL(page_offset_base);
unsigned long vmalloc_base = __VMALLOC_BASE;
EXPORT_SYMBOL(vmalloc_base);
+unsigned long vmemmap_base = __VMEMMAP_BASE;
+EXPORT_SYMBOL(vmemmap_base);
/*
* Memory regions randomized by KASLR (except modules that use a separate logic
@@ -63,6 +72,7 @@ static __initdata struct kaslr_memory_region {
} kaslr_regions[] = {
{ &page_offset_base, 64/* Maximum */ },
{ &vmalloc_base, VMALLOC_SIZE_TB },
+ { &vmemmap_base, 1 },
};
/* Get size in bytes used by the memory region */
@@ -89,6 +99,18 @@ void __init kernel_randomize_memory(void)
struct rnd_state rand_state;
unsigned long remain_entropy;
+ /*
+ * All these BUILD_BUG_ON checks ensures the memory layout is
+ * consistent with the vaddr_start/vaddr_end variables.
+ */
+ BUILD_BUG_ON(vaddr_start >= vaddr_end);
+ BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) &&
+ vaddr_end >= EFI_VA_START);
+ BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) ||
+ config_enabled(CONFIG_EFI)) &&
+ vaddr_end >= __START_KERNEL_map);
+ BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
+
if (!kaslr_memory_enabled())
return;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fb682108f4dc..3f35b48d1d9d 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -722,22 +722,19 @@ void __init x86_numa_init(void)
numa_init(dummy_numa_init);
}
-static __init int find_near_online_node(int node)
+static void __init init_memory_less_node(int nid)
{
- int n, val;
- int min_val = INT_MAX;
- int best_node = -1;
+ unsigned long zones_size[MAX_NR_ZONES] = {0};
+ unsigned long zholes_size[MAX_NR_ZONES] = {0};
- for_each_online_node(n) {
- val = node_distance(node, n);
+ /* Allocate and initialize node data. Memory-less node is now online.*/
+ alloc_node_data(nid);
+ free_area_init_node(nid, zones_size, 0, zholes_size);
- if (val < min_val) {
- min_val = val;
- best_node = n;
- }
- }
-
- return best_node;
+ /*
+ * All zonelists will be built later in start_kernel() after per cpu
+ * areas are initialized.
+ */
}
/*
@@ -766,8 +763,10 @@ void __init init_cpu_to_node(void)
if (node == NUMA_NO_NODE)
continue;
+
if (!node_online(node))
- node = find_near_online_node(node);
+ init_memory_less_node(node);
+
numa_set_node(cpu, node);
}
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 849dc09fa4f0..e3353c97d086 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -917,11 +917,11 @@ static void populate_pte(struct cpa_data *cpa,
}
}
-static int populate_pmd(struct cpa_data *cpa,
- unsigned long start, unsigned long end,
- unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+static long populate_pmd(struct cpa_data *cpa,
+ unsigned long start, unsigned long end,
+ unsigned num_pages, pud_t *pud, pgprot_t pgprot)
{
- unsigned int cur_pages = 0;
+ long cur_pages = 0;
pmd_t *pmd;
pgprot_t pmd_pgprot;
@@ -991,12 +991,12 @@ static int populate_pmd(struct cpa_data *cpa,
return num_pages;
}
-static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
- pgprot_t pgprot)
+static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
+ pgprot_t pgprot)
{
pud_t *pud;
unsigned long end;
- int cur_pages = 0;
+ long cur_pages = 0;
pgprot_t pud_pgprot;
end = start + (cpa->numpages << PAGE_SHIFT);
@@ -1052,7 +1052,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
/* Map trailing leftover */
if (start < end) {
- int tmp;
+ long tmp;
pud = pud_offset(pgd, start);
if (pud_none(*pud))
@@ -1078,7 +1078,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
pud_t *pud = NULL; /* shut up gcc */
pgd_t *pgd_entry;
- int ret;
+ long ret;
pgd_entry = cpa->pgd + pgd_index(addr);
@@ -1327,7 +1327,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
{
- int ret, numpages = cpa->numpages;
+ unsigned long numpages = cpa->numpages;
+ int ret;
while (numpages) {
/*
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index ecb1b69c1651..170cc4ff057b 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -927,9 +927,10 @@ int track_pfn_copy(struct vm_area_struct *vma)
}
/*
- * prot is passed in as a parameter for the new mapping. If the vma has a
- * linear pfn mapping for the entire range reserve the entire vma range with
- * single reserve_pfn_range call.
+ * prot is passed in as a parameter for the new mapping. If the vma has
+ * a linear pfn mapping for the entire range, or no vma is provided,
+ * reserve the entire pfn + size range with single reserve_pfn_range
+ * call.
*/
int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr, unsigned long size)
@@ -938,11 +939,12 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
enum page_cache_mode pcm;
/* reserve the whole chunk starting from paddr */
- if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) {
+ if (!vma || (addr == vma->vm_start
+ && size == (vma->vm_end - vma->vm_start))) {
int ret;
ret = reserve_pfn_range(paddr, size, prot, 0);
- if (!ret)
+ if (ret == 0 && vma)
vma->vm_flags |= VM_PAT;
return ret;
}
@@ -997,7 +999,7 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
resource_size_t paddr;
unsigned long prot;
- if (!(vma->vm_flags & VM_PAT))
+ if (vma && !(vma->vm_flags & VM_PAT))
return;
/* free the chunk starting from pfn or the whole chunk */
@@ -1011,7 +1013,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
size = vma->vm_end - vma->vm_start;
}
free_pfn_range(paddr, size);
- vma->vm_flags &= ~VM_PAT;
+ if (vma)
+ vma->vm_flags &= ~VM_PAT;
}
/*
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index de391b7bc19a..159b52ccd600 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -254,9 +254,7 @@ struct memtype *rbt_memtype_erase(u64 start, u64 end)
struct memtype *rbt_memtype_lookup(u64 addr)
{
- struct memtype *data;
- data = memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE);
- return data;
+ return memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE);
}
#if defined(CONFIG_DEBUG_FS)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 4dbe65622810..a7655f6caf7d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -77,10 +77,25 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
unsigned cpu = smp_processor_id();
if (likely(prev != next)) {
+ if (IS_ENABLED(CONFIG_VMAP_STACK)) {
+ /*
+ * If our current stack is in vmalloc space and isn't
+ * mapped in the new pgd, we'll double-fault. Forcibly
+ * map it.
+ */
+ unsigned int stack_pgd_index = pgd_index(current_stack_pointer());
+
+ pgd_t *pgd = next->pgd + stack_pgd_index;
+
+ if (unlikely(pgd_none(*pgd)))
+ set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
+ }
+
#ifdef CONFIG_SMP
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
this_cpu_write(cpu_tlbstate.active_mm, next);
#endif
+
cpumask_set_cpu(cpu, mm_cpumask(next));
/*
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index cb31a4440e58..a2488b6e27d6 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -16,27 +16,7 @@
#include <asm/ptrace.h>
#include <asm/stacktrace.h>
-
-static int backtrace_stack(void *data, char *name)
-{
- /* Yes, we want all stacks */
- return 0;
-}
-
-static int backtrace_address(void *data, unsigned long addr, int reliable)
-{
- unsigned int *depth = data;
-
- if ((*depth)--)
- oprofile_add_trace(addr);
- return 0;
-}
-
-static struct stacktrace_ops backtrace_ops = {
- .stack = backtrace_stack,
- .address = backtrace_address,
- .walk_stack = print_context_stack,
-};
+#include <asm/unwind.h>
#ifdef CONFIG_COMPAT
static struct stack_frame_ia32 *
@@ -113,10 +93,29 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
struct stack_frame *head = (struct stack_frame *)frame_pointer(regs);
if (!user_mode(regs)) {
- unsigned long stack = kernel_stack_pointer(regs);
- if (depth)
- dump_trace(NULL, regs, (unsigned long *)stack, 0,
- &backtrace_ops, &depth);
+ struct unwind_state state;
+ unsigned long addr;
+
+ if (!depth)
+ return;
+
+ oprofile_add_trace(regs->ip);
+
+ if (!--depth)
+ return;
+
+ for (unwind_start(&state, current, regs, NULL);
+ !unwind_done(&state); unwind_next_frame(&state)) {
+ addr = unwind_get_return_address(&state);
+ if (!addr)
+ break;
+
+ oprofile_add_trace(addr);
+
+ if (!--depth)
+ break;
+ }
+
return;
}
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 837ea36a837d..6d52b94f4bb9 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -553,15 +553,21 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev)
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
/*
- * Broadwell EP Home Agent BARs erroneously return non-zero values when read.
+ * Device [8086:2fc0]
+ * Erratum HSE43
+ * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html
*
- * See http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
- * entry BDF2.
