summaryrefslogtreecommitdiffstats
path: root/kernel/arch
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/arch')
-rw-r--r--kernel/arch/alpha/include/asm/uaccess.h19
-rw-r--r--kernel/arch/arc/Kconfig2
-rw-r--r--kernel/arch/arc/Makefile16
-rw-r--r--kernel/arch/arc/include/asm/arcregs.h6
-rw-r--r--kernel/arch/arc/include/asm/bitops.h15
-rw-r--r--kernel/arch/arc/include/asm/cacheflush.h6
-rw-r--r--kernel/arch/arc/include/asm/delay.h11
-rw-r--r--kernel/arch/arc/include/asm/entry.h4
-rw-r--r--kernel/arch/arc/include/asm/io.h45
-rw-r--r--kernel/arch/arc/include/asm/irqflags-compact.h2
-rw-r--r--kernel/arch/arc/include/asm/pgtable.h5
-rw-r--r--kernel/arch/arc/include/asm/uaccess.h11
-rw-r--r--kernel/arch/arc/kernel/setup.c4
-rw-r--r--kernel/arch/arc/kernel/signal.c8
-rw-r--r--kernel/arch/arc/kernel/stacktrace.c2
-rw-r--r--kernel/arch/arc/kernel/time.c19
-rw-r--r--kernel/arch/arc/kernel/unaligned.c3
-rw-r--r--kernel/arch/arc/mm/cache.c22
-rw-r--r--kernel/arch/arm/boot/compressed/head.S2
-rw-r--r--kernel/arch/arm/boot/dts/am43x-epos-evm.dts5
-rw-r--r--kernel/arch/arm/boot/dts/armada-375.dtsi2
-rw-r--r--kernel/arch/arm/boot/dts/armada-385-linksys.dtsi12
-rw-r--r--kernel/arch/arm/boot/dts/armada-390.dtsi3
-rw-r--r--kernel/arch/arm/boot/dts/armada-xp-linksys-mamba.dts4
-rw-r--r--kernel/arch/arm/boot/dts/at91-sama5d3_xplained.dts1
-rw-r--r--kernel/arch/arm/boot/dts/at91-sama5d4_xplained.dts1
-rw-r--r--kernel/arch/arm/boot/dts/at91sam9x5.dtsi2
-rw-r--r--kernel/arch/arm/boot/dts/da850-evm.dts1
-rw-r--r--kernel/arch/arm/boot/dts/exynos4210-trats.dts2
-rw-r--r--kernel/arch/arm/boot/dts/imx31.dtsi18
-rw-r--r--kernel/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi4
-rw-r--r--kernel/arch/arm/boot/dts/imx6qdl.dtsi2
-rw-r--r--kernel/arch/arm/boot/dts/kirkwood-ib62x0.dts2
-rw-r--r--kernel/arch/arm/boot/dts/omap3-overo-base.dtsi4
-rw-r--r--kernel/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi2
-rw-r--r--kernel/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi2
-rw-r--r--kernel/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi3
-rw-r--r--kernel/arch/arm/boot/dts/pxa3xx.dtsi2
-rw-r--r--kernel/arch/arm/boot/dts/qcom-apq8064.dtsi76
-rw-r--r--kernel/arch/arm/boot/dts/r8a7794.dtsi2
-rw-r--r--kernel/arch/arm/boot/dts/sama5d2-pinfunc.h4
-rw-r--r--kernel/arch/arm/boot/dts/stih407-family.dtsi10
-rw-r--r--kernel/arch/arm/boot/dts/stih410.dtsi12
-rw-r--r--kernel/arch/arm/boot/dts/sun4i-a10-a1000.dts1
-rw-r--r--kernel/arch/arm/boot/dts/sun4i-a10-hackberry.dts1
-rw-r--r--kernel/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts1
-rw-r--r--kernel/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts1
-rw-r--r--kernel/arch/arm/boot/dts/sun5i-a13.dtsi2
-rw-r--r--kernel/arch/arm/boot/dts/sun5i-r8-chip.dts2
-rw-r--r--kernel/arch/arm/common/sa1111.c22
-rw-r--r--kernel/arch/arm/crypto/aes-ce-glue.c7
-rw-r--r--kernel/arch/arm/crypto/ghash-ce-glue.c24
-rw-r--r--kernel/arch/arm/include/asm/cputype.h3
-rw-r--r--kernel/arch/arm/include/asm/dma-mapping.h2
-rw-r--r--kernel/arch/arm/include/asm/floppy.h2
-rw-r--r--kernel/arch/arm/include/asm/pgtable-2level.h1
-rw-r--r--kernel/arch/arm/include/asm/pgtable-3level.h5
-rw-r--r--kernel/arch/arm/include/asm/pgtable.h1
-rw-r--r--kernel/arch/arm/kernel/devtree.c14
-rw-r--r--kernel/arch/arm/kernel/entry-armv.S6
-rw-r--r--kernel/arch/arm/kernel/hw_breakpoint.c16
-rw-r--r--kernel/arch/arm/kernel/patch.c6
-rw-r--r--kernel/arch/arm/kernel/ptrace.c4
-rw-r--r--kernel/arch/arm/kernel/smp_tlb.c7
-rw-r--r--kernel/arch/arm/kernel/sys_oabi-compat.c8
-rw-r--r--kernel/arch/arm/kvm/arm.c2
-rw-r--r--kernel/arch/arm/kvm/mmu.c18
-rw-r--r--kernel/arch/arm/mach-cns3xxx/pcie.c6
-rw-r--r--kernel/arch/arm/mach-davinci/da850.c12
-rw-r--r--kernel/arch/arm/mach-exynos/Kconfig1
-rw-r--r--kernel/arch/arm/mach-exynos/pm_domains.c2
-rw-r--r--kernel/arch/arm/mach-imx/mach-imx6ul.c2
-rw-r--r--kernel/arch/arm/mach-imx/pm-imx6.c4
-rw-r--r--kernel/arch/arm/mach-mvebu/coherency.c22
-rw-r--r--kernel/arch/arm/mach-omap2/cpuidle34xx.c69
-rw-r--r--kernel/arch/arm/mach-omap2/io.c1
-rw-r--r--kernel/arch/arm/mach-omap2/omap-mpuss-lowpower.c5
-rw-r--r--kernel/arch/arm/mach-omap2/omap_hwmod.c8
-rw-r--r--kernel/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c1
-rw-r--r--kernel/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c12
-rw-r--r--kernel/arch/arm/mach-omap2/prcm43xx.h1
-rw-r--r--kernel/arch/arm/mach-prima2/Kconfig1
-rw-r--r--kernel/arch/arm/mach-pxa/idp.c3
-rw-r--r--kernel/arch/arm/mach-pxa/pxa_cplds_irqs.c24
-rw-r--r--kernel/arch/arm/mach-pxa/xcep.c3
-rw-r--r--kernel/arch/arm/mach-realview/core.c3
-rw-r--r--kernel/arch/arm/mach-s3c64xx/dev-audio.c41
-rw-r--r--kernel/arch/arm/mach-s3c64xx/include/mach/dma.h52
-rw-r--r--kernel/arch/arm/mach-sa1100/clock.c5
-rw-r--r--kernel/arch/arm/mach-sa1100/generic.c4
-rw-r--r--kernel/arch/arm/mach-sa1100/generic.h2
-rw-r--r--kernel/arch/arm/mach-sa1100/pleb.c2
-rw-r--r--kernel/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c62
-rw-r--r--kernel/arch/arm/mach-socfpga/headsmp.S1
-rw-r--r--kernel/arch/arm/mach-ux500/pm.c4
-rw-r--r--kernel/arch/arm/mach-zynq/common.c2
-rw-r--r--kernel/arch/arm/mm/fault.c4
-rw-r--r--kernel/arch/arm/mm/fault.h4
-rw-r--r--kernel/arch/arm/plat-samsung/devs.c11
-rw-r--r--kernel/arch/arm/xen/enlighten.c3
-rw-r--r--kernel/arch/arm64/Kconfig20
-rw-r--r--kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi4
-rw-r--r--kernel/arch/arm64/crypto/aes-ce-ccm-core.S53
-rw-r--r--kernel/arch/arm64/crypto/aes-ce-cipher.c25
-rw-r--r--kernel/arch/arm64/crypto/aes-ce.S1
-rw-r--r--kernel/arch/arm64/crypto/aes-glue.c2
-rw-r--r--kernel/arch/arm64/crypto/aes-modes.S91
-rw-r--r--kernel/arch/arm64/crypto/aes-neon.S25
-rw-r--r--kernel/arch/arm64/crypto/ghash-ce-core.S6
-rw-r--r--kernel/arch/arm64/crypto/sha1-ce-core.S4
-rw-r--r--kernel/arch/arm64/crypto/sha2-ce-core.S4
-rw-r--r--kernel/arch/arm64/include/asm/arch_gicv3.h1
-rw-r--r--kernel/arch/arm64/include/asm/cpufeature.h5
-rw-r--r--kernel/arch/arm64/include/asm/elf.h5
-rw-r--r--kernel/arch/arm64/include/asm/futex.h2
-rw-r--r--kernel/arch/arm64/include/asm/kvm_arm.h2
-rw-r--r--kernel/arch/arm64/include/asm/opcodes.h4
-rw-r--r--kernel/arch/arm64/include/asm/percpu.h120
-rw-r--r--kernel/arch/arm64/include/asm/pgtable-hwdef.h1
-rw-r--r--kernel/arch/arm64/include/asm/pgtable.h47
-rw-r--r--kernel/arch/arm64/include/asm/processor.h2
-rw-r--r--kernel/arch/arm64/include/asm/ptrace.h35
-rw-r--r--kernel/arch/arm64/include/asm/spinlock.h10
-rw-r--r--kernel/arch/arm64/include/uapi/asm/auxvec.h2
-rw-r--r--kernel/arch/arm64/include/uapi/asm/ptrace.h1
-rw-r--r--kernel/arch/arm64/kernel/asm-offsets.c1
-rw-r--r--kernel/arch/arm64/kernel/cpu_errata.c9
-rw-r--r--kernel/arch/arm64/kernel/cpufeature.c10
-rw-r--r--kernel/arch/arm64/kernel/cpuinfo.c11
-rw-r--r--kernel/arch/arm64/kernel/debug-monitors.c7
-rw-r--r--kernel/arch/arm64/kernel/entry.S17
-rw-r--r--kernel/arch/arm64/kernel/head.S3
-rw-r--r--kernel/arch/arm64/kernel/ptrace.c97
-rw-r--r--kernel/arch/arm64/kernel/signal.c4
-rw-r--r--kernel/arch/arm64/kernel/signal32.c2
-rw-r--r--kernel/arch/arm64/kernel/smp.c3
-rw-r--r--kernel/arch/arm64/kernel/suspend.c9
-rw-r--r--kernel/arch/arm64/kernel/traps.c28
-rw-r--r--kernel/arch/arm64/kvm/hyp-init.S13
-rw-r--r--kernel/arch/arm64/kvm/inject_fault.c2
-rw-r--r--kernel/arch/arm64/mm/fault.c62
-rw-r--r--kernel/arch/arm64/mm/mmu.c8
-rw-r--r--kernel/arch/arm64/mm/proc.S14
-rw-r--r--kernel/arch/avr32/include/asm/uaccess.h11
-rw-r--r--kernel/arch/avr32/kernel/avr32_ksyms.c2
-rw-r--r--kernel/arch/avr32/lib/copy_user.S8
-rw-r--r--kernel/arch/avr32/mach-at32ap/pio.c2
-rw-r--r--kernel/arch/blackfin/include/asm/uaccess.h9
-rw-r--r--kernel/arch/blackfin/mach-bf561/boards/cm_bf561.c3
-rw-r--r--kernel/arch/blackfin/mach-bf561/boards/ezkit.c3
-rw-r--r--kernel/arch/cris/boot/rescue/Makefile8
-rw-r--r--kernel/arch/cris/include/asm/uaccess.h71
-rw-r--r--kernel/arch/frv/include/asm/uaccess.h12
-rw-r--r--kernel/arch/h8300/include/asm/thread_info.h4
-rw-r--r--kernel/arch/h8300/kernel/signal.c2
-rw-r--r--kernel/arch/hexagon/include/asm/uaccess.h3
-rw-r--r--kernel/arch/ia64/include/asm/io.h1
-rw-r--r--kernel/arch/ia64/include/asm/uaccess.h20
-rw-r--r--kernel/arch/m32r/include/asm/uaccess.h2
-rw-r--r--kernel/arch/m68k/include/asm/delay.h2
-rw-r--r--kernel/arch/metag/include/asm/atomic.h3
-rw-r--r--kernel/arch/metag/include/asm/atomic_lnkget.h2
-rw-r--r--kernel/arch/metag/include/asm/cmpxchg_lnkget.h2
-rw-r--r--kernel/arch/metag/include/asm/uaccess.h3
-rw-r--r--kernel/arch/microblaze/include/asm/uaccess.h11
-rw-r--r--kernel/arch/mips/Kconfig.debug36
-rw-r--r--kernel/arch/mips/Makefile4
-rw-r--r--kernel/arch/mips/alchemy/devboards/db1000.c18
-rw-r--r--kernel/arch/mips/alchemy/devboards/db1550.c4
-rw-r--r--kernel/arch/mips/ath79/early_printk.c6
-rw-r--r--kernel/arch/mips/include/asm/asmmacro.h41
-rw-r--r--kernel/arch/mips/include/asm/cacheflush.h6
-rw-r--r--kernel/arch/mips/include/asm/kvm_host.h10
-rw-r--r--kernel/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h2
-rw-r--r--kernel/arch/mips/include/asm/msa.h13
-rw-r--r--kernel/arch/mips/include/asm/pgtable.h26
-rw-r--r--kernel/arch/mips/include/asm/processor.h2
-rw-r--r--kernel/arch/mips/include/asm/ptrace.h2
-rw-r--r--kernel/arch/mips/include/asm/switch_to.h2
-rw-r--r--kernel/arch/mips/include/asm/uaccess.h3
-rw-r--r--kernel/arch/mips/include/asm/uprobes.h1
-rw-r--r--kernel/arch/mips/include/asm/watch.h10
-rw-r--r--kernel/arch/mips/include/uapi/asm/siginfo.h22
-rw-r--r--kernel/arch/mips/kernel/csrc-r4k.c4
-rw-r--r--kernel/arch/mips/kernel/mips-r2-to-r6-emul.c107
-rw-r--r--kernel/arch/mips/kernel/pm.c2
-rw-r--r--kernel/arch/mips/kernel/process.c14
-rw-r--r--kernel/arch/mips/kernel/ptrace.c27
-rw-r--r--kernel/arch/mips/kernel/r4k_fpu.S10
-rw-r--r--kernel/arch/mips/kernel/scall64-n32.S2
-rw-r--r--kernel/arch/mips/kernel/scall64-o32.S2
-rw-r--r--kernel/arch/mips/kernel/setup.c3
-rw-r--r--kernel/arch/mips/kernel/signal.c15
-rw-r--r--kernel/arch/mips/kernel/smp.c7
-rw-r--r--kernel/arch/mips/kernel/traps.c8
-rw-r--r--kernel/arch/mips/kernel/unaligned.c51
-rw-r--r--kernel/arch/mips/kernel/uprobes.c25
-rw-r--r--kernel/arch/mips/kernel/vdso.c8
-rw-r--r--kernel/arch/mips/kernel/watch.c5
-rw-r--r--kernel/arch/mips/kvm/emulate.c224
-rw-r--r--kernel/arch/mips/kvm/interrupt.h1
-rw-r--r--kernel/arch/mips/kvm/locore.S1
-rw-r--r--kernel/arch/mips/kvm/mips.c15
-rw-r--r--kernel/arch/mips/kvm/tlb.c70
-rw-r--r--kernel/arch/mips/kvm/trap_emul.c2
-rw-r--r--kernel/arch/mips/lib/ashldi3.c2
-rw-r--r--kernel/arch/mips/lib/ashrdi3.c2
-rw-r--r--kernel/arch/mips/lib/bswapdi.c2
-rw-r--r--kernel/arch/mips/lib/bswapsi.c2
-rw-r--r--kernel/arch/mips/lib/cmpdi2.c2
-rw-r--r--kernel/arch/mips/lib/lshrdi3.c2
-rw-r--r--kernel/arch/mips/lib/ucmpdi2.c2
-rw-r--r--kernel/arch/mips/loongson64/loongson-3/hpet.c14
-rw-r--r--kernel/arch/mips/loongson64/loongson-3/numa.c6
-rw-r--r--kernel/arch/mips/math-emu/cp1emu.c8
-rw-r--r--kernel/arch/mips/mm/cache.c41
-rw-r--r--kernel/arch/mips/mm/uasm-mips.c2
-rw-r--r--kernel/arch/mips/mti-malta/malta-setup.c8
-rw-r--r--kernel/arch/mips/vdso/Makefile6
-rw-r--r--kernel/arch/mn10300/include/asm/uaccess.h1
-rw-r--r--kernel/arch/mn10300/lib/usercopy.c4
-rw-r--r--kernel/arch/nios2/include/asm/uaccess.h13
-rw-r--r--kernel/arch/openrisc/include/asm/uaccess.h35
-rw-r--r--kernel/arch/parisc/include/asm/bitops.h8
-rw-r--r--kernel/arch/parisc/include/asm/pgtable.h14
-rw-r--r--kernel/arch/parisc/include/asm/uaccess.h7
-rw-r--r--kernel/arch/parisc/include/uapi/asm/bitsperlong.h2
-rw-r--r--kernel/arch/parisc/include/uapi/asm/errno.h4
-rw-r--r--kernel/arch/parisc/include/uapi/asm/swab.h5
-rw-r--r--kernel/arch/parisc/kernel/asm-offsets.c1
-rw-r--r--kernel/arch/parisc/kernel/cache.c40
-rw-r--r--kernel/arch/parisc/kernel/pacache.S49
-rw-r--r--kernel/arch/parisc/kernel/parisc_ksyms.c10
-rw-r--r--kernel/arch/parisc/kernel/pci-dma.c2
-rw-r--r--kernel/arch/parisc/kernel/setup.c12
-rw-r--r--kernel/arch/parisc/kernel/syscall.S11
-rw-r--r--kernel/arch/parisc/kernel/traps.c3
-rw-r--r--kernel/arch/parisc/kernel/unaligned.c10
-rw-r--r--kernel/arch/parisc/kernel/vmlinux.lds.S7
-rw-r--r--kernel/arch/parisc/lib/fixup.S6
-rw-r--r--kernel/arch/parisc/mm/fault.c1
-rw-r--r--kernel/arch/powerpc/boot/ps3-head.S5
-rw-r--r--kernel/arch/powerpc/boot/ps3.c8
-rw-r--r--kernel/arch/powerpc/include/asm/icswx.h1
-rw-r--r--kernel/arch/powerpc/include/asm/kvm_host.h1
-rw-r--r--kernel/arch/powerpc/include/asm/reg.h7
-rw-r--r--kernel/arch/powerpc/include/asm/uaccess.h21
-rw-r--r--kernel/arch/powerpc/include/asm/word-at-a-time.h2
-rw-r--r--kernel/arch/powerpc/include/uapi/asm/cputable.h1
-rw-r--r--kernel/arch/powerpc/include/uapi/asm/kvm.h1
-rw-r--r--kernel/arch/powerpc/kernel/asm-offsets.c1
-rw-r--r--kernel/arch/powerpc/kernel/eeh.c4
-rw-r--r--kernel/arch/powerpc/kernel/eeh_driver.c40
-rw-r--r--kernel/arch/powerpc/kernel/entry_64.S12
-rw-r--r--kernel/arch/powerpc/kernel/exceptions-64s.S16
-rw-r--r--kernel/arch/powerpc/kernel/ibmebus.c16
-rw-r--r--kernel/arch/powerpc/kernel/idle_power7.S2
-rw-r--r--kernel/arch/powerpc/kernel/misc_32.S2
-rw-r--r--kernel/arch/powerpc/kernel/nvram_64.c6
-rw-r--r--kernel/arch/powerpc/kernel/process.c28
-rw-r--r--kernel/arch/powerpc/kernel/prom.c26
-rw-r--r--kernel/arch/powerpc/kernel/prom_init.c15
-rw-r--r--kernel/arch/powerpc/kernel/ptrace.c4
-rw-r--r--kernel/arch/powerpc/kernel/tm.S61
-rw-r--r--kernel/arch/powerpc/kernel/vdso64/datapage.S2
-rw-r--r--kernel/arch/powerpc/kernel/vdso64/gettimeofday.S2
-rw-r--r--kernel/arch/powerpc/kvm/book3s_emulate.c2
-rw-r--r--kernel/arch/powerpc/kvm/book3s_hv.c6
-rw-r--r--kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c2
-rw-r--r--kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S466
-rw-r--r--kernel/arch/powerpc/kvm/booke.c2
-rw-r--r--kernel/arch/powerpc/lib/copyuser_64.S2
-rw-r--r--kernel/arch/powerpc/mm/copro_fault.c2
-rw-r--r--kernel/arch/powerpc/mm/hugetlbpage.c4
-rw-r--r--kernel/arch/powerpc/mm/slb_low.S7
-rw-r--r--kernel/arch/powerpc/platforms/powernv/eeh-powernv.c9
-rw-r--r--kernel/arch/powerpc/platforms/powernv/opal-dump.c7
-rw-r--r--kernel/arch/powerpc/platforms/powernv/opal-elog.c7
-rw-r--r--kernel/arch/powerpc/platforms/powernv/pci.c4
-rw-r--r--kernel/arch/powerpc/platforms/pseries/eeh_pseries.c51
-rw-r--r--kernel/arch/powerpc/platforms/pseries/iommu.c24
-rw-r--r--kernel/arch/powerpc/platforms/pseries/lpar.c4
-rw-r--r--kernel/arch/s390/crypto/prng.c8
-rw-r--r--kernel/arch/s390/hypfs/hypfs_diag.c6
-rw-r--r--kernel/arch/s390/include/asm/fpu/api.h2
-rw-r--r--kernel/arch/s390/include/asm/mmu.h2
-rw-r--r--kernel/arch/s390/include/asm/mmu_context.h28
-rw-r--r--kernel/arch/s390/include/asm/pci.h3
-rw-r--r--kernel/arch/s390/include/asm/pci_dma.h2
-rw-r--r--kernel/arch/s390/include/asm/pgalloc.h4
-rw-r--r--kernel/arch/s390/include/asm/processor.h2
-rw-r--r--kernel/arch/s390/include/asm/tlbflush.h12
-rw-r--r--kernel/arch/s390/include/asm/uaccess.h8
-rw-r--r--kernel/arch/s390/kernel/entry.S106
-rw-r--r--kernel/arch/s390/kernel/head64.S2
-rw-r--r--kernel/arch/s390/kernel/ipl.c7
-rw-r--r--kernel/arch/s390/kernel/ptrace.c8
-rw-r--r--kernel/arch/s390/kernel/setup.c1
-rw-r--r--kernel/arch/s390/mm/init.c3
-rw-r--r--kernel/arch/s390/mm/mmap.c6
-rw-r--r--kernel/arch/s390/mm/pgtable.c89
-rw-r--r--kernel/arch/s390/net/bpf_jit.h4
-rw-r--r--kernel/arch/s390/net/bpf_jit_comp.c4
-rw-r--r--kernel/arch/s390/pci/pci.c8
-rw-r--r--kernel/arch/s390/pci/pci_dma.c19
-rw-r--r--kernel/arch/score/include/asm/uaccess.h46
-rw-r--r--kernel/arch/sh/include/asm/uaccess.h5
-rw-r--r--kernel/arch/sh/include/asm/uaccess_64.h1
-rw-r--r--kernel/arch/sh/mm/kmap.c2
-rw-r--r--kernel/arch/sparc/include/asm/head_64.h4
-rw-r--r--kernel/arch/sparc/include/asm/mmu_64.h3
-rw-r--r--kernel/arch/sparc/include/asm/pgtable_64.h43
-rw-r--r--kernel/arch/sparc/include/asm/tlbflush_64.h3
-rw-r--r--kernel/arch/sparc/include/asm/ttable.h8
-rw-r--r--kernel/arch/sparc/include/asm/uaccess_32.h4
-rw-r--r--kernel/arch/sparc/include/asm/uaccess_64.h66
-rw-r--r--kernel/arch/sparc/kernel/Makefile1
-rw-r--r--kernel/arch/sparc/kernel/cherrs.S14
-rw-r--r--kernel/arch/sparc/kernel/dtlb_prot.S4
-rw-r--r--kernel/arch/sparc/kernel/entry.S17
-rw-r--r--kernel/arch/sparc/kernel/fpu_traps.S11
-rw-r--r--kernel/arch/sparc/kernel/head_64.S60
-rw-r--r--kernel/arch/sparc/kernel/jump_label.c23
-rw-r--r--kernel/arch/sparc/kernel/ktlb.S12
-rw-r--r--kernel/arch/sparc/kernel/misctrap.S12
-rw-r--r--kernel/arch/sparc/kernel/pci.c17
-rw-r--r--kernel/arch/sparc/kernel/rtrap_64.S57
-rw-r--r--kernel/arch/sparc/kernel/signal32.c46
-rw-r--r--kernel/arch/sparc/kernel/signal_32.c41
-rw-r--r--kernel/arch/sparc/kernel/signal_64.c33
-rw-r--r--kernel/arch/sparc/kernel/sigutil_32.c9
-rw-r--r--kernel/arch/sparc/kernel/sigutil_64.c10
-rw-r--r--kernel/arch/sparc/kernel/sparc_ksyms_64.c1
-rw-r--r--kernel/arch/sparc/kernel/spiterrs.S18
-rw-r--r--kernel/arch/sparc/kernel/syscalls.S36
-rw-r--r--kernel/arch/sparc/kernel/tsb.S12
-rw-r--r--kernel/arch/sparc/kernel/urtt_fill.S98
-rw-r--r--kernel/arch/sparc/kernel/utrap.S3
-rw-r--r--kernel/arch/sparc/kernel/vmlinux.lds.S4
-rw-r--r--kernel/arch/sparc/kernel/winfixup.S3
-rw-r--r--kernel/arch/sparc/lib/GENcopy_from_user.S4
-rw-r--r--kernel/arch/sparc/lib/GENcopy_to_user.S4
-rw-r--r--kernel/arch/sparc/lib/GENmemcpy.S48
-rw-r--r--kernel/arch/sparc/lib/Makefile2
-rw-r--r--kernel/arch/sparc/lib/NG2copy_from_user.S8
-rw-r--r--kernel/arch/sparc/lib/NG2copy_to_user.S8
-rw-r--r--kernel/arch/sparc/lib/NG2memcpy.S228
-rw-r--r--kernel/arch/sparc/lib/NG4copy_from_user.S8
-rw-r--r--kernel/arch/sparc/lib/NG4copy_to_user.S8
-rw-r--r--kernel/arch/sparc/lib/NG4memcpy.S294
-rw-r--r--kernel/arch/sparc/lib/NGcopy_from_user.S4
-rw-r--r--kernel/arch/sparc/lib/NGcopy_to_user.S4
-rw-r--r--kernel/arch/sparc/lib/NGmemcpy.S233
-rw-r--r--kernel/arch/sparc/lib/U1copy_from_user.S8
-rw-r--r--kernel/arch/sparc/lib/U1copy_to_user.S8
-rw-r--r--kernel/arch/sparc/lib/U1memcpy.S345
-rw-r--r--kernel/arch/sparc/lib/U3copy_from_user.S8
-rw-r--r--kernel/arch/sparc/lib/U3copy_to_user.S8
-rw-r--r--kernel/arch/sparc/lib/U3memcpy.S227
-rw-r--r--kernel/arch/sparc/lib/copy_in_user.S35
-rw-r--r--kernel/arch/sparc/lib/user_fixup.c71
-rw-r--r--kernel/arch/sparc/mm/fault_64.c6
-rw-r--r--kernel/arch/sparc/mm/hugetlbpage.c37
-rw-r--r--kernel/arch/sparc/mm/init_64.c111
-rw-r--r--kernel/arch/sparc/mm/tlb.c29
-rw-r--r--kernel/arch/sparc/mm/tsb.c63
-rw-r--r--kernel/arch/sparc/mm/ultra.S374
-rw-r--r--kernel/arch/tile/include/asm/elf.h1
-rw-r--r--kernel/arch/tile/include/uapi/asm/auxvec.h2
-rw-r--r--kernel/arch/tile/kernel/ptrace.c2
-rw-r--r--kernel/arch/tile/kernel/time.c4
-rw-r--r--kernel/arch/um/drivers/mconsole_kern.c2
-rw-r--r--kernel/arch/um/include/asm/common.lds.S2
-rw-r--r--kernel/arch/x86/Kconfig27
-rw-r--r--kernel/arch/x86/boot/Makefile3
-rw-r--r--kernel/arch/x86/boot/compressed/Makefile14
-rw-r--r--kernel/arch/x86/boot/compressed/head_32.S28
-rw-r--r--kernel/arch/x86/boot/compressed/head_64.S8
-rw-r--r--kernel/arch/x86/configs/tiny.config2
-rw-r--r--kernel/arch/x86/crypto/sha-mb/sha1_mb.c4
-rw-r--r--kernel/arch/x86/entry/common.c23
-rw-r--r--kernel/arch/x86/entry/entry_32.S4
-rw-r--r--kernel/arch/x86/entry/syscalls/syscall_32.tbl2
-rw-r--r--kernel/arch/x86/include/asm/apic.h2
-rw-r--r--kernel/arch/x86/include/asm/hugetlb.h1
-rw-r--r--kernel/arch/x86/include/asm/hw_irq.h1
-rw-r--r--kernel/arch/x86/include/asm/kvm_host.h2
-rw-r--r--kernel/arch/x86/include/asm/microcode.h26
-rw-r--r--kernel/arch/x86/include/asm/mtrr.h6
-rw-r--r--kernel/arch/x86/include/asm/pat.h2
-rw-r--r--kernel/arch/x86/include/asm/pci_x86.h2
-rw-r--r--kernel/arch/x86/include/asm/perf_event.h1
-rw-r--r--kernel/arch/x86/include/asm/preempt.h17
-rw-r--r--kernel/arch/x86/include/asm/pvclock.h2
-rw-r--r--kernel/arch/x86/include/asm/tlbflush.h9
-rw-r--r--kernel/arch/x86/include/asm/uaccess.h10
-rw-r--r--kernel/arch/x86/include/asm/xen/hypervisor.h2
-rw-r--r--kernel/arch/x86/kernel/acpi/boot.c2
-rw-r--r--kernel/arch/x86/kernel/amd_nb.c4
-rw-r--r--kernel/arch/x86/kernel/apic/apic.c3
-rw-r--r--kernel/arch/x86/kernel/apic/io_apic.c2
-rw-r--r--kernel/arch/x86/kernel/apic/vector.c114
-rw-r--r--kernel/arch/x86/kernel/cpu/amd.c18
-rw-r--r--kernel/arch/x86/kernel/cpu/common.c25
-rw-r--r--kernel/arch/x86/kernel/cpu/mcheck/mce-genpool.c4
-rw-r--r--kernel/arch/x86/kernel/cpu/mcheck/mce.c2
-rw-r--r--kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c3
-rw-r--r--kernel/arch/x86/kernel/cpu/microcode/intel.c38
-rw-r--r--kernel/arch/x86/kernel/cpu/mshyperv.c12
-rw-r--r--kernel/arch/x86/kernel/cpu/mtrr/generic.c24
-rw-r--r--kernel/arch/x86/kernel/cpu/mtrr/main.c13
-rw-r--r--kernel/arch/x86/kernel/cpu/mtrr/mtrr.h1
-rw-r--r--kernel/arch/x86/kernel/cpu/perf_event.c15
-rw-r--r--kernel/arch/x86/kernel/cpu/perf_event.h3
-rw-r--r--kernel/arch/x86/kernel/cpu/perf_event_intel.c31
-rw-r--r--kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c56
-rw-r--r--kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c33
-rw-r--r--kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c2
-rw-r--r--kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c20
-rw-r--r--kernel/arch/x86/kernel/cpu/perf_event_knc.c4
-rw-r--r--kernel/arch/x86/kernel/e820.c12
-rw-r--r--kernel/arch/x86/kernel/early-quirks.c116
-rw-r--r--kernel/arch/x86/kernel/head_32.S2
-rw-r--r--kernel/arch/x86/kernel/hpet.c1
-rw-r--r--kernel/arch/x86/kernel/ioport.c12
-rw-r--r--kernel/arch/x86/kernel/kprobes/core.c12
-rw-r--r--kernel/arch/x86/kernel/mcount_64.S3
-rw-r--r--kernel/arch/x86/kernel/nmi.c16
-rw-r--r--kernel/arch/x86/kernel/paravirt.c4
-rw-r--r--kernel/arch/x86/kernel/process_64.c12
-rw-r--r--kernel/arch/x86/kernel/ptrace.c4
-rw-r--r--kernel/arch/x86/kernel/pvclock.c4
-rw-r--r--kernel/arch/x86/kernel/reboot.c20
-rw-r--r--kernel/arch/x86/kernel/sysfb_efi.c14
-rw-r--r--kernel/arch/x86/kernel/traps.c20
-rw-r--r--kernel/arch/x86/kernel/tsc_msr.c2
-rw-r--r--kernel/arch/x86/kernel/uprobes.c22
-rw-r--r--kernel/arch/x86/kvm/cpuid.c1
-rw-r--r--kernel/arch/x86/kvm/emulate.c287
-rw-r--r--kernel/arch/x86/kvm/i8254.c12
-rw-r--r--kernel/arch/x86/kvm/ioapic.c2
-rw-r--r--kernel/arch/x86/kvm/irq_comm.c13
-rw-r--r--kernel/arch/x86/kvm/lapic.c6
-rw-r--r--kernel/arch/x86/kvm/lapic.h1
-rw-r--r--kernel/arch/x86/kvm/mtrr.c3
-rw-r--r--kernel/arch/x86/kvm/vmx.c85
-rw-r--r--kernel/arch/x86/kvm/x86.c66
-rw-r--r--kernel/arch/x86/mm/kmmio.c88
-rw-r--r--kernel/arch/x86/mm/mmap.c14
-rw-r--r--kernel/arch/x86/mm/pat.c109
-rw-r--r--kernel/arch/x86/mm/tlb.c12
-rw-r--r--kernel/arch/x86/pci/acpi.c10
-rw-r--r--kernel/arch/x86/pci/common.c26
-rw-r--r--kernel/arch/x86/pci/fixup.c7
-rw-r--r--kernel/arch/x86/pci/intel_mid_pci.c21
-rw-r--r--kernel/arch/x86/pci/irq.c23
-rw-r--r--kernel/arch/x86/pci/xen.c7
-rw-r--r--kernel/arch/x86/purgatory/Makefile1
-rw-r--r--kernel/arch/x86/xen/enlighten.c11
-rw-r--r--kernel/arch/x86/xen/mmu.c2
-rw-r--r--kernel/arch/x86/xen/setup.c65
-rw-r--r--kernel/arch/xtensa/kernel/head.S2
-rw-r--r--kernel/arch/xtensa/mm/cache.c8
-rw-r--r--kernel/arch/xtensa/platforms/iss/console.c10
464 files changed, 5713 insertions, 3244 deletions
diff --git a/kernel/arch/alpha/include/asm/uaccess.h b/kernel/arch/alpha/include/asm/uaccess.h
index 9b0d40093..c0ddbbf73 100644
--- a/kernel/arch/alpha/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/arc/Kconfig b/kernel/arch/arc/Kconfig
index 6312f6079..2d785f5a3 100644
--- a/kernel/arch/arc/Kconfig
+++ b/kernel/arch/arc/Kconfig
@@ -387,7 +387,7 @@ config ARC_HAS_LLSC
config ARC_STAR_9000923308
bool "Workaround for llock/scond livelock"
- default y
+ default n
depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
config ARC_HAS_SWAPE
diff --git a/kernel/arch/arc/Makefile b/kernel/arch/arc/Makefile
index aeb190210..c05ea2b54 100644
--- a/kernel/arch/arc/Makefile
+++ b/kernel/arch/arc/Makefile
@@ -18,6 +18,20 @@ cflags-y += -fno-common -pipe -fno-builtin -D__linux__
cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7
cflags-$(CONFIG_ISA_ARCV2) += -mcpu=archs
+is_700 = $(shell $(CC) -dM -E - < /dev/null | grep -q "ARC700" && echo 1 || echo 0)
+
+ifdef CONFIG_ISA_ARCOMPACT
+ifeq ($(is_700), 0)
+ $(error Toolchain not configured for ARCompact builds)
+endif
+endif
+
+ifdef CONFIG_ISA_ARCV2
+ifeq ($(is_700), 1)
+ $(error Toolchain not configured for ARCv2 builds)
+endif
+endif
+
ifdef CONFIG_ARC_CURR_IN_REG
# For a global register defintion, make sure it gets passed to every file
# We had a customer reported bug where some code built in kernel was NOT using
@@ -48,8 +62,6 @@ endif
endif
-cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables
-
# By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok
ifeq ($(atleast_gcc48),y)
cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2
diff --git a/kernel/arch/arc/include/asm/arcregs.h b/kernel/arch/arc/include/asm/arcregs.h
index 7fac7d85e..2c30a016c 100644
--- a/kernel/arch/arc/include/asm/arcregs.h
+++ b/kernel/arch/arc/include/asm/arcregs.h
@@ -374,12 +374,6 @@ static inline int is_isa_arcompact(void)
return IS_ENABLED(CONFIG_ISA_ARCOMPACT);
}
-#if defined(CONFIG_ISA_ARCOMPACT) && !defined(_CPU_DEFAULT_A7)
-#error "Toolchain not configured for ARCompact builds"
-#elif defined(CONFIG_ISA_ARCV2) && !defined(_CPU_DEFAULT_HS)
-#error "Toolchain not configured for ARCv2 builds"
-#endif
-
#endif /* __ASEMBLY__ */
#endif /* _ASM_ARC_ARCREGS_H */
diff --git a/kernel/arch/arc/include/asm/bitops.h b/kernel/arch/arc/include/asm/bitops.h
index 57c1f3384..0352fb8d2 100644
--- a/kernel/arch/arc/include/asm/bitops.h
+++ b/kernel/arch/arc/include/asm/bitops.h
@@ -35,21 +35,6 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
\
m += nr >> 5; \
\
- /* \
- * ARC ISA micro-optimization: \
- * \
- * Instructions dealing with bitpos only consider lower 5 bits \
- * e.g (x << 33) is handled like (x << 1) by ASL instruction \
- * (mem pointer still needs adjustment to point to next word) \
- * \
- * Hence the masking to clamp @nr arg can be elided in general. \
- * \
- * However if @nr is a constant (above assumed in a register), \
- * and greater than 31, gcc can optimize away (x << 33) to 0, \
- * as overflow, given the 32-bit ISA. Thus masking needs to be \
- * done for const @nr, but no code is generated due to gcc \
- * const prop. \
- */ \
nr &= 0x1f; \
\
__asm__ __volatile__( \
diff --git a/kernel/arch/arc/include/asm/cacheflush.h b/kernel/arch/arc/include/asm/cacheflush.h
index fbe3587c4..56aeb5efe 100644
--- a/kernel/arch/arc/include/asm/cacheflush.h
+++ b/kernel/arch/arc/include/asm/cacheflush.h
@@ -85,6 +85,10 @@ void flush_anon_page(struct vm_area_struct *vma,
*/
#define PG_dc_clean PG_arch_1
+#define CACHE_COLORS_NUM 4
+#define CACHE_COLORS_MSK (CACHE_COLORS_NUM - 1)
+#define CACHE_COLOR(addr) (((unsigned long)(addr) >> (PAGE_SHIFT)) & CACHE_COLORS_MSK)
+
/*
* Simple wrapper over config option
* Bootup code ensures that hardware matches kernel configuration
@@ -94,8 +98,6 @@ static inline int cache_is_vipt_aliasing(void)
return IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
}
-#define CACHE_COLOR(addr) (((unsigned long)(addr) >> (PAGE_SHIFT)) & 1)
-
/*
* checks if two addresses (after page aligning) index into same cache set
*/
diff --git a/kernel/arch/arc/include/asm/delay.h b/kernel/arch/arc/include/asm/delay.h
index 08e7e2a16..d5da2115d 100644
--- a/kernel/arch/arc/include/asm/delay.h
+++ b/kernel/arch/arc/include/asm/delay.h
@@ -22,10 +22,13 @@
static inline void __delay(unsigned long loops)
{
__asm__ __volatile__(
- " lp 1f \n"
- " nop \n"
- "1: \n"
- : "+l"(loops));
+ " mov lp_count, %0 \n"
+ " lp 1f \n"
+ " nop \n"
+ "1: \n"
+ :
+ : "r"(loops)
+ : "lp_count");
}
extern void __bad_udelay(void);
diff --git a/kernel/arch/arc/include/asm/entry.h b/kernel/arch/arc/include/asm/entry.h
index ad7860c5c..51597f344 100644
--- a/kernel/arch/arc/include/asm/entry.h
+++ b/kernel/arch/arc/include/asm/entry.h
@@ -142,7 +142,7 @@
#ifdef CONFIG_ARC_CURR_IN_REG
; Retrieve orig r25 and save it with rest of callee_regs
- ld.as r12, [r12, PT_user_r25]
+ ld r12, [r12, PT_user_r25]
PUSH r12
#else
PUSH r25
@@ -198,7 +198,7 @@
; SP is back to start of pt_regs
#ifdef CONFIG_ARC_CURR_IN_REG
- st.as r12, [sp, PT_user_r25]
+ st r12, [sp, PT_user_r25]
#endif
.endm
diff --git a/kernel/arch/arc/include/asm/io.h b/kernel/arch/arc/include/asm/io.h
index 694ece8a0..cb69299a4 100644
--- a/kernel/arch/arc/include/asm/io.h
+++ b/kernel/arch/arc/include/asm/io.h
@@ -13,6 +13,15 @@
#include <asm/byteorder.h>
#include <asm/page.h>
+#ifdef CONFIG_ISA_ARCV2
+#include <asm/barrier.h>
+#define __iormb() rmb()
+#define __iowmb() wmb()
+#else
+#define __iormb() do { } while (0)
+#define __iowmb() do { } while (0)
+#endif
+
extern void __iomem *ioremap(unsigned long physaddr, unsigned long size);
extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
unsigned long flags);
@@ -22,6 +31,15 @@ extern void iounmap(const void __iomem *addr);
#define ioremap_wc(phy, sz) ioremap(phy, sz)
#define ioremap_wt(phy, sz) ioremap(phy, sz)
+/*
+ * io{read,write}{16,32}be() macros
+ */
+#define ioread16be(p) ({ u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32be(p) ({ u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+
+#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force u16)cpu_to_be16(v), p); })
+#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force u32)cpu_to_be32(v), p); })
+
/* Change struct page to physical address */
#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)
@@ -99,15 +117,6 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
}
-#ifdef CONFIG_ISA_ARCV2
-#include <asm/barrier.h>
-#define __iormb() rmb()
-#define __iowmb() wmb()
-#else
-#define __iormb() do { } while (0)
-#define __iowmb() do { } while (0)
-#endif
-
/*
* MMIO can also get buffered/optimized in micro-arch, so barriers needed
* Based on ARM model for the typical use case
@@ -129,15 +138,23 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
#define writel(v,c) ({ __iowmb(); writel_relaxed(v,c); })
/*
- * Relaxed API for drivers which can handle any ordering themselves
+ * Relaxed API for drivers which can handle barrier ordering themselves
+ *
+ * Also these are defined to perform little endian accesses.
+ * To provide the typical device register semantics of fixed endian,
+ * swap the byte order for Big Endian
+ *
+ * http://lkml.kernel.org/r/201603100845.30602.arnd@arndb.de
*/
#define readb_relaxed(c) __raw_readb(c)
-#define readw_relaxed(c) __raw_readw(c)
-#define readl_relaxed(c) __raw_readl(c)
+#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \
+ __raw_readw(c)); __r; })
+#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \
+ __raw_readl(c)); __r; })
#define writeb_relaxed(v,c) __raw_writeb(v,c)
-#define writew_relaxed(v,c) __raw_writew(v,c)
-#define writel_relaxed(v,c) __raw_writel(v,c)
+#define writew_relaxed(v,c) __raw_writew((__force u16) cpu_to_le16(v),c)
+#define writel_relaxed(v,c) __raw_writel((__force u32) cpu_to_le32(v),c)
#include <asm-generic/io.h>
diff --git a/kernel/arch/arc/include/asm/irqflags-compact.h b/kernel/arch/arc/include/asm/irqflags-compact.h
index c1d36458b..4c6eed80c 100644
--- a/kernel/arch/arc/include/asm/irqflags-compact.h
+++ b/kernel/arch/arc/include/asm/irqflags-compact.h
@@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void)
.endm
.macro IRQ_ENABLE scratch
+ TRACE_ASM_IRQ_ENABLE
lr \scratch, [status32]
or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
flag \scratch
- TRACE_ASM_IRQ_ENABLE
.endm
#endif /* __ASSEMBLY__ */
diff --git a/kernel/arch/arc/include/asm/pgtable.h b/kernel/arch/arc/include/asm/pgtable.h
index 57af2f05a..e5fec320f 100644
--- a/kernel/arch/arc/include/asm/pgtable.h
+++ b/kernel/arch/arc/include/asm/pgtable.h
@@ -110,7 +110,7 @@
#define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE)
/* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL)
/* More Abbrevaited helpers */
#define PAGE_U_NONE __pgprot(___DEF)
@@ -277,8 +277,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot)
#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT)
-#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | \
- pgprot_val(prot)))
+#define pfn_pte(pfn, prot) (__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
#define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
/*
diff --git a/kernel/arch/arc/include/asm/uaccess.h b/kernel/arch/arc/include/asm/uaccess.h
index d1da6032b..d4d8df706 100644
--- a/kernel/arch/arc/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/arc/kernel/setup.c b/kernel/arch/arc/kernel/setup.c
index e1b87444e..05131805a 100644
--- a/kernel/arch/arc/kernel/setup.c
+++ b/kernel/arch/arc/kernel/setup.c
@@ -332,10 +332,6 @@ static void arc_chk_core_config(void)
pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
else if (!cpu->extn.fpu_dp && fpu_enabled)
panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
-
- if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
- !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
- panic("llock/scond livelock workaround missing\n");
}
/*
diff --git a/kernel/arch/arc/kernel/signal.c b/kernel/arch/arc/kernel/signal.c
index 004b7f0bc..257b8699e 100644
--- a/kernel/arch/arc/kernel/signal.c
+++ b/kernel/arch/arc/kernel/signal.c
@@ -107,13 +107,13 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
struct user_regs_struct uregs;
err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
- if (!err)
- set_current_blocked(&set);
-
err |= __copy_from_user(&uregs.scratch,
&(sf->uc.uc_mcontext.regs.scratch),
sizeof(sf->uc.uc_mcontext.regs.scratch));
+ if (err)
+ return err;
+ set_current_blocked(&set);
regs->bta = uregs.scratch.bta;
regs->lp_start = uregs.scratch.lp_start;
regs->lp_end = uregs.scratch.lp_end;
@@ -138,7 +138,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
regs->r0 = uregs.scratch.r0;
regs->sp = uregs.scratch.sp;
- return err;
+ return 0;
}
static inline int is_do_ss_needed(unsigned int magic)
diff --git a/kernel/arch/arc/kernel/stacktrace.c b/kernel/arch/arc/kernel/stacktrace.c
index 001de4ce7..11b50959f 100644
--- a/kernel/arch/arc/kernel/stacktrace.c
+++ b/kernel/arch/arc/kernel/stacktrace.c
@@ -142,7 +142,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
* prelogue is setup (callee regs saved and then fp set and not other
* way around
*/
- pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
+ pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
return 0;
#endif
diff --git a/kernel/arch/arc/kernel/time.c b/kernel/arch/arc/kernel/time.c
index dfad287f1..dbedc576e 100644
--- a/kernel/arch/arc/kernel/time.c
+++ b/kernel/arch/arc/kernel/time.c
@@ -130,14 +130,17 @@ static cycle_t arc_counter_read(struct clocksource *cs)
cycle_t full;
} stamp;
-
- __asm__ __volatile(
- "1: \n"
- " lr %0, [AUX_RTC_LOW] \n"
- " lr %1, [AUX_RTC_HIGH] \n"
- " lr %2, [AUX_RTC_CTRL] \n"
- " bbit0.nt %2, 31, 1b \n"
- : "=r" (stamp.low), "=r" (stamp.high), "=r" (status));
+ /*
+ * hardware has an internal state machine which tracks readout of
+ * low/high and updates the CTRL.status if
+ * - interrupt/exception taken between the two reads
+ * - high increments after low has been read
+ */
+ do {
+ stamp.low = read_aux_reg(AUX_RTC_LOW);
+ stamp.high = read_aux_reg(AUX_RTC_HIGH);
+ status = read_aux_reg(AUX_RTC_CTRL);
+ } while (!(status & _BITUL(31)));
return stamp.full;
}
diff --git a/kernel/arch/arc/kernel/unaligned.c b/kernel/arch/arc/kernel/unaligned.c
index abd961f3e..5f69c3bd5 100644
--- a/kernel/arch/arc/kernel/unaligned.c
+++ b/kernel/arch/arc/kernel/unaligned.c
@@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
if (state.fault)
goto fault;
+ /* clear any remanants of delay slot */
if (delay_mode(regs)) {
- regs->ret = regs->bta;
+ regs->ret = regs->bta & ~1U;
regs->status32 &= ~STATUS_DE_MASK;
} else {
regs->ret += state.instr_len;
diff --git a/kernel/arch/arc/mm/cache.c b/kernel/arch/arc/mm/cache.c
index ff7ff6cbb..d81b6d7e1 100644
--- a/kernel/arch/arc/mm/cache.c
+++ b/kernel/arch/arc/mm/cache.c
@@ -914,6 +914,15 @@ void arc_cache_init(void)
printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
+ /*
+ * Only master CPU needs to execute rest of function:
+ * - Assume SMP so all cores will have same cache config so
+ * any geomtry checks will be same for all
+ * - IOC setup / dma callbacks only need to be setup once
+ */
+ if (cpu)
+ return;
+
if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
@@ -951,11 +960,16 @@ void arc_cache_init(void)
/* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */
if (is_isa_arcompact()) {
int handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
-
- if (dc->alias && !handled)
- panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
- else if (!dc->alias && handled)
+ int num_colors = dc->sz_k/dc->assoc/TO_KB(PAGE_SIZE);
+
+ if (dc->alias) {
+ if (!handled)
+ panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+ if (CACHE_COLORS_NUM != num_colors)
+ panic("CACHE_COLORS_NUM not optimized for config\n");
+ } else if (!dc->alias && handled) {
panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+ }
}
}
diff --git a/kernel/arch/arm/boot/compressed/head.S b/kernel/arch/arm/boot/compressed/head.S
index 06e983f59..856913705 100644
--- a/kernel/arch/arm/boot/compressed/head.S
+++ b/kernel/arch/arm/boot/compressed/head.S
@@ -776,7 +776,7 @@ __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/kernel/arch/arm/boot/dts/am43x-epos-evm.dts b/kernel/arch/arm/boot/dts/am43x-epos-evm.dts
index 47954ed99..00707aac7 100644
--- a/kernel/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/kernel/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -792,3 +792,8 @@
tx-num-evt = <32>;
rx-num-evt = <32>;
};
+
+&synctimer_32kclk {
+ assigned-clocks = <&mux_synctimer32k_ck>;
+ assigned-clock-parents = <&clkdiv32k_ick>;
+};
diff --git a/kernel/arch/arm/boot/dts/armada-375.dtsi b/kernel/arch/arm/boot/dts/armada-375.dtsi
index 7ccce7529..cc952cf8e 100644
--- a/kernel/arch/arm/boot/dts/armada-375.dtsi
+++ b/kernel/arch/arm/boot/dts/armada-375.dtsi
@@ -529,7 +529,7 @@
};
sata@a0000 {
- compatible = "marvell,orion-sata";
+ compatible = "marvell,armada-370-sata";
reg = <0xa0000 0x5000>;
interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&gateclk 14>, <&gateclk 20>;
diff --git a/kernel/arch/arm/boot/dts/armada-385-linksys.dtsi b/kernel/arch/arm/boot/dts/armada-385-linksys.dtsi
index 3710755c6..22f7a13e2 100644
--- a/kernel/arch/arm/boot/dts/armada-385-linksys.dtsi
+++ b/kernel/arch/arm/boot/dts/armada-385-linksys.dtsi
@@ -58,8 +58,8 @@
soc {
ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000
MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000
- MBUS_ID(0x09, 0x09) 0 0xf1100000 0x10000
- MBUS_ID(0x09, 0x05) 0 0xf1110000 0x10000>;
+ MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000
+ MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>;
internal-regs {
@@ -117,7 +117,7 @@
};
/* USB part of the eSATA/USB 2.0 port */
- usb@50000 {
+ usb@58000 {
status = "okay";
};
@@ -245,7 +245,7 @@
button@2 {
label = "Factory Reset Button";
linux,code = <KEY_RESTART>;
- gpios = <&gpio1 15 GPIO_ACTIVE_LOW>;
+ gpios = <&gpio0 29 GPIO_ACTIVE_LOW>;
};
};
@@ -260,7 +260,7 @@
};
sata {
- gpios = <&gpio1 22 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpio1 22 GPIO_ACTIVE_LOW>;
default-state = "off";
};
};
@@ -313,7 +313,7 @@
&pinctrl {
keys_pin: keys-pin {
- marvell,pins = "mpp24", "mpp47";
+ marvell,pins = "mpp24", "mpp29";
marvell,function = "gpio";
};
diff --git a/kernel/arch/arm/boot/dts/armada-390.dtsi b/kernel/arch/arm/boot/dts/armada-390.dtsi
index 094e39c66..6cd18d8aa 100644
--- a/kernel/arch/arm/boot/dts/armada-390.dtsi
+++ b/kernel/arch/arm/boot/dts/armada-390.dtsi
@@ -47,6 +47,8 @@
#include "armada-39x.dtsi"
/ {
+ compatible = "marvell,armada390";
+
soc {
internal-regs {
pinctrl@18000 {
@@ -54,4 +56,5 @@
reg = <0x18000 0x20>;
};
};
+ };
};
diff --git a/kernel/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/kernel/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
index b89e6cf12..7a461541c 100644
--- a/kernel/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
+++ b/kernel/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
@@ -304,13 +304,13 @@
button@1 {
label = "WPS";
linux,code = <KEY_WPS_BUTTON>;
- gpios = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
};
button@2 {
label = "Factory Reset Button";
linux,code = <KEY_RESTART>;
- gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
};
};
diff --git a/kernel/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/kernel/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index ff888d21c..f3e2b96c0 100644
--- a/kernel/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/kernel/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -303,6 +303,7 @@
regulator-name = "mmc0-card-supply";
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
+ regulator-always-on;
};
gpio_keys {
diff --git a/kernel/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/kernel/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 569026e8f..da84e65b5 100644
--- a/kernel/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/kernel/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -268,5 +268,6 @@
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
vin-supply = <&vcc_3v3_reg>;
+ regulator-always-on;
};
};
diff --git a/kernel/arch/arm/boot/dts/at91sam9x5.dtsi b/kernel/arch/arm/boot/dts/at91sam9x5.dtsi
index 0827d594b..cd0cd5fd0 100644
--- a/kernel/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/kernel/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -106,7 +106,7 @@
pmc: pmc@fffffc00 {
compatible = "atmel,at91sam9x5-pmc", "syscon";
- reg = <0xfffffc00 0x100>;
+ reg = <0xfffffc00 0x200>;
interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
interrupt-controller;
#address-cells = <1>;
diff --git a/kernel/arch/arm/boot/dts/da850-evm.dts b/kernel/arch/arm/boot/dts/da850-evm.dts
index 4f935ad9f..6881757b0 100644
--- a/kernel/arch/arm/boot/dts/da850-evm.dts
+++ b/kernel/arch/arm/boot/dts/da850-evm.dts
@@ -85,6 +85,7 @@
#size-cells = <1>;
compatible = "m25p64";
spi-max-frequency = <30000000>;
+ m25p,fast-read;
reg = <0>;
partition@0 {
label = "U-Boot-SPL";
diff --git a/kernel/arch/arm/boot/dts/exynos4210-trats.dts b/kernel/arch/arm/boot/dts/exynos4210-trats.dts
index a50be640f..59411e447 100644
--- a/kernel/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/kernel/arch/arm/boot/dts/exynos4210-trats.dts
@@ -298,6 +298,8 @@
compatible = "maxim,max8997-pmic";
reg = <0x66>;
+ interrupt-parent = <&gpx0>;
+ interrupts = <7 0>;
max8997,pmic-buck1-uses-gpio-dvs;
max8997,pmic-buck2-uses-gpio-dvs;
diff --git a/kernel/arch/arm/boot/dts/imx31.dtsi b/kernel/arch/arm/boot/dts/imx31.dtsi
index 5fdb22263..cbe5fd5ed 100644
--- a/kernel/arch/arm/boot/dts/imx31.dtsi
+++ b/kernel/arch/arm/boot/dts/imx31.dtsi
@@ -30,11 +30,11 @@
};
};
- avic: avic-interrupt-controller@60000000 {
+ avic: interrupt-controller@68000000 {
compatible = "fsl,imx31-avic", "fsl,avic";
interrupt-controller;
#interrupt-cells = <1>;
- reg = <0x60000000 0x100000>;
+ reg = <0x68000000 0x100000>;
};
soc {
@@ -110,13 +110,6 @@
interrupts = <19>;
clocks = <&clks 25>;
};
-
- clks: ccm@53f80000{
- compatible = "fsl,imx31-ccm";
- reg = <0x53f80000 0x4000>;
- interrupts = <0 31 0x04 0 53 0x04>;
- #clock-cells = <1>;
- };
};
aips@53f00000 { /* AIPS2 */
@@ -126,6 +119,13 @@
reg = <0x53f00000 0x100000>;
ranges;
+ clks: ccm@53f80000{
+ compatible = "fsl,imx31-ccm";
+ reg = <0x53f80000 0x4000>;
+ interrupts = <31>, <53>;
+ #clock-cells = <1>;
+ };
+
gpt: timer@53f90000 {
compatible = "fsl,imx31-gpt";
reg = <0x53f90000 0x4000>;
diff --git a/kernel/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/kernel/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
index a35d54fd9..ddfdb75a6 100644
--- a/kernel/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
+++ b/kernel/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
@@ -319,8 +319,6 @@
compatible = "fsl,imx6q-nitrogen6_max-sgtl5000",
"fsl,imx-audio-sgtl5000";
model = "imx6q-nitrogen6_max-sgtl5000";
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_sgtl5000>;
ssi-controller = <&ssi1>;
audio-codec = <&codec>;
audio-routing =
@@ -401,6 +399,8 @@
codec: sgtl5000@0a {
compatible = "fsl,sgtl5000";
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_sgtl5000>;
reg = <0x0a>;
clocks = <&clks 201>;
VDDA-supply = <&reg_2p5v>;
diff --git a/kernel/arch/arm/boot/dts/imx6qdl.dtsi b/kernel/arch/arm/boot/dts/imx6qdl.dtsi
index 2b6cc8bf3..e6af41c4b 100644
--- a/kernel/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/kernel/arch/arm/boot/dts/imx6qdl.dtsi
@@ -221,7 +221,7 @@
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/kernel/arch/arm/boot/dts/kirkwood-ib62x0.dts b/kernel/arch/arm/boot/dts/kirkwood-ib62x0.dts
index bfa5edde1..2c1e7f092 100644
--- a/kernel/arch/arm/boot/dts/kirkwood-ib62x0.dts
+++ b/kernel/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/kernel/arch/arm/boot/dts/omap3-overo-base.dtsi b/kernel/arch/arm/boot/dts/omap3-overo-base.dtsi
index a29ad16cc..64c5af30c 100644
--- a/kernel/arch/arm/boot/dts/omap3-overo-base.dtsi
+++ b/kernel/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 {
linux,mtd-name= "micron,mt29c4g96maz";
diff --git a/kernel/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi b/kernel/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
index 17b82f826..640477882 100644
--- a/kernel/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
+++ b/kernel/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/kernel/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi b/kernel/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
index 9e24b6a1d..1b304e2f1 100644
--- a/kernel/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
+++ b/kernel/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/kernel/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi b/kernel/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
index 334109e14..82e98ee30 100644
--- a/kernel/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
+++ b/kernel/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/kernel/arch/arm/boot/dts/pxa3xx.dtsi b/kernel/arch/arm/boot/dts/pxa3xx.dtsi
index cf6998a08..564341af7 100644
--- a/kernel/arch/arm/boot/dts/pxa3xx.dtsi
+++ b/kernel/arch/arm/boot/dts/pxa3xx.dtsi
@@ -30,7 +30,7 @@
reg = <0x43100000 90>;
interrupts = <45>;
clocks = <&clks CLK_NAND>;
- dmas = <&pdma 97>;
+ dmas = <&pdma 97 3>;
dma-names = "data";
#address-cells = <1>;
#size-cells = <1>;
diff --git a/kernel/arch/arm/boot/dts/qcom-apq8064.dtsi b/kernel/arch/arm/boot/dts/qcom-apq8064.dtsi
index a4c1762b5..e00d50ef6 100644
--- a/kernel/arch/arm/boot/dts/qcom-apq8064.dtsi
+++ b/kernel/arch/arm/boot/dts/qcom-apq8064.dtsi
@@ -5,6 +5,7 @@
#include <dt-bindings/reset/qcom,gcc-msm8960.h>
#include <dt-bindings/clock/qcom,mmcc-msm8960.h>
#include <dt-bindings/soc/qcom,gsbi.h>
+#include <dt-bindings/interrupt-controller/irq.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
/ {
model = "Qualcomm APQ8064";
@@ -354,22 +355,50 @@
compatible = "qcom,pm8921-gpio";
reg = <0x150>;
- interrupts = <192 1>, <193 1>, <194 1>,
- <195 1>, <196 1>, <197 1>,
- <198 1>, <199 1>, <200 1>,
- <201 1>, <202 1>, <203 1>,
- <204 1>, <205 1>, <206 1>,
- <207 1>, <208 1>, <209 1>,
- <210 1>, <211 1>, <212 1>,
- <213 1>, <214 1>, <215 1>,
- <216 1>, <217 1>, <218 1>,
- <219 1>, <220 1>, <221 1>,
- <222 1>, <223 1>, <224 1>,
- <225 1>, <226 1>, <227 1>,
- <228 1>, <229 1>, <230 1>,
- <231 1>, <232 1>, <233 1>,
- <234 1>, <235 1>;
-
+ interrupts = <192 IRQ_TYPE_NONE>,
+ <193 IRQ_TYPE_NONE>,
+ <194 IRQ_TYPE_NONE>,
+ <195 IRQ_TYPE_NONE>,
+ <196 IRQ_TYPE_NONE>,
+ <197 IRQ_TYPE_NONE>,
+ <198 IRQ_TYPE_NONE>,
+ <199 IRQ_TYPE_NONE>,
+ <200 IRQ_TYPE_NONE>,
+ <201 IRQ_TYPE_NONE>,
+ <202 IRQ_TYPE_NONE>,
+ <203 IRQ_TYPE_NONE>,
+ <204 IRQ_TYPE_NONE>,
+ <205 IRQ_TYPE_NONE>,
+ <206 IRQ_TYPE_NONE>,
+ <207 IRQ_TYPE_NONE>,
+ <208 IRQ_TYPE_NONE>,
+ <209 IRQ_TYPE_NONE>,
+ <210 IRQ_TYPE_NONE>,
+ <211 IRQ_TYPE_NONE>,
+ <212 IRQ_TYPE_NONE>,
+ <213 IRQ_TYPE_NONE>,
+ <214 IRQ_TYPE_NONE>,
+ <215 IRQ_TYPE_NONE>,
+ <216 IRQ_TYPE_NONE>,
+ <217 IRQ_TYPE_NONE>,
+ <218 IRQ_TYPE_NONE>,
+ <219 IRQ_TYPE_NONE>,
+ <220 IRQ_TYPE_NONE>,
+ <221 IRQ_TYPE_NONE>,
+ <222 IRQ_TYPE_NONE>,
+ <223 IRQ_TYPE_NONE>,
+ <224 IRQ_TYPE_NONE>,
+ <225 IRQ_TYPE_NONE>,
+ <226 IRQ_TYPE_NONE>,
+ <227 IRQ_TYPE_NONE>,
+ <228 IRQ_TYPE_NONE>,
+ <229 IRQ_TYPE_NONE>,
+ <230 IRQ_TYPE_NONE>,
+ <231 IRQ_TYPE_NONE>,
+ <232 IRQ_TYPE_NONE>,
+ <233 IRQ_TYPE_NONE>,
+ <234 IRQ_TYPE_NONE>,
+ <235 IRQ_TYPE_NONE>;
gpio-controller;
#gpio-cells = <2>;
@@ -381,9 +410,18 @@
gpio-controller;
#gpio-cells = <2>;
interrupts =
- <128 1>, <129 1>, <130 1>, <131 1>,
- <132 1>, <133 1>, <134 1>, <135 1>,
- <136 1>, <137 1>, <138 1>, <139 1>;
+ <128 IRQ_TYPE_NONE>,
+ <129 IRQ_TYPE_NONE>,
+ <130 IRQ_TYPE_NONE>,
+ <131 IRQ_TYPE_NONE>,
+ <132 IRQ_TYPE_NONE>,
+ <133 IRQ_TYPE_NONE>,
+ <134 IRQ_TYPE_NONE>,
+ <135 IRQ_TYPE_NONE>,
+ <136 IRQ_TYPE_NONE>,
+ <137 IRQ_TYPE_NONE>,
+ <138 IRQ_TYPE_NONE>,
+ <139 IRQ_TYPE_NONE>;
};
rtc@11d {
diff --git a/kernel/arch/arm/boot/dts/r8a7794.dtsi b/kernel/arch/arm/boot/dts/r8a7794.dtsi
index a9977d6ee..169653586 100644
--- a/kernel/arch/arm/boot/dts/r8a7794.dtsi
+++ b/kernel/arch/arm/boot/dts/r8a7794.dtsi
@@ -1023,7 +1023,7 @@
mstp7_clks: mstp7_clks@e615014c {
compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
reg = <0 0xe615014c 0 4>, <0 0xe61501c4 0 4>;
- clocks = <&mp_clk>, <&mp_clk>,
+ clocks = <&mp_clk>, <&hp_clk>,
<&zs_clk>, <&p_clk>, <&p_clk>, <&zs_clk>,
<&zs_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>;
#clock-cells = <1>;
diff --git a/kernel/arch/arm/boot/dts/sama5d2-pinfunc.h b/kernel/arch/arm/boot/dts/sama5d2-pinfunc.h
index b0c912fea..8a394f336 100644
--- a/kernel/arch/arm/boot/dts/sama5d2-pinfunc.h
+++ b/kernel/arch/arm/boot/dts/sama5d2-pinfunc.h
@@ -837,8 +837,8 @@
#define PIN_PD23__ISC_FIELD PINMUX_PIN(PIN_PD23, 6, 4)
#define PIN_PD24 120
#define PIN_PD24__GPIO PINMUX_PIN(PIN_PD24, 0, 0)
-#define PIN_PD24__UTXD2 PINMUX_PIN(PIN_PD23, 1, 2)
-#define PIN_PD24__FLEXCOM4_IO3 PINMUX_PIN(PIN_PD23, 3, 3)
+#define PIN_PD24__UTXD2 PINMUX_PIN(PIN_PD24, 1, 2)
+#define PIN_PD24__FLEXCOM4_IO3 PINMUX_PIN(PIN_PD24, 3, 3)
#define PIN_PD25 121
#define PIN_PD25__GPIO PINMUX_PIN(PIN_PD25, 0, 0)
#define PIN_PD25__SPI1_SPCK PINMUX_PIN(PIN_PD25, 1, 3)
diff --git a/kernel/arch/arm/boot/dts/stih407-family.dtsi b/kernel/arch/arm/boot/dts/stih407-family.dtsi
index 81f81214c..bbf95375c 100644
--- a/kernel/arch/arm/boot/dts/stih407-family.dtsi
+++ b/kernel/arch/arm/boot/dts/stih407-family.dtsi
@@ -497,8 +497,9 @@
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;
};
@@ -512,8 +513,9 @@
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/kernel/arch/arm/boot/dts/stih410.dtsi b/kernel/arch/arm/boot/dts/stih410.dtsi
index 18ed1ad10..40318869c 100644
--- a/kernel/arch/arm/boot/dts/stih410.dtsi
+++ b/kernel/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/kernel/arch/arm/boot/dts/sun4i-a10-a1000.dts b/kernel/arch/arm/boot/dts/sun4i-a10-a1000.dts
index 97570cb7f..1d23527d4 100644
--- a/kernel/arch/arm/boot/dts/sun4i-a10-a1000.dts
+++ b/kernel/arch/arm/boot/dts/sun4i-a10-a1000.dts
@@ -84,6 +84,7 @@
regulator-name = "emac-3v3";
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
+ startup-delay-us = <20000>;
enable-active-high;
gpio = <&pio 7 15 GPIO_ACTIVE_HIGH>;
};
diff --git a/kernel/arch/arm/boot/dts/sun4i-a10-hackberry.dts b/kernel/arch/arm/boot/dts/sun4i-a10-hackberry.dts
index 2b17c5199..6de83a618 100644
--- a/kernel/arch/arm/boot/dts/sun4i-a10-hackberry.dts
+++ b/kernel/arch/arm/boot/dts/sun4i-a10-hackberry.dts
@@ -66,6 +66,7 @@
regulator-name = "emac-3v3";
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
+ startup-delay-us = <20000>;
enable-active-high;
gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;
};
diff --git a/kernel/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts b/kernel/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
index 7afc7a64e..e28f080b1 100644
--- a/kernel/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
+++ b/kernel/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
@@ -80,6 +80,7 @@
regulator-name = "emac-3v3";
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
+ startup-delay-us = <20000>;
enable-active-high;
gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>; /* PH19 */
};
diff --git a/kernel/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts b/kernel/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
index 9fea918f9..39731a78f 100644
--- a/kernel/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
+++ b/kernel/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
@@ -79,6 +79,7 @@
regulator-name = "emac-3v3";
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
+ startup-delay-us = <20000>;
enable-active-high;
gpio = <&pio 0 2 GPIO_ACTIVE_HIGH>;
};
diff --git a/kernel/arch/arm/boot/dts/sun5i-a13.dtsi b/kernel/arch/arm/boot/dts/sun5i-a13.dtsi
index d910d3a6c..84bdba480 100644
--- a/kernel/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/kernel/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -83,7 +83,7 @@
trips {
cpu_alert0: cpu_alert0 {
/* milliCelsius */
- temperature = <850000>;
+ temperature = <85000>;
hysteresis = <2000>;
type = "passive";
};
diff --git a/kernel/arch/arm/boot/dts/sun5i-r8-chip.dts b/kernel/arch/arm/boot/dts/sun5i-r8-chip.dts
index 530ab28e9..d21f50ba3 100644
--- a/kernel/arch/arm/boot/dts/sun5i-r8-chip.dts
+++ b/kernel/arch/arm/boot/dts/sun5i-r8-chip.dts
@@ -52,7 +52,7 @@
/ {
model = "NextThing C.H.I.P.";
- compatible = "nextthing,chip", "allwinner,sun5i-r8";
+ compatible = "nextthing,chip", "allwinner,sun5i-r8", "allwinner,sun5i-a13";
aliases {
i2c0 = &i2c0;
diff --git a/kernel/arch/arm/common/sa1111.c b/kernel/arch/arm/common/sa1111.c
index 3d224941b..a3a9ad4dc 100644
--- a/kernel/arch/arm/common/sa1111.c
+++ b/kernel/arch/arm/common/sa1111.c
@@ -869,9 +869,9 @@ 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 +934,9 @@ 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 +952,7 @@ 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 +1003,8 @@ 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)
@@ -1038,6 +1038,11 @@ 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 +1055,9 @@ 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/kernel/arch/arm/crypto/aes-ce-glue.c b/kernel/arch/arm/crypto/aes-ce-glue.c
index b445a5d56..679c589c4 100644
--- a/kernel/arch/arm/crypto/aes-ce-glue.c
+++ b/kernel/arch/arm/crypto/aes-ce-glue.c
@@ -87,8 +87,13 @@ static int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
u32 *rki = ctx->key_enc + (i * kwords);
u32 *rko = rki + kwords;
+#ifndef CONFIG_CPU_BIG_ENDIAN
rko[0] = ror32(ce_aes_sub(rki[kwords - 1]), 8);
rko[0] = rko[0] ^ rki[0] ^ rcon[i];
+#else
+ rko[0] = rol32(ce_aes_sub(rki[kwords - 1]), 8);
+ rko[0] = rko[0] ^ rki[0] ^ (rcon[i] << 24);
+#endif
rko[1] = rko[0] ^ rki[1];
rko[2] = rko[1] ^ rki[2];
rko[3] = rko[2] ^ rki[3];
@@ -279,7 +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/kernel/arch/arm/crypto/ghash-ce-glue.c b/kernel/arch/arm/crypto/ghash-ce-glue.c
index 03a39fe29..9d9ba9acd 100644
--- a/kernel/arch/arm/crypto/ghash-ce-glue.c
+++ b/kernel/arch/arm/crypto/ghash-ce-glue.c
@@ -226,6 +226,27 @@ static int ghash_async_digest(struct ahash_request *req)
}
}
+static int ghash_async_import(struct ahash_request *req, const void *in)
+{
+ struct ahash_request *cryptd_req = ahash_request_ctx(req);
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+ desc->tfm = cryptd_ahash_child(ctx->cryptd_tfm);
+ desc->flags = req->base.flags;
+
+ return crypto_shash_import(desc, in);
+}
+
+static int ghash_async_export(struct ahash_request *req, void *out)
+{
+ struct ahash_request *cryptd_req = ahash_request_ctx(req);
+ struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+ return crypto_shash_export(desc, out);
+}
+
static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
unsigned int keylen)
{
@@ -274,7 +295,10 @@ static struct ahash_alg ghash_async_alg = {
.final = ghash_async_final,
.setkey = ghash_async_setkey,
.digest = ghash_async_digest,
+ .import = ghash_async_import,
+ .export = ghash_async_export,
.halg.digestsize = GHASH_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct ghash_desc_ctx),
.halg.base = {
.cra_name = "ghash",
.cra_driver_name = "ghash-ce",
diff --git a/kernel/arch/arm/include/asm/cputype.h b/kernel/arch/arm/include/asm/cputype.h
index 85e374f87..e9d04f475 100644
--- a/kernel/arch/arm/include/asm/cputype.h
+++ b/kernel/arch/arm/include/asm/cputype.h
@@ -81,6 +81,9 @@
#define ARM_CPU_XSCALE_ARCH_V2 0x4000
#define ARM_CPU_XSCALE_ARCH_V3 0x6000
+/* Qualcomm implemented cores */
+#define ARM_CPU_PART_SCORPION 0x510002d0
+
extern unsigned int processor_id;
#ifdef CONFIG_CPU_CP15
diff --git a/kernel/arch/arm/include/asm/dma-mapping.h b/kernel/arch/arm/include/asm/dma-mapping.h
index ccb3aa646..b91a2d17a 100644
--- a/kernel/arch/arm/include/asm/dma-mapping.h
+++ b/kernel/arch/arm/include/asm/dma-mapping.h
@@ -119,7 +119,7 @@ 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/kernel/arch/arm/include/asm/floppy.h b/kernel/arch/arm/include/asm/floppy.h
index f4882553f..85a34cc83 100644
--- a/kernel/arch/arm/include/asm/floppy.h
+++ b/kernel/arch/arm/include/asm/floppy.h
@@ -17,7 +17,7 @@
#define fd_outb(val,port) \
do { \
- if ((port) == FD_DOR) \
+ if ((port) == (u32)FD_DOR) \
fd_setdor((val)); \
else \
outb((val),(port)); \
diff --git a/kernel/arch/arm/include/asm/pgtable-2level.h b/kernel/arch/arm/include/asm/pgtable-2level.h
index aeddd28b3..92fd2c8a9 100644
--- a/kernel/arch/arm/include/asm/pgtable-2level.h
+++ b/kernel/arch/arm/include/asm/pgtable-2level.h
@@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
#define pmd_large(pmd) (pmd_val(pmd) & 2)
#define pmd_bad(pmd) (pmd_val(pmd) & 2)
+#define pmd_present(pmd) (pmd_val(pmd))
#define copy_pmd(pmdpd,pmdps) \
do { \
diff --git a/kernel/arch/arm/include/asm/pgtable-3level.h b/kernel/arch/arm/include/asm/pgtable-3level.h
index a745a2a53..fd929b5de 100644
--- a/kernel/arch/arm/include/asm/pgtable-3level.h
+++ b/kernel/arch/arm/include/asm/pgtable-3level.h
@@ -212,6 +212,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
: !!(pmd_val(pmd) & (val)))
#define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val)))
+#define pmd_present(pmd) (pmd_isset((pmd), L_PMD_SECT_VALID))
#define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF))
#define pte_special(pte) (pte_isset((pte), L_PTE_SPECIAL))
static inline pte_t pte_mkspecial(pte_t pte)
@@ -257,10 +258,10 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF);
#define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot)
-/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */
static inline pmd_t pmd_mknotpresent(pmd_t pmd)
{
- return __pmd(0);
+ return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID);
}
static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
diff --git a/kernel/arch/arm/include/asm/pgtable.h b/kernel/arch/arm/include/asm/pgtable.h
index 348caabb7..d62204060 100644
--- a/kernel/arch/arm/include/asm/pgtable.h
+++ b/kernel/arch/arm/include/asm/pgtable.h
@@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
#define pgd_offset_k(addr) pgd_offset(&init_mm, addr)
#define pmd_none(pmd) (!pmd_val(pmd))
-#define pmd_present(pmd) (pmd_val(pmd))
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
{
diff --git a/kernel/arch/arm/kernel/devtree.c b/kernel/arch/arm/kernel/devtree.c
index 65addcbf5..b3b950fc8 100644
--- a/kernel/arch/arm/kernel/devtree.c
+++ b/kernel/arch/arm/kernel/devtree.c
@@ -87,6 +87,8 @@ 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"))
@@ -98,7 +100,8 @@ 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);
@@ -106,10 +109,15 @@ 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/kernel/arch/arm/kernel/entry-armv.S b/kernel/arch/arm/kernel/entry-armv.S
index d66b1aef2..d044cea59 100644
--- a/kernel/arch/arm/kernel/entry-armv.S
+++ b/kernel/arch/arm/kernel/entry-armv.S
@@ -244,7 +244,11 @@ svc_preempt:
bne 1b
tst r0, #_TIF_NEED_RESCHED_LAZY
reteq r8 @ go again
- b 1b
+ ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count
+ teq r0, #0 @ if preempt lazy count != 0
+ beq 1b
+ ret r8 @ go again
+
#endif
__und_fault:
diff --git a/kernel/arch/arm/kernel/hw_breakpoint.c b/kernel/arch/arm/kernel/hw_breakpoint.c
index 6284779d6..abcbea1ae 100644
--- a/kernel/arch/arm/kernel/hw_breakpoint.c
+++ b/kernel/arch/arm/kernel/hw_breakpoint.c
@@ -1066,6 +1066,22 @@ static int __init arch_hw_breakpoint_init(void)
return 0;
}
+ /*
+ * Scorpion CPUs (at least those in APQ8060) seem to set DBGPRSR.SPD
+ * whenever a WFI is issued, even if the core is not powered down, in
+ * violation of the architecture. When DBGPRSR.SPD is set, accesses to
+ * breakpoint and watchpoint registers are treated as undefined, so
+ * this results in boot time and runtime failures when these are
+ * accessed and we unexpectedly take a trap.
+ *
+ * It's not clear if/how this can be worked around, so we blacklist
+ * Scorpion CPUs to avoid these issues.