+ * Devices [8086:6f60,6fa0,6fc0]
+ * Erratum BDF2
+ * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
*/
-static void pci_bdwep_bar(struct pci_dev *dev)
+static void pci_invalid_bar(struct pci_dev *dev)
{
dev->non_compliant_bars = 1;
}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 9770e55e768f..1d97cea3b3a4 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -120,9 +120,12 @@ static unsigned long __init bios32_service(unsigned long service)
static struct {
unsigned long address;
unsigned short segment;
-} pci_indirect = { 0, __KERNEL_CS };
+} pci_indirect __ro_after_init = {
+ .address = 0,
+ .segment = __KERNEL_CS,
+};
-static int pci_bios_present;
+static int pci_bios_present __ro_after_init;
static int __init check_pcibios(void)
{
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index 184842ef332e..3c3c19ea94df 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -8,6 +8,7 @@ obj-y += iris/
obj-y += intel/
obj-y += intel-mid/
obj-y += intel-quark/
+obj-y += mellanox/
obj-y += olpc/
obj-y += scx200/
obj-y += sfi/
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
index 8ff7b9355416..d49d3be81953 100644
--- a/arch/x86/platform/atom/punit_atom_debug.c
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -155,7 +155,7 @@ static void punit_dbgfs_unregister(void)
static const struct x86_cpu_id intel_punit_cpu_ids[] = {
ICPU(INTEL_FAM6_ATOM_SILVERMONT1, punit_device_byt),
- ICPU(INTEL_FAM6_ATOM_MERRIFIELD1, punit_device_tng),
+ ICPU(INTEL_FAM6_ATOM_MERRIFIELD, punit_device_tng),
ICPU(INTEL_FAM6_ATOM_AIRMONT, punit_device_cht),
{}
};
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 6a2f5691b1ab..6aad870e8962 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -82,21 +82,12 @@ void __init efi_bgrt_init(void)
}
bgrt_image_size = bmp_header.size;
- bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN);
+ bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
if (!bgrt_image) {
- pr_notice("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n",
- bgrt_image_size);
- return;
- }
-
- image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
- if (!image) {
pr_notice("Ignoring BGRT: failed to map image memory\n");
- kfree(bgrt_image);
bgrt_image = NULL;
return;
}
- memcpy(bgrt_image, image, bgrt_image_size);
- memunmap(image);
+ efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size);
}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1fbb408e2e72..bf99aa7005eb 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -166,13 +166,15 @@ static void __init do_add_efi_memmap(void)
}
e820_add_region(start, size, e820_type);
}
- sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
}
int __init efi_memblock_x86_reserve_range(void)
{
struct efi_info *e = &boot_params.efi_info;
+ struct efi_memory_map_data data;
phys_addr_t pmap;
+ int rv;
if (efi_enabled(EFI_PARAVIRT))
return 0;
@@ -187,11 +189,17 @@ int __init efi_memblock_x86_reserve_range(void)
#else
pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32));
#endif
- efi.memmap.phys_map = pmap;
- efi.memmap.nr_map = e->efi_memmap_size /
- e->efi_memdesc_size;
- efi.memmap.desc_size = e->efi_memdesc_size;
- efi.memmap.desc_version = e->efi_memdesc_version;
+ data.phys_map = pmap;
+ data.size = e->efi_memmap_size;
+ data.desc_size = e->efi_memdesc_size;
+ data.desc_version = e->efi_memdesc_version;
+
+ rv = efi_memmap_init_early(&data);
+ if (rv)
+ return rv;
+
+ if (add_efi_memmap)
+ do_add_efi_memmap();
WARN(efi.memmap.desc_version != 1,
"Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
@@ -218,19 +226,6 @@ void __init efi_print_memmap(void)
}
}
-void __init efi_unmap_memmap(void)
-{
- unsigned long size;
-
- clear_bit(EFI_MEMMAP, &efi.flags);
-
- size = efi.memmap.nr_map * efi.memmap.desc_size;
- if (efi.memmap.map) {
- early_memunmap(efi.memmap.map, size);
- efi.memmap.map = NULL;
- }
-}
-
static int __init efi_systab_init(void *phys)
{
if (efi_enabled(EFI_64BIT)) {
@@ -414,33 +409,6 @@ static int __init efi_runtime_init(void)
return 0;
}
-static int __init efi_memmap_init(void)
-{
- unsigned long addr, size;
-
- if (efi_enabled(EFI_PARAVIRT))
- return 0;
-
- /* Map the EFI memory map */
- size = efi.memmap.nr_map * efi.memmap.desc_size;
- addr = (unsigned long)efi.memmap.phys_map;
-
- efi.memmap.map = early_memremap(addr, size);
- if (efi.memmap.map == NULL) {
- pr_err("Could not map the memory map!\n");
- return -ENOMEM;
- }
-
- efi.memmap.map_end = efi.memmap.map + size;
-
- if (add_efi_memmap)
- do_add_efi_memmap();
-
- set_bit(EFI_MEMMAP, &efi.flags);
-
- return 0;
-}
-
void __init efi_init(void)
{
efi_char16_t *c16;
@@ -498,16 +466,14 @@ void __init efi_init(void)
if (!efi_runtime_supported())
pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
else {
- if (efi_runtime_disabled() || efi_runtime_init())
+ if (efi_runtime_disabled() || efi_runtime_init()) {
+ efi_memmap_unmap();
return;
+ }
}
- if (efi_memmap_init())
- return;
if (efi_enabled(EFI_DBG))
efi_print_memmap();
-
- efi_esrt_init();
}
void __init efi_late_init(void)
@@ -624,42 +590,6 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md)
}
}
-static void __init save_runtime_map(void)
-{
-#ifdef CONFIG_KEXEC_CORE
- unsigned long desc_size;
- efi_memory_desc_t *md;
- void *tmp, *q = NULL;
- int count = 0;
-
- if (efi_enabled(EFI_OLD_MEMMAP))
- return;
-
- desc_size = efi.memmap.desc_size;
-
- for_each_efi_memory_desc(md) {
- if (!(md->attribute & EFI_MEMORY_RUNTIME) ||
- (md->type == EFI_BOOT_SERVICES_CODE) ||
- (md->type == EFI_BOOT_SERVICES_DATA))
- continue;
- tmp = krealloc(q, (count + 1) * desc_size, GFP_KERNEL);
- if (!tmp)
- goto out;
- q = tmp;
-
- memcpy(q + count * desc_size, md, desc_size);
- count++;
- }
-
- efi_runtime_map_setup(q, count, desc_size);
- return;
-
-out:
- kfree(q);
- pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
-#endif
-}
-
static void *realloc_pages(void *old_memmap, int old_shift)
{
void *ret;
@@ -745,6 +675,46 @@ static void *efi_map_next_entry(void *entry)
return entry;
}
+static bool should_map_region(efi_memory_desc_t *md)
+{
+ /*
+ * Runtime regions always require runtime mappings (obviously).
+ */
+ if (md->attribute & EFI_MEMORY_RUNTIME)
+ return true;
+
+ /*
+ * 32-bit EFI doesn't suffer from the bug that requires us to
+ * reserve boot services regions, and mixed mode support
+ * doesn't exist for 32-bit kernels.
+ */
+ if (IS_ENABLED(CONFIG_X86_32))
+ return false;
+
+ /*
+ * Map all of RAM so that we can access arguments in the 1:1
+ * mapping when making EFI runtime calls.
+ */
+ if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_is_native()) {
+ if (md->type == EFI_CONVENTIONAL_MEMORY ||
+ md->type == EFI_LOADER_DATA ||
+ md->type == EFI_LOADER_CODE)
+ return true;
+ }
+
+ /*
+ * Map boot services regions as a workaround for buggy
+ * firmware that accesses them even when they shouldn't.
+ *
+ * See efi_{reserve,free}_boot_services().
+ */
+ if (md->type == EFI_BOOT_SERVICES_CODE ||
+ md->type == EFI_BOOT_SERVICES_DATA)
+ return true;
+
+ return false;
+}
+
/*
* Map the efi memory ranges of the runtime services and update new_mmap with
* virtual addresses.
@@ -761,13 +731,9 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
p = NULL;
while ((p = efi_map_next_entry(p))) {
md = p;
- if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
-#ifdef CONFIG_X86_64
- if (md->type != EFI_BOOT_SERVICES_CODE &&
- md->type != EFI_BOOT_SERVICES_DATA)
-#endif
- continue;
- }
+
+ if (!should_map_region(md))
+ continue;
efi_map_region(md);
get_systab_virt_addr(md);
@@ -803,7 +769,7 @@ static void __init kexec_enter_virtual_mode(void)
* non-native EFI
*/
if (!efi_is_native()) {
- efi_unmap_memmap();
+ efi_memmap_unmap();
clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return;
}
@@ -823,7 +789,18 @@ static void __init kexec_enter_virtual_mode(void)
get_systab_virt_addr(md);
}
- save_runtime_map();
+ /*
+ * Unregister the early EFI memmap from efi_init() and install
+ * the new EFI memory map.
+ */
+ efi_memmap_unmap();
+
+ if (efi_memmap_init_late(efi.memmap.phys_map,
+ efi.memmap.desc_size * efi.memmap.nr_map)) {
+ pr_err("Failed to remap late EFI memory map\n");
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ return;
+ }
BUG_ON(!efi.systab);
@@ -884,6 +861,7 @@ static void __init __efi_enter_virtual_mode(void)
int count = 0, pg_shift = 0;
void *new_memmap = NULL;
efi_status_t status;
+ phys_addr_t pa;
efi.systab = NULL;
@@ -901,11 +879,24 @@ static void __init __efi_enter_virtual_mode(void)
return;
}
- save_runtime_map();
+ pa = __pa(new_memmap);
+
+ /*
+ * Unregister the early EFI memmap from efi_init() and install
+ * the new EFI memory map that we are about to pass to the
+ * firmware via SetVirtualAddressMap().
+ */
+ efi_memmap_unmap();
+
+ if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) {
+ pr_err("Failed to remap late EFI memory map\n");
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ return;
+ }
BUG_ON(!efi.systab);
- if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift)) {
+ if (efi_setup_page_tables(pa, 1 << pg_shift)) {
clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return;
}
@@ -917,14 +908,14 @@ static void __init __efi_enter_virtual_mode(void)
efi.memmap.desc_size * count,
efi.memmap.desc_size,
efi.memmap.desc_version,
- (efi_memory_desc_t *)__pa(new_memmap));
+ (efi_memory_desc_t *)pa);
} else {
status = efi_thunk_set_virtual_address_map(
efi_phys.set_virtual_address_map,
efi.memmap.desc_size * count,
efi.memmap.desc_size,
efi.memmap.desc_version,
- (efi_memory_desc_t *)__pa(new_memmap));
+ (efi_memory_desc_t *)pa);
}
if (status != EFI_SUCCESS) {
@@ -956,15 +947,6 @@ static void __init __efi_enter_virtual_mode(void)
efi_runtime_update_mappings();
efi_dump_pagetable();
- /*
- * We mapped the descriptor array into the EFI pagetable above
- * but we're not unmapping it here because if we're running in
- * EFI mixed mode we need all of memory to be accessible when
- * we pass parameters to the EFI runtime services in the
- * thunking code.
- */
- free_pages((unsigned long)new_memmap, pg_shift);
-
/* clean DUMMY object */
efi_delete_dummy_variable();
}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 677e29e29473..58b0f801f66f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -85,7 +85,7 @@ pgd_t * __init efi_call_phys_prolog(void)
early_code_mapping_set_exec(1);
n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
- save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
+ save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
for (pgd = 0; pgd < n_pgds; pgd++) {
save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
@@ -214,7 +214,6 @@ void efi_sync_low_kernel_mappings(void)
int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
unsigned long pfn, text;
- efi_memory_desc_t *md;
struct page *page;
unsigned npages;
pgd_t *pgd;
@@ -245,28 +244,9 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
* text and allocate a new stack because we can't rely on the
* stack pointer being < 4GB.