+ */
+ if (read_cpuid_part() == ARM_CPU_PART_SCORPION) {
+ pr_info("Scorpion CPU detected. Hardware breakpoints and watchpoints disabled\n");
+ return 0;
+ }
+
has_ossr = core_has_os_save_restore();
/* Determine how many BRPs/WRPs are available. */
diff --git a/kernel/arch/arm/kernel/patch.c b/kernel/arch/arm/kernel/patch.c
index 69bda1a57..1f665acaa 100644
--- a/kernel/arch/arm/kernel/patch.c
+++ b/kernel/arch/arm/kernel/patch.c
@@ -15,7 +15,7 @@ struct patch {
unsigned int insn;
};
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
__acquires(&patch_lock)
@@ -32,7 +32,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
return addr;
if (flags)
- spin_lock_irqsave(&patch_lock, *flags);
+ raw_spin_lock_irqsave(&patch_lock, *flags);
else
__acquire(&patch_lock);
@@ -47,7 +47,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
clear_fixmap(fixmap);
if (flags)
- spin_unlock_irqrestore(&patch_lock, *flags);
+ raw_spin_unlock_irqrestore(&patch_lock, *flags);
else
__release(&patch_lock);
}
diff --git a/kernel/arch/arm/kernel/ptrace.c b/kernel/arch/arm/kernel/ptrace.c
index ef9119f74..d54c53b7a 100644
--- a/kernel/arch/arm/kernel/ptrace.c
+++ b/kernel/arch/arm/kernel/ptrace.c
@@ -600,7 +600,7 @@ static int gpr_set(struct task_struct *target,
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct pt_regs newregs;
+ struct pt_regs newregs = *task_pt_regs(target);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&newregs,
@@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target,
if (ret)
return ret;
- vfp_flush_hwstate(thread);
thread->vfpstate.hard = new_vfp;
+ vfp_flush_hwstate(thread);
return 0;
}
diff --git a/kernel/arch/arm/kernel/smp_tlb.c b/kernel/arch/arm/kernel/smp_tlb.c
index 2e72be4f6..7cb079e74 100644
--- a/kernel/arch/arm/kernel/smp_tlb.c
+++ b/kernel/arch/arm/kernel/smp_tlb.c
@@ -9,6 +9,7 @@
*/
#include <linux/preempt.h>
#include <linux/smp.h>
+#include <linux/uaccess.h>
#include <asm/smp_plat.h>
#include <asm/tlbflush.h>
@@ -40,8 +41,11 @@ static inline void ipi_flush_tlb_mm(void *arg)
static inline void ipi_flush_tlb_page(void *arg)
{
struct tlb_args *ta = (struct tlb_args *)arg;
+ unsigned int __ua_flags = uaccess_save_and_enable();
local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+
+ uaccess_restore(__ua_flags);
}
static inline void ipi_flush_tlb_kernel_page(void *arg)
@@ -54,8 +58,11 @@ static inline void ipi_flush_tlb_kernel_page(void *arg)
static inline void ipi_flush_tlb_range(void *arg)
{
struct tlb_args *ta = (struct tlb_args *)arg;
+ unsigned int __ua_flags = uaccess_save_and_enable();
local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+
+ uaccess_restore(__ua_flags);
}
static inline void ipi_flush_tlb_kernel_range(void *arg)
diff --git a/kernel/arch/arm/kernel/sys_oabi-compat.c b/kernel/arch/arm/kernel/sys_oabi-compat.c
index 087acb569..5f221acd2 100644
--- a/kernel/arch/arm/kernel/sys_oabi-compat.c
+++ b/kernel/arch/arm/kernel/sys_oabi-compat.c
@@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd,
mm_segment_t fs;
long ret, err, i;
- if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event)))
+ if (maxevents <= 0 ||
+ maxevents > (INT_MAX/sizeof(*kbuf)) ||
+ maxevents > (INT_MAX/sizeof(*events)))
return -EINVAL;
+ if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents))
+ return -EFAULT;
kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
@@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid,
if (nsops < 1 || nsops > SEMOPM)
return -EINVAL;
+ if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops))
+ return -EFAULT;
sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL);
if (!sops)
return -ENOMEM;
diff --git a/kernel/arch/arm/kvm/arm.c b/kernel/arch/arm/kvm/arm.c
index bb43bc396..36a3e5149 100644
--- a/kernel/arch/arm/kvm/arm.c
+++ b/kernel/arch/arm/kvm/arm.c
@@ -155,8 +155,6 @@ 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/kernel/arch/arm/kvm/mmu.c b/kernel/arch/arm/kvm/mmu.c
index 61d96a645..11b6595c2 100644
--- a/kernel/arch/arm/kvm/mmu.c
+++ b/kernel/arch/arm/kvm/mmu.c
@@ -886,11 +886,14 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd));
old_pmd = *pmd;
- kvm_set_pmd(pmd, *new_pmd);
- if (pmd_present(old_pmd))
+ if (pmd_present(old_pmd)) {
+ pmd_clear(pmd);
kvm_tlb_flush_vmid_ipa(kvm, addr);
- else
+ } else {
get_page(virt_to_page(pmd));
+ }
+
+ kvm_set_pmd(pmd, *new_pmd);
return 0;
}
@@ -939,12 +942,14 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
/* Create 2nd stage page table mapping - Level 3 */
old_pte = *pte;
- kvm_set_pte(pte, *new_pte);
- if (pte_present(old_pte))
+ if (pte_present(old_pte)) {
+ kvm_set_pte(pte, __pte(0));
kvm_tlb_flush_vmid_ipa(kvm, addr);
- else
+ } else {
get_page(virt_to_page(pte));
+ }
+ kvm_set_pte(pte, *new_pte);
return 0;
}
@@ -1847,6 +1852,7 @@ 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/kernel/arch/arm/mach-cns3xxx/pcie.c b/kernel/arch/arm/mach-cns3xxx/pcie.c
index 47905a50e..318394ed5 100644
--- a/kernel/arch/arm/mach-cns3xxx/pcie.c
+++ b/kernel/arch/arm/mach-cns3xxx/pcie.c
@@ -220,13 +220,13 @@ static void cns3xxx_write_config(struct cns3xxx_pcie *cnspci,
u32 mask = (0x1ull << (size * 8)) - 1;
int shift = (where % 4) * 8;
- v = readl_relaxed(base + (where & 0xffc));
+ v = readl_relaxed(base);
v &= ~(mask << shift);
v |= (val & mask) << shift;
- writel_relaxed(v, base + (where & 0xffc));
- readl_relaxed(base + (where & 0xffc));
+ writel_relaxed(v, base);
+ readl_relaxed(base);
}
static void __init cns3xxx_pcie_hw_init(struct cns3xxx_pcie *cnspci)
diff --git a/kernel/arch/arm/mach-davinci/da850.c b/kernel/arch/arm/mach-davinci/da850.c
index 676997895..f5f81a107 100644
--- a/kernel/arch/arm/mach-davinci/da850.c
+++ b/kernel/arch/arm/mach-davinci/da850.c
@@ -298,6 +298,16 @@ static struct clk emac_clk = {
.gpsc = 1,
};
+/*
+ * In order to avoid adding the emac_clk to the clock lookup table twice (and
+ * screwing up the linked list in the process) create a separate clock for
+ * mdio inheriting the rate from emac_clk.
+ */
+static struct clk mdio_clk = {
+ .name = "mdio",
+ .parent = &emac_clk,
+};
+
static struct clk mcasp_clk = {
.name = "mcasp",
.parent = &pll0_sysclk2,
@@ -462,7 +472,7 @@ static struct clk_lookup da850_clks[] = {
CLK(NULL, "arm", &arm_clk),
CLK(NULL, "rmii", &rmii_clk),
CLK("davinci_emac.1", NULL, &emac_clk),
- CLK("davinci_mdio.0", "fck", &emac_clk),
+ CLK("davinci_mdio.0", "fck", &mdio_clk),
CLK("davinci-mcasp.0", NULL, &mcasp_clk),
CLK("da8xx_lcdc.0", "fck", &lcdc_clk),
CLK("da830-mmc.0", NULL, &mmcsd0_clk),
diff --git a/kernel/arch/arm/mach-exynos/Kconfig b/kernel/arch/arm/mach-exynos/Kconfig
index 3a10f1a83..bfd8bb371 100644
--- a/kernel/arch/arm/mach-exynos/Kconfig
+++ b/kernel/arch/arm/mach-exynos/Kconfig
@@ -26,6 +26,7 @@ menuconfig ARCH_EXYNOS
select S5P_DEV_MFC
select SRAM
select THERMAL
+ select THERMAL_OF
select MFD_SYSCON
help
Support for SAMSUNG EXYNOS SoCs (EXYNOS4/5)
diff --git a/kernel/arch/arm/mach-exynos/pm_domains.c b/kernel/arch/arm/mach-exynos/pm_domains.c
index 7c21760f5..875a2bab6 100644
--- a/kernel/arch/arm/mach-exynos/pm_domains.c
+++ b/kernel/arch/arm/mach-exynos/pm_domains.c
@@ -92,7 +92,7 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
if (IS_ERR(pd->clk[i]))
break;
- if (IS_ERR(pd->clk[i]))
+ if (IS_ERR(pd->pclk[i]))
continue; /* Skip on first power up */
if (clk_set_parent(pd->clk[i], pd->pclk[i]))
pr_err("%s: error setting parent to clock%d\n",
diff --git a/kernel/arch/arm/mach-imx/mach-imx6ul.c b/kernel/arch/arm/mach-imx/mach-imx6ul.c
index acaf7056e..e08d02667 100644
--- a/kernel/arch/arm/mach-imx/mach-imx6ul.c
+++ b/kernel/arch/arm/mach-imx/mach-imx6ul.c
@@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev)
static void __init imx6ul_enet_phy_init(void)
{
if (IS_BUILTIN(CONFIG_PHYLIB))
- phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff,
+ phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK,
ksz8081_phy_fixup);
}
diff --git a/kernel/arch/arm/mach-imx/pm-imx6.c b/kernel/arch/arm/mach-imx/pm-imx6.c
index 4470376af..a19d20f23 100644
--- a/kernel/arch/arm/mach-imx/pm-imx6.c
+++ b/kernel/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/kernel/arch/arm/mach-mvebu/coherency.c b/kernel/arch/arm/mach-mvebu/coherency.c
index 55348ee5a..feed36b32 100644
--- a/kernel/arch/arm/mach-mvebu/coherency.c
+++ b/kernel/arch/arm/mach-mvebu/coherency.c
@@ -162,22 +162,16 @@ exit:
}
/*
- * This ioremap hook is used on Armada 375/38x to ensure that PCIe
- * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This
- * is needed as a workaround for a deadlock issue between the PCIe
- * interface and the cache controller.
+ * This ioremap hook is used on Armada 375/38x to ensure that all MMIO
+ * areas are mapped as MT_UNCACHED instead of MT_DEVICE. This is
+ * needed for the HW I/O coherency mechanism to work properly without
+ * deadlock.
*/
static void __iomem *
-armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size,
- unsigned int mtype, void *caller)
+armada_wa_ioremap_caller(phys_addr_t phys_addr, size_t size,
+ unsigned int mtype, void *caller)
{
- struct resource pcie_mem;
-
- mvebu_mbus_get_pcie_mem_aperture(&pcie_mem);
-
- if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end)
- mtype = MT_UNCACHED;
-
+ mtype = MT_UNCACHED;
return __arm_ioremap_caller(phys_addr, size, mtype, caller);
}
@@ -186,7 +180,7 @@ static void __init armada_375_380_coherency_init(struct device_node *np)
struct device_node *cache_dn;
coherency_cpu_base = of_iomap(np, 0);
- arch_ioremap_caller = armada_pcie_wa_ioremap_caller;
+ arch_ioremap_caller = armada_wa_ioremap_caller;
/*
* We should switch the PL310 to I/O coherency mode only if
diff --git a/kernel/arch/arm/mach-omap2/cpuidle34xx.c b/kernel/arch/arm/mach-omap2/cpuidle34xx.c
index aa7b379e2..2a3db0bd9 100644
--- a/kernel/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/kernel/arch/arm/mach-omap2/cpuidle34xx.c
@@ -34,6 +34,7 @@
#include "pm.h"
#include "control.h"
#include "common.h"
+#include "soc.h"
/* Mach specific information to be recorded in the C-state driver_data */
struct omap3_idle_statedata {
@@ -315,6 +316,69 @@ static struct cpuidle_driver omap3_idle_driver = {
.safe_state_index = 0,
};
+/*
+ * Numbers based on measurements made in October 2009 for PM optimized kernel
+ * with CPU freq enabled on device Nokia N900. Assumes OPP2 (main idle OPP,
+ * and worst case latencies).
+ */
+static struct cpuidle_driver omap3430_idle_driver = {
+ .name = "omap3430_idle",
+ .owner = THIS_MODULE,
+ .states = {
+ {
+ .enter = omap3_enter_idle_bm,
+ .exit_latency = 110 + 162,
+ .target_residency = 5,
+ .name = "C1",
+ .desc = "MPU ON + CORE ON",
+ },
+ {
+ .enter = omap3_enter_idle_bm,
+ .exit_latency = 106 + 180,
+ .target_residency = 309,
+ .name = "C2",
+ .desc = "MPU ON + CORE ON",
+ },
+ {
+ .enter = omap3_enter_idle_bm,
+ .exit_latency = 107 + 410,
+ .target_residency = 46057,
+ .name = "C3",
+ .desc = "MPU RET + CORE ON",
+ },
+ {
+ .enter = omap3_enter_idle_bm,
+ .exit_latency = 121 + 3374,
+ .target_residency = 46057,
+ .name = "C4",
+ .desc = "MPU OFF + CORE ON",
+ },
+ {
+ .enter = omap3_enter_idle_bm,
+ .exit_latency = 855 + 1146,
+ .target_residency = 46057,
+ .name = "C5",
+ .desc = "MPU RET + CORE RET",
+ },
+ {
+ .enter = omap3_enter_idle_bm,
+ .exit_latency = 7580 + 4134,
+ .target_residency = 484329,
+ .name = "C6",
+ .desc = "MPU OFF + CORE RET",
+ },
+ {
+ .enter = omap3_enter_idle_bm,
+ .exit_latency = 7505 + 15274,
+ .target_residency = 484329,
+ .name = "C7",
+ .desc = "MPU OFF + CORE OFF",
+ },
+ },
+ .state_count = ARRAY_SIZE(omap3_idle_data),
+ .safe_state_index = 0,
+};
+
/* Public functions */
/**
@@ -333,5 +397,8 @@ int __init omap3_idle_init(void)
if (!mpu_pd || !core_pd || !per_pd || !cam_pd)
return -ENODEV;
- return cpuidle_register(&omap3_idle_driver, NULL);
+ if (cpu_is_omap3430())
+ return cpuidle_register(&omap3430_idle_driver, NULL);
+ else
+ return cpuidle_register(&omap3_idle_driver, NULL);
}
diff --git a/kernel/arch/arm/mach-omap2/io.c b/kernel/arch/arm/mach-omap2/io.c
index 3eaeaca5d..3a911d8de 100644
--- a/kernel/arch/arm/mach-omap2/io.c
+++ b/kernel/arch/arm/mach-omap2/io.c
@@ -368,6 +368,7 @@ void __init omap5_map_io(void)
void __init dra7xx_map_io(void)
{
iotable_init(dra7xx_io_desc, ARRAY_SIZE(dra7xx_io_desc));
+ omap_barriers_init();
}
#endif
/*
diff --git a/kernel/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/kernel/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index 65024af16..d3c14da7d 100644
--- a/kernel/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/kernel/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -243,10 +243,9 @@ int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state)
save_state = 1;
break;
case PWRDM_POWER_RET:
- if (IS_PM44XX_ERRATUM(PM_OMAP4_CPU_OSWR_DISABLE)) {
+ if (IS_PM44XX_ERRATUM(PM_OMAP4_CPU_OSWR_DISABLE))
save_state = 0;
- break;
- }
+ break;
default:
/*
* CPUx CSWR is invalid hardware state. Also CPUx OSWR
diff --git a/kernel/arch/arm/mach-omap2/omap_hwmod.c b/kernel/arch/arm/mach-omap2/omap_hwmod.c
index 8e0bd5939..147c90e70 100644
--- a/kernel/arch/arm/mach-omap2/omap_hwmod.c
+++ b/kernel/arch/arm/mach-omap2/omap_hwmod.c
@@ -1416,9 +1416,7 @@ static void _enable_sysc(struct omap_hwmod *oh)
(sf & SYSC_HAS_CLOCKACTIVITY))
_set_clockactivity(oh, oh->class->sysc->clockact, &v);
- /* If the cached value is the same as the new value, skip the write */
- if (oh->_sysc_cache != v)
- _write_sysconfig(v, oh);
+ _write_sysconfig(v, oh);
/*
* Set the autoidle bit only after setting the smartidle bit
@@ -1481,7 +1479,9 @@ static void _idle_sysc(struct omap_hwmod *oh)
_set_master_standbymode(oh, idlemode, &v);
}
- _write_sysconfig(v, oh);
+ /* If the cached value is the same as the new value, skip the write */
+ if (oh->_sysc_cache != v)
+ _write_sysconfig(v, oh);
}
/**
diff --git a/kernel/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/kernel/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
index 907a452b7..b31ad596b 100644
--- a/kernel/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
+++ b/kernel/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
@@ -1474,6 +1474,7 @@ static void omap_hwmod_am43xx_rst(void)
{
RSTCTRL(am33xx_pruss_hwmod, AM43XX_RM_PER_RSTCTRL_OFFSET);
RSTCTRL(am33xx_gfx_hwmod, AM43XX_RM_GFX_RSTCTRL_OFFSET);
+ RSTST(am33xx_pruss_hwmod, AM43XX_RM_PER_RSTST_OFFSET);
RSTST(am33xx_gfx_hwmod, AM43XX_RM_GFX_RSTST_OFFSET);
}
diff --git a/kernel/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/kernel/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index aff78d519..131f89675 100644
--- a/kernel/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/kernel/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -723,8 +723,20 @@ 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/kernel/arch/arm/mach-omap2/prcm43xx.h b/kernel/arch/arm/mach-omap2/prcm43xx.h
index 7c34c44eb..babb5db5a 100644
--- a/kernel/arch/arm/mach-omap2/prcm43xx.h
+++ b/kernel/arch/arm/mach-omap2/prcm43xx.h
@@ -39,6 +39,7 @@
/* RM RSTST offsets */
#define AM43XX_RM_GFX_RSTST_OFFSET 0x0014
+#define AM43XX_RM_PER_RSTST_OFFSET 0x0014
#define AM43XX_RM_WKUP_RSTST_OFFSET 0x0014
/* CM instances */
diff --git a/kernel/arch/arm/mach-prima2/Kconfig b/kernel/arch/arm/mach-prima2/Kconfig
index 9ab893240..56e55fd37 100644
--- a/kernel/arch/arm/mach-prima2/Kconfig
+++ b/kernel/arch/arm/mach-prima2/Kconfig
@@ -1,6 +1,7 @@
menuconfig ARCH_SIRF
bool "CSR SiRF" if ARCH_MULTI_V7
select ARCH_HAS_RESET_CONTROLLER
+ select RESET_CONTROLLER
select ARCH_REQUIRE_GPIOLIB
select GENERIC_IRQ_CHIP
select NO_IOPORT_MAP
diff --git a/kernel/arch/arm/mach-pxa/idp.c b/kernel/arch/arm/mach-pxa/idp.c
index f6d02e4cb..5c87dff5d 100644
--- a/kernel/arch/arm/mach-pxa/idp.c
+++ b/kernel/arch/arm/mach-pxa/idp.c
@@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = {
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_USE_DMA | SMC91X_NOWAIT,
};
static struct platform_device smc91x_device = {
diff --git a/kernel/arch/arm/mach-pxa/pxa_cplds_irqs.c b/kernel/arch/arm/mach-pxa/pxa_cplds_irqs.c
index 2385052b0..e362f865f 100644
--- a/kernel/arch/arm/mach-pxa/pxa_cplds_irqs.c
+++ b/kernel/arch/arm/mach-pxa/pxa_cplds_irqs.c
@@ -41,30 +41,35 @@ static irqreturn_t cplds_irq_handler(int in_irq, void *d)
unsigned long pending;
unsigned int bit;
- pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask;
- for_each_set_bit(bit, &pending, CPLDS_NB_IRQ)
- generic_handle_irq(irq_find_mapping(fpga->irqdomain, bit));
+ do {
+ pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask;
+ for_each_set_bit(bit, &pending, CPLDS_NB_IRQ) {
+ generic_handle_irq(irq_find_mapping(fpga->irqdomain,
+ bit));
+ }
+ } while (pending);
return IRQ_HANDLED;
}
-static void cplds_irq_mask_ack(struct irq_data *d)
+static void cplds_irq_mask(struct irq_data *d)
{
struct cplds *fpga = irq_data_get_irq_chip_data(d);
unsigned int cplds_irq = irqd_to_hwirq(d);
- unsigned int set, bit = BIT(cplds_irq);
+ unsigned int bit = BIT(cplds_irq);
fpga->irq_mask &= ~bit;
writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
- set = readl(fpga->base + FPGA_IRQ_SET_CLR);
- writel(set & ~bit, fpga->base + FPGA_IRQ_SET_CLR);
}
static void cplds_irq_unmask(struct irq_data *d)
{
struct cplds *fpga = irq_data_get_irq_chip_data(d);
unsigned int cplds_irq = irqd_to_hwirq(d);
- unsigned int bit = BIT(cplds_irq);
+ unsigned int set, bit = BIT(cplds_irq);
+
+ set = readl(fpga->base + FPGA_IRQ_SET_CLR);
+ writel(set & ~bit, fpga->base + FPGA_IRQ_SET_CLR);
fpga->irq_mask |= bit;
writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
@@ -72,7 +77,8 @@ static void cplds_irq_unmask(struct irq_data *d)
static struct irq_chip cplds_irq_chip = {
.name = "pxa_cplds",
- .irq_mask_ack = cplds_irq_mask_ack,
+ .irq_ack = cplds_irq_mask,
+ .irq_mask = cplds_irq_mask,
.irq_unmask = cplds_irq_unmask,
.flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE,
};
diff --git a/kernel/arch/arm/mach-pxa/xcep.c b/kernel/arch/arm/mach-pxa/xcep.c
index 13b1d4586..900131271 100644
--- a/kernel/arch/arm/mach-pxa/xcep.c
+++ b/kernel/arch/arm/mach-pxa/xcep.c
@@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = {
};
static struct smc91x_platdata xcep_smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT | SMC91X_USE_DMA,
};
static struct platform_device smc91x_device = {
diff --git a/kernel/arch/arm/mach-realview/core.c b/kernel/arch/arm/mach-realview/core.c
index 44575edc4..cf0a7c235 100644
--- a/kernel/arch/arm/mach-realview/core.c
+++ b/kernel/arch/arm/mach-realview/core.c
@@ -95,7 +95,8 @@ static struct smsc911x_platform_config smsc911x_config = {
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
};
static struct platform_device realview_eth_device = {
diff --git a/kernel/arch/arm/mach-s3c64xx/dev-audio.c b/kernel/arch/arm/mach-s3c64xx/dev-audio.c
index ff780a8d8..9a42736ef 100644
--- a/kernel/arch/arm/mach-s3c64xx/dev-audio.c
+++ b/kernel/arch/arm/mach-s3c64xx/dev-audio.c
@@ -54,12 +54,12 @@ static int s3c64xx_i2s_cfg_gpio(struct platform_device *pdev)
static struct resource s3c64xx_iis0_resource[] = {
[0] = DEFINE_RES_MEM(S3C64XX_PA_IIS0, SZ_256),
- [1] = DEFINE_RES_DMA(DMACH_I2S0_OUT),
- [2] = DEFINE_RES_DMA(DMACH_I2S0_IN),
};
-static struct s3c_audio_pdata i2sv3_pdata = {
+static struct s3c_audio_pdata i2s0_pdata = {
.cfg_gpio = s3c64xx_i2s_cfg_gpio,
+ .dma_playback = DMACH_I2S0_OUT,
+ .dma_capture = DMACH_I2S0_IN,
};
struct platform_device s3c64xx_device_iis0 = {
@@ -68,15 +68,19 @@ struct platform_device s3c64xx_device_iis0 = {
.num_resources = ARRAY_SIZE(s3c64xx_iis0_resource),
.resource = s3c64xx_iis0_resource,
.dev = {
- .platform_data = &i2sv3_pdata,
+ .platform_data = &i2s0_pdata,
},
};
EXPORT_SYMBOL(s3c64xx_device_iis0);
static struct resource s3c64xx_iis1_resource[] = {
[0] = DEFINE_RES_MEM(S3C64XX_PA_IIS1, SZ_256),
- [1] = DEFINE_RES_DMA(DMACH_I2S1_OUT),
- [2] = DEFINE_RES_DMA(DMACH_I2S1_IN),
+};
+
+static struct s3c_audio_pdata i2s1_pdata = {
+ .cfg_gpio = s3c64xx_i2s_cfg_gpio,
+ .dma_playback = DMACH_I2S1_OUT,
+ .dma_capture = DMACH_I2S1_IN,
};
struct platform_device s3c64xx_device_iis1 = {
@@ -85,19 +89,19 @@ struct platform_device s3c64xx_device_iis1 = {
.num_resources = ARRAY_SIZE(s3c64xx_iis1_resource),
.resource = s3c64xx_iis1_resource,
.dev = {
- .platform_data = &i2sv3_pdata,
+ .platform_data = &i2s1_pdata,
},
};
EXPORT_SYMBOL(s3c64xx_device_iis1);
static struct resource s3c64xx_iisv4_resource[] = {
[0] = DEFINE_RES_MEM(S3C64XX_PA_IISV4, SZ_256),
- [1] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_TX),
- [2] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_RX),
};
static struct s3c_audio_pdata i2sv4_pdata = {
.cfg_gpio = s3c64xx_i2s_cfg_gpio,
+ .dma_playback = DMACH_HSI_I2SV40_TX,
+ .dma_capture = DMACH_HSI_I2SV40_RX,
.type = {
.i2s = {
.quirks = QUIRK_PRI_6CHAN,
@@ -142,12 +146,12 @@ static int s3c64xx_pcm_cfg_gpio(struct platform_device *pdev)
static struct resource s3c64xx_pcm0_resource[] = {
[0] = DEFINE_RES_MEM(S3C64XX_PA_PCM0, SZ_256),
- [1] = DEFINE_RES_DMA(DMACH_PCM0_TX),
- [2] = DEFINE_RES_DMA(DMACH_PCM0_RX),
};
static struct s3c_audio_pdata s3c_pcm0_pdata = {
.cfg_gpio = s3c64xx_pcm_cfg_gpio,
+ .dma_capture = DMACH_PCM0_RX,
+ .dma_playback = DMACH_PCM0_TX,
};
struct platform_device s3c64xx_device_pcm0 = {
@@ -163,12 +167,12 @@ EXPORT_SYMBOL(s3c64xx_device_pcm0);
static struct resource s3c64xx_pcm1_resource[] = {
[0] = DEFINE_RES_MEM(S3C64XX_PA_PCM1, SZ_256),
- [1] = DEFINE_RES_DMA(DMACH_PCM1_TX),
- [2] = DEFINE_RES_DMA(DMACH_PCM1_RX),
};
static struct s3c_audio_pdata s3c_pcm1_pdata = {
.cfg_gpio = s3c64xx_pcm_cfg_gpio,
+ .dma_playback = DMACH_PCM1_TX,
+ .dma_capture = DMACH_PCM1_RX,
};
struct platform_device s3c64xx_device_pcm1 = {
@@ -196,13 +200,14 @@ static int s3c64xx_ac97_cfg_gpe(struct platform_device *pdev)
static struct resource s3c64xx_ac97_resource[] = {
[0] = DEFINE_RES_MEM(S3C64XX_PA_AC97, SZ_256),
- [1] = DEFINE_RES_DMA(DMACH_AC97_PCMOUT),
- [2] = DEFINE_RES_DMA(DMACH_AC97_PCMIN),
- [3] = DEFINE_RES_DMA(DMACH_AC97_MICIN),
- [4] = DEFINE_RES_IRQ(IRQ_AC97),
+ [1] = DEFINE_RES_IRQ(IRQ_AC97),
};
-static struct s3c_audio_pdata s3c_ac97_pdata;
+static struct s3c_audio_pdata s3c_ac97_pdata = {
+ .dma_playback = DMACH_AC97_PCMOUT,
+ .dma_capture = DMACH_AC97_PCMIN,
+ .dma_capture_mic = DMACH_AC97_MICIN,
+};
static u64 s3c64xx_ac97_dmamask = DMA_BIT_MASK(32);
diff --git a/kernel/arch/arm/mach-s3c64xx/include/mach/dma.h b/kernel/arch/arm/mach-s3c64xx/include/mach/dma.h
index 096e14073..9c739eafe 100644
--- a/kernel/arch/arm/mach-s3c64xx/include/mach/dma.h
+++ b/kernel/arch/arm/mach-s3c64xx/include/mach/dma.h
@@ -14,38 +14,38 @@
#define S3C64XX_DMA_CHAN(name) ((unsigned long)(name))
/* DMA0/SDMA0 */
-#define DMACH_UART0 S3C64XX_DMA_CHAN("uart0_tx")
-#define DMACH_UART0_SRC2 S3C64XX_DMA_CHAN("uart0_rx")
-#define DMACH_UART1 S3C64XX_DMA_CHAN("uart1_tx")
-#define DMACH_UART1_SRC2 S3C64XX_DMA_CHAN("uart1_rx")
-#define DMACH_UART2 S3C64XX_DMA_CHAN("uart2_tx")
-#define DMACH_UART2_SRC2 S3C64XX_DMA_CHAN("uart2_rx")
-#define DMACH_UART3 S3C64XX_DMA_CHAN("uart3_tx")
-#define DMACH_UART3_SRC2 S3C64XX_DMA_CHAN("uart3_rx")
-#define DMACH_PCM0_TX S3C64XX_DMA_CHAN("pcm0_tx")
-#define DMACH_PCM0_RX S3C64XX_DMA_CHAN("pcm0_rx")
-#define DMACH_I2S0_OUT S3C64XX_DMA_CHAN("i2s0_tx")
-#define DMACH_I2S0_IN S3C64XX_DMA_CHAN("i2s0_rx")
+#define DMACH_UART0 "uart0_tx"
+#define DMACH_UART0_SRC2 "uart0_rx"
+#define DMACH_UART1 "uart1_tx"
+#define DMACH_UART1_SRC2 "uart1_rx"
+#define DMACH_UART2 "uart2_tx"
+#define DMACH_UART2_SRC2 "uart2_rx"
+#define DMACH_UART3 "uart3_tx"
+#define DMACH_UART3_SRC2 "uart3_rx"
+#define DMACH_PCM0_TX "pcm0_tx"
+#define DMACH_PCM0_RX "pcm0_rx"
+#define DMACH_I2S0_OUT "i2s0_tx"
+#define DMACH_I2S0_IN "i2s0_rx"
#define DMACH_SPI0_TX S3C64XX_DMA_CHAN("spi0_tx")
#define DMACH_SPI0_RX S3C64XX_DMA_CHAN("spi0_rx")
-#define DMACH_HSI_I2SV40_TX S3C64XX_DMA_CHAN("i2s2_tx")
-#define DMACH_HSI_I2SV40_RX S3C64XX_DMA_CHAN("i2s2_rx")
+#define DMACH_HSI_I2SV40_TX "i2s2_tx"
+#define DMACH_HSI_I2SV40_RX "i2s2_rx"
/* DMA1/SDMA1 */
-#define DMACH_PCM1_TX S3C64XX_DMA_CHAN("pcm1_tx")
-#define DMACH_PCM1_RX S3C64XX_DMA_CHAN("pcm1_rx")
-#define DMACH_I2S1_OUT S3C64XX_DMA_CHAN("i2s1_tx")
-#define DMACH_I2S1_IN S3C64XX_DMA_CHAN("i2s1_rx")
+#define DMACH_PCM1_TX "pcm1_tx"
+#define DMACH_PCM1_RX "pcm1_rx"
+#define DMACH_I2S1_OUT "i2s1_tx"
+#define DMACH_I2S1_IN "i2s1_rx"
#define DMACH_SPI1_TX S3C64XX_DMA_CHAN("spi1_tx")
#define DMACH_SPI1_RX S3C64XX_DMA_CHAN("spi1_rx")
-#define DMACH_AC97_PCMOUT S3C64XX_DMA_CHAN("ac97_out")
-#define DMACH_AC97_PCMIN S3C64XX_DMA_CHAN("ac97_in")
-#define DMACH_AC97_MICIN S3C64XX_DMA_CHAN("ac97_mic")
-#define DMACH_PWM S3C64XX_DMA_CHAN("pwm")
-#define DMACH_IRDA S3C64XX_DMA_CHAN("irda")
-#define DMACH_EXTERNAL S3C64XX_DMA_CHAN("external")
-#define DMACH_SECURITY_RX S3C64XX_DMA_CHAN("sec_rx")
-#define DMACH_SECURITY_TX S3C64XX_DMA_CHAN("sec_tx")
+#define DMACH_AC97_PCMOUT "ac97_out"
+#define DMACH_AC97_PCMIN "ac97_in"
+#define DMACH_AC97_MICIN "ac97_mic"
+#define DMACH_PWM "pwm"
+#define DMACH_IRDA "irda"
+#define DMACH_EXTERNAL "external"
+#define DMACH_SECURITY_RX "sec_rx"
+#define DMACH_SECURITY_TX "sec_tx"
enum dma_ch {
DMACH_MAX = 32
diff --git a/kernel/arch/arm/mach-sa1100/clock.c b/kernel/arch/arm/mach-sa1100/clock.c
index cbf53bb9c..0db46895c 100644
--- a/kernel/arch/arm/mach-sa1100/clock.c
+++ b/kernel/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/kernel/arch/arm/mach-sa1100/generic.c b/kernel/arch/arm/mach-sa1100/generic.c
index 345e63f4e..3e09beddb 100644
--- a/kernel/arch/arm/mach-sa1100/generic.c
+++ b/kernel/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/kernel/arch/arm/mach-sa1100/generic.h b/kernel/arch/arm/mach-sa1100/generic.h
index 0d92e119b..68199b603 100644
--- a/kernel/arch/arm/mach-sa1100/generic.h
+++ b/kernel/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/kernel/arch/arm/mach-sa1100/pleb.c b/kernel/arch/arm/mach-sa1100/pleb.c
index 1525d7b5f..88149f85b 100644
--- a/kernel/arch/arm/mach-sa1100/pleb.c
+++ b/kernel/arch/arm/mach-sa1100/pleb.c
@@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = {
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT,
};
static struct platform_device smc91x_device = {
diff --git a/kernel/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/kernel/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
index 62437b578..73e3adbc1 100644
--- a/kernel/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
+++ b/kernel/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/kernel/arch/arm/mach-socfpga/headsmp.S b/kernel/arch/arm/mach-socfpga/headsmp.S
index 5d94b7a2f..c160fa300 100644
--- a/kernel/arch/arm/mach-socfpga/headsmp.S
+++ b/kernel/arch/arm/mach-socfpga/headsmp.S
@@ -13,6 +13,7 @@
#include <asm/assembler.h>
.arch armv7-a
+ .arm
ENTRY(secondary_trampoline)
/* CPU1 will always fetch from 0x0 when it is brought out of reset.
diff --git a/kernel/arch/arm/mach-ux500/pm.c b/kernel/arch/arm/mach-ux500/pm.c
index 8538910db..a970e7fcb 100644
--- a/kernel/arch/arm/mach-ux500/pm.c
+++ b/kernel/arch/arm/mach-ux500/pm.c
@@ -134,8 +134,8 @@ bool prcmu_pending_irq(void)
*/
bool prcmu_is_cpu_in_wfi(int cpu)
{
- return readl(PRCM_ARM_WFI_STANDBY) & cpu ? PRCM_ARM_WFI_STANDBY_WFI1 :
- PRCM_ARM_WFI_STANDBY_WFI0;
+ return readl(PRCM_ARM_WFI_STANDBY) &
+ (cpu ? PRCM_ARM_WFI_STANDBY_WFI1 : PRCM_ARM_WFI_STANDBY_WFI0);
}
/*
diff --git a/kernel/arch/arm/mach-zynq/common.c b/kernel/arch/arm/mach-zynq/common.c
index 6f39d03cc..0a43143e9 100644
--- a/kernel/arch/arm/mach-zynq/common.c
+++ b/kernel/arch/arm/mach-zynq/common.c
@@ -59,7 +59,7 @@ void __iomem *zynq_scu_base;
static void __init zynq_memory_init(void)
{
if (!__pa(PAGE_OFFSET))
- memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir));
+ memblock_reserve(__pa(PAGE_OFFSET), 0x80000);
}
static struct platform_device zynq_cpuidle_device = {
diff --git a/kernel/arch/arm/mm/fault.c b/kernel/arch/arm/mm/fault.c
index b8aa1e9ee..276ac73f8 100644
--- a/kernel/arch/arm/mm/fault.c
+++ b/kernel/arch/arm/mm/fault.c
@@ -616,9 +616,9 @@ static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
void __init early_abt_enable(void)
{
- fsr_info[22].fn = early_abort_handler;
+ fsr_info[FSR_FS_AEA].fn = early_abort_handler;
local_abt_enable();
- fsr_info[22].fn = do_bad;
+ fsr_info[FSR_FS_AEA].fn = do_bad;
}
#ifndef CONFIG_ARM_LPAE
diff --git a/kernel/arch/arm/mm/fault.h b/kernel/arch/arm/mm/fault.h
index 05ec5e0df..78830657c 100644
--- a/kernel/arch/arm/mm/fault.h
+++ b/kernel/arch/arm/mm/fault.h
@@ -11,11 +11,15 @@
#define FSR_FS5_0 (0x3f)
#ifdef CONFIG_ARM_LPAE
+#define FSR_FS_AEA 17
+
static inline int fsr_fs(unsigned int fsr)
{
return fsr & FSR_FS5_0;
}
#else
+#define FSR_FS_AEA 22
+
static inline int fsr_fs(unsigned int fsr)
{
return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
diff --git a/kernel/arch/arm/plat-samsung/devs.c b/kernel/arch/arm/plat-samsung/devs.c
index 82074625d..e212f9d80 100644
--- a/kernel/arch/arm/plat-samsung/devs.c
+++ b/kernel/arch/arm/plat-samsung/devs.c
@@ -65,6 +65,7 @@
#include <linux/platform_data/usb-ohci-s3c2410.h>
#include <plat/usb-phy.h>
#include <plat/regs-spi.h>
+#include <linux/platform_data/asoc-s3c.h>
#include <linux/platform_data/spi-s3c64xx.h>
static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
@@ -74,9 +75,12 @@ static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
static struct resource s3c_ac97_resource[] = {
[0] = DEFINE_RES_MEM(S3C2440_PA_AC97, S3C2440_SZ_AC97),
[1] = DEFINE_RES_IRQ(IRQ_S3C244X_AC97),
- [2] = DEFINE_RES_DMA_NAMED(DMACH_PCM_OUT, "PCM out"),
- [3] = DEFINE_RES_DMA_NAMED(DMACH_PCM_IN, "PCM in"),
- [4] = DEFINE_RES_DMA_NAMED(DMACH_MIC_IN, "Mic in"),
+};
+
+static struct s3c_audio_pdata s3c_ac97_pdata = {
+ .dma_playback = (void *)DMACH_PCM_OUT,
+ .dma_capture = (void *)DMACH_PCM_IN,
+ .dma_capture_mic = (void *)DMACH_MIC_IN,
};
struct platform_device s3c_device_ac97 = {
@@ -87,6 +91,7 @@ struct platform_device s3c_device_ac97 = {
.dev = {
.dma_mask = &samsung_device_dma_mask,
.coherent_dma_mask = DMA_BIT_MASK(32),
+ .platform_data = &s3c_ac97_pdata,
}
};
#endif /* CONFIG_CPU_S3C2440 */
diff --git a/kernel/arch/arm/xen/enlighten.c b/kernel/arch/arm/xen/enlighten.c
index fc7ea529f..52c8c1f64 100644
--- a/kernel/arch/arm/xen/enlighten.c
+++ b/kernel/arch/arm/xen/enlighten.c
@@ -239,8 +239,7 @@ static int __init xen_guest_init(void)
* for secondary CPUs as they are brought up.
* For uniformity we use VCPUOP_register_vcpu_info even on cpu0.
*/
- xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info),
- sizeof(struct vcpu_info));
+ xen_vcpu_info = alloc_percpu(struct vcpu_info);
if (xen_vcpu_info == NULL)
return -ENOMEM;
diff --git a/kernel/arch/arm64/Kconfig b/kernel/arch/arm64/Kconfig
index 1baa6537c..9196cf82f 100644
--- a/kernel/arch/arm64/Kconfig
+++ b/kernel/arch/arm64/Kconfig
@@ -392,6 +392,15 @@ config CAVIUM_ERRATUM_22375
If unsure, say Y.
+config CAVIUM_ERRATUM_23144
+ bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+ depends on NUMA
+ default y
+ help
+ ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_23154
bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
default y
@@ -402,6 +411,17 @@ config CAVIUM_ERRATUM_23154
If unsure, say Y.
+config CAVIUM_ERRATUM_27456
+ bool "Cavium erratum 27456: Broadcast TLBI instructions may cause icache corruption"
+ default y
+ help
+ On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI
+ instructions may cause the icache to become corrupted if it
+ contains data for a non-current ASID. The fix is to
+ invalidate the icache when changing the mm context.
+
+ If unsure, say Y.
+
endmenu
diff --git a/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index cc093a482..e0ee2b00d 100644
--- a/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -262,6 +262,8 @@
#io-channel-cells = <1>;
clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
clock-names = "saradc", "apb_pclk";
+ resets = <&cru SRST_SARADC>;
+ reset-names = "saradc-apb";
status = "disabled";
};
@@ -517,7 +519,7 @@
#address-cells = <0>;
reg = <0x0 0xffb71000 0x0 0x1000>,
- <0x0 0xffb72000 0x0 0x1000>,
+ <0x0 0xffb72000 0x0 0x2000>,
<0x0 0xffb74000 0x0 0x2000>,
<0x0 0xffb76000 0x0 0x2000>;
interrupts = <GIC_PPI 9
diff --git a/kernel/arch/arm64/crypto/aes-ce-ccm-core.S b/kernel/arch/arm64/crypto/aes-ce-ccm-core.S
index a2a7fbcac..3363560c7 100644
--- a/kernel/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/kernel/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
.text
.arch armv8-a+crypto
@@ -19,7 +20,7 @@
*/
ENTRY(ce_aes_ccm_auth_data)
ldr w8, [x3] /* leftover from prev round? */
- ld1 {v0.2d}, [x0] /* load mac */
+ ld1 {v0.16b}, [x0] /* load mac */
cbz w8, 1f
sub w8, w8, #16
eor v1.16b, v1.16b, v1.16b
@@ -31,7 +32,7 @@ ENTRY(ce_aes_ccm_auth_data)
beq 8f /* out of input? */
cbnz w8, 0b
eor v0.16b, v0.16b, v1.16b
-1: ld1 {v3.2d}, [x4] /* load first round key */
+1: ld1 {v3.16b}, [x4] /* load first round key */
prfm pldl1strm, [x1]
cmp w5, #12 /* which key size? */
add x6, x4, #16
@@ -41,17 +42,17 @@ ENTRY(ce_aes_ccm_auth_data)
mov v5.16b, v3.16b
b 4f
2: mov v4.16b, v3.16b
- ld1 {v5.2d}, [x6], #16 /* load 2nd round key */
+ ld1 {v5.16b}, [x6], #16 /* load 2nd round key */
3: aese v0.16b, v4.16b
aesmc v0.16b, v0.16b
-4: ld1 {v3.2d}, [x6], #16 /* load next round key */
+4: ld1 {v3.16b}, [x6], #16 /* load next round key */
aese v0.16b, v5.16b
aesmc v0.16b, v0.16b
-5: ld1 {v4.2d}, [x6], #16 /* load next round key */
+5: ld1 {v4.16b}, [x6], #16 /* load next round key */
subs w7, w7, #3
aese v0.16b, v3.16b
aesmc v0.16b, v0.16b
- ld1 {v5.2d}, [x6], #16 /* load next round key */
+ ld1 {v5.16b}, [x6], #16 /* load next round key */
bpl 3b
aese v0.16b, v4.16b
subs w2, w2, #16 /* last data? */
@@ -60,7 +61,7 @@ ENTRY(ce_aes_ccm_auth_data)
ld1 {v1.16b}, [x1], #16 /* load next input block */
eor v0.16b, v0.16b, v1.16b /* xor with mac */
bne 1b
-6: st1 {v0.2d}, [x0] /* store mac */
+6: st1 {v0.16b}, [x0] /* store mac */
beq 10f
adds w2, w2, #16
beq 10f
@@ -79,7 +80,7 @@ ENTRY(ce_aes_ccm_auth_data)
adds w7, w7, #1
bne 9b
eor v0.16b, v0.16b, v1.16b
- st1 {v0.2d}, [x0]
+ st1 {v0.16b}, [x0]
10: str w8, [x3]
ret
ENDPROC(ce_aes_ccm_auth_data)
@@ -89,27 +90,27 @@ ENDPROC(ce_aes_ccm_auth_data)
* u32 rounds);
*/
ENTRY(ce_aes_ccm_final)
- ld1 {v3.2d}, [x2], #16 /* load first round key */
- ld1 {v0.2d}, [x0] /* load mac */
+ ld1 {v3.16b}, [x2], #16 /* load first round key */
+ ld1 {v0.16b}, [x0] /* load mac */
cmp w3, #12 /* which key size? */
sub w3, w3, #2 /* modified # of rounds */
- ld1 {v1.2d}, [x1] /* load 1st ctriv */
+ ld1 {v1.16b}, [x1] /* load 1st ctriv */
bmi 0f
bne 3f
mov v5.16b, v3.16b
b 2f
0: mov v4.16b, v3.16b
-1: ld1 {v5.2d}, [x2], #16 /* load next round key */
+1: ld1 {v5.16b}, [x2], #16 /* load next round key */
aese v0.16b, v4.16b
aesmc v0.16b, v0.16b
aese v1.16b, v4.16b
aesmc v1.16b, v1.16b
-2: ld1 {v3.2d}, [x2], #16 /* load next round key */
+2: ld1 {v3.16b}, [x2], #16 /* load next round key */
aese v0.16b, v5.16b
aesmc v0.16b, v0.16b
aese v1.16b, v5.16b
aesmc v1.16b, v1.16b
-3: ld1 {v4.2d}, [x2], #16 /* load next round key */
+3: ld1 {v4.16b}, [x2], #16 /* load next round key */
subs w3, w3, #3
aese v0.16b, v3.16b
aesmc v0.16b, v0.16b
@@ -120,47 +121,47 @@ ENTRY(ce_aes_ccm_final)
aese v1.16b, v4.16b
/* final round key cancels out */
eor v0.16b, v0.16b, v1.16b /* en-/decrypt the mac */
- st1 {v0.2d}, [x0] /* store result */
+ st1 {v0.16b}, [x0] /* store result */
ret
ENDPROC(ce_aes_ccm_final)
.macro aes_ccm_do_crypt,enc
ldr x8, [x6, #8] /* load lower ctr */
- ld1 {v0.2d}, [x5] /* load mac */
- rev x8, x8 /* keep swabbed ctr in reg */
+ ld1 {v0.16b}, [x5] /* load mac */
+CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */
0: /* outer loop */
- ld1 {v1.1d}, [x6] /* load upper ctr */
+ ld1 {v1.8b}, [x6] /* load upper ctr */
prfm pldl1strm, [x1]
add x8, x8, #1
rev x9, x8
cmp w4, #12 /* which key size? */
sub w7, w4, #2 /* get modified # of rounds */
ins v1.d[1], x9 /* no carry in lower ctr */
- ld1 {v3.2d}, [x3] /* load first round key */
+ ld1 {v3.16b}, [x3] /* load first round key */
add x10, x3, #16
bmi 1f
bne 4f
mov v5.16b, v3.16b
b 3f
1: mov v4.16b, v3.16b
- ld1 {v5.2d}, [x10], #16 /* load 2nd round key */
+ ld1 {v5.16b}, [x10], #16 /* load 2nd round key */
2: /* inner loop: 3 rounds, 2x interleaved */
aese v0.16b, v4.16b
aesmc v0.16b, v0.16b
aese v1.16b, v4.16b
aesmc v1.16b, v1.16b
-3: ld1 {v3.2d}, [x10], #16 /* load next round key */
+3: ld1 {v3.16b}, [x10], #16 /* load next round key */
aese v0.16b, v5.16b
aesmc v0.16b, v0.16b
aese v1.16b, v5.16b
aesmc v1.16b, v1.16b
-4: ld1 {v4.2d}, [x10], #16 /* load next round key */
+4: ld1 {v4.16b}, [x10], #16 /* load next round key */
subs w7, w7, #3
aese v0.16b, v3.16b
aesmc v0.16b, v0.16b
aese v1.16b, v3.16b
aesmc v1.16b, v1.16b
- ld1 {v5.2d}, [x10], #16 /* load next round key */
+ ld1 {v5.16b}, [x10], #16 /* load next round key */
bpl 2b
aese v0.16b, v4.16b
aese v1.16b, v4.16b
@@ -177,14 +178,14 @@ ENDPROC(ce_aes_ccm_final)
eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */
st1 {v1.16b}, [x0], #16 /* write output block */
bne 0b
- rev x8, x8
- st1 {v0.2d}, [x5] /* store mac */
+CPU_LE( rev x8, x8 )
+ st1 {v0.16b}, [x5] /* store mac */
str x8, [x6, #8] /* store lsb end of ctr (BE) */
5: ret
6: eor v0.16b, v0.16b, v5.16b /* final round mac */
eor v1.16b, v1.16b, v5.16b /* final round enc */
- st1 {v0.2d}, [x5] /* store mac */
+ st1 {v0.16b}, [x5] /* store mac */
add w2, w2, #16 /* process partial tail block */
7: ldrb w9, [x1], #1 /* get 1 byte of input */
umov w6, v1.b[0] /* get top crypted ctr byte */
diff --git a/kernel/arch/arm64/crypto/aes-ce-cipher.c b/kernel/arch/arm64/crypto/aes-ce-cipher.c
index f7bd9bf0b..50d9fe11d 100644
--- a/kernel/arch/arm64/crypto/aes-ce-cipher.c
+++ b/kernel/arch/arm64/crypto/aes-ce-cipher.c
@@ -47,24 +47,24 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
kernel_neon_begin_partial(4);
__asm__(" ld1 {v0.16b}, %[in] ;"
- " ld1 {v1.2d}, [%[key]], #16 ;"
+ " ld1 {v1.16b}, [%[key]], #16 ;"
" cmp %w[rounds], #10 ;"
" bmi 0f ;"
" bne 3f ;"
" mov v3.16b, v1.16b ;"
" b 2f ;"
"0: mov v2.16b, v1.16b ;"
- " ld1 {v3.2d}, [%[key]], #16 ;"
+ " ld1 {v3.16b}, [%[key]], #16 ;"
"1: aese v0.16b, v2.16b ;"
" aesmc v0.16b, v0.16b ;"
- "2: ld1 {v1.2d}, [%[key]], #16 ;"
+ "2: ld1 {v1.16b}, [%[key]], #16 ;"
" aese v0.16b, v3.16b ;"
" aesmc v0.16b, v0.16b ;"
- "3: ld1 {v2.2d}, [%[key]], #16 ;"
+ "3: ld1 {v2.16b}, [%[key]], #16 ;"
" subs %w[rounds], %w[rounds], #3 ;"
" aese v0.16b, v1.16b ;"
" aesmc v0.16b, v0.16b ;"
- " ld1 {v3.2d}, [%[key]], #16 ;"
+ " ld1 {v3.16b}, [%[key]], #16 ;"
" bpl 1b ;"
" aese v0.16b, v2.16b ;"
" eor v0.16b, v0.16b, v3.16b ;"
@@ -92,24 +92,24 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
kernel_neon_begin_partial(4);
__asm__(" ld1 {v0.16b}, %[in] ;"
- " ld1 {v1.2d}, [%[key]], #16 ;"
+ " ld1 {v1.16b}, [%[key]], #16 ;"
" cmp %w[rounds], #10 ;"
" bmi 0f ;"
" bne 3f ;"
" mov v3.16b, v1.16b ;"
" b 2f ;"
"0: mov v2.16b, v1.16b ;"
- " ld1 {v3.2d}, [%[key]], #16 ;"
+ " ld1 {v3.16b}, [%[key]], #16 ;"
"1: aesd v0.16b, v2.16b ;"
" aesimc v0.16b, v0.16b ;"
- "2: ld1 {v1.2d}, [%[key]], #16 ;"
+ "2: ld1 {v1.16b}, [%[key]], #16 ;"
" aesd v0.16b, v3.16b ;"
" aesimc v0.16b, v0.16b ;"
- "3: ld1 {v2.2d}, [%[key]], #16 ;"
+ "3: ld1 {v2.16b}, [%[key]], #16 ;"
" subs %w[rounds], %w[rounds], #3 ;"
" aesd v0.16b, v1.16b ;"
" aesimc v0.16b, v0.16b ;"
- " ld1 {v3.2d}, [%[key]], #16 ;"
+ " ld1 {v3.16b}, [%[key]], #16 ;"
" bpl 1b ;"
" aesd v0.16b, v2.16b ;"
" eor v0.16b, v0.16b, v3.16b ;"
@@ -173,7 +173,12 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
u32 *rki = ctx->key_enc + (i * kwords);
u32 *rko = rki + kwords;
+#ifndef CONFIG_CPU_BIG_ENDIAN
rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+#else
+ rko[0] = rol32(aes_sub(rki[kwords - 1]), 8) ^ (rcon[i] << 24) ^
+ rki[0];
+#endif
rko[1] = rko[0] ^ rki[1];
rko[2] = rko[1] ^ rki[2];
rko[3] = rko[2] ^ rki[3];
diff --git a/kernel/arch/arm64/crypto/aes-ce.S b/kernel/arch/arm64/crypto/aes-ce.S
index 78f3cfe92..b46093d56 100644
--- a/kernel/arch/arm64/crypto/aes-ce.S
+++ b/kernel/arch/arm64/crypto/aes-ce.S
@@ -10,6 +10,7 @@
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
#define AES_ENTRY(func) ENTRY(ce_ ## func)
#define AES_ENDPROC(func) ENDPROC(ce_ ## func)
diff --git a/kernel/arch/arm64/crypto/aes-glue.c b/kernel/arch/arm64/crypto/aes-glue.c
index 05d9e16c0..6a51dfccf 100644
--- a/kernel/arch/arm64/crypto/aes-glue.c
+++ b/kernel/arch/arm64/crypto/aes-glue.c
@@ -211,7 +211,7 @@ 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/kernel/arch/arm64/crypto/aes-modes.S b/kernel/arch/arm64/crypto/aes-modes.S
index f6e372c52..838dad5c2 100644
--- a/kernel/arch/arm64/crypto/aes-modes.S
+++ b/kernel/arch/arm64/crypto/aes-modes.S
@@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt)
cbz w6, .Lcbcencloop
ld1 {v0.16b}, [x5] /* get iv */
- enc_prepare w3, x2, x5
+ enc_prepare w3, x2, x6
.Lcbcencloop:
ld1 {v1.16b}, [x1], #16 /* get next pt block */
eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */
- encrypt_block v0, w3, x2, x5, w6
+ encrypt_block v0, w3, x2, x6, w7
st1 {v0.16b}, [x0], #16
subs w4, w4, #1
bne .Lcbcencloop
+ st1 {v0.16b}, [x5] /* return iv */
ret
AES_ENDPROC(aes_cbc_encrypt)
@@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt)
cbz w6, .LcbcdecloopNx
ld1 {v7.16b}, [x5] /* get iv */
- dec_prepare w3, x2, x5
+ dec_prepare w3, x2, x6
.LcbcdecloopNx:
#if INTERLEAVE >= 2
@@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt)
.Lcbcdecloop:
ld1 {v1.16b}, [x1], #16 /* get next ct block */
mov v0.16b, v1.16b /* ...and copy to v0 */
- decrypt_block v0, w3, x2, x5, w6
+ decrypt_block v0, w3, x2, x6, w7
eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */
mov v7.16b, v1.16b /* ct is next iv */
st1 {v0.16b}, [x0], #16
@@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt)
bne .Lcbcdecloop
.Lcbcdecout:
FRAME_POP
+ st1 {v7.16b}, [x5] /* return iv */
ret
AES_ENDPROC(aes_cbc_decrypt)
@@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt)
AES_ENTRY(aes_ctr_encrypt)
FRAME_PUSH
- cbnz w6, .Lctrfirst /* 1st time around? */
- umov x5, v4.d[1] /* keep swabbed ctr in reg */
- rev x5, x5
-#if INTERLEAVE >= 2
- cmn w5, w4 /* 32 bit overflow? */
- bcs .Lctrinc
- add x5, x5, #1 /* increment BE ctr */
- b .LctrincNx
-#else
- b .Lctrinc
-#endif
-.Lctrfirst:
+ cbz w6, .Lctrnotfirst /* 1st time around? */
enc_prepare w3, x2, x6
ld1 {v4.16b}, [x5]
- umov x5, v4.d[1] /* keep swabbed ctr in reg */
- rev x5, x5
+
+.Lctrnotfirst:
+ umov x8, v4.d[1] /* keep swabbed ctr in reg */
+ rev x8, x8
#if INTERLEAVE >= 2
- cmn w5, w4 /* 32 bit overflow? */
+ cmn w8, w4 /* 32 bit overflow? */
bcs .Lctrloop
.LctrloopNx:
subs w4, w4, #INTERLEAVE
@@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt)
#if INTERLEAVE == 2
mov v0.8b, v4.8b
mov v1.8b, v4.8b
- rev x7, x5
- add x5, x5, #1
+ rev x7, x8
+ add x8, x8, #1
ins v0.d[1], x7
- rev x7, x5
- add x5, x5, #1
+ rev x7, x8
+ add x8, x8, #1
ins v1.d[1], x7
ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */
do_encrypt_block2x
@@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt)
st1 {v0.16b-v1.16b}, [x0], #32
#else
ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */
- dup v7.4s, w5
+ dup v7.4s, w8
mov v0.16b, v4.16b
add v7.4s, v7.4s, v8.4s
mov v1.16b, v4.16b
@@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt)
eor v2.16b, v7.16b, v2.16b
eor v3.16b, v5.16b, v3.16b
st1 {v0.16b-v3.16b}, [x0], #64
- add x5, x5, #INTERLEAVE
+ add x8, x8, #INTERLEAVE
#endif
- cbz w4, .LctroutNx
-.LctrincNx:
- rev x7, x5
+ rev x7, x8
ins v4.d[1], x7
+ cbz w4, .Lctrout
b .LctrloopNx
-.LctroutNx:
- sub x5, x5, #1
- rev x7, x5
- ins v4.d[1], x7
- b .Lctrout
.Lctr1x:
adds w4, w4, #INTERLEAVE
beq .Lctrout
@@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt)
.Lctrloop:
mov v0.16b, v4.16b
encrypt_block v0, w3, x2, x6, w7
+
+ adds x8, x8, #1 /* increment BE ctr */
+ rev x7, x8
+ ins v4.d[1], x7
+ bcs .Lctrcarry /* overflow? */
+
+.Lctrcarrydone:
subs w4, w4, #1
bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */
ld1 {v3.16b}, [x1], #16
eor v3.16b, v0.16b, v3.16b
st1 {v3.16b}, [x0], #16
- beq .Lctrout
-.Lctrinc:
- adds x5, x5, #1 /* increment BE ctr */
- rev x7, x5
- ins v4.d[1], x7
- bcc .Lctrloop /* no overflow? */
- umov x7, v4.d[0] /* load upper word of ctr */
- rev x7, x7 /* ... to handle the carry */
- add x7, x7, #1
- rev x7, x7
- ins v4.d[0], x7
- b .Lctrloop
+ bne .Lctrloop
+
+.Lctrout:
+ st1 {v4.16b}, [x5] /* return next CTR value */
+ FRAME_POP
+ ret
+
.Lctrhalfblock:
ld1 {v3.8b}, [x1]
eor v3.8b, v0.8b, v3.8b
st1 {v3.8b}, [x0]
-.Lctrout:
FRAME_POP
ret
+
+.Lctrcarry:
+ umov x7, v4.d[0] /* load upper word of ctr */
+ rev x7, x7 /* ... to handle the carry */
+ add x7, x7, #1
+ rev x7, x7
+ ins v4.d[0], x7
+ b .Lctrcarrydone
AES_ENDPROC(aes_ctr_encrypt)
.ltorg
@@ -386,7 +382,8 @@ AES_ENDPROC(aes_ctr_encrypt)
.endm
.Lxts_mul_x:
- .word 1, 0, 0x87, 0
+CPU_LE( .quad 1, 0x87 )
+CPU_BE( .quad 0x87, 1 )
AES_ENTRY(aes_xts_encrypt)
FRAME_PUSH
diff --git a/kernel/arch/arm64/crypto/aes-neon.S b/kernel/arch/arm64/crypto/aes-neon.S
index b93170e1c..85f07ead7 100644
--- a/kernel/arch/arm64/crypto/aes-neon.S
+++ b/kernel/arch/arm64/crypto/aes-neon.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
#define AES_ENTRY(func) ENTRY(neon_ ## func)
#define AES_ENDPROC(func) ENDPROC(neon_ ## func)
@@ -83,13 +84,13 @@
.endm
.macro do_block, enc, in, rounds, rk, rkp, i
- ld1 {v15.16b}, [\rk]
+ ld1 {v15.4s}, [\rk]
add \rkp, \rk, #16
mov \i, \rounds
1111: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
tbl \in\().16b, {\in\().16b}, v13.16b /* ShiftRows */
sub_bytes \in
- ld1 {v15.16b}, [\rkp], #16
+ ld1 {v15.4s}, [\rkp], #16
subs \i, \i, #1
beq 2222f
.if \enc == 1
@@ -229,7 +230,7 @@
.endm
.macro do_block_2x, enc, in0, in1 rounds, rk, rkp, i
- ld1 {v15.16b}, [\rk]
+ ld1 {v15.4s}, [\rk]
add \rkp, \rk, #16
mov \i, \rounds
1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
@@ -237,7 +238,7 @@
sub_bytes_2x \in0, \in1
tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
- ld1 {v15.16b}, [\rkp], #16
+ ld1 {v15.4s}, [\rkp], #16
subs \i, \i, #1
beq 2222f
.if \enc == 1
@@ -254,7 +255,7 @@
.endm
.macro do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
- ld1 {v15.16b}, [\rk]
+ ld1 {v15.4s}, [\rk]
add \rkp, \rk, #16
mov \i, \rounds
1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
@@ -266,7 +267,7 @@
tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
tbl \in2\().16b, {\in2\().16b}, v13.16b /* ShiftRows */
tbl \in3\().16b, {\in3\().16b}, v13.16b /* ShiftRows */
- ld1 {v15.16b}, [\rkp], #16
+ ld1 {v15.4s}, [\rkp], #16
subs \i, \i, #1
beq 2222f
.if \enc == 1
@@ -306,12 +307,16 @@
.text
.align 4
.LForward_ShiftRows:
- .byte 0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
- .byte 0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+CPU_LE( .byte 0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3 )
+CPU_LE( .byte 0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb )
+CPU_BE( .byte 0xb, 0x6, 0x1, 0xc, 0x7, 0x2, 0xd, 0x8 )
+CPU_BE( .byte 0x3, 0xe, 0x9, 0x4, 0xf, 0xa, 0x5, 0x0 )
.LReverse_ShiftRows:
- .byte 0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
- .byte 0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+CPU_LE( .byte 0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb )
+CPU_LE( .byte 0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3 )
+CPU_BE( .byte 0x3, 0x6, 0x9, 0xc, 0xf, 0x2, 0x5, 0x8 )
+CPU_BE( .byte 0xb, 0xe, 0x1, 0x4, 0x7, 0xa, 0xd, 0x0 )
.LForward_Sbox:
.byte 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
diff --git a/kernel/arch/arm64/crypto/ghash-ce-core.S b/kernel/arch/arm64/crypto/ghash-ce-core.S
index dc4570158..f0bb9f0b5 100644
--- a/kernel/arch/arm64/crypto/ghash-ce-core.S
+++ b/kernel/arch/arm64/crypto/ghash-ce-core.S
@@ -29,8 +29,8 @@
* struct ghash_key const *k, const char *head)
*/
ENTRY(pmull_ghash_update)
- ld1 {SHASH.16b}, [x3]
- ld1 {XL.16b}, [x1]
+ ld1 {SHASH.2d}, [x3]
+ ld1 {XL.2d}, [x1]
movi MASK.16b, #0xe1
ext SHASH2.16b, SHASH.16b, SHASH.16b, #8
shl MASK.2d, MASK.2d, #57
@@ -74,6 +74,6 @@ CPU_LE( rev64 T1.16b, T1.16b )
cbnz w0, 0b
- st1 {XL.16b}, [x1]
+ st1 {XL.2d}, [x1]
ret
ENDPROC(pmull_ghash_update)
diff --git a/kernel/arch/arm64/crypto/sha1-ce-core.S b/kernel/arch/arm64/crypto/sha1-ce-core.S
index 033aae6d7..c98e7e849 100644
--- a/kernel/arch/arm64/crypto/sha1-ce-core.S
+++ b/kernel/arch/arm64/crypto/sha1-ce-core.S
@@ -78,7 +78,7 @@ ENTRY(sha1_ce_transform)
ld1r {k3.4s}, [x6]
/* load state */
- ldr dga, [x0]
+ ld1 {dgav.4s}, [x0]
ldr dgb, [x0, #16]
/* load sha1_ce_state::finalize */
@@ -144,7 +144,7 @@ CPU_LE( rev32 v11.16b, v11.16b )
b 1b
/* store new state */
-3: str dga, [x0]
+3: st1 {dgav.4s}, [x0]
str dgb, [x0, #16]
ret
ENDPROC(sha1_ce_transform)
diff --git a/kernel/arch/arm64/crypto/sha2-ce-core.S b/kernel/arch/arm64/crypto/sha2-ce-core.S
index 5df9d9d47..01cfee066 100644
--- a/kernel/arch/arm64/crypto/sha2-ce-core.S
+++ b/kernel/arch/arm64/crypto/sha2-ce-core.S
@@ -85,7 +85,7 @@ ENTRY(sha2_ce_transform)
ld1 {v12.4s-v15.4s}, [x8]
/* load state */
- ldp dga, dgb, [x0]
+ ld1 {dgav.4s, dgbv.4s}, [x0]
/* load sha256_ce_state::finalize */
ldr w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
@@ -148,6 +148,6 @@ CPU_LE( rev32 v19.16b, v19.16b )
b 1b
/* store new state */
-3: stp dga, dgb, [x0]
+3: st1 {dgav.4s, dgbv.4s}, [x0]
ret
ENDPROC(sha2_ce_transform)
diff --git a/kernel/arch/arm64/include/asm/arch_gicv3.h b/kernel/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b25..8ec88e5b2 100644
--- a/kernel/arch/arm64/include/asm/arch_gicv3.h
+++ b/kernel/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
u64 irqstat;
asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+ dsb(sy);
return irqstat;
}
diff --git a/kernel/arch/arm64/include/asm/cpufeature.h b/kernel/arch/arm64/include/asm/cpufeature.h
index 8f271b83f..8884b5d5f 100644
--- a/kernel/arch/arm64/include/asm/cpufeature.h
+++ b/kernel/arch/arm64/include/asm/cpufeature.h
@@ -30,8 +30,9 @@
#define ARM64_HAS_LSE_ATOMICS 5
#define ARM64_WORKAROUND_CAVIUM_23154 6
#define ARM64_WORKAROUND_834220 7
+#define ARM64_WORKAROUND_CAVIUM_27456 8
-#define ARM64_NCAPS 8
+#define ARM64_NCAPS 9
#ifndef __ASSEMBLY__
@@ -76,7 +77,7 @@ struct arm64_cpu_capabilities {
const char *desc;
u16 capability;
bool (*matches)(const struct arm64_cpu_capabilities *);
- void (*enable)(void *); /* Called on all active CPUs */
+ int (*enable)(void *); /* Called on all active CPUs */
union {
struct { /* To be used for erratum handling only */
u32 midr_model;
diff --git a/kernel/arch/arm64/include/asm/elf.h b/kernel/arch/arm64/include/asm/elf.h
index faad6df49..44dd892a4 100644
--- a/kernel/arch/arm64/include/asm/elf.h
+++ b/kernel/arch/arm64/include/asm/elf.h
@@ -136,6 +136,7 @@ typedef struct user_fpsimd_state elf_fpregset_t;
#define SET_PERSONALITY(ex) clear_thread_flag(TIF_32BIT);
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
#define ARCH_DLINFO \
do { \
NEW_AUX_ENT(AT_SYSINFO_EHDR, \
@@ -156,14 +157,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
#define STACK_RND_MASK (0x3ffff >> (PAGE_SHIFT - 12))
#endif
-#ifdef CONFIG_COMPAT
-
#ifdef __AARCH64EB__
#define COMPAT_ELF_PLATFORM ("v8b")
#else
#define COMPAT_ELF_PLATFORM ("v8l")
#endif
+#ifdef CONFIG_COMPAT
+
#define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3)
/* AArch32 registers. */
diff --git a/kernel/arch/arm64/include/asm/futex.h b/kernel/arch/arm64/include/asm/futex.h
index 007a69fc4..5f3ab8c1d 100644
--- a/kernel/arch/arm64/include/asm/futex.h
+++ b/kernel/arch/arm64/include/asm/futex.h
@@ -121,6 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
return -EFAULT;
asm volatile("// futex_atomic_cmpxchg_inatomic\n"
+ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
" prfm pstl1strm, %2\n"
"1: ldxr %w1, %2\n"
" sub %w3, %w1, %w4\n"
@@ -137,6 +138,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
" .align 3\n"
" .quad 1b, 4b, 2b, 4b\n"
" .popsection\n"
+ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
: "memory");
diff --git a/kernel/arch/arm64/include/asm/kvm_arm.h b/kernel/arch/arm64/include/asm/kvm_arm.h
index 5e6857b6b..2d960f858 100644
--- a/kernel/arch/arm64/include/asm/kvm_arm.h
+++ b/kernel/arch/arm64/include/asm/kvm_arm.h
@@ -107,8 +107,6 @@
#define TCR_EL2_MASK (TCR_EL2_TG0 | TCR_EL2_SH0 | \
TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
-#define TCR_EL2_FLAGS (TCR_EL2_RES1 | TCR_EL2_PS_40B)
-
/* VTCR_EL2 Registers bits */
#define VTCR_EL2_RES1 (1 << 31)
#define VTCR_EL2_PS_MASK (7 << 16)
diff --git a/kernel/arch/arm64/include/asm/opcodes.h b/kernel/arch/arm64/include/asm/opcodes.h
index 4e603ea36..123f45d92 100644
--- a/kernel/arch/arm64/include/asm/opcodes.h
+++ b/kernel/arch/arm64/include/asm/opcodes.h
@@ -1 +1,5 @@
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN
+#endif
+
#include <../../arm/include/asm/opcodes.h>
diff --git a/kernel/arch/arm64/include/asm/percpu.h b/kernel/arch/arm64/include/asm/percpu.h
index 0a456bef8..8a336852e 100644
--- a/kernel/arch/arm64/include/asm/percpu.h
+++ b/kernel/arch/arm64/include/asm/percpu.h
@@ -44,48 +44,44 @@ static inline unsigned long __percpu_##op(void *ptr, \
\
switch (size) { \
case 1: \
- do { \
- asm ("//__per_cpu_" #op "_1\n" \
- "ldxrb %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_1\n" \
+ "1: ldxrb %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxrb %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u8 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxrb %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u8 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 2: \
- do { \
- asm ("//__per_cpu_" #op "_2\n" \
- "ldxrh %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_2\n" \
+ "1: ldxrh %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxrh %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u16 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxrh %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u16 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 4: \
- do { \
- asm ("//__per_cpu_" #op "_4\n" \
- "ldxr %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_4\n" \
+ "1: ldxr %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxr %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u32 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxr %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u32 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 8: \
- do { \
- asm ("//__per_cpu_" #op "_8\n" \
- "ldxr %[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_8\n" \
+ "1: ldxr %[ret], %[ptr]\n" \
#asm_op " %[ret], %[ret], %[val]\n" \
- "stxr %w[loop], %[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u64 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxr %w[loop], %[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u64 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
default: \
BUILD_BUG(); \
@@ -150,44 +146,40 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
switch (size) {
case 1:
- do {
- asm ("//__percpu_xchg_1\n"
- "ldxrb %w[ret], %[ptr]\n"
- "stxrb %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u8 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_1\n"
+ "1: ldxrb %w[ret], %[ptr]\n"
+ " stxrb %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u8 *)ptr)
+ : [val] "r" (val));
break;
case 2:
- do {
- asm ("//__percpu_xchg_2\n"
- "ldxrh %w[ret], %[ptr]\n"
- "stxrh %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u16 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_2\n"
+ "1: ldxrh %w[ret], %[ptr]\n"
+ " stxrh %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u16 *)ptr)
+ : [val] "r" (val));
break;
case 4:
- do {
- asm ("//__percpu_xchg_4\n"
- "ldxr %w[ret], %[ptr]\n"
- "stxr %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u32 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_4\n"
+ "1: ldxr %w[ret], %[ptr]\n"
+ " stxr %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u32 *)ptr)
+ : [val] "r" (val));
break;
case 8:
- do {
- asm ("//__percpu_xchg_8\n"
- "ldxr %[ret], %[ptr]\n"
- "stxr %w[loop], %[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u64 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_8\n"
+ "1: ldxr %[ret], %[ptr]\n"
+ " stxr %w[loop], %[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u64 *)ptr)
+ : [val] "r" (val));
break;
default:
BUILD_BUG();
diff --git a/kernel/arch/arm64/include/asm/pgtable-hwdef.h b/kernel/arch/arm64/include/asm/pgtable-hwdef.h
index d6739e836..b9da9545b 100644
--- a/kernel/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/kernel/arch/arm64/include/asm/pgtable-hwdef.h
@@ -117,7 +117,6 @@
* Section
*/
#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_PROT_NONE (_AT(pmdval_t, 1) << 58)
#define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */
#define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */
#define PMD_SECT_S (_AT(pmdval_t, 3) << 8)
diff --git a/kernel/arch/arm64/include/asm/pgtable.h b/kernel/arch/arm64/include/asm/pgtable.h
index eaa9cabf4..67c2ad6d3 100644
--- a/kernel/arch/arm64/include/asm/pgtable.h
+++ b/kernel/arch/arm64/include/asm/pgtable.h
@@ -69,11 +69,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
-#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
-#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT))
-#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
+#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
#define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
#define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -83,7 +83,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
@@ -155,6 +155,7 @@ extern struct page *empty_zero_page;
#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))
#ifdef CONFIG_ARM64_HW_AFDBM
#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -165,8 +166,6 @@ extern struct page *empty_zero_page;
#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte))
#define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_user(pte) \
- ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
#define pte_valid_not_user(pte) \
((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
@@ -264,13 +263,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
- if (pte_valid_user(pte)) {
- if (!pte_special(pte) && pte_exec(pte))
- __sync_icache_dcache(pte, addr);
+ if (pte_present(pte)) {
if (pte_sw_dirty(pte) && pte_write(pte))
pte_val(pte) &= ~PTE_RDONLY;
else
pte_val(pte) |= PTE_RDONLY;
+ if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+ __sync_icache_dcache(pte, addr);
}
/*
@@ -348,6 +347,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmd_present(pmd) pte_present(pmd_pte(pmd))
#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd))
#define pmd_young(pmd) pte_young(pmd_pte(pmd))
#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd)))
@@ -356,7 +356,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd)))
#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd)))
#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
+#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_SECT_VALID))
#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
@@ -395,7 +395,6 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot);
#define pmd_none(pmd) (!pmd_val(pmd))
-#define pmd_present(pmd) (pmd_val(pmd))
#define pmd_bad(pmd) (!(pmd_val(pmd) & 2))
@@ -539,6 +538,21 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
}
#ifdef CONFIG_ARM64_HW_AFDBM
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep,
+ pte_t entry, int dirty);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp,
+ pmd_t entry, int dirty)
+{
+ return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
+}
+#endif
+
/*
* Atomic pte/pmd modifications.
*/
@@ -591,9 +605,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
- unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+ unsigned long address, pmd_t *pmdp)
{
return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
}
@@ -641,6 +655,7 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
* bits 0-1: present (must be zero)
* bits 2-7: swap type
* bits 8-57: swap offset
+ * bit 58: PTE_PROT_NONE (must be zero)
*/
#define __SWP_TYPE_SHIFT 2
#define __SWP_TYPE_BITS 6
diff --git a/kernel/arch/arm64/include/asm/processor.h b/kernel/arch/arm64/include/asm/processor.h
index 4acb7ca94..d08559528 100644
--- a/kernel/arch/arm64/include/asm/processor.h
+++ b/kernel/arch/arm64/include/asm/processor.h
@@ -186,6 +186,6 @@ static inline void spin_lock_prefetch(const void *x)
#endif
-void cpu_enable_pan(void *__unused);
+int cpu_enable_pan(void *__unused);
#endif /* __ASM_PROCESSOR_H */
diff --git a/kernel/arch/arm64/include/asm/ptrace.h b/kernel/arch/arm64/include/asm/ptrace.h
index e9e5467e0..7f9475508 100644
--- a/kernel/arch/arm64/include/asm/ptrace.h
+++ b/kernel/arch/arm64/include/asm/ptrace.h
@@ -58,6 +58,7 @@
#define COMPAT_PSR_Z_BIT 0x40000000
#define COMPAT_PSR_N_BIT 0x80000000
#define COMPAT_PSR_IT_MASK 0x0600fc00 /* If-Then execution state mask */
+#define COMPAT_PSR_GE_MASK 0x000f0000
#ifdef CONFIG_CPU_BIG_ENDIAN
#define COMPAT_PSR_ENDSTATE COMPAT_PSR_E_BIT
@@ -116,6 +117,8 @@ struct pt_regs {
};
u64 orig_x0;
u64 syscallno;
+ u64 orig_addr_limit;
+ u64 unused; // maintain 16 byte alignment
};
#define arch_has_single_step() (1)
@@ -151,35 +154,9 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
return regs->regs[0];
}
-/*
- * Are the current registers suitable for user mode? (used to maintain
- * security in signal handlers)
- */
-static inline int valid_user_regs(struct user_pt_regs *regs)
-{
- if (user_mode(regs) && (regs->pstate & PSR_I_BIT) == 0) {
- regs->pstate &= ~(PSR_F_BIT | PSR_A_BIT);
-
- /* The T bit is reserved for AArch64 */
- if (!(regs->pstate & PSR_MODE32_BIT))
- regs->pstate &= ~COMPAT_PSR_T_BIT;
-
- return 1;
- }
-
- /*
- * Force PSR to something logical...
- */
- regs->pstate &= PSR_f | PSR_s | (PSR_x & ~PSR_A_BIT) | \
- COMPAT_PSR_T_BIT | PSR_MODE32_BIT;
-
- if (!(regs->pstate & PSR_MODE32_BIT)) {
- regs->pstate &= ~COMPAT_PSR_T_BIT;
- regs->pstate |= PSR_MODE_EL0t;
- }
-
- return 0;
-}
+/* We must avoid circular header include via sched.h */
+struct task_struct;
+int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
#define instruction_pointer(regs) ((unsigned long)(regs)->pc)
diff --git a/kernel/arch/arm64/include/asm/spinlock.h b/kernel/arch/arm64/include/asm/spinlock.h
index c85e96d17..499e8de33 100644
--- a/kernel/arch/arm64/include/asm/spinlock.h
+++ b/kernel/arch/arm64/include/asm/spinlock.h
@@ -312,4 +312,14 @@ 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/kernel/arch/arm64/include/uapi/asm/auxvec.h b/kernel/arch/arm64/include/uapi/asm/auxvec.h
index 22d6d8885..4cf0c1778 100644
--- a/kernel/arch/arm64/include/uapi/asm/auxvec.h
+++ b/kernel/arch/arm64/include/uapi/asm/auxvec.h
@@ -19,4 +19,6 @@
/* vDSO location */
#define AT_SYSINFO_EHDR 33
+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
#endif
diff --git a/kernel/arch/arm64/include/uapi/asm/ptrace.h b/kernel/arch/arm64/include/uapi/asm/ptrace.h
index 208db3df1..3378238b5 100644
--- a/kernel/arch/arm64/include/uapi/asm/ptrace.h
+++ b/kernel/arch/arm64/include/uapi/asm/ptrace.h
@@ -76,6 +76,7 @@ struct user_fpsimd_state {
__uint128_t vregs[32];
__u32 fpsr;
__u32 fpcr;
+ __u32 __reserved[2];
};
struct user_hwdebug_state {
diff --git a/kernel/arch/arm64/kernel/asm-offsets.c b/kernel/arch/arm64/kernel/asm-offsets.c
index c5038409e..d74475928 100644
--- a/kernel/arch/arm64/kernel/asm-offsets.c
+++ b/kernel/arch/arm64/kernel/asm-offsets.c
@@ -59,6 +59,7 @@ int main(void)
DEFINE(S_PC, offsetof(struct pt_regs, pc));
DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0));
DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno));
+ DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit));
DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
BLANK();
DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter));
diff --git a/kernel/arch/arm64/kernel/cpu_errata.c b/kernel/arch/arm64/kernel/cpu_errata.c
index feb6b4efa..a3e846a28 100644
--- a/kernel/arch/arm64/kernel/cpu_errata.c
+++ b/kernel/arch/arm64/kernel/cpu_errata.c
@@ -100,6 +100,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01),
},
#endif
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+ {
+ /* Cavium ThunderX, T88 pass 1.x - 2.1 */
+ .desc = "Cavium erratum 27456",
+ .capability = ARM64_WORKAROUND_CAVIUM_27456,
+ MIDR_RANGE(MIDR_THUNDERX, 0x00,
+ (1 << MIDR_VARIANT_SHIFT) | 1),
+ },
+#endif
{
}
};
diff --git a/kernel/arch/arm64/kernel/cpufeature.c b/kernel/arch/arm64/kernel/cpufeature.c
index 0669c6328..2735bf814 100644
--- a/kernel/arch/arm64/kernel/cpufeature.c
+++ b/kernel/arch/arm64/kernel/cpufeature.c
@@ -19,7 +19,9 @@
#define pr_fmt(fmt) "CPU features: " fmt
#include <linux/bsearch.h>
+#include <linux/cpumask.h>
#include <linux/sort.h>
+#include <linux/stop_machine.h>
#include <linux/types.h>
#include <asm/cpu.h>
#include <asm/cpufeature.h>
@@ -764,7 +766,13 @@ static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
for (i = 0; caps[i].desc; i++)
if (caps[i].enable && cpus_have_cap(caps[i].capability))
- on_each_cpu(caps[i].enable, NULL, true);
+ /*
+ * Use stop_machine() as it schedules the work allowing
+ * us to modify PSTATE, instead of on_each_cpu() which
+ * uses an IPI, giving us a PSTATE that disappears when
+ * we return.
+ */
+ stop_machine(caps[i].enable, NULL, cpu_online_mask);
}
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/kernel/arch/arm64/kernel/cpuinfo.c b/kernel/arch/arm64/kernel/cpuinfo.c
index 212ae6361..0166cfbc8 100644
--- a/kernel/arch/arm64/kernel/cpuinfo.c
+++ b/kernel/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
#include <linux/bitops.h>
#include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/personality.h>
@@ -85,7 +87,8 @@ static const char *const compat_hwcap_str[] = {
"idivt",
"vfpd32",
"lpae",
- "evtstrm"
+ "evtstrm",
+ NULL
};
static const char *const compat_hwcap2_str[] = {
@@ -101,6 +104,7 @@ static const char *const compat_hwcap2_str[] = {
static int c_show(struct seq_file *m, void *v)
{
int i, j;
+ bool compat = personality(current->personality) == PER_LINUX32;
for_each_online_cpu(i) {
struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -112,6 +116,9 @@ static int c_show(struct seq_file *m, void *v)
* "processor". Give glibc what it expects.
*/
seq_printf(m, "processor\t: %d\n", i);
+ if (compat)
+ seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+ MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
loops_per_jiffy / (500000UL/HZ),
@@ -124,7 +131,7 @@ static int c_show(struct seq_file *m, void *v)
* software which does already (at least for 32-bit).