*/
- if (!IS_ENABLED(CONFIG_EFI_MIXED))
+ if (!IS_ENABLED(CONFIG_EFI_MIXED) || efi_is_native())
return 0;
- /*
- * Map all of RAM so that we can access arguments in the 1:1
- * mapping when making EFI runtime calls.
- */
- for_each_efi_memory_desc(md) {
- if (md->type != EFI_CONVENTIONAL_MEMORY &&
- md->type != EFI_LOADER_DATA &&
- md->type != EFI_LOADER_CODE)
- continue;
-
- pfn = md->phys_addr >> PAGE_SHIFT;
- npages = md->num_pages;
-
- if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, npages, _PAGE_RW)) {
- pr_err("Failed to map 1:1 memory\n");
- return 1;
- }
- }
-
page = alloc_page(GFP_KERNEL|__GFP_DMA32);
if (!page)
panic("Unable to allocate EFI runtime stack < 4GB\n");
@@ -359,6 +339,7 @@ void __init efi_map_region(efi_memory_desc_t *md)
*/
void __init efi_map_region_fixed(efi_memory_desc_t *md)
{
+ __map_region(md, md->phys_addr);
__map_region(md, md->virt_addr);
}
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 89d1146f5a6f..10aca63a50d7 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -164,6 +164,75 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size,
EXPORT_SYMBOL_GPL(efi_query_variable_store);
/*
+ * The UEFI specification makes it clear that the operating system is
+ * free to do whatever it wants with boot services code after
+ * ExitBootServices() has been called. Ignoring this recommendation a
+ * significant bunch of EFI implementations continue calling into boot
+ * services code (SetVirtualAddressMap). In order to work around such
+ * buggy implementations we reserve boot services region during EFI
+ * init and make sure it stays executable. Then, after
+ * SetVirtualAddressMap(), it is discarded.
+ *
+ * However, some boot services regions contain data that is required
+ * by drivers, so we need to track which memory ranges can never be
+ * freed. This is done by tagging those regions with the
+ * EFI_MEMORY_RUNTIME attribute.
+ *
+ * Any driver that wants to mark a region as reserved must use
+ * efi_mem_reserve() which will insert a new EFI memory descriptor
+ * into efi.memmap (splitting existing regions if necessary) and tag
+ * it with EFI_MEMORY_RUNTIME.
+ */
+void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
+{
+ phys_addr_t new_phys, new_size;
+ struct efi_mem_range mr;
+ efi_memory_desc_t md;
+ int num_entries;
+ void *new;
+
+ if (efi_mem_desc_lookup(addr, &md)) {
+ pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr);
+ return;
+ }
+
+ if (addr + size > md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT)) {
+ pr_err("Region spans EFI memory descriptors, %pa\n", &addr);
+ return;
+ }
+
+ size += addr % EFI_PAGE_SIZE;
+ size = round_up(size, EFI_PAGE_SIZE);
+ addr = round_down(addr, EFI_PAGE_SIZE);
+
+ mr.range.start = addr;
+ mr.range.end = addr + size - 1;
+ mr.attribute = md.attribute | EFI_MEMORY_RUNTIME;
+
+ num_entries = efi_memmap_split_count(&md, &mr.range);
+ num_entries += efi.memmap.nr_map;
+
+ new_size = efi.memmap.desc_size * num_entries;
+
+ new_phys = memblock_alloc(new_size, 0);
+ if (!new_phys) {
+ pr_err("Could not allocate boot services memmap\n");
+ return;
+ }
+
+ new = early_memremap(new_phys, new_size);
+ if (!new) {
+ pr_err("Failed to map new boot services memmap\n");
+ return;
+ }
+
+ efi_memmap_insert(&efi.memmap, new, &mr);
+ early_memunmap(new, new_size);
+
+ efi_memmap_install(new_phys, num_entries);
+}
+
+/*
* Helper function for efi_reserve_boot_services() to figure out if we
* can free regions in efi_free_boot_services().
*
@@ -184,15 +253,6 @@ static bool can_free_region(u64 start, u64 size)
return true;
}
-/*
- * The UEFI specification makes it clear that the operating system is free to do
- * whatever it wants with boot services code after ExitBootServices() has been
- * called. Ignoring this recommendation a significant bunch of EFI implementations
- * continue calling into boot services code (SetVirtualAddressMap). In order to
- * work around such buggy implementations we reserve boot services region during
- * EFI init and make sure it stays executable. Then, after SetVirtualAddressMap(), it
-* is discarded.
-*/
void __init efi_reserve_boot_services(void)
{
efi_memory_desc_t *md;
@@ -249,7 +309,10 @@ void __init efi_reserve_boot_services(void)
void __init efi_free_boot_services(void)
{
+ phys_addr_t new_phys, new_size;
efi_memory_desc_t *md;
+ int num_entries = 0;
+ void *new, *new_md;
for_each_efi_memory_desc(md) {
unsigned long long start = md->phys_addr;
@@ -257,12 +320,16 @@ void __init efi_free_boot_services(void)
size_t rm_size;
if (md->type != EFI_BOOT_SERVICES_CODE &&
- md->type != EFI_BOOT_SERVICES_DATA)
+ md->type != EFI_BOOT_SERVICES_DATA) {
+ num_entries++;
continue;
+ }
/* Do not free, someone else owns it: */
- if (md->attribute & EFI_MEMORY_RUNTIME)
+ if (md->attribute & EFI_MEMORY_RUNTIME) {
+ num_entries++;
continue;
+ }
/*
* Nasty quirk: if all sub-1MB memory is used for boot
@@ -287,7 +354,41 @@ void __init efi_free_boot_services(void)
free_bootmem_late(start, size);
}
- efi_unmap_memmap();
+ new_size = efi.memmap.desc_size * num_entries;
+ new_phys = memblock_alloc(new_size, 0);
+ if (!new_phys) {
+ pr_err("Failed to allocate new EFI memmap\n");
+ return;
+ }
+
+ new = memremap(new_phys, new_size, MEMREMAP_WB);
+ if (!new) {
+ pr_err("Failed to map new EFI memmap\n");
+ return;
+ }
+
+ /*
+ * Build a new EFI memmap that excludes any boot services
+ * regions that are not tagged EFI_MEMORY_RUNTIME, since those
+ * regions have now been freed.
+ */
+ new_md = new;
+ for_each_efi_memory_desc(md) {
+ if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+ (md->type == EFI_BOOT_SERVICES_CODE ||
+ md->type == EFI_BOOT_SERVICES_DATA))
+ continue;
+
+ memcpy(new_md, md, efi.memmap.desc_size);
+ new_md += efi.memmap.desc_size;
+ }
+
+ memunmap(new);
+
+ if (efi_memmap_install(new_phys, num_entries)) {
+ pr_err("Could not install new EFI memmap\n");
+ return;
+ }
}
/*
@@ -365,7 +466,7 @@ void __init efi_apply_memmap_quirks(void)
*/
if (!efi_runtime_supported()) {
pr_info("Setup done, disabling due to 32/64-bit mismatch\n");
- efi_unmap_memmap();
+ efi_memmap_unmap();
}
/* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index fc135bf70511..429d08be7848 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -1,5 +1,9 @@
# Family-Level Interface Shim (FLIS)
obj-$(subst m,y,$(CONFIG_PINCTRL_MERRIFIELD)) += platform_mrfld_pinctrl.o
+# SDHCI Devices
+obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o
+# WiFi
+obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o
# IPC Devices
obj-y += platform_ipc.o
obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c
new file mode 100644
index 000000000000..4392c15ed9e0
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c
@@ -0,0 +1,95 @@
+/*
+ * platform_bcm43xx.c: bcm43xx platform data initilization file
+ *
+ * (C) Copyright 2016 Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.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; version 2
+ * of the License.
+ */
+
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
+#include <linux/sfi.h>
+
+#include <asm/intel-mid.h>
+
+#define WLAN_SFI_GPIO_IRQ_NAME "WLAN-interrupt"
+#define WLAN_SFI_GPIO_ENABLE_NAME "WLAN-enable"
+
+#define WLAN_DEV_NAME "0000:00:01.3"
+
+static struct regulator_consumer_supply bcm43xx_vmmc_supply = {
+ .dev_name = WLAN_DEV_NAME,
+ .supply = "vmmc",
+};
+
+static struct regulator_init_data bcm43xx_vmmc_data = {
+ .constraints = {
+ .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+ },
+ .num_consumer_supplies = 1,
+ .consumer_supplies = &bcm43xx_vmmc_supply,
+};
+
+static struct fixed_voltage_config bcm43xx_vmmc = {
+ .supply_name = "bcm43xx-vmmc-regulator",
+ /*
+ * Announce 2.0V here to be compatible with SDIO specification. The
+ * real voltage and signaling are still 1.8V.