*/
seq_puts(m, "Features\t:");
- if (personality(current->personality) == PER_LINUX32) {
+ if (compat) {
#ifdef CONFIG_COMPAT
for (j = 0; compat_hwcap_str[j]; j++)
if (compat_elf_hwcap & (1 << j))
diff --git a/kernel/arch/arm64/kernel/debug-monitors.c b/kernel/arch/arm64/kernel/debug-monitors.c
index c1492ba1f..c8875b64b 100644
--- a/kernel/arch/arm64/kernel/debug-monitors.c
+++ b/kernel/arch/arm64/kernel/debug-monitors.c
@@ -152,7 +152,6 @@ static int debug_monitors_init(void)
/* Clear the OS lock. */
on_each_cpu(clear_os_lock, NULL, 1);
isb();
- local_dbg_enable();
/* Register hotplug handler. */
__register_cpu_notifier(&os_lock_nb);
@@ -423,8 +422,10 @@ int kernel_active_single_step(void)
/* 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));
}
void user_disable_single_step(struct task_struct *task)
diff --git a/kernel/arch/arm64/kernel/entry.S b/kernel/arch/arm64/kernel/entry.S
index dd8fd31f8..cf92d4ee5 100644
--- a/kernel/arch/arm64/kernel/entry.S
+++ b/kernel/arch/arm64/kernel/entry.S
@@ -27,6 +27,7 @@
#include <asm/cpufeature.h>
#include <asm/errno.h>
#include <asm/esr.h>
+#include <asm/memory.h>
#include <asm/thread_info.h>
#include <asm/unistd.h>
@@ -93,7 +94,13 @@
disable_step_tsk x19, x20 // exceptions when scheduling.
.else
add x21, sp, #S_FRAME_SIZE
- .endif
+ get_thread_info tsk
+ /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+ ldr x20, [tsk, #TI_ADDR_LIMIT]
+ str x20, [sp, #S_ORIG_ADDR_LIMIT]
+ mov x20, #TASK_SIZE_64
+ str x20, [tsk, #TI_ADDR_LIMIT]
+ .endif /* \el == 0 */
mrs x22, elr_el1
mrs x23, spsr_el1
stp lr, x21, [sp, #S_LR]
@@ -117,6 +124,12 @@
.endm
.macro kernel_exit, el
+ .if \el != 0
+ /* Restore the task's original addr_limit. */
+ ldr x20, [sp, #S_ORIG_ADDR_LIMIT]
+ str x20, [tsk, #TI_ADDR_LIMIT]
+ .endif
+
ldp x21, x22, [sp, #S_PC] // load ELR, SPSR
.if \el == 0
ct_user_enter
@@ -555,7 +568,7 @@ el0_inv:
mov x0, sp
mov x1, #BAD_SYNC
mov x2, x25
- bl bad_mode
+ bl bad_el0_sync
b ret_to_user
ENDPROC(el0_sync)
diff --git a/kernel/arch/arm64/kernel/head.S b/kernel/arch/arm64/kernel/head.S
index b68525792..20ceb5edf 100644
--- a/kernel/arch/arm64/kernel/head.S
+++ b/kernel/arch/arm64/kernel/head.S
@@ -518,8 +518,9 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems
b.lt 4f // Skip if no PMU present
mrs x0, pmcr_el0 // Disable debug access traps
ubfx x0, x0, #11, #5 // to EL2 and allow access to
- msr mdcr_el2, x0 // all PMU counters from EL1
4:
+ csel x0, xzr, x0, lt // all PMU counters from EL1
+ msr mdcr_el2, x0 // (if they exist)
/* Stage-2 translation */
msr vttbr_el2, xzr
diff --git a/kernel/arch/arm64/kernel/ptrace.c b/kernel/arch/arm64/kernel/ptrace.c
index ff7f13239..55909b220 100644
--- a/kernel/arch/arm64/kernel/ptrace.c
+++ b/kernel/arch/arm64/kernel/ptrace.c
@@ -39,6 +39,7 @@
#include <linux/elf.h>
#include <asm/compat.h>
+#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
#include <asm/pgtable.h>
#include <asm/syscall.h>
@@ -449,6 +450,8 @@ static int hw_break_set(struct task_struct *target,
/* (address, ctrl) registers */
limit = regset->n * regset->size;
while (count && offset < limit) {
+ if (count < PTRACE_HBP_ADDR_SZ)
+ return -EINVAL;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr,
offset, offset + PTRACE_HBP_ADDR_SZ);
if (ret)
@@ -458,6 +461,8 @@ static int hw_break_set(struct task_struct *target,
return ret;
offset += PTRACE_HBP_ADDR_SZ;
+ if (!count)
+ break;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl,
offset, offset + PTRACE_HBP_CTRL_SZ);
if (ret)
@@ -494,13 +499,13 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct user_pt_regs newregs;
+ struct user_pt_regs newregs = task_pt_regs(target)->user_regs;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1);
if (ret)
return ret;
- if (!valid_user_regs(&newregs))
+ if (!valid_user_regs(&newregs, target))
return -EINVAL;
task_pt_regs(target)->user_regs = newregs;
@@ -524,7 +529,8 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct user_fpsimd_state newstate;
+ struct user_fpsimd_state newstate =
+ target->thread.fpsimd_state.user_fpsimd;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
if (ret)
@@ -548,7 +554,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
const void *kbuf, const void __user *ubuf)
{
int ret;
- unsigned long tls;
+ unsigned long tls = target->thread.tp_value;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
if (ret)
@@ -574,7 +580,8 @@ static int system_call_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- int syscallno, ret;
+ int syscallno = task_pt_regs(target)->syscallno;
+ int ret;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1);
if (ret)
@@ -770,7 +777,7 @@ static int compat_gpr_set(struct task_struct *target,
}
- if (valid_user_regs(&newregs.user_regs))
+ if (valid_user_regs(&newregs.user_regs, target))
*task_pt_regs(target) = newregs;
else
ret = -EINVAL;
@@ -846,7 +853,7 @@ static int compat_tls_set(struct task_struct *target,
const void __user *ubuf)
{
int ret;
- compat_ulong_t tls;
+ compat_ulong_t tls = target->thread.tp_value;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
if (ret)
@@ -1272,3 +1279,79 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs)
if (test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
}
+
+/*
+ * Bits which are always architecturally RES0 per ARM DDI 0487A.h
+ * Userspace cannot use these until they have an architectural meaning.
+ * We also reserve IL for the kernel; SS is handled dynamically.
+ */
+#define SPSR_EL1_AARCH64_RES0_BITS \
+ (GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \
+ GENMASK_ULL(5, 5))
+#define SPSR_EL1_AARCH32_RES0_BITS \
+ (GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20))
+
+static int valid_compat_regs(struct user_pt_regs *regs)
+{
+ regs->pstate &= ~SPSR_EL1_AARCH32_RES0_BITS;
+
+ if (!system_supports_mixed_endian_el0()) {
+ if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+ regs->pstate |= COMPAT_PSR_E_BIT;
+ else
+ regs->pstate &= ~COMPAT_PSR_E_BIT;
+ }
+
+ if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) &&
+ (regs->pstate & COMPAT_PSR_A_BIT) == 0 &&
+ (regs->pstate & COMPAT_PSR_I_BIT) == 0 &&
+ (regs->pstate & COMPAT_PSR_F_BIT) == 0) {
+ return 1;
+ }
+
+ /*
+ * Force PSR to a valid 32-bit EL0t, preserving the same bits as
+ * arch/arm.
+ */
+ regs->pstate &= COMPAT_PSR_N_BIT | COMPAT_PSR_Z_BIT |
+ COMPAT_PSR_C_BIT | COMPAT_PSR_V_BIT |
+ COMPAT_PSR_Q_BIT | COMPAT_PSR_IT_MASK |
+ COMPAT_PSR_GE_MASK | COMPAT_PSR_E_BIT |
+ COMPAT_PSR_T_BIT;
+ regs->pstate |= PSR_MODE32_BIT;
+
+ return 0;
+}
+
+static int valid_native_regs(struct user_pt_regs *regs)
+{
+ regs->pstate &= ~SPSR_EL1_AARCH64_RES0_BITS;
+
+ if (user_mode(regs) && !(regs->pstate & PSR_MODE32_BIT) &&
+ (regs->pstate & PSR_D_BIT) == 0 &&
+ (regs->pstate & PSR_A_BIT) == 0 &&
+ (regs->pstate & PSR_I_BIT) == 0 &&
+ (regs->pstate & PSR_F_BIT) == 0) {
+ return 1;
+ }
+
+ /* Force PSR to a valid 64-bit EL0t */
+ regs->pstate &= PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT;
+
+ return 0;
+}
+
+/*
+ * Are the current registers suitable for user mode? (used to maintain
+ * security in signal handlers)
+ */
+int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
+{
+ if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
+ regs->pstate &= ~DBG_SPSR_SS;
+
+ if (is_compat_thread(task_thread_info(task)))
+ return valid_compat_regs(regs);
+ else
+ return valid_native_regs(regs);
+}
diff --git a/kernel/arch/arm64/kernel/signal.c b/kernel/arch/arm64/kernel/signal.c
index e18c48cb6..a8eafdbc7 100644
--- a/kernel/arch/arm64/kernel/signal.c
+++ b/kernel/arch/arm64/kernel/signal.c
@@ -115,7 +115,7 @@ static int restore_sigframe(struct pt_regs *regs,
*/
regs->syscallno = ~0UL;
- err |= !valid_user_regs(&regs->user_regs);
+ err |= !valid_user_regs(&regs->user_regs, current);
if (err == 0) {
struct fpsimd_context *fpsimd_ctx =
@@ -307,7 +307,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
/*
* Check that the resulting registers are actually sane.
*/
- ret |= !valid_user_regs(&regs->user_regs);
+ ret |= !valid_user_regs(&regs->user_regs, current);
/*
* Fast forward the stepping logic so we step into the signal
diff --git a/kernel/arch/arm64/kernel/signal32.c b/kernel/arch/arm64/kernel/signal32.c
index 71ef6dc89..107335637 100644
--- a/kernel/arch/arm64/kernel/signal32.c
+++ b/kernel/arch/arm64/kernel/signal32.c
@@ -356,7 +356,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
*/
regs->syscallno = ~0UL;
- err |= !valid_user_regs(&regs->user_regs);
+ err |= !valid_user_regs(&regs->user_regs, current);
aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace;
if (err == 0)
diff --git a/kernel/arch/arm64/kernel/smp.c b/kernel/arch/arm64/kernel/smp.c
index b1adc51b2..f3c3d8fee 100644
--- a/kernel/arch/arm64/kernel/smp.c
+++ b/kernel/arch/arm64/kernel/smp.c
@@ -188,7 +188,6 @@ asmlinkage void secondary_start_kernel(void)
set_cpu_online(cpu, true);
complete(&cpu_running);
- local_dbg_enable();
local_irq_enable();
local_async_enable();
@@ -334,8 +333,8 @@ void __init smp_cpus_done(unsigned int max_cpus)
void __init smp_prepare_boot_cpu(void)
{
- cpuinfo_store_boot_cpu();
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+ cpuinfo_store_boot_cpu();
}
static u64 __init of_get_cpu_mpidr(struct device_node *dn)
diff --git a/kernel/arch/arm64/kernel/suspend.c b/kernel/arch/arm64/kernel/suspend.c
index 1095aa483..00c1372bf 100644
--- a/kernel/arch/arm64/kernel/suspend.c
+++ b/kernel/arch/arm64/kernel/suspend.c
@@ -1,7 +1,9 @@
#include <linux/ftrace.h>
#include <linux/percpu.h>
#include <linux/slab.h>
+#include <asm/alternative.h>
#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
#include <asm/pgtable.h>
#include <asm/memory.h>
@@ -111,6 +113,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
/*
+ * PSTATE was not saved over suspend/resume, re-enable any
+ * detected features that might not have been set correctly.
+ */
+ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+ CONFIG_ARM64_PAN));
+
+ /*
* Restore HW breakpoint registers to sane values
* before debug exceptions are possibly reenabled
* through local_dbg_restore.
diff --git a/kernel/arch/arm64/kernel/traps.c b/kernel/arch/arm64/kernel/traps.c
index e9b9b5364..ca7f0ac5f 100644
--- a/kernel/arch/arm64/kernel/traps.c
+++ b/kernel/arch/arm64/kernel/traps.c
@@ -434,16 +434,33 @@ const char *esr_get_class_string(u32 esr)
}
/*
- * bad_mode handles the impossible case in the exception vector.
+ * bad_mode handles the impossible case in the exception vector. This is always
+ * fatal.
*/
asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
{
- siginfo_t info;
- void __user *pc = (void __user *)instruction_pointer(regs);
console_verbose();
pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
handler[reason], esr, esr_get_class_string(esr));
+
+ die("Oops - bad mode", regs, 0);
+ local_irq_disable();
+ panic("bad mode");
+}
+
+/*
+ * bad_el0_sync handles unexpected, but potentially recoverable synchronous
+ * exceptions taken from EL0. Unlike bad_mode, this returns.
+ */
+asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+{
+ siginfo_t info;
+ void __user *pc = (void __user *)instruction_pointer(regs);
+ console_verbose();
+
+ pr_crit("Bad EL0 synchronous exception detected on CPU%d, code 0x%08x -- %s\n",
+ smp_processor_id(), esr, esr_get_class_string(esr));
__show_regs(regs);
info.si_signo = SIGILL;
@@ -451,7 +468,10 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
info.si_code = ILL_ILLOPC;
info.si_addr = pc;
- arm64_notify_die("Oops - bad mode", regs, &info, 0);
+ current->thread.fault_address = 0;
+ current->thread.fault_code = 0;
+
+ force_sig_info(info.si_signo, &info, current);
}
void __pte_error(const char *file, int line, unsigned long val)
diff --git a/kernel/arch/arm64/kvm/hyp-init.S b/kernel/arch/arm64/kvm/hyp-init.S
index 178ba2248..84c338f01 100644
--- a/kernel/arch/arm64/kvm/hyp-init.S
+++ b/kernel/arch/arm64/kvm/hyp-init.S
@@ -64,7 +64,7 @@ __do_hyp_init:
mrs x4, tcr_el1
ldr x5, =TCR_EL2_MASK
and x4, x4, x5
- ldr x5, =TCR_EL2_FLAGS
+ mov x5, #TCR_EL2_RES1
orr x4, x4, x5
#ifndef CONFIG_ARM64_VA_BITS_48
@@ -85,15 +85,18 @@ __do_hyp_init:
ldr_l x5, idmap_t0sz
bfi x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
#endif
- msr tcr_el2, x4
-
- ldr x4, =VTCR_EL2_FLAGS
/*
* Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
- * VTCR_EL2.
+ * TCR_EL2 and VTCR_EL2.
*/
mrs x5, ID_AA64MMFR0_EL1
bfi x4, x5, #16, #3
+
+ msr tcr_el2, x4
+
+ ldr x4, =VTCR_EL2_FLAGS
+ bfi x4, x5, #16, #3
+
msr vtcr_el2, x4
mrs x4, mair_el1
diff --git a/kernel/arch/arm64/kvm/inject_fault.c b/kernel/arch/arm64/kvm/inject_fault.c
index 648112e90..3972e65fb 100644
--- a/kernel/arch/arm64/kvm/inject_fault.c
+++ b/kernel/arch/arm64/kvm/inject_fault.c
@@ -130,7 +130,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);
if (!is_iabt)
- esr |= ESR_ELx_EC_DABT_LOW;
+ esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT;
}
diff --git a/kernel/arch/arm64/mm/fault.c b/kernel/arch/arm64/mm/fault.c
index 92ddac1e8..247bae758 100644
--- a/kernel/arch/arm64/mm/fault.c
+++ b/kernel/arch/arm64/mm/fault.c
@@ -29,7 +29,9 @@
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>
+#include <linux/preempt.h>
+#include <asm/bug.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
#include <asm/debug-monitors.h>
@@ -81,6 +83,56 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
printk("\n");
}
+#ifdef CONFIG_ARM64_HW_AFDBM
+/*
+ * This function sets the access flags (dirty, accessed), as well as write
+ * permission, and only to a more permissive setting.
+ *
+ * It needs to cope with hardware update of the accessed/dirty state by other
+ * agents in the system and can safely skip the __sync_icache_dcache() call as,
+ * like set_pte_at(), the PTE is never changed from no-exec to exec here.
+ *
+ * Returns whether or not the PTE actually changed.
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep,
+ pte_t entry, int dirty)
+{
+ pteval_t old_pteval;
+ unsigned int tmp;
+
+ if (pte_same(*ptep, entry))
+ return 0;
+
+ /* only preserve the access flags and write permission */
+ pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
+
+ /*
+ * PTE_RDONLY is cleared by default in the asm below, so set it in
+ * back if necessary (read-only or clean PTE).
+ */
+ if (!pte_write(entry) || !pte_sw_dirty(entry))
+ pte_val(entry) |= PTE_RDONLY;
+
+ /*
+ * Setting the flags must be done atomically to avoid racing with the
+ * hardware update of the access/dirty state.
+ */
+ asm volatile("// ptep_set_access_flags\n"
+ " prfm pstl1strm, %2\n"
+ "1: ldxr %0, %2\n"
+ " and %0, %0, %3 // clear PTE_RDONLY\n"
+ " orr %0, %0, %4 // set flags\n"
+ " stxr %w1, %0, %2\n"
+ " cbnz %w1, 1b\n"
+ : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
+ : "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+
+ flush_tlb_fix_spurious_fault(vma, address);
+ return 1;
+}
+#endif
+
/*
* The kernel tried to access some page that wasn't present.
*/
@@ -556,8 +608,16 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
}
#ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
{
+ /*
+ * We modify PSTATE. This won't work from irq context as the PSTATE
+ * is discarded once we return from the exception.
+ */
+ WARN_ON_ONCE(in_interrupt());
+
config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+ asm(SET_PSTATE_PAN(1));
+ return 0;
}
#endif /* CONFIG_ARM64_PAN */
diff --git a/kernel/arch/arm64/mm/mmu.c b/kernel/arch/arm64/mm/mmu.c
index 116ad654d..653735a8c 100644
--- a/kernel/arch/arm64/mm/mmu.c
+++ b/kernel/arch/arm64/mm/mmu.c
@@ -652,9 +652,9 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
/*
* Check whether the physical FDT address is set and meets the minimum
* alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
- * at least 8 bytes so that we can always access the size field of the
- * FDT header after mapping the first chunk, double check here if that
- * is indeed the case.
+ * at least 8 bytes so that we can always access the magic and size
+ * fields of the FDT header after mapping the first chunk, double check
+ * here if that is indeed the case.
*/
BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
@@ -682,7 +682,7 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
SWAPPER_BLOCK_SIZE, prot);
- if (fdt_check_header(dt_virt) != 0)
+ if (fdt_magic(dt_virt) != FDT_MAGIC)
return NULL;
size = fdt_totalsize(dt_virt);
diff --git a/kernel/arch/arm64/mm/proc.S b/kernel/arch/arm64/mm/proc.S
index b8f04b3f2..18201e9e8 100644
--- a/kernel/arch/arm64/mm/proc.S
+++ b/kernel/arch/arm64/mm/proc.S
@@ -25,6 +25,8 @@
#include <asm/hwcap.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
#include "proc-macros.S"
@@ -137,7 +139,17 @@ 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
+ ic iallu
+ dsb nsh
+ isb
+ ret
+alternative_endif
ENDPROC(cpu_do_switch_mm)
.section ".text.init", #alloc, #execinstr
@@ -156,6 +168,8 @@ ENTRY(__cpu_setup)
msr cpacr_el1, x0 // Enable FP/ASIMD
mov x0, #1 << 12 // Reset mdscr_el1 and disable
msr mdscr_el1, x0 // access to the DCC from EL0
+ isb // Unmask debug exceptions now,
+ enable_dbg // since this is per-cpu
reset_pmuserenr_el0 x0 // Disable PMU access from EL0
/*
* Memory region attributes for LPAE:
diff --git a/kernel/arch/avr32/include/asm/uaccess.h b/kernel/arch/avr32/include/asm/uaccess.h
index 68cf638fa..b1ec1fa06 100644
--- a/kernel/arch/avr32/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/avr32/kernel/avr32_ksyms.c b/kernel/arch/avr32/kernel/avr32_ksyms.c
index d93ead02d..7c6cf14f0 100644
--- a/kernel/arch/avr32/kernel/avr32_ksyms.c
+++ b/kernel/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/kernel/arch/avr32/lib/copy_user.S b/kernel/arch/avr32/lib/copy_user.S
index ea59c04b0..075373471 100644
--- a/kernel/arch/avr32/lib/copy_user.S
+++ b/kernel/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/kernel/arch/avr32/mach-at32ap/pio.c b/kernel/arch/avr32/mach-at32ap/pio.c
index 4f61378c3..456128174 100644
--- a/kernel/arch/avr32/mach-at32ap/pio.c
+++ b/kernel/arch/avr32/mach-at32ap/pio.c
@@ -435,7 +435,7 @@ void __init at32_init_pio(struct platform_device *pdev)
struct resource *regs;
struct pio_device *pio;
- if (pdev->id > MAX_NR_PIO_DEVICES) {
+ if (pdev->id >= MAX_NR_PIO_DEVICES) {
dev_err(&pdev->dev, "only %d PIO devices supported\n",
MAX_NR_PIO_DEVICES);
return;
diff --git a/kernel/arch/blackfin/include/asm/uaccess.h b/kernel/arch/blackfin/include/asm/uaccess.h
index 90612a7f2..8cd0184ea 100644
--- a/kernel/arch/blackfin/include/asm/uaccess.h
+++ b/kernel/arch/blackfin/include/asm/uaccess.h
@@ -177,11 +177,12 @@ 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/kernel/arch/blackfin/mach-bf561/boards/cm_bf561.c b/kernel/arch/blackfin/mach-bf561/boards/cm_bf561.c
index c6db52ba3..10c577718 100644
--- a/kernel/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/kernel/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = {
#include <linux/smc91x.h>
static struct smc91x_platdata smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
.leda = RPC_LED_100_10,
.ledb = RPC_LED_TX_RX,
};
diff --git a/kernel/arch/blackfin/mach-bf561/boards/ezkit.c b/kernel/arch/blackfin/mach-bf561/boards/ezkit.c
index 2de71e8c1..93c22468c 100644
--- a/kernel/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/kernel/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = {
#include <linux/smc91x.h>
static struct smc91x_platdata smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
.leda = RPC_LED_100_10,
.ledb = RPC_LED_TX_RX,
};
diff --git a/kernel/arch/cris/boot/rescue/Makefile b/kernel/arch/cris/boot/rescue/Makefile
index 52bd0bd1d..d98edbb30 100644
--- a/kernel/arch/cris/boot/rescue/Makefile
+++ b/kernel/arch/cris/boot/rescue/Makefile
@@ -10,6 +10,9 @@
asflags-y += $(LINUXINCLUDE)
ccflags-y += -O2 $(LINUXINCLUDE)
+
+ifdef CONFIG_ETRAX_AXISFLASHMAP
+
arch-$(CONFIG_ETRAX_ARCH_V10) = v10
arch-$(CONFIG_ETRAX_ARCH_V32) = v32
@@ -28,6 +31,11 @@ $(obj)/rescue.bin: $(obj)/rescue.o FORCE
$(call if_changed,objcopy)
cp -p $(obj)/rescue.bin $(objtree)
+else
+$(obj)/rescue.bin:
+
+endif
+
$(obj)/testrescue.bin: $(obj)/testrescue.o
$(OBJCOPY) $(OBJCOPYFLAGS) $(obj)/testrescue.o tr.bin
# Pad it to 784 bytes
diff --git a/kernel/arch/cris/include/asm/uaccess.h b/kernel/arch/cris/include/asm/uaccess.h
index e3530d0f1..56c7d5750 100644
--- a/kernel/arch/cris/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/frv/include/asm/uaccess.h b/kernel/arch/frv/include/asm/uaccess.h
index 3ac9a59d6..87d9e34c5 100644
--- a/kernel/arch/frv/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/h8300/include/asm/thread_info.h b/kernel/arch/h8300/include/asm/thread_info.h
index b408fe660..3cef06875 100644
--- a/kernel/arch/h8300/include/asm/thread_info.h
+++ b/kernel/arch/h8300/include/asm/thread_info.h
@@ -31,7 +31,6 @@ struct thread_info {
int cpu; /* cpu we're on */
int preempt_count; /* 0 => preemptable, <0 => BUG */
mm_segment_t addr_limit;
- struct restart_block restart_block;
};
/*
@@ -44,9 +43,6 @@ struct thread_info {
.cpu = 0, \
.preempt_count = INIT_PREEMPT_COUNT, \
.addr_limit = KERNEL_DS, \
- .restart_block = { \
- .fn = do_no_restart_syscall, \
- }, \
}
#define init_thread_info (init_thread_union.thread_info)
diff --git a/kernel/arch/h8300/kernel/signal.c b/kernel/arch/h8300/kernel/signal.c
index 380fffd08..036ad04ed 100644
--- a/kernel/arch/h8300/kernel/signal.c
+++ b/kernel/arch/h8300/kernel/signal.c
@@ -79,7 +79,7 @@ restore_sigcontext(struct sigcontext *usc, int *pd0)
unsigned int er0;
/* Always make any pending restarted system calls return -EINTR */
- current_thread_info()->restart_block.fn = do_no_restart_syscall;
+ current->restart_block.fn = do_no_restart_syscall;
/* restore passed registers */
#define COPY(r) do { err |= get_user(regs->r, &usc->sc_##r); } while (0)
diff --git a/kernel/arch/hexagon/include/asm/uaccess.h b/kernel/arch/hexagon/include/asm/uaccess.h
index f000a382b..f61cfb28e 100644
--- a/kernel/arch/hexagon/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/ia64/include/asm/io.h b/kernel/arch/ia64/include/asm/io.h
index 9041bbe2b..8fdb9c7ee 100644
--- a/kernel/arch/ia64/include/asm/io.h
+++ b/kernel/arch/ia64/include/asm/io.h
@@ -436,6 +436,7 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo
return ioremap(phys_addr, size);
}
#define ioremap_cache ioremap_cache
+#define ioremap_uc ioremap_nocache
/*
diff --git a/kernel/arch/ia64/include/asm/uaccess.h b/kernel/arch/ia64/include/asm/uaccess.h
index 4f3fb6ccb..40c2027a2 100644
--- a/kernel/arch/ia64/include/asm/uaccess.h
+++ b/kernel/arch/ia64/include/asm/uaccess.h
@@ -263,17 +263,15 @@ __copy_from_user (void *to, const void __user *from, unsigned long count)
__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())) \
- __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)
+{
+ 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/kernel/arch/m32r/include/asm/uaccess.h b/kernel/arch/m32r/include/asm/uaccess.h
index cac7014da..6f8982157 100644
--- a/kernel/arch/m32r/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/m68k/include/asm/delay.h b/kernel/arch/m68k/include/asm/delay.h
index d28fa8fe2..c598d847d 100644
--- a/kernel/arch/m68k/include/asm/delay.h
+++ b/kernel/arch/m68k/include/asm/delay.h
@@ -114,6 +114,6 @@ static inline void __udelay(unsigned long usecs)
*/
#define HZSCALE (268435456 / (1000000 / HZ))
-#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000));
+#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000))
#endif /* defined(_M68K_DELAY_H) */
diff --git a/kernel/arch/metag/include/asm/atomic.h b/kernel/arch/metag/include/asm/atomic.h
index 470e365f0..8ff0a7086 100644
--- a/kernel/arch/metag/include/asm/atomic.h
+++ b/kernel/arch/metag/include/asm/atomic.h
@@ -39,11 +39,10 @@
#define atomic_dec(v) atomic_sub(1, (v))
#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
#endif
-#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
-
#include <asm-generic/atomic64.h>
#endif /* __ASM_METAG_ATOMIC_H */
diff --git a/kernel/arch/metag/include/asm/atomic_lnkget.h b/kernel/arch/metag/include/asm/atomic_lnkget.h
index a62581815..88fa25fae 100644
--- a/kernel/arch/metag/include/asm/atomic_lnkget.h
+++ b/kernel/arch/metag/include/asm/atomic_lnkget.h
@@ -61,7 +61,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \
" CMPT %0, #HI(0x02000000)\n" \
" BNZ 1b\n" \
: "=&d" (temp), "=&da" (result) \
- : "da" (&v->counter), "bd" (i) \
+ : "da" (&v->counter), "br" (i) \
: "cc"); \
\
smp_mb(); \
diff --git a/kernel/arch/metag/include/asm/cmpxchg_lnkget.h b/kernel/arch/metag/include/asm/cmpxchg_lnkget.h
index 0154e2807..2369ad394 100644
--- a/kernel/arch/metag/include/asm/cmpxchg_lnkget.h
+++ b/kernel/arch/metag/include/asm/cmpxchg_lnkget.h
@@ -73,7 +73,7 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
" DCACHE [%2], %0\n"
#endif
"2:\n"
- : "=&d" (temp), "=&da" (retval)
+ : "=&d" (temp), "=&d" (retval)
: "da" (m), "bd" (old), "da" (new)
: "cc"
);
diff --git a/kernel/arch/metag/include/asm/uaccess.h b/kernel/arch/metag/include/asm/uaccess.h
index 8282cbce7..273e61225 100644
--- a/kernel/arch/metag/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/microblaze/include/asm/uaccess.h b/kernel/arch/microblaze/include/asm/uaccess.h
index 331b0d35f..826676778 100644
--- a/kernel/arch/microblaze/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/mips/Kconfig.debug b/kernel/arch/mips/Kconfig.debug
index f0e314ceb..7f975b20b 100644
--- a/kernel/arch/mips/Kconfig.debug
+++ b/kernel/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/kernel/arch/mips/Makefile b/kernel/arch/mips/Makefile
index 3f70ba54a..252e34795 100644
--- a/kernel/arch/mips/Makefile
+++ b/kernel/arch/mips/Makefile
@@ -204,10 +204,6 @@ toolchain-msa := $(call cc-option-yn,$(mips-cflags) -mhard-float -mfp64 -Wa$(
cflags-$(toolchain-msa) += -DTOOLCHAIN_SUPPORTS_MSA
endif
-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/kernel/arch/mips/alchemy/devboards/db1000.c b/kernel/arch/mips/alchemy/devboards/db1000.c
index bdeed9d13..433c4b9a9 100644
--- a/kernel/arch/mips/alchemy/devboards/db1000.c
+++ b/kernel/arch/mips/alchemy/devboards/db1000.c
@@ -503,15 +503,15 @@ int __init db1000_dev_setup(void)
if (board == BCSR_WHOAMI_DB1500) {
c0 = AU1500_GPIO2_INT;
c1 = AU1500_GPIO5_INT;
- d0 = AU1500_GPIO0_INT;
- d1 = AU1500_GPIO3_INT;
+ d0 = 0; /* GPIO number, NOT irq! */
+ d1 = 3; /* GPIO number, NOT irq! */
s0 = AU1500_GPIO1_INT;
s1 = AU1500_GPIO4_INT;
} else if (board == BCSR_WHOAMI_DB1100) {
c0 = AU1100_GPIO2_INT;
c1 = AU1100_GPIO5_INT;
- d0 = AU1100_GPIO0_INT;
- d1 = AU1100_GPIO3_INT;
+ d0 = 0; /* GPIO number, NOT irq! */
+ d1 = 3; /* GPIO number, NOT irq! */
s0 = AU1100_GPIO1_INT;
s1 = AU1100_GPIO4_INT;
@@ -545,15 +545,15 @@ int __init db1000_dev_setup(void)
} else if (board == BCSR_WHOAMI_DB1000) {
c0 = AU1000_GPIO2_INT;
c1 = AU1000_GPIO5_INT;
- d0 = AU1000_GPIO0_INT;
- d1 = AU1000_GPIO3_INT;
+ d0 = 0; /* GPIO number, NOT irq! */
+ d1 = 3; /* GPIO number, NOT irq! */
s0 = AU1000_GPIO1_INT;
s1 = AU1000_GPIO4_INT;
platform_add_devices(db1000_devs, ARRAY_SIZE(db1000_devs));
} else if ((board == BCSR_WHOAMI_PB1500) ||
(board == BCSR_WHOAMI_PB1500R2)) {
c0 = AU1500_GPIO203_INT;
- d0 = AU1500_GPIO201_INT;
+ d0 = 1; /* GPIO number, NOT irq! */
s0 = AU1500_GPIO202_INT;
twosocks = 0;
flashsize = 64;
@@ -566,7 +566,7 @@ int __init db1000_dev_setup(void)
*/
} else if (board == BCSR_WHOAMI_PB1100) {
c0 = AU1100_GPIO11_INT;
- d0 = AU1100_GPIO9_INT;
+ d0 = 9; /* GPIO number, NOT irq! */
s0 = AU1100_GPIO10_INT;
twosocks = 0;
flashsize = 64;
@@ -583,7 +583,6 @@ int __init db1000_dev_setup(void)
} else
return 0; /* unknown board, no further dev setup to do */
- irq_set_irq_type(d0, IRQ_TYPE_EDGE_BOTH);
irq_set_irq_type(c0, IRQ_TYPE_LEVEL_LOW);
irq_set_irq_type(s0, IRQ_TYPE_LEVEL_LOW);
@@ -597,7 +596,6 @@ int __init db1000_dev_setup(void)
c0, d0, /*s0*/0, 0, 0);
if (twosocks) {
- irq_set_irq_type(d1, IRQ_TYPE_EDGE_BOTH);
irq_set_irq_type(c1, IRQ_TYPE_LEVEL_LOW);
irq_set_irq_type(s1, IRQ_TYPE_LEVEL_LOW);
diff --git a/kernel/arch/mips/alchemy/devboards/db1550.c b/kernel/arch/mips/alchemy/devboards/db1550.c
index 5740bcfdf..6c37b9326 100644
--- a/kernel/arch/mips/alchemy/devboards/db1550.c
+++ b/kernel/arch/mips/alchemy/devboards/db1550.c
@@ -514,7 +514,7 @@ static void __init db1550_devices(void)
AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
AU1000_PCMCIA_IO_PHYS_ADDR,
AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
- AU1550_GPIO3_INT, AU1550_GPIO0_INT,
+ AU1550_GPIO3_INT, 0,
/*AU1550_GPIO21_INT*/0, 0, 0);
db1x_register_pcmcia_socket(
@@ -524,7 +524,7 @@ static void __init db1550_devices(void)
AU1000_PCMCIA_MEM_PHYS_ADDR + 0x004400000 - 1,
AU1000_PCMCIA_IO_PHYS_ADDR + 0x004000000,
AU1000_PCMCIA_IO_PHYS_ADDR + 0x004010000 - 1,
- AU1550_GPIO5_INT, AU1550_GPIO1_INT,
+ AU1550_GPIO5_INT, 1,
/*AU1550_GPIO22_INT*/0, 0, 1);
platform_device_register(&db1550_nand_dev);
diff --git a/kernel/arch/mips/ath79/early_printk.c b/kernel/arch/mips/ath79/early_printk.c
index b955fafc5..d1adc59af 100644
--- a/kernel/arch/mips/ath79/early_printk.c
+++ b/kernel/arch/mips/ath79/early_printk.c
@@ -31,13 +31,15 @@ static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
} while (1);
}
+#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
+
static void prom_putchar_ar71xx(unsigned char ch)
{
void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE));
- prom_putchar_wait(base + UART_LSR * 4, UART_LSR_THRE, UART_LSR_THRE);
+ prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
__raw_writel(ch, base + UART_TX * 4);
- prom_putchar_wait(base + UART_LSR * 4, UART_LSR_THRE, UART_LSR_THRE);
+ prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
}
static void prom_putchar_ar933x(unsigned char ch)
diff --git a/kernel/arch/mips/include/asm/asmmacro.h b/kernel/arch/mips/include/asm/asmmacro.h
index 867f924b0..8dedee1de 100644
--- a/kernel/arch/mips/include/asm/asmmacro.h
+++ b/kernel/arch/mips/include/asm/asmmacro.h
@@ -135,6 +135,7 @@
ldc1 $f28, THREAD_FPR28(\thread)
ldc1 $f30, THREAD_FPR30(\thread)
ctc1 \tmp, fcr31
+ .set pop
.endm
.macro fpu_restore_16odd thread
@@ -298,21 +299,21 @@
.set pop
.endm
- .macro copy_u_w ws, n
+ .macro copy_s_w ws, n
.set push
.set mips32r2
.set fp=64
.set msa
- copy_u.w $1, $w\ws[\n]
+ copy_s.w $1, $w\ws[\n]
.set pop
.endm
- .macro copy_u_d ws, n
+ .macro copy_s_d ws, n
.set push
.set mips64r2
.set fp=64
.set msa
- copy_u.d $1, $w\ws[\n]
+ copy_s.d $1, $w\ws[\n]
.set pop
.endm
@@ -346,8 +347,8 @@
#define STH_MSA_INSN 0x5800081f
#define STW_MSA_INSN 0x5800082f
#define STD_MSA_INSN 0x5800083f
-#define COPY_UW_MSA_INSN 0x58f00056
-#define COPY_UD_MSA_INSN 0x58f80056
+#define COPY_SW_MSA_INSN 0x58b00056
+#define COPY_SD_MSA_INSN 0x58b80056
#define INSERT_W_MSA_INSN 0x59300816
#define INSERT_D_MSA_INSN 0x59380816
#else
@@ -361,8 +362,8 @@
#define STH_MSA_INSN 0x78000825
#define STW_MSA_INSN 0x78000826
#define STD_MSA_INSN 0x78000827
-#define COPY_UW_MSA_INSN 0x78f00059
-#define COPY_UD_MSA_INSN 0x78f80059
+#define COPY_SW_MSA_INSN 0x78b00059
+#define COPY_SD_MSA_INSN 0x78b80059
#define INSERT_W_MSA_INSN 0x79300819
#define INSERT_D_MSA_INSN 0x79380819
#endif
@@ -393,7 +394,7 @@
.set push
.set noat
SET_HARDFLOAT
- addu $1, \base, \off
+ PTR_ADDU $1, \base, \off
.word LDB_MSA_INSN | (\wd << 6)
.set pop
.endm
@@ -402,7 +403,7 @@
.set push
.set noat
SET_HARDFLOAT
- addu $1, \base, \off
+ PTR_ADDU $1, \base, \off
.word LDH_MSA_INSN | (\wd << 6)
.set pop
.endm
@@ -411,7 +412,7 @@
.set push
.set noat
SET_HARDFLOAT
- addu $1, \base, \off
+ PTR_ADDU $1, \base, \off
.word LDW_MSA_INSN | (\wd << 6)
.set pop
.endm
@@ -420,7 +421,7 @@
.set push
.set noat
SET_HARDFLOAT
- addu $1, \base, \off
+ PTR_ADDU $1, \base, \off
.word LDD_MSA_INSN | (\wd << 6)
.set pop
.endm
@@ -429,7 +430,7 @@
.set push
.set noat
SET_HARDFLOAT
- addu $1, \base, \off
+ PTR_ADDU $1, \base, \off
.word STB_MSA_INSN | (\wd << 6)
.set pop
.endm
@@ -438,7 +439,7 @@
.set push
.set noat
SET_HARDFLOAT
- addu $1, \base, \off
+ PTR_ADDU $1, \base, \off
.word STH_MSA_INSN | (\wd << 6)
.set pop
.endm
@@ -447,7 +448,7 @@
.set push
.set noat
SET_HARDFLOAT
- addu $1, \base, \off
+ PTR_ADDU $1, \base, \off
.word STW_MSA_INSN | (\wd << 6)
.set pop
.endm
@@ -456,26 +457,26 @@
.set push
.set noat
SET_HARDFLOAT
- addu $1, \base, \off
+ PTR_ADDU $1, \base, \off
.word STD_MSA_INSN | (\wd << 6)
.set pop
.endm
- .macro copy_u_w ws, n
+ .macro copy_s_w ws, n
.set push
.set noat
SET_HARDFLOAT
.insn
- .word COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11)
+ .word COPY_SW_MSA_INSN | (\n << 16) | (\ws << 11)
.set pop
.endm
- .macro copy_u_d ws, n
+ .macro copy_s_d ws, n
.set push
.set noat
SET_HARDFLOAT
.insn
- .word COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11)
+ .word COPY_SD_MSA_INSN | (\n << 16) | (\ws << 11)
.set pop
.endm
diff --git a/kernel/arch/mips/include/asm/cacheflush.h b/kernel/arch/mips/include/asm/cacheflush.h
index 723229f4c..176de586a 100644
--- a/kernel/arch/mips/include/asm/cacheflush.h
+++ b/kernel/arch/mips/include/asm/cacheflush.h
@@ -51,7 +51,6 @@ extern void (*flush_cache_range)(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
extern void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn);
extern void __flush_dcache_page(struct page *page);
-extern void __flush_icache_page(struct vm_area_struct *vma, struct page *page);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
static inline void flush_dcache_page(struct page *page)
@@ -77,11 +76,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
static inline void flush_icache_page(struct vm_area_struct *vma,
struct page *page)
{
- if (!cpu_has_ic_fills_f_dc && (vma->vm_flags & VM_EXEC) &&
- Page_dcache_dirty(page)) {
- __flush_icache_page(vma, page);
- ClearPageDcacheDirty(page);
- }
}
extern void (*flush_icache_range)(unsigned long start, unsigned long end);
diff --git a/kernel/arch/mips/include/asm/kvm_host.h b/kernel/arch/mips/include/asm/kvm_host.h
index 6ded8d347..c8c04a1f1 100644
--- a/kernel/arch/mips/include/asm/kvm_host.h
+++ b/kernel/arch/mips/include/asm/kvm_host.h
@@ -372,6 +372,7 @@ struct kvm_mips_tlb {
#define KVM_MIPS_GUEST_TLB_SIZE 64
struct kvm_vcpu_arch {
void *host_ebase, *guest_ebase;
+ int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
unsigned long host_stack;
unsigned long host_gp;
@@ -399,7 +400,10 @@ struct kvm_vcpu_arch {
/* Host KSEG0 address of the EI/DI offset */
void *kseg0_commpage;
- u32 io_gpr; /* GPR used as IO source/target */
+ /* Resume PC after MMIO completion */
+ unsigned long io_pc;
+ /* GPR used as IO source/target */
+ u32 io_gpr;
struct hrtimer comparecount_timer;
/* Count timer control KVM register */
@@ -421,8 +425,6 @@ struct kvm_vcpu_arch {
/* Bitmask of pending exceptions to be cleared */
unsigned long pending_exceptions_clr;
- unsigned long pending_load_cause;
-
/* Save/Restore the entryhi register when are are preempted/scheduled back in */
unsigned long preempt_entryhi;
@@ -784,7 +786,7 @@ extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu);
void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count);
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare);
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack);
void kvm_mips_init_count(struct kvm_vcpu *vcpu);
int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl);
int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume);
diff --git a/kernel/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h b/kernel/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
index 2f82bfa3a..c9f5769df 100644
--- a/kernel/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
+++ b/kernel/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/kernel/arch/mips/include/asm/msa.h b/kernel/arch/mips/include/asm/msa.h
index bbb85fe21..6e4effa6f 100644
--- a/kernel/arch/mips/include/asm/msa.h
+++ b/kernel/arch/mips/include/asm/msa.h
@@ -147,6 +147,19 @@ static inline void restore_msa(struct task_struct *t)
_restore_msa(t);
}
+static inline void init_msa_upper(void)
+{
+ /*
+ * Check cpu_has_msa only if it's a constant. This will allow the
+ * compiler to optimise out code for CPUs without MSA without adding
+ * an extra redundant check for CPUs with MSA.
+ */
+ if (__builtin_constant_p(cpu_has_msa) && !cpu_has_msa)
+ return;
+
+ _init_msa_upper();
+}
+
#ifdef TOOLCHAIN_SUPPORTS_MSA
#define __BUILD_MSA_CTL_REG(name, cs) \
diff --git a/kernel/arch/mips/include/asm/pgtable.h b/kernel/arch/mips/include/asm/pgtable.h
index 18826aa15..4e68c644a 100644
--- a/kernel/arch/mips/include/asm/pgtable.h
+++ b/kernel/arch/mips/include/asm/pgtable.h
@@ -127,10 +127,14 @@ do { \
} \
} while(0)
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pteval);
+
#if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
#define pte_none(pte) (!(((pte).pte_high) & ~_PAGE_GLOBAL))
#define pte_present(pte) ((pte).pte_low & _PAGE_PRESENT)
+#define pte_no_exec(pte) ((pte).pte_low & _PAGE_NO_EXEC)
static inline void set_pte(pte_t *ptep, pte_t pte)
{
@@ -148,7 +152,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
buddy->pte_high |= _PAGE_GLOBAL;
}
}
-#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval)
static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
@@ -166,6 +169,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
#define pte_none(pte) (!(pte_val(pte) & ~_PAGE_GLOBAL))
#define pte_present(pte) (pte_val(pte) & _PAGE_PRESENT)
+#define pte_no_exec(pte) (pte_val(pte) & _PAGE_NO_EXEC)
/*
* Certain architectures need to do special things when pte's
@@ -218,7 +222,6 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
}
#endif
}
-#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval)
static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
@@ -234,6 +237,22 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
}
#endif
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pteval)
+{
+ extern void __update_cache(unsigned long address, pte_t pte);
+
+ if (!pte_present(pteval))
+ goto cache_sync_done;
+
+ if (pte_present(*ptep) && (pte_pfn(*ptep) == pte_pfn(pteval)))
+ goto cache_sync_done;
+
+ __update_cache(addr, pteval);
+cache_sync_done:
+ set_pte(ptep, pteval);
+}
+
/*
* (pmds are folded into puds so this doesn't get actually called,
* but the define is needed for a generic inline function.)
@@ -430,15 +449,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
extern void __update_tlb(struct vm_area_struct *vma, unsigned long address,
pte_t pte);
-extern void __update_cache(struct vm_area_struct *vma, unsigned long address,
- pte_t pte);
static inline void update_mmu_cache(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
pte_t pte = *ptep;
__update_tlb(vma, address, pte);
- __update_cache(vma, address, pte);
}
static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
diff --git a/kernel/arch/mips/include/asm/processor.h b/kernel/arch/mips/include/asm/processor.h
index 3f832c3dd..041153f5c 100644
--- a/kernel/arch/mips/include/asm/processor.h
+++ b/kernel/arch/mips/include/asm/processor.h
@@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count;
* User space process size: 2GB. This is hardcoded into a few places,
* so don't change it unless you know what you are doing.
*/
-#define TASK_SIZE 0x7fff8000UL
+#define TASK_SIZE 0x80000000UL
#endif
#define STACK_TOP_MAX TASK_SIZE
diff --git a/kernel/arch/mips/include/asm/ptrace.h b/kernel/arch/mips/include/asm/ptrace.h
index f6fc6aac5..b6578611d 100644
--- a/kernel/arch/mips/include/asm/ptrace.h
+++ b/kernel/arch/mips/include/asm/ptrace.h
@@ -152,7 +152,7 @@ static inline int is_syscall_success(struct pt_regs *regs)
static inline long regs_return_value(struct pt_regs *regs)
{
- if (is_syscall_success(regs))
+ if (is_syscall_success(regs) || !user_mode(regs))
return regs->regs[2];
else
return -regs->regs[2];
diff --git a/kernel/arch/mips/include/asm/switch_to.h b/kernel/arch/mips/include/asm/switch_to.h
index 28b5d84a5..ebb5c0f2f 100644
--- a/kernel/arch/mips/include/asm/switch_to.h
+++ b/kernel/arch/mips/include/asm/switch_to.h
@@ -105,7 +105,7 @@ do { \
__clear_software_ll_bit(); \
if (cpu_has_userlocal) \
write_c0_userlocal(task_thread_info(next)->tp_value); \
- __restore_watch(); \
+ __restore_watch(next); \
(last) = resume(prev, next, task_thread_info(next)); \
} while (0)
diff --git a/kernel/arch/mips/include/asm/uaccess.h b/kernel/arch/mips/include/asm/uaccess.h
index 095ecafe6..c74c32ccc 100644
--- a/kernel/arch/mips/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/mips/include/asm/uprobes.h b/kernel/arch/mips/include/asm/uprobes.h
index 34c325c67..70a4a2f17 100644
--- a/kernel/arch/mips/include/asm/uprobes.h
+++ b/kernel/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/kernel/arch/mips/include/asm/watch.h b/kernel/arch/mips/include/asm/watch.h
index 20126ec79..6ffe3eadf 100644
--- a/kernel/arch/mips/include/asm/watch.h
+++ b/kernel/arch/mips/include/asm/watch.h
@@ -12,21 +12,21 @@
#include <asm/mipsregs.h>
-void mips_install_watch_registers(void);
+void mips_install_watch_registers(struct task_struct *t);
void mips_read_watch_registers(void);
void mips_clear_watch_registers(void);
void mips_probe_watch_registers(struct cpuinfo_mips *c);
#ifdef CONFIG_HARDWARE_WATCHPOINTS
-#define __restore_watch() do { \
+#define __restore_watch(task) do { \
if (unlikely(test_bit(TIF_LOAD_WATCH, \
- &current_thread_info()->flags))) { \
- mips_install_watch_registers(); \
+ &task_thread_info(task)->flags))) { \
+ mips_install_watch_registers(task); \
} \
} while (0)
#else
-#define __restore_watch() do {} while (0)
+#define __restore_watch(task) do {} while (0)
#endif
#endif /* _ASM_WATCH_H */
diff --git a/kernel/arch/mips/include/uapi/asm/siginfo.h b/kernel/arch/mips/include/uapi/asm/siginfo.h
index 2cb7fdead..e2b5337e8 100644
--- a/kernel/arch/mips/include/uapi/asm/siginfo.h
+++ b/kernel/arch/mips/include/uapi/asm/siginfo.h
@@ -28,7 +28,7 @@
#define __ARCH_SIGSYS
-#include <uapi/asm-generic/siginfo.h>
+#include <asm-generic/siginfo.h>
/* We can't use generic siginfo_t, because our si_code and si_errno are swapped */
typedef struct siginfo {
@@ -42,13 +42,13 @@ typedef struct siginfo {
/* kill() */
struct {
- pid_t _pid; /* sender's pid */
+ __kernel_pid_t _pid; /* sender's pid */
__ARCH_SI_UID_T _uid; /* sender's uid */
} _kill;
/* POSIX.1b timers */
struct {
- timer_t _tid; /* timer id */
+ __kernel_timer_t _tid; /* timer id */
int _overrun; /* overrun count */
char _pad[sizeof( __ARCH_SI_UID_T) - sizeof(int)];
sigval_t _sigval; /* same as below */
@@ -57,26 +57,26 @@ typedef struct siginfo {
/* POSIX.1b signals */
struct {
- pid_t _pid; /* sender's pid */
+ __kernel_pid_t _pid; /* sender's pid */
__ARCH_SI_UID_T _uid; /* sender's uid */
sigval_t _sigval;
} _rt;
/* SIGCHLD */
struct {
- pid_t _pid; /* which child */
+ __kernel_pid_t _pid; /* which child */
__ARCH_SI_UID_T _uid; /* sender's uid */
int _status; /* exit code */
- clock_t _utime;
- clock_t _stime;
+ __kernel_clock_t _utime;
+ __kernel_clock_t _stime;
} _sigchld;
/* IRIX SIGCHLD */
struct {
- pid_t _pid; /* which child */
- clock_t _utime;
+ __kernel_pid_t _pid; /* which child */
+ __kernel_clock_t _utime;
int _status; /* exit code */
- clock_t _stime;
+ __kernel_clock_t _stime;
} _irix_sigchld;
/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
@@ -118,6 +118,4 @@ typedef struct siginfo {
#define SI_TIMER __SI_CODE(__SI_TIMER, -3) /* sent by timer expiration */
#define SI_MESGQ __SI_CODE(__SI_MESGQ, -4) /* sent by real time mesq state change */
-#include <asm-generic/siginfo.h>
-
#endif /* _UAPI_ASM_SIGINFO_H */
diff --git a/kernel/arch/mips/kernel/csrc-r4k.c b/kernel/arch/mips/kernel/csrc-r4k.c
index 1f910563f..d76275da5 100644
--- a/kernel/arch/mips/kernel/csrc-r4k.c
+++ b/kernel/arch/mips/kernel/csrc-r4k.c
@@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = {
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-static u64 notrace r4k_read_sched_clock(void)
+static u64 __maybe_unused notrace r4k_read_sched_clock(void)
{
return read_c0_count();
}
@@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void)
clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
+#ifndef CONFIG_CPU_FREQ
sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency);
+#endif
return 0;
}
diff --git a/kernel/arch/mips/kernel/mips-r2-to-r6-emul.c b/kernel/arch/mips/kernel/mips-r2-to-r6-emul.c
index 1f5aac7f9..af27334d6 100644
--- a/kernel/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/kernel/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -28,6 +28,7 @@
#include <asm/inst.h>
#include <asm/mips-r2-to-r6-emul.h>
#include <asm/local.h>
+#include <asm/mipsregs.h>
#include <asm/ptrace.h>
#include <asm/uaccess.h>
@@ -1163,7 +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. */
@@ -1251,10 +1254,10 @@ fpu_emul:
" j 10b\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .word 1b,8b\n"
- " .word 2b,8b\n"
- " .word 3b,8b\n"
- " .word 4b,8b\n"
+ STR(PTR) " 1b,8b\n"
+ STR(PTR) " 2b,8b\n"
+ STR(PTR) " 3b,8b\n"
+ STR(PTR) " 4b,8b\n"
" .previous\n"
" .set pop\n"
: "+&r"(rt), "=&r"(rs),
@@ -1326,10 +1329,10 @@ fpu_emul:
" j 10b\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .word 1b,8b\n"
- " .word 2b,8b\n"
- " .word 3b,8b\n"
- " .word 4b,8b\n"
+ STR(PTR) " 1b,8b\n"
+ STR(PTR) " 2b,8b\n"
+ STR(PTR) " 3b,8b\n"
+ STR(PTR) " 4b,8b\n"
" .previous\n"
" .set pop\n"
: "+&r"(rt), "=&r"(rs),
@@ -1397,10 +1400,10 @@ fpu_emul:
" j 9b\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .word 1b,8b\n"
- " .word 2b,8b\n"
- " .word 3b,8b\n"
- " .word 4b,8b\n"
+ STR(PTR) " 1b,8b\n"
+ STR(PTR) " 2b,8b\n"
+ STR(PTR) " 3b,8b\n"
+ STR(PTR) " 4b,8b\n"
" .previous\n"
" .set pop\n"
: "+&r"(rt), "=&r"(rs),
@@ -1467,10 +1470,10 @@ fpu_emul:
" j 9b\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .word 1b,8b\n"
- " .word 2b,8b\n"
- " .word 3b,8b\n"
- " .word 4b,8b\n"
+ STR(PTR) " 1b,8b\n"
+ STR(PTR) " 2b,8b\n"
+ STR(PTR) " 3b,8b\n"
+ STR(PTR) " 4b,8b\n"
" .previous\n"
" .set pop\n"
: "+&r"(rt), "=&r"(rs),
@@ -1582,14 +1585,14 @@ fpu_emul:
" j 9b\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .word 1b,8b\n"
- " .word 2b,8b\n"
- " .word 3b,8b\n"
- " .word 4b,8b\n"
- " .word 5b,8b\n"
- " .word 6b,8b\n"
- " .word 7b,8b\n"
- " .word 0b,8b\n"
+ STR(PTR) " 1b,8b\n"
+ STR(PTR) " 2b,8b\n"
+ STR(PTR) " 3b,8b\n"
+ STR(PTR) " 4b,8b\n"
+ STR(PTR) " 5b,8b\n"
+ STR(PTR) " 6b,8b\n"
+ STR(PTR) " 7b,8b\n"
+ STR(PTR) " 0b,8b\n"
" .previous\n"
" .set pop\n"
: "+&r"(rt), "=&r"(rs),
@@ -1701,14 +1704,14 @@ fpu_emul:
" j 9b\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .word 1b,8b\n"
- " .word 2b,8b\n"
- " .word 3b,8b\n"
- " .word 4b,8b\n"
- " .word 5b,8b\n"
- " .word 6b,8b\n"
- " .word 7b,8b\n"
- " .word 0b,8b\n"
+ STR(PTR) " 1b,8b\n"
+ STR(PTR) " 2b,8b\n"
+ STR(PTR) " 3b,8b\n"
+ STR(PTR) " 4b,8b\n"
+ STR(PTR) " 5b,8b\n"
+ STR(PTR) " 6b,8b\n"
+ STR(PTR) " 7b,8b\n"
+ STR(PTR) " 0b,8b\n"
" .previous\n"
" .set pop\n"
: "+&r"(rt), "=&r"(rs),
@@ -1820,14 +1823,14 @@ fpu_emul:
" j 9b\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .word 1b,8b\n"
- " .word 2b,8b\n"
- " .word 3b,8b\n"
- " .word 4b,8b\n"
- " .word 5b,8b\n"
- " .word 6b,8b\n"
- " .word 7b,8b\n"
- " .word 0b,8b\n"
+ STR(PTR) " 1b,8b\n"
+ STR(PTR) " 2b,8b\n"
+ STR(PTR) " 3b,8b\n"
+ STR(PTR) " 4b,8b\n"
+ STR(PTR) " 5b,8b\n"
+ STR(PTR) " 6b,8b\n"
+ STR(PTR) " 7b,8b\n"
+ STR(PTR) " 0b,8b\n"
" .previous\n"
" .set pop\n"
: "+&r"(rt), "=&r"(rs),
@@ -1938,14 +1941,14 @@ fpu_emul:
" j 9b\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
- " .word 1b,8b\n"
- " .word 2b,8b\n"
- " .word 3b,8b\n"
- " .word 4b,8b\n"
- " .word 5b,8b\n"
- " .word 6b,8b\n"
- " .word 7b,8b\n"
- " .word 0b,8b\n"
+ STR(PTR) " 1b,8b\n"
+ STR(PTR) " 2b,8b\n"
+ STR(PTR) " 3b,8b\n"
+ STR(PTR) " 4b,8b\n"
+ STR(PTR) " 5b,8b\n"
+ STR(PTR) " 6b,8b\n"
+ STR(PTR) " 7b,8b\n"
+ STR(PTR) " 0b,8b\n"
" .previous\n"
" .set pop\n"
: "+&r"(rt), "=&r"(rs),
@@ -2000,7 +2003,7 @@ fpu_emul:
"j 2b\n"
".previous\n"
".section __ex_table,\"a\"\n"
- ".word 1b, 3b\n"
+ STR(PTR) " 1b,3b\n"
".previous\n"
: "=&r"(res), "+&r"(err)
: "r"(vaddr), "i"(SIGSEGV)
@@ -2058,7 +2061,7 @@ fpu_emul:
"j 2b\n"
".previous\n"
".section __ex_table,\"a\"\n"
- ".word 1b, 3b\n"
+ STR(PTR) " 1b,3b\n"
".previous\n"
: "+&r"(res), "+&r"(err)
: "r"(vaddr), "i"(SIGSEGV));
@@ -2119,7 +2122,7 @@ fpu_emul:
"j 2b\n"
".previous\n"
".section __ex_table,\"a\"\n"
- ".word 1b, 3b\n"
+ STR(PTR) " 1b,3b\n"
".previous\n"
: "=&r"(res), "+&r"(err)
: "r"(vaddr), "i"(SIGSEGV)
@@ -2182,7 +2185,7 @@ fpu_emul:
"j 2b\n"
".previous\n"
".section __ex_table,\"a\"\n"
- ".word 1b, 3b\n"
+ STR(PTR) " 1b,3b\n"
".previous\n"
: "+&r"(res), "+&r"(err)
: "r"(vaddr), "i"(SIGSEGV));
diff --git a/kernel/arch/mips/kernel/pm.c b/kernel/arch/mips/kernel/pm.c
index fefdf39d3..dc8148921 100644
--- a/kernel/arch/mips/kernel/pm.c
+++ b/kernel/arch/mips/kernel/pm.c
@@ -56,7 +56,7 @@ static void mips_cpu_restore(void)
write_c0_userlocal(current_thread_info()->tp_value);
/* Restore watch registers */
- __restore_watch();
+ __restore_watch(current);
}
/**
diff --git a/kernel/arch/mips/kernel/process.c b/kernel/arch/mips/kernel/process.c
index f2975d4d1..44a6f25e9 100644
--- a/kernel/arch/mips/kernel/process.c
+++ b/kernel/arch/mips/kernel/process.c
@@ -457,7 +457,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
*sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
regs = (struct pt_regs *)*sp;
pc = regs->cp0_epc;
- if (__kernel_text_address(pc)) {
+ if (!user_mode(regs) && __kernel_text_address(pc)) {
*sp = regs->regs[29];
*ra = regs->regs[31];
return pc;
@@ -593,16 +593,19 @@ 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 */
+ preempt_disable();
+
/* Save FP & vector context, then disable FPU & MSA */
if (task->signal == current->signal)
lose_fpu(1);
@@ -661,6 +664,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
/* Allow threads to use FP again */
atomic_set(&task->mm->context.fp_mode_switching, 0);
+ preempt_enable();
return 0;
}
diff --git a/kernel/arch/mips/kernel/ptrace.c b/kernel/arch/mips/kernel/ptrace.c
index 4f0ac78d1..74d581569 100644
--- a/kernel/arch/mips/kernel/ptrace.c
+++ b/kernel/arch/mips/kernel/ptrace.c
@@ -57,8 +57,7 @@ static void init_fp_ctx(struct task_struct *target)
/* Begin with data registers set to all 1s... */
memset(&target->thread.fpu.fpr, ~0, sizeof(target->thread.fpu.fpr));
- /* ...and FCSR zeroed */
- target->thread.fpu.fcr31 = 0;
+ /* FCSR has been preset by `mips_set_personality_nan'. */
/*
* Record that the target has "used" math, such that the context
@@ -80,6 +79,22 @@ void ptrace_disable(struct task_struct *child)
}
/*
+ * Poke at FCSR according to its mask. Don't set the cause bits as
+ * this is currently not handled correctly in FP context restoration
+ * and will cause an oops if a corresponding enable bit is set.
+ */
+static void ptrace_setfcr31(struct task_struct *child, u32 value)
+{
+ u32 fcr31;
+ u32 mask;
+
+ value &= ~FPU_CSR_ALL_X;
+ fcr31 = child->thread.fpu.fcr31;
+ mask = boot_cpu_data.fpu_msk31;
+ child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
+}
+
+/*
* Read a general register set. We always use the 64-bit format, even
* for 32-bit kernels and for 32-bit processes on a 64-bit kernel.
* Registers are sign extended to fill the available space.
@@ -159,9 +174,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
{
union fpureg *fregs;
u64 fpr_val;
- u32 fcr31;
u32 value;
- u32 mask;
int i;
if (!access_ok(VERIFY_READ, data, 33 * 8))
@@ -176,9 +189,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
}
__get_user(value, data + 64);
- fcr31 = child->thread.fpu.fcr31;
- mask = boot_cpu_data.fpu_msk31;
- child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
+ ptrace_setfcr31(child, value);
/* FIR may not be written. */
@@ -808,7 +819,7 @@ long arch_ptrace(struct task_struct *child, long request,
break;
#endif
case FPC_CSR:
- child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X;
+ ptrace_setfcr31(child, data);
break;
case DSP_BASE ... DSP_BASE + 5: {
dspreg_t *dregs;
diff --git a/kernel/arch/mips/kernel/r4k_fpu.S b/kernel/arch/mips/kernel/r4k_fpu.S
index f09546ee2..bc74485ec 100644
--- a/kernel/arch/mips/kernel/r4k_fpu.S
+++ b/kernel/arch/mips/kernel/r4k_fpu.S
@@ -244,17 +244,17 @@ LEAF(\name)
.set push
.set noat
#ifdef CONFIG_64BIT
- copy_u_d \wr, 1
+ copy_s_d \wr, 1
EX sd $1, \off(\base)
#elif defined(CONFIG_CPU_LITTLE_ENDIAN)
- copy_u_w \wr, 2
+ copy_s_w \wr, 2
EX sw $1, \off(\base)
- copy_u_w \wr, 3
+ copy_s_w \wr, 3
EX sw $1, (\off+4)(\base)
#else /* CONFIG_CPU_BIG_ENDIAN */
- copy_u_w \wr, 2
+ copy_s_w \wr, 2
EX sw $1, (\off+4)(\base)
- copy_u_w \wr, 3
+ copy_s_w \wr, 3
EX sw $1, \off(\base)
#endif
.set pop
diff --git a/kernel/arch/mips/kernel/scall64-n32.S b/kernel/arch/mips/kernel/scall64-n32.S
index 5a69eb48d..ee93d5fe6 100644
--- a/kernel/arch/mips/kernel/scall64-n32.S
+++ b/kernel/arch/mips/kernel/scall64-n32.S
@@ -344,7 +344,7 @@ EXPORT(sysn32_call_table)
PTR sys_ni_syscall /* available, was setaltroot */
PTR sys_add_key
PTR sys_request_key
- PTR sys_keyctl /* 6245 */
+ PTR compat_sys_keyctl /* 6245 */
PTR sys_set_thread_area
PTR sys_inotify_init
PTR sys_inotify_add_watch
diff --git a/kernel/arch/mips/kernel/scall64-o32.S b/kernel/arch/mips/kernel/scall64-o32.S
index e4b6d7c97..b77052ec6 100644
--- a/kernel/arch/mips/kernel/scall64-o32.S
+++ b/kernel/arch/mips/kernel/scall64-o32.S
@@ -500,7 +500,7 @@ EXPORT(sys32_call_table)
PTR sys_ni_syscall /* available, was setaltroot */
PTR sys_add_key /* 4280 */
PTR sys_request_key
- PTR sys_keyctl
+ PTR compat_sys_keyctl
PTR sys_set_thread_area
PTR sys_inotify_init
PTR sys_inotify_add_watch /* 4285 */
diff --git a/kernel/arch/mips/kernel/setup.c b/kernel/arch/mips/kernel/setup.c
index 66aac55df..8acae316f 100644
--- a/kernel/arch/mips/kernel/setup.c
+++ b/kernel/arch/mips/kernel/setup.c
@@ -706,6 +706,9 @@ static void __init arch_mem_init(char **cmdline_p)
for_each_memblock(reserved, reg)
if (reg->size != 0)
reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+
+ reserve_bootmem_region(__pa_symbol(&__nosave_begin),
+ __pa_symbol(&__nosave_end)); /* Reserve for hibernation */
}
static void __init resource_init(void)
diff --git a/kernel/arch/mips/kernel/signal.c b/kernel/arch/mips/kernel/signal.c
index bf792e283..9e35b6b26 100644
--- a/kernel/arch/mips/kernel/signal.c
+++ b/kernel/arch/mips/kernel/signal.c
@@ -195,6 +195,9 @@ static int restore_msa_extcontext(void __user *buf, unsigned int size)
unsigned int csr;
int i, err;
+ if (!config_enabled(CONFIG_CPU_HAS_MSA))
+ return SIGSYS;
+
if (size != sizeof(*msa))
return -EINVAL;
@@ -398,8 +401,8 @@ int protected_restore_fp_context(void __user *sc)
}
fp_done:
- if (used & USED_EXTCONTEXT)
- err |= restore_extcontext(sc_to_extcontext(sc));
+ if (!err && (used & USED_EXTCONTEXT))
+ err = restore_extcontext(sc_to_extcontext(sc));
return err ?: sig;
}
@@ -767,15 +770,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
sigset_t *oldset = sigmask_to_save();
int ret;
struct mips_abi *abi = current->thread.abi;
-#ifdef CONFIG_CPU_MICROMIPS
- void *vdso;
- unsigned long tmp = (unsigned long)current->mm->context.vdso;
-
- set_isa16_mode(tmp);
- vdso = (void *)tmp;
-#else
void *vdso = current->mm->context.vdso;
-#endif
if (regs->regs[0]) {
switch(regs->regs[2]) {
diff --git a/kernel/arch/mips/kernel/smp.c b/kernel/arch/mips/kernel/smp.c
index 2b521e07b..7fef02a9e 100644
--- a/kernel/arch/mips/kernel/smp.c
+++ b/kernel/arch/mips/kernel/smp.c
@@ -174,6 +174,9 @@ 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);
@@ -181,10 +184,6 @@ 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/kernel/arch/mips/kernel/traps.c b/kernel/arch/mips/kernel/traps.c
index ca9a81007..99a402231 100644
--- a/kernel/arch/mips/kernel/traps.c
+++ b/kernel/arch/mips/kernel/traps.c
@@ -144,7 +144,7 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs)
if (!task)
task = current;
- if (raw_show_trace || !__kernel_text_address(pc)) {
+ if (raw_show_trace || user_mode(regs) || !__kernel_text_address(pc)) {
show_raw_backtrace(sp);
return;
}
@@ -1241,7 +1241,7 @@ static int enable_restore_fp_context(int msa)
err = init_fpu();
if (msa && !err) {
enable_msa();
- _init_msa_upper();
+ init_msa_upper();
set_thread_flag(TIF_USEDMSA);
set_thread_flag(TIF_MSA_CTX_LIVE);
}
@@ -1304,7 +1304,7 @@ static int enable_restore_fp_context(int msa)
*/
prior_msa = test_and_set_thread_flag(TIF_MSA_CTX_LIVE);
if (!prior_msa && was_fpu_owner) {
- _init_msa_upper();
+ init_msa_upper();
goto out;
}
@@ -1321,7 +1321,7 @@ static int enable_restore_fp_context(int msa)
* of each vector register such that it cannot see data left
* behind by another task.
*/
- _init_msa_upper();
+ init_msa_upper();
} else {
/* We need to restore the vector context. */
restore_msa(current);
diff --git a/kernel/arch/mips/kernel/unaligned.c b/kernel/arch/mips/kernel/unaligned.c
index 490cea569..5c62065cb 100644
--- a/kernel/arch/mips/kernel/unaligned.c
+++ b/kernel/arch/mips/kernel/unaligned.c
@@ -885,7 +885,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
{
union mips_instruction insn;
unsigned long value;
- unsigned int res;
+ unsigned int res, preempted;
unsigned long origpc;
unsigned long orig31;
void __user *fault_addr = NULL;
@@ -1226,27 +1226,36 @@ static void emulate_load_store_insn(struct pt_regs *regs,
if (!access_ok(VERIFY_READ, addr, sizeof(*fpr)))
goto sigbus;
- /*
- * Disable preemption to avoid a race between copying
- * state from userland, migrating to another CPU and
- * updating the hardware vector register below.
- */
- preempt_disable();
-
- res = __copy_from_user_inatomic(fpr, addr,
- sizeof(*fpr));
- if (res)
- goto fault;
-
- /*
- * Update the hardware register if it is in use by the
- * task in this quantum, in order to avoid having to
- * save & restore the whole vector context.
- */
- if (test_thread_flag(TIF_USEDMSA))
- write_msa_wr(wd, fpr, df);
+ do {
+ /*
+ * If we have live MSA context keep track of
+ * whether we get preempted in order to avoid
+ * the register context we load being clobbered
+ * by the live context as it's saved during
+ * preemption. If we don't have live context
+ * then it can't be saved to clobber the value
+ * we load.
+ */
+ preempted = test_thread_flag(TIF_USEDMSA);
+
+ res = __copy_from_user_inatomic(fpr, addr,
+ sizeof(*fpr));
+ if (res)
+ goto fault;
- preempt_enable();
+ /*
+ * Update the hardware register if it is in use
+ * by the task in this quantum, in order to
+ * avoid having to save & restore the whole
+ * vector context.
+ */
+ preempt_disable();
+ if (test_thread_flag(TIF_USEDMSA)) {
+ write_msa_wr(wd, fpr, df);
+ preempted = 0;
+ }
+ preempt_enable();
+ } while (preempted);
break;
case msa_st_op:
diff --git a/kernel/arch/mips/kernel/uprobes.c b/kernel/arch/mips/kernel/uprobes.c
index 8452d933a..4e7b89f2e 100644
--- a/kernel/arch/mips/kernel/uprobes.c
+++ b/kernel/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;
@@ -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/kernel/arch/mips/kernel/vdso.c b/kernel/arch/mips/kernel/vdso.c
index 975e99759..5649a9e42 100644
--- a/kernel/arch/mips/kernel/vdso.c
+++ b/kernel/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/kernel/arch/mips/kernel/watch.c b/kernel/arch/mips/kernel/watch.c
index 2a03abb5b..9b78e3751 100644
--- a/kernel/arch/mips/kernel/watch.c
+++ b/kernel/arch/mips/kernel/watch.c
@@ -15,10 +15,9 @@
* Install the watch registers for the current thread. A maximum of
* four registers are installed although the machine may have more.
*/
-void mips_install_watch_registers(void)
+void mips_install_watch_registers(struct task_struct *t)
{
- struct mips3264_watch_reg_state *watches =
- &current->thread.watch.mips3264;
+ struct mips3264_watch_reg_state *watches = &t->thread.watch.mips3264;
switch (current_cpu_data.watch_reg_use_cnt) {
default:
BUG();
diff --git a/kernel/arch/mips/kvm/emulate.c b/kernel/arch/mips/kvm/emulate.c
index 41b1b090f..4c85ab808 100644
--- a/kernel/arch/mips/kvm/emulate.c
+++ b/kernel/arch/mips/kvm/emulate.c
@@ -302,12 +302,31 @@ static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu)
*/
static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
{
- ktime_t expires;
+ struct mips_coproc *cop0 = vcpu->arch.cop0;
+ ktime_t expires, threshold;
+ uint32_t count, compare;
int running;
- /* Is the hrtimer pending? */
+ /* Calculate the biased and scaled guest CP0_Count */
+ count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+ compare = kvm_read_c0_guest_compare(cop0);
+
+ /*
+ * Find whether CP0_Count has reached the closest timer interrupt. If
+ * not, we shouldn't inject it.
+ */
+ if ((int32_t)(count - compare) < 0)
+ return count;
+
+ /*
+ * The CP0_Count we're going to return has already reached the closest
+ * timer interrupt. Quickly check if it really is a new interrupt by
+ * looking at whether the interval until the hrtimer expiry time is
+ * less than 1/4 of the timer period.
+ */
expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer);
- if (ktime_compare(now, expires) >= 0) {
+ threshold = ktime_add_ns(now, vcpu->arch.count_period / 4);
+ if (ktime_before(expires, threshold)) {
/*
* Cancel it while we handle it so there's no chance of
* interference with the timeout handler.
@@ -329,8 +348,7 @@ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
}
}
- /* Return the biased and scaled guest CP0_Count */
- return vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+ return count;
}
/**
@@ -420,32 +438,6 @@ static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
}
/**
- * kvm_mips_update_hrtimer() - Update next expiry time of hrtimer.
- * @vcpu: Virtual CPU.
- *
- * Recalculates and updates the expiry time of the hrtimer. This can be used
- * after timer parameters have been altered which do not depend on the time that
- * the change occurs (in those cases kvm_mips_freeze_hrtimer() and
- * kvm_mips_resume_hrtimer() are used directly).
- *
- * It is guaranteed that no timer interrupts will be lost in the process.
- *
- * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
- */
-static void kvm_mips_update_hrtimer(struct kvm_vcpu *vcpu)
-{
- ktime_t now;
- uint32_t count;
-
- /*
- * freeze_hrtimer takes care of a timer interrupts <= count, and
- * resume_hrtimer the hrtimer takes care of a timer interrupts > count.
- */
- now = kvm_mips_freeze_hrtimer(vcpu, &count);
- kvm_mips_resume_hrtimer(vcpu, now, count);
-}
-
-/**
* kvm_mips_write_count() - Modify the count and update timer.
* @vcpu: Virtual CPU.
* @count: Guest CP0_Count value to set.
@@ -540,23 +532,42 @@ int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz)
* kvm_mips_write_compare() - Modify compare and update timer.
* @vcpu: Virtual CPU.
* @compare: New CP0_Compare value.
+ * @ack: Whether to acknowledge timer interrupt.
*
* Update CP0_Compare to a new value and update the timeout.
+ * If @ack, atomically acknowledge any pending timer interrupt, otherwise ensure
+ * any pending timer interrupt is preserved.
*/
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare)
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack)
{
struct mips_coproc *cop0 = vcpu->arch.cop0;
+ int dc;
+ u32 old_compare = kvm_read_c0_guest_compare(cop0);
+ ktime_t now;
+ uint32_t count;
/* if unchanged, must just be an ack */
- if (kvm_read_c0_guest_compare(cop0) == compare)
+ if (old_compare == compare) {
+ if (!ack)
+ return;
+ kvm_mips_callbacks->dequeue_timer_int(vcpu);
+ kvm_write_c0_guest_compare(cop0, compare);
return;
+ }
+
+ /* freeze_hrtimer() takes care of timer interrupts <= count */
+ dc = kvm_mips_count_disabled(vcpu);
+ if (!dc)
+ now = kvm_mips_freeze_hrtimer(vcpu, &count);
+
+ if (ack)
+ kvm_mips_callbacks->dequeue_timer_int(vcpu);
- /* Update compare */
kvm_write_c0_guest_compare(cop0, compare);
- /* Update timeout if count enabled */
- if (!kvm_mips_count_disabled(vcpu))
- kvm_mips_update_hrtimer(vcpu);
+ /* resume_hrtimer() takes care of timer interrupts > count */
+ if (!dc)
+ kvm_mips_resume_hrtimer(vcpu, now, count);
}
/**
@@ -741,15 +752,15 @@ enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
struct mips_coproc *cop0 = vcpu->arch.cop0;
enum emulation_result er = EMULATE_DONE;
- if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
+ if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
+ kvm_clear_c0_guest_status(cop0, ST0_ERL);
+ vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
+ } else if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
kvm_debug("[%#lx] ERET to %#lx\n", vcpu->arch.pc,
kvm_read_c0_guest_epc(cop0));
kvm_clear_c0_guest_status(cop0, ST0_EXL);
vcpu->arch.pc = kvm_read_c0_guest_epc(cop0);
- } else if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
- kvm_clear_c0_guest_status(cop0, ST0_ERL);
- vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
} else {
kvm_err("[%#lx] ERET when MIPS_SR_EXL|MIPS_SR_ERL == 0\n",
vcpu->arch.pc);
@@ -796,6 +807,47 @@ enum emulation_result kvm_mips_emul_tlbr(struct kvm_vcpu *vcpu)
return EMULATE_FAIL;
}
+/**
+ * kvm_mips_invalidate_guest_tlb() - Indicates a change in guest MMU map.
+ * @vcpu: VCPU with changed mappings.
+ * @tlb: TLB entry being removed.
+ *
+ * This is called to indicate a single change in guest MMU mappings, so that we
+ * can arrange TLB flushes on this and other CPUs.
+ */
+static void kvm_mips_invalidate_guest_tlb(struct kvm_vcpu *vcpu,
+ struct kvm_mips_tlb *tlb)
+{
+ int cpu, i;
+ bool user;
+
+ /* No need to flush for entries which are already invalid */
+ if (!((tlb->tlb_lo0 | tlb->tlb_lo1) & MIPS3_PG_V))
+ return;
+ /* User address space doesn't need flushing for KSeg2/3 changes */
+ user = tlb->tlb_hi < KVM_GUEST_KSEG0;
+
+ preempt_disable();
+
+ /*
+ * Probe the shadow host TLB for the entry being overwritten, if one
+ * matches, invalidate it
+ */
+ kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+
+ /* Invalidate the whole ASID on other CPUs */
+ cpu = smp_processor_id();
+ for_each_possible_cpu(i) {
+ if (i == cpu)
+ continue;
+ if (user)
+ vcpu->arch.guest_user_asid[i] = 0;
+ vcpu->arch.guest_kernel_asid[i] = 0;
+ }
+
+ preempt_enable();
+}
+
/* Write Guest TLB Entry @ Index */
enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
{
@@ -815,11 +867,8 @@ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
}
tlb = &vcpu->arch.guest_tlb[index];
- /*
- * Probe the shadow host TLB for the entry being overwritten, if one
- * matches, invalidate it
- */
- kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+
+ kvm_mips_invalidate_guest_tlb(vcpu, tlb);
tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
@@ -848,11 +897,7 @@ enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu)
tlb = &vcpu->arch.guest_tlb[index];
- /*
- * Probe the shadow host TLB for the entry being overwritten, if one
- * matches, invalidate it
- */
- kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+ kvm_mips_invalidate_guest_tlb(vcpu, tlb);
tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
@@ -971,6 +1016,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
int32_t rt, rd, copz, sel, co_bit, op;
uint32_t pc = vcpu->arch.pc;
unsigned long curr_pc;
+ int cpu, i;
/*
* Update PC and hold onto current PC in case there is
@@ -1078,8 +1124,16 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
vcpu->arch.gprs[rt]
& ASID_MASK);
+ preempt_disable();
/* Blow away the shadow host TLBs */
kvm_mips_flush_host_tlb(1);
+ cpu = smp_processor_id();
+ for_each_possible_cpu(i)
+ if (i != cpu) {
+ vcpu->arch.guest_user_asid[i] = 0;
+ vcpu->arch.guest_kernel_asid[i] = 0;
+ }
+ preempt_enable();
}
kvm_write_c0_guest_entryhi(cop0,
vcpu->arch.gprs[rt]);
@@ -1095,9 +1149,9 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
/* If we are writing to COMPARE */
/* Clear pending timer interrupt, if any */
- kvm_mips_callbacks->dequeue_timer_int(vcpu);
kvm_mips_write_compare(vcpu,
- vcpu->arch.gprs[rt]);
+ vcpu->arch.gprs[rt],
+ true);
} else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) {
unsigned int old_val, val, change;
@@ -1419,6 +1473,7 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
struct kvm_vcpu *vcpu)
{
enum emulation_result er = EMULATE_DO_MMIO;
+ unsigned long curr_pc;
int32_t op, base, rt, offset;
uint32_t bytes;
@@ -1427,7 +1482,18 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
offset = inst & 0xffff;
op = (inst >> 26) & 0x3f;
- vcpu->arch.pending_load_cause = cause;
+ /*
+ * Find the resume PC now while we have safe and easy access to the
+ * prior branch instruction, and save it for
+ * kvm_mips_complete_mmio_load() to restore later.