+ */
+ .microvolts = 2000000, /* 1.8V */
+ .gpio = -EINVAL,
+ .startup_delay = 250 * 1000, /* 250ms */
+ .enable_high = 1, /* active high */
+ .enabled_at_boot = 0, /* disabled at boot */
+ .init_data = &bcm43xx_vmmc_data,
+};
+
+static struct platform_device bcm43xx_vmmc_regulator = {
+ .name = "reg-fixed-voltage",
+ .id = PLATFORM_DEVID_AUTO,
+ .dev = {
+ .platform_data = &bcm43xx_vmmc,
+ },
+};
+
+static int __init bcm43xx_regulator_register(void)
+{
+ int ret;
+
+ bcm43xx_vmmc.gpio = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME);
+ ret = platform_device_register(&bcm43xx_vmmc_regulator);
+ if (ret) {
+ pr_err("%s: vmmc regulator register failed\n", __func__);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void __init *bcm43xx_platform_data(void *info)
+{
+ int ret;
+
+ ret = bcm43xx_regulator_register();
+ if (ret)
+ return NULL;
+
+ pr_info("Using generic wifi platform data\n");
+
+ /* For now it's empty */
+ return NULL;
+}
+
+static const struct devs_id bcm43xx_clk_vmmc_dev_id __initconst = {
+ .name = "bcm43xx_clk_vmmc",
+ .type = SFI_DEV_TYPE_SD,
+ .get_platform_data = &bcm43xx_platform_data,
+};
+
+sfi_device(bcm43xx_clk_vmmc_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c
new file mode 100644
index 000000000000..00c4a034ad93
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c
@@ -0,0 +1,47 @@
+/*
+ * SDHCI platform data initilisation file
+ *
+ * (C) Copyright 2016 Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.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; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/pci.h>
+
+#include <linux/mmc/sdhci-pci-data.h>
+
+#include <asm/intel-mid.h>
+
+#define INTEL_MRFLD_SD 2
+#define INTEL_MRFLD_SD_CD_GPIO 77
+
+static struct sdhci_pci_data mrfld_sdhci_pci_data = {
+ .rst_n_gpio = -EINVAL,
+ .cd_gpio = INTEL_MRFLD_SD_CD_GPIO,
+};
+
+static struct sdhci_pci_data *
+mrfld_sdhci_pci_get_data(struct pci_dev *pdev, int slotno)
+{
+ unsigned int func = PCI_FUNC(pdev->devfn);
+
+ if (func == INTEL_MRFLD_SD)
+ return &mrfld_sdhci_pci_data;
+
+ return NULL;
+}
+
+static int __init mrfld_sd_init(void)
+{
+ if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+ return -ENODEV;
+
+ sdhci_pci_get_data = mrfld_sdhci_pci_get_data;
+ return 0;
+}
+arch_initcall(mrfld_sd_init);
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index ce119d2ba0d0..7850128f0026 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -70,6 +70,11 @@ EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
static void intel_mid_power_off(void)
{
+ /* Shut down South Complex via PWRMU */
+ intel_mid_pwr_power_off();
+
+ /* Only for Tangier, the rest will ignore this command */
+ intel_scu_ipc_simple_command(IPCMSG_COLD_OFF, 1);
};
static void intel_mid_reboot(void)
diff --git a/arch/x86/platform/intel-mid/pwr.c b/arch/x86/platform/intel-mid/pwr.c
index c901a3423772..5d3b45ad1c03 100644
--- a/arch/x86/platform/intel-mid/pwr.c
+++ b/arch/x86/platform/intel-mid/pwr.c
@@ -44,7 +44,19 @@
/* Bits in PM_CMD */
#define PM_CMD_CMD(x) ((x) << 0)
#define PM_CMD_IOC (1 << 8)
-#define PM_CMD_D3cold (1 << 21)
+#define PM_CMD_CM_NOP (0 << 9)
+#define PM_CMD_CM_IMMEDIATE (1 << 9)
+#define PM_CMD_CM_DELAY (2 << 9)
+#define PM_CMD_CM_TRIGGER (3 << 9)
+
+/* System states */
+#define PM_CMD_SYS_STATE_S5 (5 << 16)
+
+/* Trigger variants */
+#define PM_CMD_CFG_TRIGGER_NC (3 << 19)
+
+/* Message to wait for TRIGGER_NC case */
+#define TRIGGER_NC_MSG_2 (2 << 22)
/* List of commands */
#define CMD_SET_CFG 0x01
@@ -137,7 +149,7 @@ static int mid_pwr_wait(struct mid_pwr *pwr)
static int mid_pwr_wait_for_cmd(struct mid_pwr *pwr, u8 cmd)
{
- writel(PM_CMD_CMD(cmd), pwr->regs + PM_CMD);
+ writel(PM_CMD_CMD(cmd) | PM_CMD_CM_IMMEDIATE, pwr->regs + PM_CMD);
return mid_pwr_wait(pwr);
}
@@ -260,6 +272,20 @@ int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state)
}
EXPORT_SYMBOL_GPL(intel_mid_pci_set_power_state);
+void intel_mid_pwr_power_off(void)
+{
+ struct mid_pwr *pwr = midpwr;
+ u32 cmd = PM_CMD_SYS_STATE_S5 |
+ PM_CMD_CMD(CMD_SET_CFG) |
+ PM_CMD_CM_TRIGGER |
+ PM_CMD_CFG_TRIGGER_NC |
+ TRIGGER_NC_MSG_2;
+
+ /* Send command to SCU */
+ writel(cmd, pwr->regs + PM_CMD);
+ mid_pwr_wait(pwr);
+}
+
int intel_mid_pwr_get_lss_id(struct pci_dev *pdev)
{
int vndr;
@@ -354,7 +380,7 @@ static int mid_pwr_probe(struct pci_dev *pdev, const struct pci_device_id *id)
return 0;
}
-static int mid_set_initial_state(struct mid_pwr *pwr)
+static int mid_set_initial_state(struct mid_pwr *pwr, const u32 *states)
{
unsigned int i, j;
int ret;
@@ -379,10 +405,10 @@ static int mid_set_initial_state(struct mid_pwr *pwr)
* NOTE: The actual device mapping is provided by a platform at run
* time using vendor capability of PCI configuration space.
*/
- mid_pwr_set_state(pwr, 0, 0xffffffff);
- mid_pwr_set_state(pwr, 1, 0xffffffff);
- mid_pwr_set_state(pwr, 2, 0xffffffff);
- mid_pwr_set_state(pwr, 3, 0xffffffff);
+ mid_pwr_set_state(pwr, 0, states[0]);
+ mid_pwr_set_state(pwr, 1, states[1]);
+ mid_pwr_set_state(pwr, 2, states[2]);
+ mid_pwr_set_state(pwr, 3, states[3]);
/* Send command to SCU */
ret = mid_pwr_wait_for_cmd(pwr, CMD_SET_CFG);
@@ -397,13 +423,41 @@ static int mid_set_initial_state(struct mid_pwr *pwr)
return 0;
}
-static const struct mid_pwr_device_info mid_info = {
- .set_initial_state = mid_set_initial_state,
+static int pnw_set_initial_state(struct mid_pwr *pwr)
+{
+ /* On Penwell SRAM must stay powered on */
+ const u32 states[] = {
+ 0xf00fffff, /* PM_SSC(0) */
+ 0xffffffff, /* PM_SSC(1) */
+ 0xffffffff, /* PM_SSC(2) */
+ 0xffffffff, /* PM_SSC(3) */
+ };
+ return mid_set_initial_state(pwr, states);
+}
+
+static int tng_set_initial_state(struct mid_pwr *pwr)
+{
+ const u32 states[] = {
+ 0xffffffff, /* PM_SSC(0) */
+ 0xffffffff, /* PM_SSC(1) */
+ 0xffffffff, /* PM_SSC(2) */
+ 0xffffffff, /* PM_SSC(3) */
+ };
+ return mid_set_initial_state(pwr, states);
+}
+
+static const struct mid_pwr_device_info pnw_info = {
+ .set_initial_state = pnw_set_initial_state,
+};
+
+static const struct mid_pwr_device_info tng_info = {
+ .set_initial_state = tng_set_initial_state,
};
+/* This table should be in sync with the one in drivers/pci/pci-mid.c */
static const struct pci_device_id mid_pwr_pci_ids[] = {
- { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_PENWELL), (kernel_ulong_t)&mid_info },
- { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_TANGIER), (kernel_ulong_t)&mid_info },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_PENWELL), (kernel_ulong_t)&pnw_info },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_TANGIER), (kernel_ulong_t)&tng_info },
{}
};
diff --git a/arch/x86/platform/mellanox/Makefile b/arch/x86/platform/mellanox/Makefile
new file mode 100644
index 000000000000..f43c93188a1d
--- /dev/null
+++ b/arch/x86/platform/mellanox/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_MLX_PLATFORM) += mlx-platform.o
diff --git a/arch/x86/platform/mellanox/mlx-platform.c b/arch/x86/platform/mellanox/mlx-platform.c
new file mode 100644
index 000000000000..7dcfcca97399
--- /dev/null
+++ b/arch/x86/platform/mellanox/mlx-platform.c
@@ -0,0 +1,266 @@
+/*
+ * arch/x86/platform/mellanox/mlx-platform.c
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/device.h>
+#include <linux/dmi.h>
+#include <linux/i2c.h>
+#include <linux/i2c-mux.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/i2c-mux-reg.h>
+
+#define MLX_PLAT_DEVICE_NAME "mlxplat"
+
+/* LPC bus IO offsets */
+#define MLXPLAT_CPLD_LPC_I2C_BASE_ADRR 0x2000
+#define MLXPLAT_CPLD_LPC_REG_BASE_ADRR 0x2500
+#define MLXPLAT_CPLD_LPC_IO_RANGE 0x100
+#define MLXPLAT_CPLD_LPC_I2C_CH1_OFF 0xdb
+#define MLXPLAT_CPLD_LPC_I2C_CH2_OFF 0xda
+#define MLXPLAT_CPLD_LPC_PIO_OFFSET 0x10000UL
+#define MLXPLAT_CPLD_LPC_REG1 ((MLXPLAT_CPLD_LPC_REG_BASE_ADRR + \