+ */
+ curr_pc = vcpu->arch.pc;
+ er = update_pc(vcpu, cause);
+ if (er == EMULATE_FAIL)
+ return er;
+ vcpu->arch.io_pc = vcpu->arch.pc;
+ vcpu->arch.pc = curr_pc;
+
vcpu->arch.io_gpr = rt;
switch (op) {
@@ -1618,8 +1684,14 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
preempt_disable();
if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
- if (kvm_mips_host_tlb_lookup(vcpu, va) < 0)
- kvm_mips_handle_kseg0_tlb_fault(va, vcpu);
+ if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 &&
+ kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) {
+ kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n",
+ __func__, va, vcpu, read_c0_entryhi());
+ er = EMULATE_FAIL;
+ preempt_enable();
+ goto done;
+ }
} else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) ||
KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
int index;
@@ -1654,14 +1726,19 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
run, vcpu);
preempt_enable();
goto dont_update_pc;
- } else {
- /*
- * We fault an entry from the guest tlb to the
- * shadow host TLB
- */
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
- NULL,
- NULL);
+ }
+ /*
+ * We fault an entry from the guest tlb to the
+ * shadow host TLB
+ */
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
+ NULL, NULL)) {
+ kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, va, index, vcpu,
+ read_c0_entryhi());
+ er = EMULATE_FAIL;
+ preempt_enable();
+ goto done;
}
}
} else {
@@ -2396,9 +2473,8 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
goto done;
}
- er = update_pc(vcpu, vcpu->arch.pending_load_cause);
- if (er == EMULATE_FAIL)
- return er;
+ /* Restore saved resume PC */
+ vcpu->arch.pc = vcpu->arch.io_pc;
switch (run->mmio.len) {
case 4:
@@ -2420,11 +2496,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
break;
}
- if (vcpu->arch.pending_load_cause & CAUSEF_BD)
- kvm_debug("[%#lx] Completing %d byte BD Load to gpr %d (0x%08lx) type %d\n",
- vcpu->arch.pc, run->mmio.len, vcpu->arch.io_gpr, *gpr,
- vcpu->mmio_needed);
-
done:
return er;
}
@@ -2622,8 +2693,13 @@ enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause,
* OK we have a Guest TLB entry, now inject it into the
* shadow host TLB
*/
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, NULL,
- NULL);
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
+ NULL, NULL)) {
+ kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, va, index, vcpu,
+ read_c0_entryhi());
+ er = EMULATE_FAIL;
+ }
}
}
diff --git a/kernel/arch/mips/kvm/interrupt.h b/kernel/arch/mips/kvm/interrupt.h
index 4ab4bdfad..214388470 100644
--- a/kernel/arch/mips/kvm/interrupt.h
+++ b/kernel/arch/mips/kvm/interrupt.h
@@ -28,6 +28,7 @@
#define MIPS_EXC_MAX 12
/* XXXSL More to follow */
+extern char __kvm_mips_vcpu_run_end[];
extern char mips32_exception[], mips32_exceptionEnd[];
extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
diff --git a/kernel/arch/mips/kvm/locore.S b/kernel/arch/mips/kvm/locore.S
index 7e2210846..777064336 100644
--- a/kernel/arch/mips/kvm/locore.S
+++ b/kernel/arch/mips/kvm/locore.S
@@ -227,6 +227,7 @@ FEXPORT(__kvm_mips_load_k0k1)
/* Jump to guest */
eret
+EXPORT(__kvm_mips_vcpu_run_end)
VECTOR(MIPSX(exception), unknown)
/* Find out what mode we came from and jump to the proper handler. */
diff --git a/kernel/arch/mips/kvm/mips.c b/kernel/arch/mips/kvm/mips.c
index 8a113298b..8d4d92701 100644
--- a/kernel/arch/mips/kvm/mips.c
+++ b/kernel/arch/mips/kvm/mips.c
@@ -314,9 +314,18 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
memcpy(gebase + offset, mips32_GuestException,
mips32_GuestExceptionEnd - mips32_GuestException);
+#ifdef MODULE
+ offset += mips32_GuestExceptionEnd - mips32_GuestException;
+ memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
+ __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
+ vcpu->arch.vcpu_run = gebase + offset;
+#else
+ vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
+#endif
+
/* Invalidate the icache for these ranges */
- local_flush_icache_range((unsigned long)gebase,
- (unsigned long)gebase + ALIGN(size, PAGE_SIZE));
+ flush_icache_range((unsigned long)gebase,
+ (unsigned long)gebase + ALIGN(size, PAGE_SIZE));
/*
* Allocate comm page for guest kernel, a TLB will be reserved for
@@ -403,7 +412,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
/* Disable hardware page table walking while in guest */
htw_stop();
- r = __kvm_mips_vcpu_run(run, vcpu);
+ r = vcpu->arch.vcpu_run(run, vcpu);
/* Re-enable HTW before enabling interrupts */
htw_start();
diff --git a/kernel/arch/mips/kvm/tlb.c b/kernel/arch/mips/kvm/tlb.c
index aed0ac2a4..eff71c75d 100644
--- a/kernel/arch/mips/kvm/tlb.c
+++ b/kernel/arch/mips/kvm/tlb.c
@@ -152,7 +152,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
srcu_idx = srcu_read_lock(&kvm->srcu);
pfn = kvm_mips_gfn_to_pfn(kvm, gfn);
- if (kvm_mips_is_error_pfn(pfn)) {
+ if (is_error_noslot_pfn(pfn)) {
kvm_err("Couldn't get pfn for gfn %#" PRIx64 "!\n", gfn);
err = -EFAULT;
goto out;
@@ -276,7 +276,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
}
gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
- if (gfn >= kvm->arch.guest_pmap_npages) {
+ if ((gfn | 1) >= kvm->arch.guest_pmap_npages) {
kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
gfn, badvaddr);
kvm_mips_dump_host_tlbs();
@@ -361,25 +361,39 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
struct kvm *kvm = vcpu->kvm;
pfn_t pfn0, pfn1;
-
- if ((tlb->tlb_hi & VPN2_MASK) == 0) {
- pfn0 = 0;
- pfn1 = 0;
- } else {
- if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
- >> PAGE_SHIFT) < 0)
- return -1;
-
- if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
- >> PAGE_SHIFT) < 0)
- return -1;
-
- pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
- >> PAGE_SHIFT];
- pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
- >> PAGE_SHIFT];
+ gfn_t gfn0, gfn1;
+ long tlb_lo[2];
+
+ tlb_lo[0] = tlb->tlb_lo0;
+ tlb_lo[1] = tlb->tlb_lo1;
+
+ /*
+ * The commpage address must not be mapped to anything else if the guest
+ * TLB contains entries nearby, or commpage accesses will break.
+ */
+ if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) &
+ VPN2_MASK & (PAGE_MASK << 1)))
+ tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0;
+
+ gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT;
+ gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT;
+ if (gfn0 >= kvm->arch.guest_pmap_npages ||
+ gfn1 >= kvm->arch.guest_pmap_npages) {
+ kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n",
+ __func__, gfn0, gfn1, tlb->tlb_hi);
+ kvm_mips_dump_guest_tlbs(vcpu);
+ return -1;
}
+ if (kvm_mips_map_page(kvm, gfn0) < 0)
+ return -1;
+
+ if (kvm_mips_map_page(kvm, gfn1) < 0)
+ return -1;
+
+ pfn0 = kvm->arch.guest_pmap[gfn0];
+ pfn1 = kvm->arch.guest_pmap[gfn1];
+
if (hpa0)
*hpa0 = pfn0 << PAGE_SHIFT;
@@ -391,9 +405,9 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
kvm_mips_get_kernel_asid(vcpu) :
kvm_mips_get_user_asid(vcpu));
entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
- (tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V);
+ (tlb_lo[0] & MIPS3_PG_D) | (tlb_lo[0] & MIPS3_PG_V);
entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
- (tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V);
+ (tlb_lo[1] & MIPS3_PG_D) | (tlb_lo[1] & MIPS3_PG_V);
kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
tlb->tlb_lo0, tlb->tlb_lo1);
@@ -794,10 +808,16 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
local_irq_restore(flags);
return KVM_INVALID_INST;
}
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
- &vcpu->arch.
- guest_tlb[index],
- NULL, NULL);
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+ &vcpu->arch.guest_tlb[index],
+ NULL, NULL)) {
+ kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, opc, index, vcpu,
+ read_c0_entryhi());
+ kvm_mips_dump_guest_tlbs(vcpu);
+ local_irq_restore(flags);
+ return KVM_INVALID_INST;
+ }
inst = *(opc);
}
local_irq_restore(flags);
diff --git a/kernel/arch/mips/kvm/trap_emul.c b/kernel/arch/mips/kvm/trap_emul.c
index d836ed5b0..307cc4c98 100644
--- a/kernel/arch/mips/kvm/trap_emul.c
+++ b/kernel/arch/mips/kvm/trap_emul.c
@@ -547,7 +547,7 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu,
kvm_mips_write_count(vcpu, v);
break;
case KVM_REG_MIPS_CP0_COMPARE:
- kvm_mips_write_compare(vcpu, v);
+ kvm_mips_write_compare(vcpu, v, false);
break;
case KVM_REG_MIPS_CP0_CAUSE:
/*
diff --git a/kernel/arch/mips/lib/ashldi3.c b/kernel/arch/mips/lib/ashldi3.c
index beb80f316..927dc94a0 100644
--- a/kernel/arch/mips/lib/ashldi3.c
+++ b/kernel/arch/mips/lib/ashldi3.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-long long __ashldi3(long long u, word_type b)
+long long notrace __ashldi3(long long u, word_type b)
{
DWunion uu, w;
word_type bm;
diff --git a/kernel/arch/mips/lib/ashrdi3.c b/kernel/arch/mips/lib/ashrdi3.c
index c884a912b..9fdf1a598 100644
--- a/kernel/arch/mips/lib/ashrdi3.c
+++ b/kernel/arch/mips/lib/ashrdi3.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-long long __ashrdi3(long long u, word_type b)
+long long notrace __ashrdi3(long long u, word_type b)
{
DWunion uu, w;
word_type bm;
diff --git a/kernel/arch/mips/lib/bswapdi.c b/kernel/arch/mips/lib/bswapdi.c
index 77e5f9c1f..e3e77aa52 100644
--- a/kernel/arch/mips/lib/bswapdi.c
+++ b/kernel/arch/mips/lib/bswapdi.c
@@ -1,6 +1,6 @@
#include <linux/module.h>
-unsigned long long __bswapdi2(unsigned long long u)
+unsigned long long notrace __bswapdi2(unsigned long long u)
{
return (((u) & 0xff00000000000000ull) >> 56) |
(((u) & 0x00ff000000000000ull) >> 40) |
diff --git a/kernel/arch/mips/lib/bswapsi.c b/kernel/arch/mips/lib/bswapsi.c
index 2b302ff12..530a8afe6 100644
--- a/kernel/arch/mips/lib/bswapsi.c
+++ b/kernel/arch/mips/lib/bswapsi.c
@@ -1,6 +1,6 @@
#include <linux/module.h>
-unsigned int __bswapsi2(unsigned int u)
+unsigned int notrace __bswapsi2(unsigned int u)
{
return (((u) & 0xff000000) >> 24) |
(((u) & 0x00ff0000) >> 8) |
diff --git a/kernel/arch/mips/lib/cmpdi2.c b/kernel/arch/mips/lib/cmpdi2.c
index 8c1306437..06857da96 100644
--- a/kernel/arch/mips/lib/cmpdi2.c
+++ b/kernel/arch/mips/lib/cmpdi2.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-word_type __cmpdi2(long long a, long long b)
+word_type notrace __cmpdi2(long long a, long long b)
{
const DWunion au = {
.ll = a
diff --git a/kernel/arch/mips/lib/lshrdi3.c b/kernel/arch/mips/lib/lshrdi3.c
index dcf8d6810..364547449 100644
--- a/kernel/arch/mips/lib/lshrdi3.c
+++ b/kernel/arch/mips/lib/lshrdi3.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-long long __lshrdi3(long long u, word_type b)
+long long notrace __lshrdi3(long long u, word_type b)
{
DWunion uu, w;
word_type bm;
diff --git a/kernel/arch/mips/lib/ucmpdi2.c b/kernel/arch/mips/lib/ucmpdi2.c
index bb4cb2f82..bd599f582 100644
--- a/kernel/arch/mips/lib/ucmpdi2.c
+++ b/kernel/arch/mips/lib/ucmpdi2.c
@@ -2,7 +2,7 @@
#include "libgcc.h"
-word_type __ucmpdi2(unsigned long long a, unsigned long long b)
+word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b)
{
const DWunion au = {.ll = a};
const DWunion bu = {.ll = b};
diff --git a/kernel/arch/mips/loongson64/loongson-3/hpet.c b/kernel/arch/mips/loongson64/loongson-3/hpet.c
index a2631a52c..444802e78 100644
--- a/kernel/arch/mips/loongson64/loongson-3/hpet.c
+++ b/kernel/arch/mips/loongson64/loongson-3/hpet.c
@@ -13,8 +13,8 @@
#define SMBUS_PCI_REG64 0x64
#define SMBUS_PCI_REGB4 0xb4
-#define HPET_MIN_CYCLES 64
-#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+#define HPET_MIN_CYCLES 16
+#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES * 12)
static DEFINE_SPINLOCK(hpet_lock);
DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device);
@@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt)
static int hpet_next_event(unsigned long delta,
struct clock_event_device *evt)
{
- unsigned int cnt;
- int res;
+ u32 cnt;
+ s32 res;
cnt = hpet_read(HPET_COUNTER);
- cnt += delta;
+ cnt += (u32) delta;
hpet_write(HPET_T0_CMP, cnt);
- res = (int)(cnt - hpet_read(HPET_COUNTER));
+ res = (s32)(cnt - hpet_read(HPET_COUNTER));
return res < HPET_MIN_CYCLES ? -ETIME : 0;
}
@@ -230,7 +230,7 @@ void __init setup_hpet_timer(void)
cd = &per_cpu(hpet_clockevent_device, cpu);
cd->name = "hpet";
- cd->rating = 320;
+ cd->rating = 100;
cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
cd->set_state_shutdown = hpet_set_state_shutdown;
cd->set_state_periodic = hpet_set_state_periodic;
diff --git a/kernel/arch/mips/loongson64/loongson-3/numa.c b/kernel/arch/mips/loongson64/loongson-3/numa.c
index 6f9e010ce..282c5a8c2 100644
--- a/kernel/arch/mips/loongson64/loongson-3/numa.c
+++ b/kernel/arch/mips/loongson64/loongson-3/numa.c
@@ -213,10 +213,10 @@ static void __init node_mem_init(unsigned int node)
BOOTMEM_DEFAULT);
if (node == 0 && node_end_pfn(0) >= (0xffffffff >> PAGE_SHIFT)) {
- /* Reserve 0xff800000~0xffffffff for RS780E integrated GPU */
+ /* Reserve 0xfe000000~0xffffffff for RS780E integrated GPU */
reserve_bootmem_node(NODE_DATA(node),
- (node_addrspace_offset | 0xff800000),
- 8 << 20, BOOTMEM_DEFAULT);
+ (node_addrspace_offset | 0xfe000000),
+ 32 << 20, BOOTMEM_DEFAULT);
}
sparse_memory_present_with_active_regions(node);
diff --git a/kernel/arch/mips/math-emu/cp1emu.c b/kernel/arch/mips/math-emu/cp1emu.c
index 32f0e19a0..734a2c766 100644
--- a/kernel/arch/mips/math-emu/cp1emu.c
+++ b/kernel/arch/mips/math-emu/cp1emu.c
@@ -445,9 +445,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
case spec_op:
switch (insn.r_format.func) {
case jalr_op:
- regs->regs[insn.r_format.rd] =
- regs->cp0_epc + dec_insn.pc_inc +
- dec_insn.next_pc_inc;
+ if (insn.r_format.rd != 0) {
+ regs->regs[insn.r_format.rd] =
+ regs->cp0_epc + dec_insn.pc_inc +
+ dec_insn.next_pc_inc;
+ }
/* Fall through */
case jr_op:
/* For R6, JR already emulated in jalr_op */
diff --git a/kernel/arch/mips/mm/cache.c b/kernel/arch/mips/mm/cache.c
index aab218c36..e87bccd6e 100644
--- a/kernel/arch/mips/mm/cache.c
+++ b/kernel/arch/mips/mm/cache.c
@@ -16,6 +16,7 @@
#include <linux/mm.h>
#include <asm/cacheflush.h>
+#include <asm/highmem.h>
#include <asm/processor.h>
#include <asm/cpu.h>
#include <asm/cpu-features.h>
@@ -83,8 +84,6 @@ void __flush_dcache_page(struct page *page)
struct address_space *mapping = page_mapping(page);
unsigned long addr;
- if (PageHighMem(page))
- return;
if (mapping && !mapping_mapped(mapping)) {
SetPageDcacheDirty(page);
return;
@@ -95,8 +94,15 @@ void __flush_dcache_page(struct page *page)
* case is for exec env/arg pages and those are %99 certainly going to
* get faulted into the tlb (and thus flushed) anyways.
*/
- addr = (unsigned long) page_address(page);
+ if (PageHighMem(page))
+ addr = (unsigned long)kmap_atomic(page);
+ else
+ addr = (unsigned long)page_address(page);
+
flush_data_cache_page(addr);
+
+ if (PageHighMem(page))
+ __kunmap_atomic((void *)addr);
}
EXPORT_SYMBOL(__flush_dcache_page);
@@ -119,33 +125,28 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr)
EXPORT_SYMBOL(__flush_anon_page);
-void __flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
- unsigned long addr;
-
- if (PageHighMem(page))
- return;
-
- addr = (unsigned long) page_address(page);
- flush_data_cache_page(addr);
-}
-EXPORT_SYMBOL_GPL(__flush_icache_page);
-
-void __update_cache(struct vm_area_struct *vma, unsigned long address,
- pte_t pte)
+void __update_cache(unsigned long address, pte_t pte)
{
struct page *page;
unsigned long pfn, addr;
- int exec = (vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc;
+ int exec = !pte_no_exec(pte) && !cpu_has_ic_fills_f_dc;
pfn = pte_pfn(pte);
if (unlikely(!pfn_valid(pfn)))
return;
page = pfn_to_page(pfn);
- if (page_mapping(page) && Page_dcache_dirty(page)) {
- addr = (unsigned long) page_address(page);
+ if (Page_dcache_dirty(page)) {
+ if (PageHighMem(page))
+ addr = (unsigned long)kmap_atomic(page);
+ else
+ addr = (unsigned long)page_address(page);
+
if (exec || pages_do_alias(addr, address & PAGE_MASK))
flush_data_cache_page(addr);
+
+ if (PageHighMem(page))
+ __kunmap_atomic((void *)addr);
+
ClearPageDcacheDirty(page);
}
}
diff --git a/kernel/arch/mips/mm/uasm-mips.c b/kernel/arch/mips/mm/uasm-mips.c
index b4a837893..5abe51cad 100644
--- a/kernel/arch/mips/mm/uasm-mips.c
+++ b/kernel/arch/mips/mm/uasm-mips.c
@@ -65,7 +65,7 @@ static struct insn insn_table[] = {
#ifndef CONFIG_CPU_MIPSR6
{ insn_cache, M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
#else
- { insn_cache, M6(cache_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 },
+ { insn_cache, M6(spec3_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 },
#endif
{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
diff --git a/kernel/arch/mips/mti-malta/malta-setup.c b/kernel/arch/mips/mti-malta/malta-setup.c
index 4740c82fb..36b09b2ea 100644
--- a/kernel/arch/mips/mti-malta/malta-setup.c
+++ b/kernel/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/kernel/arch/mips/vdso/Makefile b/kernel/arch/mips/vdso/Makefile
index 14568900f..6c7d78546 100644
--- a/kernel/arch/mips/vdso/Makefile
+++ b/kernel/arch/mips/vdso/Makefile
@@ -5,10 +5,12 @@ obj-vdso-y := elf.o gettimeofday.o sigreturn.o
ccflags-vdso := \
$(filter -I%,$(KBUILD_CFLAGS)) \
$(filter -E%,$(KBUILD_CFLAGS)) \
+ $(filter -mmicromips,$(KBUILD_CFLAGS)) \
$(filter -march=%,$(KBUILD_CFLAGS))
cflags-vdso := $(ccflags-vdso) \
$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
- -O2 -g -fPIC -fno-common -fno-builtin -G 0 -DDISABLE_BRANCH_PROFILING \
+ -O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
+ -DDISABLE_BRANCH_PROFILING \
$(call cc-option, -fno-stack-protector)
aflags-vdso := $(ccflags-vdso) \
$(filter -I%,$(KBUILD_CFLAGS)) \
@@ -73,7 +75,7 @@ obj-vdso := $(obj-vdso-y:%.o=$(obj)/%.o)
$(obj-vdso): KBUILD_CFLAGS := $(cflags-vdso) $(native-abi)
$(obj-vdso): KBUILD_AFLAGS := $(aflags-vdso) $(native-abi)
-$(obj)/vdso.lds: KBUILD_CPPFLAGS := $(native-abi)
+$(obj)/vdso.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) $(native-abi)
$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
$(call if_changed,vdsold)
diff --git a/kernel/arch/mn10300/include/asm/uaccess.h b/kernel/arch/mn10300/include/asm/uaccess.h
index 537278746..4af43d9ba 100644
--- a/kernel/arch/mn10300/include/asm/uaccess.h
+++ b/kernel/arch/mn10300/include/asm/uaccess.h
@@ -181,6 +181,7 @@ 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/kernel/arch/mn10300/lib/usercopy.c b/kernel/arch/mn10300/lib/usercopy.c
index 7826e6c36..ce8899e5e 100644
--- a/kernel/arch/mn10300/lib/usercopy.c
+++ b/kernel/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/kernel/arch/nios2/include/asm/uaccess.h b/kernel/arch/nios2/include/asm/uaccess.h
index caa51ff85..0ab82324c 100644
--- a/kernel/arch/nios2/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/openrisc/include/asm/uaccess.h b/kernel/arch/openrisc/include/asm/uaccess.h
index a6bd07ca3..5cc6b4f1b 100644
--- a/kernel/arch/openrisc/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/parisc/include/asm/bitops.h b/kernel/arch/parisc/include/asm/bitops.h
index 3f9406d9b..da8794332 100644
--- a/kernel/arch/parisc/include/asm/bitops.h
+++ b/kernel/arch/parisc/include/asm/bitops.h
@@ -6,7 +6,7 @@
#endif
#include <linux/compiler.h>
-#include <asm/types.h> /* for BITS_PER_LONG/SHIFT_PER_LONG */
+#include <asm/types.h>
#include <asm/byteorder.h>
#include <asm/barrier.h>
#include <linux/atomic.h>
@@ -17,6 +17,12 @@
* to include/asm-i386/bitops.h or kerneldoc
*/
+#if __BITS_PER_LONG == 64
+#define SHIFT_PER_LONG 6
+#else
+#define SHIFT_PER_LONG 5
+#endif
+
#define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
diff --git a/kernel/arch/parisc/include/asm/pgtable.h b/kernel/arch/parisc/include/asm/pgtable.h
index 291cee28c..3a4ed9f91 100644
--- a/kernel/arch/parisc/include/asm/pgtable.h
+++ b/kernel/arch/parisc/include/asm/pgtable.h
@@ -65,9 +65,9 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
unsigned long flags; \
spin_lock_irqsave(&pa_tlb_lock, flags); \
old_pte = *ptep; \
- set_pte(ptep, pteval); \
if (pte_inserted(old_pte)) \
purge_tlb_entries(mm, addr); \
+ set_pte(ptep, pteval); \
spin_unlock_irqrestore(&pa_tlb_lock, flags); \
} while (0)
@@ -83,10 +83,10 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
/* This is the size of the initially mapped kernel memory */
-#ifdef CONFIG_64BIT
-#define KERNEL_INITIAL_ORDER 25 /* 1<<25 = 32MB */
+#if defined(CONFIG_64BIT)
+#define KERNEL_INITIAL_ORDER 26 /* 1<<26 = 64MB */
#else
-#define KERNEL_INITIAL_ORDER 24 /* 1<<24 = 16MB */
+#define KERNEL_INITIAL_ORDER 25 /* 1<<25 = 32MB */
#endif
#define KERNEL_INITIAL_SIZE (1 << KERNEL_INITIAL_ORDER)
@@ -478,8 +478,8 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
spin_unlock_irqrestore(&pa_tlb_lock, flags);
return 0;
}
- set_pte(ptep, pte_mkold(pte));
purge_tlb_entries(vma->vm_mm, addr);
+ set_pte(ptep, pte_mkold(pte));
spin_unlock_irqrestore(&pa_tlb_lock, flags);
return 1;
}
@@ -492,9 +492,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
spin_lock_irqsave(&pa_tlb_lock, flags);
old_pte = *ptep;
- set_pte(ptep, __pte(0));
if (pte_inserted(old_pte))
purge_tlb_entries(mm, addr);
+ set_pte(ptep, __pte(0));
spin_unlock_irqrestore(&pa_tlb_lock, flags);
return old_pte;
@@ -504,8 +504,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
{
unsigned long flags;
spin_lock_irqsave(&pa_tlb_lock, flags);
- set_pte(ptep, pte_wrprotect(*ptep));
purge_tlb_entries(mm, addr);
+ set_pte(ptep, pte_wrprotect(*ptep));
spin_unlock_irqrestore(&pa_tlb_lock, flags);
}
diff --git a/kernel/arch/parisc/include/asm/uaccess.h b/kernel/arch/parisc/include/asm/uaccess.h
index 0abdd4c60..4ad514658 100644
--- a/kernel/arch/parisc/include/asm/uaccess.h
+++ b/kernel/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
@@ -76,6 +77,7 @@ struct exception_table_entry {
*/
struct exception_data {
unsigned long fault_ip;
+ unsigned long fault_gp;
unsigned long fault_space;
unsigned long fault_addr;
};
@@ -244,13 +246,14 @@ 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 || !__builtin_constant_p(n) || sz >= n))
ret = __copy_from_user(to, from, n);
else
copy_from_user_overflow();
-
+ if (unlikely(ret))
+ memset(to + (n - ret), 0, ret);
return ret;
}
diff --git a/kernel/arch/parisc/include/uapi/asm/bitsperlong.h b/kernel/arch/parisc/include/uapi/asm/bitsperlong.h
index e0a23c7bd..07fa7e50b 100644
--- a/kernel/arch/parisc/include/uapi/asm/bitsperlong.h
+++ b/kernel/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -3,10 +3,8 @@
#if defined(__LP64__)
#define __BITS_PER_LONG 64
-#define SHIFT_PER_LONG 6
#else
#define __BITS_PER_LONG 32
-#define SHIFT_PER_LONG 5
#endif
#include <asm-generic/bitsperlong.h>
diff --git a/kernel/arch/parisc/include/uapi/asm/errno.h b/kernel/arch/parisc/include/uapi/asm/errno.h
index c0ae62520..274d5bc6e 100644
--- a/kernel/arch/parisc/include/uapi/asm/errno.h
+++ b/kernel/arch/parisc/include/uapi/asm/errno.h
@@ -97,10 +97,10 @@
#define ENOTCONN 235 /* Transport endpoint is not connected */
#define ESHUTDOWN 236 /* Cannot send after transport endpoint shutdown */
#define ETOOMANYREFS 237 /* Too many references: cannot splice */
-#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */
#define ETIMEDOUT 238 /* Connection timed out */
#define ECONNREFUSED 239 /* Connection refused */
-#define EREMOTERELEASE 240 /* Remote peer released connection */
+#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */
+#define EREMOTERELEASE 240 /* Remote peer released connection */
#define EHOSTDOWN 241 /* Host is down */
#define EHOSTUNREACH 242 /* No route to host */
diff --git a/kernel/arch/parisc/include/uapi/asm/swab.h b/kernel/arch/parisc/include/uapi/asm/swab.h
index e78403b12..928e1bbac 100644
--- a/kernel/arch/parisc/include/uapi/asm/swab.h
+++ b/kernel/arch/parisc/include/uapi/asm/swab.h
@@ -1,6 +1,7 @@
#ifndef _PARISC_SWAB_H
#define _PARISC_SWAB_H
+#include <asm/bitsperlong.h>
#include <linux/types.h>
#include <linux/compiler.h>
@@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
}
#define __arch_swab32 __arch_swab32
-#if BITS_PER_LONG > 32
+#if __BITS_PER_LONG > 32
/*
** From "PA-RISC 2.0 Architecture", HP Professional Books.
** See Appendix I page 8 , "Endian Byte Swapping".
@@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
return x;
}
#define __arch_swab64 __arch_swab64
-#endif /* BITS_PER_LONG > 32 */
+#endif /* __BITS_PER_LONG > 32 */
#endif /* _PARISC_SWAB_H */
diff --git a/kernel/arch/parisc/kernel/asm-offsets.c b/kernel/arch/parisc/kernel/asm-offsets.c
index d2f62570a..78d30d2ea 100644
--- a/kernel/arch/parisc/kernel/asm-offsets.c
+++ b/kernel/arch/parisc/kernel/asm-offsets.c
@@ -299,6 +299,7 @@ int main(void)
#endif
BLANK();
DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip));
+ DEFINE(EXCDATA_GP, offsetof(struct exception_data, fault_gp));
DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space));
DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr));
BLANK();
diff --git a/kernel/arch/parisc/kernel/cache.c b/kernel/arch/parisc/kernel/cache.c
index cda6dbbe9..6857a104b 100644
--- a/kernel/arch/parisc/kernel/cache.c
+++ b/kernel/arch/parisc/kernel/cache.c
@@ -351,6 +351,7 @@ void __init parisc_setup_cache_timing(void)
{
unsigned long rangetime, alltime;
unsigned long size, start;
+ unsigned long threshold;
alltime = mfctl(16);
flush_data_cache();
@@ -364,26 +365,30 @@ void __init parisc_setup_cache_timing(void)
printk(KERN_DEBUG "Whole cache flush %lu cycles, flushing %lu bytes %lu cycles\n",
alltime, size, rangetime);
- /* Racy, but if we see an intermediate value, it's ok too... */
- parisc_cache_flush_threshold = size * alltime / rangetime;
-
- parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold);
- if (!parisc_cache_flush_threshold)
- parisc_cache_flush_threshold = FLUSH_THRESHOLD;
-
- if (parisc_cache_flush_threshold > cache_info.dc_size)
- parisc_cache_flush_threshold = cache_info.dc_size;
-
- printk(KERN_INFO "Setting cache flush threshold to %lu kB\n",
+ threshold = L1_CACHE_ALIGN(size * alltime / rangetime);
+ if (threshold > cache_info.dc_size)
+ threshold = cache_info.dc_size;
+ if (threshold)
+ parisc_cache_flush_threshold = threshold;
+ printk(KERN_INFO "Cache flush threshold set to %lu KiB\n",
parisc_cache_flush_threshold/1024);
/* calculate TLB flush threshold */
+ /* On SMP machines, skip the TLB measure of kernel text which
+ * has been mapped as huge pages. */
+ if (num_online_cpus() > 1 && !parisc_requires_coherency()) {
+ threshold = max(cache_info.it_size, cache_info.dt_size);
+ threshold *= PAGE_SIZE;
+ threshold /= num_online_cpus();
+ goto set_tlb_threshold;
+ }
+
alltime = mfctl(16);
flush_tlb_all();
alltime = mfctl(16) - alltime;
- size = PAGE_SIZE;
+ size = 0;
start = (unsigned long) _text;
rangetime = mfctl(16);
while (start < (unsigned long) _end) {
@@ -396,13 +401,12 @@ void __init parisc_setup_cache_timing(void)
printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
alltime, size, rangetime);
- parisc_tlb_flush_threshold = size * alltime / rangetime;
- parisc_tlb_flush_threshold *= num_online_cpus();
- parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold);
- if (!parisc_tlb_flush_threshold)
- parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
+ threshold = PAGE_ALIGN(num_online_cpus() * size * alltime / rangetime);
- printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n",
+set_tlb_threshold:
+ if (threshold)
+ parisc_tlb_flush_threshold = threshold;
+ printk(KERN_INFO "TLB flush threshold set to %lu KiB\n",
parisc_tlb_flush_threshold/1024);
}
diff --git a/kernel/arch/parisc/kernel/pacache.S b/kernel/arch/parisc/kernel/pacache.S
index b743a80ea..a4761b772 100644
--- a/kernel/arch/parisc/kernel/pacache.S
+++ b/kernel/arch/parisc/kernel/pacache.S
@@ -96,7 +96,7 @@ fitmanyloop: /* Loop if LOOP >= 2 */
fitmanymiddle: /* Loop if LOOP >= 2 */
addib,COND(>) -1, %r31, fitmanymiddle /* Adjusted inner loop decr */
- pitlbe 0(%sr1, %r28)
+ pitlbe %r0(%sr1, %r28)
pitlbe,m %arg1(%sr1, %r28) /* Last pitlbe and addr adjust */
addib,COND(>) -1, %r29, fitmanymiddle /* Middle loop decr */
copy %arg3, %r31 /* Re-init inner loop count */
@@ -139,7 +139,7 @@ fdtmanyloop: /* Loop if LOOP >= 2 */
fdtmanymiddle: /* Loop if LOOP >= 2 */
addib,COND(>) -1, %r31, fdtmanymiddle /* Adjusted inner loop decr */
- pdtlbe 0(%sr1, %r28)
+ pdtlbe %r0(%sr1, %r28)
pdtlbe,m %arg1(%sr1, %r28) /* Last pdtlbe and addr adjust */
addib,COND(>) -1, %r29, fdtmanymiddle /* Middle loop decr */
copy %arg3, %r31 /* Re-init inner loop count */
@@ -620,12 +620,12 @@ ENTRY(copy_user_page_asm)
/* Purge any old translations */
#ifdef CONFIG_PA20
- pdtlb,l 0(%r28)
- pdtlb,l 0(%r29)
+ pdtlb,l %r0(%r28)
+ pdtlb,l %r0(%r29)
#else
tlb_lock %r20,%r21,%r22
- pdtlb 0(%r28)
- pdtlb 0(%r29)
+ pdtlb %r0(%r28)
+ pdtlb %r0(%r29)
tlb_unlock %r20,%r21,%r22
#endif
@@ -768,10 +768,10 @@ ENTRY(clear_user_page_asm)
/* Purge any old translation */
#ifdef CONFIG_PA20
- pdtlb,l 0(%r28)
+ pdtlb,l %r0(%r28)
#else
tlb_lock %r20,%r21,%r22
- pdtlb 0(%r28)
+ pdtlb %r0(%r28)
tlb_unlock %r20,%r21,%r22
#endif
@@ -852,10 +852,10 @@ ENTRY(flush_dcache_page_asm)
/* Purge any old translation */
#ifdef CONFIG_PA20
- pdtlb,l 0(%r28)
+ pdtlb,l %r0(%r28)
#else
tlb_lock %r20,%r21,%r22
- pdtlb 0(%r28)
+ pdtlb %r0(%r28)
tlb_unlock %r20,%r21,%r22
#endif
@@ -886,19 +886,10 @@ ENTRY(flush_dcache_page_asm)
fdc,m r31(%r28)
fdc,m r31(%r28)
fdc,m r31(%r28)
- cmpb,COND(<<) %r28, %r25,1b
+ cmpb,COND(<<) %r28, %r25,1b
fdc,m r31(%r28)
sync
-
-#ifdef CONFIG_PA20
- pdtlb,l 0(%r25)
-#else
- tlb_lock %r20,%r21,%r22
- pdtlb 0(%r25)
- tlb_unlock %r20,%r21,%r22
-#endif
-
bv %r0(%r2)
nop
.exit
@@ -925,13 +916,18 @@ ENTRY(flush_icache_page_asm)
depwi 0, 31,PAGE_SHIFT, %r28 /* Clear any offset bits */
#endif
- /* Purge any old translation */
+ /* Purge any old translation. Note that the FIC instruction
+ * may use either the instruction or data TLB. Given that we
+ * have a flat address space, it's not clear which TLB will be
+ * used. So, we purge both entries. */
#ifdef CONFIG_PA20
+ pdtlb,l %r0(%r28)
pitlb,l %r0(%sr4,%r28)
#else
tlb_lock %r20,%r21,%r22
- pitlb (%sr4,%r28)
+ pdtlb %r0(%r28)
+ pitlb %r0(%sr4,%r28)
tlb_unlock %r20,%r21,%r22
#endif
@@ -968,15 +964,6 @@ ENTRY(flush_icache_page_asm)
fic,m %r31(%sr4,%r28)
sync
-
-#ifdef CONFIG_PA20
- pitlb,l %r0(%sr4,%r25)
-#else
- tlb_lock %r20,%r21,%r22
- pitlb (%sr4,%r25)
- tlb_unlock %r20,%r21,%r22
-#endif
-
bv %r0(%r2)
nop
.exit
diff --git a/kernel/arch/parisc/kernel/parisc_ksyms.c b/kernel/arch/parisc/kernel/parisc_ksyms.c
index 568b2c61e..3cad8aadc 100644
--- a/kernel/arch/parisc/kernel/parisc_ksyms.c
+++ b/kernel/arch/parisc/kernel/parisc_ksyms.c
@@ -47,11 +47,11 @@ EXPORT_SYMBOL(__cmpxchg_u64);
EXPORT_SYMBOL(lclear_user);
EXPORT_SYMBOL(lstrnlen_user);
-/* Global fixups */
-extern void fixup_get_user_skip_1(void);
-extern void fixup_get_user_skip_2(void);
-extern void fixup_put_user_skip_1(void);
-extern void fixup_put_user_skip_2(void);
+/* Global fixups - defined as int to avoid creation of function pointers */
+extern int fixup_get_user_skip_1;
+extern int fixup_get_user_skip_2;
+extern int fixup_put_user_skip_1;
+extern int fixup_put_user_skip_2;
EXPORT_SYMBOL(fixup_get_user_skip_1);
EXPORT_SYMBOL(fixup_get_user_skip_2);
EXPORT_SYMBOL(fixup_put_user_skip_1);
diff --git a/kernel/arch/parisc/kernel/pci-dma.c b/kernel/arch/parisc/kernel/pci-dma.c
index b9402c9b3..af0d7fae7 100644
--- a/kernel/arch/parisc/kernel/pci-dma.c
+++ b/kernel/arch/parisc/kernel/pci-dma.c
@@ -95,8 +95,8 @@ static inline int map_pte_uncached(pte_t * pte,
if (!pte_none(*pte))
printk(KERN_ERR "map_pte_uncached: page already exists\n");
- set_pte(pte, __mk_pte(*paddr_ptr, PAGE_KERNEL_UNC));
purge_tlb_start(flags);
+ set_pte(pte, __mk_pte(*paddr_ptr, PAGE_KERNEL_UNC));
pdtlb_kernel(orig_vaddr);
purge_tlb_end(flags);
vaddr += PAGE_SIZE;
diff --git a/kernel/arch/parisc/kernel/setup.c b/kernel/arch/parisc/kernel/setup.c
index f7ea626e2..2e66a8877 100644
--- a/kernel/arch/parisc/kernel/setup.c
+++ b/kernel/arch/parisc/kernel/setup.c
@@ -38,6 +38,7 @@
#include <linux/export.h>
#include <asm/processor.h>
+#include <asm/sections.h>
#include <asm/pdc.h>
#include <asm/led.h>
#include <asm/machdep.h> /* for pa7300lc_init() proto */
@@ -140,6 +141,13 @@ void __init setup_arch(char **cmdline_p)
#endif
printk(KERN_CONT ".\n");
+ /*
+ * Check if initial kernel page mappings are sufficient.
+ * panic early if not, else we may access kernel functions
+ * and variables which can't be reached.
+ */
+ if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE)
+ panic("KERNEL_INITIAL_ORDER too small!");
pdc_console_init();
@@ -326,6 +334,10 @@ static int __init parisc_init(void)
/* tell PDC we're Linux. Nevermind failure. */
pdc_stable_write(0x40, &osid, sizeof(osid));
+ /* start with known state */
+ flush_cache_all_local();
+ flush_tlb_all_local(NULL);
+
processor_init();
#ifdef CONFIG_SMP
pr_info("CPU(s): %d out of %d %s at %d.%06d MHz online\n",
diff --git a/kernel/arch/parisc/kernel/syscall.S b/kernel/arch/parisc/kernel/syscall.S
index fbafa0d0e..a86b19fcc 100644
--- a/kernel/arch/parisc/kernel/syscall.S
+++ b/kernel/arch/parisc/kernel/syscall.S
@@ -106,8 +106,6 @@ linux_gateway_entry:
mtsp %r0,%sr4 /* get kernel space into sr4 */
mtsp %r0,%sr5 /* get kernel space into sr5 */
mtsp %r0,%sr6 /* get kernel space into sr6 */
- mfsp %sr7,%r1 /* save user sr7 */
- mtsp %r1,%sr3 /* and store it in sr3 */
#ifdef CONFIG_64BIT
/* for now we can *always* set the W bit on entry to the syscall
@@ -133,6 +131,14 @@ linux_gateway_entry:
depdi 0, 31, 32, %r21
1:
#endif
+
+ /* We use a rsm/ssm pair to prevent sr3 from being clobbered
+ * by external interrupts.
+ */
+ mfsp %sr7,%r1 /* save user sr7 */
+ rsm PSW_SM_I, %r0 /* disable interrupts */
+ mtsp %r1,%sr3 /* and store it in sr3 */
+
mfctl %cr30,%r1
xor %r1,%r30,%r30 /* ye olde xor trick */
xor %r1,%r30,%r1
@@ -147,6 +153,7 @@ linux_gateway_entry:
*/
mtsp %r0,%sr7 /* get kernel space into sr7 */
+ ssm PSW_SM_I, %r0 /* enable interrupts */
STREGM %r1,FRAME_SIZE(%r30) /* save r1 (usp) here for now */
mfctl %cr30,%r1 /* get task ptr in %r1 */
LDREG TI_TASK(%r1),%r1
diff --git a/kernel/arch/parisc/kernel/traps.c b/kernel/arch/parisc/kernel/traps.c
index 553b09855..77e2262c9 100644
--- a/kernel/arch/parisc/kernel/traps.c
+++ b/kernel/arch/parisc/kernel/traps.c
@@ -798,6 +798,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
if (fault_space == 0 && !faulthandler_disabled())
{
+ /* Clean up and return if in exception table. */
+ if (fixup_exception(regs))
+ return;
pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
parisc_terminate("Kernel Fault", regs, code, fault_address);
}
diff --git a/kernel/arch/parisc/kernel/unaligned.c b/kernel/arch/parisc/kernel/unaligned.c
index d7c0acb35..8d49614d6 100644
--- a/kernel/arch/parisc/kernel/unaligned.c
+++ b/kernel/arch/parisc/kernel/unaligned.c
@@ -666,7 +666,7 @@ void handle_unaligned(struct pt_regs *regs)
break;
}
- if (modify && R1(regs->iir))
+ if (ret == 0 && modify && R1(regs->iir))
regs->gr[R1(regs->iir)] = newbase;
@@ -677,6 +677,14 @@ void handle_unaligned(struct pt_regs *regs)
if (ret)
{
+ /*
+ * The unaligned handler failed.
+ * If we were called by __get_user() or __put_user() jump
+ * to it's exception fixup handler instead of crashing.
+ */
+ if (!user_mode(regs) && fixup_exception(regs))
+ return;
+
printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret);
die_if_kernel("Unaligned data reference", regs, 28);
diff --git a/kernel/arch/parisc/kernel/vmlinux.lds.S b/kernel/arch/parisc/kernel/vmlinux.lds.S
index 308f29081..60771df10 100644
--- a/kernel/arch/parisc/kernel/vmlinux.lds.S
+++ b/kernel/arch/parisc/kernel/vmlinux.lds.S
@@ -88,8 +88,9 @@ SECTIONS
/* Start of data section */
_sdata = .;
- RO_DATA_SECTION(8)
-
+ /* Architecturally we need to keep __gp below 0x1000000 and thus
+ * in front of RO_DATA_SECTION() which stores lots of tracepoint
+ * and ftrace symbols. */
#ifdef CONFIG_64BIT
. = ALIGN(16);
/* Linkage tables */
@@ -104,6 +105,8 @@ SECTIONS
}
#endif
+ RO_DATA_SECTION(8)
+
/* unwind info */
.PARISC.unwind : {
__start___unwind = .;
diff --git a/kernel/arch/parisc/lib/fixup.S b/kernel/arch/parisc/lib/fixup.S
index 536ef66bb..1052b747e 100644
--- a/kernel/arch/parisc/lib/fixup.S
+++ b/kernel/arch/parisc/lib/fixup.S
@@ -26,6 +26,7 @@
#ifdef CONFIG_SMP
.macro get_fault_ip t1 t2
+ loadgp
addil LT%__per_cpu_offset,%r27
LDREG RT%__per_cpu_offset(%r1),\t1
/* t2 = smp_processor_id() */
@@ -40,14 +41,19 @@
LDREG RT%exception_data(%r1),\t1
/* t1 = this_cpu_ptr(&exception_data) */
add,l \t1,\t2,\t1
+ /* %r27 = t1->fault_gp - restore gp */
+ LDREG EXCDATA_GP(\t1), %r27
/* t1 = t1->fault_ip */
LDREG EXCDATA_IP(\t1), \t1
.endm
#else
.macro get_fault_ip t1 t2
+ loadgp
/* t1 = this_cpu_ptr(&exception_data) */
addil LT%exception_data,%r27
LDREG RT%exception_data(%r1),\t2
+ /* %r27 = t2->fault_gp - restore gp */
+ LDREG EXCDATA_GP(\t2), %r27
/* t1 = t2->fault_ip */
LDREG EXCDATA_IP(\t2), \t1
.endm
diff --git a/kernel/arch/parisc/mm/fault.c b/kernel/arch/parisc/mm/fault.c
index a762864ec..f90644499 100644
--- a/kernel/arch/parisc/mm/fault.c
+++ b/kernel/arch/parisc/mm/fault.c
@@ -151,6 +151,7 @@ int fixup_exception(struct pt_regs *regs)
struct exception_data *d;
d = this_cpu_ptr(&exception_data);
d->fault_ip = regs->iaoq[0];
+ d->fault_gp = regs->gr[27];
d->fault_space = regs->isr;
d->fault_addr = regs->ior;
diff --git a/kernel/arch/powerpc/boot/ps3-head.S b/kernel/arch/powerpc/boot/ps3-head.S
index b6fcbaf50..3dc44b05f 100644
--- a/kernel/arch/powerpc/boot/ps3-head.S
+++ b/kernel/arch/powerpc/boot/ps3-head.S
@@ -57,11 +57,6 @@ __system_reset_overlay:
bctr
1:
- /* Save the value at addr zero for a null pointer write check later. */
-
- li r4, 0
- lwz r3, 0(r4)
-
/* Primary delays then goes to _zimage_start in wrapper. */
or 31, 31, 31 /* db16cyc */
diff --git a/kernel/arch/powerpc/boot/ps3.c b/kernel/arch/powerpc/boot/ps3.c
index 4ec2d86d3..a05558a7e 100644
--- a/kernel/arch/powerpc/boot/ps3.c
+++ b/kernel/arch/powerpc/boot/ps3.c
@@ -119,13 +119,12 @@ void ps3_copy_vectors(void)
flush_cache((void *)0x100, 512);
}
-void platform_init(unsigned long null_check)
+void platform_init(void)
{
const u32 heapsize = 0x1000000 - (u32)_end; /* 16MiB */
void *chosen;
unsigned long ft_addr;
u64 rm_size;
- unsigned long val;
console_ops.write = ps3_console_write;
platform_ops.exit = ps3_exit;
@@ -153,11 +152,6 @@ void platform_init(unsigned long null_check)
printf(" flat tree at 0x%lx\n\r", ft_addr);
- val = *(unsigned long *)0;
-
- if (val != null_check)
- printf("null check failed: %lx != %lx\n\r", val, null_check);
-
((kernel_entry_t)0)(ft_addr, 0, NULL);
ps3_exit();
diff --git a/kernel/arch/powerpc/include/asm/icswx.h b/kernel/arch/powerpc/include/asm/icswx.h
index 9f8402b35..27e588f6c 100644
--- a/kernel/arch/powerpc/include/asm/icswx.h
+++ b/kernel/arch/powerpc/include/asm/icswx.h
@@ -164,6 +164,7 @@ struct coprocessor_request_block {
#define ICSWX_INITIATED (0x8)
#define ICSWX_BUSY (0x4)
#define ICSWX_REJECTED (0x2)
+#define ICSWX_XERS0 (0x1) /* undefined or set from XERSO. */
static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb)
{
diff --git a/kernel/arch/powerpc/include/asm/kvm_host.h b/kernel/arch/powerpc/include/asm/kvm_host.h
index f8673ff84..203765805 100644
--- a/kernel/arch/powerpc/include/asm/kvm_host.h
+++ b/kernel/arch/powerpc/include/asm/kvm_host.h
@@ -545,6 +545,7 @@ struct kvm_vcpu_arch {
u64 tfiar;
u32 cr_tm;
+ u64 xer_tm;
u64 lr_tm;
u64 ctr_tm;
u64 amr_tm;
diff --git a/kernel/arch/powerpc/include/asm/reg.h b/kernel/arch/powerpc/include/asm/reg.h
index 2220f7a60..627d129d7 100644
--- a/kernel/arch/powerpc/include/asm/reg.h
+++ b/kernel/arch/powerpc/include/asm/reg.h
@@ -707,7 +707,8 @@
#define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */
#define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */
#define SPRN_MMCR1 798
-#define SPRN_MMCR2 769
+#define SPRN_MMCR2 785
+#define SPRN_UMMCR2 769
#define SPRN_MMCRA 0x312
#define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */
#define MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -744,13 +745,13 @@
#define SPRN_PMC6 792
#define SPRN_PMC7 793
#define SPRN_PMC8 794
-#define SPRN_SIAR 780
-#define SPRN_SDAR 781
#define SPRN_SIER 784
#define SIER_SIPR 0x2000000 /* Sampled MSR_PR */
#define SIER_SIHV 0x1000000 /* Sampled MSR_HV */
#define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */
#define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */
+#define SPRN_SIAR 796
+#define SPRN_SDAR 797
#define SPRN_TACR 888
#define SPRN_TCSCR 889
#define SPRN_CSIGR 890
diff --git a/kernel/arch/powerpc/include/asm/uaccess.h b/kernel/arch/powerpc/include/asm/uaccess.h
index 2a8ebae09..a5ffe0207 100644
--- a/kernel/arch/powerpc/include/asm/uaccess.h
+++ b/kernel/arch/powerpc/include/asm/uaccess.h
@@ -323,30 +323,17 @@ 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 (likely(access_ok(VERIFY_READ, from, n)))
return __copy_tofrom_user((__force void __user *)to, from, n);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- 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))
return __copy_tofrom_user(to, (__force void __user *)from, n);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- return __copy_tofrom_user(to, (__force void __user *)from,
- n - over) + over;
- }
return n;
}
@@ -437,10 +424,6 @@ 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/kernel/arch/powerpc/include/asm/word-at-a-time.h b/kernel/arch/powerpc/include/asm/word-at-a-time.h
index e4396a7d0..4afe66aa1 100644
--- a/kernel/arch/powerpc/include/asm/word-at-a-time.h
+++ b/kernel/arch/powerpc/include/asm/word-at-a-time.h
@@ -82,7 +82,7 @@ static inline unsigned long create_zero_mask(unsigned long bits)
"andc %1,%1,%2\n\t"
"popcntd %0,%1"
: "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask)
- : "r" (bits));
+ : "b" (bits));
return leading_zero_bits;
}
diff --git a/kernel/arch/powerpc/include/uapi/asm/cputable.h b/kernel/arch/powerpc/include/uapi/asm/cputable.h
index 43686043e..2734c005d 100644
--- a/kernel/arch/powerpc/include/uapi/asm/cputable.h
+++ b/kernel/arch/powerpc/include/uapi/asm/cputable.h
@@ -31,6 +31,7 @@
#define PPC_FEATURE_PSERIES_PERFMON_COMPAT \
0x00000040
+/* Reserved - do not use 0x00000004 */
#define PPC_FEATURE_TRUE_LE 0x00000002
#define PPC_FEATURE_PPC_LE 0x00000001
diff --git a/kernel/arch/powerpc/include/uapi/asm/kvm.h b/kernel/arch/powerpc/include/uapi/asm/kvm.h
index ab4d4732c..720b71a63 100644
--- a/kernel/arch/powerpc/include/uapi/asm/kvm.h
+++ b/kernel/arch/powerpc/include/uapi/asm/kvm.h
@@ -587,6 +587,7 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
#define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
#define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
/* PPC64 eXternal Interrupt Controller Specification */
#define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */
diff --git a/kernel/arch/powerpc/kernel/asm-offsets.c b/kernel/arch/powerpc/kernel/asm-offsets.c
index d6d0c59ef..bd0408153 100644
--- a/kernel/arch/powerpc/kernel/asm-offsets.c
+++ b/kernel/arch/powerpc/kernel/asm-offsets.c
@@ -585,6 +585,7 @@ int main(void)
DEFINE(VCPU_VRS_TM, offsetof(struct kvm_vcpu, arch.vr_tm.vr));
DEFINE(VCPU_VRSAVE_TM, offsetof(struct kvm_vcpu, arch.vrsave_tm));
DEFINE(VCPU_CR_TM, offsetof(struct kvm_vcpu, arch.cr_tm));
+ DEFINE(VCPU_XER_TM, offsetof(struct kvm_vcpu, arch.xer_tm));
DEFINE(VCPU_LR_TM, offsetof(struct kvm_vcpu, arch.lr_tm));
DEFINE(VCPU_CTR_TM, offsetof(struct kvm_vcpu, arch.ctr_tm));
DEFINE(VCPU_AMR_TM, offsetof(struct kvm_vcpu, arch.amr_tm));
diff --git a/kernel/arch/powerpc/kernel/eeh.c b/kernel/arch/powerpc/kernel/eeh.c
index 40e4d4a27..98949b0df 100644
--- a/kernel/arch/powerpc/kernel/eeh.c
+++ b/kernel/arch/powerpc/kernel/eeh.c
@@ -677,7 +677,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
/* Check if the request is finished successfully */
if (active_flag) {
rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
- if (rc <= 0)
+ if (rc < 0)
return rc;
if (rc & active_flag)
@@ -1072,7 +1072,7 @@ void eeh_add_device_early(struct pci_dn *pdn)
struct pci_controller *phb;
struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
- if (!edev || !eeh_enabled())
+ if (!edev)
return;
if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
diff --git a/kernel/arch/powerpc/kernel/eeh_driver.c b/kernel/arch/powerpc/kernel/eeh_driver.c
index 52c1e273f..c314db8b7 100644
--- a/kernel/arch/powerpc/kernel/eeh_driver.c
+++ b/kernel/arch/powerpc/kernel/eeh_driver.c
@@ -166,6 +166,16 @@ static void *eeh_dev_save_state(void *data, void *userdata)
if (!edev)
return NULL;
+ /*
+ * We cannot access the config space on some adapters.
+ * Otherwise, it will cause fenced PHB. We don't save
+ * the content in their config space and will restore
+ * from the initial config space saved when the EEH
+ * device is created.
+ */
+ if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED))
+ return NULL;
+
pdev = eeh_dev_to_pci_dev(edev);
if (!pdev)
return NULL;
@@ -305,6 +315,19 @@ static void *eeh_dev_restore_state(void *data, void *userdata)
if (!edev)
return NULL;
+ /*
+ * The content in the config space isn't saved because
+ * the blocked config space on some adapters. We have
+ * to restore the initial saved config space when the
+ * EEH device is created.
+ */
+ if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) {
+ if (list_is_last(&edev->list, &edev->pe->edevs))
+ eeh_pe_restore_bars(edev->pe);
+
+ return NULL;
+ }
+
pdev = eeh_dev_to_pci_dev(edev);
if (!pdev)
return NULL;
@@ -462,7 +485,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
{
struct eeh_pe *pe = (struct eeh_pe *)data;
- bool *clear_sw_state = flag;
+ bool clear_sw_state = *(bool *)flag;
int i, rc = 1;
for (i = 0; rc && i < 3; i++)
@@ -504,9 +527,6 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
/* Save states */
eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);
- /* Report error */
- eeh_pe_dev_traverse(pe, eeh_report_error, &result);
-
/* Issue reset */
ret = eeh_reset_pe(pe);
if (ret) {
@@ -592,8 +612,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
/* Clear frozen state */
rc = eeh_clear_pe_frozen_state(pe, false);
- if (rc)
+ if (rc) {
+ pci_unlock_rescan_remove();
return rc;
+ }
/* Give the system 5 seconds to finish running the user-space
* hotplug shutdown scripts, e.g. ifdown for ethernet. Yes,
@@ -889,6 +911,14 @@ static void eeh_handle_special_event(void)
/* Notify all devices to be down */
eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
bus = eeh_pe_bus_get(phb_pe);
+ if (!bus) {
+ pr_err("%s: Cannot find PCI bus for "
+ "PHB#%d-PE#%x\n",
+ __func__,
+ pe->phb->global_number,
+ pe->addr);
+ break;
+ }
eeh_pe_dev_traverse(pe,
eeh_report_failure, NULL);
pcibios_remove_pci_devices(bus);
diff --git a/kernel/arch/powerpc/kernel/entry_64.S b/kernel/arch/powerpc/kernel/entry_64.S
index 5bb3148e5..1aae3fdb0 100644
--- a/kernel/arch/powerpc/kernel/entry_64.S
+++ b/kernel/arch/powerpc/kernel/entry_64.S
@@ -334,13 +334,13 @@ syscall_exit_work:
tabort_syscall:
/* Firstly we need to enable TM in the kernel */
mfmsr r10
- li r13, 1
- rldimi r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+ li r9, 1
+ rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG
mtmsrd r10, 0
/* tabort, this dooms the transaction, nothing else */
- li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
- TABORT(R13)
+ li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+ TABORT(R9)
/*
* Return directly to userspace. We have corrupted user register state,
@@ -348,8 +348,8 @@ tabort_syscall:
* resume after the tbegin of the aborted transaction with the
* checkpointed register state.
*/
- li r13, MSR_RI
- andc r10, r10, r13
+ li r9, MSR_RI
+ andc r10, r10, r9
mtmsrd r10, 1
mtspr SPRN_SRR0, r11
mtspr SPRN_SRR1, r12
diff --git a/kernel/arch/powerpc/kernel/exceptions-64s.S b/kernel/arch/powerpc/kernel/exceptions-64s.S
index 0a0399c2a..b81ccc5fb 100644
--- a/kernel/arch/powerpc/kernel/exceptions-64s.S
+++ b/kernel/arch/powerpc/kernel/exceptions-64s.S
@@ -962,11 +962,6 @@ hv_facility_unavailable_relon_trampoline:
#endif
STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist)
- /* Other future vectors */
- .align 7
- .globl __end_interrupts
-__end_interrupts:
-
.align 7
system_call_entry:
b system_call_common
@@ -1253,6 +1248,17 @@ __end_handlers:
STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
+ /*
+ * The __end_interrupts marker must be past the out-of-line (OOL)
+ * handlers, so that they are copied to real address 0x100 when running
+ * a relocatable kernel. This ensures they can be reached from the short
+ * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch
+ * directly, without using LOAD_HANDLER().
+ */
+ .align 7
+ .globl __end_interrupts
+__end_interrupts:
+
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
/*
* Data area reserved for FWNMI option.
diff --git a/kernel/arch/powerpc/kernel/ibmebus.c b/kernel/arch/powerpc/kernel/ibmebus.c
index ac86c53e2..e524a775f 100644
--- a/kernel/arch/powerpc/kernel/ibmebus.c
+++ b/kernel/arch/powerpc/kernel/ibmebus.c
@@ -180,6 +180,7 @@ static int ibmebus_create_device(struct device_node *dn)
static int ibmebus_create_devices(const struct of_device_id *matches)
{
struct device_node *root, *child;
+ struct device *dev;
int ret = 0;
root = of_find_node_by_path("/");
@@ -188,9 +189,12 @@ static int ibmebus_create_devices(const struct of_device_id *matches)
if (!of_match_node(matches, child))
continue;
- if (bus_find_device(&ibmebus_bus_type, NULL, child,
- ibmebus_match_node))
+ dev = bus_find_device(&ibmebus_bus_type, NULL, child,
+ ibmebus_match_node);
+ if (dev) {
+ put_device(dev);
continue;
+ }
ret = ibmebus_create_device(child);
if (ret) {
@@ -262,6 +266,7 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus,
const char *buf, size_t count)
{
struct device_node *dn = NULL;
+ struct device *dev;
char *path;
ssize_t rc = 0;
@@ -269,8 +274,10 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus,
if (!path)
return -ENOMEM;
- if (bus_find_device(&ibmebus_bus_type, NULL, path,
- ibmebus_match_path)) {
+ dev = bus_find_device(&ibmebus_bus_type, NULL, path,
+ ibmebus_match_path);
+ if (dev) {
+ put_device(dev);
printk(KERN_WARNING "%s: %s has already been probed\n",
__func__, path);
rc = -EEXIST;
@@ -307,6 +314,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus,
if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path,
ibmebus_match_path))) {
of_device_unregister(to_platform_device(dev));
+ put_device(dev);
kfree(path);
return count;
diff --git a/kernel/arch/powerpc/kernel/idle_power7.S b/kernel/arch/powerpc/kernel/idle_power7.S
index 112ccf497..73f638789 100644
--- a/kernel/arch/powerpc/kernel/idle_power7.S
+++ b/kernel/arch/powerpc/kernel/idle_power7.S
@@ -44,7 +44,7 @@
std r0,0(r1); \
ptesync; \
ld r0,0(r1); \
-1: cmp cr0,r0,r0; \
+1: cmpd cr0,r0,r0; \
bne 1b; \
IDLE_INST; \
b .
diff --git a/kernel/arch/powerpc/kernel/misc_32.S b/kernel/arch/powerpc/kernel/misc_32.S
index 8b261416c..9cb0c2f6e 100644
--- a/kernel/arch/powerpc/kernel/misc_32.S
+++ b/kernel/arch/powerpc/kernel/misc_32.S
@@ -315,7 +315,7 @@ _GLOBAL(flush_instruction_cache)
lis r3, KERNELBASE@h
iccci 0,r3
#endif
-#elif CONFIG_FSL_BOOKE
+#elif defined(CONFIG_FSL_BOOKE)
BEGIN_FTR_SECTION
mfspr r3,SPRN_L1CSR0
ori r3,r3,L1CSR0_CFI|L1CSR0_CLFC
diff --git a/kernel/arch/powerpc/kernel/nvram_64.c b/kernel/arch/powerpc/kernel/nvram_64.c
index 32e26526f..1eb698f65 100644
--- a/kernel/arch/powerpc/kernel/nvram_64.c
+++ b/kernel/arch/powerpc/kernel/nvram_64.c
@@ -969,7 +969,7 @@ int __init nvram_remove_partition(const char *name, int sig,
/* Make partition a free partition */
part->header.signature = NVRAM_SIG_FREE;
- strncpy(part->header.name, "wwwwwwwwwwww", 12);
+ memset(part->header.name, 'w', 12);
part->header.checksum = nvram_checksum(&part->header);
rc = nvram_write_header(part);
if (rc <= 0) {
@@ -987,8 +987,8 @@ int __init nvram_remove_partition(const char *name, int sig,
}
if (prev) {
prev->header.length += part->header.length;
- prev->header.checksum = nvram_checksum(&part->header);
- rc = nvram_write_header(part);
+ prev->header.checksum = nvram_checksum(&prev->header);
+ rc = nvram_write_header(prev);
if (rc <= 0) {
printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc);
return rc;
diff --git a/kernel/arch/powerpc/kernel/process.c b/kernel/arch/powerpc/kernel/process.c
index ef2ad2d68..cf788d7d7 100644
--- a/kernel/arch/powerpc/kernel/process.c
+++ b/kernel/arch/powerpc/kernel/process.c
@@ -569,24 +569,6 @@ static void tm_reclaim_thread(struct thread_struct *thr,
if (!MSR_TM_SUSPENDED(mfmsr()))
return;
- /*
- * Use the current MSR TM suspended bit to track if we have
- * checkpointed state outstanding.
- * On signal delivery, we'd normally reclaim the checkpointed
- * state to obtain stack pointer (see:get_tm_stackpointer()).
- * This will then directly return to userspace without going
- * through __switch_to(). However, if the stack frame is bad,
- * we need to exit this thread which calls __switch_to() which
- * will again attempt to reclaim the already saved tm state.
- * Hence we need to check that we've not already reclaimed
- * this state.
- * We do this using the current MSR, rather tracking it in
- * some specific thread_struct bit, as it has the additional
- * benifit of checking for a potential TM bad thing exception.
- */
- if (!MSR_TM_SUSPENDED(mfmsr()))
- return;
-
tm_reclaim(thr, thr->regs->msr, cause);
/* Having done the reclaim, we now have the checkpointed
@@ -1257,6 +1239,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
current->thread.regs = regs - 1;
}
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * Clear any transactional state, we're exec()ing. The cause is
+ * not important as there will never be a recheckpoint so it's not
+ * user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+#endif
+
memset(regs->gpr, 0, sizeof(regs->gpr));
regs->ctr = 0;
regs->link = 0;
diff --git a/kernel/arch/powerpc/kernel/prom.c b/kernel/arch/powerpc/kernel/prom.c
index 7030b0359..a15fe1d4e 100644
--- a/kernel/arch/powerpc/kernel/prom.c
+++ b/kernel/arch/powerpc/kernel/prom.c
@@ -148,23 +148,25 @@ static struct ibm_pa_feature {
unsigned long cpu_features; /* CPU_FTR_xxx bit */
unsigned long mmu_features; /* MMU_FTR_xxx bit */
unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */
+ unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */
unsigned char pabyte; /* byte number in ibm,pa-features */
unsigned char pabit; /* bit number (big-endian) */
unsigned char invert; /* if 1, pa bit set => clear feature */
} ibm_pa_features[] __initdata = {
- {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0},
- {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 0},
- {CPU_FTR_CTRL, 0, 0, 0, 3, 0},
- {CPU_FTR_NOEXECUTE, 0, 0, 0, 6, 0},
- {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1},
- {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0},
- {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
+ {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0, 0},
+ {0, 0, PPC_FEATURE_HAS_FPU, 0, 0, 1, 0},
+ {CPU_FTR_CTRL, 0, 0, 0, 0, 3, 0},
+ {CPU_FTR_NOEXECUTE, 0, 0, 0, 0, 6, 0},
+ {CPU_FTR_NODSISRALIGN, 0, 0, 0, 1, 1, 1},
+ {0, MMU_FTR_CI_LARGE_PAGE, 0, 0, 1, 2, 0},
+ {CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0},
/*
- * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n),
- * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP
- * which is 0 if the kernel doesn't support TM.
+ * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n),
+ * we don't want to turn on TM here, so we use the *_COMP versions
+ * which are 0 if the kernel doesn't support TM.
*/
- {CPU_FTR_TM_COMP, 0, 0, 22, 0, 0},
+ {CPU_FTR_TM_COMP, 0, 0,
+ PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0},
};
static void __init scan_features(unsigned long node, const unsigned char *ftrs,
@@ -195,10 +197,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs,
if (bit ^ fp->invert) {
cur_cpu_spec->cpu_features |= fp->cpu_features;
cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
+ cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2;
cur_cpu_spec->mmu_features |= fp->mmu_features;
} else {
cur_cpu_spec->cpu_features &= ~fp->cpu_features;
cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
+ cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2;
cur_cpu_spec->mmu_features &= ~fp->mmu_features;
}
}
diff --git a/kernel/arch/powerpc/kernel/prom_init.c b/kernel/arch/powerpc/kernel/prom_init.c
index 92dea8df6..313953364 100644
--- a/kernel/arch/powerpc/kernel/prom_init.c
+++ b/kernel/arch/powerpc/kernel/prom_init.c
@@ -655,6 +655,7 @@ unsigned char ibm_architecture_vec[] = {
W(0xffff0000), W(0x003e0000), /* POWER6 */
W(0xffff0000), W(0x003f0000), /* POWER7 */
W(0xffff0000), W(0x004b0000), /* POWER8E */
+ W(0xffff0000), W(0x004c0000), /* POWER8NVL */
W(0xffff0000), W(0x004d0000), /* POWER8 */
W(0xffffffff), W(0x0f000004), /* all 2.07-compliant */
W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */
@@ -693,7 +694,7 @@ unsigned char ibm_architecture_vec[] = {
OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */
/* option vector 5: PAPR/OF options */
- VECTOR_LENGTH(18), /* length */
+ VECTOR_LENGTH(21), /* length */
0, /* don't ignore, don't halt */
OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
@@ -717,15 +718,18 @@ unsigned char ibm_architecture_vec[] = {
* must match by the macro below. Update the definition if
* the structure layout changes.
*/
-#define IBM_ARCH_VEC_NRCORES_OFFSET 125
+#define IBM_ARCH_VEC_NRCORES_OFFSET 133
W(NR_CPUS), /* number of cores supported */
0,
0,
0,
0,
OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
- OV5_FEAT(OV5_PFO_HW_842),
- OV5_FEAT(OV5_SUB_PROCESSORS),
+ OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */
+ 0, /* Byte 18 */
+ 0, /* Byte 19 */
+ 0, /* Byte 20 */
+ OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */
/* option vector 6: IBM PAPR hints */
VECTOR_LENGTH(3), /* length */
@@ -2660,6 +2664,9 @@ static void __init prom_find_boot_cpu(void)
cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu);
+ if (!PHANDLE_VALID(cpu_pkg))
+ return;
+
prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval));
prom.cpu = be32_to_cpu(rval);
diff --git a/kernel/arch/powerpc/kernel/ptrace.c b/kernel/arch/powerpc/kernel/ptrace.c
index 737c0d0b5..b38fd081b 100644
--- a/kernel/arch/powerpc/kernel/ptrace.c
+++ b/kernel/arch/powerpc/kernel/ptrace.c
@@ -376,7 +376,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
#else
BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
- offsetof(struct thread_fp_state, fpr[32][0]));
+ offsetof(struct thread_fp_state, fpr[32]));
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
&target->thread.fp_state, 0, -1);
@@ -404,7 +404,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
return 0;
#else
BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
- offsetof(struct thread_fp_state, fpr[32][0]));
+ offsetof(struct thread_fp_state, fpr[32]));
return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&target->thread.fp_state, 0, -1);
diff --git a/kernel/arch/powerpc/kernel/tm.S b/kernel/arch/powerpc/kernel/tm.S
index bf8f34a58..b7019b559 100644
--- a/kernel/arch/powerpc/kernel/tm.S
+++ b/kernel/arch/powerpc/kernel/tm.S
@@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim)
std r3, STK_PARAM(R3)(r1)
SAVE_NVGPRS(r1)
- /* We need to setup MSR for VSX register save instructions. Here we
- * also clear the MSR RI since when we do the treclaim, we won't have a
- * valid kernel pointer for a while. We clear RI here as it avoids
- * adding another mtmsr closer to the treclaim. This makes the region
- * maked as non-recoverable wider than it needs to be but it saves on
- * inserting another mtmsrd later.
- */
+ /* We need to setup MSR for VSX register save instructions. */
mfmsr r14
mr r15, r14
ori r15, r15, MSR_FP
- li r16, MSR_RI
+ li r16, 0
ori r16, r16, MSR_EE /* IRQs hard off */
andc r15, r15, r16
oris r15, r15, MSR_VEC@h
@@ -176,7 +170,17 @@ dont_backup_fp:
1: tdeqi r6, 0
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
- /* The moment we treclaim, ALL of our GPRs will switch
+ /* Clear MSR RI since we are about to change r1, EE is already off. */
+ li r4, 0
+ mtmsrd r4, 1
+
+ /*
+ * BE CAREFUL HERE:
+ * At this point we can't take an SLB miss since we have MSR_RI
+ * off. Load only to/from the stack/paca which are in SLB bolted regions
+ * until we turn MSR RI back on.
+ *
+ * The moment we treclaim, ALL of our GPRs will switch
* to user register state. (FPRs, CCR etc. also!)
* Use an sprg and a tm_scratch in the PACA to shuffle.
*/
@@ -197,6 +201,11 @@ dont_backup_fp:
/* Store the PPR in r11 and reset to decent value */
std r11, GPR11(r1) /* Temporary stash */
+
+ /* Reset MSR RI so we can take SLB faults again */
+ li r11, MSR_RI
+ mtmsrd r11, 1
+
mfspr r11, SPRN_PPR
HMT_MEDIUM
@@ -397,11 +406,6 @@ restore_gprs:
ld r5, THREAD_TM_DSCR(r3)
ld r6, THREAD_TM_PPR(r3)
- /* Clear the MSR RI since we are about to change R1. EE is already off
- */
- li r4, 0
- mtmsrd r4, 1
-
REST_GPR(0, r7) /* GPR0 */
REST_2GPRS(2, r7) /* GPR2-3 */
REST_GPR(4, r7) /* GPR4 */
@@ -439,10 +443,33 @@ restore_gprs:
ld r6, _CCR(r7)
mtcr r6
- REST_GPR(1, r7) /* GPR1 */
- REST_GPR(5, r7) /* GPR5-7 */
REST_GPR(6, r7)
- ld r7, GPR7(r7)
+
+ /*
+ * Store r1 and r5 on the stack so that we can access them
+ * after we clear MSR RI.
+ */
+
+ REST_GPR(5, r7)
+ std r5, -8(r1)
+ ld r5, GPR1(r7)
+ std r5, -16(r1)
+
+ REST_GPR(7, r7)
+
+ /* Clear MSR RI since we are about to change r1. EE is already off */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /*
+ * BE CAREFUL HERE:
+ * At this point we can't take an SLB miss since we have MSR_RI
+ * off. Load only to/from the stack/paca which are in SLB bolted regions
+ * until we turn MSR RI back on.
+ */
+
+ ld r5, -8(r1)
+ ld r1, -16(r1)
/* Commit register state as checkpointed state: */
TRECHKPT
diff --git a/kernel/arch/powerpc/kernel/vdso64/datapage.S b/kernel/arch/powerpc/kernel/vdso64/datapage.S
index 2f01c4a0d..7612eeb31 100644
--- a/kernel/arch/powerpc/kernel/vdso64/datapage.S
+++ b/kernel/arch/powerpc/kernel/vdso64/datapage.S
@@ -59,7 +59,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
bl V_LOCAL_FUNC(__get_datapage)
mtlr r12
addi r3,r3,CFG_SYSCALL_MAP64
- cmpli cr0,r4,0
+ cmpldi cr0,r4,0
crclr cr0*4+so
beqlr
li r0,__NR_syscalls
diff --git a/kernel/arch/powerpc/kernel/vdso64/gettimeofday.S b/kernel/arch/powerpc/kernel/vdso64/gettimeofday.S
index a76b4af37..382021324 100644
--- a/kernel/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/kernel/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -145,7 +145,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
bne cr0,99f
li r3,0
- cmpli cr0,r4,0
+ cmpldi cr0,r4,0
crclr cr0*4+so
beqlr
lis r5,CLOCK_REALTIME_RES@h
diff --git a/kernel/arch/powerpc/kvm/book3s_emulate.c b/kernel/arch/powerpc/kvm/book3s_emulate.c
index 2afdb9c09..729f8faa9 100644
--- a/kernel/arch/powerpc/kvm/book3s_emulate.c
+++ b/kernel/arch/powerpc/kvm/book3s_emulate.c
@@ -498,6 +498,7 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
case SPRN_MMCR0:
case SPRN_MMCR1:
case SPRN_MMCR2:
+ case SPRN_UMMCR2:
#endif
break;
unprivileged:
@@ -640,6 +641,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
case SPRN_MMCR0:
case SPRN_MMCR1:
case SPRN_MMCR2:
+ case SPRN_UMMCR2:
case SPRN_TIR:
#endif
*spr_val = 0;
diff --git a/kernel/arch/powerpc/kvm/book3s_hv.c b/kernel/arch/powerpc/kvm/book3s_hv.c
index df34a6432..2ac7a8b10 100644
--- a/kernel/arch/powerpc/kvm/book3s_hv.c
+++ b/kernel/arch/powerpc/kvm/book3s_hv.c
@@ -1186,6 +1186,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_TM_CR:
*val = get_reg_val(id, vcpu->arch.cr_tm);
break;
+ case KVM_REG_PPC_TM_XER:
+ *val = get_reg_val(id, vcpu->arch.xer_tm);
+ break;
case KVM_REG_PPC_TM_LR:
*val = get_reg_val(id, vcpu->arch.lr_tm);
break;
@@ -1393,6 +1396,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_TM_CR:
vcpu->arch.cr_tm = set_reg_val(id, *val);
break;
+ case KVM_REG_PPC_TM_XER:
+ vcpu->arch.xer_tm = set_reg_val(id, *val);
+ break;
case KVM_REG_PPC_TM_LR:
vcpu->arch.lr_tm = set_reg_val(id, *val);
break;
diff --git a/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 91700518b..d509ff5c8 100644
--- a/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -653,6 +653,8 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
HPTE_V_ABSENT);
do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags),
true);
+ /* Don't lose R/C bit updates done by hardware */
+ r |= be64_to_cpu(hpte[1]) & (HPTE_R_R | HPTE_R_C);
hpte[1] = cpu_to_be64(r);
}
}
diff --git a/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 463af88c9..1a743f87b 100644
--- a/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -655,112 +655,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
- b skip_tm
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-
- /* Turn on TM/FP/VSX/VMX so we can restore them. */
- mfmsr r5
- li r6, MSR_TM >> 32
- sldi r6, r6, 32
- or r5, r5, r6
- ori r5, r5, MSR_FP
- oris r5, r5, (MSR_VEC | MSR_VSX)@h
- mtmsrd r5
-
- /*
- * The user may change these outside of a transaction, so they must
- * always be context switched.
- */
- ld r5, VCPU_TFHAR(r4)
- ld r6, VCPU_TFIAR(r4)
- ld r7, VCPU_TEXASR(r4)
- mtspr SPRN_TFHAR, r5
- mtspr SPRN_TFIAR, r6
- mtspr SPRN_TEXASR, r7
-
- ld r5, VCPU_MSR(r4)
- rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
- beq skip_tm /* TM not active in guest */
-
- /* Make sure the failure summary is set, otherwise we'll program check
- * when we trechkpt. It's possible that this might have been not set
- * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
- * host.
- */
- oris r7, r7, (TEXASR_FS)@h
- mtspr SPRN_TEXASR, r7
-
- /*
- * We need to load up the checkpointed state for the guest.
- * We need to do this early as it will blow away any GPRs, VSRs and
- * some SPRs.
- */
-
- mr r31, r4
- addi r3, r31, VCPU_FPRS_TM
- bl load_fp_state
- addi r3, r31, VCPU_VRS_TM
- bl load_vr_state
- mr r4, r31
- lwz r7, VCPU_VRSAVE_TM(r4)
- mtspr SPRN_VRSAVE, r7
-
- ld r5, VCPU_LR_TM(r4)
- lwz r6, VCPU_CR_TM(r4)
- ld r7, VCPU_CTR_TM(r4)
- ld r8, VCPU_AMR_TM(r4)
- ld r9, VCPU_TAR_TM(r4)
- mtlr r5
- mtcr r6
- mtctr r7
- mtspr SPRN_AMR, r8
- mtspr SPRN_TAR, r9
-
- /*
- * Load up PPR and DSCR values but don't put them in the actual SPRs
- * till the last moment to avoid running with userspace PPR and DSCR for
- * too long.
- */
- ld r29, VCPU_DSCR_TM(r4)
- ld r30, VCPU_PPR_TM(r4)
-
- std r2, PACATMSCRATCH(r13) /* Save TOC */
-
- /* Clear the MSR RI since r1, r13 are all going to be foobar. */
- li r5, 0
- mtmsrd r5, 1
-
- /* Load GPRs r0-r28 */
- reg = 0
- .rept 29
- ld reg, VCPU_GPRS_TM(reg)(r31)
- reg = reg + 1
- .endr
-
- mtspr SPRN_DSCR, r29
- mtspr SPRN_PPR, r30
-
- /* Load final GPRs */
- ld 29, VCPU_GPRS_TM(29)(r31)
- ld 30, VCPU_GPRS_TM(30)(r31)
- ld 31, VCPU_GPRS_TM(31)(r31)
-
- /* TM checkpointed state is now setup. All GPRs are now volatile. */
- TRECHKPT
-
- /* Now let's get back the state we need. */
- HMT_MEDIUM
- GET_PACA(r13)
- ld r29, HSTATE_DSCR(r13)
- mtspr SPRN_DSCR, r29
- ld r4, HSTATE_KVM_VCPU(r13)
- ld r1, HSTATE_HOST_R1(r13)
- ld r2, PACATMSCRATCH(r13)
-
- /* Set the MSR RI since we have our registers back. */
- li r5, MSR_RI
- mtmsrd r5, 1
-skip_tm:
+ bl kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
/* Load guest PMU registers */
@@ -841,12 +737,6 @@ BEGIN_FTR_SECTION
/* Skip next section on POWER7 */
b 8f
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
- /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
- mfmsr r8
- li r0, 1
- rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
- mtmsrd r8
-
/* Load up POWER8-specific registers */
ld r5, VCPU_IAMR(r4)
lwz r6, VCPU_PSPB(r4)
@@ -1436,106 +1326,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
- b 2f
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
- /* Turn on TM. */
- mfmsr r8
- li r0, 1
- rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
- mtmsrd r8
-
- ld r5, VCPU_MSR(r9)
- rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
- beq 1f /* TM not active in guest. */
-
- li r3, TM_CAUSE_KVM_RESCHED
-
- /* Clear the MSR RI since r1, r13 are all going to be foobar. */
- li r5, 0
- mtmsrd r5, 1
-
- /* All GPRs are volatile at this point. */
- TRECLAIM(R3)
-
- /* Temporarily store r13 and r9 so we have some regs to play with */
- SET_SCRATCH0(r13)
- GET_PACA(r13)
- std r9, PACATMSCRATCH(r13)
- ld r9, HSTATE_KVM_VCPU(r13)
-
- /* Get a few more GPRs free. */
- std r29, VCPU_GPRS_TM(29)(r9)
- std r30, VCPU_GPRS_TM(30)(r9)
- std r31, VCPU_GPRS_TM(31)(r9)
-
- /* Save away PPR and DSCR soon so don't run with user values. */
- mfspr r31, SPRN_PPR
- HMT_MEDIUM
- mfspr r30, SPRN_DSCR
- ld r29, HSTATE_DSCR(r13)
- mtspr SPRN_DSCR, r29
-
- /* Save all but r9, r13 & r29-r31 */
- reg = 0
- .rept 29
- .if (reg != 9) && (reg != 13)
- std reg, VCPU_GPRS_TM(reg)(r9)
- .endif
- reg = reg + 1
- .endr
- /* ... now save r13 */
- GET_SCRATCH0(r4)
- std r4, VCPU_GPRS_TM(13)(r9)
- /* ... and save r9 */
- ld r4, PACATMSCRATCH(r13)
- std r4, VCPU_GPRS_TM(9)(r9)
-
- /* Reload stack pointer and TOC. */
- ld r1, HSTATE_HOST_R1(r13)
- ld r2, PACATOC(r13)
-
- /* Set MSR RI now we have r1 and r13 back. */
- li r5, MSR_RI
- mtmsrd r5, 1
-
- /* Save away checkpinted SPRs. */
- std r31, VCPU_PPR_TM(r9)
- std r30, VCPU_DSCR_TM(r9)
- mflr r5
- mfcr r6
- mfctr r7
- mfspr r8, SPRN_AMR
- mfspr r10, SPRN_TAR
- std r5, VCPU_LR_TM(r9)
- stw r6, VCPU_CR_TM(r9)
- std r7, VCPU_CTR_TM(r9)
- std r8, VCPU_AMR_TM(r9)
- std r10, VCPU_TAR_TM(r9)
-
- /* Restore r12 as trap number. */
- lwz r12, VCPU_TRAP(r9)
-
- /* Save FP/VSX. */
- addi r3, r9, VCPU_FPRS_TM
- bl store_fp_state
- addi r3, r9, VCPU_VRS_TM
- bl store_vr_state
- mfspr r6, SPRN_VRSAVE
- stw r6, VCPU_VRSAVE_TM(r9)
-1:
- /*
- * We need to save these SPRs after the treclaim so that the software
- * error code is recorded correctly in the TEXASR. Also the user may
- * change these outside of a transaction, so they must always be
- * context switched.
- */
- mfspr r5, SPRN_TFHAR
- mfspr r6, SPRN_TFIAR
- mfspr r7, SPRN_TEXASR
- std r5, VCPU_TFHAR(r9)
- std r6, VCPU_TFIAR(r9)
- std r7, VCPU_TEXASR(r9)
-2:
+ bl kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
/* Increment yield count if they have a VPA */
@@ -2245,6 +2037,13 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
/* save FP state */
bl kvmppc_save_fp
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+ ld r9, HSTATE_KVM_VCPU(r13)
+ bl kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
/*
* Set DEC to the smaller of DEC and HDEC, so that we wake
* no later than the end of our timeslice (HDEC interrupts
@@ -2321,6 +2120,12 @@ kvm_end_cede:
bl kvmhv_accumulate_time
#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+ bl kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
/* load up FP state */
bl kvmppc_load_fp
@@ -2629,6 +2434,243 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
mr r4,r31
blr
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Save transactional state and TM-related registers.
+ * Called with r9 pointing to the vcpu struct.
+ * This can modify all checkpointed registers, but
+ * restores r1, r2 and r9 (vcpu pointer) before exit.
+ */
+kvmppc_save_tm:
+ mflr r0
+ std r0, PPC_LR_STKOFF(r1)
+
+ /* Turn on TM. */
+ mfmsr r8
+ li r0, 1
+ rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+ mtmsrd r8
+
+ ld r5, VCPU_MSR(r9)
+ rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+ beq 1f /* TM not active in guest. */
+
+ std r1, HSTATE_HOST_R1(r13)
+ li r3, TM_CAUSE_KVM_RESCHED
+
+ /* Clear the MSR RI since r1, r13 are all going to be foobar. */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /* All GPRs are volatile at this point. */
+ TRECLAIM(R3)
+
+ /* Temporarily store r13 and r9 so we have some regs to play with */
+ SET_SCRATCH0(r13)
+ GET_PACA(r13)
+ std r9, PACATMSCRATCH(r13)
+ ld r9, HSTATE_KVM_VCPU(r13)
+
+ /* Get a few more GPRs free. */
+ std r29, VCPU_GPRS_TM(29)(r9)
+ std r30, VCPU_GPRS_TM(30)(r9)
+ std r31, VCPU_GPRS_TM(31)(r9)
+
+ /* Save away PPR and DSCR soon so don't run with user values. */
+ mfspr r31, SPRN_PPR
+ HMT_MEDIUM
+ mfspr r30, SPRN_DSCR
+ ld r29, HSTATE_DSCR(r13)
+ mtspr SPRN_DSCR, r29
+
+ /* Save all but r9, r13 & r29-r31 */
+ reg = 0
+ .rept 29
+ .if (reg != 9) && (reg != 13)
+ std reg, VCPU_GPRS_TM(reg)(r9)
+ .endif
+ reg = reg + 1
+ .endr
+ /* ... now save r13 */
+ GET_SCRATCH0(r4)
+ std r4, VCPU_GPRS_TM(13)(r9)
+ /* ... and save r9 */
+ ld r4, PACATMSCRATCH(r13)
+ std r4, VCPU_GPRS_TM(9)(r9)
+
+ /* Reload stack pointer and TOC. */
+ ld r1, HSTATE_HOST_R1(r13)
+ ld r2, PACATOC(r13)
+
+ /* Set MSR RI now we have r1 and r13 back. */
+ li r5, MSR_RI
+ mtmsrd r5, 1
+
+ /* Save away checkpinted SPRs. */
+ std r31, VCPU_PPR_TM(r9)
+ std r30, VCPU_DSCR_TM(r9)
+ mflr r5
+ mfcr r6
+ mfctr r7
+ mfspr r8, SPRN_AMR
+ mfspr r10, SPRN_TAR
+ mfxer r11
+ std r5, VCPU_LR_TM(r9)
+ stw r6, VCPU_CR_TM(r9)
+ std r7, VCPU_CTR_TM(r9)
+ std r8, VCPU_AMR_TM(r9)
+ std r10, VCPU_TAR_TM(r9)
+ std r11, VCPU_XER_TM(r9)
+
+ /* Restore r12 as trap number. */
+ lwz r12, VCPU_TRAP(r9)
+
+ /* Save FP/VSX. */
+ addi r3, r9, VCPU_FPRS_TM
+ bl store_fp_state
+ addi r3, r9, VCPU_VRS_TM
+ bl store_vr_state
+ mfspr r6, SPRN_VRSAVE
+ stw r6, VCPU_VRSAVE_TM(r9)
+1:
+ /*
+ * We need to save these SPRs after the treclaim so that the software
+ * error code is recorded correctly in the TEXASR. Also the user may
+ * change these outside of a transaction, so they must always be
+ * context switched.
+ */
+ mfspr r5, SPRN_TFHAR
+ mfspr r6, SPRN_TFIAR
+ mfspr r7, SPRN_TEXASR
+ std r5, VCPU_TFHAR(r9)
+ std r6, VCPU_TFIAR(r9)
+ std r7, VCPU_TEXASR(r9)
+
+ ld r0, PPC_LR_STKOFF(r1)
+ mtlr r0
+ blr
+
+/*
+ * Restore transactional state and TM-related registers.
+ * Called with r4 pointing to the vcpu struct.
+ * This potentially modifies all checkpointed registers.
+ * It restores r1, r2, r4 from the PACA.
+ */
+kvmppc_restore_tm:
+ mflr r0
+ std r0, PPC_LR_STKOFF(r1)
+
+ /* Turn on TM/FP/VSX/VMX so we can restore them. */
+ mfmsr r5
+ li r6, MSR_TM >> 32
+ sldi r6, r6, 32
+ or r5, r5, r6
+ ori r5, r5, MSR_FP
+ oris r5, r5, (MSR_VEC | MSR_VSX)@h
+ mtmsrd r5
+
+ /*
+ * The user may change these outside of a transaction, so they must
+ * always be context switched.
+ */
+ ld r5, VCPU_TFHAR(r4)
+ ld r6, VCPU_TFIAR(r4)
+ ld r7, VCPU_TEXASR(r4)
+ mtspr SPRN_TFHAR, r5
+ mtspr SPRN_TFIAR, r6
+ mtspr SPRN_TEXASR, r7
+
+ ld r5, VCPU_MSR(r4)
+ rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+ beqlr /* TM not active in guest */
+ std r1, HSTATE_HOST_R1(r13)
+
+ /* Make sure the failure summary is set, otherwise we'll program check
+ * when we trechkpt. It's possible that this might have been not set
+ * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
+ * host.
+ */
+ oris r7, r7, (TEXASR_FS)@h
+ mtspr SPRN_TEXASR, r7
+
+ /*
+ * We need to load up the checkpointed state for the guest.
+ * We need to do this early as it will blow away any GPRs, VSRs and
+ * some SPRs.
+ */
+
+ mr r31, r4
+ addi r3, r31, VCPU_FPRS_TM
+ bl load_fp_state
+ addi r3, r31, VCPU_VRS_TM
+ bl load_vr_state
+ mr r4, r31
+ lwz r7, VCPU_VRSAVE_TM(r4)
+ mtspr SPRN_VRSAVE, r7
+
+ ld r5, VCPU_LR_TM(r4)
+ lwz r6, VCPU_CR_TM(r4)
+ ld r7, VCPU_CTR_TM(r4)
+ ld r8, VCPU_AMR_TM(r4)
+ ld r9, VCPU_TAR_TM(r4)
+ ld r10, VCPU_XER_TM(r4)
+ mtlr r5
+ mtcr r6
+ mtctr r7
+ mtspr SPRN_AMR, r8
+ mtspr SPRN_TAR, r9
+ mtxer r10
+
+ /*
+ * Load up PPR and DSCR values but don't put them in the actual SPRs
+ * till the last moment to avoid running with userspace PPR and DSCR for
+ * too long.
+ */
+ ld r29, VCPU_DSCR_TM(r4)
+ ld r30, VCPU_PPR_TM(r4)
+
+ std r2, PACATMSCRATCH(r13) /* Save TOC */
+
+ /* Clear the MSR RI since r1, r13 are all going to be foobar. */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /* Load GPRs r0-r28 */
+ reg = 0
+ .rept 29
+ ld reg, VCPU_GPRS_TM(reg)(r31)
+ reg = reg + 1
+ .endr
+
+ mtspr SPRN_DSCR, r29
+ mtspr SPRN_PPR, r30
+
+ /* Load final GPRs */
+ ld 29, VCPU_GPRS_TM(29)(r31)
+ ld 30, VCPU_GPRS_TM(30)(r31)
+ ld 31, VCPU_GPRS_TM(31)(r31)
+
+ /* TM checkpointed state is now setup. All GPRs are now volatile. */
+ TRECHKPT
+
+ /* Now let's get back the state we need. */
+ HMT_MEDIUM
+ GET_PACA(r13)
+ ld r29, HSTATE_DSCR(r13)
+ mtspr SPRN_DSCR, r29
+ ld r4, HSTATE_KVM_VCPU(r13)
+ ld r1, HSTATE_HOST_R1(r13)
+ ld r2, PACATMSCRATCH(r13)
+
+ /* Set the MSR RI since we have our registers back. */
+ li r5, MSR_RI
+ mtmsrd r5, 1
+
+ ld r0, PPC_LR_STKOFF(r1)
+ mtlr r0
+ blr
+#endif
+
/*
* We come here if we get any exception or interrupt while we are
* executing host real mode code while in guest MMU context.
diff --git a/kernel/arch/powerpc/kvm/booke.c b/kernel/arch/powerpc/kvm/booke.c
index fd5875179..6d63cd67b 100644
--- a/kernel/arch/powerpc/kvm/booke.c
+++ b/kernel/arch/powerpc/kvm/booke.c
@@ -2033,7 +2033,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
if (type == KVMPPC_DEBUG_NONE)
continue;
- if (type & !(KVMPPC_DEBUG_WATCH_READ |
+ if (type & ~(KVMPPC_DEBUG_WATCH_READ |
KVMPPC_DEBUG_WATCH_WRITE |
KVMPPC_DEBUG_BREAKPOINT))
return -EINVAL;
diff --git a/kernel/arch/powerpc/lib/copyuser_64.S b/kernel/arch/powerpc/lib/copyuser_64.S
index f09899e35..7b22624f3 100644
--- a/kernel/arch/powerpc/lib/copyuser_64.S
+++ b/kernel/arch/powerpc/lib/copyuser_64.S
@@ -359,6 +359,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
addi r3,r3,8
171:
177:
+179:
addi r3,r3,8
370:
372:
@@ -373,7 +374,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
173:
174:
175:
-179:
181:
184:
186:
diff --git a/kernel/arch/powerpc/mm/copro_fault.c b/kernel/arch/powerpc/mm/copro_fault.c
index 6527882ce..ddfd2740a 100644
--- a/kernel/arch/powerpc/mm/copro_fault.c
+++ b/kernel/arch/powerpc/mm/copro_fault.c
@@ -106,6 +106,8 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
switch (REGION_ID(ea)) {
case USER_REGION_ID:
pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
+ if (mm == NULL)
+ return 1;
psize = get_slice_psize(mm, ea);
ssize = user_segment_size(ea);
vsid = get_vsid(mm->context.id, ea, ssize);
diff --git a/kernel/arch/powerpc/mm/hugetlbpage.c b/kernel/arch/powerpc/mm/hugetlbpage.c
index 9833fee49..807f15947 100644
--- a/kernel/arch/powerpc/mm/hugetlbpage.c
+++ b/kernel/arch/powerpc/mm/hugetlbpage.c
@@ -486,13 +486,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
{
struct hugepd_freelist **batchp;
- batchp = this_cpu_ptr(&hugepd_freelist_cur);
+ batchp = &get_cpu_var(hugepd_freelist_cur);
if (atomic_read(&tlb->mm->mm_users) < 2 ||
cpumask_equal(mm_cpumask(tlb->mm),
cpumask_of(smp_processor_id()))) {
kmem_cache_free(hugepte_cache, hugepte);
- put_cpu_var(hugepd_freelist_cur);
+ put_cpu_var(hugepd_freelist_cur);
return;
}
diff --git a/kernel/arch/powerpc/mm/slb_low.S b/kernel/arch/powerpc/mm/slb_low.S
index 736d18b3c..4c48b4876 100644
--- a/kernel/arch/powerpc/mm/slb_low.S
+++ b/kernel/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/kernel/arch/powerpc/platforms/powernv/eeh-powernv.c b/kernel/arch/powerpc/platforms/powernv/eeh-powernv.c
index 2ba602591..92736851c 100644
--- a/kernel/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/kernel/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -956,6 +956,11 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
}
bus = eeh_pe_bus_get(pe);
+ if (!bus) {
+ pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
+ __func__, pe->phb->global_number, pe->addr);
+ return -EIO;
+ }
if (pci_is_root_bus(bus) ||
pci_is_root_bus(bus->parent))
ret = pnv_eeh_root_reset(hose, option);
@@ -1163,7 +1168,7 @@ static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose)
return;
}
- switch (data->type) {
+ switch (be16_to_cpu(data->type)) {
case OPAL_P7IOC_DIAG_TYPE_RGC:
pr_info("P7IOC diag-data for RGC\n\n");
pnv_eeh_dump_hub_diag_common(data);
@@ -1395,7 +1400,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
/* Try best to clear it */
opal_pci_eeh_freeze_clear(phb->opal_id,
- frozen_pe_no,
+ be64_to_cpu(frozen_pe_no),
OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
ret = EEH_NEXT_ERR_NONE;
} else if ((*pe)->state & EEH_PE_ISOLATED ||
diff --git a/kernel/arch/powerpc/platforms/powernv/opal-dump.c b/kernel/arch/powerpc/platforms/powernv/opal-dump.c
index 2ee96431f..4c827826c 100644
--- a/kernel/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/kernel/arch/powerpc/platforms/powernv/opal-dump.c
@@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data)
uint32_t dump_id, dump_size, dump_type;
struct dump_obj *dump;
char name[22];
+ struct kobject *kobj;
rc = dump_read_info(&dump_id, &dump_size, &dump_type);
if (rc != OPAL_SUCCESS)
@@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data)
* that gracefully and not create two conflicting
* entries.
*/
- if (kset_find_obj(dump_kset, name))
+ kobj = kset_find_obj(dump_kset, name);
+ if (kobj) {
+ /* Drop reference added by kset_find_obj() */
+ kobject_put(kobj);
return 0;
+ }
dump = create_dump_obj(dump_id, dump_size, dump_type);
if (!dump)
diff --git a/kernel/arch/powerpc/platforms/powernv/opal-elog.c b/kernel/arch/powerpc/platforms/powernv/opal-elog.c
index 37f959bf3..f2344cbd2 100644
--- a/kernel/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/kernel/arch/powerpc/platforms/powernv/opal-elog.c
@@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data)
uint64_t elog_type;
int rc;
char name[2+16+1];
+ struct kobject *kobj;
rc = opal_get_elog_size(&id, &size, &type);
if (rc != OPAL_SUCCESS) {
@@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data)
* that gracefully and not create two conflicting
* entries.
*/
- if (kset_find_obj(elog_kset, name))
+ kobj = kset_find_obj(elog_kset, name);
+ if (kobj) {
+ /* Drop reference added by kset_find_obj() */
+ kobject_put(kobj);
return IRQ_HANDLED;
+ }
create_elog_obj(log_id, elog_size, elog_type);
diff --git a/kernel/arch/powerpc/platforms/powernv/pci.c b/kernel/arch/powerpc/platforms/powernv/pci.c
index ad8c3f4a5..dd5e0f3b1 100644
--- a/kernel/arch/powerpc/platforms/powernv/pci.c
+++ b/kernel/arch/powerpc/platforms/powernv/pci.c
@@ -197,8 +197,8 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
be64_to_cpu(data->dma1ErrorLog1));
for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
- if ((data->pestA[i] >> 63) == 0 &&
- (data->pestB[i] >> 63) == 0)
+ if ((be64_to_cpu(data->pestA[i]) >> 63) == 0 &&
+ (be64_to_cpu(data->pestB[i]) >> 63) == 0)
continue;
pr_info("PE[%3d] A/B: %016llx %016llx\n",
diff --git a/kernel/arch/powerpc/platforms/pseries/eeh_pseries.c b/kernel/arch/powerpc/platforms/pseries/eeh_pseries.c
index ac3ffd97e..405baaf96 100644
--- a/kernel/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/kernel/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -615,29 +615,50 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
{
int config_addr;
int ret;
+ /* Waiting 0.2s maximum before skipping configuration */
+ int max_wait = 200;
/* Figure out the PE address */
config_addr = pe->config_addr;
if (pe->addr)
config_addr = pe->addr;
- /* Use new configure-pe function, if supported */
- if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
- ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
- config_addr, BUID_HI(pe->phb->buid),
- BUID_LO(pe->phb->buid));
- } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
- ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
- config_addr, BUID_HI(pe->phb->buid),
- BUID_LO(pe->phb->buid));
- } else {
- return -EFAULT;
- }
+ while (max_wait > 0) {
+ /* Use new configure-pe function, if supported */
+ if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+ ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
+ config_addr, BUID_HI(pe->phb->buid),
+ BUID_LO(pe->phb->buid));
+ } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
+ ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
+ config_addr, BUID_HI(pe->phb->buid),
+ BUID_LO(pe->phb->buid));
+ } else {
+ return -EFAULT;
+ }
- if (ret)
- pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
- __func__, pe->phb->global_number, pe->addr, ret);
+ if (!ret)
+ return ret;
+
+ /*
+ * If RTAS returns a delay value that's above 100ms, cut it
+ * down to 100ms in case firmware made a mistake. For more
+ * on how these delay values work see rtas_busy_delay_time
+ */
+ if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+ ret <= RTAS_EXTENDED_DELAY_MAX)
+ ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+ max_wait -= rtas_busy_delay_time(ret);
+
+ if (max_wait < 0)
+ break;
+
+ rtas_busy_delay(ret);
+ }
+ pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+ __func__, pe->phb->global_number, pe->addr, ret);
return ret;
}
diff --git a/kernel/arch/powerpc/platforms/pseries/iommu.c b/kernel/arch/powerpc/platforms/pseries/iommu.c
index bd98ce2be..3e8865b18 100644
--- a/kernel/arch/powerpc/platforms/pseries/iommu.c
+++ b/kernel/arch/powerpc/platforms/pseries/iommu.c
@@ -912,7 +912,8 @@ machine_arch_initcall(pseries, find_existing_ddw_windows);
static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
struct ddw_query_response *query)
{
- struct eeh_dev *edev;
+ struct device_node *dn;
+ struct pci_dn *pdn;
u32 cfg_addr;
u64 buid;
int ret;
@@ -923,11 +924,10 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
* Retrieve them from the pci device, not the node with the
* dma-window property
*/
- edev = pci_dev_to_eeh_dev(dev);
- cfg_addr = edev->config_addr;
- if (edev->pe_config_addr)
- cfg_addr = edev->pe_config_addr;
- buid = edev->phb->buid;
+ dn = pci_device_to_OF_node(dev);
+ pdn = PCI_DN(dn);
+ buid = pdn->phb->buid;
+ cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
cfg_addr, BUID_HI(buid), BUID_LO(buid));
@@ -941,7 +941,8 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
struct ddw_create_response *create, int page_shift,
int window_shift)
{
- struct eeh_dev *edev;
+ struct device_node *dn;
+ struct pci_dn *pdn;
u32 cfg_addr;
u64 buid;
int ret;
@@ -952,11 +953,10 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
* Retrieve them from the pci device, not the node with the
* dma-window property
*/
- edev = pci_dev_to_eeh_dev(dev);
- cfg_addr = edev->config_addr;
- if (edev->pe_config_addr)
- cfg_addr = edev->pe_config_addr;
- buid = edev->phb->buid;
+ dn = pci_device_to_OF_node(dev);
+ pdn = PCI_DN(dn);
+ buid = pdn->phb->buid;
+ cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
do {
/* extra outputs are LIOBN and dma-addr (hi, lo) */
diff --git a/kernel/arch/powerpc/platforms/pseries/lpar.c b/kernel/arch/powerpc/platforms/pseries/lpar.c
index b7a67e3d2..3ae432824 100644
--- a/kernel/arch/powerpc/platforms/pseries/lpar.c
+++ b/kernel/arch/powerpc/platforms/pseries/lpar.c
@@ -406,7 +406,7 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
unsigned long *vpn, int count,
int psize, int ssize)
{
- unsigned long param[8];
+ unsigned long param[PLPAR_HCALL9_BUFSIZE];
int i = 0, pix = 0, rc;
unsigned long flags = 0;
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
@@ -523,7 +523,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
unsigned long flags = 0;
struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
- unsigned long param[9];
+ unsigned long param[PLPAR_HCALL9_BUFSIZE];
unsigned long hash, index, shift, hidx, slot;
real_pte_t pte;
int psize, ssize;
diff --git a/kernel/arch/s390/crypto/prng.c b/kernel/arch/s390/crypto/prng.c
index b8045b97f..683a966b5 100644
--- a/kernel/arch/s390/crypto/prng.c
+++ b/kernel/arch/s390/crypto/prng.c
@@ -565,8 +565,10 @@ static ssize_t prng_tdes_read(struct file *file, char __user *ubuf,
prng_data->prngws.byte_counter += n;
prng_data->prngws.reseed_counter += n;
- if (copy_to_user(ubuf, prng_data->buf, chunk))
- return -EFAULT;
+ if (copy_to_user(ubuf, prng_data->buf, chunk)) {
+ ret = -EFAULT;
+ break;
+ }
nbytes -= chunk;
ret += chunk;
@@ -669,11 +671,13 @@ static const struct file_operations prng_tdes_fops = {
static struct miscdevice prng_sha512_dev = {
.name = "prandom",
.minor = MISC_DYNAMIC_MINOR,
+ .mode = 0644,
.fops = &prng_sha512_fops,
};
static struct miscdevice prng_tdes_dev = {
.name = "prandom",
.minor = MISC_DYNAMIC_MINOR,
+ .mode = 0644,
.fops = &prng_tdes_fops,
};
diff --git a/kernel/arch/s390/hypfs/hypfs_diag.c b/kernel/arch/s390/hypfs/hypfs_diag.c
index 045035796..b63b9a42a 100644
--- a/kernel/arch/s390/hypfs/hypfs_diag.c
+++ b/kernel/arch/s390/hypfs/hypfs_diag.c
@@ -525,11 +525,11 @@ static int diag224(void *ptr)
static int diag224_get_name_table(void)
{
/* memory must be below 2GB */
- diag224_cpu_names = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA);
+ diag224_cpu_names = (char *) __get_free_page(GFP_KERNEL | GFP_DMA);
if (!diag224_cpu_names)
return -ENOMEM;
if (diag224(diag224_cpu_names)) {
- kfree(diag224_cpu_names);
+ free_page((unsigned long) diag224_cpu_names);
return -EOPNOTSUPP;
}
EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16);
@@ -538,7 +538,7 @@ static int diag224_get_name_table(void)
static void diag224_delete_name_table(void)
{
- kfree(diag224_cpu_names);
+ free_page((unsigned long) diag224_cpu_names);
}
static int diag224_idx2name(int index, char *name)
diff --git a/kernel/arch/s390/include/asm/fpu/api.h b/kernel/arch/s390/include/asm/fpu/api.h
index 5e04f3cbd..8ae236b0f 100644
--- a/kernel/arch/s390/include/asm/fpu/api.h
+++ b/kernel/arch/s390/include/asm/fpu/api.h
@@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc)
" la %0,0\n"
"1:\n"
EX_TABLE(0b,1b)
- : "=d" (rc), "=d" (orig_fpc)
+ : "=d" (rc), "=&d" (orig_fpc)
: "d" (fpc), "0" (-EINVAL));
return rc;
}
diff --git a/kernel/arch/s390/include/asm/mmu.h b/kernel/arch/s390/include/asm/mmu.h
index d29ad9545..081b2ad99 100644
--- a/kernel/arch/s390/include/asm/mmu.h
+++ b/kernel/arch/s390/include/asm/mmu.h
@@ -11,7 +11,7 @@ typedef struct {
spinlock_t list_lock;
struct list_head pgtable_list;
struct list_head gmap_list;
- unsigned long asce_bits;
+ unsigned long asce;
unsigned long asce_limit;
unsigned long vdso_base;
/* The mmu context allocates 4K page tables. */
diff --git a/kernel/arch/s390/include/asm/mmu_context.h b/kernel/arch/s390/include/asm/mmu_context.h
index e485817f7..22877c944 100644
--- a/kernel/arch/s390/include/asm/mmu_context.h
+++ b/kernel/arch/s390/include/asm/mmu_context.h
@@ -26,12 +26,28 @@ static inline int init_new_context(struct task_struct *tsk,
mm->context.has_pgste = 0;
mm->context.use_skey = 0;
#endif
- if (mm->context.asce_limit == 0) {
+ switch (mm->context.asce_limit) {
+ case 1UL << 42:
+ /*
+ * forked 3-level task, fall through to set new asce with new
+ * mm->pgd
+ */
+ case 0:
/* context created by exec, set asce limit to 4TB */
- mm->context.asce_bits = _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
mm->context.asce_limit = STACK_TOP_MAX;
- } else if (mm->context.asce_limit == (1UL << 31)) {
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
+ break;
+ case 1UL << 53:
+ /* forked 4-level task, set new asce with new mm->pgd */
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+ break;
+ case 1UL << 31:
+ /* forked 2-level compat task, set new asce with new mm->pgd */
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
+ /* pgd_alloc() did not increase mm->nr_pmds */
mm_inc_nr_pmds(mm);
}
crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
@@ -42,7 +58,7 @@ static inline int init_new_context(struct task_struct *tsk,
static inline void set_user_asce(struct mm_struct *mm)
{
- S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd);
+ S390_lowcore.user_asce = mm->context.asce;
if (current->thread.mm_segment.ar4)
__ctl_load(S390_lowcore.user_asce, 7, 7);
set_cpu_flag(CIF_ASCE);
@@ -71,7 +87,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
{
int cpu = smp_processor_id();
- S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd);
+ S390_lowcore.user_asce = next->context.asce;
if (prev == next)
return;
if (MACHINE_HAS_TLB_LC)
diff --git a/kernel/arch/s390/include/asm/pci.h b/kernel/arch/s390/include/asm/pci.h
index c873e682b..6dafabb6a 100644
--- a/kernel/arch/s390/include/asm/pci.h
+++ b/kernel/arch/s390/include/asm/pci.h
@@ -45,7 +45,8 @@ struct zpci_fmb {
u64 rpcit_ops;
u64 dma_rbytes;
u64 dma_wbytes;
-} __packed __aligned(16);
+ u64 pad[2];
+} __packed __aligned(128);
enum zpci_state {
ZPCI_FN_STATE_RESERVED,
diff --git a/kernel/arch/s390/include/asm/pci_dma.h b/kernel/arch/s390/include/asm/pci_dma.h
index 1aac41e83..92df3eb8d 100644
--- a/kernel/arch/s390/include/asm/pci_dma.h
+++ b/kernel/arch/s390/include/asm/pci_dma.h
@@ -23,6 +23,8 @@ enum zpci_ioat_dtype {
#define ZPCI_IOTA_FS_2G 2
#define ZPCI_KEY (PAGE_DEFAULT_KEY << 5)
+#define ZPCI_TABLE_SIZE_RT (1UL << 42)
+
#define ZPCI_IOTA_STO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_ST)
#define ZPCI_IOTA_RTTO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RT)
#define ZPCI_IOTA_RSTO_FLAG (ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RS)
diff --git a/kernel/arch/s390/include/asm/pgalloc.h b/kernel/arch/s390/include/asm/pgalloc.h
index d7cc79fb6..5991cdcb5 100644
--- a/kernel/arch/s390/include/asm/pgalloc.h
+++ b/kernel/arch/s390/include/asm/pgalloc.h
@@ -56,8 +56,8 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm)
return _REGION2_ENTRY_EMPTY;
}
-int crst_table_upgrade(struct mm_struct *, unsigned long limit);
-void crst_table_downgrade(struct mm_struct *, unsigned long limit);
+int crst_table_upgrade(struct mm_struct *);
+void crst_table_downgrade(struct mm_struct *);
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
{
diff --git a/kernel/arch/s390/include/asm/processor.h b/kernel/arch/s390/include/asm/processor.h
index b16c3d0a1..c1ea67db8 100644
--- a/kernel/arch/s390/include/asm/processor.h
+++ b/kernel/arch/s390/include/asm/processor.h
@@ -163,7 +163,7 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS];
regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \
regs->psw.addr = new_psw | PSW_ADDR_AMODE; \
regs->gprs[15] = new_stackp; \
- crst_table_downgrade(current->mm, 1UL << 31); \
+ crst_table_downgrade(current->mm); \
execve_tail(); \
} while (0)
diff --git a/kernel/arch/s390/include/asm/tlbflush.h b/kernel/arch/s390/include/asm/tlbflush.h
index ca148f7c3..0a2031618 100644
--- a/kernel/arch/s390/include/asm/tlbflush.h
+++ b/kernel/arch/s390/include/asm/tlbflush.h
@@ -81,7 +81,8 @@ static inline void __tlb_flush_full(struct mm_struct *mm)
}
/*
- * Flush TLB entries for a specific ASCE on all CPUs.
+ * Flush TLB entries for a specific ASCE on all CPUs. Should never be used
+ * when more than one asce (e.g. gmap) ran on this mm.
*/
static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
{
@@ -110,8 +111,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
static inline void __tlb_flush_kernel(void)
{
if (MACHINE_HAS_IDTE)
- __tlb_flush_idte((unsigned long) init_mm.pgd |
- init_mm.context.asce_bits);
+ __tlb_flush_idte(init_mm.context.asce);
else
__tlb_flush_global();
}
@@ -133,8 +133,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
static inline void __tlb_flush_kernel(void)
{
if (MACHINE_HAS_TLB_LC)
- __tlb_flush_idte_local((unsigned long) init_mm.pgd |
- init_mm.context.asce_bits);
+ __tlb_flush_idte_local(init_mm.context.asce);
else
__tlb_flush_local();
}
@@ -148,8 +147,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
* only ran on the local cpu.
*/
if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list))
- __tlb_flush_asce(mm, (unsigned long) mm->pgd |
- mm->context.asce_bits);
+ __tlb_flush_asce(mm, mm->context.asce);
else
__tlb_flush_full(mm);
}
diff --git a/kernel/arch/s390/include/asm/uaccess.h b/kernel/arch/s390/include/asm/uaccess.h
index 9dd4cc47d..5c7381c5a 100644
--- a/kernel/arch/s390/include/asm/uaccess.h
+++ b/kernel/arch/s390/include/asm/uaccess.h
@@ -215,28 +215,28 @@ 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/kernel/arch/s390/kernel/entry.S b/kernel/arch/s390/kernel/entry.S
index 857b6526d..424e6809a 100644
--- a/kernel/arch/s390/kernel/entry.S
+++ b/kernel/arch/s390/kernel/entry.S
@@ -1197,114 +1197,12 @@ cleanup_critical:
.quad .Lpsw_idle_lpsw
.Lcleanup_save_fpu_regs:
- TSTMSK __LC_CPU_FLAGS,_CIF_FPU
- bor %r14
- clg %r9,BASED(.Lcleanup_save_fpu_regs_done)
- jhe 5f
- clg %r9,BASED(.Lcleanup_save_fpu_regs_fp)
- jhe 4f
- clg %r9,BASED(.Lcleanup_save_fpu_regs_vx_high)
- jhe 3f
- clg %r9,BASED(.Lcleanup_save_fpu_regs_vx_low)
- jhe 2f
- clg %r9,BASED(.Lcleanup_save_fpu_fpc_end)
- jhe 1f
- lg %r2,__LC_CURRENT
- aghi %r2,__TASK_thread
-0: # Store floating-point controls
- stfpc __THREAD_FPU_fpc(%r2)
-1: # Load register save area and check if VX is active
- lg %r3,__THREAD_FPU_regs(%r2)
- TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX
- jz 4f # no VX -> store FP regs
-2: # Store vector registers (V0-V15)
- VSTM %v0,%v15,0,%r3 # vstm 0,15,0(3)
-3: # Store vector registers (V16-V31)
- VSTM %v16,%v31,256,%r3 # vstm 16,31,256(3)
- j 5f # -> done, set CIF_FPU flag
-4: # Store floating-point registers
- std 0,0(%r3)
- std 1,8(%r3)
- std 2,16(%r3)
- std 3,24(%r3)
- std 4,32(%r3)
- std 5,40(%r3)
- std 6,48(%r3)
- std 7,56(%r3)
- std 8,64(%r3)
- std 9,72(%r3)
- std 10,80(%r3)
- std 11,88(%r3)
- std 12,96(%r3)
- std 13,104(%r3)
- std 14,112(%r3)
- std 15,120(%r3)
-5: # Set CIF_FPU flag
- oi __LC_CPU_FLAGS+7,_CIF_FPU
- lg %r9,48(%r11) # return from save_fpu_regs
+ larl %r9,save_fpu_regs
br %r14
-.Lcleanup_save_fpu_fpc_end:
- .quad .Lsave_fpu_regs_fpc_end
-.Lcleanup_save_fpu_regs_vx_low:
- .quad .Lsave_fpu_regs_vx_low
-.Lcleanup_save_fpu_regs_vx_high:
- .quad .Lsave_fpu_regs_vx_high
-.Lcleanup_save_fpu_regs_fp:
- .quad .Lsave_fpu_regs_fp
-.Lcleanup_save_fpu_regs_done:
- .quad .Lsave_fpu_regs_done
.Lcleanup_load_fpu_regs:
- TSTMSK __LC_CPU_FLAGS,_CIF_FPU
- bnor %r14
- clg %r9,BASED(.Lcleanup_load_fpu_regs_done)
- jhe 1f
- clg %r9,BASED(.Lcleanup_load_fpu_regs_fp)
- jhe 2f
- clg %r9,BASED(.Lcleanup_load_fpu_regs_vx_high)
- jhe 3f
- clg %r9,BASED(.Lcleanup_load_fpu_regs_vx)
- jhe 4f
- lg %r4,__LC_CURRENT
- aghi %r4,__TASK_thread
- lfpc __THREAD_FPU_fpc(%r4)
- TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX
- lg %r4,__THREAD_FPU_regs(%r4) # %r4 <- reg save area
- jz 2f # -> no VX, load FP regs
-4: # Load V0 ..V15 registers
- VLM %v0,%v15,0,%r4
-3: # Load V16..V31 registers
- VLM %v16,%v31,256,%r4
- j 1f
-2: # Load floating-point registers
- ld 0,0(%r4)
- ld 1,8(%r4)
- ld 2,16(%r4)
- ld 3,24(%r4)
- ld 4,32(%r4)
- ld 5,40(%r4)
- ld 6,48(%r4)
- ld 7,56(%r4)
- ld 8,64(%r4)
- ld 9,72(%r4)
- ld 10,80(%r4)
- ld 11,88(%r4)
- ld 12,96(%r4)
- ld 13,104(%r4)
- ld 14,112(%r4)
- ld 15,120(%r4)
-1: # Clear CIF_FPU bit
- ni __LC_CPU_FLAGS+7,255-_CIF_FPU
- lg %r9,48(%r11) # return from load_fpu_regs
+ larl %r9,load_fpu_regs
br %r14
-.Lcleanup_load_fpu_regs_vx:
- .quad .Lload_fpu_regs_vx
-.Lcleanup_load_fpu_regs_vx_high:
- .quad .Lload_fpu_regs_vx_high
-.Lcleanup_load_fpu_regs_fp:
- .quad .Lload_fpu_regs_fp
-.Lcleanup_load_fpu_regs_done:
- .quad .Lload_fpu_regs_done
/*
* Integer constants
diff --git a/kernel/arch/s390/kernel/head64.S b/kernel/arch/s390/kernel/head64.S
index 58b719fa8..1ad2407c7 100644
--- a/kernel/arch/s390/kernel/head64.S
+++ b/kernel/arch/s390/kernel/head64.S
@@ -16,7 +16,7 @@
__HEAD
ENTRY(startup_continue)
- tm __LC_STFL_FAC_LIST+6,0x80 # LPP available ?
+ tm __LC_STFL_FAC_LIST+5,0x80 # LPP available ?
jz 0f
xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid
mvi __LC_LPP,0x80 # and set LPP_MAGIC
diff --git a/kernel/arch/s390/kernel/ipl.c b/kernel/arch/s390/kernel/ipl.c
index b1f0a90f9..42570d8fb 100644
--- a/kernel/arch/s390/kernel/ipl.c
+++ b/kernel/arch/s390/kernel/ipl.c
@@ -2070,13 +2070,6 @@ void s390_reset_system(void (*fn_pre)(void),
S390_lowcore.program_new_psw.addr =
PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
- /*
- * Clear subchannel ID and number to signal new kernel that no CCW or
- * SCSI IPL has been done (for kexec and kdump)
- */
- S390_lowcore.subchannel_id = 0;
- S390_lowcore.subchannel_nr = 0;
-
/* Store status at absolute zero */
store_status();
diff --git a/kernel/arch/s390/kernel/ptrace.c b/kernel/arch/s390/kernel/ptrace.c
index 01c37b36c..02bd587b6 100644
--- a/kernel/arch/s390/kernel/ptrace.c
+++ b/kernel/arch/s390/kernel/ptrace.c
@@ -963,6 +963,11 @@ static int s390_fpregs_set(struct task_struct *target,
if (target == current)
save_fpu_regs();
+ if (MACHINE_HAS_VX)
+ convert_vx_to_fp(fprs, target->thread.fpu.vxrs);
+ else
+ memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
+
/* If setting FPC, must validate it first. */
if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
@@ -1067,6 +1072,9 @@ static int s390_vxrs_low_set(struct task_struct *target,
if (target == current)
save_fpu_regs();
+ for (i = 0; i < __NUM_VXRS_LOW; i++)
+ vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1);
+
rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
if (rc == 0)
for (i = 0; i < __NUM_VXRS_LOW; i++)
diff --git a/kernel/arch/s390/kernel/setup.c b/kernel/arch/s390/kernel/setup.c
index c837bcacf..1f581eb61 100644
--- a/kernel/arch/s390/kernel/setup.c
+++ b/kernel/arch/s390/kernel/setup.c
@@ -329,6 +329,7 @@ static void __init setup_lowcore(void)
+ PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
lc->current_task = (unsigned long) init_thread_union.thread_info.task;
lc->thread_info = (unsigned long) &init_thread_union;
+ lc->lpp = LPP_MAGIC;
lc->machine_flags = S390_lowcore.machine_flags;
lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
diff --git a/kernel/arch/s390/mm/init.c b/kernel/arch/s390/mm/init.c
index c722400c7..feff9caf8 100644
--- a/kernel/arch/s390/mm/init.c
+++ b/kernel/arch/s390/mm/init.c
@@ -89,7 +89,8 @@ void __init paging_init(void)
asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
pgd_type = _REGION3_ENTRY_EMPTY;
}
- S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+ init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+ S390_lowcore.kernel_asce = init_mm.context.asce;
clear_table((unsigned long *) init_mm.pgd, pgd_type,
sizeof(unsigned long)*2048);
vmem_map_init();
diff --git a/kernel/arch/s390/mm/mmap.c b/kernel/arch/s390/mm/mmap.c
index ea01477b4..f2b6b1d9c 100644
--- a/kernel/arch/s390/mm/mmap.c
+++ b/kernel/arch/s390/mm/mmap.c
@@ -174,7 +174,7 @@ int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags)
if (!(flags & MAP_FIXED))
addr = 0;
if ((addr + len) >= TASK_SIZE)
- return crst_table_upgrade(current->mm, 1UL << 53);
+ return crst_table_upgrade(current->mm);
return 0;
}
@@ -191,7 +191,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr,
return area;
if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
/* Upgrade the page table to 4 levels and retry. */
- rc = crst_table_upgrade(mm, 1UL << 53);
+ rc = crst_table_upgrade(mm);
if (rc)
return (unsigned long) rc;
area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
@@ -213,7 +213,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
return area;
if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
/* Upgrade the page table to 4 levels and retry. */
- rc = crst_table_upgrade(mm, 1UL << 53);
+ rc = crst_table_upgrade(mm);
if (rc)
return (unsigned long) rc;
area = arch_get_unmapped_area_topdown(filp, addr, len,
diff --git a/kernel/arch/s390/mm/pgtable.c b/kernel/arch/s390/mm/pgtable.c
index 54ef3bc01..8345ae1f1 100644
--- a/kernel/arch/s390/mm/pgtable.c
+++ b/kernel/arch/s390/mm/pgtable.c
@@ -49,81 +49,52 @@ static void __crst_table_upgrade(void *arg)
__tlb_flush_local();
}
-int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
+int crst_table_upgrade(struct mm_struct *mm)
{
unsigned long *table, *pgd;
- unsigned long entry;
- int flush;
- BUG_ON(limit > (1UL << 53));
- flush = 0;
-repeat:
+ /* upgrade should only happen from 3 to 4 levels */
+ BUG_ON(mm->context.asce_limit != (1UL << 42));
+
table = crst_table_alloc(mm);
if (!table)
return -ENOMEM;
+
spin_lock_bh(&mm->page_table_lock);
- if (mm->context.asce_limit < limit) {
- pgd = (unsigned long *) mm->pgd;
- if (mm->context.asce_limit <= (1UL << 31)) {
- entry = _REGION3_ENTRY_EMPTY;
- mm->context.asce_limit = 1UL << 42;
- mm->context.asce_bits = _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS |
- _ASCE_TYPE_REGION3;
- } else {
- entry = _REGION2_ENTRY_EMPTY;
- mm->context.asce_limit = 1UL << 53;
- mm->context.asce_bits = _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS |
- _ASCE_TYPE_REGION2;
- }
- crst_table_init(table, entry);
- pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
- mm->pgd = (pgd_t *) table;
- mm->task_size = mm->context.asce_limit;
- table = NULL;
- flush = 1;
- }
+ pgd = (unsigned long *) mm->pgd;
+ crst_table_init(table, _REGION2_ENTRY_EMPTY);
+ pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
+ mm->pgd = (pgd_t *) table;
+ mm->context.asce_limit = 1UL << 53;
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+ mm->task_size = mm->context.asce_limit;
spin_unlock_bh(&mm->page_table_lock);
- if (table)
- crst_table_free(mm, table);
- if (mm->context.asce_limit < limit)
- goto repeat;
- if (flush)
- on_each_cpu(__crst_table_upgrade, mm, 0);
+
+ on_each_cpu(__crst_table_upgrade, mm, 0);
return 0;
}
-void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
+void crst_table_downgrade(struct mm_struct *mm)
{
pgd_t *pgd;
+ /* downgrade should only happen from 3 to 2 levels (compat only) */
+ BUG_ON(mm->context.asce_limit != (1UL << 42));
+
if (current->active_mm == mm) {
clear_user_asce();
__tlb_flush_mm(mm);
}
- while (mm->context.asce_limit > limit) {
- pgd = mm->pgd;
- switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
- case _REGION_ENTRY_TYPE_R2:
- mm->context.asce_limit = 1UL << 42;
- mm->context.asce_bits = _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS |
- _ASCE_TYPE_REGION3;
- break;
- case _REGION_ENTRY_TYPE_R3:
- mm->context.asce_limit = 1UL << 31;
- mm->context.asce_bits = _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS |
- _ASCE_TYPE_SEGMENT;
- break;
- default:
- BUG();
- }
- mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
- mm->task_size = mm->context.asce_limit;
- crst_table_free(mm, (unsigned long *) pgd);
- }
+
+ pgd = mm->pgd;
+ mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
+ mm->context.asce_limit = 1UL << 31;
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
+ mm->task_size = mm->context.asce_limit;
+ crst_table_free(mm, (unsigned long *) pgd);
+
if (current->active_mm == mm)
set_user_asce(mm);
}
@@ -195,7 +166,7 @@ EXPORT_SYMBOL_GPL(gmap_alloc);
static void gmap_flush_tlb(struct gmap *gmap)
{
if (MACHINE_HAS_IDTE)
- __tlb_flush_asce(gmap->mm, gmap->asce);
+ __tlb_flush_idte(gmap->asce);
else
__tlb_flush_global();
}
@@ -234,7 +205,7 @@ void gmap_free(struct gmap *gmap)
/* Flush tlb. */
if (MACHINE_HAS_IDTE)
- __tlb_flush_asce(gmap->mm, gmap->asce);
+ __tlb_flush_idte(gmap->asce);
else
__tlb_flush_global();
diff --git a/kernel/arch/s390/net/bpf_jit.h b/kernel/arch/s390/net/bpf_jit.h
index f010c93a8..fda605dbc 100644
--- a/kernel/arch/s390/net/bpf_jit.h
+++ b/kernel/arch/s390/net/bpf_jit.h
@@ -37,7 +37,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
* | | |
* +---------------+ |
* | 8 byte skbp | |
- * R15+170 -> +---------------+ |
+ * R15+176 -> +---------------+ |
* | 8 byte hlen | |
* R15+168 -> +---------------+ |
* | 4 byte align | |
@@ -58,7 +58,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
#define STK_OFF (STK_SPACE - STK_160_UNUSED)
#define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */
#define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */
-#define STK_OFF_SKBP 170 /* Offset of SKB pointer on stack */
+#define STK_OFF_SKBP 176 /* Offset of SKB pointer on stack */
#define STK_OFF_R6 (160 - 11 * 8) /* Offset of r6 on stack */
#define STK_OFF_TCCNT (160 - 12 * 8) /* Offset of tail_call_cnt on stack */
diff --git a/kernel/arch/s390/net/bpf_jit_comp.c b/kernel/arch/s390/net/bpf_jit_comp.c
index 9a0c4c22e..0e2919dd8 100644
--- a/kernel/arch/s390/net/bpf_jit_comp.c
+++ b/kernel/arch/s390/net/bpf_jit_comp.c
@@ -45,7 +45,7 @@ struct bpf_jit {
int labels[1]; /* Labels for local jumps */
};
-#define BPF_SIZE_MAX 0x7ffff /* Max size for program (20 bit signed displ) */
+#define BPF_SIZE_MAX 0xffff /* Max size for program (16 bit branches) */
#define SEEN_SKB 1 /* skb access */
#define SEEN_MEM 2 /* use mem[] for temporary storage */
@@ -446,7 +446,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
emit_load_skb_data_hlen(jit);
if (jit->seen & SEEN_SKB_CHANGE)
/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
- EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
+ EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
STK_OFF_SKBP);
/* Clear A (%b0) and X (%b7) registers for converted BPF programs */
if (is_classic) {
diff --git a/kernel/arch/s390/pci/pci.c b/kernel/arch/s390/pci/pci.c
index 7ef12a3ac..f2f6720a3 100644
--- a/kernel/arch/s390/pci/pci.c
+++ b/kernel/arch/s390/pci/pci.c
@@ -701,8 +701,7 @@ static int zpci_restore(struct device *dev)
goto out;
zpci_map_resources(pdev);
- zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET,
- zdev->start_dma + zdev->iommu_size - 1,
+ zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
(u64) zdev->dma_table);
out:
@@ -871,8 +870,11 @@ static inline int barsize(u8 size)
static int zpci_mem_init(void)
{
+ BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) ||
+ __alignof__(struct zpci_fmb) < sizeof(struct zpci_fmb));
+
zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
- 16, 0, NULL);
+ __alignof__(struct zpci_fmb), 0, NULL);
if (!zdev_fmb_cache)
goto error_zdev;
diff --git a/kernel/arch/s390/pci/pci_dma.c b/kernel/arch/s390/pci/pci_dma.c
index d348f2c09..3a40f718b 100644
--- a/kernel/arch/s390/pci/pci_dma.c
+++ b/kernel/arch/s390/pci/pci_dma.c
@@ -458,7 +458,19 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
goto out_clean;
}
- zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
+ /*
+ * Restrict the iommu bitmap size to the minimum of the following:
+ * - main memory size
+ * - 3-level pagetable address limit minus start_dma offset
+ * - DMA address range allowed by the hardware (clp query pci fn)
+ *
+ * Also set zdev->end_dma to the actual end address of the usable
+ * range, instead of the theoretical maximum as reported by hardware.
+ */
+ zdev->iommu_size = min3((u64) high_memory,
+ ZPCI_TABLE_SIZE_RT - zdev->start_dma,
+ zdev->end_dma - zdev->start_dma + 1);
+ zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1;
zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
if (!zdev->iommu_bitmap) {
@@ -466,10 +478,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
goto out_reg;
}
- rc = zpci_register_ioat(zdev,
- 0,
- zdev->start_dma + PAGE_OFFSET,
- zdev->start_dma + zdev->iommu_size - 1,
+ rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
(u64) zdev->dma_table);
if (rc)
goto out_reg;
diff --git a/kernel/arch/score/include/asm/uaccess.h b/kernel/arch/score/include/asm/uaccess.h
index 20a359122..01aec8ccd 100644
--- a/kernel/arch/score/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/sh/include/asm/uaccess.h b/kernel/arch/sh/include/asm/uaccess.h
index a49635c51..92ade79ac 100644
--- a/kernel/arch/sh/include/asm/uaccess.h
+++ b/kernel/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/kernel/arch/sh/include/asm/uaccess_64.h b/kernel/arch/sh/include/asm/uaccess_64.h
index c01376c76..ca5073dd4 100644
--- a/kernel/arch/sh/include/asm/uaccess_64.h
+++ b/kernel/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/kernel/arch/sh/mm/kmap.c b/kernel/arch/sh/mm/kmap.c
index ec29e14ec..bf25d7c79 100644
--- a/kernel/arch/sh/mm/kmap.c
+++ b/kernel/arch/sh/mm/kmap.c
@@ -36,6 +36,7 @@ void *kmap_coherent(struct page *page, unsigned long addr)
BUG_ON(!test_bit(PG_dcache_clean, &page->flags));
+ preempt_disable();
pagefault_disable();
idx = FIX_CMAP_END -
@@ -64,4 +65,5 @@ void kunmap_coherent(void *kvaddr)
}
pagefault_enable();
+ preempt_enable();
}
diff --git a/kernel/arch/sparc/include/asm/head_64.h b/kernel/arch/sparc/include/asm/head_64.h
index 10e9dabc4..f0700cfee 100644
--- a/kernel/arch/sparc/include/asm/head_64.h
+++ b/kernel/arch/sparc/include/asm/head_64.h
@@ -15,6 +15,10 @@
#define PTREGS_OFF (STACK_BIAS + STACKFRAME_SZ)
+#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
+#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
+#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
+
#define __CHEETAH_ID 0x003e0014
#define __JALAPENO_ID 0x003e0016
#define __SERRANO_ID 0x003e0022
diff --git a/kernel/arch/sparc/include/asm/mmu_64.h b/kernel/arch/sparc/include/asm/mmu_64.h
index 70067ce18..f7de0dbc3 100644
--- a/kernel/arch/sparc/include/asm/mmu_64.h
+++ b/kernel/arch/sparc/include/asm/mmu_64.h
@@ -92,7 +92,8 @@ struct tsb_config {
typedef struct {
spinlock_t lock;
unsigned long sparc64_ctx_val;
- unsigned long huge_pte_count;
+ unsigned long hugetlb_pte_count;
+ unsigned long thp_pte_count;
struct tsb_config tsb_block[MM_NUM_TSBS];
struct hv_tsb_descr tsb_descr[MM_NUM_TSBS];
} mm_context_t;
diff --git a/kernel/arch/sparc/include/asm/pgtable_64.h b/kernel/arch/sparc/include/asm/pgtable_64.h
index 131d36fcd..408b715c9 100644
--- a/kernel/arch/sparc/include/asm/pgtable_64.h
+++ b/kernel/arch/sparc/include/asm/pgtable_64.h
@@ -375,7 +375,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
#define pgprot_noncached pgprot_noncached
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline pte_t pte_mkhuge(pte_t pte)
+static inline unsigned long __pte_huge_mask(void)
{
unsigned long mask;
@@ -390,8 +390,19 @@ static inline pte_t pte_mkhuge(pte_t pte)
: "=r" (mask)
: "i" (_PAGE_SZHUGE_4U), "i" (_PAGE_SZHUGE_4V));
- return __pte(pte_val(pte) | mask);
+ return mask;
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+ return __pte(pte_val(pte) | __pte_huge_mask());
+}
+
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+ return !!(pte_val(pte) & __pte_huge_mask());
}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
@@ -403,6 +414,11 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
return __pmd(pte_val(pte));
}
#endif
+#else
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+ return false;
+}
#endif
static inline pte_t pte_mkdirty(pte_t pte)
@@ -865,6 +881,19 @@ static inline unsigned long pud_pfn(pud_t pud)
void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
pte_t *ptep, pte_t orig, int fullmm);
+static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+ pte_t *ptep, pte_t orig, int fullmm)
+{
+ /* It is more efficient to let flush_tlb_kernel_range()
+ * handle init_mm tlb flushes.
+ *
+ * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
+ * and SUN4V pte layout, so this inline test is fine.
+ */
+ if (likely(mm != &init_mm) && pte_accessible(mm, orig))
+ tlb_batch_add(mm, vaddr, ptep, orig, fullmm);
+}
+
#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
unsigned long addr,
@@ -881,15 +910,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t orig = *ptep;
*ptep = pte;
-
- /* It is more efficient to let flush_tlb_kernel_range()
- * handle init_mm tlb flushes.
- *
- * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
- * and SUN4V pte layout, so this inline test is fine.
- */
- if (likely(mm != &init_mm) && pte_accessible(mm, orig))
- tlb_batch_add(mm, addr, ptep, orig, fullmm);
+ maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm);
}
#define set_pte_at(mm,addr,ptep,pte) \
diff --git a/kernel/arch/sparc/include/asm/tlbflush_64.h b/kernel/arch/sparc/include/asm/tlbflush_64.h
index dea1cfa21..a8e192e90 100644
--- a/kernel/arch/sparc/include/asm/tlbflush_64.h
+++ b/kernel/arch/sparc/include/asm/tlbflush_64.h
@@ -8,6 +8,7 @@
#define TLB_BATCH_NR 192
struct tlb_batch {
+ bool huge;
struct mm_struct *mm;
unsigned long tlb_nr;
unsigned long active;
@@ -16,7 +17,7 @@ struct tlb_batch {
void flush_tsb_kernel_range(unsigned long start, unsigned long end);
void flush_tsb_user(struct tlb_batch *tb);
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge);
/* TLB flush operations. */
diff --git a/kernel/arch/sparc/include/asm/ttable.h b/kernel/arch/sparc/include/asm/ttable.h
index 71b5a6752..781b9f1db 100644
--- a/kernel/arch/sparc/include/asm/ttable.h
+++ b/kernel/arch/sparc/include/asm/ttable.h
@@ -589,8 +589,8 @@ user_rtt_fill_64bit: \
restored; \
nop; nop; nop; nop; nop; nop; \
nop; nop; nop; nop; nop; \
- ba,a,pt %xcc, user_rtt_fill_fixup; \
- ba,a,pt %xcc, user_rtt_fill_fixup; \
+ ba,a,pt %xcc, user_rtt_fill_fixup_dax; \
+ ba,a,pt %xcc, user_rtt_fill_fixup_mna; \
ba,a,pt %xcc, user_rtt_fill_fixup;
@@ -652,8 +652,8 @@ user_rtt_fill_32bit: \
restored; \
nop; nop; nop; nop; nop; \
nop; nop; nop; \
- ba,a,pt %xcc, user_rtt_fill_fixup; \
- ba,a,pt %xcc, user_rtt_fill_fixup; \
+ ba,a,pt %xcc, user_rtt_fill_fixup_dax; \
+ ba,a,pt %xcc, user_rtt_fill_fixup_mna; \
ba,a,pt %xcc, user_rtt_fill_fixup;
diff --git a/kernel/arch/sparc/include/asm/uaccess_32.h b/kernel/arch/sparc/include/asm/uaccess_32.h
index 64ee103dc..dfb542c7c 100644
--- a/kernel/arch/sparc/include/asm/uaccess_32.h
+++ b/kernel/arch/sparc/include/asm/uaccess_32.h
@@ -328,8 +328,10 @@ static inline unsigned long copy_from_user(void *to, const void __user *from, un
{
if (n && __access_ok((unsigned long) from, n))
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/kernel/arch/sparc/include/asm/uaccess_64.h b/kernel/arch/sparc/include/asm/uaccess_64.h
index ea6e9a20f..f42851248 100644
--- a/kernel/arch/sparc/include/asm/uaccess_64.h
+++ b/kernel/arch/sparc/include/asm/uaccess_64.h
@@ -98,7 +98,6 @@ struct exception_table_entry {
unsigned int insn, fixup;
};
-void __ret_efault(void);
void __retl_efault(void);
/* Uh, these should become the main single-value transfer routines..
@@ -179,20 +178,6 @@ int __put_user_bad(void);
__gu_ret; \
})
-#define __get_user_nocheck_ret(data, addr, size, type, retval) ({ \
- register unsigned long __gu_val __asm__ ("l1"); \
- switch (size) { \
- case 1: __get_user_asm_ret(__gu_val, ub, addr, retval); break; \
- case 2: __get_user_asm_ret(__gu_val, uh, addr, retval); break; \
- case 4: __get_user_asm_ret(__gu_val, uw, addr, retval); break; \
- case 8: __get_user_asm_ret(__gu_val, x, addr, retval); break; \
- default: \
- if (__get_user_bad()) \
- return retval; \
- } \
- data = (__force type) __gu_val; \
-})
-
#define __get_user_asm(x, size, addr, ret) \
__asm__ __volatile__( \
"/* Get user asm, inline. */\n" \
@@ -214,80 +199,35 @@ __asm__ __volatile__( \
: "=r" (ret), "=r" (x) : "r" (__m(addr)), \
"i" (-EFAULT))
-#define __get_user_asm_ret(x, size, addr, retval) \
-if (__builtin_constant_p(retval) && retval == -EFAULT) \
- __asm__ __volatile__( \
- "/* Get user asm ret, inline. */\n" \
- "1:\t" "ld"#size "a [%1] %%asi, %0\n\n\t" \
- ".section __ex_table,\"a\"\n\t" \
- ".align 4\n\t" \
- ".word 1b,__ret_efault\n\n\t" \
- ".previous\n\t" \
- : "=r" (x) : "r" (__m(addr))); \
-else \
- __asm__ __volatile__( \
- "/* Get user asm ret, inline. */\n" \
- "1:\t" "ld"#size "a [%1] %%asi, %0\n\n\t" \
- ".section .fixup,#alloc,#execinstr\n\t" \
- ".align 4\n" \
- "3:\n\t" \
- "ret\n\t" \
- " restore %%g0, %2, %%o0\n\n\t" \
- ".previous\n\t" \
- ".section __ex_table,\"a\"\n\t" \
- ".align 4\n\t" \
- ".word 1b, 3b\n\n\t" \
- ".previous\n\t" \
- : "=r" (x) : "r" (__m(addr)), "i" (retval))
-
int __get_user_bad(void);
unsigned long __must_check ___copy_from_user(void *to,
const void __user *from,
unsigned long size);
-unsigned long copy_from_user_fixup(void *to, const void __user *from,
- unsigned long size);
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long size)
{
- unsigned long ret = ___copy_from_user(to, from, size);
-
- if (unlikely(ret))
- ret = copy_from_user_fixup(to, from, size);
-
- return ret;
+ return ___copy_from_user(to, from, size);
}
#define __copy_from_user copy_from_user
unsigned long __must_check ___copy_to_user(void __user *to,
const void *from,
unsigned long size);
-unsigned long copy_to_user_fixup(void __user *to, const void *from,
- unsigned long size);
static inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long size)
{
- unsigned long ret = ___copy_to_user(to, from, size);
-
- if (unlikely(ret))
- ret = copy_to_user_fixup(to, from, size);
- return ret;
+ return ___copy_to_user(to, from, size);
}
#define __copy_to_user copy_to_user
unsigned long __must_check ___copy_in_user(void __user *to,
const void __user *from,
unsigned long size);
-unsigned long copy_in_user_fixup(void __user *to, void __user *from,
- unsigned long size);
static inline unsigned long __must_check
copy_in_user(void __user *to, void __user *from, unsigned long size)
{
- unsigned long ret = ___copy_in_user(to, from, size);
-
- if (unlikely(ret))
- ret = copy_in_user_fixup(to, from, size);
- return ret;
+ return ___copy_in_user(to, from, size);
}
#define __copy_in_user copy_in_user
diff --git a/kernel/arch/sparc/kernel/Makefile b/kernel/arch/sparc/kernel/Makefile
index 7cf9c6ea3..fdb13327f 100644
--- a/kernel/arch/sparc/kernel/Makefile
+++ b/kernel/arch/sparc/kernel/Makefile
@@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg
CFLAGS_REMOVE_pcr.o := -pg
endif
+obj-$(CONFIG_SPARC64) += urtt_fill.o
obj-$(CONFIG_SPARC32) += entry.o wof.o wuf.o
obj-$(CONFIG_SPARC32) += etrap_32.o
obj-$(CONFIG_SPARC32) += rtrap_32.o
diff --git a/kernel/arch/sparc/kernel/cherrs.S b/kernel/arch/sparc/kernel/cherrs.S
index 4ee1ad420..655628def 100644
--- a/kernel/arch/sparc/kernel/cherrs.S
+++ b/kernel/arch/sparc/kernel/cherrs.S
@@ -214,8 +214,7 @@ do_dcpe_tl1_nonfatal: /* Ok we may use interrupt globals safely. */
subcc %g1, %g2, %g1 ! Next cacheline
bge,pt %icc, 1b
nop
- ba,pt %xcc, dcpe_icpe_tl1_common
- nop
+ ba,a,pt %xcc, dcpe_icpe_tl1_common
do_dcpe_tl1_fatal:
sethi %hi(1f), %g7
@@ -224,8 +223,7 @@ do_dcpe_tl1_fatal:
mov 0x2, %o0
call cheetah_plus_parity_error
add %sp, PTREGS_OFF, %o1
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size do_dcpe_tl1,.-do_dcpe_tl1
.globl do_icpe_tl1
@@ -259,8 +257,7 @@ do_icpe_tl1_nonfatal: /* Ok we may use interrupt globals safely. */
subcc %g1, %g2, %g1
bge,pt %icc, 1b
nop
- ba,pt %xcc, dcpe_icpe_tl1_common
- nop
+ ba,a,pt %xcc, dcpe_icpe_tl1_common
do_icpe_tl1_fatal:
sethi %hi(1f), %g7
@@ -269,8 +266,7 @@ do_icpe_tl1_fatal:
mov 0x3, %o0
call cheetah_plus_parity_error
add %sp, PTREGS_OFF, %o1
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size do_icpe_tl1,.-do_icpe_tl1
.type dcpe_icpe_tl1_common,#function
@@ -456,7 +452,7 @@ __cheetah_log_error:
cmp %g2, 0x63
be c_cee
nop
- ba,pt %xcc, c_deferred
+ ba,a,pt %xcc, c_deferred
.size __cheetah_log_error,.-__cheetah_log_error
/* Cheetah FECC trap handling, we get here from tl{0,1}_fecc
diff --git a/kernel/arch/sparc/kernel/dtlb_prot.S b/kernel/arch/sparc/kernel/dtlb_prot.S
index d668ca149..4087a62f9 100644
--- a/kernel/arch/sparc/kernel/dtlb_prot.S
+++ b/kernel/arch/sparc/kernel/dtlb_prot.S
@@ -25,13 +25,13 @@
/* PROT ** ICACHE line 2: More real fault processing */
ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5
+ srlx %g5, PAGE_SHIFT, %g5
+ sllx %g5, PAGE_SHIFT, %g5 ! Clear context ID bits
bgu,pn %xcc, winfix_trampoline ! Yes, perform winfixup
mov FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault
nop
nop
- nop
- nop
/* PROT ** ICACHE line 3: Unused... */
nop
diff --git a/kernel/arch/sparc/kernel/entry.S b/kernel/arch/sparc/kernel/entry.S
index 33c02b15f..a83707c83 100644
--- a/kernel/arch/sparc/kernel/entry.S
+++ b/kernel/arch/sparc/kernel/entry.S
@@ -948,7 +948,24 @@ linux_syscall_trace:
cmp %o0, 0
bne 3f
mov -ENOSYS, %o0
+
+ /* Syscall tracing can modify the registers. */
+ ld [%sp + STACKFRAME_SZ + PT_G1], %g1
+ sethi %hi(sys_call_table), %l7
+ ld [%sp + STACKFRAME_SZ + PT_I0], %i0
+ or %l7, %lo(sys_call_table), %l7
+ ld [%sp + STACKFRAME_SZ + PT_I1], %i1
+ ld [%sp + STACKFRAME_SZ + PT_I2], %i2
+ ld [%sp + STACKFRAME_SZ + PT_I3], %i3
+ ld [%sp + STACKFRAME_SZ + PT_I4], %i4
+ ld [%sp + STACKFRAME_SZ + PT_I5], %i5
+ cmp %g1, NR_syscalls
+ bgeu 3f
+ mov -ENOSYS, %o0
+
+ sll %g1, 2, %l4
mov %i0, %o0
+ ld [%l7 + %l4], %l7
mov %i1, %o1
mov %i2, %o2
mov %i3, %o3
diff --git a/kernel/arch/sparc/kernel/fpu_traps.S b/kernel/arch/sparc/kernel/fpu_traps.S
index a6864826a..336d2750f 100644
--- a/kernel/arch/sparc/kernel/fpu_traps.S
+++ b/kernel/arch/sparc/kernel/fpu_traps.S
@@ -100,8 +100,8 @@ do_fpdis:
fmuld %f0, %f2, %f26
faddd %f0, %f2, %f28
fmuld %f0, %f2, %f30
- b,pt %xcc, fpdis_exit
- nop
+ ba,a,pt %xcc, fpdis_exit
+
2: andcc %g5, FPRS_DU, %g0
bne,pt %icc, 3f
fzero %f32
@@ -144,8 +144,8 @@ do_fpdis:
fmuld %f32, %f34, %f58
faddd %f32, %f34, %f60
fmuld %f32, %f34, %f62
- ba,pt %xcc, fpdis_exit
- nop
+ ba,a,pt %xcc, fpdis_exit
+
3: mov SECONDARY_CONTEXT, %g3
add %g6, TI_FPREGS, %g1
@@ -197,8 +197,7 @@ fpdis_exit2:
fp_other_bounce:
call do_fpother
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size fp_other_bounce,.-fp_other_bounce
.align 32
diff --git a/kernel/arch/sparc/kernel/head_64.S b/kernel/arch/sparc/kernel/head_64.S
index f2d30cab5..7eeeb1d5a 100644
--- a/kernel/arch/sparc/kernel/head_64.S
+++ b/kernel/arch/sparc/kernel/head_64.S
@@ -461,9 +461,8 @@ sun4v_chip_type:
subcc %g3, 1, %g3
bne,pt %xcc, 41b
add %g1, 1, %g1
- mov SUN4V_CHIP_SPARC64X, %g4
ba,pt %xcc, 5f
- nop
+ mov SUN4V_CHIP_SPARC64X, %g4
49:
mov SUN4V_CHIP_UNKNOWN, %g4
@@ -548,8 +547,7 @@ sun4u_init:
stxa %g0, [%g7] ASI_DMMU
membar #Sync
- ba,pt %xcc, sun4u_continue
- nop
+ ba,a,pt %xcc, sun4u_continue
sun4v_init:
/* Set ctx 0 */
@@ -560,14 +558,12 @@ sun4v_init:
mov SECONDARY_CONTEXT, %g7
stxa %g0, [%g7] ASI_MMU
membar #Sync
- ba,pt %xcc, niagara_tlb_fixup
- nop
+ ba,a,pt %xcc, niagara_tlb_fixup
sun4u_continue:
BRANCH_IF_ANY_CHEETAH(g1, g7, cheetah_tlb_fixup)
- ba,pt %xcc, spitfire_tlb_fixup
- nop
+ ba,a,pt %xcc, spitfire_tlb_fixup
niagara_tlb_fixup:
mov 3, %g2 /* Set TLB type to hypervisor. */
@@ -639,8 +635,7 @@ niagara_patch:
call hypervisor_patch_cachetlbops
nop
- ba,pt %xcc, tlb_fixup_done
- nop
+ ba,a,pt %xcc, tlb_fixup_done
cheetah_tlb_fixup:
mov 2, %g2 /* Set TLB type to cheetah+. */
@@ -659,8 +654,7 @@ cheetah_tlb_fixup:
call cheetah_patch_cachetlbops
nop
- ba,pt %xcc, tlb_fixup_done
- nop
+ ba,a,pt %xcc, tlb_fixup_done
spitfire_tlb_fixup:
/* Set TLB type to spitfire. */
@@ -782,8 +776,7 @@ setup_trap_table:
call %o1
add %sp, (2047 + 128), %o0
- ba,pt %xcc, 2f
- nop
+ ba,a,pt %xcc, 2f
1: sethi %hi(sparc64_ttable_tl0), %o0
set prom_set_trap_table_name, %g2
@@ -822,8 +815,7 @@ setup_trap_table:
BRANCH_IF_ANY_CHEETAH(o2, o3, 1f)
- ba,pt %xcc, 2f
- nop
+ ba,a,pt %xcc, 2f
/* Disable STICK_INT interrupts. */
1:
@@ -930,47 +922,11 @@ prom_tba: .xword 0
tlb_type: .word 0 /* Must NOT end up in BSS */
.section ".fixup",#alloc,#execinstr
- .globl __ret_efault, __retl_efault, __ret_one, __retl_one
-ENTRY(__ret_efault)
- ret
- restore %g0, -EFAULT, %o0
-ENDPROC(__ret_efault)
-
ENTRY(__retl_efault)
retl
mov -EFAULT, %o0
ENDPROC(__retl_efault)
-ENTRY(__retl_one)
- retl
- mov 1, %o0
-ENDPROC(__retl_one)
-
-ENTRY(__retl_one_fp)
- VISExitHalf
- retl
- mov 1, %o0
-ENDPROC(__retl_one_fp)
-
-ENTRY(__ret_one_asi)
- wr %g0, ASI_AIUS, %asi
- ret
- restore %g0, 1, %o0
-ENDPROC(__ret_one_asi)
-
-ENTRY(__retl_one_asi)
- wr %g0, ASI_AIUS, %asi
- retl
- mov 1, %o0
-ENDPROC(__retl_one_asi)
-
-ENTRY(__retl_one_asi_fp)
- wr %g0, ASI_AIUS, %asi
- VISExitHalf
- retl
- mov 1, %o0
-ENDPROC(__retl_one_asi_fp)
-
ENTRY(__retl_o1)
retl
mov %o1, %o0
diff --git a/kernel/arch/sparc/kernel/jump_label.c b/kernel/arch/sparc/kernel/jump_label.c
index 59bbeff55..07933b9e9 100644
--- a/kernel/arch/sparc/kernel/jump_label.c
+++ b/kernel/arch/sparc/kernel/jump_label.c
@@ -13,19 +13,30 @@
void arch_jump_label_transform(struct jump_entry *entry,
enum jump_label_type type)
{
- u32 val;
u32 *insn = (u32 *) (unsigned long) entry->code;
+ u32 val;
if (type == JUMP_LABEL_JMP) {
s32 off = (s32)entry->target - (s32)entry->code;
+ bool use_v9_branch = false;
+
+ BUG_ON(off & 3);
#ifdef CONFIG_SPARC64
- /* ba,pt %xcc, . + (off << 2) */
- val = 0x10680000 | ((u32) off >> 2);
-#else
- /* ba . + (off << 2) */
- val = 0x10800000 | ((u32) off >> 2);
+ if (off <= 0xfffff && off >= -0x100000)
+ use_v9_branch = true;
#endif
+ if (use_v9_branch) {
+ /* WDISP19 - target is . + immed << 2 */
+ /* ba,pt %xcc, . + off */
+ val = 0x10680000 | (((u32) off >> 2) & 0x7ffff);
+ } else {
+ /* WDISP22 - target is . + immed << 2 */
+ BUG_ON(off > 0x7fffff);
+ BUG_ON(off < -0x800000);
+ /* ba . + off */
+ val = 0x10800000 | (((u32) off >> 2) & 0x3fffff);
+ }
} else {
val = 0x01000000;
}
diff --git a/kernel/arch/sparc/kernel/ktlb.S b/kernel/arch/sparc/kernel/ktlb.S
index ef0d8e9e1..f22bec0db 100644
--- a/kernel/arch/sparc/kernel/ktlb.S
+++ b/kernel/arch/sparc/kernel/ktlb.S
@@ -20,6 +20,10 @@ kvmap_itlb:
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_IMMU, %g4
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g4 here.
+ */
+
/* sun4v_itlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
@@ -128,6 +132,10 @@ kvmap_dtlb:
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_DMMU, %g4
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g4 here.
+ */
+
/* sun4v_dtlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
@@ -251,6 +259,10 @@ kvmap_dtlb_longpath:
nop
.previous
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g5 here.
+ */
+
be,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_DTLB, %g4
ba,pt %xcc, winfix_trampoline
diff --git a/kernel/arch/sparc/kernel/misctrap.S b/kernel/arch/sparc/kernel/misctrap.S
index 753b4f031..34b493390 100644
--- a/kernel/arch/sparc/kernel/misctrap.S
+++ b/kernel/arch/sparc/kernel/misctrap.S
@@ -18,8 +18,7 @@ __do_privact:
109: or %g7, %lo(109b), %g7
call do_privact
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size __do_privact,.-__do_privact
.type do_mna,#function
@@ -46,8 +45,7 @@ do_mna:
mov %l5, %o2
call mem_address_unaligned
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size do_mna,.-do_mna
.type do_lddfmna,#function
@@ -65,8 +63,7 @@ do_lddfmna:
mov %l5, %o2
call handle_lddfmna
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size do_lddfmna,.-do_lddfmna
.type do_stdfmna,#function
@@ -84,8 +81,7 @@ do_stdfmna:
mov %l5, %o2
call handle_stdfmna
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size do_stdfmna,.-do_stdfmna
.type breakpoint_trap,#function
diff --git a/kernel/arch/sparc/kernel/pci.c b/kernel/arch/sparc/kernel/pci.c
index badf0951d..9f9614df9 100644
--- a/kernel/arch/sparc/kernel/pci.c
+++ b/kernel/arch/sparc/kernel/pci.c
@@ -994,6 +994,23 @@ void pcibios_set_master(struct pci_dev *dev)
/* No special bus mastering setup handling */
}
+#ifdef CONFIG_PCI_IOV
+int pcibios_add_device(struct pci_dev *dev)
+{
+ struct pci_dev *pdev;
+
+ /* Add sriov arch specific initialization here.