+ MLXPLAT_CPLD_LPC_I2C_CH1_OFF) | \
+ MLXPLAT_CPLD_LPC_PIO_OFFSET)
+#define MLXPLAT_CPLD_LPC_REG2 ((MLXPLAT_CPLD_LPC_REG_BASE_ADRR + \
+ MLXPLAT_CPLD_LPC_I2C_CH2_OFF) | \
+ MLXPLAT_CPLD_LPC_PIO_OFFSET)
+
+/* Start channel numbers */
+#define MLXPLAT_CPLD_CH1 2
+#define MLXPLAT_CPLD_CH2 10
+
+/* Number of LPC attached MUX platform devices */
+#define MLXPLAT_CPLD_LPC_MUX_DEVS 2
+
+/* mlxplat_priv - platform private data
+ * @pdev_i2c - i2c controller platform device
+ * @pdev_mux - array of mux platform devices
+ */
+struct mlxplat_priv {
+ struct platform_device *pdev_i2c;
+ struct platform_device *pdev_mux[MLXPLAT_CPLD_LPC_MUX_DEVS];
+};
+
+/* Regions for LPC I2C controller and LPC base register space */
+static const struct resource mlxplat_lpc_resources[] = {
+ [0] = DEFINE_RES_NAMED(MLXPLAT_CPLD_LPC_I2C_BASE_ADRR,
+ MLXPLAT_CPLD_LPC_IO_RANGE,
+ "mlxplat_cpld_lpc_i2c_ctrl", IORESOURCE_IO),
+ [1] = DEFINE_RES_NAMED(MLXPLAT_CPLD_LPC_REG_BASE_ADRR,
+ MLXPLAT_CPLD_LPC_IO_RANGE,
+ "mlxplat_cpld_lpc_regs",
+ IORESOURCE_IO),
+};
+
+/* Platform default channels */
+static const int mlxplat_default_channels[][8] = {
+ {
+ MLXPLAT_CPLD_CH1, MLXPLAT_CPLD_CH1 + 1, MLXPLAT_CPLD_CH1 + 2,
+ MLXPLAT_CPLD_CH1 + 3, MLXPLAT_CPLD_CH1 + 4, MLXPLAT_CPLD_CH1 +
+ 5, MLXPLAT_CPLD_CH1 + 6, MLXPLAT_CPLD_CH1 + 7
+ },
+ {
+ MLXPLAT_CPLD_CH2, MLXPLAT_CPLD_CH2 + 1, MLXPLAT_CPLD_CH2 + 2,
+ MLXPLAT_CPLD_CH2 + 3, MLXPLAT_CPLD_CH2 + 4, MLXPLAT_CPLD_CH2 +
+ 5, MLXPLAT_CPLD_CH2 + 6, MLXPLAT_CPLD_CH2 + 7
+ },
+};
+
+/* Platform channels for MSN21xx system family */
+static const int mlxplat_msn21xx_channels[] = { 1, 2, 3, 4, 5, 6, 7, 8 };
+
+/* Platform mux data */
+static struct i2c_mux_reg_platform_data mlxplat_mux_data[] = {
+ {
+ .parent = 1,
+ .base_nr = MLXPLAT_CPLD_CH1,
+ .write_only = 1,
+ .reg = (void __iomem *)MLXPLAT_CPLD_LPC_REG1,
+ .reg_size = 1,
+ .idle_in_use = 1,
+ },
+ {
+ .parent = 1,
+ .base_nr = MLXPLAT_CPLD_CH2,
+ .write_only = 1,
+ .reg = (void __iomem *)MLXPLAT_CPLD_LPC_REG2,
+ .reg_size = 1,
+ .idle_in_use = 1,
+ },
+
+};
+
+static struct platform_device *mlxplat_dev;
+
+static int __init mlxplat_dmi_default_matched(const struct dmi_system_id *dmi)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) {
+ mlxplat_mux_data[i].values = mlxplat_default_channels[i];
+ mlxplat_mux_data[i].n_values =
+ ARRAY_SIZE(mlxplat_default_channels[i]);
+ }
+
+ return 1;
+};
+
+static int __init mlxplat_dmi_msn21xx_matched(const struct dmi_system_id *dmi)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) {
+ mlxplat_mux_data[i].values = mlxplat_msn21xx_channels;
+ mlxplat_mux_data[i].n_values =
+ ARRAY_SIZE(mlxplat_msn21xx_channels);
+ }
+
+ return 1;
+};
+
+static struct dmi_system_id mlxplat_dmi_table[] __initdata = {
+ {
+ .callback = mlxplat_dmi_default_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MSN24"),
+ },
+ },
+ {
+ .callback = mlxplat_dmi_default_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MSN27"),
+ },
+ },
+ {
+ .callback = mlxplat_dmi_default_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MSB"),
+ },
+ },
+ {
+ .callback = mlxplat_dmi_default_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MSX"),
+ },
+ },
+ {
+ .callback = mlxplat_dmi_msn21xx_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MSN21"),
+ },
+ },
+ { }
+};
+
+static int __init mlxplat_init(void)
+{
+ struct mlxplat_priv *priv;
+ int i, err;
+
+ if (!dmi_check_system(mlxplat_dmi_table))
+ return -ENODEV;
+
+ mlxplat_dev = platform_device_register_simple(MLX_PLAT_DEVICE_NAME, -1,
+ mlxplat_lpc_resources,
+ ARRAY_SIZE(mlxplat_lpc_resources));
+
+ if (IS_ERR(mlxplat_dev))
+ return PTR_ERR(mlxplat_dev);
+
+ priv = devm_kzalloc(&mlxplat_dev->dev, sizeof(struct mlxplat_priv),
+ GFP_KERNEL);
+ if (!priv) {
+ err = -ENOMEM;
+ goto fail_alloc;
+ }
+ platform_set_drvdata(mlxplat_dev, priv);
+
+ priv->pdev_i2c = platform_device_register_simple("i2c_mlxcpld", -1,
+ NULL, 0);
+ if (IS_ERR(priv->pdev_i2c)) {
+ err = PTR_ERR(priv->pdev_i2c);
+ goto fail_alloc;
+ };
+
+ for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) {
+ priv->pdev_mux[i] = platform_device_register_resndata(
+ &mlxplat_dev->dev,
+ "i2c-mux-reg", i, NULL,
+ 0, &mlxplat_mux_data[i],
+ sizeof(mlxplat_mux_data[i]));
+ if (IS_ERR(priv->pdev_mux[i])) {
+ err = PTR_ERR(priv->pdev_mux[i]);
+ goto fail_platform_mux_register;
+ }
+ }
+
+ return 0;
+
+fail_platform_mux_register:
+ for (i--; i > 0 ; i--)
+ platform_device_unregister(priv->pdev_mux[i]);
+ platform_device_unregister(priv->pdev_i2c);
+fail_alloc:
+ platform_device_unregister(mlxplat_dev);
+
+ return err;
+}
+module_init(mlxplat_init);
+
+static void __exit mlxplat_exit(void)
+{
+ struct mlxplat_priv *priv = platform_get_drvdata(mlxplat_dev);
+ int i;
+
+ for (i = ARRAY_SIZE(mlxplat_mux_data) - 1; i >= 0 ; i--)
+ platform_device_unregister(priv->pdev_mux[i]);
+
+ platform_device_unregister(priv->pdev_i2c);
+ platform_device_unregister(mlxplat_dev);
+}
+module_exit(mlxplat_exit);
+
+MODULE_AUTHOR("Vadim Pasternak (vadimp@mellanox.com)");
+MODULE_DESCRIPTION("Mellanox platform driver");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_ALIAS("dmi:*:*Mellanox*:MSN24*:");
+MODULE_ALIAS("dmi:*:*Mellanox*:MSN27*:");
+MODULE_ALIAS("dmi:*:*Mellanox*:MSB*:");
+MODULE_ALIAS("dmi:*:*Mellanox*:MSX*:");
+MODULE_ALIAS("dmi:*:*Mellanox*:MSN21*:");
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index 23f2f3e41c7f..b4d5e95fe4df 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -149,11 +149,8 @@ EXPORT_SYMBOL_GPL(uv_bios_change_memprotect);
s64
uv_bios_reserved_page_pa(u64 buf, u64 *cookie, u64 *addr, u64 *len)
{
- s64 ret;
-
- ret = uv_bios_call_irqsave(UV_BIOS_GET_PARTITION_ADDR, (u64)cookie,
- (u64)addr, buf, (u64)len, 0);
- return ret;
+ return uv_bios_call_irqsave(UV_BIOS_GET_PARTITION_ADDR, (u64)cookie,
+ (u64)addr, buf, (u64)len, 0);
}
EXPORT_SYMBOL_GPL(uv_bios_reserved_page_pa);
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index fdb4d42b4ce5..9e42842e924a 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -24,6 +24,29 @@
#include <asm/irq_vectors.h>
#include <asm/timer.h>
+static struct bau_operations ops;
+
+static struct bau_operations uv123_bau_ops = {
+ .bau_gpa_to_offset = uv_gpa_to_offset,
+ .read_l_sw_ack = read_mmr_sw_ack,
+ .read_g_sw_ack = read_gmmr_sw_ack,
+ .write_l_sw_ack = write_mmr_sw_ack,
+ .write_g_sw_ack = write_gmmr_sw_ack,
+ .write_payload_first = write_mmr_payload_first,
+ .write_payload_last = write_mmr_payload_last,
+};
+
+static struct bau_operations uv4_bau_ops = {
+ .bau_gpa_to_offset = uv_gpa_to_soc_phys_ram,
+ .read_l_sw_ack = read_mmr_proc_sw_ack,
+ .read_g_sw_ack = read_gmmr_proc_sw_ack,
+ .write_l_sw_ack = write_mmr_proc_sw_ack,
+ .write_g_sw_ack = write_gmmr_proc_sw_ack,
+ .write_payload_first = write_mmr_proc_payload_first,
+ .write_payload_last = write_mmr_proc_payload_last,
+};
+
+
/* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */
static int timeout_base_ns[] = {
20,
@@ -55,16 +78,16 @@ static int congested_reps = CONGESTED_REPS;
static int disabled_period = DISABLED_PERIOD;
static struct tunables tunables[] = {
- {&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */
- {&plugged_delay, PLUGGED_DELAY},
- {&plugsb4reset, PLUGSB4RESET},
- {&timeoutsb4reset, TIMEOUTSB4RESET},
- {&ipi_reset_limit, IPI_RESET_LIMIT},
- {&complete_threshold, COMPLETE_THRESHOLD},
- {&congested_respns_us, CONGESTED_RESPONSE_US},
- {&congested_reps, CONGESTED_REPS},
- {&disabled_period, DISABLED_PERIOD},
- {&giveup_limit, GIVEUP_LIMIT}
+ {&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */
+ {&plugged_delay, PLUGGED_DELAY},
+ {&plugsb4reset, PLUGSB4RESET},
+ {&timeoutsb4reset, TIMEOUTSB4RESET},
+ {&ipi_reset_limit, IPI_RESET_LIMIT},
+ {&complete_threshold, COMPLETE_THRESHOLD},