+ * Copy dev_archdata from PF to VF
+ */
+ if (dev->is_virtfn) {
+ pdev = dev->physfn;
+ memcpy(&dev->dev.archdata, &pdev->dev.archdata,
+ sizeof(struct dev_archdata));
+ }
+ return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
static int __init pcibios_init(void)
{
pci_dfl_cache_line_size = 64 >> 2;
diff --git a/kernel/arch/sparc/kernel/rtrap_64.S b/kernel/arch/sparc/kernel/rtrap_64.S
index d08bdaffd..216948ca4 100644
--- a/kernel/arch/sparc/kernel/rtrap_64.S
+++ b/kernel/arch/sparc/kernel/rtrap_64.S
@@ -14,10 +14,6 @@
#include <asm/visasm.h>
#include <asm/processor.h>
-#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
-#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
-#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
-
#ifdef CONFIG_CONTEXT_TRACKING
# define SCHEDULE_USER schedule_user
#else
@@ -242,52 +238,17 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1
wrpr %g1, %cwp
ba,a,pt %xcc, user_rtt_fill_64bit
-user_rtt_fill_fixup:
- rdpr %cwp, %g1
- add %g1, 1, %g1
- wrpr %g1, 0x0, %cwp
-
- rdpr %wstate, %g2
- sll %g2, 3, %g2
- wrpr %g2, 0x0, %wstate
-
- /* We know %canrestore and %otherwin are both zero. */
-
- sethi %hi(sparc64_kern_pri_context), %g2
- ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2
- mov PRIMARY_CONTEXT, %g1
-
-661: stxa %g2, [%g1] ASI_DMMU
- .section .sun4v_1insn_patch, "ax"
- .word 661b
- stxa %g2, [%g1] ASI_MMU
- .previous
-
- sethi %hi(KERNBASE), %g1
- flush %g1
+user_rtt_fill_fixup_dax:
+ ba,pt %xcc, user_rtt_fill_fixup_common
+ mov 1, %g3
- or %g4, FAULT_CODE_WINFIXUP, %g4
- stb %g4, [%g6 + TI_FAULT_CODE]
- stx %g5, [%g6 + TI_FAULT_ADDR]
+user_rtt_fill_fixup_mna:
+ ba,pt %xcc, user_rtt_fill_fixup_common
+ mov 2, %g3
- mov %g6, %l1
- wrpr %g0, 0x0, %tl
-
-661: nop
- .section .sun4v_1insn_patch, "ax"
- .word 661b
- SET_GL(0)
- .previous
-
- wrpr %g0, RTRAP_PSTATE, %pstate
-
- mov %l1, %g6
- ldx [%g6 + TI_TASK], %g4
- LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
- call do_sparc64_fault
- add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+user_rtt_fill_fixup:
+ ba,pt %xcc, user_rtt_fill_fixup_common
+ clr %g3
user_rtt_pre_restore:
add %g1, 1, %g1
diff --git a/kernel/arch/sparc/kernel/signal32.c b/kernel/arch/sparc/kernel/signal32.c
index 4eed773a7..77655f0f0 100644
--- a/kernel/arch/sparc/kernel/signal32.c
+++ b/kernel/arch/sparc/kernel/signal32.c
@@ -138,12 +138,24 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
return 0;
}
+/* Checks if the fp is valid. We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+ if ((((unsigned long) fp) & 15) ||
+ ((unsigned long)fp) > 0x100000000ULL - fplen)
+ return true;
+ return false;
+}
+
void do_sigreturn32(struct pt_regs *regs)
{
struct signal_frame32 __user *sf;
compat_uptr_t fpu_save;
compat_uptr_t rwin_save;
- unsigned int psr;
+ unsigned int psr, ufp;
unsigned pc, npc;
sigset_t set;
compat_sigset_t seta;
@@ -158,11 +170,16 @@ void do_sigreturn32(struct pt_regs *regs)
sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
- if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
- (((unsigned long) sf) & 3))
+ if (invalid_frame_pointer(sf, sizeof(*sf)))
+ goto segv;
+
+ if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
+ goto segv;
+
+ if (ufp & 0x7)
goto segv;
- if (get_user(pc, &sf->info.si_regs.pc) ||
+ if (__get_user(pc, &sf->info.si_regs.pc) ||
__get_user(npc, &sf->info.si_regs.npc))
goto segv;
@@ -227,7 +244,7 @@ segv:
asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
{
struct rt_signal_frame32 __user *sf;
- unsigned int psr, pc, npc;
+ unsigned int psr, pc, npc, ufp;
compat_uptr_t fpu_save;
compat_uptr_t rwin_save;
sigset_t set;
@@ -242,11 +259,16 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
- if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
- (((unsigned long) sf) & 3))
+ if (invalid_frame_pointer(sf, sizeof(*sf)))
goto segv;
- if (get_user(pc, &sf->regs.pc) ||
+ if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+ goto segv;
+
+ if (ufp & 0x7)
+ goto segv;
+
+ if (__get_user(pc, &sf->regs.pc) ||
__get_user(npc, &sf->regs.npc))
goto segv;
@@ -307,14 +329,6 @@ segv:
force_sig(SIGSEGV, current);
}
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp, int fplen)
-{
- if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen)
- return 1;
- return 0;
-}
-
static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
{
unsigned long sp;
diff --git a/kernel/arch/sparc/kernel/signal_32.c b/kernel/arch/sparc/kernel/signal_32.c
index 52aa5e4ce..9c0c8fd0b 100644
--- a/kernel/arch/sparc/kernel/signal_32.c
+++ b/kernel/arch/sparc/kernel/signal_32.c
@@ -60,10 +60,22 @@ struct rt_signal_frame {
#define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7)))
#define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame) + 7) & (~7)))
+/* Checks if the fp is valid. We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static inline bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+ if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen))
+ return true;
+
+ return false;
+}
+
asmlinkage void do_sigreturn(struct pt_regs *regs)
{
+ unsigned long up_psr, pc, npc, ufp;
struct signal_frame __user *sf;
- unsigned long up_psr, pc, npc;
sigset_t set;
__siginfo_fpu_t __user *fpu_save;
__siginfo_rwin_t __user *rwin_save;
@@ -77,10 +89,13 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
- if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
+ if (invalid_frame_pointer(sf, sizeof(*sf)))
+ goto segv_and_exit;
+
+ if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
goto segv_and_exit;
- if (((unsigned long) sf) & 3)
+ if (ufp & 0x7)
goto segv_and_exit;
err = __get_user(pc, &sf->info.si_regs.pc);
@@ -127,7 +142,7 @@ segv_and_exit:
asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
{
struct rt_signal_frame __user *sf;
- unsigned int psr, pc, npc;
+ unsigned int psr, pc, npc, ufp;
__siginfo_fpu_t __user *fpu_save;
__siginfo_rwin_t __user *rwin_save;
sigset_t set;
@@ -135,8 +150,13 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
synchronize_user_stack();
sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
- if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
- (((unsigned long) sf) & 0x03))
+ if (invalid_frame_pointer(sf, sizeof(*sf)))
+ goto segv;
+
+ if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+ goto segv;
+
+ if (ufp & 0x7)
goto segv;
err = __get_user(pc, &sf->regs.pc);
@@ -178,15 +198,6 @@ segv:
force_sig(SIGSEGV, current);
}
-/* Checks if the fp is valid */
-static inline int invalid_frame_pointer(void __user *fp, int fplen)
-{
- if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen))
- return 1;
-
- return 0;
-}
-
static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
{
unsigned long sp = regs->u_regs[UREG_FP];
diff --git a/kernel/arch/sparc/kernel/signal_64.c b/kernel/arch/sparc/kernel/signal_64.c
index d88beff47..5ee930c48 100644
--- a/kernel/arch/sparc/kernel/signal_64.c
+++ b/kernel/arch/sparc/kernel/signal_64.c
@@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs)
unsigned char fenab;
int err;
- flush_user_windows();
+ synchronize_user_stack();
if (get_thread_wsaved() ||
(((unsigned long)ucp) & (sizeof(unsigned long)-1)) ||
(!__access_ok(ucp, sizeof(*ucp))))
@@ -234,6 +234,17 @@ do_sigsegv:
goto out;
}
+/* Checks if the fp is valid. We always build rt signal frames which
+ * are 16-byte aligned, therefore we can always enforce that the
+ * restore frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp)
+{
+ if (((unsigned long) fp) & 15)
+ return true;
+ return false;
+}
+
struct rt_signal_frame {
struct sparc_stackf ss;
siginfo_t info;
@@ -246,8 +257,8 @@ struct rt_signal_frame {
void do_rt_sigreturn(struct pt_regs *regs)
{
+ unsigned long tpc, tnpc, tstate, ufp;
struct rt_signal_frame __user *sf;
- unsigned long tpc, tnpc, tstate;
__siginfo_fpu_t __user *fpu_save;
__siginfo_rwin_t __user *rwin_save;
sigset_t set;
@@ -261,10 +272,16 @@ void do_rt_sigreturn(struct pt_regs *regs)
(regs->u_regs [UREG_FP] + STACK_BIAS);
/* 1. Make sure we are not getting garbage from the user */
- if (((unsigned long) sf) & 3)
+ if (invalid_frame_pointer(sf))
+ goto segv;
+
+ if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
goto segv;
- err = get_user(tpc, &sf->regs.tpc);
+ if ((ufp + STACK_BIAS) & 0x7)
+ goto segv;
+
+ err = __get_user(tpc, &sf->regs.tpc);
err |= __get_user(tnpc, &sf->regs.tnpc);
if (test_thread_flag(TIF_32BIT)) {
tpc &= 0xffffffff;
@@ -308,14 +325,6 @@ segv:
force_sig(SIGSEGV, current);
}
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp)
-{
- if (((unsigned long) fp) & 15)
- return 1;
- return 0;
-}
-
static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
{
unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS;
diff --git a/kernel/arch/sparc/kernel/sigutil_32.c b/kernel/arch/sparc/kernel/sigutil_32.c
index 0f6eebe71..e5fe8cef9 100644
--- a/kernel/arch/sparc/kernel/sigutil_32.c
+++ b/kernel/arch/sparc/kernel/sigutil_32.c
@@ -48,6 +48,10 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
{
int err;
+
+ if (((unsigned long) fpu) & 3)
+ return -EFAULT;
+
#ifdef CONFIG_SMP
if (test_tsk_thread_flag(current, TIF_USEDFPU))
regs->psr &= ~PSR_EF;
@@ -97,7 +101,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
struct thread_info *t = current_thread_info();
int i, wsaved, err;
- __get_user(wsaved, &rp->wsaved);
+ if (((unsigned long) rp) & 3)
+ return -EFAULT;
+
+ get_user(wsaved, &rp->wsaved);
if (wsaved > NSWINS)
return -EFAULT;
diff --git a/kernel/arch/sparc/kernel/sigutil_64.c b/kernel/arch/sparc/kernel/sigutil_64.c
index 387834a9c..36aadcbea 100644
--- a/kernel/arch/sparc/kernel/sigutil_64.c
+++ b/kernel/arch/sparc/kernel/sigutil_64.c
@@ -37,7 +37,10 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
unsigned long fprs;
int err;
- err = __get_user(fprs, &fpu->si_fprs);
+ if (((unsigned long) fpu) & 7)
+ return -EFAULT;
+
+ err = get_user(fprs, &fpu->si_fprs);
fprs_write(0);
regs->tstate &= ~TSTATE_PEF;
if (fprs & FPRS_DL)
@@ -72,7 +75,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
struct thread_info *t = current_thread_info();
int i, wsaved, err;
- __get_user(wsaved, &rp->wsaved);
+ if (((unsigned long) rp) & 7)
+ return -EFAULT;
+
+ get_user(wsaved, &rp->wsaved);
if (wsaved > NSWINS)
return -EFAULT;
diff --git a/kernel/arch/sparc/kernel/sparc_ksyms_64.c b/kernel/arch/sparc/kernel/sparc_ksyms_64.c
index a92d5d2c4..51b25325a 100644
--- a/kernel/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/kernel/arch/sparc/kernel/sparc_ksyms_64.c
@@ -27,7 +27,6 @@ EXPORT_SYMBOL(__flushw_user);
EXPORT_SYMBOL_GPL(real_hard_smp_processor_id);
/* from head_64.S */
-EXPORT_SYMBOL(__ret_efault);
EXPORT_SYMBOL(tlb_type);
EXPORT_SYMBOL(sun4v_chip_type);
EXPORT_SYMBOL(prom_root_node);
diff --git a/kernel/arch/sparc/kernel/spiterrs.S b/kernel/arch/sparc/kernel/spiterrs.S
index c357e40ff..4a73009f6 100644
--- a/kernel/arch/sparc/kernel/spiterrs.S
+++ b/kernel/arch/sparc/kernel/spiterrs.S
@@ -85,8 +85,7 @@ __spitfire_cee_trap_continue:
ba,pt %xcc, etraptl1
rd %pc, %g7
- ba,pt %xcc, 2f
- nop
+ ba,a,pt %xcc, 2f
1: ba,pt %xcc, etrap_irq
rd %pc, %g7
@@ -100,8 +99,7 @@ __spitfire_cee_trap_continue:
mov %l5, %o2
call spitfire_access_error
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size __spitfire_access_error,.-__spitfire_access_error
/* This is the trap handler entry point for ECC correctable
@@ -179,8 +177,7 @@ __spitfire_data_access_exception_tl1:
mov %l5, %o2
call spitfire_data_access_exception_tl1
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size __spitfire_data_access_exception_tl1,.-__spitfire_data_access_exception_tl1
.type __spitfire_data_access_exception,#function
@@ -200,8 +197,7 @@ __spitfire_data_access_exception:
mov %l5, %o2
call spitfire_data_access_exception
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size __spitfire_data_access_exception,.-__spitfire_data_access_exception
.type __spitfire_insn_access_exception_tl1,#function
@@ -220,8 +216,7 @@ __spitfire_insn_access_exception_tl1:
mov %l5, %o2
call spitfire_insn_access_exception_tl1
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size __spitfire_insn_access_exception_tl1,.-__spitfire_insn_access_exception_tl1
.type __spitfire_insn_access_exception,#function
@@ -240,6 +235,5 @@ __spitfire_insn_access_exception:
mov %l5, %o2
call spitfire_insn_access_exception
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
.size __spitfire_insn_access_exception,.-__spitfire_insn_access_exception
diff --git a/kernel/arch/sparc/kernel/syscalls.S b/kernel/arch/sparc/kernel/syscalls.S
index bb0008927..c4a1b5c40 100644
--- a/kernel/arch/sparc/kernel/syscalls.S
+++ b/kernel/arch/sparc/kernel/syscalls.S
@@ -158,7 +158,25 @@ linux_syscall_trace32:
add %sp, PTREGS_OFF, %o0
brnz,pn %o0, 3f
mov -ENOSYS, %o0
+
+ /* Syscall tracing can modify the registers. */
+ ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1
+ sethi %hi(sys_call_table32), %l7
+ ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0
+ or %l7, %lo(sys_call_table32), %l7
+ ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1
+ ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2
+ ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3
+ ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4
+ ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+ cmp %g1, NR_syscalls
+ bgeu,pn %xcc, 3f
+ mov -ENOSYS, %o0
+
+ sll %g1, 2, %l4
srl %i0, 0, %o0
+ lduw [%l7 + %l4], %l7
srl %i4, 0, %o4
srl %i1, 0, %o1
srl %i2, 0, %o2
@@ -170,7 +188,25 @@ linux_syscall_trace:
add %sp, PTREGS_OFF, %o0
brnz,pn %o0, 3f
mov -ENOSYS, %o0
+
+ /* Syscall tracing can modify the registers. */
+ ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1
+ sethi %hi(sys_call_table64), %l7
+ ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0
+ or %l7, %lo(sys_call_table64), %l7
+ ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1
+ ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2
+ ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3
+ ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4
+ ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+ cmp %g1, NR_syscalls
+ bgeu,pn %xcc, 3f
+ mov -ENOSYS, %o0
+
+ sll %g1, 2, %l4
mov %i0, %o0
+ lduw [%l7 + %l4], %l7
mov %i1, %o1
mov %i2, %o2
mov %i3, %o3
diff --git a/kernel/arch/sparc/kernel/tsb.S b/kernel/arch/sparc/kernel/tsb.S
index be98685c1..d568c8207 100644
--- a/kernel/arch/sparc/kernel/tsb.S
+++ b/kernel/arch/sparc/kernel/tsb.S
@@ -29,13 +29,17 @@
*/
tsb_miss_dtlb:
mov TLB_TAG_ACCESS, %g4
+ ldxa [%g4] ASI_DMMU, %g4
+ srlx %g4, PAGE_SHIFT, %g4
ba,pt %xcc, tsb_miss_page_table_walk
- ldxa [%g4] ASI_DMMU, %g4
+ sllx %g4, PAGE_SHIFT, %g4
tsb_miss_itlb:
mov TLB_TAG_ACCESS, %g4
+ ldxa [%g4] ASI_IMMU, %g4
+ srlx %g4, PAGE_SHIFT, %g4
ba,pt %xcc, tsb_miss_page_table_walk
- ldxa [%g4] ASI_IMMU, %g4
+ sllx %g4, PAGE_SHIFT, %g4
/* At this point we have:
* %g1 -- PAGE_SIZE TSB entry address
@@ -284,6 +288,10 @@ tsb_do_dtlb_fault:
nop
.previous
+ /* Clear context ID bits. */
+ srlx %g5, PAGE_SHIFT, %g5
+ sllx %g5, PAGE_SHIFT, %g5
+
be,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_DTLB, %g4
ba,pt %xcc, winfix_trampoline
diff --git a/kernel/arch/sparc/kernel/urtt_fill.S b/kernel/arch/sparc/kernel/urtt_fill.S
new file mode 100644
index 000000000..5604a2b05
--- /dev/null
+++ b/kernel/arch/sparc/kernel/urtt_fill.S
@@ -0,0 +1,98 @@
+#include <asm/thread_info.h>
+#include <asm/trap_block.h>
+#include <asm/spitfire.h>
+#include <asm/ptrace.h>
+#include <asm/head.h>
+
+ .text
+ .align 8
+ .globl user_rtt_fill_fixup_common
+user_rtt_fill_fixup_common:
+ rdpr %cwp, %g1
+ add %g1, 1, %g1
+ wrpr %g1, 0x0, %cwp
+
+ rdpr %wstate, %g2
+ sll %g2, 3, %g2
+ wrpr %g2, 0x0, %wstate
+
+ /* We know %canrestore and %otherwin are both zero. */
+
+ sethi %hi(sparc64_kern_pri_context), %g2
+ ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2
+ mov PRIMARY_CONTEXT, %g1
+
+661: stxa %g2, [%g1] ASI_DMMU
+ .section .sun4v_1insn_patch, "ax"
+ .word 661b
+ stxa %g2, [%g1] ASI_MMU
+ .previous
+
+ sethi %hi(KERNBASE), %g1
+ flush %g1
+
+ mov %g4, %l4
+ mov %g5, %l5
+ brnz,pn %g3, 1f
+ mov %g3, %l3
+
+ or %g4, FAULT_CODE_WINFIXUP, %g4
+ stb %g4, [%g6 + TI_FAULT_CODE]
+ stx %g5, [%g6 + TI_FAULT_ADDR]
+1:
+ mov %g6, %l1
+ wrpr %g0, 0x0, %tl
+
+661: nop
+ .section .sun4v_1insn_patch, "ax"
+ .word 661b
+ SET_GL(0)
+ .previous
+
+ wrpr %g0, RTRAP_PSTATE, %pstate
+
+ mov %l1, %g6
+ ldx [%g6 + TI_TASK], %g4
+ LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
+
+ brnz,pn %l3, 1f
+ nop
+
+ call do_sparc64_fault
+ add %sp, PTREGS_OFF, %o0
+ ba,pt %xcc, rtrap
+ nop
+
+1: cmp %g3, 2
+ bne,pn %xcc, 2f
+ nop
+
+ sethi %hi(tlb_type), %g1
+ lduw [%g1 + %lo(tlb_type)], %g1
+ cmp %g1, 3
+ bne,pt %icc, 1f
+ add %sp, PTREGS_OFF, %o0
+ mov %l4, %o2
+ call sun4v_do_mna
+ mov %l5, %o1
+ ba,a,pt %xcc, rtrap
+1: mov %l4, %o1
+ mov %l5, %o2
+ call mem_address_unaligned
+ nop
+ ba,a,pt %xcc, rtrap
+
+2: sethi %hi(tlb_type), %g1
+ mov %l4, %o1
+ lduw [%g1 + %lo(tlb_type)], %g1
+ mov %l5, %o2
+ cmp %g1, 3
+ bne,pt %icc, 1f
+ add %sp, PTREGS_OFF, %o0
+ call sun4v_data_access_exception
+ nop
+ ba,a,pt %xcc, rtrap
+
+1: call spitfire_data_access_exception
+ nop
+ ba,a,pt %xcc, rtrap
diff --git a/kernel/arch/sparc/kernel/utrap.S b/kernel/arch/sparc/kernel/utrap.S
index b7f0f3f3a..c731e8023 100644
--- a/kernel/arch/sparc/kernel/utrap.S
+++ b/kernel/arch/sparc/kernel/utrap.S
@@ -11,8 +11,7 @@ utrap_trap: /* %g3=handler,%g4=level */
mov %l4, %o1
call bad_trap
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
invoke_utrap:
sllx %g3, 3, %g3
diff --git a/kernel/arch/sparc/kernel/vmlinux.lds.S b/kernel/arch/sparc/kernel/vmlinux.lds.S
index f1a2f688b..4a41d412d 100644
--- a/kernel/arch/sparc/kernel/vmlinux.lds.S
+++ b/kernel/arch/sparc/kernel/vmlinux.lds.S
@@ -33,6 +33,10 @@ ENTRY(_start)
jiffies = jiffies_64;
#endif
+#ifdef CONFIG_SPARC64
+ASSERT((swapper_tsb == 0x0000000000408000), "Error: sparc64 early assembler too large")
+#endif
+
SECTIONS
{
#ifdef CONFIG_SPARC64
diff --git a/kernel/arch/sparc/kernel/winfixup.S b/kernel/arch/sparc/kernel/winfixup.S
index 1e67ce958..855019a85 100644
--- a/kernel/arch/sparc/kernel/winfixup.S
+++ b/kernel/arch/sparc/kernel/winfixup.S
@@ -32,8 +32,7 @@ fill_fixup:
rd %pc, %g7
call do_sparc64_fault
add %sp, PTREGS_OFF, %o0
- ba,pt %xcc, rtrap
- nop
+ ba,a,pt %xcc, rtrap
/* Be very careful about usage of the trap globals here.
* You cannot touch %g5 as that has the fault information.
diff --git a/kernel/arch/sparc/lib/GENcopy_from_user.S b/kernel/arch/sparc/lib/GENcopy_from_user.S
index b7d0bd6b1..69a439fa2 100644
--- a/kernel/arch/sparc/lib/GENcopy_from_user.S
+++ b/kernel/arch/sparc/lib/GENcopy_from_user.S
@@ -3,11 +3,11 @@
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/GENcopy_to_user.S b/kernel/arch/sparc/lib/GENcopy_to_user.S
index 780550e1a..9947427ce 100644
--- a/kernel/arch/sparc/lib/GENcopy_to_user.S
+++ b/kernel/arch/sparc/lib/GENcopy_to_user.S
@@ -3,11 +3,11 @@
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/GENmemcpy.S b/kernel/arch/sparc/lib/GENmemcpy.S
index 89358ee94..059ea24ad 100644
--- a/kernel/arch/sparc/lib/GENmemcpy.S
+++ b/kernel/arch/sparc/lib/GENmemcpy.S
@@ -4,21 +4,18 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#define GLOBAL_SPARE %g7
#else
#define GLOBAL_SPARE %g5
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST(x,y) x
#endif
#ifndef LOAD
@@ -45,6 +42,29 @@
.register %g3,#scratch
.text
+
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+ENTRY(GEN_retl_o4_1)
+ add %o4, %o2, %o4
+ retl
+ add %o4, 1, %o0
+ENDPROC(GEN_retl_o4_1)
+ENTRY(GEN_retl_g1_8)
+ add %g1, %o2, %g1
+ retl
+ add %g1, 8, %o0
+ENDPROC(GEN_retl_g1_8)
+ENTRY(GEN_retl_o2_4)
+ retl
+ add %o2, 4, %o0
+ENDPROC(GEN_retl_o2_4)
+ENTRY(GEN_retl_o2_1)
+ retl
+ add %o2, 1, %o0
+ENDPROC(GEN_retl_o2_1)
+#endif
+
.align 64
.globl FUNC_NAME
@@ -73,8 +93,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
sub %g0, %o4, %o4
sub %o2, %o4, %o2
1: subcc %o4, 1, %o4
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o0))
+ EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o4_1)
+ EX_ST(STORE(stb, %g1, %o0),GEN_retl_o4_1)
add %o1, 1, %o1
bne,pt %XCC, 1b
add %o0, 1, %o0
@@ -82,8 +102,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
andn %o2, 0x7, %g1
sub %o2, %g1, %o2
1: subcc %g1, 0x8, %g1
- EX_LD(LOAD(ldx, %o1, %g2))
- EX_ST(STORE(stx, %g2, %o0))
+ EX_LD(LOAD(ldx, %o1, %g2),GEN_retl_g1_8)
+ EX_ST(STORE(stx, %g2, %o0),GEN_retl_g1_8)
add %o1, 0x8, %o1
bne,pt %XCC, 1b
add %o0, 0x8, %o0
@@ -100,8 +120,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
1:
subcc %o2, 4, %o2
- EX_LD(LOAD(lduw, %o1, %g1))
- EX_ST(STORE(stw, %g1, %o1 + %o3))
+ EX_LD(LOAD(lduw, %o1, %g1),GEN_retl_o2_4)
+ EX_ST(STORE(stw, %g1, %o1 + %o3),GEN_retl_o2_4)
bgu,pt %XCC, 1b
add %o1, 4, %o1
@@ -111,8 +131,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
.align 32
90:
subcc %o2, 1, %o2
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o1 + %o3))
+ EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o2_1)
+ EX_ST(STORE(stb, %g1, %o1 + %o3),GEN_retl_o2_1)
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
diff --git a/kernel/arch/sparc/lib/Makefile b/kernel/arch/sparc/lib/Makefile
index 3269b0234..4f2384a42 100644
--- a/kernel/arch/sparc/lib/Makefile
+++ b/kernel/arch/sparc/lib/Makefile
@@ -38,7 +38,7 @@ lib-$(CONFIG_SPARC64) += NG4patch.o NG4copy_page.o NG4clear_page.o NG4memset.o
lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
-lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
+lib-$(CONFIG_SPARC64) += copy_in_user.o memmove.o
lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
obj-$(CONFIG_SPARC64) += iomap.o
diff --git a/kernel/arch/sparc/lib/NG2copy_from_user.S b/kernel/arch/sparc/lib/NG2copy_from_user.S
index d5242b8c4..b79a6998d 100644
--- a/kernel/arch/sparc/lib/NG2copy_from_user.S
+++ b/kernel/arch/sparc/lib/NG2copy_from_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_LD_FP(x) \
+#define EX_LD_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/NG2copy_to_user.S b/kernel/arch/sparc/lib/NG2copy_to_user.S
index 4e962d993..dcec55f25 100644
--- a/kernel/arch/sparc/lib/NG2copy_to_user.S
+++ b/kernel/arch/sparc/lib/NG2copy_to_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_ST_FP(x) \
+#define EX_ST_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/NG2memcpy.S b/kernel/arch/sparc/lib/NG2memcpy.S
index d5f585df2..c629dbd12 100644
--- a/kernel/arch/sparc/lib/NG2memcpy.S
+++ b/kernel/arch/sparc/lib/NG2memcpy.S
@@ -4,6 +4,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/visasm.h>
#include <asm/asi.h>
#define GLOBAL_SPARE %g7
@@ -32,21 +33,17 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_LD_FP
-#define EX_LD_FP(x) x
+#define EX_LD_FP(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
+#define EX_ST(x,y) x
#endif
#ifndef EX_ST_FP
-#define EX_ST_FP(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST_FP(x,y) x
#endif
#ifndef LOAD
@@ -140,45 +137,110 @@
fsrc2 %x6, %f12; \
fsrc2 %x7, %f14;
#define FREG_LOAD_1(base, x0) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0))
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1)
#define FREG_LOAD_2(base, x0, x1) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1);
#define FREG_LOAD_3(base, x0, x1, x2) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1);
#define FREG_LOAD_4(base, x0, x1, x2, x3) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
- EX_LD_FP(LOAD(ldd, base + 0x18, %x3));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1);
#define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
- EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
- EX_LD_FP(LOAD(ldd, base + 0x20, %x4));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1);
#define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
- EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
- EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
- EX_LD_FP(LOAD(ldd, base + 0x28, %x5));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1);
#define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
- EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
- EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
- EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \
- EX_LD_FP(LOAD(ldd, base + 0x30, %x6));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x30, %x6), NG2_retl_o2_plus_g1);
.register %g2,#scratch
.register %g3,#scratch
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+__restore_fp:
+ VISExitHalf
+__restore_asi:
+ retl
+ wr %g0, ASI_AIUS, %asi
+ENTRY(NG2_retl_o2)
+ ba,pt %xcc, __restore_asi
+ mov %o2, %o0
+ENDPROC(NG2_retl_o2)
+ENTRY(NG2_retl_o2_plus_1)
+ ba,pt %xcc, __restore_asi
+ add %o2, 1, %o0
+ENDPROC(NG2_retl_o2_plus_1)
+ENTRY(NG2_retl_o2_plus_4)
+ ba,pt %xcc, __restore_asi
+ add %o2, 4, %o0
+ENDPROC(NG2_retl_o2_plus_4)
+ENTRY(NG2_retl_o2_plus_8)
+ ba,pt %xcc, __restore_asi
+ add %o2, 8, %o0
+ENDPROC(NG2_retl_o2_plus_8)
+ENTRY(NG2_retl_o2_plus_o4_plus_1)
+ add %o4, 1, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_1)
+ENTRY(NG2_retl_o2_plus_o4_plus_8)
+ add %o4, 8, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_8)
+ENTRY(NG2_retl_o2_plus_o4_plus_16)
+ add %o4, 16, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_16)
+ENTRY(NG2_retl_o2_plus_g1_fp)
+ ba,pt %xcc, __restore_fp
+ add %o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_fp)
+ENTRY(NG2_retl_o2_plus_g1_plus_64_fp)
+ add %g1, 64, %g1
+ ba,pt %xcc, __restore_fp
+ add %o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_plus_64_fp)
+ENTRY(NG2_retl_o2_plus_g1_plus_1)
+ add %g1, 1, %g1
+ ba,pt %xcc, __restore_asi
+ add %o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_plus_1)
+ENTRY(NG2_retl_o2_and_7_plus_o4)
+ and %o2, 7, %o2
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_and_7_plus_o4)
+ENTRY(NG2_retl_o2_and_7_plus_o4_plus_8)
+ and %o2, 7, %o2
+ add %o4, 8, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_and_7_plus_o4_plus_8)
+#endif
+
.align 64
.globl FUNC_NAME
@@ -230,8 +292,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
sub %g0, %o4, %o4 ! bytes to align dst
sub %o2, %o4, %o2
1: subcc %o4, 1, %o4
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o0))
+ EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_o4_plus_1)
+ EX_ST(STORE(stb, %g1, %o0), NG2_retl_o2_plus_o4_plus_1)
add %o1, 1, %o1
bne,pt %XCC, 1b
add %o0, 1, %o0
@@ -281,11 +343,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
nop
/* fall through for 0 < low bits < 8 */
110: sub %o4, 64, %g2
- EX_LD_FP(LOAD_BLK(%g2, %f0))
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+ EX_LD_FP(LOAD_BLK(%g2, %f0), NG2_retl_o2_plus_g1)
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -296,10 +358,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
120: sub %o4, 56, %g2
FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -310,10 +372,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
130: sub %o4, 48, %g2
FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_6(f20, f22, f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -324,10 +386,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
140: sub %o4, 40, %g2
FREG_LOAD_5(%g2, f0, f2, f4, f6, f8)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_5(f22, f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -338,10 +400,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
150: sub %o4, 32, %g2
FREG_LOAD_4(%g2, f0, f2, f4, f6)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_4(f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -352,10 +414,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
160: sub %o4, 24, %g2
FREG_LOAD_3(%g2, f0, f2, f4)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_3(f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -366,10 +428,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
170: sub %o4, 16, %g2
FREG_LOAD_2(%g2, f0, f2)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_2(f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -380,10 +442,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
180: sub %o4, 8, %g2
FREG_LOAD_1(%g2, f0)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_1(f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -393,10 +455,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
nop
190:
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
subcc %g1, 64, %g1
- EX_LD_FP(LOAD_BLK(%o4, %f0))
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_LD_FP(LOAD_BLK(%o4, %f0), NG2_retl_o2_plus_g1_plus_64)
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1_plus_64)
add %o4, 64, %o4
bne,pt %xcc, 1b
LOAD(prefetch, %o4 + 64, #one_read)
@@ -423,28 +485,28 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
andn %o2, 0xf, %o4
and %o2, 0xf, %o2
1: subcc %o4, 0x10, %o4
- EX_LD(LOAD(ldx, %o1, %o5))
+ EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_o4_plus_16)
add %o1, 0x08, %o1
- EX_LD(LOAD(ldx, %o1, %g1))
+ EX_LD(LOAD(ldx, %o1, %g1), NG2_retl_o2_plus_o4_plus_16)
sub %o1, 0x08, %o1
- EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE))
+ EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_16)
add %o1, 0x8, %o1
- EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE))
+ EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_8)
bgu,pt %XCC, 1b
add %o1, 0x8, %o1
73: andcc %o2, 0x8, %g0
be,pt %XCC, 1f
nop
sub %o2, 0x8, %o2
- EX_LD(LOAD(ldx, %o1, %o5))
- EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_8)
+ EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_8)
add %o1, 0x8, %o1
1: andcc %o2, 0x4, %g0
be,pt %XCC, 1f
nop
sub %o2, 0x4, %o2
- EX_LD(LOAD(lduw, %o1, %o5))
- EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(lduw, %o1, %o5), NG2_retl_o2_plus_4)
+ EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4)
add %o1, 0x4, %o1
1: cmp %o2, 0
be,pt %XCC, 85f
@@ -460,8 +522,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
sub %o2, %g1, %o2
1: subcc %g1, 1, %g1
- EX_LD(LOAD(ldub, %o1, %o5))
- EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(ldub, %o1, %o5), NG2_retl_o2_plus_g1_plus_1)
+ EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_g1_plus_1)
bgu,pt %icc, 1b
add %o1, 1, %o1
@@ -477,16 +539,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
8: mov 64, GLOBAL_SPARE
andn %o1, 0x7, %o1
- EX_LD(LOAD(ldx, %o1, %g2))
+ EX_LD(LOAD(ldx, %o1, %g2), NG2_retl_o2)
sub GLOBAL_SPARE, %g1, GLOBAL_SPARE
andn %o2, 0x7, %o4
sllx %g2, %g1, %g2
1: add %o1, 0x8, %o1
- EX_LD(LOAD(ldx, %o1, %g3))
+ EX_LD(LOAD(ldx, %o1, %g3), NG2_retl_o2_and_7_plus_o4)
subcc %o4, 0x8, %o4
srlx %g3, GLOBAL_SPARE, %o5
or %o5, %g2, %o5
- EX_ST(STORE(stx, %o5, %o0))
+ EX_ST(STORE(stx, %o5, %o0), NG2_retl_o2_and_7_plus_o4_plus_8)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
@@ -506,8 +568,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
1:
subcc %o2, 4, %o2
- EX_LD(LOAD(lduw, %o1, %g1))
- EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(lduw, %o1, %g1), NG2_retl_o2_plus_4)
+ EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4)
bgu,pt %XCC, 1b
add %o1, 4, %o1
@@ -517,8 +579,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
.align 32
90:
subcc %o2, 1, %o2
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_1)
+ EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_1)
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
diff --git a/kernel/arch/sparc/lib/NG4copy_from_user.S b/kernel/arch/sparc/lib/NG4copy_from_user.S
index 2e8ee7ad0..16a286c1a 100644
--- a/kernel/arch/sparc/lib/NG4copy_from_user.S
+++ b/kernel/arch/sparc/lib/NG4copy_from_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 2012 David S. Miller (davem@davemloft.net)
*/
-#define EX_LD(x) \
+#define EX_LD(x, y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_LD_FP(x) \
+#define EX_LD_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/NG4copy_to_user.S b/kernel/arch/sparc/lib/NG4copy_to_user.S
index be0bf4590..6b0276ffc 100644
--- a/kernel/arch/sparc/lib/NG4copy_to_user.S
+++ b/kernel/arch/sparc/lib/NG4copy_to_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 2012 David S. Miller (davem@davemloft.net)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_ST_FP(x) \
+#define EX_ST_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/NG4memcpy.S b/kernel/arch/sparc/lib/NG4memcpy.S
index 8e13ee1f4..75bb93b14 100644
--- a/kernel/arch/sparc/lib/NG4memcpy.S
+++ b/kernel/arch/sparc/lib/NG4memcpy.S
@@ -4,6 +4,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/visasm.h>
#include <asm/asi.h>
#define GLOBAL_SPARE %g7
@@ -46,22 +47,19 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_LD_FP
-#define EX_LD_FP(x) x
+#define EX_LD_FP(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
+#define EX_ST(x,y) x
#endif
#ifndef EX_ST_FP
-#define EX_ST_FP(x) x
+#define EX_ST_FP(x,y) x
#endif
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
-#endif
#ifndef LOAD
#define LOAD(type,addr,dest) type [addr], dest
@@ -94,6 +92,158 @@
.register %g3,#scratch
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+__restore_asi_fp:
+ VISExitHalf
+__restore_asi:
+ retl
+ wr %g0, ASI_AIUS, %asi
+
+ENTRY(NG4_retl_o2)
+ ba,pt %xcc, __restore_asi
+ mov %o2, %o0
+ENDPROC(NG4_retl_o2)
+ENTRY(NG4_retl_o2_plus_1)
+ ba,pt %xcc, __restore_asi
+ add %o2, 1, %o0
+ENDPROC(NG4_retl_o2_plus_1)
+ENTRY(NG4_retl_o2_plus_4)
+ ba,pt %xcc, __restore_asi
+ add %o2, 4, %o0
+ENDPROC(NG4_retl_o2_plus_4)
+ENTRY(NG4_retl_o2_plus_o5)
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5)
+ENTRY(NG4_retl_o2_plus_o5_plus_4)
+ add %o5, 4, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_4)
+ENTRY(NG4_retl_o2_plus_o5_plus_8)
+ add %o5, 8, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_8)
+ENTRY(NG4_retl_o2_plus_o5_plus_16)
+ add %o5, 16, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_16)
+ENTRY(NG4_retl_o2_plus_o5_plus_24)
+ add %o5, 24, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_24)
+ENTRY(NG4_retl_o2_plus_o5_plus_32)
+ add %o5, 32, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_32)
+ENTRY(NG4_retl_o2_plus_g1)
+ ba,pt %xcc, __restore_asi
+ add %o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1)
+ENTRY(NG4_retl_o2_plus_g1_plus_1)
+ add %g1, 1, %g1
+ ba,pt %xcc, __restore_asi
+ add %o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_1)
+ENTRY(NG4_retl_o2_plus_g1_plus_8)
+ add %g1, 8, %g1
+ ba,pt %xcc, __restore_asi
+ add %o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_8)
+ENTRY(NG4_retl_o2_plus_o4)
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4)
+ENTRY(NG4_retl_o2_plus_o4_plus_8)
+ add %o4, 8, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8)
+ENTRY(NG4_retl_o2_plus_o4_plus_16)
+ add %o4, 16, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16)
+ENTRY(NG4_retl_o2_plus_o4_plus_24)
+ add %o4, 24, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24)
+ENTRY(NG4_retl_o2_plus_o4_plus_32)
+ add %o4, 32, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32)
+ENTRY(NG4_retl_o2_plus_o4_plus_40)
+ add %o4, 40, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40)
+ENTRY(NG4_retl_o2_plus_o4_plus_48)
+ add %o4, 48, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48)
+ENTRY(NG4_retl_o2_plus_o4_plus_56)
+ add %o4, 56, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56)
+ENTRY(NG4_retl_o2_plus_o4_plus_64)
+ add %o4, 64, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64)
+ENTRY(NG4_retl_o2_plus_o4_fp)
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_8_fp)
+ add %o4, 8, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_16_fp)
+ add %o4, 16, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_24_fp)
+ add %o4, 24, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_32_fp)
+ add %o4, 32, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_40_fp)
+ add %o4, 40, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_48_fp)
+ add %o4, 48, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_56_fp)
+ add %o4, 56, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_64_fp)
+ add %o4, 64, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64_fp)
+#endif
.align 64
.globl FUNC_NAME
@@ -124,12 +274,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
brz,pt %g1, 51f
sub %o2, %g1, %o2
-1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+
+1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
add %o1, 1, %o1
subcc %g1, 1, %g1
add %o0, 1, %o0
bne,pt %icc, 1b
- EX_ST(STORE(stb, %g2, %o0 - 0x01))
+ EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
51: LOAD(prefetch, %o1 + 0x040, #n_reads_strong)
LOAD(prefetch, %o1 + 0x080, #n_reads_strong)
@@ -154,43 +305,43 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
brz,pt %g1, .Llarge_aligned
sub %o2, %g1, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2))
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
add %o1, 8, %o1
subcc %g1, 8, %g1
add %o0, 8, %o0
bne,pt %icc, 1b
- EX_ST(STORE(stx, %g2, %o0 - 0x08))
+ EX_ST(STORE(stx, %g2, %o0 - 0x08), NG4_retl_o2_plus_g1_plus_8)
.Llarge_aligned:
/* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */
andn %o2, 0x3f, %o4
sub %o2, %o4, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o4)
add %o1, 0x40, %o1
- EX_LD(LOAD(ldx, %o1 - 0x38, %g2))
+ EX_LD(LOAD(ldx, %o1 - 0x38, %g2), NG4_retl_o2_plus_o4)
subcc %o4, 0x40, %o4
- EX_LD(LOAD(ldx, %o1 - 0x30, %g3))
- EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE))
- EX_LD(LOAD(ldx, %o1 - 0x20, %o5))
- EX_ST(STORE_INIT(%g1, %o0))
+ EX_LD(LOAD(ldx, %o1 - 0x30, %g3), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD(LOAD(ldx, %o1 - 0x20, %o5), NG4_retl_o2_plus_o4_plus_64)
+ EX_ST(STORE_INIT(%g1, %o0), NG4_retl_o2_plus_o4_plus_64)
add %o0, 0x08, %o0
- EX_ST(STORE_INIT(%g2, %o0))
+ EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_56)
add %o0, 0x08, %o0
- EX_LD(LOAD(ldx, %o1 - 0x18, %g2))
- EX_ST(STORE_INIT(%g3, %o0))
+ EX_LD(LOAD(ldx, %o1 - 0x18, %g2), NG4_retl_o2_plus_o4_plus_48)
+ EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_48)
add %o0, 0x08, %o0
- EX_LD(LOAD(ldx, %o1 - 0x10, %g3))
- EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+ EX_LD(LOAD(ldx, %o1 - 0x10, %g3), NG4_retl_o2_plus_o4_plus_40)
+ EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_40)
add %o0, 0x08, %o0
- EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE))
- EX_ST(STORE_INIT(%o5, %o0))
+ EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_32)
+ EX_ST(STORE_INIT(%o5, %o0), NG4_retl_o2_plus_o4_plus_32)
add %o0, 0x08, %o0
- EX_ST(STORE_INIT(%g2, %o0))
+ EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_24)
add %o0, 0x08, %o0
- EX_ST(STORE_INIT(%g3, %o0))
+ EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_16)
add %o0, 0x08, %o0
- EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+ EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_8)
add %o0, 0x08, %o0
bne,pt %icc, 1b
LOAD(prefetch, %o1 + 0x200, #n_reads_strong)
@@ -216,17 +367,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
sub %o2, %o4, %o2
alignaddr %o1, %g0, %g1
add %o1, %o4, %o1
- EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0))
-1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2))
+ EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0), NG4_retl_o2_plus_o4)
+1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2), NG4_retl_o2_plus_o4)
subcc %o4, 0x40, %o4
- EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4))
- EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6))
- EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8))
- EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10))
- EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12))
- EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14))
+ EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14), NG4_retl_o2_plus_o4_plus_64)
faligndata %f0, %f2, %f16
- EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0))
+ EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0), NG4_retl_o2_plus_o4_plus_64)
faligndata %f2, %f4, %f18
add %g1, 0x40, %g1
faligndata %f4, %f6, %f20
@@ -235,14 +386,14 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
faligndata %f10, %f12, %f26
faligndata %f12, %f14, %f28
faligndata %f14, %f0, %f30
- EX_ST_FP(STORE(std, %f16, %o0 + 0x00))
- EX_ST_FP(STORE(std, %f18, %o0 + 0x08))
- EX_ST_FP(STORE(std, %f20, %o0 + 0x10))
- EX_ST_FP(STORE(std, %f22, %o0 + 0x18))
- EX_ST_FP(STORE(std, %f24, %o0 + 0x20))
- EX_ST_FP(STORE(std, %f26, %o0 + 0x28))
- EX_ST_FP(STORE(std, %f28, %o0 + 0x30))
- EX_ST_FP(STORE(std, %f30, %o0 + 0x38))
+ EX_ST_FP(STORE(std, %f16, %o0 + 0x00), NG4_retl_o2_plus_o4_plus_64)
+ EX_ST_FP(STORE(std, %f18, %o0 + 0x08), NG4_retl_o2_plus_o4_plus_56)
+ EX_ST_FP(STORE(std, %f20, %o0 + 0x10), NG4_retl_o2_plus_o4_plus_48)
+ EX_ST_FP(STORE(std, %f22, %o0 + 0x18), NG4_retl_o2_plus_o4_plus_40)
+ EX_ST_FP(STORE(std, %f24, %o0 + 0x20), NG4_retl_o2_plus_o4_plus_32)
+ EX_ST_FP(STORE(std, %f26, %o0 + 0x28), NG4_retl_o2_plus_o4_plus_24)
+ EX_ST_FP(STORE(std, %f28, %o0 + 0x30), NG4_retl_o2_plus_o4_plus_16)
+ EX_ST_FP(STORE(std, %f30, %o0 + 0x38), NG4_retl_o2_plus_o4_plus_8)
add %o0, 0x40, %o0
bne,pt %icc, 1b
LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
@@ -270,37 +421,38 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
andncc %o2, 0x20 - 1, %o5
be,pn %icc, 2f
sub %o2, %o5, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
- EX_LD(LOAD(ldx, %o1 + 0x08, %g2))
- EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE))
- EX_LD(LOAD(ldx, %o1 + 0x18, %o4))
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
+ EX_LD(LOAD(ldx, %o1 + 0x08, %g2), NG4_retl_o2_plus_o5)
+ EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE), NG4_retl_o2_plus_o5)
+ EX_LD(LOAD(ldx, %o1 + 0x18, %o4), NG4_retl_o2_plus_o5)
add %o1, 0x20, %o1
subcc %o5, 0x20, %o5
- EX_ST(STORE(stx, %g1, %o0 + 0x00))
- EX_ST(STORE(stx, %g2, %o0 + 0x08))
- EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10))
- EX_ST(STORE(stx, %o4, %o0 + 0x18))
+ EX_ST(STORE(stx, %g1, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_32)
+ EX_ST(STORE(stx, %g2, %o0 + 0x08), NG4_retl_o2_plus_o5_plus_24)
+ EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), NG4_retl_o2_plus_o5_plus_24)
+ EX_ST(STORE(stx, %o4, %o0 + 0x18), NG4_retl_o2_plus_o5_plus_8)
bne,pt %icc, 1b
add %o0, 0x20, %o0
2: andcc %o2, 0x18, %o5
be,pt %icc, 3f
sub %o2, %o5, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
add %o1, 0x08, %o1
add %o0, 0x08, %o0
subcc %o5, 0x08, %o5
bne,pt %icc, 1b
- EX_ST(STORE(stx, %g1, %o0 - 0x08))
+ EX_ST(STORE(stx, %g1, %o0 - 0x08), NG4_retl_o2_plus_o5_plus_8)
3: brz,pt %o2, .Lexit
cmp %o2, 0x04
bl,pn %icc, .Ltiny
nop
- EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+ EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2)
add %o1, 0x04, %o1
add %o0, 0x04, %o0
subcc %o2, 0x04, %o2
bne,pn %icc, .Ltiny
- EX_ST(STORE(stw, %g1, %o0 - 0x04))
+ EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_4)
ba,a,pt %icc, .Lexit
.Lmedium_unaligned:
/* First get dest 8 byte aligned. */
@@ -309,12 +461,12 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
brz,pt %g1, 2f
sub %o2, %g1, %o2
-1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
add %o1, 1, %o1
subcc %g1, 1, %g1
add %o0, 1, %o0
bne,pt %icc, 1b
- EX_ST(STORE(stb, %g2, %o0 - 0x01))
+ EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
2:
and %o1, 0x7, %g1
brz,pn %g1, .Lmedium_noprefetch
@@ -322,16 +474,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
mov 64, %g2
sub %g2, %g1, %g2
andn %o1, 0x7, %o1
- EX_LD(LOAD(ldx, %o1 + 0x00, %o4))
+ EX_LD(LOAD(ldx, %o1 + 0x00, %o4), NG4_retl_o2)
sllx %o4, %g1, %o4
andn %o2, 0x08 - 1, %o5
sub %o2, %o5, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3))
+1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3), NG4_retl_o2_plus_o5)
add %o1, 0x08, %o1
subcc %o5, 0x08, %o5
srlx %g3, %g2, GLOBAL_SPARE
or GLOBAL_SPARE, %o4, GLOBAL_SPARE
- EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00))
+ EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_8)
add %o0, 0x08, %o0
bne,pt %icc, 1b
sllx %g3, %g1, %o4
@@ -342,17 +494,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
ba,pt %icc, .Lsmall_unaligned
.Ltiny:
- EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+ EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
subcc %o2, 1, %o2
be,pn %icc, .Lexit
- EX_ST(STORE(stb, %g1, %o0 + 0x00))
- EX_LD(LOAD(ldub, %o1 + 0x01, %g1))
+ EX_ST(STORE(stb, %g1, %o0 + 0x00), NG4_retl_o2_plus_1)
+ EX_LD(LOAD(ldub, %o1 + 0x01, %g1), NG4_retl_o2)
subcc %o2, 1, %o2
be,pn %icc, .Lexit
- EX_ST(STORE(stb, %g1, %o0 + 0x01))
- EX_LD(LOAD(ldub, %o1 + 0x02, %g1))
+ EX_ST(STORE(stb, %g1, %o0 + 0x01), NG4_retl_o2_plus_1)
+ EX_LD(LOAD(ldub, %o1 + 0x02, %g1), NG4_retl_o2)
ba,pt %icc, .Lexit
- EX_ST(STORE(stb, %g1, %o0 + 0x02))
+ EX_ST(STORE(stb, %g1, %o0 + 0x02), NG4_retl_o2)
.Lsmall:
andcc %g2, 0x3, %g0
@@ -360,22 +512,22 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
andn %o2, 0x4 - 1, %o5
sub %o2, %o5, %o2
1:
- EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+ EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
add %o1, 0x04, %o1
subcc %o5, 0x04, %o5
add %o0, 0x04, %o0
bne,pt %icc, 1b
- EX_ST(STORE(stw, %g1, %o0 - 0x04))
+ EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_o5_plus_4)
brz,pt %o2, .Lexit
nop
ba,a,pt %icc, .Ltiny
.Lsmall_unaligned:
-1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
add %o1, 1, %o1
add %o0, 1, %o0
subcc %o2, 1, %o2
bne,pt %icc, 1b
- EX_ST(STORE(stb, %g1, %o0 - 0x01))
+ EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
ba,a,pt %icc, .Lexit
.size FUNC_NAME, .-FUNC_NAME
diff --git a/kernel/arch/sparc/lib/NGcopy_from_user.S b/kernel/arch/sparc/lib/NGcopy_from_user.S
index 5d1e4d1ac..9cd42fcbc 100644
--- a/kernel/arch/sparc/lib/NGcopy_from_user.S
+++ b/kernel/arch/sparc/lib/NGcopy_from_user.S
@@ -3,11 +3,11 @@
* Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __ret_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/NGcopy_to_user.S b/kernel/arch/sparc/lib/NGcopy_to_user.S
index ff630dcb2..5c358afd4 100644
--- a/kernel/arch/sparc/lib/NGcopy_to_user.S
+++ b/kernel/arch/sparc/lib/NGcopy_to_user.S
@@ -3,11 +3,11 @@
* Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __ret_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/NGmemcpy.S b/kernel/arch/sparc/lib/NGmemcpy.S
index 96a14caf6..d88c4ed50 100644
--- a/kernel/arch/sparc/lib/NGmemcpy.S
+++ b/kernel/arch/sparc/lib/NGmemcpy.S
@@ -4,6 +4,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/asi.h>
#include <asm/thread_info.h>
#define GLOBAL_SPARE %g7
@@ -27,15 +28,11 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST(x,y) x
#endif
#ifndef LOAD
@@ -79,6 +76,92 @@
.register %g3,#scratch
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+__restore_asi:
+ ret
+ wr %g0, ASI_AIUS, %asi
+ restore
+ENTRY(NG_ret_i2_plus_i4_plus_1)
+ ba,pt %xcc, __restore_asi
+ add %i2, %i5, %i0
+ENDPROC(NG_ret_i2_plus_i4_plus_1)
+ENTRY(NG_ret_i2_plus_g1)
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1)
+ENTRY(NG_ret_i2_plus_g1_minus_8)
+ sub %g1, 8, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_8)
+ENTRY(NG_ret_i2_plus_g1_minus_16)
+ sub %g1, 16, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_16)
+ENTRY(NG_ret_i2_plus_g1_minus_24)
+ sub %g1, 24, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_24)
+ENTRY(NG_ret_i2_plus_g1_minus_32)
+ sub %g1, 32, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_32)
+ENTRY(NG_ret_i2_plus_g1_minus_40)
+ sub %g1, 40, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_40)
+ENTRY(NG_ret_i2_plus_g1_minus_48)
+ sub %g1, 48, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_48)
+ENTRY(NG_ret_i2_plus_g1_minus_56)
+ sub %g1, 56, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_56)
+ENTRY(NG_ret_i2_plus_i4)
+ ba,pt %xcc, __restore_asi
+ add %i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4)
+ENTRY(NG_ret_i2_plus_i4_minus_8)
+ sub %i4, 8, %i4
+ ba,pt %xcc, __restore_asi
+ add %i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4_minus_8)
+ENTRY(NG_ret_i2_plus_8)
+ ba,pt %xcc, __restore_asi
+ add %i2, 8, %i0
+ENDPROC(NG_ret_i2_plus_8)
+ENTRY(NG_ret_i2_plus_4)
+ ba,pt %xcc, __restore_asi
+ add %i2, 4, %i0
+ENDPROC(NG_ret_i2_plus_4)
+ENTRY(NG_ret_i2_plus_1)
+ ba,pt %xcc, __restore_asi
+ add %i2, 1, %i0
+ENDPROC(NG_ret_i2_plus_1)
+ENTRY(NG_ret_i2_plus_g1_plus_1)
+ add %g1, 1, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_plus_1)
+ENTRY(NG_ret_i2)
+ ba,pt %xcc, __restore_asi
+ mov %i2, %i0
+ENDPROC(NG_ret_i2)
+ENTRY(NG_ret_i2_and_7_plus_i4)
+ and %i2, 7, %i2
+ ba,pt %xcc, __restore_asi
+ add %i2, %i4, %i0
+ENDPROC(NG_ret_i2_and_7_plus_i4)
+#endif
+
.align 64
.globl FUNC_NAME
@@ -126,8 +209,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
sub %g0, %i4, %i4 ! bytes to align dst
sub %i2, %i4, %i2
1: subcc %i4, 1, %i4
- EX_LD(LOAD(ldub, %i1, %g1))
- EX_ST(STORE(stb, %g1, %o0))
+ EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_i4_plus_1)
+ EX_ST(STORE(stb, %g1, %o0), NG_ret_i2_plus_i4_plus_1)
add %i1, 1, %i1
bne,pt %XCC, 1b
add %o0, 1, %o0
@@ -160,7 +243,7 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
and %i4, 0x7, GLOBAL_SPARE
sll GLOBAL_SPARE, 3, GLOBAL_SPARE
mov 64, %i5
- EX_LD(LOAD_TWIN(%i1, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1, %g2, %g3), NG_ret_i2_plus_g1)
sub %i5, GLOBAL_SPARE, %i5
mov 16, %o4
mov 32, %o5
@@ -178,31 +261,31 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
srlx WORD3, PRE_SHIFT, TMP; \
or WORD2, TMP, WORD2;
-8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
LOAD(prefetch, %i1 + %i3, #one_read)
- EX_ST(STORE_INIT(%g2, %o0 + 0x00))
- EX_ST(STORE_INIT(%g3, %o0 + 0x08))
+ EX_ST(STORE_INIT(%g2, %o0 + 0x00), NG_ret_i2_plus_g1)
+ EX_ST(STORE_INIT(%g3, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
- EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%o2, %o0 + 0x10))
- EX_ST(STORE_INIT(%o3, %o0 + 0x18))
+ EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
- EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+ EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%g2, %o0 + 0x20))
- EX_ST(STORE_INIT(%g3, %o0 + 0x28))
+ EX_ST(STORE_INIT(%g2, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%g3, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
- EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%o2, %o0 + 0x30))
- EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+ EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 8b
@@ -211,31 +294,31 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
ba,pt %XCC, 60f
add %i1, %i4, %i1
-9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
LOAD(prefetch, %i1 + %i3, #one_read)
- EX_ST(STORE_INIT(%g3, %o0 + 0x00))
- EX_ST(STORE_INIT(%o2, %o0 + 0x08))
+ EX_ST(STORE_INIT(%g3, %o0 + 0x00), NG_ret_i2_plus_g1)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
- EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%o3, %o0 + 0x10))
- EX_ST(STORE_INIT(%g2, %o0 + 0x18))
+ EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%g2, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
- EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+ EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%g3, %o0 + 0x20))
- EX_ST(STORE_INIT(%o2, %o0 + 0x28))
+ EX_ST(STORE_INIT(%g3, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
- EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%o3, %o0 + 0x30))
- EX_ST(STORE_INIT(%g2, %o0 + 0x38))
+ EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+ EX_ST(STORE_INIT(%g2, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 9b
@@ -249,25 +332,25 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
* one twin load ahead, then add 8 back into source when
* we finish the loop.
*/
- EX_LD(LOAD_TWIN(%i1, %o4, %o5))
+ EX_LD(LOAD_TWIN(%i1, %o4, %o5), NG_ret_i2_plus_g1)
mov 16, %o7
mov 32, %g2
mov 48, %g3
mov 64, %o1
-1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
LOAD(prefetch, %i1 + %o1, #one_read)
- EX_ST(STORE_INIT(%o5, %o0 + 0x00)) ! initializes cache line
- EX_ST(STORE_INIT(%o2, %o0 + 0x08))
- EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
- EX_ST(STORE_INIT(%o3, %o0 + 0x10))
- EX_ST(STORE_INIT(%o4, %o0 + 0x18))
- EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
- EX_ST(STORE_INIT(%o5, %o0 + 0x20))
- EX_ST(STORE_INIT(%o2, %o0 + 0x28))
- EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5))
+ EX_ST(STORE_INIT(%o5, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line
+ EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+ EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o4, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+ EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%o5, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+ EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
- EX_ST(STORE_INIT(%o3, %o0 + 0x30))
- EX_ST(STORE_INIT(%o4, %o0 + 0x38))
+ EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+ EX_ST(STORE_INIT(%o4, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 1b
add %o0, 64, %o0
@@ -282,20 +365,20 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
mov 32, %g2
mov 48, %g3
mov 64, %o1
-1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5))
- EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5), NG_ret_i2_plus_g1)
+ EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
LOAD(prefetch, %i1 + %o1, #one_read)
- EX_ST(STORE_INIT(%o4, %o0 + 0x00)) ! initializes cache line
- EX_ST(STORE_INIT(%o5, %o0 + 0x08))
- EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
- EX_ST(STORE_INIT(%o2, %o0 + 0x10))
- EX_ST(STORE_INIT(%o3, %o0 + 0x18))
- EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
+ EX_ST(STORE_INIT(%o4, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line
+ EX_ST(STORE_INIT(%o5, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+ EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+ EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
add %i1, 64, %i1
- EX_ST(STORE_INIT(%o4, %o0 + 0x20))
- EX_ST(STORE_INIT(%o5, %o0 + 0x28))
- EX_ST(STORE_INIT(%o2, %o0 + 0x30))
- EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+ EX_ST(STORE_INIT(%o4, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%o5, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 1b
add %o0, 64, %o0
@@ -321,28 +404,28 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
andn %i2, 0xf, %i4
and %i2, 0xf, %i2
1: subcc %i4, 0x10, %i4
- EX_LD(LOAD(ldx, %i1, %o4))
+ EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4)
add %i1, 0x08, %i1
- EX_LD(LOAD(ldx, %i1, %g1))
+ EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4)
sub %i1, 0x08, %i1
- EX_ST(STORE(stx, %o4, %i1 + %i3))
+ EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4)
add %i1, 0x8, %i1
- EX_ST(STORE(stx, %g1, %i1 + %i3))
+ EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8)
bgu,pt %XCC, 1b
add %i1, 0x8, %i1
73: andcc %i2, 0x8, %g0
be,pt %XCC, 1f
nop
sub %i2, 0x8, %i2
- EX_LD(LOAD(ldx, %i1, %o4))
- EX_ST(STORE(stx, %o4, %i1 + %i3))
+ EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_8)
+ EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_8)
add %i1, 0x8, %i1
1: andcc %i2, 0x4, %g0
be,pt %XCC, 1f
nop
sub %i2, 0x4, %i2
- EX_LD(LOAD(lduw, %i1, %i5))
- EX_ST(STORE(stw, %i5, %i1 + %i3))
+ EX_LD(LOAD(lduw, %i1, %i5), NG_ret_i2_plus_4)
+ EX_ST(STORE(stw, %i5, %i1 + %i3), NG_ret_i2_plus_4)
add %i1, 0x4, %i1
1: cmp %i2, 0
be,pt %XCC, 85f
@@ -358,8 +441,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
sub %i2, %g1, %i2
1: subcc %g1, 1, %g1
- EX_LD(LOAD(ldub, %i1, %i5))
- EX_ST(STORE(stb, %i5, %i1 + %i3))
+ EX_LD(LOAD(ldub, %i1, %i5), NG_ret_i2_plus_g1_plus_1)
+ EX_ST(STORE(stb, %i5, %i1 + %i3), NG_ret_i2_plus_g1_plus_1)
bgu,pt %icc, 1b
add %i1, 1, %i1
@@ -375,16 +458,16 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
8: mov 64, %i3
andn %i1, 0x7, %i1
- EX_LD(LOAD(ldx, %i1, %g2))
+ EX_LD(LOAD(ldx, %i1, %g2), NG_ret_i2)
sub %i3, %g1, %i3
andn %i2, 0x7, %i4
sllx %g2, %g1, %g2
1: add %i1, 0x8, %i1
- EX_LD(LOAD(ldx, %i1, %g3))
+ EX_LD(LOAD(ldx, %i1, %g3), NG_ret_i2_and_7_plus_i4)
subcc %i4, 0x8, %i4
srlx %g3, %i3, %i5
or %i5, %g2, %i5
- EX_ST(STORE(stx, %i5, %o0))
+ EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
@@ -404,8 +487,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
1:
subcc %i2, 4, %i2
- EX_LD(LOAD(lduw, %i1, %g1))
- EX_ST(STORE(stw, %g1, %i1 + %i3))
+ EX_LD(LOAD(lduw, %i1, %g1), NG_ret_i2_plus_4)
+ EX_ST(STORE(stw, %g1, %i1 + %i3), NG_ret_i2_plus_4)
bgu,pt %XCC, 1b
add %i1, 4, %i1
@@ -415,8 +498,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
.align 32
90:
subcc %i2, 1, %i2
- EX_LD(LOAD(ldub, %i1, %g1))
- EX_ST(STORE(stb, %g1, %i1 + %i3))
+ EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_1)
+ EX_ST(STORE(stb, %g1, %i1 + %i3), NG_ret_i2_plus_1)
bgu,pt %XCC, 90b
add %i1, 1, %i1
ret
diff --git a/kernel/arch/sparc/lib/U1copy_from_user.S b/kernel/arch/sparc/lib/U1copy_from_user.S
index ecc5692fa..bb6ff7322 100644
--- a/kernel/arch/sparc/lib/U1copy_from_user.S
+++ b/kernel/arch/sparc/lib/U1copy_from_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_LD_FP(x) \
+#define EX_LD_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_fp;\
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/U1copy_to_user.S b/kernel/arch/sparc/lib/U1copy_to_user.S
index 9eea392e4..ed92ce739 100644
--- a/kernel/arch/sparc/lib/U1copy_to_user.S
+++ b/kernel/arch/sparc/lib/U1copy_to_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_ST_FP(x) \
+#define EX_ST_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_fp;\
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/U1memcpy.S b/kernel/arch/sparc/lib/U1memcpy.S
index 3e6209ebb..f30d2ab2c 100644
--- a/kernel/arch/sparc/lib/U1memcpy.S
+++ b/kernel/arch/sparc/lib/U1memcpy.S
@@ -5,6 +5,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/visasm.h>
#include <asm/asi.h>
#define GLOBAL_SPARE g7
@@ -23,21 +24,17 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_LD_FP
-#define EX_LD_FP(x) x
+#define EX_LD_FP(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
+#define EX_ST(x,y) x
#endif
#ifndef EX_ST_FP
-#define EX_ST_FP(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST_FP(x,y) x
#endif
#ifndef LOAD
@@ -78,53 +75,169 @@
faligndata %f7, %f8, %f60; \
faligndata %f8, %f9, %f62;
-#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \
- EX_LD_FP(LOAD_BLK(%src, %fdest)); \
- EX_ST_FP(STORE_BLK(%fsrc, %dest)); \
- add %src, 0x40, %src; \
- subcc %len, 0x40, %len; \
- be,pn %xcc, jmptgt; \
- add %dest, 0x40, %dest; \
-
-#define LOOP_CHUNK1(src, dest, len, branch_dest) \
- MAIN_LOOP_CHUNK(src, dest, f0, f48, len, branch_dest)
-#define LOOP_CHUNK2(src, dest, len, branch_dest) \
- MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest)
-#define LOOP_CHUNK3(src, dest, len, branch_dest) \
- MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)
+#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, jmptgt) \
+ EX_LD_FP(LOAD_BLK(%src, %fdest), U1_gs_80_fp); \
+ EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \
+ add %src, 0x40, %src; \
+ subcc %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE; \
+ be,pn %xcc, jmptgt; \
+ add %dest, 0x40, %dest; \
+
+#define LOOP_CHUNK1(src, dest, branch_dest) \
+ MAIN_LOOP_CHUNK(src, dest, f0, f48, branch_dest)
+#define LOOP_CHUNK2(src, dest, branch_dest) \
+ MAIN_LOOP_CHUNK(src, dest, f16, f48, branch_dest)
+#define LOOP_CHUNK3(src, dest, branch_dest) \
+ MAIN_LOOP_CHUNK(src, dest, f32, f48, branch_dest)
#define DO_SYNC membar #Sync;
#define STORE_SYNC(dest, fsrc) \
- EX_ST_FP(STORE_BLK(%fsrc, %dest)); \
+ EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \
add %dest, 0x40, %dest; \
DO_SYNC
#define STORE_JUMP(dest, fsrc, target) \
- EX_ST_FP(STORE_BLK(%fsrc, %dest)); \
+ EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_40_fp); \
add %dest, 0x40, %dest; \
ba,pt %xcc, target; \
nop;
-#define FINISH_VISCHUNK(dest, f0, f1, left) \
- subcc %left, 8, %left;\
- bl,pn %xcc, 95f; \
- faligndata %f0, %f1, %f48; \
- EX_ST_FP(STORE(std, %f48, %dest)); \
+#define FINISH_VISCHUNK(dest, f0, f1) \
+ subcc %g3, 8, %g3; \
+ bl,pn %xcc, 95f; \
+ faligndata %f0, %f1, %f48; \
+ EX_ST_FP(STORE(std, %f48, %dest), U1_g3_8_fp); \
add %dest, 8, %dest;
-#define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \
- subcc %left, 8, %left; \
- bl,pn %xcc, 95f; \
+#define UNEVEN_VISCHUNK_LAST(dest, f0, f1) \
+ subcc %g3, 8, %g3; \
+ bl,pn %xcc, 95f; \
fsrc2 %f0, %f1;
-#define UNEVEN_VISCHUNK(dest, f0, f1, left) \
- UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \
+#define UNEVEN_VISCHUNK(dest, f0, f1) \
+ UNEVEN_VISCHUNK_LAST(dest, f0, f1) \
ba,a,pt %xcc, 93f;
.register %g2,#scratch
.register %g3,#scratch
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+ENTRY(U1_g1_1_fp)
+ VISExitHalf
+ add %g1, 1, %g1
+ add %g1, %g2, %g1
+ retl
+ add %g1, %o2, %o0
+ENDPROC(U1_g1_1_fp)
+ENTRY(U1_g2_0_fp)
+ VISExitHalf
+ retl
+ add %g2, %o2, %o0
+ENDPROC(U1_g2_0_fp)
+ENTRY(U1_g2_8_fp)
+ VISExitHalf
+ add %g2, 8, %g2
+ retl
+ add %g2, %o2, %o0
+ENDPROC(U1_g2_8_fp)
+ENTRY(U1_gs_0_fp)
+ VISExitHalf
+ add %GLOBAL_SPARE, %g3, %o0
+ retl
+ add %o0, %o2, %o0
+ENDPROC(U1_gs_0_fp)
+ENTRY(U1_gs_80_fp)
+ VISExitHalf
+ add %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
+ add %GLOBAL_SPARE, %g3, %o0
+ retl
+ add %o0, %o2, %o0
+ENDPROC(U1_gs_80_fp)
+ENTRY(U1_gs_40_fp)
+ VISExitHalf
+ add %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE
+ add %GLOBAL_SPARE, %g3, %o0
+ retl
+ add %o0, %o2, %o0
+ENDPROC(U1_gs_40_fp)
+ENTRY(U1_g3_0_fp)
+ VISExitHalf
+ retl
+ add %g3, %o2, %o0
+ENDPROC(U1_g3_0_fp)
+ENTRY(U1_g3_8_fp)
+ VISExitHalf
+ add %g3, 8, %g3
+ retl
+ add %g3, %o2, %o0
+ENDPROC(U1_g3_8_fp)
+ENTRY(U1_o2_0_fp)
+ VISExitHalf
+ retl
+ mov %o2, %o0
+ENDPROC(U1_o2_0_fp)
+ENTRY(U1_o2_1_fp)
+ VISExitHalf
+ retl
+ add %o2, 1, %o0
+ENDPROC(U1_o2_1_fp)
+ENTRY(U1_gs_0)
+ VISExitHalf
+ retl
+ add %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0)
+ENTRY(U1_gs_8)
+ VISExitHalf
+ add %GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+ retl
+ add %GLOBAL_SPARE, 0x8, %o0
+ENDPROC(U1_gs_8)
+ENTRY(U1_gs_10)
+ VISExitHalf
+ add %GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+ retl
+ add %GLOBAL_SPARE, 0x10, %o0
+ENDPROC(U1_gs_10)
+ENTRY(U1_o2_0)
+ retl
+ mov %o2, %o0
+ENDPROC(U1_o2_0)
+ENTRY(U1_o2_8)
+ retl
+ add %o2, 8, %o0
+ENDPROC(U1_o2_8)
+ENTRY(U1_o2_4)
+ retl
+ add %o2, 4, %o0
+ENDPROC(U1_o2_4)
+ENTRY(U1_o2_1)
+ retl
+ add %o2, 1, %o0
+ENDPROC(U1_o2_1)
+ENTRY(U1_g1_0)
+ retl
+ add %g1, %o2, %o0
+ENDPROC(U1_g1_0)
+ENTRY(U1_g1_1)
+ add %g1, 1, %g1
+ retl
+ add %g1, %o2, %o0
+ENDPROC(U1_g1_1)
+ENTRY(U1_gs_0_o2_adj)
+ and %o2, 7, %o2
+ retl
+ add %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0_o2_adj)
+ENTRY(U1_gs_8_o2_adj)
+ and %o2, 7, %o2
+ add %GLOBAL_SPARE, 8, %GLOBAL_SPARE
+ retl
+ add %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_8_o2_adj)
+#endif
+
.align 64
.globl FUNC_NAME
@@ -166,8 +279,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
and %g2, 0x38, %g2
1: subcc %g1, 0x1, %g1
- EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
- EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
+ EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U1_g1_1_fp)
+ EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE), U1_g1_1_fp)
bgu,pt %XCC, 1b
add %o1, 0x1, %o1
@@ -178,20 +291,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
be,pt %icc, 3f
alignaddr %o1, %g0, %o1
- EX_LD_FP(LOAD(ldd, %o1, %f4))
-1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+ EX_LD_FP(LOAD(ldd, %o1, %f4), U1_g2_0_fp)
+1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U1_g2_0_fp)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f4, %f6, %f0
- EX_ST_FP(STORE(std, %f0, %o0))
+ EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
be,pn %icc, 3f
add %o0, 0x8, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U1_g2_0_fp)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f6, %f4, %f0
- EX_ST_FP(STORE(std, %f0, %o0))
+ EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
bne,pt %icc, 1b
add %o0, 0x8, %o0
@@ -214,13 +327,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
add %g1, %GLOBAL_SPARE, %g1
subcc %o2, %g3, %o2
- EX_LD_FP(LOAD_BLK(%o1, %f0))
+ EX_LD_FP(LOAD_BLK(%o1, %f0), U1_gs_0_fp)
add %o1, 0x40, %o1
add %g1, %g3, %g1
- EX_LD_FP(LOAD_BLK(%o1, %f16))
+ EX_LD_FP(LOAD_BLK(%o1, %f16), U1_gs_0_fp)
add %o1, 0x40, %o1
sub %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
- EX_LD_FP(LOAD_BLK(%o1, %f32))
+ EX_LD_FP(LOAD_BLK(%o1, %f32), U1_gs_80_fp)
add %o1, 0x40, %o1
/* There are 8 instances of the unrolled loop,
@@ -240,11 +353,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
.align 64
1: FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f0, %f2, %f48
1: FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
@@ -261,11 +374,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
STORE_JUMP(o0, f48, 56f)
1: FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f2, %f4, %f48
1: FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
@@ -282,11 +395,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
STORE_JUMP(o0, f48, 57f)
1: FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f4, %f6, %f48
1: FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
@@ -303,11 +416,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
STORE_JUMP(o0, f48, 58f)
1: FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f6, %f8, %f48
1: FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
@@ -324,11 +437,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
STORE_JUMP(o0, f48, 59f)
1: FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f8, %f10, %f48
1: FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
@@ -345,11 +458,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
STORE_JUMP(o0, f48, 60f)
1: FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f10, %f12, %f48
1: FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
@@ -366,11 +479,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
STORE_JUMP(o0, f48, 61f)
1: FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f12, %f14, %f48
1: FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
@@ -387,11 +500,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
STORE_JUMP(o0, f48, 62f)
1: FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f14, %f16, %f48
1: FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
@@ -407,53 +520,53 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
STORE_JUMP(o0, f48, 63f)
-40: FINISH_VISCHUNK(o0, f0, f2, g3)
-41: FINISH_VISCHUNK(o0, f2, f4, g3)
-42: FINISH_VISCHUNK(o0, f4, f6, g3)
-43: FINISH_VISCHUNK(o0, f6, f8, g3)
-44: FINISH_VISCHUNK(o0, f8, f10, g3)
-45: FINISH_VISCHUNK(o0, f10, f12, g3)
-46: FINISH_VISCHUNK(o0, f12, f14, g3)
-47: UNEVEN_VISCHUNK(o0, f14, f0, g3)
-48: FINISH_VISCHUNK(o0, f16, f18, g3)
-49: FINISH_VISCHUNK(o0, f18, f20, g3)
-50: FINISH_VISCHUNK(o0, f20, f22, g3)
-51: FINISH_VISCHUNK(o0, f22, f24, g3)
-52: FINISH_VISCHUNK(o0, f24, f26, g3)
-53: FINISH_VISCHUNK(o0, f26, f28, g3)
-54: FINISH_VISCHUNK(o0, f28, f30, g3)
-55: UNEVEN_VISCHUNK(o0, f30, f0, g3)
-56: FINISH_VISCHUNK(o0, f32, f34, g3)
-57: FINISH_VISCHUNK(o0, f34, f36, g3)
-58: FINISH_VISCHUNK(o0, f36, f38, g3)
-59: FINISH_VISCHUNK(o0, f38, f40, g3)
-60: FINISH_VISCHUNK(o0, f40, f42, g3)
-61: FINISH_VISCHUNK(o0, f42, f44, g3)
-62: FINISH_VISCHUNK(o0, f44, f46, g3)
-63: UNEVEN_VISCHUNK_LAST(o0, f46, f0, g3)
-
-93: EX_LD_FP(LOAD(ldd, %o1, %f2))
+40: FINISH_VISCHUNK(o0, f0, f2)
+41: FINISH_VISCHUNK(o0, f2, f4)
+42: FINISH_VISCHUNK(o0, f4, f6)
+43: FINISH_VISCHUNK(o0, f6, f8)
+44: FINISH_VISCHUNK(o0, f8, f10)
+45: FINISH_VISCHUNK(o0, f10, f12)
+46: FINISH_VISCHUNK(o0, f12, f14)
+47: UNEVEN_VISCHUNK(o0, f14, f0)
+48: FINISH_VISCHUNK(o0, f16, f18)
+49: FINISH_VISCHUNK(o0, f18, f20)
+50: FINISH_VISCHUNK(o0, f20, f22)
+51: FINISH_VISCHUNK(o0, f22, f24)
+52: FINISH_VISCHUNK(o0, f24, f26)
+53: FINISH_VISCHUNK(o0, f26, f28)
+54: FINISH_VISCHUNK(o0, f28, f30)
+55: UNEVEN_VISCHUNK(o0, f30, f0)
+56: FINISH_VISCHUNK(o0, f32, f34)
+57: FINISH_VISCHUNK(o0, f34, f36)
+58: FINISH_VISCHUNK(o0, f36, f38)
+59: FINISH_VISCHUNK(o0, f38, f40)
+60: FINISH_VISCHUNK(o0, f40, f42)
+61: FINISH_VISCHUNK(o0, f42, f44)
+62: FINISH_VISCHUNK(o0, f44, f46)
+63: UNEVEN_VISCHUNK_LAST(o0, f46, f0)
+
+93: EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp)
add %o1, 8, %o1
subcc %g3, 8, %g3
faligndata %f0, %f2, %f8
- EX_ST_FP(STORE(std, %f8, %o0))
+ EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
bl,pn %xcc, 95f
add %o0, 8, %o0
- EX_LD_FP(LOAD(ldd, %o1, %f0))
+ EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp)
add %o1, 8, %o1
subcc %g3, 8, %g3
faligndata %f2, %f0, %f8
- EX_ST_FP(STORE(std, %f8, %o0))
+ EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
bge,pt %xcc, 93b
add %o0, 8, %o0
95: brz,pt %o2, 2f
mov %g1, %o1
-1: EX_LD_FP(LOAD(ldub, %o1, %o3))
+1: EX_LD_FP(LOAD(ldub, %o1, %o3), U1_o2_0_fp)
add %o1, 1, %o1
subcc %o2, 1, %o2
- EX_ST_FP(STORE(stb, %o3, %o0))
+ EX_ST_FP(STORE(stb, %o3, %o0), U1_o2_1_fp)
bne,pt %xcc, 1b
add %o0, 1, %o0
@@ -469,27 +582,27 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
72: andn %o2, 0xf, %GLOBAL_SPARE
and %o2, 0xf, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
- EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U1_gs_0)
+ EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U1_gs_0)
subcc %GLOBAL_SPARE, 0x10, %GLOBAL_SPARE
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U1_gs_10)
add %o1, 0x8, %o1
- EX_ST(STORE(stx, %g1, %o1 + %o3))
+ EX_ST(STORE(stx, %g1, %o1 + %o3), U1_gs_8)
bgu,pt %XCC, 1b
add %o1, 0x8, %o1
73: andcc %o2, 0x8, %g0
be,pt %XCC, 1f
nop
- EX_LD(LOAD(ldx, %o1, %o5))
+ EX_LD(LOAD(ldx, %o1, %o5), U1_o2_0)
sub %o2, 0x8, %o2
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U1_o2_8)
add %o1, 0x8, %o1
1: andcc %o2, 0x4, %g0
be,pt %XCC, 1f
nop
- EX_LD(LOAD(lduw, %o1, %o5))
+ EX_LD(LOAD(lduw, %o1, %o5), U1_o2_0)
sub %o2, 0x4, %o2
- EX_ST(STORE(stw, %o5, %o1 + %o3))
+ EX_ST(STORE(stw, %o5, %o1 + %o3), U1_o2_4)
add %o1, 0x4, %o1
1: cmp %o2, 0
be,pt %XCC, 85f
@@ -503,9 +616,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
sub %g0, %g1, %g1
sub %o2, %g1, %o2
-1: EX_LD(LOAD(ldub, %o1, %o5))
+1: EX_LD(LOAD(ldub, %o1, %o5), U1_g1_0)
subcc %g1, 1, %g1
- EX_ST(STORE(stb, %o5, %o1 + %o3))
+ EX_ST(STORE(stb, %o5, %o1 + %o3), U1_g1_1)
bgu,pt %icc, 1b
add %o1, 1, %o1
@@ -521,16 +634,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
8: mov 64, %o3
andn %o1, 0x7, %o1
- EX_LD(LOAD(ldx, %o1, %g2))
+ EX_LD(LOAD(ldx, %o1, %g2), U1_o2_0)
sub %o3, %g1, %o3
andn %o2, 0x7, %GLOBAL_SPARE
sllx %g2, %g1, %g2
-1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U1_gs_0_o2_adj)
subcc %GLOBAL_SPARE, 0x8, %GLOBAL_SPARE
add %o1, 0x8, %o1
srlx %g3, %o3, %o5
or %o5, %g2, %o5
- EX_ST(STORE(stx, %o5, %o0))
+ EX_ST(STORE(stx, %o5, %o0), U1_gs_8_o2_adj)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
@@ -548,9 +661,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
bne,pn %XCC, 90f
sub %o0, %o1, %o3
-1: EX_LD(LOAD(lduw, %o1, %g1))
+1: EX_LD(LOAD(lduw, %o1, %g1), U1_o2_0)
subcc %o2, 4, %o2
- EX_ST(STORE(stw, %g1, %o1 + %o3))
+ EX_ST(STORE(stw, %g1, %o1 + %o3), U1_o2_4)
bgu,pt %XCC, 1b
add %o1, 4, %o1
@@ -558,9 +671,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
mov EX_RETVAL(%o4), %o0
.align 32
-90: EX_LD(LOAD(ldub, %o1, %g1))
+90: EX_LD(LOAD(ldub, %o1, %g1), U1_o2_0)
subcc %o2, 1, %o2
- EX_ST(STORE(stb, %g1, %o1 + %o3))
+ EX_ST(STORE(stb, %g1, %o1 + %o3), U1_o2_1)
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
diff --git a/kernel/arch/sparc/lib/U3copy_from_user.S b/kernel/arch/sparc/lib/U3copy_from_user.S
index 88ad73d86..db73010a1 100644
--- a/kernel/arch/sparc/lib/U3copy_from_user.S
+++ b/kernel/arch/sparc/lib/U3copy_from_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_LD_FP(x) \
+#define EX_LD_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/U3copy_to_user.S b/kernel/arch/sparc/lib/U3copy_to_user.S
index 845139d75..c4ee858e3 100644
--- a/kernel/arch/sparc/lib/U3copy_to_user.S
+++ b/kernel/arch/sparc/lib/U3copy_to_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_ST_FP(x) \
+#define EX_ST_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/kernel/arch/sparc/lib/U3memcpy.S b/kernel/arch/sparc/lib/U3memcpy.S
index 491ee69e4..54f98706b 100644
--- a/kernel/arch/sparc/lib/U3memcpy.S
+++ b/kernel/arch/sparc/lib/U3memcpy.S
@@ -4,6 +4,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/visasm.h>
#include <asm/asi.h>
#define GLOBAL_SPARE %g7
@@ -22,21 +23,17 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_LD_FP
-#define EX_LD_FP(x) x
+#define EX_LD_FP(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
+#define EX_ST(x,y) x
#endif
#ifndef EX_ST_FP
-#define EX_ST_FP(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST_FP(x,y) x
#endif
#ifndef LOAD
@@ -77,6 +74,87 @@
*/
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+__restore_fp:
+ VISExitHalf
+ retl
+ nop
+ENTRY(U3_retl_o2_plus_g2_plus_g1_plus_1_fp)
+ add %g1, 1, %g1
+ add %g2, %g1, %g2
+ ba,pt %xcc, __restore_fp
+ add %o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_plus_g1_plus_1_fp)
+ENTRY(U3_retl_o2_plus_g2_fp)
+ ba,pt %xcc, __restore_fp
+ add %o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_fp)
+ENTRY(U3_retl_o2_plus_g2_plus_8_fp)
+ add %g2, 8, %g2
+ ba,pt %xcc, __restore_fp
+ add %o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_plus_8_fp)
+ENTRY(U3_retl_o2)
+ retl
+ mov %o2, %o0
+ENDPROC(U3_retl_o2)
+ENTRY(U3_retl_o2_plus_1)
+ retl
+ add %o2, 1, %o0
+ENDPROC(U3_retl_o2_plus_1)
+ENTRY(U3_retl_o2_plus_4)
+ retl
+ add %o2, 4, %o0
+ENDPROC(U3_retl_o2_plus_4)
+ENTRY(U3_retl_o2_plus_8)
+ retl
+ add %o2, 8, %o0
+ENDPROC(U3_retl_o2_plus_8)
+ENTRY(U3_retl_o2_plus_g1_plus_1)
+ add %g1, 1, %g1
+ retl
+ add %o2, %g1, %o0
+ENDPROC(U3_retl_o2_plus_g1_plus_1)
+ENTRY(U3_retl_o2_fp)
+ ba,pt %xcc, __restore_fp
+ mov %o2, %o0
+ENDPROC(U3_retl_o2_fp)
+ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp)
+ sll %o3, 6, %o3
+ add %o3, 0x80, %o3
+ ba,pt %xcc, __restore_fp
+ add %o2, %o3, %o0
+ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp)
+ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp)
+ sll %o3, 6, %o3
+ add %o3, 0x40, %o3
+ ba,pt %xcc, __restore_fp
+ add %o2, %o3, %o0
+ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp)
+ENTRY(U3_retl_o2_plus_GS_plus_0x10)
+ add GLOBAL_SPARE, 0x10, GLOBAL_SPARE
+ retl
+ add %o2, GLOBAL_SPARE, %o0
+ENDPROC(U3_retl_o2_plus_GS_plus_0x10)
+ENTRY(U3_retl_o2_plus_GS_plus_0x08)
+ add GLOBAL_SPARE, 0x08, GLOBAL_SPARE
+ retl
+ add %o2, GLOBAL_SPARE, %o0
+ENDPROC(U3_retl_o2_plus_GS_plus_0x08)
+ENTRY(U3_retl_o2_and_7_plus_GS)
+ and %o2, 7, %o2
+ retl
+ add %o2, GLOBAL_SPARE, %o2
+ENDPROC(U3_retl_o2_and_7_plus_GS)
+ENTRY(U3_retl_o2_and_7_plus_GS_plus_8)
+ add GLOBAL_SPARE, 8, GLOBAL_SPARE
+ and %o2, 7, %o2
+ retl
+ add %o2, GLOBAL_SPARE, %o2
+ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8)
+#endif
+
.align 64
/* The cheetah's flexible spine, oversized liver, enlarged heart,
@@ -126,8 +204,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
and %g2, 0x38, %g2
1: subcc %g1, 0x1, %g1
- EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
- EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE))
+ EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U3_retl_o2_plus_g2_plus_g1_plus_1)
+ EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE), U3_retl_o2_plus_g2_plus_g1_plus_1)
bgu,pt %XCC, 1b
add %o1, 0x1, %o1
@@ -138,20 +216,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
be,pt %icc, 3f
alignaddr %o1, %g0, %o1
- EX_LD_FP(LOAD(ldd, %o1, %f4))
-1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+ EX_LD_FP(LOAD(ldd, %o1, %f4), U3_retl_o2_plus_g2)
+1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U3_retl_o2_plus_g2)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f4, %f6, %f0
- EX_ST_FP(STORE(std, %f0, %o0))
+ EX_ST_FP(STORE(std, %f0, %o0), U3_retl_o2_plus_g2_plus_8)
be,pn %icc, 3f
add %o0, 0x8, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U3_retl_o2_plus_g2)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f6, %f4, %f2
- EX_ST_FP(STORE(std, %f2, %o0))
+ EX_ST_FP(STORE(std, %f2, %o0), U3_retl_o2_plus_g2_plus_8)
bne,pt %icc, 1b
add %o0, 0x8, %o0
@@ -161,25 +239,25 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
LOAD(prefetch, %o1 + 0x080, #one_read)
LOAD(prefetch, %o1 + 0x0c0, #one_read)
LOAD(prefetch, %o1 + 0x100, #one_read)
- EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0), U3_retl_o2)
LOAD(prefetch, %o1 + 0x140, #one_read)
- EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2)
LOAD(prefetch, %o1 + 0x180, #one_read)
- EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2)
LOAD(prefetch, %o1 + 0x1c0, #one_read)
faligndata %f0, %f2, %f16
- EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2)
faligndata %f2, %f4, %f18
- EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2)
faligndata %f4, %f6, %f20
- EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2)
faligndata %f6, %f8, %f22
- EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2)
faligndata %f8, %f10, %f24
- EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2)
faligndata %f10, %f12, %f26
- EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2)
subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE
add %o1, 0x40, %o1
@@ -190,26 +268,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
.align 64
1:
- EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f12, %f14, %f28
- EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f14, %f0, %f30
- EX_ST_FP(STORE_BLK(%f16, %o0))
- EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+ EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
+ EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f0, %f2, %f16
add %o0, 0x40, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f2, %f4, %f18
- EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f4, %f6, %f20
- EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40)
subcc %o3, 0x01, %o3
faligndata %f6, %f8, %f22
- EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f8, %f10, %f24
- EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
LOAD(prefetch, %o1 + 0x1c0, #one_read)
faligndata %f10, %f12, %f26
bg,pt %XCC, 1b
@@ -217,29 +295,29 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
/* Finally we copy the last full 64-byte block. */
2:
- EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f12, %f14, %f28
- EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f14, %f0, %f30
- EX_ST_FP(STORE_BLK(%f16, %o0))
- EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+ EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
+ EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f0, %f2, %f16
- EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f2, %f4, %f18
- EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f4, %f6, %f20
- EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f6, %f8, %f22
- EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f8, %f10, %f24
cmp %g1, 0
be,pt %XCC, 1f
add %o0, 0x40, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x40)
1: faligndata %f10, %f12, %f26
faligndata %f12, %f14, %f28
faligndata %f14, %f0, %f30
- EX_ST_FP(STORE_BLK(%f16, %o0))
+ EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x40)
add %o0, 0x40, %o0
add %o1, 0x40, %o1
membar #Sync
@@ -259,20 +337,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
sub %o2, %g2, %o2
be,a,pt %XCC, 1f
- EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0), U3_retl_o2_plus_g2)
-1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2))
+1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2), U3_retl_o2_plus_g2)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f0, %f2, %f8
- EX_ST_FP(STORE(std, %f8, %o0))
+ EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8)
be,pn %XCC, 2f
add %o0, 0x8, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0), U3_retl_o2_plus_g2)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f2, %f0, %f8
- EX_ST_FP(STORE(std, %f8, %o0))
+ EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8)
bne,pn %XCC, 1b
add %o0, 0x8, %o0
@@ -292,30 +370,33 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
andcc %o2, 0x8, %g0
be,pt %icc, 1f
nop
- EX_LD(LOAD(ldx, %o1, %o5))
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2)
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2)
add %o1, 0x8, %o1
+ sub %o2, 8, %o2
1: andcc %o2, 0x4, %g0
be,pt %icc, 1f
nop
- EX_LD(LOAD(lduw, %o1, %o5))
- EX_ST(STORE(stw, %o5, %o1 + %o3))
+ EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2)
+ EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2)
add %o1, 0x4, %o1
+ sub %o2, 4, %o2
1: andcc %o2, 0x2, %g0
be,pt %icc, 1f
nop
- EX_LD(LOAD(lduh, %o1, %o5))
- EX_ST(STORE(sth, %o5, %o1 + %o3))
+ EX_LD(LOAD(lduh, %o1, %o5), U3_retl_o2)
+ EX_ST(STORE(sth, %o5, %o1 + %o3), U3_retl_o2)
add %o1, 0x2, %o1
+ sub %o2, 2, %o2
1: andcc %o2, 0x1, %g0
be,pt %icc, 85f
nop
- EX_LD(LOAD(ldub, %o1, %o5))
+ EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2)
ba,pt %xcc, 85f
- EX_ST(STORE(stb, %o5, %o1 + %o3))
+ EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2)
.align 64
70: /* 16 < len <= 64 */
@@ -326,26 +407,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
andn %o2, 0xf, GLOBAL_SPARE
and %o2, 0xf, %o2
1: subcc GLOBAL_SPARE, 0x10, GLOBAL_SPARE
- EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
- EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U3_retl_o2_plus_GS_plus_0x10)
+ EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U3_retl_o2_plus_GS_plus_0x10)
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x10)
add %o1, 0x8, %o1
- EX_ST(STORE(stx, %g1, %o1 + %o3))
+ EX_ST(STORE(stx, %g1, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x08)
bgu,pt %XCC, 1b
add %o1, 0x8, %o1
73: andcc %o2, 0x8, %g0
be,pt %XCC, 1f
nop
sub %o2, 0x8, %o2
- EX_LD(LOAD(ldx, %o1, %o5))
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2_plus_8)
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_8)
add %o1, 0x8, %o1
1: andcc %o2, 0x4, %g0
be,pt %XCC, 1f
nop
sub %o2, 0x4, %o2
- EX_LD(LOAD(lduw, %o1, %o5))
- EX_ST(STORE(stw, %o5, %o1 + %o3))
+ EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2_plus_4)
+ EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2_plus_4)
add %o1, 0x4, %o1
1: cmp %o2, 0
be,pt %XCC, 85f
@@ -361,8 +442,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
sub %o2, %g1, %o2
1: subcc %g1, 1, %g1
- EX_LD(LOAD(ldub, %o1, %o5))
- EX_ST(STORE(stb, %o5, %o1 + %o3))
+ EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2_plus_g1_plus_1)
+ EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2_plus_g1_plus_1)
bgu,pt %icc, 1b
add %o1, 1, %o1
@@ -378,16 +459,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
8: mov 64, %o3
andn %o1, 0x7, %o1
- EX_LD(LOAD(ldx, %o1, %g2))
+ EX_LD(LOAD(ldx, %o1, %g2), U3_retl_o2)
sub %o3, %g1, %o3
andn %o2, 0x7, GLOBAL_SPARE
sllx %g2, %g1, %g2
-1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U3_retl_o2_and_7_plus_GS)
subcc GLOBAL_SPARE, 0x8, GLOBAL_SPARE
add %o1, 0x8, %o1
srlx %g3, %o3, %o5
or %o5, %g2, %o5
- EX_ST(STORE(stx, %o5, %o0))
+ EX_ST(STORE(stx, %o5, %o0), U3_retl_o2_and_7_plus_GS_plus_8)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
@@ -407,8 +488,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
1:
subcc %o2, 4, %o2
- EX_LD(LOAD(lduw, %o1, %g1))
- EX_ST(STORE(stw, %g1, %o1 + %o3))
+ EX_LD(LOAD(lduw, %o1, %g1), U3_retl_o2_plus_4)
+ EX_ST(STORE(stw, %g1, %o1 + %o3), U3_retl_o2_plus_4)
bgu,pt %XCC, 1b
add %o1, 4, %o1
@@ -418,8 +499,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
.align 32
90:
subcc %o2, 1, %o2
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o1 + %o3))
+ EX_LD(LOAD(ldub, %o1, %g1), U3_retl_o2_plus_1)
+ EX_ST(STORE(stb, %g1, %o1 + %o3), U3_retl_o2_plus_1)
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
diff --git a/kernel/arch/sparc/lib/copy_in_user.S b/kernel/arch/sparc/lib/copy_in_user.S
index 302c0e60d..4c89b486f 100644
--- a/kernel/arch/sparc/lib/copy_in_user.S
+++ b/kernel/arch/sparc/lib/copy_in_user.S
@@ -8,18 +8,33 @@
#define XCC xcc
-#define EX(x,y) \
+#define EX(x,y,z) \
98: x,y; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, z; \
.text; \
.align 4;
+#define EX_O4(x,y) EX(x,y,__retl_o4_plus_8)
+#define EX_O2_4(x,y) EX(x,y,__retl_o2_plus_4)
+#define EX_O2_1(x,y) EX(x,y,__retl_o2_plus_1)
+
.register %g2,#scratch
.register %g3,#scratch
.text
+__retl_o4_plus_8:
+ add %o4, %o2, %o4
+ retl
+ add %o4, 8, %o0
+__retl_o2_plus_4:
+ retl
+ add %o2, 4, %o0
+__retl_o2_plus_1:
+ retl
+ add %o2, 1, %o0
+
.align 32
/* Don't try to get too fancy here, just nice and
@@ -44,8 +59,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */
andn %o2, 0x7, %o4
and %o2, 0x7, %o2
1: subcc %o4, 0x8, %o4
- EX(ldxa [%o1] %asi, %o5)
- EX(stxa %o5, [%o0] %asi)
+ EX_O4(ldxa [%o1] %asi, %o5)
+ EX_O4(stxa %o5, [%o0] %asi)
add %o1, 0x8, %o1
bgu,pt %XCC, 1b
add %o0, 0x8, %o0
@@ -53,8 +68,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */
be,pt %XCC, 1f
nop
sub %o2, 0x4, %o2
- EX(lduwa [%o1] %asi, %o5)
- EX(stwa %o5, [%o0] %asi)
+ EX_O2_4(lduwa [%o1] %asi, %o5)
+ EX_O2_4(stwa %o5, [%o0] %asi)
add %o1, 0x4, %o1
add %o0, 0x4, %o0
1: cmp %o2, 0
@@ -70,8 +85,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */
82:
subcc %o2, 4, %o2
- EX(lduwa [%o1] %asi, %g1)
- EX(stwa %g1, [%o0] %asi)
+ EX_O2_4(lduwa [%o1] %asi, %g1)
+ EX_O2_4(stwa %g1, [%o0] %asi)
add %o1, 4, %o1
bgu,pt %XCC, 82b
add %o0, 4, %o0
@@ -82,8 +97,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */
.align 32
90:
subcc %o2, 1, %o2
- EX(lduba [%o1] %asi, %g1)
- EX(stba %g1, [%o0] %asi)
+ EX_O2_1(lduba [%o1] %asi, %g1)
+ EX_O2_1(stba %g1, [%o0] %asi)
add %o1, 1, %o1
bgu,pt %XCC, 90b
add %o0, 1, %o0
diff --git a/kernel/arch/sparc/lib/user_fixup.c b/kernel/arch/sparc/lib/user_fixup.c
deleted file mode 100644
index ac96ae236..000000000
--- a/kernel/arch/sparc/lib/user_fixup.c
+++ /dev/null
@@ -1,71 +0,0 @@
-/* user_fixup.c: Fix up user copy faults.
- *
- * Copyright (C) 2004 David S. Miller <davem@redhat.com>
- */
-
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/module.h>
-
-#include <asm/uaccess.h>
-
-/* Calculating the exact fault address when using
- * block loads and stores can be very complicated.
- *
- * Instead of trying to be clever and handling all
- * of the cases, just fix things up simply here.
- */
-
-static unsigned long compute_size(unsigned long start, unsigned long size, unsigned long *offset)
-{
- unsigned long fault_addr = current_thread_info()->fault_address;
- unsigned long end = start + size;
-
- if (fault_addr < start || fault_addr >= end) {
- *offset = 0;
- } else {
- *offset = fault_addr - start;
- size = end - fault_addr;
- }
- return size;
-}
-
-unsigned long copy_from_user_fixup(void *to, const void __user *from, unsigned long size)
-{
- unsigned long offset;
-
- size = compute_size((unsigned long) from, size, &offset);
- if (likely(size))
- memset(to + offset, 0, size);
-
- return size;
-}
-EXPORT_SYMBOL(copy_from_user_fixup);
-
-unsigned long copy_to_user_fixup(void __user *to, const void *from, unsigned long size)
-{
- unsigned long offset;
-
- return compute_size((unsigned long) to, size, &offset);
-}
-EXPORT_SYMBOL(copy_to_user_fixup);
-
-unsigned long copy_in_user_fixup(void __user *to, void __user *from, unsigned long size)
-{
- unsigned long fault_addr = current_thread_info()->fault_address;
- unsigned long start = (unsigned long) to;
- unsigned long end = start + size;
-
- if (fault_addr >= start && fault_addr < end)
- return end - fault_addr;
-
- start = (unsigned long) from;
- end = start + size;
- if (fault_addr >= start && fault_addr < end)
- return end - fault_addr;
-
- return size;
-}
-EXPORT_SYMBOL(copy_in_user_fixup);
diff --git a/kernel/arch/sparc/mm/fault_64.c b/kernel/arch/sparc/mm/fault_64.c
index dbabe5713..e15f33715 100644
--- a/kernel/arch/sparc/mm/fault_64.c
+++ b/kernel/arch/sparc/mm/fault_64.c
@@ -479,14 +479,14 @@ good_area:
up_read(&mm->mmap_sem);
mm_rss = get_mm_rss(mm);
-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- mm_rss -= (mm->context.huge_pte_count * (HPAGE_SIZE / PAGE_SIZE));
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
+ mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE));
#endif
if (unlikely(mm_rss >
mm->context.tsb_block[MM_TSB_BASE].tsb_rss_limit))
tsb_grow(mm, MM_TSB_BASE, mm_rss);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- mm_rss = mm->context.huge_pte_count;
+ mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count;
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/kernel/arch/sparc/mm/hugetlbpage.c b/kernel/arch/sparc/mm/hugetlbpage.c
index 131eaf4ad..da1142401 100644
--- a/kernel/arch/sparc/mm/hugetlbpage.c
+++ b/kernel/arch/sparc/mm/hugetlbpage.c
@@ -176,17 +176,31 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t entry)
{
int i;
+ pte_t orig[2];
+ unsigned long nptes;
if (!pte_present(*ptep) && pte_present(entry))
- mm->context.huge_pte_count++;
+ mm->context.hugetlb_pte_count++;
addr &= HPAGE_MASK;
- for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
- set_pte_at(mm, addr, ptep, entry);
+
+ nptes = 1 << HUGETLB_PAGE_ORDER;
+ orig[0] = *ptep;
+ orig[1] = *(ptep + nptes / 2);
+ for (i = 0; i < nptes; i++) {
+ *ptep = entry;
ptep++;
addr += PAGE_SIZE;
pte_val(entry) += PAGE_SIZE;
}
+
+ /* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
+ addr -= REAL_HPAGE_SIZE;
+ ptep -= nptes / 2;
+ maybe_tlb_batch_add(mm, addr, ptep, orig[1], 0);
+ addr -= REAL_HPAGE_SIZE;
+ ptep -= nptes / 2;
+ maybe_tlb_batch_add(mm, addr, ptep, orig[0], 0);
}
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
@@ -194,19 +208,28 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
{
pte_t entry;
int i;
+ unsigned long nptes;
entry = *ptep;
if (pte_present(entry))
- mm->context.huge_pte_count--;
+ mm->context.hugetlb_pte_count--;
addr &= HPAGE_MASK;
-
- for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
- pte_clear(mm, addr, ptep);
+ nptes = 1 << HUGETLB_PAGE_ORDER;
+ for (i = 0; i < nptes; i++) {
+ *ptep = __pte(0UL);
addr += PAGE_SIZE;
ptep++;
}
+ /* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
+ addr -= REAL_HPAGE_SIZE;
+ ptep -= nptes / 2;
+ maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+ addr -= REAL_HPAGE_SIZE;
+ ptep -= nptes / 2;
+ maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+
return entry;
}
diff --git a/kernel/arch/sparc/mm/init_64.c b/kernel/arch/sparc/mm/init_64.c
index 3025bd57f..3d3414c14 100644
--- a/kernel/arch/sparc/mm/init_64.c
+++ b/kernel/arch/sparc/mm/init_64.c
@@ -324,18 +324,6 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
tsb_insert(tsb, tag, tte);
}
-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline bool is_hugetlb_pte(pte_t pte)
-{
- if ((tlb_type == hypervisor &&
- (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) ||
- (tlb_type != hypervisor &&
- (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U))
- return true;
- return false;
-}
-#endif
-
void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
{
struct mm_struct *mm;
@@ -358,7 +346,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
spin_lock_irqsave(&mm->context.lock, flags);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (mm->context.huge_pte_count && is_hugetlb_pte(pte))
+ if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) &&
+ is_hugetlb_pte(pte))
__update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT,
address, pte_val(pte));
else
@@ -811,8 +800,10 @@ struct mdesc_mblock {
};
static struct mdesc_mblock *mblocks;
static int num_mblocks;
+static int find_numa_node_for_addr(unsigned long pa,
+ struct node_mem_mask *pnode_mask);
-static unsigned long ra_to_pa(unsigned long addr)
+static unsigned long __init ra_to_pa(unsigned long addr)
{
int i;
@@ -828,8 +819,11 @@ static unsigned long ra_to_pa(unsigned long addr)
return addr;
}
-static int find_node(unsigned long addr)
+static int __init find_node(unsigned long addr)
{
+ static bool search_mdesc = true;
+ static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL };
+ static int last_index;
int i;
addr = ra_to_pa(addr);
@@ -839,13 +833,30 @@ static int find_node(unsigned long addr)
if ((addr & p->mask) == p->val)
return i;
}
- /* The following condition has been observed on LDOM guests.*/
- WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
- " rule. Some physical memory will be owned by node 0.");
- return 0;
+ /* The following condition has been observed on LDOM guests because
+ * node_masks only contains the best latency mask and value.
+ * LDOM guest's mdesc can contain a single latency group to
+ * cover multiple address range. Print warning message only if the
+ * address cannot be found in node_masks nor mdesc.
+ */
+ if ((search_mdesc) &&
+ ((addr & last_mem_mask.mask) != last_mem_mask.val)) {
+ /* find the available node in the mdesc */
+ last_index = find_numa_node_for_addr(addr, &last_mem_mask);
+ numadbg("find_node: latency group for address 0x%lx is %d\n",
+ addr, last_index);
+ if ((last_index < 0) || (last_index >= num_node_masks)) {
+ /* WARN_ONCE() and use default group 0 */
+ WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.");
+ search_mdesc = false;
+ last_index = 0;
+ }
+ }
+
+ return last_index;
}
-static u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 __init memblock_nid_range(u64 start, u64 end, int *nid)
{
*nid = find_node(start);
start += PAGE_SIZE;
@@ -1169,6 +1180,41 @@ int __node_distance(int from, int to)
return numa_latency[from][to];
}
+static int find_numa_node_for_addr(unsigned long pa,
+ struct node_mem_mask *pnode_mask)
+{
+ struct mdesc_handle *md = mdesc_grab();
+ u64 node, arc;
+ int i = 0;
+
+ node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
+ if (node == MDESC_NODE_NULL)
+ goto out;
+
+ mdesc_for_each_node_by_name(md, node, "group") {
+ mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) {
+ u64 target = mdesc_arc_target(md, arc);
+ struct mdesc_mlgroup *m = find_mlgroup(target);
+
+ if (!m)
+ continue;
+ if ((pa & m->mask) == m->match) {
+ if (pnode_mask) {
+ pnode_mask->mask = m->mask;
+ pnode_mask->val = m->match;
+ }
+ mdesc_release(md);
+ return i;
+ }
+ }
+ i++;
+ }
+
+out:
+ mdesc_release(md);
+ return -1;
+}
+
static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
{
int i;
@@ -1267,13 +1313,6 @@ static int __init numa_parse_mdesc(void)
int i, j, err, count;
u64 node;
- /* Some sane defaults for numa latency values */
- for (i = 0; i < MAX_NUMNODES; i++) {
- for (j = 0; j < MAX_NUMNODES; j++)
- numa_latency[i][j] = (i == j) ?
- LOCAL_DISTANCE : REMOTE_DISTANCE;
- }
-
node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
if (node == MDESC_NODE_NULL) {
mdesc_release(md);
@@ -1369,10 +1408,18 @@ static int __init numa_parse_sun4u(void)
static int __init bootmem_init_numa(void)
{
+ int i, j;
int err = -1;
numadbg("bootmem_init_numa()\n");
+ /* Some sane defaults for numa latency values */
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ for (j = 0; j < MAX_NUMNODES; j++)
+ numa_latency[i][j] = (i == j) ?
+ LOCAL_DISTANCE : REMOTE_DISTANCE;
+ }
+
if (numa_enabled) {
if (tlb_type == hypervisor)
err = numa_parse_mdesc();
@@ -2832,9 +2879,10 @@ void hugetlb_setup(struct pt_regs *regs)
* the Data-TLB for huge pages.
*/
if (tlb_type == cheetah_plus) {
+ bool need_context_reload = false;
unsigned long ctx;
- spin_lock(&ctx_alloc_lock);
+ spin_lock_irq(&ctx_alloc_lock);
ctx = mm->context.sparc64_ctx_val;
ctx &= ~CTX_PGSZ_MASK;
ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
@@ -2853,9 +2901,12 @@ void hugetlb_setup(struct pt_regs *regs)
* also executing in this address space.
*/
mm->context.sparc64_ctx_val = ctx;
- on_each_cpu(context_reload, mm, 0);
+ need_context_reload = true;
}
- spin_unlock(&ctx_alloc_lock);
+ spin_unlock_irq(&ctx_alloc_lock);
+
+ if (need_context_reload)
+ on_each_cpu(context_reload, mm, 0);
}
}
#endif
diff --git a/kernel/arch/sparc/mm/tlb.c b/kernel/arch/sparc/mm/tlb.c
index 9df2190c0..3659d37b4 100644
--- a/kernel/arch/sparc/mm/tlb.c
+++ b/kernel/arch/sparc/mm/tlb.c
@@ -67,7 +67,7 @@ void arch_leave_lazy_mmu_mode(void)
}
static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
- bool exec)
+ bool exec, bool huge)
{
struct tlb_batch *tb = &get_cpu_var(tlb_batch);
unsigned long nr;
@@ -84,13 +84,21 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
}
if (!tb->active) {
- flush_tsb_user_page(mm, vaddr);
+ flush_tsb_user_page(mm, vaddr, huge);
global_flush_tlb_page(mm, vaddr);
goto out;
}
- if (nr == 0)
+ if (nr == 0) {
tb->mm = mm;
+ tb->huge = huge;
+ }
+
+ if (tb->huge != huge) {
+ flush_tlb_pending();
+ tb->huge = huge;
+ nr = 0;
+ }
tb->vaddrs[nr] = vaddr;
tb->tlb_nr = ++nr;
@@ -104,6 +112,8 @@ out:
void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
pte_t *ptep, pte_t orig, int fullmm)
{
+ bool huge = is_hugetlb_pte(orig);
+
if (tlb_type != hypervisor &&
pte_dirty(orig)) {
unsigned long paddr, pfn = pte_pfn(orig);
@@ -129,7 +139,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
no_cache_flush:
if (!fullmm)
- tlb_batch_add_one(mm, vaddr, pte_exec(orig));
+ tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -145,7 +155,7 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
if (pte_val(*pte) & _PAGE_VALID) {
bool exec = pte_exec(*pte);
- tlb_batch_add_one(mm, vaddr, exec);
+ tlb_batch_add_one(mm, vaddr, exec, false);
}
pte++;
vaddr += PAGE_SIZE;
@@ -165,9 +175,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
if (pmd_val(pmd) & _PAGE_PMD_HUGE)
- mm->context.huge_pte_count++;
+ mm->context.thp_pte_count++;
else
- mm->context.huge_pte_count--;
+ 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
@@ -185,8 +195,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pte_t orig_pte = __pte(pmd_val(orig));
bool exec = pte_exec(orig_pte);
- tlb_batch_add_one(mm, addr, exec);
- tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec);
+ tlb_batch_add_one(mm, addr, exec, true);
+ tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
+ true);
} else {
tlb_batch_pmd_scan(mm, addr, orig);
}
diff --git a/kernel/arch/sparc/mm/tsb.c b/kernel/arch/sparc/mm/tsb.c
index a06576683..9cdeca0fa 100644
--- a/kernel/arch/sparc/mm/tsb.c
+++ b/kernel/arch/sparc/mm/tsb.c
@@ -27,6 +27,20 @@ static inline int tag_compare(unsigned long tag, unsigned long vaddr)
return (tag == (vaddr >> 22));
}
+static void flush_tsb_kernel_range_scan(unsigned long start, unsigned long end)
+{
+ unsigned long idx;
+
+ for (idx = 0; idx < KERNEL_TSB_NENTRIES; idx++) {
+ struct tsb *ent = &swapper_tsb[idx];
+ unsigned long match = idx << 13;
+
+ match |= (ent->tag << 22);
+ if (match >= start && match < end)
+ ent->tag = (1UL << TSB_TAG_INVALID_BIT);
+ }
+}
+
/* TSB flushes need only occur on the processor initiating the address
* space modification, not on each cpu the address space has run on.
* Only the TLB flush needs that treatment.
@@ -36,6 +50,9 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
{
unsigned long v;
+ if ((end - start) >> PAGE_SHIFT >= 2 * KERNEL_TSB_NENTRIES)
+ return flush_tsb_kernel_range_scan(start, end);
+
for (v = start; v < end; v += PAGE_SIZE) {
unsigned long hash = tsb_hash(v, PAGE_SHIFT,
KERNEL_TSB_NENTRIES);
@@ -76,14 +93,15 @@ void flush_tsb_user(struct tlb_batch *tb)
spin_lock_irqsave(&mm->context.lock, flags);
- base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
- nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
- if (tlb_type == cheetah_plus || tlb_type == hypervisor)
- base = __pa(base);
- __flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
-
+ if (!tb->huge) {
+ base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+ nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+ if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+ base = __pa(base);
+ __flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
+ }
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+ if (tb->huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
@@ -94,20 +112,21 @@ void flush_tsb_user(struct tlb_batch *tb)
spin_unlock_irqrestore(&mm->context.lock, flags);
}
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge)
{
unsigned long nentries, base, flags;
spin_lock_irqsave(&mm->context.lock, flags);
- base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
- nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
- if (tlb_type == cheetah_plus || tlb_type == hypervisor)
- base = __pa(base);
- __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
-
+ if (!huge) {
+ base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+ nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+ if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+ base = __pa(base);
+ __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+ }
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+ if (huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
@@ -468,7 +487,7 @@ retry_tsb_alloc:
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- unsigned long huge_pte_count;
+ unsigned long total_huge_pte_count;
#endif
unsigned int i;
@@ -477,12 +496,14 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
mm->context.sparc64_ctx_val = 0UL;
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- /* We reset it to zero because the fork() page copying
+ /* We reset them to zero because the fork() page copying
* will re-increment the counters as the parent PTEs are
* copied into the child address space.
*/
- huge_pte_count = mm->context.huge_pte_count;
- mm->context.huge_pte_count = 0;
+ total_huge_pte_count = mm->context.hugetlb_pte_count +
+ mm->context.thp_pte_count;
+ mm->context.hugetlb_pte_count = 0;
+ mm->context.thp_pte_count = 0;
#endif
/* copy_mm() copies over the parent's mm_struct before calling
@@ -498,8 +519,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (unlikely(huge_pte_count))
- tsb_grow(mm, MM_TSB_HUGE, huge_pte_count);
+ if (unlikely(total_huge_pte_count))
+ tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count);
#endif
if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))
diff --git a/kernel/arch/sparc/mm/ultra.S b/kernel/arch/sparc/mm/ultra.S
index b4f4733ab..5d2fd6cd3 100644
--- a/kernel/arch/sparc/mm/ultra.S
+++ b/kernel/arch/sparc/mm/ultra.S
@@ -30,7 +30,7 @@
.text
.align 32
.globl __flush_tlb_mm
-__flush_tlb_mm: /* 18 insns */
+__flush_tlb_mm: /* 19 insns */
/* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */
ldxa [%o1] ASI_DMMU, %g2
cmp %g2, %o0
@@ -81,7 +81,7 @@ __flush_tlb_page: /* 22 insns */
.align 32
.globl __flush_tlb_pending
-__flush_tlb_pending: /* 26 insns */
+__flush_tlb_pending: /* 27 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
rdpr %pstate, %g7
sllx %o1, 3, %o1
@@ -113,12 +113,14 @@ __flush_tlb_pending: /* 26 insns */
.align 32
.globl __flush_tlb_kernel_range
-__flush_tlb_kernel_range: /* 16 insns */
+__flush_tlb_kernel_range: /* 31 insns */
/* %o0=start, %o1=end */
cmp %o0, %o1
be,pn %xcc, 2f
+ sub %o1, %o0, %o3
+ srlx %o3, 18, %o4
+ brnz,pn %o4, __spitfire_flush_tlb_kernel_range_slow
sethi %hi(PAGE_SIZE), %o4
- sub %o1, %o0, %o3
sub %o3, %o4, %o3
or %o0, 0x20, %o0 ! Nucleus
1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP
@@ -131,6 +133,41 @@ __flush_tlb_kernel_range: /* 16 insns */
retl
nop
nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
+__spitfire_flush_tlb_kernel_range_slow:
+ mov 63 * 8, %o4
+1: ldxa [%o4] ASI_ITLB_DATA_ACCESS, %o3
+ andcc %o3, 0x40, %g0 /* _PAGE_L_4U */
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %o3
+ stxa %g0, [%o3] ASI_IMMU
+ stxa %g0, [%o4] ASI_ITLB_DATA_ACCESS
+ membar #Sync
+2: ldxa [%o4] ASI_DTLB_DATA_ACCESS, %o3
+ andcc %o3, 0x40, %g0
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %o3
+ stxa %g0, [%o3] ASI_DMMU
+ stxa %g0, [%o4] ASI_DTLB_DATA_ACCESS
+ membar #Sync
+2: sub %o4, 8, %o4
+ brgez,pt %o4, 1b
+ nop
+ retl
+ nop
__spitfire_flush_tlb_mm_slow:
rdpr %pstate, %g1
@@ -285,6 +322,40 @@ __cheetah_flush_tlb_pending: /* 27 insns */
retl
wrpr %g7, 0x0, %pstate
+__cheetah_flush_tlb_kernel_range: /* 31 insns */
+ /* %o0=start, %o1=end */
+ cmp %o0, %o1
+ be,pn %xcc, 2f
+ sub %o1, %o0, %o3
+ srlx %o3, 18, %o4
+ brnz,pn %o4, 3f
+ sethi %hi(PAGE_SIZE), %o4
+ sub %o3, %o4, %o3
+ or %o0, 0x20, %o0 ! Nucleus
+1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP
+ stxa %g0, [%o0 + %o3] ASI_IMMU_DEMAP
+ membar #Sync
+ brnz,pt %o3, 1b
+ sub %o3, %o4, %o3
+2: sethi %hi(KERNBASE), %o3
+ flush %o3
+ retl
+ nop
+3: mov 0x80, %o4
+ stxa %g0, [%o4] ASI_DMMU_DEMAP
+ membar #Sync
+ stxa %g0, [%o4] ASI_IMMU_DEMAP
+ membar #Sync
+ retl
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
#ifdef DCACHE_ALIASING_POSSIBLE
__cheetah_flush_dcache_page: /* 11 insns */
sethi %hi(PAGE_OFFSET), %g1
@@ -309,19 +380,28 @@ __hypervisor_tlb_tl0_error:
ret
restore
-__hypervisor_flush_tlb_mm: /* 10 insns */
+__hypervisor_flush_tlb_mm: /* 19 insns */
mov %o0, %o2 /* ARG2: mmu context */
mov 0, %o0 /* ARG0: CPU lists unimplemented */
mov 0, %o1 /* ARG1: CPU lists unimplemented */
mov HV_MMU_ALL, %o3 /* ARG3: flags */
mov HV_FAST_MMU_DEMAP_CTX, %o5
ta HV_FAST_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_FAST_MMU_DEMAP_CTX, %o1
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o5
+ jmpl %o5 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_page: /* 11 insns */
+__hypervisor_flush_tlb_page: /* 22 insns */
/* %o0 = context, %o1 = vaddr */
mov %o0, %g2
mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */
@@ -330,12 +410,23 @@ __hypervisor_flush_tlb_page: /* 11 insns */
srlx %o0, PAGE_SHIFT, %o0
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_pending: /* 16 insns */
+__hypervisor_flush_tlb_pending: /* 27 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
sllx %o1, 3, %g1
mov %o2, %g2
@@ -347,31 +438,57 @@ __hypervisor_flush_tlb_pending: /* 16 insns */
srlx %o0, PAGE_SHIFT, %o0
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
brnz,pt %g1, 1b
nop
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_kernel_range: /* 16 insns */
+__hypervisor_flush_tlb_kernel_range: /* 31 insns */
/* %o0=start, %o1=end */
cmp %o0, %o1
be,pn %xcc, 2f
- sethi %hi(PAGE_SIZE), %g3
- mov %o0, %g1
- sub %o1, %g1, %g2
+ sub %o1, %o0, %g2
+ srlx %g2, 18, %g3
+ brnz,pn %g3, 4f
+ mov %o0, %g1
+ sethi %hi(PAGE_SIZE), %g3
sub %g2, %g3, %g2
1: add %g1, %g2, %o0 /* ARG0: virtual address */
mov 0, %o1 /* ARG1: mmu context */
mov HV_MMU_ALL, %o2 /* ARG2: flags */
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 3f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
brnz,pt %g2, 1b
sub %g2, %g3, %g2
2: retl
nop
+3: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+4: mov 0, %o0 /* ARG0: CPU lists unimplemented */
+ mov 0, %o1 /* ARG1: CPU lists unimplemented */
+ mov 0, %o2 /* ARG2: mmu context == nucleus */
+ mov HV_MMU_ALL, %o3 /* ARG3: flags */
+ mov HV_FAST_MMU_DEMAP_CTX, %o5
+ ta HV_FAST_TRAP
+ brnz,pn %o0, 3b
+ mov HV_FAST_MMU_DEMAP_CTX, %o1
+ retl
+ nop
#ifdef DCACHE_ALIASING_POSSIBLE
/* XXX Niagara and friends have an 8K cache, so no aliasing is
@@ -394,43 +511,6 @@ tlb_patch_one:
retl
nop
- .globl cheetah_patch_cachetlbops
-cheetah_patch_cachetlbops:
- save %sp, -128, %sp
-
- sethi %hi(__flush_tlb_mm), %o0
- or %o0, %lo(__flush_tlb_mm), %o0
- sethi %hi(__cheetah_flush_tlb_mm), %o1
- or %o1, %lo(__cheetah_flush_tlb_mm), %o1
- call tlb_patch_one
- mov 19, %o2
-
- sethi %hi(__flush_tlb_page), %o0
- or %o0, %lo(__flush_tlb_page), %o0
- sethi %hi(__cheetah_flush_tlb_page), %o1
- or %o1, %lo(__cheetah_flush_tlb_page), %o1
- call tlb_patch_one
- mov 22, %o2
-
- sethi %hi(__flush_tlb_pending), %o0
- or %o0, %lo(__flush_tlb_pending), %o0
- sethi %hi(__cheetah_flush_tlb_pending), %o1
- or %o1, %lo(__cheetah_flush_tlb_pending), %o1
- call tlb_patch_one
- mov 27, %o2
-
-#ifdef DCACHE_ALIASING_POSSIBLE
- sethi %hi(__flush_dcache_page), %o0
- or %o0, %lo(__flush_dcache_page), %o0
- sethi %hi(__cheetah_flush_dcache_page), %o1
- or %o1, %lo(__cheetah_flush_dcache_page), %o1
- call tlb_patch_one
- mov 11, %o2
-#endif /* DCACHE_ALIASING_POSSIBLE */
-
- ret
- restore
-
#ifdef CONFIG_SMP
/* These are all called by the slaves of a cross call, at
* trap level 1, with interrupts fully disabled.
@@ -447,7 +527,7 @@ cheetah_patch_cachetlbops:
*/
.align 32
.globl xcall_flush_tlb_mm
-xcall_flush_tlb_mm: /* 21 insns */
+xcall_flush_tlb_mm: /* 24 insns */
mov PRIMARY_CONTEXT, %g2
ldxa [%g2] ASI_DMMU, %g3
srlx %g3, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -469,9 +549,12 @@ xcall_flush_tlb_mm: /* 21 insns */
nop
nop
nop
+ nop
+ nop
+ nop
.globl xcall_flush_tlb_page
-xcall_flush_tlb_page: /* 17 insns */
+xcall_flush_tlb_page: /* 20 insns */
/* %g5=context, %g1=vaddr */
mov PRIMARY_CONTEXT, %g4
ldxa [%g4] ASI_DMMU, %g2
@@ -490,15 +573,20 @@ xcall_flush_tlb_page: /* 17 insns */
retry
nop
nop
+ nop
+ nop
+ nop
.globl xcall_flush_tlb_kernel_range
-xcall_flush_tlb_kernel_range: /* 25 insns */
+xcall_flush_tlb_kernel_range: /* 44 insns */
sethi %hi(PAGE_SIZE - 1), %g2
or %g2, %lo(PAGE_SIZE - 1), %g2
andn %g1, %g2, %g1
andn %g7, %g2, %g7
sub %g7, %g1, %g3
- add %g2, 1, %g2
+ srlx %g3, 18, %g2
+ brnz,pn %g2, 2f
+ add %g2, 1, %g2
sub %g3, %g2, %g3
or %g1, 0x20, %g1 ! Nucleus
1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP
@@ -507,8 +595,25 @@ xcall_flush_tlb_kernel_range: /* 25 insns */
brnz,pt %g3, 1b
sub %g3, %g2, %g3
retry
- nop
- nop
+2: mov 63 * 8, %g1
+1: ldxa [%g1] ASI_ITLB_DATA_ACCESS, %g2
+ andcc %g2, 0x40, %g0 /* _PAGE_L_4U */
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %g2
+ stxa %g0, [%g2] ASI_IMMU
+ stxa %g0, [%g1] ASI_ITLB_DATA_ACCESS
+ membar #Sync
+2: ldxa [%g1] ASI_DTLB_DATA_ACCESS, %g2
+ andcc %g2, 0x40, %g0
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %g2
+ stxa %g0, [%g2] ASI_DMMU
+ stxa %g0, [%g1] ASI_DTLB_DATA_ACCESS
+ membar #Sync
+2: sub %g1, 8, %g1
+ brgez,pt %g1, 1b
+ nop
+ retry
nop
nop
nop
@@ -637,6 +742,52 @@ xcall_fetch_glob_pmu_n4:
retry
+__cheetah_xcall_flush_tlb_kernel_range: /* 44 insns */
+ sethi %hi(PAGE_SIZE - 1), %g2
+ or %g2, %lo(PAGE_SIZE - 1), %g2
+ andn %g1, %g2, %g1
+ andn %g7, %g2, %g7
+ sub %g7, %g1, %g3
+ srlx %g3, 18, %g2
+ brnz,pn %g2, 2f
+ add %g2, 1, %g2
+ sub %g3, %g2, %g3
+ or %g1, 0x20, %g1 ! Nucleus
+1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP
+ stxa %g0, [%g1 + %g3] ASI_IMMU_DEMAP
+ membar #Sync
+ brnz,pt %g3, 1b
+ sub %g3, %g2, %g3
+ retry
+2: mov 0x80, %g2
+ stxa %g0, [%g2] ASI_DMMU_DEMAP
+ membar #Sync
+ stxa %g0, [%g2] ASI_IMMU_DEMAP
+ membar #Sync
+ retry
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
#ifdef DCACHE_ALIASING_POSSIBLE
.align 32
.globl xcall_flush_dcache_page_cheetah
@@ -700,7 +851,7 @@ __hypervisor_tlb_xcall_error:
ba,a,pt %xcc, rtrap
.globl __hypervisor_xcall_flush_tlb_mm
-__hypervisor_xcall_flush_tlb_mm: /* 21 insns */
+__hypervisor_xcall_flush_tlb_mm: /* 24 insns */
/* %g5=ctx, g1,g2,g3,g4,g7=scratch, %g6=unusable */
mov %o0, %g2
mov %o1, %g3
@@ -714,7 +865,7 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
mov HV_FAST_MMU_DEMAP_CTX, %o5
ta HV_FAST_TRAP
mov HV_FAST_MMU_DEMAP_CTX, %g6
- brnz,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,pn %o0, 1f
mov %o0, %g5
mov %g2, %o0
mov %g3, %o1
@@ -723,9 +874,12 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
mov %g7, %o5
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
.globl __hypervisor_xcall_flush_tlb_page
-__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+__hypervisor_xcall_flush_tlb_page: /* 20 insns */
/* %g5=ctx, %g1=vaddr */
mov %o0, %g2
mov %o1, %g3
@@ -737,42 +891,64 @@ __hypervisor_xcall_flush_tlb_page: /* 17 insns */
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
mov HV_MMU_UNMAP_ADDR_TRAP, %g6
- brnz,a,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,a,pn %o0, 1f
mov %o0, %g5
mov %g2, %o0
mov %g3, %o1
mov %g4, %o2
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
.globl __hypervisor_xcall_flush_tlb_kernel_range
-__hypervisor_xcall_flush_tlb_kernel_range: /* 25 insns */
+__hypervisor_xcall_flush_tlb_kernel_range: /* 44 insns */
/* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */
sethi %hi(PAGE_SIZE - 1), %g2
or %g2, %lo(PAGE_SIZE - 1), %g2
andn %g1, %g2, %g1
andn %g7, %g2, %g7
sub %g7, %g1, %g3
+ srlx %g3, 18, %g7
add %g2, 1, %g2
sub %g3, %g2, %g3
mov %o0, %g2
mov %o1, %g4
- mov %o2, %g7
+ brnz,pn %g7, 2f
+ mov %o2, %g7
1: add %g1, %g3, %o0 /* ARG0: virtual address */
mov 0, %o1 /* ARG1: mmu context */
mov HV_MMU_ALL, %o2 /* ARG2: flags */
ta HV_MMU_UNMAP_ADDR_TRAP
mov HV_MMU_UNMAP_ADDR_TRAP, %g6
- brnz,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,pn %o0, 1f
mov %o0, %g5
sethi %hi(PAGE_SIZE), %o2
brnz,pt %g3, 1b
sub %g3, %o2, %g3
- mov %g2, %o0
+5: mov %g2, %o0
mov %g4, %o1
mov %g7, %o2
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
+2: mov %o3, %g1
+ mov %o5, %g3
+ mov 0, %o0 /* ARG0: CPU lists unimplemented */
+ mov 0, %o1 /* ARG1: CPU lists unimplemented */
+ mov 0, %o2 /* ARG2: mmu context == nucleus */
+ mov HV_MMU_ALL, %o3 /* ARG3: flags */
+ mov HV_FAST_MMU_DEMAP_CTX, %o5
+ ta HV_FAST_TRAP
+ mov %g1, %o3
+ brz,pt %o0, 5b
+ mov %g3, %o5
+ mov HV_FAST_MMU_DEMAP_CTX, %g6
+ ba,pt %xcc, 1b
+ clr %g5
/* These just get rescheduled to PIL vectors. */
.globl xcall_call_function
@@ -809,6 +985,58 @@ xcall_kgdb_capture:
#endif /* CONFIG_SMP */
+ .globl cheetah_patch_cachetlbops
+cheetah_patch_cachetlbops:
+ save %sp, -128, %sp
+
+ sethi %hi(__flush_tlb_mm), %o0
+ or %o0, %lo(__flush_tlb_mm), %o0
+ sethi %hi(__cheetah_flush_tlb_mm), %o1
+ or %o1, %lo(__cheetah_flush_tlb_mm), %o1
+ call tlb_patch_one
+ mov 19, %o2
+
+ sethi %hi(__flush_tlb_page), %o0
+ or %o0, %lo(__flush_tlb_page), %o0
+ sethi %hi(__cheetah_flush_tlb_page), %o1
+ or %o1, %lo(__cheetah_flush_tlb_page), %o1
+ call tlb_patch_one
+ mov 22, %o2
+
+ sethi %hi(__flush_tlb_pending), %o0
+ or %o0, %lo(__flush_tlb_pending), %o0
+ sethi %hi(__cheetah_flush_tlb_pending), %o1
+ or %o1, %lo(__cheetah_flush_tlb_pending), %o1
+ call tlb_patch_one
+ mov 27, %o2
+
+ sethi %hi(__flush_tlb_kernel_range), %o0
+ or %o0, %lo(__flush_tlb_kernel_range), %o0
+ sethi %hi(__cheetah_flush_tlb_kernel_range), %o1
+ or %o1, %lo(__cheetah_flush_tlb_kernel_range), %o1
+ call tlb_patch_one
+ mov 31, %o2
+
+#ifdef DCACHE_ALIASING_POSSIBLE
+ sethi %hi(__flush_dcache_page), %o0
+ or %o0, %lo(__flush_dcache_page), %o0
+ sethi %hi(__cheetah_flush_dcache_page), %o1
+ or %o1, %lo(__cheetah_flush_dcache_page), %o1
+ call tlb_patch_one
+ mov 11, %o2
+#endif /* DCACHE_ALIASING_POSSIBLE */
+
+#ifdef CONFIG_SMP
+ sethi %hi(xcall_flush_tlb_kernel_range), %o0
+ or %o0, %lo(xcall_flush_tlb_kernel_range), %o0
+ sethi %hi(__cheetah_xcall_flush_tlb_kernel_range), %o1
+ or %o1, %lo(__cheetah_xcall_flush_tlb_kernel_range), %o1
+ call tlb_patch_one
+ mov 44, %o2
+#endif /* CONFIG_SMP */
+
+ ret
+ restore
.globl hypervisor_patch_cachetlbops
hypervisor_patch_cachetlbops:
@@ -819,28 +1047,28 @@ hypervisor_patch_cachetlbops:
sethi %hi(__hypervisor_flush_tlb_mm), %o1
or %o1, %lo(__hypervisor_flush_tlb_mm), %o1
call tlb_patch_one
- mov 10, %o2
+ mov 19, %o2
sethi %hi(__flush_tlb_page), %o0
or %o0, %lo(__flush_tlb_page), %o0
sethi %hi(__hypervisor_flush_tlb_page), %o1
or %o1, %lo(__hypervisor_flush_tlb_page), %o1
call tlb_patch_one
- mov 11, %o2
+ mov 22, %o2
sethi %hi(__flush_tlb_pending), %o0
or %o0, %lo(__flush_tlb_pending), %o0
sethi %hi(__hypervisor_flush_tlb_pending), %o1
or %o1, %lo(__hypervisor_flush_tlb_pending), %o1
call tlb_patch_one
- mov 16, %o2
+ mov 27, %o2
sethi %hi(__flush_tlb_kernel_range), %o0
or %o0, %lo(__flush_tlb_kernel_range), %o0
sethi %hi(__hypervisor_flush_tlb_kernel_range), %o1
or %o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1
call tlb_patch_one
- mov 16, %o2
+ mov 31, %o2
#ifdef DCACHE_ALIASING_POSSIBLE
sethi %hi(__flush_dcache_page), %o0
@@ -857,21 +1085,21 @@ hypervisor_patch_cachetlbops:
sethi %hi(__hypervisor_xcall_flush_tlb_mm), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_mm), %o1
call tlb_patch_one
- mov 21, %o2
+ mov 24, %o2
sethi %hi(xcall_flush_tlb_page), %o0
or %o0, %lo(xcall_flush_tlb_page), %o0
sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
call tlb_patch_one
- mov 17, %o2
+ mov 20, %o2
sethi %hi(xcall_flush_tlb_kernel_range), %o0
or %o0, %lo(xcall_flush_tlb_kernel_range), %o0
sethi %hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1
call tlb_patch_one
- mov 25, %o2
+ mov 44, %o2
#endif /* CONFIG_SMP */
ret
diff --git a/kernel/arch/tile/include/asm/elf.h b/kernel/arch/tile/include/asm/elf.h
index c505d77e4..e9d54a067 100644
--- a/kernel/arch/tile/include/asm/elf.h
+++ b/kernel/arch/tile/include/asm/elf.h
@@ -129,6 +129,7 @@ extern int dump_task_regs(struct task_struct *, elf_gregset_t *);
struct linux_binprm;
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int executable_stack);
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
#define ARCH_DLINFO \
do { \
NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_BASE); \
diff --git a/kernel/arch/tile/include/uapi/asm/auxvec.h b/kernel/arch/tile/include/uapi/asm/auxvec.h
index c93e92709..f497123ed 100644
--- a/kernel/arch/tile/include/uapi/asm/auxvec.h
+++ b/kernel/arch/tile/include/uapi/asm/auxvec.h
@@ -18,4 +18,6 @@
/* The vDSO location. */
#define AT_SYSINFO_EHDR 33
+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
#endif /* _ASM_TILE_AUXVEC_H */
diff --git a/kernel/arch/tile/kernel/ptrace.c b/kernel/arch/tile/kernel/ptrace.c
index bdc126faf..6239aa155 100644
--- a/kernel/arch/tile/kernel/ptrace.c
+++ b/kernel/arch/tile/kernel/ptrace.c
@@ -111,7 +111,7 @@ static int tile_gpr_set(struct task_struct *target,
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct pt_regs regs;
+ struct pt_regs regs = *task_pt_regs(target);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &regs, 0,
sizeof(regs));
diff --git a/kernel/arch/tile/kernel/time.c b/kernel/arch/tile/kernel/time.c
index 178989e6d..ea960d660 100644
--- a/kernel/arch/tile/kernel/time.c
+++ b/kernel/arch/tile/kernel/time.c
@@ -218,8 +218,8 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num)
*/
unsigned long long sched_clock(void)
{
- return clocksource_cyc2ns(get_cycles(),
- sched_clock_mult, SCHED_CLOCK_SHIFT);
+ return mult_frac(get_cycles(),
+ sched_clock_mult, 1ULL << SCHED_CLOCK_SHIFT);
}
int setup_profiling_timer(unsigned int multiplier)
diff --git a/kernel/arch/um/drivers/mconsole_kern.c b/kernel/arch/um/drivers/mconsole_kern.c
index 29880c9b3..e22e57298 100644
--- a/kernel/arch/um/drivers/mconsole_kern.c
+++ b/kernel/arch/um/drivers/mconsole_kern.c
@@ -133,7 +133,7 @@ void mconsole_proc(struct mc_request *req)
ptr += strlen("proc");
ptr = skip_spaces(ptr);
- file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY);
+ file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0);
if (IS_ERR(file)) {
mconsole_reply(req, "Failed to open file", 1, 0);
printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file));
diff --git a/kernel/arch/um/include/asm/common.lds.S b/kernel/arch/um/include/asm/common.lds.S
index 1dd5bd8a8..133055311 100644
--- a/kernel/arch/um/include/asm/common.lds.S
+++ b/kernel/arch/um/include/asm/common.lds.S
@@ -81,7 +81,7 @@
.altinstr_replacement : { *(.altinstr_replacement) }
/* .exit.text is discard at runtime, not link time, to deal with references
from .altinstructions and .eh_frame */
- .exit.text : { *(.exit.text) }
+ .exit.text : { EXIT_TEXT }
.exit.data : { *(.exit.data) }
.preinit_array : {
diff --git a/kernel/arch/x86/Kconfig b/kernel/arch/x86/Kconfig
index d8a1650a0..6ee1dd0de 100644
--- a/kernel/arch/x86/Kconfig
+++ b/kernel/arch/x86/Kconfig
@@ -1130,22 +1130,23 @@ config MICROCODE
bool "CPU microcode loading support"
default y
depends on CPU_SUP_AMD || CPU_SUP_INTEL
- depends on BLK_DEV_INITRD
select FW_LOADER
---help---
-
If you say Y here, you will be able to update the microcode on
- certain Intel and AMD processors. The Intel support is for the
- IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4,
- Xeon etc. The AMD support is for families 0x10 and later. You will
- obviously need the actual microcode binary data itself which is not
- shipped with the Linux kernel.
-
- This option selects the general module only, you need to select
- at least one vendor specific module as well.
-
- To compile this driver as a module, choose M here: the module
- will be called microcode.
+ Intel and AMD processors. The Intel support is for the IA32 family,
+ e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. The
+ AMD support is for families 0x10 and later. You will obviously need
+ the actual microcode binary data itself which is not shipped with
+ the Linux kernel.
+
+ The preferred method to load microcode from a detached initrd is described
+ in Documentation/x86/early-microcode.txt. For that you need to enable
+ CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the
+ initrd for microcode blobs.
+
+ In addition, you can build-in the microcode into the kernel. For that you
+ need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode
+ to the CONFIG_EXTRA_FIRMWARE config option.
config MICROCODE_INTEL
bool "Intel microcode loading support"
diff --git a/kernel/arch/x86/boot/Makefile b/kernel/arch/x86/boot/Makefile
index 2ee62dba0..c0cc2a6be 100644
--- a/kernel/arch/x86/boot/Makefile
+++ b/kernel/arch/x86/boot/Makefile
@@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage
for i in lib lib64 share end ; do \
if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+ if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \
+ cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \
+ fi ; \
break ; \
fi ; \
if [ $$i = end ] ; then exit 1 ; fi ; \
diff --git a/kernel/arch/x86/boot/compressed/Makefile b/kernel/arch/x86/boot/compressed/Makefile
index 0a291cdfa..efa6073ff 100644
--- a/kernel/arch/x86/boot/compressed/Makefile
+++ b/kernel/arch/x86/boot/compressed/Makefile
@@ -22,7 +22,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
-KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
+KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
cflags-$(CONFIG_X86_32) := -march=i386
cflags-$(CONFIG_X86_64) := -mcmodel=small
@@ -35,6 +35,18 @@ KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
GCOV_PROFILE := n
LDFLAGS := -m elf_$(UTS_MACHINE)
+ifeq ($(CONFIG_RELOCATABLE),y)
+# If kernel is relocatable, build compressed kernel as PIE.
+ifeq ($(CONFIG_X86_32),y)
+LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
+else
+# To build 64-bit compressed kernel as PIE, we disable relocation
+# overflow check to avoid relocation overflow error with a new linker
+# command-line option, -z noreloc-overflow.
+LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
+ && echo "-z noreloc-overflow -pie --no-dynamic-linker")
+endif
+endif
LDFLAGS_vmlinux := -T
hostprogs-y := mkpiggy
diff --git a/kernel/arch/x86/boot/compressed/head_32.S b/kernel/arch/x86/boot/compressed/head_32.S
index 8ef964ddc..0256064da 100644
--- a/kernel/arch/x86/boot/compressed/head_32.S
+++ b/kernel/arch/x86/boot/compressed/head_32.S
@@ -31,6 +31,34 @@
#include <asm/asm-offsets.h>
#include <asm/bootparam.h>
+/*
+ * The 32-bit x86 assembler in binutils 2.26 will generate R_386_GOT32X
+ * relocation to get the symbol address in PIC. When the compressed x86
+ * kernel isn't built as PIC, the linker optimizes R_386_GOT32X
+ * relocations to their fixed symbol addresses. However, when the
+ * compressed x86 kernel is loaded at a different address, it leads
+ * to the following load failure:
+ *
+ * Failed to allocate space for phdrs
+ *
+ * during the decompression stage.
+ *
+ * If the compressed x86 kernel is relocatable at run-time, it should be
+ * compiled with -fPIE, instead of -fPIC, if possible and should be built as
+ * Position Independent Executable (PIE) so that linker won't optimize
+ * R_386_GOT32X relocation to its fixed symbol address. Older
+ * linkers generate R_386_32 relocations against locally defined symbols,
+ * _bss, _ebss, _got and _egot, in PIE. It isn't wrong, just less
+ * optimal than R_386_RELATIVE. But the x86 kernel fails to properly handle
+ * R_386_32 relocations when relocating the kernel. To generate
+ * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as
+ * hidden:
+ */
+ .hidden _bss
+ .hidden _ebss
+ .hidden _got
+ .hidden _egot
+
__HEAD
ENTRY(startup_32)
#ifdef CONFIG_EFI_STUB
diff --git a/kernel/arch/x86/boot/compressed/head_64.S b/kernel/arch/x86/boot/compressed/head_64.S
index b0c0d16ef..86558a199 100644
--- a/kernel/arch/x86/boot/compressed/head_64.S
+++ b/kernel/arch/x86/boot/compressed/head_64.S
@@ -33,6 +33,14 @@
#include <asm/asm-offsets.h>
#include <asm/bootparam.h>
+/*
+ * Locally defined symbols should be marked hidden:
+ */
+ .hidden _bss
+ .hidden _ebss
+ .hidden _got
+ .hidden _egot
+
__HEAD
.code32
ENTRY(startup_32)
diff --git a/kernel/arch/x86/configs/tiny.config b/kernel/arch/x86/configs/tiny.config
index 4e2ecfa23..4b429df40 100644
--- a/kernel/arch/x86/configs/tiny.config
+++ b/kernel/arch/x86/configs/tiny.config
@@ -1 +1,3 @@
CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
diff --git a/kernel/arch/x86/crypto/sha-mb/sha1_mb.c b/kernel/arch/x86/crypto/sha-mb/sha1_mb.c
index a841e9765..8381c09d2 100644
--- a/kernel/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/kernel/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -453,10 +453,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
req = cast_mcryptd_ctx_to_req(req_ctx);
if (irqs_disabled())
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
else {
local_bh_disable();
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
local_bh_enable();
}
}
diff --git a/kernel/arch/x86/entry/common.c b/kernel/arch/x86/entry/common.c
index 3ec240f39..75a301b6a 100644
--- a/kernel/arch/x86/entry/common.c
+++ b/kernel/arch/x86/entry/common.c
@@ -275,6 +275,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
/* 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);
u32 cached_flags;
if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
@@ -282,12 +283,22 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
lockdep_sys_exit();
- cached_flags =
- READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+ cached_flags = READ_ONCE(ti->flags);
if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
exit_to_usermode_loop(regs, cached_flags);
+#ifdef CONFIG_COMPAT
+ /*
+ * Compat syscalls set TS_COMPAT. Make sure we clear it before
+ * returning to user mode. We need to clear it *after* signal
+ * handling, because syscall restart has a fixup for compat
+ * syscalls. The fixup is exercised by the ptrace_syscall_32
+ * selftest.
+ */
+ ti->status &= ~TS_COMPAT;
+#endif
+
user_enter();
}
@@ -339,14 +350,6 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
syscall_slow_exit_work(regs, cached_flags);
-#ifdef CONFIG_COMPAT
- /*
- * Compat syscalls set TS_COMPAT. Make sure we clear it before
- * returning to user mode.
- */
- ti->status &= ~TS_COMPAT;
-#endif
-
local_irq_disable();
prepare_exit_to_usermode(regs);
}
diff --git a/kernel/arch/x86/entry/entry_32.S b/kernel/arch/x86/entry/entry_32.S
index 2d722ee01..3bcef8bdb 100644
--- a/kernel/arch/x86/entry/entry_32.S
+++ b/kernel/arch/x86/entry/entry_32.S
@@ -782,8 +782,8 @@ ftrace_graph_call:
jmp ftrace_stub
#endif
-.globl ftrace_stub
-ftrace_stub:
+/* This is weak to keep gas from relaxing the jumps */
+WEAK(ftrace_stub)
ret
END(ftrace_caller)
diff --git a/kernel/arch/x86/entry/syscalls/syscall_32.tbl b/kernel/arch/x86/entry/syscalls/syscall_32.tbl
index f17705e13..e62f4401e 100644
--- a/kernel/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/kernel/arch/x86/entry/syscalls/syscall_32.tbl
@@ -294,7 +294,7 @@
# 285 sys_setaltroot
286 i386 add_key sys_add_key
287 i386 request_key sys_request_key
-288 i386 keyctl sys_keyctl
+288 i386 keyctl sys_keyctl compat_sys_keyctl
289 i386 ioprio_set sys_ioprio_set
290 i386 ioprio_get sys_ioprio_get
291 i386 inotify_init sys_inotify_init
diff --git a/kernel/arch/x86/include/asm/apic.h b/kernel/arch/x86/include/asm/apic.h
index 9686289d2..6a03a760f 100644
--- a/kernel/arch/x86/include/asm/apic.h
+++ b/kernel/arch/x86/include/asm/apic.h
@@ -640,8 +640,8 @@ static inline void entering_irq(void)
static inline void entering_ack_irq(void)
{
- ack_APIC_irq();
entering_irq();
+ ack_APIC_irq();
}
static inline void ipi_entering_ack_irq(void)
diff --git a/kernel/arch/x86/include/asm/hugetlb.h b/kernel/arch/x86/include/asm/hugetlb.h
index f8a29d2c9..e6a8613fb 100644
--- a/kernel/arch/x86/include/asm/hugetlb.h
+++ b/kernel/arch/x86/include/asm/hugetlb.h
@@ -4,6 +4,7 @@
#include <asm/page.h>
#include <asm-generic/hugetlb.h>
+#define hugepages_supported() cpu_has_pse
static inline int is_hugepage_only_range(struct mm_struct *mm,
unsigned long addr,
diff --git a/kernel/arch/x86/include/asm/hw_irq.h b/kernel/arch/x86/include/asm/hw_irq.h
index 1e3408e88..59caa55fb 100644
--- a/kernel/arch/x86/include/asm/hw_irq.h
+++ b/kernel/arch/x86/include/asm/hw_irq.h
@@ -136,6 +136,7 @@ struct irq_alloc_info {
struct irq_cfg {
unsigned int dest_apicid;
u8 vector;
+ u8 old_vector;
};
extern struct irq_cfg *irq_cfg(unsigned int irq);
diff --git a/kernel/arch/x86/include/asm/kvm_host.h b/kernel/arch/x86/include/asm/kvm_host.h
index fe68e836e..2cf52f11a 100644
--- a/kernel/arch/x86/include/asm/kvm_host.h
+++ b/kernel/arch/x86/include/asm/kvm_host.h
@@ -41,7 +41,7 @@
#define KVM_PIO_PAGE_OFFSET 1
#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
-#define KVM_HALT_POLL_NS_DEFAULT 500000
+#define KVM_HALT_POLL_NS_DEFAULT 400000
#define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS
diff --git a/kernel/arch/x86/include/asm/microcode.h b/kernel/arch/x86/include/asm/microcode.h
index 34e62b1dc..712b24ed3 100644
--- a/kernel/arch/x86/include/asm/microcode.h
+++ b/kernel/arch/x86/include/asm/microcode.h
@@ -2,6 +2,7 @@
#define _ASM_X86_MICROCODE_H
#include <linux/earlycpio.h>
+#include <linux/initrd.h>
#define native_rdmsr(msr, val1, val2) \
do { \
@@ -168,4 +169,29 @@ static inline void reload_early_microcode(void) { }
static inline bool
get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; }
#endif
+
+static inline unsigned long get_initrd_start(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+ return initrd_start;
+#else
+ return 0;
+#endif
+}
+
+static inline unsigned long get_initrd_start_addr(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+#ifdef CONFIG_X86_32
+ unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+
+ return (unsigned long)__pa_nodebug(*initrd_start_p);
+#else
+ return get_initrd_start();
+#endif
+#else /* CONFIG_BLK_DEV_INITRD */
+ return 0;
+#endif
+}
+
#endif /* _ASM_X86_MICROCODE_H */
diff --git a/kernel/arch/x86/include/asm/mtrr.h b/kernel/arch/x86/include/asm/mtrr.h
index b94f6f64e..dbff1456d 100644
--- a/kernel/arch/x86/include/asm/mtrr.h
+++ b/kernel/arch/x86/include/asm/mtrr.h
@@ -24,6 +24,7 @@
#define _ASM_X86_MTRR_H
#include <uapi/asm/mtrr.h>
+#include <asm/pat.h>
/*
@@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
{
}
+static inline void mtrr_bp_init(void)
+{
+ pat_disable("MTRRs disabled, skipping PAT initialization too.");
+}
#define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
#define set_mtrr_aps_delayed_init() do {} while (0)
#define mtrr_aps_init() do {} while (0)
#define mtrr_bp_restore() do {} while (0)
diff --git a/kernel/arch/x86/include/asm/pat.h b/kernel/arch/x86/include/asm/pat.h
index ca6c228d5..0b1ff4c1c 100644
--- a/kernel/arch/x86/include/asm/pat.h
+++ b/kernel/arch/x86/include/asm/pat.h
@@ -5,8 +5,8 @@
#include <asm/pgtable_types.h>
bool pat_enabled(void);
+void pat_disable(const char *reason);
extern void pat_init(void);
-void pat_init_cache_modes(u64);
extern int reserve_memtype(u64 start, u64 end,
enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/kernel/arch/x86/include/asm/pci_x86.h b/kernel/arch/x86/include/asm/pci_x86.h
index fa1195dae..164e3f8d3 100644
--- a/kernel/arch/x86/include/asm/pci_x86.h
+++ b/kernel/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
extern int (*pcibios_enable_irq)(struct pci_dev *dev);
extern void (*pcibios_disable_irq)(struct pci_dev *dev);
+extern bool mp_should_keep_irq(struct device *dev);
+
struct pci_raw_ops {
int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
int reg, int len, u32 *val);
diff --git a/kernel/arch/x86/include/asm/perf_event.h b/kernel/arch/x86/include/asm/perf_event.h
index 7bcb861a0..5a2ed3ed2 100644
--- a/kernel/arch/x86/include/asm/perf_event.h
+++ b/kernel/arch/x86/include/asm/perf_event.h
@@ -165,6 +165,7 @@ struct x86_pmu_capability {
#define GLOBAL_STATUS_ASIF BIT_ULL(60)
#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59)
#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58)
+#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55)
/*
* IBS cpuid feature detection
diff --git a/kernel/arch/x86/include/asm/preempt.h b/kernel/arch/x86/include/asm/preempt.h
index 5dbd2d0f9..6f432adc5 100644
--- a/kernel/arch/x86/include/asm/preempt.h
+++ b/kernel/arch/x86/include/asm/preempt.h
@@ -89,6 +89,8 @@ static __always_inline bool __preempt_count_dec_and_test(void)
if (____preempt_count_dec_and_test())
return true;
#ifdef CONFIG_PREEMPT_LAZY
+ if (current_thread_info()->preempt_lazy_count)
+ return false;
return test_thread_flag(TIF_NEED_RESCHED_LAZY);
#else
return false;
@@ -101,8 +103,19 @@ static __always_inline bool __preempt_count_dec_and_test(void)
static __always_inline bool should_resched(int preempt_offset)
{
#ifdef CONFIG_PREEMPT_LAZY
- return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset ||
- test_thread_flag(TIF_NEED_RESCHED_LAZY));
+ u32 tmp;
+
+ tmp = raw_cpu_read_4(__preempt_count);
+ if (tmp == preempt_offset)
+ return true;
+
+ /* preempt count == 0 ? */
+ tmp &= ~PREEMPT_NEED_RESCHED;
+ if (tmp)
+ return false;
+ if (current_thread_info()->preempt_lazy_count)
+ return false;
+ return test_thread_flag(TIF_NEED_RESCHED_LAZY);
#else
return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
#endif
diff --git a/kernel/arch/x86/include/asm/pvclock.h b/kernel/arch/x86/include/asm/pvclock.h
index 7a6bed5c0..baad72e4c 100644
--- a/kernel/arch/x86/include/asm/pvclock.h
+++ b/kernel/arch/x86/include/asm/pvclock.h
@@ -76,6 +76,8 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
u8 ret_flags;
version = src->version;
+ /* Make the latest version visible */
+ smp_rmb();
offset = pvclock_get_nsec_offset(src);
ret = src->system_time + offset;
diff --git a/kernel/arch/x86/include/asm/tlbflush.h b/kernel/arch/x86/include/asm/tlbflush.h
index 6df202940..6433e28dc 100644
--- a/kernel/arch/x86/include/asm/tlbflush.h
+++ b/kernel/arch/x86/include/asm/tlbflush.h
@@ -32,7 +32,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
/* Initialize cr4 shadow for this CPU. */
static inline void cr4_init_shadow(void)
{
- this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
+ this_cpu_write(cpu_tlbstate.cr4, __read_cr4_safe());
}
/* Set in this cpu's CR4. */
@@ -86,7 +86,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
static inline void __native_flush_tlb(void)
{
+ /*
+ * If current->mm == NULL then we borrow a mm which may change during a
+ * task switch and therefore we must not be preempted while we write CR3
+ * back:
+ */
+ preempt_disable();
native_write_cr3(native_read_cr3());
+ preempt_enable();
}
static inline void __native_flush_tlb_global_irq_disabled(void)
diff --git a/kernel/arch/x86/include/asm/uaccess.h b/kernel/arch/x86/include/asm/uaccess.h
index 09b1b0ab9..b8c75f3aa 100644
--- a/kernel/arch/x86/include/asm/uaccess.h
+++ b/kernel/arch/x86/include/asm/uaccess.h
@@ -332,7 +332,7 @@ do { \
#define __get_user_asm_u64(x, ptr, retval, errret) \
__get_user_asm(x, ptr, retval, "q", "", "=r", errret)
#define __get_user_asm_ex_u64(x, ptr) \
- __get_user_asm_ex(x, ptr, "q", "", "=r")
+ __get_user_asm_ex(x, ptr, "q", "", "=&r")
#endif
#define __get_user_size(x, ptr, size, retval, errret) \
@@ -375,13 +375,13 @@ do { \
__chk_user_ptr(ptr); \
switch (size) { \
case 1: \
- __get_user_asm_ex(x, ptr, "b", "b", "=q"); \
+ __get_user_asm_ex(x, ptr, "b", "b", "=&q"); \
break; \
case 2: \
- __get_user_asm_ex(x, ptr, "w", "w", "=r"); \
+ __get_user_asm_ex(x, ptr, "w", "w", "=&r"); \
break; \
case 4: \
- __get_user_asm_ex(x, ptr, "l", "k", "=r"); \
+ __get_user_asm_ex(x, ptr, "l", "k", "=&r"); \
break; \
case 8: \
__get_user_asm_ex_u64(x, ptr); \
@@ -395,7 +395,7 @@ do { \
asm volatile("1: mov"itype" %1,%"rtype"0\n" \
"2:\n" \
_ASM_EXTABLE_EX(1b, 2b) \
- : ltype(x) : "m" (__m(addr)))
+ : ltype(x) : "m" (__m(addr)), "0" (0))
#define __put_user_nocheck(x, ptr, size) \
({ \
diff --git a/kernel/arch/x86/include/asm/xen/hypervisor.h b/kernel/arch/x86/include/asm/xen/hypervisor.h
index 8b2d4bea9..39171b364 100644
--- a/kernel/arch/x86/include/asm/xen/hypervisor.h
+++ b/kernel/arch/x86/include/asm/xen/hypervisor.h
@@ -62,4 +62,6 @@ void xen_arch_register_cpu(int num);
void xen_arch_unregister_cpu(int num);
#endif
+extern void xen_set_iopl_mask(unsigned mask);
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/kernel/arch/x86/kernel/acpi/boot.c b/kernel/arch/x86/kernel/acpi/boot.c
index e75907601..a29fc4f84 100644
--- a/kernel/arch/x86/kernel/acpi/boot.c
+++ b/kernel/arch/x86/kernel/acpi/boot.c
@@ -87,7 +87,9 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
* ->ioapic_mutex
* ->ioapic_lock
*/
+#ifdef CONFIG_X86_IO_APIC
static DEFINE_MUTEX(acpi_ioapic_lock);
+#endif
/* --------------------------------------------------------------------------
Boot-time Configuration
diff --git a/kernel/arch/x86/kernel/amd_nb.c b/kernel/arch/x86/kernel/amd_nb.c
index 29fa475ec..c986d0b3b 100644
--- a/kernel/arch/x86/kernel/amd_nb.c
+++ b/kernel/arch/x86/kernel/amd_nb.c
@@ -71,8 +71,8 @@ int amd_cache_northbridges(void)
while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
i++;
- if (i == 0)
- return 0;
+ if (!i)
+ return -ENODEV;
nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
if (!nb)
diff --git a/kernel/arch/x86/kernel/apic/apic.c b/kernel/arch/x86/kernel/apic/apic.c
index 58e7cdb25..042e744ef 100644
--- a/kernel/arch/x86/kernel/apic/apic.c
+++ b/kernel/arch/x86/kernel/apic/apic.c
@@ -1611,6 +1611,9 @@ void __init enable_IR_x2apic(void)
unsigned long flags;
int ret, ir_stat;
+ if (skip_ioapic_setup)
+ return;
+
ir_stat = irq_remapping_prepare();
if (ir_stat < 0 && !x2apic_supported())
return;
diff --git a/kernel/arch/x86/kernel/apic/io_apic.c b/kernel/arch/x86/kernel/apic/io_apic.c
index 678c711e2..7bfb53808 100644
--- a/kernel/arch/x86/kernel/apic/io_apic.c
+++ b/kernel/arch/x86/kernel/apic/io_apic.c
@@ -2116,6 +2116,7 @@ static inline void __init check_timer(void)
if (idx != -1 && irq_trigger(idx))
unmask_ioapic_irq(irq_get_chip_data(0));
}
+ irq_domain_deactivate_irq(irq_data);
irq_domain_activate_irq(irq_data);
if (timer_irq_works()) {
if (disable_timer_pin_1 > 0)
@@ -2137,6 +2138,7 @@ static inline void __init check_timer(void)
* legacy devices should be connected to IO APIC #0
*/
replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+ irq_domain_deactivate_irq(irq_data);
irq_domain_activate_irq(irq_data);
legacy_pic->unmask(0);
if (timer_irq_works()) {
diff --git a/kernel/arch/x86/kernel/apic/vector.c b/kernel/arch/x86/kernel/apic/vector.c
index a35f6b547..0988e204f 100644
--- a/kernel/arch/x86/kernel/apic/vector.c
+++ b/kernel/arch/x86/kernel/apic/vector.c
@@ -211,6 +211,7 @@ update:
*/
cpumask_and(d->old_domain, d->old_domain, cpu_online_mask);
d->move_in_progress = !cpumask_empty(d->old_domain);
+ d->cfg.old_vector = d->move_in_progress ? d->cfg.vector : 0;
d->cfg.vector = vector;
cpumask_copy(d->domain, vector_cpumask);
success:
@@ -253,7 +254,8 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
struct irq_desc *desc;
int cpu, vector;
- BUG_ON(!data->cfg.vector);
+ if (!data->cfg.vector)
+ return;
vector = data->cfg.vector;
for_each_cpu_and(cpu, data->domain, cpu_online_mask)
@@ -653,46 +655,114 @@ void irq_complete_move(struct irq_cfg *cfg)
}
/*
- * Called with @desc->lock held and interrupts disabled.
+ * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
*/
void irq_force_complete_move(struct irq_desc *desc)
{
- struct irq_data *irqdata = irq_desc_get_irq_data(desc);
- struct apic_chip_data *data = apic_chip_data(irqdata);
- struct irq_cfg *cfg = data ? &data->cfg : NULL;
+ struct irq_data *irqdata;
+ struct apic_chip_data *data;
+ struct irq_cfg *cfg;
+ unsigned int cpu;
- if (!cfg)
+ /*
+ * The function is called for all descriptors regardless of which
+ * irqdomain they belong to. For example if an IRQ is provided by
+ * an irq_chip as part of a GPIO driver, the chip data for that
+ * descriptor is specific to the irq_chip in question.
+ *
+ * Check first that the chip_data is what we expect
+ * (apic_chip_data) before touching it any further.
+ */
+ irqdata = irq_domain_get_irq_data(x86_vector_domain,
+ irq_desc_get_irq(desc));
+ if (!irqdata)
return;
- __irq_complete_move(cfg, cfg->vector);
+ data = apic_chip_data(irqdata);
+ cfg = data ? &data->cfg : NULL;
+
+ if (!cfg)
+ return;
/*
* This is tricky. If the cleanup of @data->old_domain has not been
* done yet, then the following setaffinity call will fail with
* -EBUSY. This can leave the interrupt in a stale state.
*
- * The cleanup cannot make progress because we hold @desc->lock. So in
- * case @data->old_domain is not yet cleaned up, we need to drop the
- * lock and acquire it again. @desc cannot go away, because the
- * hotplug code holds the sparse irq lock.
+ * All CPUs are stuck in stop machine with interrupts disabled so
+ * calling __irq_complete_move() would be completely pointless.
*/
raw_spin_lock(&vector_lock);
- /* Clean out all offline cpus (including ourself) first. */
+ /*
+ * Clean out all offline cpus (including the outgoing one) from the
+ * old_domain mask.
+ */
cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
- while (!cpumask_empty(data->old_domain)) {
+
+ /*
+ * If move_in_progress is cleared and the old_domain mask is empty,
+ * then there is nothing to cleanup. fixup_irqs() will take care of
+ * the stale vectors on the outgoing cpu.
+ */
+ if (!data->move_in_progress && cpumask_empty(data->old_domain)) {
raw_spin_unlock(&vector_lock);
- raw_spin_unlock(&desc->lock);
- cpu_relax();
- raw_spin_lock(&desc->lock);
+ return;
+ }
+
+ /*
+ * 1) The interrupt is in move_in_progress state. That means that we
+ * have not seen an interrupt since the io_apic was reprogrammed to
+ * the new vector.
+ *
+ * 2) The interrupt has fired on the new vector, but the cleanup IPIs
+ * have not been processed yet.
+ */
+ if (data->move_in_progress) {
/*
- * Reevaluate apic_chip_data. It might have been cleared after
- * we dropped @desc->lock.
+ * In theory there is a race:
+ *
+ * set_ioapic(new_vector) <-- Interrupt is raised before update
+ * is effective, i.e. it's raised on
+ * the old vector.
+ *
+ * So if the target cpu cannot handle that interrupt before
+ * the old vector is cleaned up, we get a spurious interrupt
+ * and in the worst case the ioapic irq line becomes stale.
+ *
+ * But in case of cpu hotplug this should be a non issue
+ * because if the affinity update happens right before all
+ * cpus rendevouz in stop machine, there is no way that the
+ * interrupt can be blocked on the target cpu because all cpus
+ * loops first with interrupts enabled in stop machine, so the
+ * old vector is not yet cleaned up when the interrupt fires.
+ *
+ * So the only way to run into this issue is if the delivery
+ * of the interrupt on the apic/system bus would be delayed
+ * beyond the point where the target cpu disables interrupts
+ * in stop machine. I doubt that it can happen, but at least
+ * there is a theroretical chance. Virtualization might be
+ * able to expose this, but AFAICT the IOAPIC emulation is not
+ * as stupid as the real hardware.
+ *
+ * Anyway, there is nothing we can do about that at this point
+ * w/o refactoring the whole fixup_irq() business completely.
+ * We print at least the irq number and the old vector number,
+ * so we have the necessary information when a problem in that
+ * area arises.
*/
- data = apic_chip_data(irqdata);
- if (!data)
- return;
- raw_spin_lock(&vector_lock);
+ pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
+ irqdata->irq, cfg->old_vector);
}
+ /*
+ * If old_domain is not empty, then other cpus still have the irq
+ * descriptor set in their vector array. Clean it up.
+ */
+ for_each_cpu(cpu, data->old_domain)
+ per_cpu(vector_irq, cpu)[cfg->old_vector] = VECTOR_UNUSED;
+
+ /* Cleanup the left overs of the (half finished) move */
+ cpumask_clear(data->old_domain);
+ data->move_in_progress = 0;
raw_spin_unlock(&vector_lock);
}
#endif
diff --git a/kernel/arch/x86/kernel/cpu/amd.c b/kernel/arch/x86/kernel/cpu/amd.c
index a8816b325..e2defc759 100644
--- a/kernel/arch/x86/kernel/cpu/amd.c
+++ b/kernel/arch/x86/kernel/cpu/amd.c
@@ -352,7 +352,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
- unsigned int socket_id, core_complex_id;
bits = c->x86_coreid_bits;
/* Low order bits define the core id (index of core in socket) */
@@ -370,10 +369,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
return;
- socket_id = (c->apicid >> bits) - 1;
- core_complex_id = (c->apicid & ((1 << bits) - 1)) >> 3;
-
- per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
#endif
}
@@ -656,6 +652,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
}
+#define MSR_AMD64_DE_CFG 0xC0011029
+
+static void init_amd_ln(struct cpuinfo_x86 *c)
+{
+ /*
+ * Apply erratum 665 fix unconditionally so machines without a BIOS
+ * fix work.
+ */
+ msr_set_bit(MSR_AMD64_DE_CFG, 31);
+}
+
static void init_amd_bd(struct cpuinfo_x86 *c)
{
u64 value;
@@ -713,6 +720,7 @@ static void init_amd(struct cpuinfo_x86 *c)
case 6: init_amd_k7(c); break;
case 0xf: init_amd_k8(c); break;
case 0x10: init_amd_gh(c); break;
+ case 0x12: init_amd_ln(c); break;
case 0x15: init_amd_bd(c); break;
}
diff --git a/kernel/arch/x86/kernel/cpu/common.c b/kernel/arch/x86/kernel/cpu/common.c
index c2b7522cb..637ca414d 100644
--- a/kernel/arch/x86/kernel/cpu/common.c
+++ b/kernel/arch/x86/kernel/cpu/common.c
@@ -737,21 +737,20 @@ 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;
+ if (have_cpuid_p()) {
+ cpu_detect(c);
+ get_cpu_vendor(c);
+ get_cpu_cap(c);
- 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);
@@ -1130,7 +1129,7 @@ static __init int setup_disablecpuid(char *arg)
{
int bit;
- if (get_option(&arg, &bit) && bit < NCAPINTS*32)
+ if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32)
setup_clear_cpu_cap(bit);
else
return 0;
diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/kernel/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 0a850100c..2658e2af7 100644
--- a/kernel/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/kernel/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -29,7 +29,7 @@ static char gen_pool_buf[MCE_POOLSZ];
void mce_gen_pool_process(void)
{
struct llist_node *head;
- struct mce_evt_llist *node;
+ struct mce_evt_llist *node, *tmp;
struct mce *mce;
head = llist_del_all(&mce_event_llist);
@@ -37,7 +37,7 @@ void mce_gen_pool_process(void)
return;
head = llist_reverse_order(head);
- llist_for_each_entry(node, head, llnode) {
+ llist_for_each_entry_safe(node, tmp, head, llnode) {
mce = &node->mce;
atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce.c b/kernel/arch/x86/kernel/cpu/mcheck/mce.c
index a080b4939..430a4ec07 100644
--- a/kernel/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/kernel/arch/x86/kernel/cpu/mcheck/mce.c
@@ -42,7 +42,7 @@
#include <linux/irq_work.h>
#include <linux/export.h>
#include <linux/jiffies.h>
-#include <linux/work-simple.h>
+#include <linux/swork.h>
#include <asm/processor.h>
#include <asm/traps.h>
diff --git a/kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c b/kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 2c5aaf8c2..05538582a 100644
--- a/kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -385,6 +385,9 @@ static void intel_thermal_interrupt(void)
{
__u64 msr_val;
+ if (static_cpu_has(X86_FEATURE_HWP))
+ wrmsrl_safe(MSR_HWP_STATUS, 0);
+
rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
/* Check for violation of core thermal thresholds*/
diff --git a/kernel/arch/x86/kernel/cpu/microcode/intel.c b/kernel/arch/x86/kernel/cpu/microcode/intel.c
index ce47402eb..ac8975a65 100644
--- a/kernel/arch/x86/kernel/cpu/microcode/intel.c
+++ b/kernel/arch/x86/kernel/cpu/microcode/intel.c
@@ -555,10 +555,14 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
cd.data = NULL;
cd.size = 0;
- cd = find_cpio_data(p, (void *)start, size, &offset);
- if (!cd.data) {
+ /* try built-in microcode if no initrd */
+ if (!size) {
if (!load_builtin_intel_microcode(&cd))
return UCODE_ERROR;
+ } else {
+ cd = find_cpio_data(p, (void *)start, size, &offset);
+ if (!cd.data)
+ return UCODE_ERROR;
}
return get_matching_model_microcode(0, start, cd.data, cd.size,
@@ -694,7 +698,7 @@ int __init save_microcode_in_initrd_intel(void)
if (count == 0)
return ret;
- copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count);
+ copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, get_initrd_start(), count);
ret = save_microcode(&mc_saved_data, mc_saved, count);
if (ret)
pr_err("Cannot save microcode patches from initrd.\n");
@@ -732,16 +736,20 @@ void __init load_ucode_intel_bsp(void)
struct boot_params *p;
p = (struct boot_params *)__pa_nodebug(&boot_params);
- start = p->hdr.ramdisk_image;
size = p->hdr.ramdisk_size;
- _load_ucode_intel_bsp(
- (struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
- (unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
- start, size);
+ /*
+ * Set start only if we have an initrd image. We cannot use initrd_start
+ * because it is not set that early yet.