+ {&congested_respns_us, CONGESTED_RESPONSE_US},
+ {&congested_reps, CONGESTED_REPS},
+ {&disabled_period, DISABLED_PERIOD},
+ {&giveup_limit, GIVEUP_LIMIT}
};
static struct dentry *tunables_dir;
@@ -216,7 +239,7 @@ static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp,
msg = mdp->msg;
if (!msg->canceled && do_acknowledge) {
dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec;
- write_mmr_sw_ack(dw);
+ ops.write_l_sw_ack(dw);
}
msg->replied_to = 1;
msg->swack_vec = 0;
@@ -252,7 +275,7 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
msg->swack_vec) == 0) &&
(msg2->sending_cpu == msg->sending_cpu) &&
(msg2->msg_type != MSG_NOOP)) {
- mmr = read_mmr_sw_ack();
+ mmr = ops.read_l_sw_ack();
msg_res = msg2->swack_vec;
/*
* This is a message retry; clear the resources held
@@ -270,7 +293,7 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
stat->d_canceled++;
cancel_count++;
mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res;
- write_mmr_sw_ack(mr);
+ ops.write_l_sw_ack(mr);
}
}
}
@@ -403,12 +426,12 @@ static void do_reset(void *ptr)
/*
* only reset the resource if it is still pending
*/
- mmr = read_mmr_sw_ack();
+ mmr = ops.read_l_sw_ack();
msg_res = msg->swack_vec;
mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res;
if (mmr & msg_res) {
stat->d_rcanceled++;
- write_mmr_sw_ack(mr);
+ ops.write_l_sw_ack(mr);
}
}
}
@@ -580,11 +603,7 @@ static int uv1_wait_completion(struct bau_desc *bau_desc,
*/
static unsigned long uv2_3_read_status(unsigned long offset, int rshft, int desc)
{
- unsigned long descriptor_status;
-
- descriptor_status =
- ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK) << 1;
- return descriptor_status;
+ return ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK) << 1;
}
/*
@@ -1202,7 +1221,7 @@ void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
struct bau_pq_entry *msg = mdp->msg;
struct bau_pq_entry *other_msg;
- mmr_image = read_mmr_sw_ack();
+ mmr_image = ops.read_l_sw_ack();
swack_vec = msg->swack_vec;
if ((swack_vec & mmr_image) == 0) {
@@ -1431,7 +1450,7 @@ static int ptc_seq_show(struct seq_file *file, void *data)
/* destination side statistics */
seq_printf(file,
"%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n",
- read_gmmr_sw_ack(uv_cpu_to_pnode(cpu)),
+ ops.read_g_sw_ack(uv_cpu_to_pnode(cpu)),
stat->d_requestee, cycles_2_us(stat->d_time),
stat->d_alltlb, stat->d_onetlb, stat->d_multmsg,
stat->d_nomsg, stat->d_retries, stat->d_canceled,
@@ -1497,16 +1516,16 @@ static ssize_t ptc_proc_write(struct file *file, const char __user *user,
}
if (kstrtol(optstr, 10, &input_arg) < 0) {
- printk(KERN_DEBUG "%s is invalid\n", optstr);
+ pr_debug("%s is invalid\n", optstr);
return -EINVAL;
}
if (input_arg == 0) {
elements = ARRAY_SIZE(stat_description);
- printk(KERN_DEBUG "# cpu: cpu number\n");
- printk(KERN_DEBUG "Sender statistics:\n");
+ pr_debug("# cpu: cpu number\n");
+ pr_debug("Sender statistics:\n");
for (i = 0; i < elements; i++)
- printk(KERN_DEBUG "%s\n", stat_description[i]);
+ pr_debug("%s\n", stat_description[i]);
} else if (input_arg == -1) {
for_each_present_cpu(cpu) {
stat = &per_cpu(ptcstats, cpu);
@@ -1554,7 +1573,7 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr,
break;
}
if (cnt != e) {
- printk(KERN_INFO "bau tunable error: should be %d values\n", e);
+ pr_info("bau tunable error: should be %d values\n", e);
return -EINVAL;
}
@@ -1571,7 +1590,7 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr,
continue;
}
if (val < 1 || val > bcp->cpus_in_uvhub) {
- printk(KERN_DEBUG
+ pr_debug(
"Error: BAU max concurrent %d is invalid\n",
val);
return -EINVAL;
@@ -1619,17 +1638,17 @@ static ssize_t tunables_write(struct file *file, const char __user *user,
for_each_present_cpu(cpu) {
bcp = &per_cpu(bau_control, cpu);
- bcp->max_concurr = max_concurr;
- bcp->max_concurr_const = max_concurr;
- bcp->plugged_delay = plugged_delay;
- bcp->plugsb4reset = plugsb4reset;
- bcp->timeoutsb4reset = timeoutsb4reset;
- bcp->ipi_reset_limit = ipi_reset_limit;
- bcp->complete_threshold = complete_threshold;
- bcp->cong_response_us = congested_respns_us;
- bcp->cong_reps = congested_reps;
- bcp->disabled_period = sec_2_cycles(disabled_period);
- bcp->giveup_limit = giveup_limit;
+ bcp->max_concurr = max_concurr;
+ bcp->max_concurr_const = max_concurr;
+ bcp->plugged_delay = plugged_delay;
+ bcp->plugsb4reset = plugsb4reset;
+ bcp->timeoutsb4reset = timeoutsb4reset;
+ bcp->ipi_reset_limit = ipi_reset_limit;
+ bcp->complete_threshold = complete_threshold;
+ bcp->cong_response_us = congested_respns_us;
+ bcp->cong_reps = congested_reps;
+ bcp->disabled_period = sec_2_cycles(disabled_period);
+ bcp->giveup_limit = giveup_limit;
}
return count;
}
@@ -1676,21 +1695,21 @@ static int __init uv_ptc_init(void)
proc_uv_ptc = proc_create(UV_PTC_BASENAME, 0444, NULL,
&proc_uv_ptc_operations);
if (!proc_uv_ptc) {
- printk(KERN_ERR "unable to create %s proc entry\n",
+ pr_err("unable to create %s proc entry\n",
UV_PTC_BASENAME);
return -EINVAL;
}
tunables_dir = debugfs_create_dir(UV_BAU_TUNABLES_DIR, NULL);
if (!tunables_dir) {
- printk(KERN_ERR "unable to create debugfs directory %s\n",
+ pr_err("unable to create debugfs directory %s\n",
UV_BAU_TUNABLES_DIR);
return -EINVAL;
}
tunables_file = debugfs_create_file(UV_BAU_TUNABLES_FILE, 0600,
tunables_dir, NULL, &tunables_fops);
if (!tunables_file) {
- printk(KERN_ERR "unable to create debugfs file %s\n",
+ pr_err("unable to create debugfs file %s\n",
UV_BAU_TUNABLES_FILE);
return -EINVAL;
}
@@ -1725,7 +1744,7 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
gpa = uv_gpa(bau_desc);
n = uv_gpa_to_gnode(gpa);
- m = uv_gpa_to_offset(gpa);
+ m = ops.bau_gpa_to_offset(gpa);
if (is_uv1_hub())
uv1 = 1;
@@ -1740,7 +1759,7 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
memset(bd2, 0, sizeof(struct bau_desc));
if (uv1) {
uv1_hdr = &bd2->header.uv1_hdr;
- uv1_hdr->swack_flag = 1;
+ uv1_hdr->swack_flag = 1;
/*
* The base_dest_nasid set in the message header
* is the nasid of the first uvhub in the partition.
@@ -1749,10 +1768,10 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
* if nasid striding is being used.
*/
uv1_hdr->base_dest_nasid =
- UV_PNODE_TO_NASID(base_pnode);
- uv1_hdr->dest_subnodeid = UV_LB_SUBNODEID;
- uv1_hdr->command = UV_NET_ENDPOINT_INTD;
- uv1_hdr->int_both = 1;
+ UV_PNODE_TO_NASID(base_pnode);
+ uv1_hdr->dest_subnodeid = UV_LB_SUBNODEID;
+ uv1_hdr->command = UV_NET_ENDPOINT_INTD;
+ uv1_hdr->int_both = 1;
/*
* all others need to be set to zero:
* fairness chaining multilevel count replied_to
@@ -1763,11 +1782,11 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
* uses native mode for selective broadcasts.
*/
uv2_3_hdr = &bd2->header.uv2_3_hdr;
- uv2_3_hdr->swack_flag = 1;
+ uv2_3_hdr->swack_flag = 1;
uv2_3_hdr->base_dest_nasid =
- UV_PNODE_TO_NASID(base_pnode);
- uv2_3_hdr->dest_subnodeid = UV_LB_SUBNODEID;
- uv2_3_hdr->command = UV_NET_ENDPOINT_INTD;
+ UV_PNODE_TO_NASID(base_pnode);
+ uv2_3_hdr->dest_subnodeid = UV_LB_SUBNODEID;
+ uv2_3_hdr->command = UV_NET_ENDPOINT_INTD;
}
}
for_each_present_cpu(cpu) {
@@ -1790,10 +1809,7 @@ static void pq_init(int node, int pnode)
size_t plsize;
char *cp;
void *vp;
- unsigned long pn;
- unsigned long first;
- unsigned long pn_first;
- unsigned long last;
+ unsigned long gnode, first, last, tail;
struct bau_pq_entry *pqp;
struct bau_control *bcp;
@@ -1814,17 +1830,25 @@ static void pq_init(int node, int pnode)
bcp->bau_msg_head = pqp;
bcp->queue_last = pqp + (DEST_Q_SIZE - 1);
}
+
+ first = ops.bau_gpa_to_offset(uv_gpa(pqp));
+ last = ops.bau_gpa_to_offset(uv_gpa(pqp + (DEST_Q_SIZE - 1)));
+
/*
- * need the gnode of where the memory was really allocated
+ * Pre UV4, the gnode is required to locate the payload queue
+ * and the payload queue tail must be maintained by the kernel.
*/
- pn = uv_gpa_to_gnode(uv_gpa(pqp));
- first = uv_physnodeaddr(pqp);
- pn_first = ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | first;
- last = uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1));
- write_mmr_payload_first(pnode, pn_first);
- write_mmr_payload_tail(pnode, first);
- write_mmr_payload_last(pnode, last);
- write_gmmr_sw_ack(pnode, 0xffffUL);
+ bcp = &per_cpu(bau_control, smp_processor_id());
+ if (bcp->uvhub_version <= 3) {
+ tail = first;
+ gnode = uv_gpa_to_gnode(uv_gpa(pqp));
+ first = (gnode << UV_PAYLOADQ_GNODE_SHIFT) | tail;
+ write_mmr_payload_tail(pnode, tail);
+ }
+
+ ops.write_payload_first(pnode, first);
+ ops.write_payload_last(pnode, last);
+ ops.write_g_sw_ack(pnode, 0xffffUL);
/* in effect, all msg_type's are set to MSG_NOOP */
memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
@@ -1914,8 +1938,8 @@ static void __init init_per_cpu_tunables(void)
bcp->complete_threshold = complete_threshold;
bcp->cong_response_us = congested_respns_us;
bcp->cong_reps = congested_reps;
- bcp->disabled_period = sec_2_cycles(disabled_period);
- bcp->giveup_limit = giveup_limit;
+ bcp->disabled_period = sec_2_cycles(disabled_period);
+ bcp->giveup_limit = giveup_limit;
spin_lock_init(&bcp->queue_lock);
spin_lock_init(&bcp->uvhub_lock);
spin_lock_init(&bcp->disable_lock);
@@ -1944,7 +1968,7 @@ static int __init get_cpu_topology(int base_pnode,
pnode = uv_cpu_hub_info(cpu)->pnode;
if ((pnode - base_pnode) >= UV_DISTRIBUTION_SIZE) {
- printk(KERN_EMERG
+ pr_emerg(
"cpu %d pnode %d-%d beyond %d; BAU disabled\n",
cpu, pnode, base_pnode, UV_DISTRIBUTION_SIZE);
return 1;
@@ -1969,7 +1993,7 @@ static int __init get_cpu_topology(int base_pnode,
sdp->cpu_number[sdp->num_cpus] = cpu;
sdp->num_cpus++;
if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) {
- printk(KERN_EMERG "%d cpus per socket invalid\n",
+ pr_emerg("%d cpus per socket invalid\n",
sdp->num_cpus);
return 1;
}
@@ -2035,15 +2059,17 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
bcp->uvhub_version = 2;
else if (is_uv3_hub())
bcp->uvhub_version = 3;
+ else if (is_uv4_hub())
+ bcp->uvhub_version = 4;
else {
- printk(KERN_EMERG "uvhub version not 1, 2 or 3\n");
+ pr_emerg("uvhub version not 1, 2, 3, or 4\n");
return 1;
}
bcp->uvhub_master = *hmasterp;
bcp->uvhub_cpu = uv_cpu_blade_processor_id(cpu);
if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
- printk(KERN_EMERG "%d cpus per uvhub invalid\n",
+ pr_emerg("%d cpus per uvhub invalid\n",
bcp->uvhub_cpu);
return 1;
}
@@ -2098,7 +2124,8 @@ static int __init init_per_cpu(int nuvhubs, int base_part_pnode)
void *vp;
struct uvhub_desc *uvhub_descs;
- timeout_us = calculate_destination_timeout();
+ if (is_uv3_hub() || is_uv2_hub() || is_uv1_hub())
+ timeout_us = calculate_destination_timeout();
vp = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL);
uvhub_descs = (struct uvhub_desc *)vp;
@@ -2138,6 +2165,15 @@ static int __init uv_bau_init(void)
if (!is_uv_system())
return 0;
+ if (is_uv4_hub())
+ ops = uv4_bau_ops;
+ else if (is_uv3_hub())
+ ops = uv123_bau_ops;
+ else if (is_uv2_hub())
+ ops = uv123_bau_ops;
+ else if (is_uv1_hub())
+ ops = uv123_bau_ops;
+
for_each_possible_cpu(cur_cpu) {
mask = &per_cpu(uv_flush_tlb_mask, cur_cpu);
zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu));
@@ -2153,7 +2189,9 @@ static int __init uv_bau_init(void)
uv_base_pnode = uv_blade_to_pnode(uvhub);
}
- enable_timeouts();
+ /* software timeouts are not supported on UV4 */
+ if (is_uv3_hub() || is_uv2_hub() || is_uv1_hub())
+ enable_timeouts();
if (init_per_cpu(nuvhubs, uv_base_pnode)) {
set_bau_off();
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index b12c26e2e309..53cace2ec0e2 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -130,7 +130,7 @@ static void __save_processor_state(struct saved_context *ctxt)
ctxt->cr0 = read_cr0();
ctxt->cr2 = read_cr2();
ctxt->cr3 = read_cr3();
- ctxt->cr4 = __read_cr4_safe();
+ ctxt->cr4 = __read_cr4();
#ifdef CONFIG_X86_64
ctxt->cr8 = read_cr8();
#endif
diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index 1104515d5ad2..1ac76479c266 100644
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -68,6 +68,7 @@ static int inj_##reg##_set(void *data, u64 val) \
MCE_INJECT_SET(status);
MCE_INJECT_SET(misc);
MCE_INJECT_SET(addr);
+MCE_INJECT_SET(synd);
#define MCE_INJECT_GET(reg) \
static int inj_##reg##_get(void *data, u64 *val) \
@@ -81,10 +82,12 @@ static int inj_##reg##_get(void *data, u64 *val) \
MCE_INJECT_GET(status);
MCE_INJECT_GET(misc);
MCE_INJECT_GET(addr);
+MCE_INJECT_GET(synd);
DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n");
DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n");
DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n");
+DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n");
/*
* Caller needs to be make sure this cpu doesn't disappear
@@ -243,27 +246,27 @@ static void toggle_nb_mca_mst_cpu(u16 nid)
static void prepare_msrs(void *info)
{
- struct mce i_mce = *(struct mce *)info;
- u8 b = i_mce.bank;
+ struct mce m = *(struct mce *)info;
+ u8 b = m.bank;
- wrmsrl(MSR_IA32_MCG_STATUS, i_mce.mcgstatus);
+ wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus);
if (boot_cpu_has(X86_FEATURE_SMCA)) {
- if (i_mce.inject_flags == DFR_INT_INJ) {
- wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), i_mce.status);
- wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), i_mce.addr);
+ if (m.inject_flags == DFR_INT_INJ) {
+ wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status);
+ wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr);
} else {
- wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), i_mce.status);
- wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), i_mce.addr);
+ wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status);
+ wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr);
}
- wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), i_mce.misc);
+ wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
+ wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd);
} else {
- wrmsrl(MSR_IA32_MCx_STATUS(b), i_mce.status);
- wrmsrl(MSR_IA32_MCx_ADDR(b), i_mce.addr);
- wrmsrl(MSR_IA32_MCx_MISC(b), i_mce.misc);
+ wrmsrl(MSR_IA32_MCx_STATUS(b), m.status);
+ wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr);
+ wrmsrl(MSR_IA32_MCx_MISC(b), m.misc);
}
-
}
static void do_inject(void)
@@ -275,6 +278,9 @@ static void do_inject(void)
if (i_mce.misc)
i_mce.status |= MCI_STATUS_MISCV;
+ if (i_mce.synd)
+ i_mce.status |= MCI_STATUS_SYNDV;
+
if (inj_type == SW_INJ) {
mce_inject_log(&i_mce);
return;
@@ -301,7 +307,9 @@ static void do_inject(void)
* only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for
* Fam10h and later BKDGs.
*/
- if (static_cpu_has(X86_FEATURE_AMD_DCM) && b == 4) {
+ if (static_cpu_has(X86_FEATURE_AMD_DCM) &&
+ b == 4 &&
+ boot_cpu_data.x86 < 0x17) {
toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu));
cpu = get_nbc_for_node(amd_get_nb_id(cpu));
}
@@ -371,6 +379,9 @@ static const char readme_msg[] =
"\t used for error thresholding purposes and its validity is indicated by\n"
"\t MCi_STATUS[MiscV].\n"
"\n"
+"synd:\t Set MCi_SYND: provide syndrome info about the error. Only valid on\n"
+"\t Scalable MCA systems, and its validity is indicated by MCi_STATUS[SyndV].\n"
+"\n"
"addr:\t Error address value to be written to MCi_ADDR. Log address information\n"
"\t associated with the error.\n"
"\n"
@@ -420,6 +431,7 @@ static struct dfs_node {
{ .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR },
+ { .name = "synd", .fops = &synd_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR },
@@ -428,7 +440,7 @@ static struct dfs_node {
static int __init init_mce_inject(void)
{
- int i;
+ unsigned int i;
u64 cap;
rdmsrl(MSR_IA32_MCG_CAP, cap);
@@ -452,26 +464,22 @@ static int __init init_mce_inject(void)
return 0;
err_dfs_add:
- while (--i >= 0)
+ while (i-- > 0)
debugfs_remove(dfs_fls[i].d);
debugfs_remove(dfs_inj);
dfs_inj = NULL;
- return -ENOMEM;
+ return -ENODEV;
}
static void __exit exit_mce_inject(void)
{
- int i;
- for (i = 0; i < ARRAY_SIZE(dfs_fls); i++)
- debugfs_remove(dfs_fls[i].d);
+ debugfs_remove_recursive(dfs_inj);
+ dfs_inj = NULL;
memset(&dfs_fls, 0, sizeof(dfs_fls));
-
- debugfs_remove(dfs_inj);
- dfs_inj = NULL;
}
module_init(init_mce_inject);
module_exit(exit_mce_inject);
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index ebd4dd6ef73b..5766ead6fdb9 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -84,7 +84,10 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
case EAX:
case EIP:
case UESP:
+ break;
case ORIG_EAX:
+ /* Update the syscall number. */
+ UPT_SYSCALL_NR(&child->thread.regs.regs) = value;
break;
case FS:
if (value && (value & 3) != 3)
@@ -191,7 +194,7 @@ int peek_user(struct task_struct *child, long addr, long data)
static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
{
- int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
+ int err, n, cpu = task_cpu(child);
struct user_i387_struct fpregs;
err = save_i387_registers(userspace_pid[cpu],
@@ -208,7 +211,7 @@ static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *c
static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
{
- int n, cpu = ((struct thread_info *) child->stack)->cpu;
+ int n, cpu = task_cpu(child);
struct user_i387_struct fpregs;
n = copy_from_user(&fpregs, buf, sizeof(fpregs));
@@ -221,7 +224,7 @@ static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *c
static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child)
{
- int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
+ int err, n, cpu = task_cpu(child);
struct user_fxsr_struct fpregs;
err = save_fpx_registers(userspace_pid[cpu], (unsigned long *) &fpregs);
@@ -237,7 +240,7 @@ static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *
static int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child)
{
- int n, cpu = ((struct thread_info *) child->stack)->cpu;
+ int n, cpu = task_cpu(child);
struct user_fxsr_struct fpregs;
n = copy_from_user(&fpregs, buf, sizeof(fpregs));
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index faab418876ce..0b5c184dd5b3 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -78,7 +78,11 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
case RSI:
case RDI:
case RBP:
+ break;
+
case ORIG_RAX:
+ /* Update the syscall number. */
+ UPT_SYSCALL_NR(&child->thread.regs.regs) = value;
break;
case FS:
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b86ebb1a9a7f..f1d2182e071f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1237,7 +1237,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.write_cr0 = xen_write_cr0,
.read_cr4 = native_read_cr4,
- .read_cr4_safe = native_read_cr4_safe,
.write_cr4 = xen_write_cr4,
#ifdef CONFIG_X86_64
@@ -1925,6 +1924,45 @@ static void xen_set_cpu_features(struct cpuinfo_x86 *c)
}
}
+static void xen_pin_vcpu(int cpu)
+{
+ static bool disable_pinning;
+ struct sched_pin_override pin_override;
+ int ret;
+
+ if (disable_pinning)
+ return;
+
+ pin_override.pcpu = cpu;
+ ret = HYPERVISOR_sched_op(SCHEDOP_pin_override, &pin_override);
+
+ /* Ignore errors when removing override. */
+ if (cpu < 0)
+ return;
+
+ switch (ret) {
+ case -ENOSYS:
+ pr_warn("Unable to pin on physical cpu %d. In case of problems consider vcpu pinning.\n",
+ cpu);
+ disable_pinning = true;
+ break;
+ case -EPERM:
+ WARN(1, "Trying to pin vcpu without having privilege to do so\n");
+ disable_pinning = true;
+ break;
+ case -EINVAL:
+ case -EBUSY:
+ pr_warn("Physical cpu %d not available for pinning. Check Xen cpu configuration.\n",
+ cpu);
+ break;
+ case 0:
+ break;
+ default:
+ WARN(1, "rc %d while trying to pin vcpu\n", ret);
+ disable_pinning = true;
+ }
+}
+
const struct hypervisor_x86 x86_hyper_xen = {
.name = "Xen",
.detect = xen_platform,
@@ -1933,6 +1971,7 @@ const struct hypervisor_x86 x86_hyper_xen = {
#endif
.x2apic_available = xen_x2apic_para_available,
.set_cpu_features = xen_set_cpu_features,
+ .pin_vcpu = xen_pin_vcpu,
};
EXPORT_SYMBOL(x86_hyper_xen);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 176425233e4d..f8960fca0827 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -861,7 +861,7 @@ char * __init xen_memory_setup(void)
e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
E820_RESERVED);
- sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
/*
* Check whether the kernel itself conflicts with the target E820 map.
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index f42e78de1e10..3d6e0064cbfc 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -21,8 +21,6 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
static DEFINE_PER_CPU(char *, irq_name);
static bool xen_pvspin = true;
-#ifdef CONFIG_QUEUED_SPINLOCKS
-
#include <asm/qspinlock.h>
static void xen_qlock_kick(int cpu)
@@ -71,207 +69,6 @@ static void xen_qlock_wait(u8 *byte, u8 val)
xen_poll_irq(irq);
}
-#else /* CONFIG_QUEUED_SPINLOCKS */
-
-enum xen_contention_stat {
- TAKEN_SLOW,
- TAKEN_SLOW_PICKUP,
- TAKEN_SLOW_SPURIOUS,
- RELEASED_SLOW,
- RELEASED_SLOW_KICKED,
- NR_CONTENTION_STATS
-};
-
-
-#ifdef CONFIG_XEN_DEBUG_FS
-#define HISTO_BUCKETS 30
-static struct xen_spinlock_stats
-{
- u32 contention_stats[NR_CONTENTION_STATS];
- u32 histo_spin_blocked[HISTO_BUCKETS+1];
- u64 time_blocked;
-} spinlock_stats;
-
-static u8 zero_stats;
-
-static inline void check_zero(void)
-{
- u8 ret;
- u8 old = READ_ONCE(zero_stats);
- if (unlikely(old)) {
- ret = cmpxchg(&zero_stats, old, 0);
- /* This ensures only one fellow resets the stat */
- if (ret == old)
- memset(&spinlock_stats, 0, sizeof(spinlock_stats));
- }
-}
-
-static inline void add_stats(enum xen_contention_stat var, u32 val)
-{
- check_zero();
- spinlock_stats.contention_stats[var] += val;
-}
-
-static inline u64 spin_time_start(void)
-{
- return xen_clocksource_read();
-}
-
-static void __spin_time_accum(u64 delta, u32 *array)
-{
- unsigned index = ilog2(delta);
-
- check_zero();
-
- if (index < HISTO_BUCKETS)
- array[index]++;
- else
- array[HISTO_BUCKETS]++;
-}
-
-static inline void spin_time_accum_blocked(u64 start)
-{
- u32 delta = xen_clocksource_read() - start;
-
- __spin_time_accum(delta, spinlock_stats.histo_spin_blocked);
- spinlock_stats.time_blocked += delta;
-}
-#else /* !CONFIG_XEN_DEBUG_FS */
-static inline void add_stats(enum xen_contention_stat var, u32 val)
-{
-}
-
-static inline u64 spin_time_start(void)
-{
- return 0;
-}
-
-static inline void spin_time_accum_blocked(u64 start)
-{
-}
-#endif /* CONFIG_XEN_DEBUG_FS */
-
-struct xen_lock_waiting {
- struct arch_spinlock *lock;
- __ticket_t want;
-};
-
-static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
-static cpumask_t waiting_cpus;
-
-__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
-{
- int irq = __this_cpu_read(lock_kicker_irq);
- struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
- int cpu = smp_processor_id();
- u64 start;
- __ticket_t head;
- unsigned long flags;
-
- /* If kicker interrupts not initialized yet, just spin */
- if (irq == -1)
- return;
-
- start = spin_time_start();
-
- /*
- * Make sure an interrupt handler can't upset things in a
- * partially setup state.
- */
- local_irq_save(flags);
- /*
- * We don't really care if we're overwriting some other
- * (lock,want) pair, as that would mean that we're currently
- * in an interrupt context, and the outer context had
- * interrupts enabled. That has already kicked the VCPU out
- * of xen_poll_irq(), so it will just return spuriously and
- * retry with newly setup (lock,want).
- *
- * The ordering protocol on this is that the "lock" pointer
- * may only be set non-NULL if the "want" ticket is correct.
- * If we're updating "want", we must first clear "lock".
- */
- w->lock = NULL;
- smp_wmb();
- w->want = want;
- smp_wmb();
- w->lock = lock;
-
- /* This uses set_bit, which atomic and therefore a barrier */
- cpumask_set_cpu(cpu, &waiting_cpus);
- add_stats(TAKEN_SLOW, 1);
-
- /* clear pending */
- xen_clear_irq_pending(irq);
-
- /* Only check lock once pending cleared */
- barrier();
-
- /*
- * Mark entry to slowpath before doing the pickup test to make
- * sure we don't deadlock with an unlocker.
- */
- __ticket_enter_slowpath(lock);
-
- /* make sure enter_slowpath, which is atomic does not cross the read */
- smp_mb__after_atomic();
-
- /*
- * check again make sure it didn't become free while
- * we weren't looking
- */
- head = READ_ONCE(lock->tickets.head);
- if (__tickets_equal(head, want)) {
- add_stats(TAKEN_SLOW_PICKUP, 1);
- goto out;
- }
-
- /* Allow interrupts while blocked */
- local_irq_restore(flags);
-
- /*
- * If an interrupt happens here, it will leave the wakeup irq
- * pending, which will cause xen_poll_irq() to return
- * immediately.
- */
-
- /* Block until irq becomes pending (or perhaps a spurious wakeup) */
- xen_poll_irq(irq);
- add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq));
-
- local_irq_save(flags);
-
- kstat_incr_irq_this_cpu(irq);
-out:
- cpumask_clear_cpu(cpu, &waiting_cpus);
- w->lock = NULL;
-
- local_irq_restore(flags);
-
- spin_time_accum_blocked(start);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning);
-
-static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
-{
- int cpu;
-
- add_stats(RELEASED_SLOW, 1);
-
- for_each_cpu(cpu, &waiting_cpus) {
- const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
-
- /* Make sure we read lock before want */
- if (READ_ONCE(w->lock) == lock &&
- READ_ONCE(w->want) == next) {
- add_stats(RELEASED_SLOW_KICKED, 1);
- xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
- break;
- }
- }
-}
-#endif /* CONFIG_QUEUED_SPINLOCKS */
-
static irqreturn_t dummy_handler(int irq, void *dev_id)
{
BUG();
@@ -334,16 +131,12 @@ void __init xen_init_spinlocks(void)
return;
}
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
-#ifdef CONFIG_QUEUED_SPINLOCKS
+
__pv_init_lock_hash();
pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = xen_qlock_wait;
pv_lock_ops.kick = xen_qlock_kick;
-#else
- pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
- pv_lock_ops.unlock_kick = xen_unlock_kick;
-#endif
}
/*
@@ -372,44 +165,3 @@ static __init int xen_parse_nopvspin(char *arg)
}
early_param("xen_nopvspin", xen_parse_nopvspin);
-#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS)
-
-static struct dentry *d_spin_debug;
-
-static int __init xen_spinlock_debugfs(void)
-{
- struct dentry *d_xen = xen_init_debugfs();
-
- if (d_xen == NULL)
- return -ENOMEM;
-
- if (!xen_pvspin)
- return 0;
-
- d_spin_debug = debugfs_create_dir("spinlocks", d_xen);
-
- debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
-
- debugfs_create_u32("taken_slow", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[TAKEN_SLOW]);
- debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
- debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]);
-
- debugfs_create_u32("released_slow", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[RELEASED_SLOW]);
- debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
-
- debugfs_create_u64("time_blocked", 0444, d_spin_debug,
- &spinlock_stats.time_blocked);
-
- debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
- spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
-
- return 0;
-}
-fs_initcall(xen_spinlock_debugfs);
-
-#endif /* CONFIG_XEN_DEBUG_FS */