+ */
+ start = (size ? p->hdr.ramdisk_image : 0);
+
+ _load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
+ (unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
+ start, size);
#else
- start = boot_params.hdr.ramdisk_image + PAGE_OFFSET;
size = boot_params.hdr.ramdisk_size;
+ start = (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0);
_load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size);
#endif
@@ -752,20 +760,14 @@ void load_ucode_intel_ap(void)
struct mc_saved_data *mc_saved_data_p;
struct ucode_cpu_info uci;
unsigned long *mc_saved_in_initrd_p;
- unsigned long initrd_start_addr;
enum ucode_state ret;
#ifdef CONFIG_X86_32
- unsigned long *initrd_start_p;
- mc_saved_in_initrd_p =
- (unsigned long *)__pa_nodebug(mc_saved_in_initrd);
+ mc_saved_in_initrd_p = (unsigned long *)__pa_nodebug(mc_saved_in_initrd);
mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
- initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
- initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
#else
- mc_saved_data_p = &mc_saved_data;
mc_saved_in_initrd_p = mc_saved_in_initrd;
- initrd_start_addr = initrd_start;
+ mc_saved_data_p = &mc_saved_data;
#endif
/*
@@ -777,7 +779,7 @@ void load_ucode_intel_ap(void)
collect_cpu_info_early(&uci);
ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
- initrd_start_addr, &uci);
+ get_initrd_start_addr(), &uci);
if (ret != UCODE_OK)
return;
diff --git a/kernel/arch/x86/kernel/cpu/mshyperv.c b/kernel/arch/x86/kernel/cpu/mshyperv.c
index 20e242ea1..cfc4a966e 100644
--- a/kernel/arch/x86/kernel/cpu/mshyperv.c
+++ b/kernel/arch/x86/kernel/cpu/mshyperv.c
@@ -152,6 +152,11 @@ static struct clocksource hyperv_cs = {
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
+static unsigned char hv_get_nmi_reason(void)
+{
+ return 0;
+}
+
static void __init ms_hyperv_init_platform(void)
{
/*
@@ -191,6 +196,13 @@ static void __init ms_hyperv_init_platform(void)
machine_ops.crash_shutdown = hv_machine_crash_shutdown;
#endif
mark_tsc_unstable("running on Hyper-V");
+
+ /*
+ * Generation 2 instances don't support reading the NMI status from
+ * 0x61 port.
+ */
+ if (efi_enabled(EFI_BOOT))
+ x86_platform.get_nmi_reason = hv_get_nmi_reason;
}
const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/kernel/arch/x86/kernel/cpu/mtrr/generic.c b/kernel/arch/x86/kernel/cpu/mtrr/generic.c
index 3b533cf37..b5624fafa 100644
--- a/kernel/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/kernel/arch/x86/kernel/cpu/mtrr/generic.c
@@ -444,11 +444,24 @@ static void __init print_mtrr_state(void)
pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20);
}
+/* PAT setup for BP. We need to go through sync steps here */
+void __init mtrr_bp_pat_init(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ prepare_set();
+
+ pat_init();
+
+ post_set();
+ local_irq_restore(flags);
+}
+
/* Grab all of the MTRR state for this CPU into *state */
bool __init get_mtrr_state(void)
{
struct mtrr_var_range *vrs;
- unsigned long flags;
unsigned lo, dummy;
unsigned int i;
@@ -481,15 +494,6 @@ bool __init get_mtrr_state(void)
mtrr_state_set = 1;
- /* PAT setup for BP. We need to go through sync steps here */
- local_irq_save(flags);
- prepare_set();
-
- pat_init();
-
- post_set();
- local_irq_restore(flags);
-
return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
}
diff --git a/kernel/arch/x86/kernel/cpu/mtrr/main.c b/kernel/arch/x86/kernel/cpu/mtrr/main.c
index f891b4750..fa77ac829 100644
--- a/kernel/arch/x86/kernel/cpu/mtrr/main.c
+++ b/kernel/arch/x86/kernel/cpu/mtrr/main.c
@@ -752,6 +752,9 @@ void __init mtrr_bp_init(void)
/* BIOS may override */
__mtrr_enabled = get_mtrr_state();
+ if (mtrr_enabled())
+ mtrr_bp_pat_init();
+
if (mtrr_cleanup(phys_addr)) {
changed_by_mtrr_cleanup = 1;
mtrr_if->set_all();
@@ -759,8 +762,16 @@ void __init mtrr_bp_init(void)
}
}
- if (!mtrr_enabled())
+ if (!mtrr_enabled()) {
pr_info("MTRR: Disabled\n");
+
+ /*
+ * PAT initialization relies on MTRR's rendezvous handler.
+ * Skip PAT init until the handler can initialize both
+ * features independently.
+ */
+ pat_disable("MTRRs disabled, skipping PAT initialization too.");
+ }
}
void mtrr_ap_init(void)
diff --git a/kernel/arch/x86/kernel/cpu/mtrr/mtrr.h b/kernel/arch/x86/kernel/cpu/mtrr/mtrr.h
index 951884dcc..6c7ced07d 100644
--- a/kernel/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/kernel/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
void fill_mtrr_var_range(unsigned int index,
u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
bool get_mtrr_state(void);
+void mtrr_bp_pat_init(void);
extern void set_mtrr_ops(const struct mtrr_ops *ops);
diff --git a/kernel/arch/x86/kernel/cpu/perf_event.c b/kernel/arch/x86/kernel/cpu/perf_event.c
index 2bf79d7c9..1a8256dd6 100644
--- a/kernel/arch/x86/kernel/cpu/perf_event.c
+++ b/kernel/arch/x86/kernel/cpu/perf_event.c
@@ -67,7 +67,7 @@ u64 x86_perf_event_update(struct perf_event *event)
int shift = 64 - x86_pmu.cntval_bits;
u64 prev_raw_count, new_raw_count;
int idx = hwc->idx;
- s64 delta;
+ u64 delta;
if (idx == INTEL_PMC_IDX_FIXED_BTS)
return 0;
@@ -593,6 +593,19 @@ void x86_pmu_disable_all(void)
}
}
+/*
+ * There may be PMI landing after enabled=0. The PMI hitting could be before or
+ * after disable_all.
+ *
+ * If PMI hits before disable_all, the PMU will be disabled in the NMI handler.
+ * It will not be re-enabled in the NMI handler again, because enabled=0. After
+ * handling the NMI, disable_all will be called, which will not change the
+ * state either. If PMI hits after disable_all, the PMU is already disabled
+ * before entering NMI handler. The NMI handler will not change the state
+ * either.
+ *
+ * So either situation is harmless.
+ */
static void x86_pmu_disable(struct pmu *pmu)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
diff --git a/kernel/arch/x86/kernel/cpu/perf_event.h b/kernel/arch/x86/kernel/cpu/perf_event.h
index d0e35ebb2..ee70445fb 100644
--- a/kernel/arch/x86/kernel/cpu/perf_event.h
+++ b/kernel/arch/x86/kernel/cpu/perf_event.h
@@ -591,6 +591,7 @@ struct x86_pmu {
pebs_active :1,
pebs_broken :1;
int pebs_record_size;
+ int pebs_buffer_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
@@ -907,6 +908,8 @@ void intel_pmu_lbr_init_hsw(void);
void intel_pmu_lbr_init_skl(void);
+void intel_pmu_pebs_data_source_nhm(void);
+
int intel_pmu_setup_lbr_filter(struct perf_event *event);
void intel_pt_interrupt(void);
diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel.c b/kernel/arch/x86/kernel/cpu/perf_event_intel.c
index e2a430021..5cc2242d7 100644
--- a/kernel/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/kernel/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1458,7 +1458,15 @@ static __initconst const u64 slm_hw_cache_event_ids
};
/*
- * Use from PMIs where the LBRs are already disabled.
+ * Used from PMIs where the LBRs are already disabled.
+ *
+ * This function could be called consecutively. It is required to remain in
+ * 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.
*/
static void __intel_pmu_disable_all(void)
{
@@ -1840,6 +1848,16 @@ again:
if (__test_and_clear_bit(62, (unsigned long *)&status)) {
handled++;
x86_pmu.drain_pebs(regs);
+ /*
+ * There are cases where, even though, the PEBS ovfl bit is set
+ * in GLOBAL_OVF_STATUS, the PEBS events may also have their
+ * overflow bits set for their counters. We must clear them
+ * here because they have been processed as exact samples in
+ * the drain_pebs() routine. They must not be processed again
+ * in the for_each_bit_set() loop for regular samples below.
+ */
+ status &= ~cpuc->pebs_enabled;
+ status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
}
/*
@@ -1885,7 +1903,10 @@ again:
goto again;
done:
- __intel_pmu_enable_all(0, true);
+ /* Only restore PMU state when it's active. See x86_pmu_disable(). */
+ if (cpuc->enabled)
+ __intel_pmu_enable_all(0, true);
+
/*
* Only unmask the NMI after the overflow counters
* have been reset. This avoids spurious NMIs on
@@ -3315,6 +3336,7 @@ __init int intel_pmu_init(void)
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
+ intel_pmu_pebs_data_source_nhm();
x86_add_quirk(intel_nehalem_quirk);
pr_cont("Nehalem events, ");
@@ -3377,6 +3399,7 @@ __init int intel_pmu_init(void)
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
+ intel_pmu_pebs_data_source_nhm();
pr_cont("Westmere events, ");
break;
@@ -3578,7 +3601,7 @@ __init int intel_pmu_init(void)
c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
}
c->idxmsk64 &=
- ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+ ~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
c->weight = hweight64(c->idxmsk64);
}
}
@@ -3613,7 +3636,7 @@ __init int intel_pmu_init(void)
/* Support full width counters using alternative MSR range */
if (x86_pmu.intel_cap.full_width_write) {
- x86_pmu.max_period = x86_pmu.cntval_mask;
+ x86_pmu.max_period = x86_pmu.cntval_mask >> 1;
x86_pmu.perfctr = MSR_IA32_PMC0;
pr_cont("full-width counters, ");
}
diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index a316ca96f..fc704ed58 100644
--- a/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -211,6 +211,20 @@ static void __put_rmid(u32 rmid)
list_add_tail(&entry->list, &cqm_rmid_limbo_lru);
}
+static void cqm_cleanup(void)
+{
+ int i;
+
+ if (!cqm_rmid_ptrs)
+ return;
+
+ for (i = 0; i < cqm_max_rmid; i++)
+ kfree(cqm_rmid_ptrs[i]);
+
+ kfree(cqm_rmid_ptrs);
+ cqm_rmid_ptrs = NULL;
+}
+
static int intel_cqm_setup_rmid_cache(void)
{
struct cqm_rmid_entry *entry;
@@ -218,7 +232,7 @@ static int intel_cqm_setup_rmid_cache(void)
int r = 0;
nr_rmids = cqm_max_rmid + 1;
- cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
+ cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) *
nr_rmids, GFP_KERNEL);
if (!cqm_rmid_ptrs)
return -ENOMEM;
@@ -249,11 +263,9 @@ static int intel_cqm_setup_rmid_cache(void)
mutex_unlock(&cache_mutex);
return 0;
-fail:
- while (r--)
- kfree(cqm_rmid_ptrs[r]);
- kfree(cqm_rmid_ptrs);
+fail:
+ cqm_cleanup();
return -ENOMEM;
}
@@ -281,9 +293,13 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
/*
* Events that target same task are placed into the same cache group.
+ * Mark it as a multi event group, so that we update ->count
+ * for every event rather than just the group leader later.
*/
- if (a->hw.target == b->hw.target)
+ if (a->hw.target == b->hw.target) {
+ b->hw.is_group_event = true;
return true;
+ }
/*
* Are we an inherited event?
@@ -849,6 +865,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
bool conflict = false;
u32 rmid;
+ event->hw.is_group_event = false;
list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
rmid = iter->hw.cqm_rmid;
@@ -940,7 +957,9 @@ static u64 intel_cqm_event_count(struct perf_event *event)
return __perf_event_count(event);
/*
- * Only the group leader gets to report values. This stops us
+ * Only the group leader gets to report values except in case of
+ * multiple events in the same group, we still need to read the
+ * other events.This stops us
* reporting duplicate values to userspace, and gives us a clear
* rule for which task gets to report the values.
*
@@ -948,7 +967,7 @@ static u64 intel_cqm_event_count(struct perf_event *event)
* specific packages - we forfeit that ability when we create
* task events.
*/
- if (!cqm_group_leader(event))
+ if (!cqm_group_leader(event) && !event->hw.is_group_event)
return 0;
/*
@@ -1315,7 +1334,7 @@ static const struct x86_cpu_id intel_cqm_match[] = {
static int __init intel_cqm_init(void)
{
- char *str, scale[20];
+ char *str = NULL, scale[20];
int i, cpu, ret;
if (!x86_match_cpu(intel_cqm_match))
@@ -1375,16 +1394,25 @@ static int __init intel_cqm_init(void)
cqm_pick_event_reader(i);
}
- __perf_cpu_notifier(intel_cqm_cpu_notifier);
-
ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
- if (ret)
+ if (ret) {
pr_err("Intel CQM perf registration failed: %d\n", ret);
- else
- pr_info("Intel CQM monitoring enabled\n");
+ goto out;
+ }
+
+ pr_info("Intel CQM monitoring enabled\n");
+ /*
+ * Register the hot cpu notifier once we are sure cqm
+ * is enabled to avoid notifier leak.
+ */
+ __perf_cpu_notifier(intel_cqm_cpu_notifier);
out:
cpu_notifier_register_done();
+ if (ret) {
+ kfree(str);
+ cqm_cleanup();
+ }
return ret;
}
diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5db1c7755..1e7de3cef 100644
--- a/kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -51,7 +51,8 @@ union intel_x86_pebs_dse {
#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
-static const u64 pebs_data_source[] = {
+/* Version for Sandy Bridge and later */
+static u64 pebs_data_source[] = {
P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */
OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */
@@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = {
OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
};
+/* Patch up minor differences in the bits */
+void __init intel_pmu_pebs_data_source_nhm(void)
+{
+ pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT);
+ pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM);
+ pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM);
+}
+
static u64 precise_store_data(u64 status)
{
union intel_x86_pebs_dse dse;
@@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu)
if (!x86_pmu.pebs)
return 0;
- buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
+ buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
if (unlikely(!buffer))
return -ENOMEM;
@@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu)
per_cpu(insn_buffer, cpu) = ibuffer;
}
- max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+ max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
ds->pebs_buffer_base = (u64)(unsigned long)buffer;
ds->pebs_index = ds->pebs_buffer_base;
@@ -1101,6 +1110,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
void *at;
u64 pebs_status;
+ /*
+ * fmt0 does not have a status bitfield (does not use
+ * perf_record_nhm format)
+ */
+ if (x86_pmu.intel_cap.pebs_format < 1)
+ return base;
+
if (base == NULL)
return NULL;
@@ -1186,7 +1202,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
if (!event->attr.precise_ip)
return;
- n = (top - at) / x86_pmu.pebs_record_size;
+ n = top - at;
if (n <= 0)
return;
@@ -1296,6 +1312,7 @@ void __init intel_ds_init(void)
x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+ x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
int format = x86_pmu.intel_cap.pebs_format;
@@ -1304,6 +1321,14 @@ void __init intel_ds_init(void)
case 0:
printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+ /*
+ * Using >PAGE_SIZE buffers makes the WRMSR to
+ * PERF_GLOBAL_CTRL in intel_pmu_enable_all()
+ * mysteriously hang on Core2.
+ *
+ * As a workaround, we don't do this.
+ */
+ x86_pmu.pebs_buffer_size = PAGE_SIZE;
x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
break;
diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 868e11943..49e35d003 100644
--- a/kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -694,6 +694,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
/* clear STOP and INT from current entry */
buf->topa_index[buf->stop_pos]->stop = 0;
+ buf->topa_index[buf->stop_pos]->intr = 0;
buf->topa_index[buf->intr_pos]->intr = 0;
/* how many pages till the STOP marker */
@@ -718,6 +719,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
buf->intr_pos = idx;
buf->topa_index[buf->stop_pos]->stop = 1;
+ buf->topa_index[buf->stop_pos]->intr = 1;
buf->topa_index[buf->intr_pos]->intr = 1;
return 0;
diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index ed446bdcb..d2ac364e2 100644
--- a/kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -117,7 +117,7 @@ static struct perf_pmu_events_attr event_attr_##v = { \
};
struct rapl_pmu {
- spinlock_t lock;
+ raw_spinlock_t lock;
int n_active; /* number of active events */
struct list_head active_list;
struct pmu *pmu; /* pointer to rapl_pmu_class */
@@ -220,13 +220,13 @@ static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
if (!pmu->n_active)
return HRTIMER_NORESTART;
- spin_lock_irqsave(&pmu->lock, flags);
+ raw_spin_lock_irqsave(&pmu->lock, flags);
list_for_each_entry(event, &pmu->active_list, active_entry) {
rapl_event_update(event);
}
- spin_unlock_irqrestore(&pmu->lock, flags);
+ raw_spin_unlock_irqrestore(&pmu->lock, flags);
hrtimer_forward_now(hrtimer, pmu->timer_interval);
@@ -263,9 +263,9 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode)
struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
unsigned long flags;
- spin_lock_irqsave(&pmu->lock, flags);
+ raw_spin_lock_irqsave(&pmu->lock, flags);
__rapl_pmu_event_start(pmu, event);
- spin_unlock_irqrestore(&pmu->lock, flags);
+ raw_spin_unlock_irqrestore(&pmu->lock, flags);
}
static void rapl_pmu_event_stop(struct perf_event *event, int mode)
@@ -274,7 +274,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
struct hw_perf_event *hwc = &event->hw;
unsigned long flags;
- spin_lock_irqsave(&pmu->lock, flags);
+ raw_spin_lock_irqsave(&pmu->lock, flags);
/* mark event as deactivated and stopped */
if (!(hwc->state & PERF_HES_STOPPED)) {
@@ -299,7 +299,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
hwc->state |= PERF_HES_UPTODATE;
}
- spin_unlock_irqrestore(&pmu->lock, flags);
+ raw_spin_unlock_irqrestore(&pmu->lock, flags);
}
static int rapl_pmu_event_add(struct perf_event *event, int mode)
@@ -308,14 +308,14 @@ static int rapl_pmu_event_add(struct perf_event *event, int mode)
struct hw_perf_event *hwc = &event->hw;
unsigned long flags;
- spin_lock_irqsave(&pmu->lock, flags);
+ raw_spin_lock_irqsave(&pmu->lock, flags);
hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
if (mode & PERF_EF_START)
__rapl_pmu_event_start(pmu, event);
- spin_unlock_irqrestore(&pmu->lock, flags);
+ raw_spin_unlock_irqrestore(&pmu->lock, flags);
return 0;
}
@@ -603,7 +603,7 @@ static int rapl_cpu_prepare(int cpu)
pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
if (!pmu)
return -1;
- spin_lock_init(&pmu->lock);
+ raw_spin_lock_init(&pmu->lock);
INIT_LIST_HEAD(&pmu->active_list);
diff --git a/kernel/arch/x86/kernel/cpu/perf_event_knc.c b/kernel/arch/x86/kernel/cpu/perf_event_knc.c
index 5b0c232d1..b931095e8 100644
--- a/kernel/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/kernel/arch/x86/kernel/cpu/perf_event_knc.c
@@ -263,7 +263,9 @@ again:
goto again;
done:
- knc_pmu_enable_all(0);
+ /* Only restore PMU state when it's active. See x86_pmu_disable(). */
+ if (cpuc->enabled)
+ knc_pmu_enable_all(0);
return handled;
}
diff --git a/kernel/arch/x86/kernel/e820.c b/kernel/arch/x86/kernel/e820.c
index 569c1e4f9..52a2526c3 100644
--- a/kernel/arch/x86/kernel/e820.c
+++ b/kernel/arch/x86/kernel/e820.c
@@ -753,7 +753,7 @@ 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;
@@ -764,11 +764,7 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn)
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;
@@ -793,12 +789,12 @@ 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)
diff --git a/kernel/arch/x86/kernel/early-quirks.c b/kernel/arch/x86/kernel/early-quirks.c
index db9a675e7..a257d6077 100644
--- a/kernel/arch/x86/kernel/early-quirks.c
+++ b/kernel/arch/x86/kernel/early-quirks.c
@@ -11,7 +11,11 @@
#include <linux/pci.h>
#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
#include <linux/pci_ids.h>
+#include <linux/bcma/bcma.h>
+#include <linux/bcma/bcma_regs.h>
#include <drm/i915_drm.h>
#include <asm/pci-direct.h>
#include <asm/dma.h>
@@ -21,6 +25,9 @@
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/irq_remapping.h>
+#include <asm/early_ioremap.h>
+
+#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg)
static void __init fix_hypertransport_config(int num, int slot, int func)
{
@@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func)
#ifdef CONFIG_ACPI
#ifdef CONFIG_X86_IO_APIC
/*
+ * Only applies to Nvidia root ports (bus 0) and not to
+ * Nvidia graphics cards with PCI ports on secondary buses.
+ */
+ if (num)
+ return;
+
+ /*
* All timer overrides on Nvidia are
* wrong unless HPET is enabled.
* Unfortunately that's not true on many Asus boards.
@@ -317,12 +331,11 @@ static u32 __init i85x_stolen_base(int num, int slot, int func, size_t stolen_si
static u32 __init i865_stolen_base(int num, int slot, int func, size_t stolen_size)
{
- /*
- * FIXME is the graphics stolen memory region
- * always at TOUD? Ie. is it always the last
- * one to be allocated by the BIOS?
- */
- return read_pci_config_16(0, 0, 0, I865_TOUD) << 16;
+ u16 toud = 0;
+
+ toud = read_pci_config_16(0, 0, 0, I865_TOUD);
+
+ return (phys_addr_t)(toud << 16) + i845_tseg_size();
}
static size_t __init i830_stolen_size(int num, int slot, int func)
@@ -589,6 +602,61 @@ static void __init force_disable_hpet(int num, int slot, int func)
#endif
}
+#define BCM4331_MMIO_SIZE 16384
+#define BCM4331_PM_CAP 0x40
+#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg)
+#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg)
+
+static void __init apple_airport_reset(int bus, int slot, int func)
+{
+ void __iomem *mmio;
+ u16 pmcsr;
+ u64 addr;
+ int i;
+
+ if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc."))
+ return;
+
+ /* Card may have been put into PCI_D3hot by grub quirk */
+ pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+
+ if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+ pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
+ write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr);
+ mdelay(10);
+
+ pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+ if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+ dev_err("Cannot power up Apple AirPort card\n");
+ return;
+ }
+ }
+
+ addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0);
+ addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32;
+ addr &= PCI_BASE_ADDRESS_MEM_MASK;
+
+ mmio = early_ioremap(addr, BCM4331_MMIO_SIZE);
+ if (!mmio) {
+ dev_err("Cannot iomap Apple AirPort card\n");
+ return;
+ }
+
+ pr_info("Resetting Apple AirPort card (left enabled by EFI)\n");
+
+ for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++)
+ udelay(10);
+
+ bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET);
+ bcma_aread32(BCMA_RESET_CTL);
+ udelay(1);
+
+ bcma_awrite32(BCMA_RESET_CTL, 0);
+ bcma_aread32(BCMA_RESET_CTL);
+ udelay(10);
+
+ early_iounmap(mmio, BCM4331_MMIO_SIZE);
+}
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
@@ -602,12 +670,6 @@ struct chipset {
void (*f)(int num, int slot, int func);
};
-/*
- * Only works for devices on the root bus. If you add any devices
- * not on bus 0 readd another loop level in early_quirks(). But
- * be careful because at least the Nvidia quirk here relies on
- * only matching on bus 0.
- */
static struct chipset early_qrk[] __initdata = {
{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
@@ -637,9 +699,13 @@ static struct chipset early_qrk[] __initdata = {
*/
{ PCI_VENDOR_ID_INTEL, 0x0f00,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+ { PCI_VENDOR_ID_BROADCOM, 0x4331,
+ PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
{}
};
+static void __init early_pci_scan_bus(int bus);
+
/**
* check_dev_quirk - apply early quirks to a given PCI device
* @num: bus number
@@ -648,7 +714,7 @@ static struct chipset early_qrk[] __initdata = {
*
* Check the vendor & device ID against the early quirks table.
*
- * If the device is single function, let early_quirks() know so we don't
+ * If the device is single function, let early_pci_scan_bus() know so we don't
* poke at this device again.
*/
static int __init check_dev_quirk(int num, int slot, int func)
@@ -657,6 +723,7 @@ static int __init check_dev_quirk(int num, int slot, int func)
u16 vendor;
u16 device;
u8 type;
+ u8 sec;
int i;
class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE);
@@ -684,25 +751,36 @@ static int __init check_dev_quirk(int num, int slot, int func)
type = read_pci_config_byte(num, slot, func,
PCI_HEADER_TYPE);
+
+ if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) {
+ sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS);
+ if (sec > num)
+ early_pci_scan_bus(sec);
+ }
+
if (!(type & 0x80))
return -1;
return 0;
}
-void __init early_quirks(void)
+static void __init early_pci_scan_bus(int bus)
{
int slot, func;
- if (!early_pci_allowed())
- return;
-
/* Poor man's PCI discovery */
- /* Only scan the root bus */
for (slot = 0; slot < 32; slot++)
for (func = 0; func < 8; func++) {
/* Only probe function 0 on single fn devices */
- if (check_dev_quirk(0, slot, func))
+ if (check_dev_quirk(bus, slot, func))
break;
}
}
+
+void __init early_quirks(void)
+{
+ if (!early_pci_allowed())
+ return;
+
+ early_pci_scan_bus(0);
+}
diff --git a/kernel/arch/x86/kernel/head_32.S b/kernel/arch/x86/kernel/head_32.S
index 6bc9ae24b..8f1a3f443 100644
--- a/kernel/arch/x86/kernel/head_32.S
+++ b/kernel/arch/x86/kernel/head_32.S
@@ -571,7 +571,7 @@ early_idt_handler_common:
movl %eax,%ds
movl %eax,%es
- cmpl $(__KERNEL_CS),32(%esp)
+ cmpw $(__KERNEL_CS),32(%esp)
jne 10f
leal 28(%esp),%eax # Pointer to %eip
diff --git a/kernel/arch/x86/kernel/hpet.c b/kernel/arch/x86/kernel/hpet.c
index b8e6ff5cd..acc9b8f19 100644
--- a/kernel/arch/x86/kernel/hpet.c
+++ b/kernel/arch/x86/kernel/hpet.c
@@ -351,6 +351,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
} else {
struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+ irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
disable_irq(hdev->irq);
irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
diff --git a/kernel/arch/x86/kernel/ioport.c b/kernel/arch/x86/kernel/ioport.c
index 37dae792d..589b3193f 100644
--- a/kernel/arch/x86/kernel/ioport.c
+++ b/kernel/arch/x86/kernel/ioport.c
@@ -96,9 +96,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
SYSCALL_DEFINE1(iopl, unsigned int, level)
{
struct pt_regs *regs = current_pt_regs();
- unsigned int old = (regs->flags >> 12) & 3;
struct thread_struct *t = &current->thread;
+ /*
+ * Careful: the IOPL bits in regs->flags are undefined under Xen PV
+ * and changing them has no effect.
+ */
+ unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT;
+
if (level > 3)
return -EINVAL;
/* Trying to gain more privileges? */
@@ -106,8 +111,9 @@ SYSCALL_DEFINE1(iopl, unsigned int, level)
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
}
- regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12);
- t->iopl = level << 12;
+ regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) |
+ (level << X86_EFLAGS_IOPL_BIT);
+ t->iopl = level << X86_EFLAGS_IOPL_BIT;
set_iopl_mask(t->iopl);
return 0;
diff --git a/kernel/arch/x86/kernel/kprobes/core.c b/kernel/arch/x86/kernel/kprobes/core.c
index 1deffe6cc..023c442c3 100644
--- a/kernel/arch/x86/kernel/kprobes/core.c
+++ b/kernel/arch/x86/kernel/kprobes/core.c
@@ -959,7 +959,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
* normal page fault.
*/
regs->ip = (unsigned long)cur->addr;
+ /*
+ * Trap flag (TF) has been set here because this fault
+ * happened where the single stepping will be done.
+ * So clear it by resetting the current kprobe:
+ */
+ regs->flags &= ~X86_EFLAGS_TF;
+
+ /*
+ * If the TF flag was set before the kprobe hit,
+ * don't touch it:
+ */
regs->flags |= kcb->kprobe_old_flags;
+
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
else
diff --git a/kernel/arch/x86/kernel/mcount_64.S b/kernel/arch/x86/kernel/mcount_64.S
index 87e1762e2..5d9afbcb6 100644
--- a/kernel/arch/x86/kernel/mcount_64.S
+++ b/kernel/arch/x86/kernel/mcount_64.S
@@ -180,7 +180,8 @@ GLOBAL(ftrace_graph_call)
jmp ftrace_stub
#endif
-GLOBAL(ftrace_stub)
+/* This is weak to keep gas from relaxing the jumps */
+WEAK(ftrace_stub)
retq
END(ftrace_caller)
diff --git a/kernel/arch/x86/kernel/nmi.c b/kernel/arch/x86/kernel/nmi.c
index 697f90db0..424aec4a4 100644
--- a/kernel/arch/x86/kernel/nmi.c
+++ b/kernel/arch/x86/kernel/nmi.c
@@ -231,7 +231,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
#endif
if (panic_on_unrecovered_nmi)
- panic("NMI: Not continuing");
+ nmi_panic(regs, "NMI: Not continuing");
pr_emerg("Dazed and confused, but trying to continue\n");
@@ -255,8 +255,16 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
reason, smp_processor_id());
show_regs(regs);
- if (panic_on_io_nmi)
- panic("NMI IOCK error: Not continuing");
+ if (panic_on_io_nmi) {
+ nmi_panic(regs, "NMI IOCK error: Not continuing");
+
+ /*
+ * If we end up here, it means we have received an NMI while
+ * processing panic(). Simply return without delaying and
+ * re-enabling NMIs.
+ */
+ return;
+ }
/* Re-enable the IOCK line, wait for a few seconds */
reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
@@ -297,7 +305,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
pr_emerg("Do you have a strange power saving mode enabled?\n");
if (unknown_nmi_panic || panic_on_unrecovered_nmi)
- panic("NMI: Not continuing");
+ nmi_panic(regs, "NMI: Not continuing");
pr_emerg("Dazed and confused, but trying to continue\n");
}
diff --git a/kernel/arch/x86/kernel/paravirt.c b/kernel/arch/x86/kernel/paravirt.c
index c2130aef3..f534a0e3a 100644
--- a/kernel/arch/x86/kernel/paravirt.c
+++ b/kernel/arch/x86/kernel/paravirt.c
@@ -55,12 +55,12 @@ asm (".pushsection .entry.text, \"ax\"\n"
".popsection");
/* identity function, which can be inlined */
-u32 _paravirt_ident_32(u32 x)
+u32 notrace _paravirt_ident_32(u32 x)
{
return x;
}
-u64 _paravirt_ident_64(u64 x)
+u64 notrace _paravirt_ident_64(u64 x)
{
return x;
}
diff --git a/kernel/arch/x86/kernel/process_64.c b/kernel/arch/x86/kernel/process_64.c
index e835d263a..4cbb60fbf 100644
--- a/kernel/arch/x86/kernel/process_64.c
+++ b/kernel/arch/x86/kernel/process_64.c
@@ -48,6 +48,7 @@
#include <asm/syscalls.h>
#include <asm/debugreg.h>
#include <asm/switch_to.h>
+#include <asm/xen/hypervisor.h>
asmlinkage extern void ret_from_fork(void);
@@ -411,6 +412,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
__switch_to_xtra(prev_p, next_p, tss);
+#ifdef CONFIG_XEN
+ /*
+ * On Xen PV, IOPL bits in pt_regs->flags have no effect, and
+ * current_pt_regs()->flags may not match the current task's
+ * intended IOPL. We need to switch it manually.
+ */
+ if (unlikely(static_cpu_has(X86_FEATURE_XENPV) &&
+ prev->iopl != next->iopl))
+ xen_set_iopl_mask(next->iopl);
+#endif
+
if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) {
/*
* AMD CPUs have a misfeature: SYSRET sets the SS selector but
diff --git a/kernel/arch/x86/kernel/ptrace.c b/kernel/arch/x86/kernel/ptrace.c
index 558f50ede..479a409dd 100644
--- a/kernel/arch/x86/kernel/ptrace.c
+++ b/kernel/arch/x86/kernel/ptrace.c
@@ -188,8 +188,8 @@ 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;
}
diff --git a/kernel/arch/x86/kernel/pvclock.c b/kernel/arch/x86/kernel/pvclock.c
index 2f355d229..bf0ce7573 100644
--- a/kernel/arch/x86/kernel/pvclock.c
+++ b/kernel/arch/x86/kernel/pvclock.c
@@ -66,6 +66,8 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
do {
version = __pvclock_read_cycles(src, &ret, &flags);
+ /* Make sure that the version double-check is last. */
+ smp_rmb();
} while ((src->version & 1) || version != src->version);
return flags & valid_flags;
@@ -80,6 +82,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
do {
version = __pvclock_read_cycles(src, &ret, &flags);
+ /* Make sure that the version double-check is last. */
+ smp_rmb();
} while ((src->version & 1) || version != src->version);
if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
diff --git a/kernel/arch/x86/kernel/reboot.c b/kernel/arch/x86/kernel/reboot.c
index f660d63f4..8384207ad 100644
--- a/kernel/arch/x86/kernel/reboot.c
+++ b/kernel/arch/x86/kernel/reboot.c
@@ -726,6 +726,7 @@ static int crashing_cpu;
static nmi_shootdown_cb shootdown_callback;
static atomic_t waiting_for_crash_ipi;
+static int crash_ipi_issued;
static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
{
@@ -788,6 +789,9 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
smp_send_nmi_allbutself();
+ /* Kick CPUs looping in NMI context. */
+ WRITE_ONCE(crash_ipi_issued, 1);
+
msecs = 1000; /* Wait at most a second for the other cpus to stop */
while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
mdelay(1);
@@ -796,6 +800,22 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
/* Leave the nmi callback set */
}
+
+/* Override the weak function in kernel/panic.c */
+void nmi_panic_self_stop(struct pt_regs *regs)
+{
+ while (1) {
+ /*
+ * Wait for the crash dumping IPI to be issued, and then
+ * call its callback directly.
+ */
+ if (READ_ONCE(crash_ipi_issued))
+ crash_nmi_callback(0, regs); /* Don't return */
+
+ cpu_relax();
+ }
+}
+
#else /* !CONFIG_SMP */
void nmi_shootdown_cpus(nmi_shootdown_cb callback)
{
diff --git a/kernel/arch/x86/kernel/sysfb_efi.c b/kernel/arch/x86/kernel/sysfb_efi.c
index b285d4e8c..5da924bbf 100644
--- a/kernel/arch/x86/kernel/sysfb_efi.c
+++ b/kernel/arch/x86/kernel/sysfb_efi.c
@@ -106,14 +106,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id)
continue;
for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
resource_size_t start, end;
+ unsigned long flags;
+
+ flags = pci_resource_flags(dev, i);
+ if (!(flags & IORESOURCE_MEM))
+ continue;
+
+ if (flags & IORESOURCE_UNSET)
+ continue;
+
+ if (pci_resource_len(dev, i) == 0)
+ continue;
start = pci_resource_start(dev, i);
- if (start == 0)
- break;
end = pci_resource_end(dev, i);
if (screen_info.lfb_base >= start &&
screen_info.lfb_base < end) {
found_bar = 1;
+ break;
}
}
}
diff --git a/kernel/arch/x86/kernel/traps.c b/kernel/arch/x86/kernel/traps.c
index ade185a46..679302c31 100644
--- a/kernel/arch/x86/kernel/traps.c
+++ b/kernel/arch/x86/kernel/traps.c
@@ -109,6 +109,12 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
preempt_count_dec();
}
+/*
+ * In IST context, we explicitly disable preemption. This serves two
+ * purposes: it makes it much less likely that we would accidentally
+ * schedule in IST context and it will force a warning if we somehow
+ * manage to schedule by accident.
+ */
void ist_enter(struct pt_regs *regs)
{
if (user_mode(regs)) {
@@ -123,13 +129,7 @@ void ist_enter(struct pt_regs *regs)
rcu_nmi_enter();
}
- /*
- * We are atomic because we're on the IST stack; or we're on
- * x86_32, in which case we still shouldn't schedule; or we're
- * on x86_64 and entered from user mode, in which case we're
- * still atomic unless ist_begin_non_atomic is called.
- */
- preempt_count_add(HARDIRQ_OFFSET);
+ preempt_disable();
/* This code is a bit fragile. Test it. */
RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
@@ -137,7 +137,7 @@ void ist_enter(struct pt_regs *regs)
void ist_exit(struct pt_regs *regs)
{
- preempt_count_sub(HARDIRQ_OFFSET);
+ preempt_enable_no_resched();
if (!user_mode(regs))
rcu_nmi_exit();
@@ -168,7 +168,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
BUG_ON((unsigned long)(current_top_of_stack() -
current_stack_pointer()) >= THREAD_SIZE);
- preempt_count_sub(HARDIRQ_OFFSET);
+ preempt_enable_no_resched();
}
/**
@@ -178,7 +178,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
*/
void ist_end_non_atomic(void)
{
- preempt_count_add(HARDIRQ_OFFSET);
+ preempt_disable();
}
static nokprobe_inline int
diff --git a/kernel/arch/x86/kernel/tsc_msr.c b/kernel/arch/x86/kernel/tsc_msr.c
index 92ae6acac..6aa0f4d9e 100644
--- a/kernel/arch/x86/kernel/tsc_msr.c
+++ b/kernel/arch/x86/kernel/tsc_msr.c
@@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void)
if (freq_desc_tables[cpu_index].msr_plat) {
rdmsr(MSR_PLATFORM_INFO, lo, hi);
- ratio = (lo >> 8) & 0x1f;
+ ratio = (lo >> 8) & 0xff;
} else {
rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
ratio = (hi >> 8) & 0x1f;
diff --git a/kernel/arch/x86/kernel/uprobes.c b/kernel/arch/x86/kernel/uprobes.c
index bf4db6eae..c6aace2bb 100644
--- a/kernel/arch/x86/kernel/uprobes.c
+++ b/kernel/arch/x86/kernel/uprobes.c
@@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
*cursor &= 0xfe;
}
/*
- * Similar treatment for VEX3 prefix.
- * TODO: add XOP/EVEX treatment when insn decoder supports them
+ * Similar treatment for VEX3/EVEX prefix.
+ * TODO: add XOP treatment when insn decoder supports them
*/
- if (insn->vex_prefix.nbytes == 3) {
+ if (insn->vex_prefix.nbytes >= 3) {
/*
* vex2: c5 rvvvvLpp (has no b bit)
* vex3/xop: c4/8f rxbmmmmm wvvvvLpp
* evex: 62 rxbR00mm wvvvv1pp zllBVaaa
- * (evex will need setting of both b and x since
- * in non-sib encoding evex.x is 4th bit of MODRM.rm)
- * Setting VEX3.b (setting because it has inverted meaning):
+ * Setting VEX3.b (setting because it has inverted meaning).
+ * Setting EVEX.x since (in non-SIB encoding) EVEX.x
+ * is the 4th bit of MODRM.rm, and needs the same treatment.
+ * For VEX3-encoded insns, VEX3.x value has no effect in
+ * non-SIB encoding, the change is superfluous but harmless.
*/
cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1;
- *cursor |= 0x20;
+ *cursor |= 0x60;
}
/*
@@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
reg = MODRM_REG(insn); /* Fetch modrm.reg */
reg2 = 0xff; /* Fetch vex.vvvv */
- if (insn->vex_prefix.nbytes == 2)
- reg2 = insn->vex_prefix.bytes[1];
- else if (insn->vex_prefix.nbytes == 3)
+ if (insn->vex_prefix.nbytes)
reg2 = insn->vex_prefix.bytes[2];
/*
- * TODO: add XOP, EXEV vvvv reading.
+ * TODO: add XOP vvvv reading.
*
* vex.vvvv field is in bits 6-3, bits are inverted.
* But in 32-bit mode, high-order bit may be ignored.
diff --git a/kernel/arch/x86/kvm/cpuid.c b/kernel/arch/x86/kvm/cpuid.c
index 6525e926f..2e1fd586b 100644
--- a/kernel/arch/x86/kvm/cpuid.c
+++ b/kernel/arch/x86/kvm/cpuid.c
@@ -509,6 +509,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
do_cpuid_1_ent(&entry[i], function, idx);
if (idx == 1) {
entry[i].eax &= kvm_supported_word10_x86_features;
+ cpuid_mask(&entry[i].eax, 10);
entry[i].ebx = 0;
if (entry[i].eax & (F(XSAVES)|F(XSAVEC)))
entry[i].ebx =
diff --git a/kernel/arch/x86/kvm/emulate.c b/kernel/arch/x86/kvm/emulate.c
index b9b09fec1..1dcea2259 100644
--- a/kernel/arch/x86/kvm/emulate.c
+++ b/kernel/arch/x86/kvm/emulate.c
@@ -172,6 +172,7 @@
#define NearBranch ((u64)1 << 52) /* Near branches */
#define No16 ((u64)1 << 53) /* No 16 bit operand */
#define IncSP ((u64)1 << 54) /* SP is incremented before ModRM calc */
+#define Aligned16 ((u64)1 << 55) /* Aligned to 16 byte boundary (e.g. FXSAVE) */
#define DstXacc (DstAccLo | SrcAccHi | SrcWrite)
@@ -434,6 +435,26 @@ FOP_END;
FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET
FOP_END;
+/*
+ * XXX: inoutclob user must know where the argument is being expanded.
+ * Relying on CC_HAVE_ASM_GOTO would allow us to remove _fault.
+ */
+#define asm_safe(insn, inoutclob...) \
+({ \
+ int _fault = 0; \
+ \
+ asm volatile("1:" insn "\n" \
+ "2:\n" \
+ ".pushsection .fixup, \"ax\"\n" \
+ "3: movl $1, %[_fault]\n" \
+ " jmp 2b\n" \
+ ".popsection\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [_fault] "+qm"(_fault) inoutclob ); \
+ \
+ _fault ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; \
+})
+
static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt,
enum x86_intercept intercept,
enum x86_intercept_stage stage)
@@ -620,21 +641,24 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector,
* depending on whether they're AVX encoded or not.
*
* Also included is CMPXCHG16B which is not a vector instruction, yet it is
- * subject to the same check.
+ * subject to the same check. FXSAVE and FXRSTOR are checked here too as their
+ * 512 bytes of data must be aligned to a 16 byte boundary.
*/
-static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size)
+static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size)
{
if (likely(size < 16))
- return false;
+ return 1;
if (ctxt->d & Aligned)
- return true;
+ return size;
else if (ctxt->d & Unaligned)
- return false;
+ return 1;
else if (ctxt->d & Avx)
- return false;
+ return 1;
+ else if (ctxt->d & Aligned16)
+ return 16;
else
- return true;
+ return size;
}
static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
@@ -692,7 +716,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
}
break;
}
- if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
+ if (la & (insn_alignment(ctxt, size) - 1))
return emulate_gp(ctxt, 0);
return X86EMUL_CONTINUE;
bad:
@@ -779,6 +803,20 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception);
}
+static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
+ struct segmented_address addr,
+ void *data,
+ unsigned int size)
+{
+ int rc;
+ ulong linear;
+
+ rc = linearize(ctxt, addr, size, true, &linear);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception);
+}
+
/*
* Prefetch the remaining bytes of the instruction without crossing page
* boundary if they are not in fetch_cache yet.
@@ -1532,7 +1570,6 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
&ctxt->exception);
}
-/* Does not support long mode */
static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
u16 selector, int seg, u8 cpl,
enum x86_transfer_type transfer,
@@ -1569,20 +1606,34 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
rpl = selector & 3;
- /* NULL selector is not valid for TR, CS and SS (except for long mode) */
- if ((seg == VCPU_SREG_CS
- || (seg == VCPU_SREG_SS
- && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl))
- || seg == VCPU_SREG_TR)
- && null_selector)
- goto exception;
-
/* TR should be in GDT only */
if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
goto exception;
- if (null_selector) /* for NULL selector skip all following checks */
+ /* NULL selector is not valid for TR, CS and (except for long mode) SS */
+ if (null_selector) {
+ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR)
+ goto exception;
+
+ if (seg == VCPU_SREG_SS) {
+ if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)
+ goto exception;
+
+ /*
+ * ctxt->ops->set_segment expects the CPL to be in
+ * SS.DPL, so fake an expand-up 32-bit data segment.
+ */
+ seg_desc.type = 3;
+ seg_desc.p = 1;
+ seg_desc.s = 1;
+ seg_desc.dpl = cpl;
+ seg_desc.d = 1;
+ seg_desc.g = 1;
+ }
+
+ /* Skip all following checks */
goto load;
+ }
ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr);
if (ret != X86EMUL_CONTINUE)
@@ -1698,6 +1749,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
u16 selector, int seg)
{
u8 cpl = ctxt->ops->cpl(ctxt);
+
+ /*
+ * None of MOV, POP and LSS can load a NULL selector in CPL=3, but
+ * they can load it at CPL<3 (Intel's manual says only LSS can,
+ * but it's wrong).
+ *
+ * However, the Intel manual says that putting IST=1/DPL=3 in
+ * an interrupt gate will result in SS=3 (the AMD manual instead
+ * says it doesn't), so allow SS=3 in __load_segment_descriptor
+ * and only forbid it here.
+ */
+ if (seg == VCPU_SREG_SS && selector == 3 &&
+ ctxt->mode == X86EMUL_MODE_PROT64)
+ return emulate_exception(ctxt, GP_VECTOR, 0, true);
+
return __load_segment_descriptor(ctxt, selector, seg, cpl,
X86_TRANSFER_NONE, NULL);
}
@@ -2093,16 +2159,10 @@ static int em_iret(struct x86_emulate_ctxt *ctxt)
static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
- unsigned short sel, old_sel;
- struct desc_struct old_desc, new_desc;
- const struct x86_emulate_ops *ops = ctxt->ops;
+ unsigned short sel;
+ struct desc_struct new_desc;
u8 cpl = ctxt->ops->cpl(ctxt);
- /* Assignment of RIP may only fail in 64-bit mode */
- if (ctxt->mode == X86EMUL_MODE_PROT64)
- ops->get_segment(ctxt, &old_sel, &old_desc, NULL,
- VCPU_SREG_CS);
-
memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl,
@@ -2112,12 +2172,10 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
return rc;
rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
- if (rc != X86EMUL_CONTINUE) {
- WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
- /* assigning eip failed; restore the old cs */
- ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS);
- return rc;
- }
+ /* Error handling is not implemented. */
+ if (rc != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
return rc;
}
@@ -2177,14 +2235,8 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
unsigned long eip, cs;
- u16 old_cs;
int cpl = ctxt->ops->cpl(ctxt);
- struct desc_struct old_desc, new_desc;
- const struct x86_emulate_ops *ops = ctxt->ops;
-
- if (ctxt->mode == X86EMUL_MODE_PROT64)
- ops->get_segment(ctxt, &old_cs, &old_desc, NULL,
- VCPU_SREG_CS);
+ struct desc_struct new_desc;
rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
@@ -2201,10 +2253,10 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
rc = assign_eip_far(ctxt, eip, &new_desc);
- if (rc != X86EMUL_CONTINUE) {
- WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
- ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
- }
+ /* Error handling is not implemented. */
+ if (rc != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
return rc;
}
@@ -3660,8 +3712,8 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt,
}
/* Disable writeback. */
ctxt->dst.type = OP_NONE;
- return segmented_write(ctxt, ctxt->dst.addr.mem,
- &desc_ptr, 2 + ctxt->op_bytes);
+ return segmented_write_std(ctxt, ctxt->dst.addr.mem,
+ &desc_ptr, 2 + ctxt->op_bytes);
}
static int em_sgdt(struct x86_emulate_ctxt *ctxt)
@@ -3844,6 +3896,131 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt)
return X86EMUL_CONTINUE;
}
+static int check_fxsr(struct x86_emulate_ctxt *ctxt)
+{
+ u32 eax = 1, ebx, ecx = 0, edx;
+
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ if (!(edx & FFL(FXSR)))
+ return emulate_ud(ctxt);
+
+ if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+ return emulate_nm(ctxt);
+
+ /*
+ * Don't emulate a case that should never be hit, instead of working
+ * around a lack of fxsave64/fxrstor64 on old compilers.
+ */
+ if (ctxt->mode >= X86EMUL_MODE_PROT64)
+ return X86EMUL_UNHANDLEABLE;
+
+ return X86EMUL_CONTINUE;
+}
+
+/*
+ * FXSAVE and FXRSTOR have 4 different formats depending on execution mode,
+ * 1) 16 bit mode
+ * 2) 32 bit mode
+ * - like (1), but FIP and FDP (foo) are only 16 bit. At least Intel CPUs
+ * preserve whole 32 bit values, though, so (1) and (2) are the same wrt.
+ * save and restore
+ * 3) 64-bit mode with REX.W prefix
+ * - like (2), but XMM 8-15 are being saved and restored
+ * 4) 64-bit mode without REX.W prefix
+ * - like (3), but FIP and FDP are 64 bit
+ *
+ * Emulation uses (3) for (1) and (2) and preserves XMM 8-15 to reach the
+ * desired result. (4) is not emulated.
+ *
+ * Note: Guest and host CPUID.(EAX=07H,ECX=0H):EBX[bit 13] (deprecate FPU CS
+ * and FPU DS) should match.
+ */
+static int em_fxsave(struct x86_emulate_ctxt *ctxt)
+{
+ struct fxregs_state fx_state;
+ size_t size;
+ int rc;
+
+ rc = check_fxsr(ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ ctxt->ops->get_fpu(ctxt);
+
+ rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+
+ ctxt->ops->put_fpu(ctxt);
+
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)
+ size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]);
+ else
+ size = offsetof(struct fxregs_state, xmm_space[0]);
+
+ return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+}
+
+static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
+ struct fxregs_state *new)
+{
+ int rc = X86EMUL_CONTINUE;
+ struct fxregs_state old;
+
+ rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old));
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ /*
+ * 64 bit host will restore XMM 8-15, which is not correct on non-64
+ * bit guests. Load the current values in order to preserve 64 bit
+ * XMMs after fxrstor.
+ */
+#ifdef CONFIG_X86_64
+ /* XXX: accessing XMM 8-15 very awkwardly */
+ memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16);
+#endif
+
+ /*
+ * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but
+ * does save and restore MXCSR.
+ */
+ if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))
+ memcpy(new->xmm_space, old.xmm_space, 8 * 16);
+
+ return rc;
+}
+
+static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
+{
+ struct fxregs_state fx_state;
+ int rc;
+
+ rc = check_fxsr(ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ if (fx_state.mxcsr >> 16)
+ return emulate_gp(ctxt, 0);
+
+ ctxt->ops->get_fpu(ctxt);
+
+ if (ctxt->mode < X86EMUL_MODE_PROT64)
+ rc = fxrstor_fixup(ctxt, &fx_state);
+
+ if (rc == X86EMUL_CONTINUE)
+ rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
+
+ ctxt->ops->put_fpu(ctxt);
+
+ return rc;
+}
+
static bool valid_cr(int nr)
{
switch (nr) {
@@ -4196,7 +4373,9 @@ static const struct gprefix pfx_0f_ae_7 = {
};
static const struct group_dual group15 = { {
- N, N, N, N, N, N, N, GP(0, &pfx_0f_ae_7),
+ I(ModRM | Aligned16, em_fxsave),
+ I(ModRM | Aligned16, em_fxrstor),
+ N, N, N, N, N, GP(0, &pfx_0f_ae_7),
}, {
N, N, N, N, N, N, N, N,
} };
@@ -5033,7 +5212,7 @@ done_prefixes:
/* Decode and fetch the destination operand: register or memory. */
rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
- if (ctxt->rip_relative)
+ if (ctxt->rip_relative && likely(ctxt->memopp))
ctxt->memopp->addr.mem.ea = address_mask(ctxt,
ctxt->memopp->addr.mem.ea + ctxt->_eip);
@@ -5068,21 +5247,13 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
{
- bool fault = false;
+ int rc;
ctxt->ops->get_fpu(ctxt);
- asm volatile("1: fwait \n\t"
- "2: \n\t"
- ".pushsection .fixup,\"ax\" \n\t"
- "3: \n\t"
- "movb $1, %[fault] \n\t"
- "jmp 2b \n\t"
- ".popsection \n\t"
- _ASM_EXTABLE(1b, 3b)
- : [fault]"+qm"(fault));
+ rc = asm_safe("fwait");
ctxt->ops->put_fpu(ctxt);
- if (unlikely(fault))
+ if (unlikely(rc != X86EMUL_CONTINUE))
return emulate_exception(ctxt, MF_VECTOR, 0, false);
return X86EMUL_CONTINUE;
diff --git a/kernel/arch/x86/kvm/i8254.c b/kernel/arch/x86/kvm/i8254.c
index b0ea42b78..ab5318727 100644
--- a/kernel/arch/x86/kvm/i8254.c
+++ b/kernel/arch/x86/kvm/i8254.c
@@ -245,7 +245,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
* PIC is being reset. Handle it gracefully here
*/
atomic_inc(&ps->pending);
- else if (value > 0)
+ else if (value > 0 && ps->reinject)
/* in this case, we had multiple outstanding pit interrupts
* that we needed to inject. Reinject
*/
@@ -288,7 +288,9 @@ static void pit_do_work(struct kthread_work *work)
* last one has been acked.
*/
spin_lock(&ps->inject_lock);
- if (ps->irq_ack) {
+ if (!ps->reinject)
+ inject = 1;
+ else if (ps->irq_ack) {
ps->irq_ack = 0;
inject = 1;
}
@@ -317,10 +319,10 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer);
struct kvm_pit *pt = ps->kvm->arch.vpit;
- if (ps->reinject || !atomic_read(&ps->pending)) {
+ if (ps->reinject)
atomic_inc(&ps->pending);
- queue_kthread_work(&pt->worker, &pt->expired);
- }
+
+ queue_kthread_work(&pt->worker, &pt->expired);
if (ps->is_periodic) {
hrtimer_add_expires_ns(&ps->timer, ps->period);
diff --git a/kernel/arch/x86/kvm/ioapic.c b/kernel/arch/x86/kvm/ioapic.c
index 88d0a92d3..3aab53f8c 100644
--- a/kernel/arch/x86/kvm/ioapic.c
+++ b/kernel/arch/x86/kvm/ioapic.c
@@ -580,7 +580,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
ioapic->irr = 0;
ioapic->irr_delivered = 0;
ioapic->id = 0;
- memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
+ memset(ioapic->irq_eoi, 0x00, sizeof(ioapic->irq_eoi));
rtc_irq_eoi_tracking_reset(ioapic);
}
diff --git a/kernel/arch/x86/kvm/irq_comm.c b/kernel/arch/x86/kvm/irq_comm.c
index 84b96d319..d09544e82 100644
--- a/kernel/arch/x86/kvm/irq_comm.c
+++ b/kernel/arch/x86/kvm/irq_comm.c
@@ -38,6 +38,15 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
bool line_status)
{
struct kvm_pic *pic = pic_irqchip(kvm);
+
+ /*
+ * XXX: rejecting pic routes when pic isn't in use would be better,
+ * but the default routing table is installed while kvm->arch.vpic is
+ * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE.
+ */
+ if (!pic)
+ return -1;
+
return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
}
@@ -46,6 +55,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
bool line_status)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+ if (!ioapic)
+ return -1;
+
return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
line_status);
}
diff --git a/kernel/arch/x86/kvm/lapic.c b/kernel/arch/x86/kvm/lapic.c
index 3d1b17068..6cd4f4b32 100644
--- a/kernel/arch/x86/kvm/lapic.c
+++ b/kernel/arch/x86/kvm/lapic.c
@@ -2266,3 +2266,9 @@ void kvm_lapic_init(void)
jump_label_rate_limit(&apic_hw_disabled, HZ);
jump_label_rate_limit(&apic_sw_disabled, HZ);
}
+
+void kvm_lapic_exit(void)
+{
+ static_key_deferred_flush(&apic_hw_disabled);
+ static_key_deferred_flush(&apic_sw_disabled);
+}
diff --git a/kernel/arch/x86/kvm/lapic.h b/kernel/arch/x86/kvm/lapic.h
index 640ad275b..04141a598 100644
--- a/kernel/arch/x86/kvm/lapic.h
+++ b/kernel/arch/x86/kvm/lapic.h
@@ -96,6 +96,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
void kvm_lapic_init(void);
+void kvm_lapic_exit(void);
static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off)
{
diff --git a/kernel/arch/x86/kvm/mtrr.c b/kernel/arch/x86/kvm/mtrr.c
index 3f8c73211..0149ac59c 100644
--- a/kernel/arch/x86/kvm/mtrr.c
+++ b/kernel/arch/x86/kvm/mtrr.c
@@ -44,8 +44,6 @@ static bool msr_mtrr_valid(unsigned msr)
case MSR_MTRRdefType:
case MSR_IA32_CR_PAT:
return true;
- case 0x2f8:
- return true;
}
return false;
}
@@ -541,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter)
iter->fixed = false;
iter->start_max = iter->start;
+ iter->range = NULL;
iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
__mtrr_lookup_var_next(iter);
diff --git a/kernel/arch/x86/kvm/vmx.c b/kernel/arch/x86/kvm/vmx.c
index a722f724c..8d744a82f 100644
--- a/kernel/arch/x86/kvm/vmx.c
+++ b/kernel/arch/x86/kvm/vmx.c
@@ -415,6 +415,7 @@ struct nested_vmx {
struct list_head vmcs02_pool;
int vmcs02_num;
u64 vmcs01_tsc_offset;
+ bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
/*
@@ -1308,10 +1309,10 @@ static inline bool nested_cpu_has_posted_intr(struct vmcs12 *vmcs12)
return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR;
}
-static inline bool is_exception(u32 intr_info)
+static inline bool is_nmi(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
- == (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK);
+ == (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
}
static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
@@ -2699,8 +2700,15 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
} else
vmx->nested.nested_vmx_ept_caps = 0;
+ /*
+ * Old versions of KVM use the single-context version without
+ * checking for support, so declare that it is supported even
+ * though it is treated as global context. The alternative is
+ * not failing the single-context invvpid, and it is worse.
+ */
if (enable_vpid)
vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
+ VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |
VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
else
vmx->nested.nested_vmx_vpid_caps = 0;
@@ -5016,8 +5024,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
- vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx->vcpu.arch.cr0 = cr0;
+ vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx_set_cr4(vcpu, 0);
vmx_set_efer(vcpu, 0);
vmx_fpu_activate(vcpu);
@@ -5295,7 +5303,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
if (is_machine_check(intr_info))
return handle_machine_check(vcpu);
- if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR)
+ if (is_nmi(intr_info))
return 1; /* already handled by vmx_vcpu_run() */
if (is_no_device(intr_info)) {
@@ -6652,7 +6660,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
/* Checks for #GP/#SS exceptions. */
exn = false;
- if (is_protmode(vcpu)) {
+ if (is_long_mode(vcpu)) {
+ /* Long mode: #GP(0)/#SS(0) if the memory address is in a
+ * non-canonical form. This is the only check on the memory
+ * destination for long mode!
+ */
+ exn = is_noncanonical_address(*ret);
+ } else if (is_protmode(vcpu)) {
/* Protected mode: apply checks for segment validity in the
* following order:
* - segment type check (#GP(0) may be thrown)
@@ -6669,17 +6683,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
* execute-only code segment
*/
exn = ((s.type & 0xa) == 8);
- }
- if (exn) {
- kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
- return 1;
- }
- if (is_long_mode(vcpu)) {
- /* Long mode: #GP(0)/#SS(0) if the memory address is in a
- * non-canonical form. This is an only check for long mode.
- */
- exn = is_noncanonical_address(*ret);
- } else if (is_protmode(vcpu)) {
+ if (exn) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+ return 1;
+ }
/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
*/
exn = (s.unusable != 0);
@@ -7420,6 +7427,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
if (!(types & (1UL << type))) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+ skip_emulated_instruction(vcpu);
return 1;
}
@@ -7478,6 +7486,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
if (!(types & (1UL << type))) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+ skip_emulated_instruction(vcpu);
return 1;
}
@@ -7494,12 +7503,17 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
}
switch (type) {
+ case VMX_VPID_EXTENT_SINGLE_CONTEXT:
+ /*
+ * Old versions of KVM use the single-context version so we
+ * have to support it; just treat it the same as all-context.
+ */
case VMX_VPID_EXTENT_ALL_CONTEXT:
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
nested_vmx_succeed(vcpu);
break;
default:
- /* Trap single context invalidation invvpid calls */
+ /* Trap individual address invalidation invvpid calls */
BUG_ON(1);
break;
}
@@ -7795,7 +7809,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
switch (exit_reason) {
case EXIT_REASON_EXCEPTION_NMI:
- if (!is_exception(intr_info))
+ if (is_nmi(intr_info))
return false;
else if (is_page_fault(intr_info))
return enable_ept;
@@ -8200,6 +8214,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
exit_reason != EXIT_REASON_EPT_VIOLATION &&
+ exit_reason != EXIT_REASON_PML_FULL &&
exit_reason != EXIT_REASON_TASK_SWITCH)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8259,6 +8274,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
{
u32 sec_exec_control;
+ /* Postpone execution until vmcs01 is the current VMCS. */
+ if (is_guest_mode(vcpu)) {
+ to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+ return;
+ }
+
/*
* There is not point to enable virtualize x2apic without enable
* apicv
@@ -8397,8 +8418,7 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
kvm_machine_check();
/* We need to handle NMIs before interrupts are enabled */
- if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
- (exit_intr_info & INTR_INFO_VALID_MASK)) {
+ if (is_nmi(exit_intr_info)) {
kvm_before_handle_nmi(&vmx->vcpu);
asm("int $2");
kvm_after_handle_nmi(&vmx->vcpu);
@@ -8834,6 +8854,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
put_cpu();
}
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int r;
+
+ r = vcpu_load(vcpu);
+ BUG_ON(r);
+ vmx_load_vmcs01(vcpu);
+ free_nested(vmx);
+ vcpu_put(vcpu);
+}
+
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8842,8 +8878,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
vmx_destroy_pml_buffer(vmx);
free_vpid(vmx->vpid);
leave_guest_mode(vcpu);
- vmx_load_vmcs01(vcpu);
- free_nested(vmx);
+ vmx_free_vcpu_nested(vcpu);
free_loaded_vmcs(vmx->loaded_vmcs);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
@@ -10576,6 +10611,12 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
PIN_BASED_VMX_PREEMPTION_TIMER);
+ if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+ vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+ vmx_set_virtual_x2apic_mode(vcpu,
+ vcpu->arch.apic_base & X2APIC_ENABLE);
+ }
+
/* This is needed for same reason as it was needed in prepare_vmcs02 */
vmx->host_rsp = 0;
diff --git a/kernel/arch/x86/kvm/x86.c b/kernel/arch/x86/kvm/x86.c
index c7695cea4..c265bb0c2 100644
--- a/kernel/arch/x86/kvm/x86.c
+++ b/kernel/arch/x86/kvm/x86.c
@@ -200,7 +200,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
struct kvm_shared_msrs *locals
= container_of(urn, struct kvm_shared_msrs, urn);
struct kvm_shared_msr_values *values;
+ unsigned long flags;
+ /*
+ * Disabling irqs at this point since the following code could be
+ * interrupted and executed through kvm_arch_hardware_disable()
+ */
+ local_irq_save(flags);
+ if (locals->registered) {
+ locals->registered = false;
+ user_return_notifier_unregister(urn);
+ }
+ local_irq_restore(flags);
for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
values = &locals->values[slot];
if (values->host != values->curr) {
@@ -208,8 +219,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
values->curr = values->host;
}
}
- locals->registered = false;
- user_return_notifier_unregister(urn);
}
static void shared_msr_update(unsigned slot, u32 msr)
@@ -698,7 +707,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
return 1;
}
- kvm_put_guest_xcr0(vcpu);
vcpu->arch.xcr0 = xcr0;
if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
@@ -2947,6 +2955,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
memset(&events->reserved, 0, sizeof(events->reserved));
}
+static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
@@ -2979,10 +2989,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+ u32 hflags = vcpu->arch.hflags;
if (events->smi.smm)
- vcpu->arch.hflags |= HF_SMM_MASK;
+ hflags |= HF_SMM_MASK;
else
- vcpu->arch.hflags &= ~HF_SMM_MASK;
+ hflags &= ~HF_SMM_MASK;
+ kvm_set_hflags(vcpu, hflags);
+
vcpu->arch.smi_pending = events->smi.pending;
if (events->smi.smm_inside_nmi)
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
@@ -3020,6 +3033,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
if (dbgregs->flags)
return -EINVAL;
+ if (dbgregs->dr6 & ~0xffffffffull)
+ return -EINVAL;
+ if (dbgregs->dr7 & ~0xffffffffull)
+ return -EINVAL;
+
memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
kvm_update_dr0123(vcpu);
vcpu->arch.dr6 = dbgregs->dr6;
@@ -3045,6 +3063,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
memcpy(dest, xsave, XSAVE_HDR_OFFSET);
/* Set XSTATE_BV */
+ xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
/*
@@ -3319,6 +3338,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
};
case KVM_SET_VAPIC_ADDR: {
struct kvm_vapic_addr va;
+ int idx;
r = -EINVAL;
if (!lapic_in_kernel(vcpu))
@@ -3326,7 +3346,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = -EFAULT;
if (copy_from_user(&va, argp, sizeof va))
goto out;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
}
case KVM_X86_SETUP_MCE: {
@@ -5834,6 +5856,7 @@ out:
void kvm_arch_exit(void)
{
+ kvm_lapic_exit();
perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -6036,12 +6059,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
}
/* try to inject new event if pending */
- if (vcpu->arch.nmi_pending) {
- if (kvm_x86_ops->nmi_allowed(vcpu)) {
- --vcpu->arch.nmi_pending;
- vcpu->arch.nmi_injected = true;
- kvm_x86_ops->set_nmi(vcpu);
- }
+ if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+ --vcpu->arch.nmi_pending;
+ vcpu->arch.nmi_injected = true;
+ kvm_x86_ops->set_nmi(vcpu);
} else if (kvm_cpu_has_injectable_intr(vcpu)) {
/*
* Because interrupts can be injected asynchronously, we are
@@ -6486,10 +6507,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (inject_pending_event(vcpu, req_int_win) != 0)
req_immediate_exit = true;
/* enable NMI/IRQ window open exits if needed */
- else if (vcpu->arch.nmi_pending)
- kvm_x86_ops->enable_nmi_window(vcpu);
- else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
- kvm_x86_ops->enable_irq_window(vcpu);
+ else {
+ if (vcpu->arch.nmi_pending)
+ kvm_x86_ops->enable_nmi_window(vcpu);
+ if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
+ kvm_x86_ops->enable_irq_window(vcpu);
+ }
if (kvm_lapic_enabled(vcpu)) {
update_cr8_intercept(vcpu);
@@ -6507,8 +6530,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_x86_ops->prepare_guest_switch(vcpu);
if (vcpu->fpu_active)
kvm_load_guest_fpu(vcpu);
- kvm_load_guest_xcr0(vcpu);
-
vcpu->mode = IN_GUEST_MODE;
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6531,6 +6552,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto cancel_injection;
}
+ kvm_load_guest_xcr0(vcpu);
+
if (req_immediate_exit)
smp_send_reschedule(vcpu->cpu);
@@ -6580,6 +6603,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
+ kvm_put_guest_xcr0(vcpu);
+
/* Interrupt is enabled by handle_external_intr() */
kvm_x86_ops->handle_external_intr(vcpu);
@@ -7227,7 +7252,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
* and assume host would use all available bits.
* Guest xcr0 would be loaded later.
*/
- kvm_put_guest_xcr0(vcpu);
vcpu->guest_fpu_loaded = 1;
__kernel_fpu_begin();
__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
@@ -7236,8 +7260,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
- kvm_put_guest_xcr0(vcpu);
-
if (!vcpu->guest_fpu_loaded) {
vcpu->fpu_counter = 0;
return;
@@ -7262,10 +7284,12 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
+ void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+
kvmclock_reset(vcpu);
- free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
kvm_x86_ops->vcpu_free(vcpu);
+ free_cpumask_var(wbinvd_dirty_mask);
}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
diff --git a/kernel/arch/x86/mm/kmmio.c b/kernel/arch/x86/mm/kmmio.c
index 637ab34ed..ddb2244b0 100644
--- a/kernel/arch/x86/mm/kmmio.c
+++ b/kernel/arch/x86/mm/kmmio.c
@@ -33,7 +33,7 @@
struct kmmio_fault_page {
struct list_head list;
struct kmmio_fault_page *release_next;
- unsigned long page; /* location of the fault page */
+ unsigned long addr; /* the requested address */
pteval_t old_presence; /* page presence prior to arming */
bool armed;
@@ -70,9 +70,16 @@ unsigned int kmmio_count;
static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE];
static LIST_HEAD(kmmio_probes);
-static struct list_head *kmmio_page_list(unsigned long page)
+static struct list_head *kmmio_page_list(unsigned long addr)
{
- return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)];
+ unsigned int l;
+ pte_t *pte = lookup_address(addr, &l);
+
+ if (!pte)
+ return NULL;
+ addr &= page_level_mask(l);
+
+ return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)];
}
/* Accessed per-cpu */
@@ -98,15 +105,19 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
}
/* You must be holding RCU read lock. */
-static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
+static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
{
struct list_head *head;
struct kmmio_fault_page *f;
+ unsigned int l;
+ pte_t *pte = lookup_address(addr, &l);
- page &= PAGE_MASK;
- head = kmmio_page_list(page);
+ if (!pte)
+ return NULL;
+ addr &= page_level_mask(l);
+ head = kmmio_page_list(addr);
list_for_each_entry_rcu(f, head, list) {
- if (f->page == page)
+ if (f->addr == addr)
return f;
}
return NULL;
@@ -137,10 +148,10 @@ static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
{
unsigned int level;
- pte_t *pte = lookup_address(f->page, &level);
+ pte_t *pte = lookup_address(f->addr, &level);
if (!pte) {
- pr_err("no pte for page 0x%08lx\n", f->page);
+ pr_err("no pte for addr 0x%08lx\n", f->addr);
return -1;
}
@@ -156,7 +167,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
return -1;
}
- __flush_tlb_one(f->page);
+ __flush_tlb_one(f->addr);
return 0;
}
@@ -176,12 +187,12 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
int ret;
WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
if (f->armed) {
- pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n",
- f->page, f->count, !!f->old_presence);
+ pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n",
+ f->addr, f->count, !!f->old_presence);
}
ret = clear_page_presence(f, true);
- WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"),
- f->page);
+ WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"),
+ f->addr);
f->armed = true;
return ret;
}
@@ -191,7 +202,7 @@ static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
{
int ret = clear_page_presence(f, false);
WARN_ONCE(ret < 0,
- KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
+ KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr);
f->armed = false;
}
@@ -215,6 +226,12 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
struct kmmio_context *ctx;
struct kmmio_fault_page *faultpage;
int ret = 0; /* default to fault not handled */
+ unsigned long page_base = addr;
+ unsigned int l;
+ pte_t *pte = lookup_address(addr, &l);
+ if (!pte)
+ return -EINVAL;
+ page_base &= page_level_mask(l);
/*
* Preemption is now disabled to prevent process switch during
@@ -227,7 +244,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
preempt_disable();
rcu_read_lock();
- faultpage = get_kmmio_fault_page(addr);
+ faultpage = get_kmmio_fault_page(page_base);
if (!faultpage) {
/*
* Either this page fault is not caused by kmmio, or
@@ -239,7 +256,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
ctx = &get_cpu_var(kmmio_ctx);
if (ctx->active) {
- if (addr == ctx->addr) {
+ if (page_base == ctx->addr) {
/*
* A second fault on the same page means some other
* condition needs handling by do_page_fault(), the
@@ -267,9 +284,9 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
ctx->active++;
ctx->fpage = faultpage;
- ctx->probe = get_kmmio_probe(addr);
+ ctx->probe = get_kmmio_probe(page_base);
ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
- ctx->addr = addr;
+ ctx->addr = page_base;
if (ctx->probe && ctx->probe->pre_handler)
ctx->probe->pre_handler(ctx->probe, regs, addr);
@@ -354,12 +371,11 @@ out:
}
/* You must be holding kmmio_lock. */
-static int add_kmmio_fault_page(unsigned long page)
+static int add_kmmio_fault_page(unsigned long addr)
{
struct kmmio_fault_page *f;
- page &= PAGE_MASK;
- f = get_kmmio_fault_page(page);
+ f = get_kmmio_fault_page(addr);
if (f) {
if (!f->count)
arm_kmmio_fault_page(f);
@@ -372,26 +388,25 @@ static int add_kmmio_fault_page(unsigned long page)
return -1;
f->count = 1;
- f->page = page;
+ f->addr = addr;
if (arm_kmmio_fault_page(f)) {
kfree(f);
return -1;
}
- list_add_rcu(&f->list, kmmio_page_list(f->page));
+ list_add_rcu(&f->list, kmmio_page_list(f->addr));
return 0;
}
/* You must be holding kmmio_lock. */
-static void release_kmmio_fault_page(unsigned long page,
+static void release_kmmio_fault_page(unsigned long addr,
struct kmmio_fault_page **release_list)
{
struct kmmio_fault_page *f;
- page &= PAGE_MASK;
- f = get_kmmio_fault_page(page);
+ f = get_kmmio_fault_page(addr);
if (!f)
return;
@@ -420,18 +435,27 @@ int register_kmmio_probe(struct kmmio_probe *p)
int ret = 0;
unsigned long size = 0;
const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
+ unsigned int l;
+ pte_t *pte;
spin_lock_irqsave(&kmmio_lock, flags);
if (get_kmmio_probe(p->addr)) {
ret = -EEXIST;
goto out;
}
+
+ pte = lookup_address(p->addr, &l);
+ if (!pte) {
+ ret = -EINVAL;
+ goto out;
+ }
+
kmmio_count++;
list_add_rcu(&p->list, &kmmio_probes);
while (size < size_lim) {
if (add_kmmio_fault_page(p->addr + size))
pr_err("Unable to set page fault.\n");
- size += PAGE_SIZE;
+ size += page_level_size(l);
}
out:
spin_unlock_irqrestore(&kmmio_lock, flags);
@@ -506,11 +530,17 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
struct kmmio_fault_page *release_list = NULL;
struct kmmio_delayed_release *drelease;
+ unsigned int l;
+ pte_t *pte;
+
+ pte = lookup_address(p->addr, &l);
+ if (!pte)
+ return;
spin_lock_irqsave(&kmmio_lock, flags);
while (size < size_lim) {
release_kmmio_fault_page(p->addr + size, &release_list);
- size += PAGE_SIZE;
+ size += page_level_size(l);
}
list_del_rcu(&p->list);
kmmio_count--;
diff --git a/kernel/arch/x86/mm/mmap.c b/kernel/arch/x86/mm/mmap.c
index 844b06d67..307f60ecf 100644
--- a/kernel/arch/x86/mm/mmap.c
+++ b/kernel/arch/x86/mm/mmap.c
@@ -94,18 +94,6 @@ static unsigned long mmap_base(unsigned long rnd)
}
/*
- * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
- * does, but not when emulating X86_32
- */
-static unsigned long mmap_legacy_base(unsigned long rnd)
-{
- if (mmap_is_ia32())
- return TASK_UNMAPPED_BASE;
- else
- return TASK_UNMAPPED_BASE + rnd;
-}
-
-/*
* This function, called very early during the creation of a new
* process VM image, sets up which VM layout function to use:
*/
@@ -116,7 +104,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
if (current->flags & PF_RANDOMIZE)
random_factor = arch_mmap_rnd();
- mm->mmap_legacy_base = mmap_legacy_base(random_factor);
+ mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor;
if (mmap_is_legacy()) {
mm->mmap_base = mm->mmap_legacy_base;
diff --git a/kernel/arch/x86/mm/pat.c b/kernel/arch/x86/mm/pat.c
index 188e3e07e..6ad687d10 100644
--- a/kernel/arch/x86/mm/pat.c
+++ b/kernel/arch/x86/mm/pat.c
@@ -39,11 +39,22 @@
static bool boot_cpu_done;
static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
+static void init_cache_modes(void);
-static inline void pat_disable(const char *reason)
+void pat_disable(const char *reason)
{
+ if (!__pat_enabled)
+ return;
+
+ if (boot_cpu_done) {
+ WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n");
+ return;
+ }
+
__pat_enabled = 0;
pr_info("x86/PAT: %s\n", reason);
+
+ init_cache_modes();
}
static int __init nopat(char *str)
@@ -180,7 +191,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
* configuration.
* Using lower indices is preferred, so we start with highest index.
*/
-void pat_init_cache_modes(u64 pat)
+static void __init_cache_modes(u64 pat)
{
enum page_cache_mode cache;
char pat_msg[33];
@@ -201,14 +212,11 @@ static void pat_bsp_init(u64 pat)
{
u64 tmp_pat;
- if (!cpu_has_pat) {
+ if (!boot_cpu_has(X86_FEATURE_PAT)) {
pat_disable("PAT not supported by CPU.");
return;
}
- if (!pat_enabled())
- goto done;
-
rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
if (!tmp_pat) {
pat_disable("PAT MSR is 0, disabled.");
@@ -217,16 +225,12 @@ static void pat_bsp_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
-done:
- pat_init_cache_modes(pat);
+ __init_cache_modes(pat);
}
static void pat_ap_init(u64 pat)
{
- if (!pat_enabled())
- return;
-
- if (!cpu_has_pat) {
+ if (!boot_cpu_has(X86_FEATURE_PAT)) {
/*
* If this happens we are on a secondary CPU, but switched to
* PAT on the boot CPU. We have no way to undo PAT.
@@ -237,18 +241,32 @@ static void pat_ap_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
}
-void pat_init(void)
+static void init_cache_modes(void)
{
- u64 pat;
- struct cpuinfo_x86 *c = &boot_cpu_data;
+ u64 pat = 0;
+ static int init_cm_done;
- if (!pat_enabled()) {
+ if (init_cm_done)
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_PAT)) {
+ /*
+ * CPU supports PAT. Set PAT table to be consistent with
+ * PAT MSR. This case supports "nopat" boot option, and
+ * virtual machine environments which support PAT without
+ * MTRRs. In specific, Xen has unique setup to PAT MSR.
+ *
+ * If PAT MSR returns 0, it is considered invalid and emulates
+ * as No PAT.
+ */
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ }
+
+ if (!pat) {
/*
* No PAT. Emulate the PAT table that corresponds to the two
- * cache bits, PWT (Write Through) and PCD (Cache Disable). This
- * setup is the same as the BIOS default setup when the system
- * has PAT but the "nopat" boot option has been specified. This
- * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+ * cache bits, PWT (Write Through) and PCD (Cache Disable).
+ * This setup is also the same as the BIOS default setup.
*
* PTE encoding:
*
@@ -265,10 +283,36 @@ void pat_init(void)
*/
pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
+ }
+
+ __init_cache_modes(pat);
+
+ init_cm_done = 1;
+}
+
+/**
+ * pat_init - Initialize PAT MSR and PAT table
+ *
+ * This function initializes PAT MSR and PAT table with an OS-defined value
+ * to enable additional cache attributes, WC and WT.
+ *
+ * This function must be called on all CPUs using the specific sequence of
+ * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this
+ * procedure for PAT.
+ */
+void pat_init(void)
+{
+ u64 pat;
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (!pat_enabled()) {
+ init_cache_modes();
+ return;
+ }
- } else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
- (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
- ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+ if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+ (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+ ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
/*
* PAT support with the lower four entries. Intel Pentium 2,
* 3, M, and 4 are affected by PAT errata, which makes the
@@ -733,25 +777,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
if (file->f_flags & O_DSYNC)
pcm = _PAGE_CACHE_MODE_UC_MINUS;
-#ifdef CONFIG_X86_32
- /*
- * On the PPro and successors, the MTRRs are used to set
- * memory types for physical addresses outside main memory,
- * so blindly setting UC or PWT on those pages is wrong.
- * For Pentiums and earlier, the surround logic should disable
- * caching for the high addresses through the KEN pin, but
- * we maintain the tradition of paranoia in this code.
- */
- if (!pat_enabled() &&
- !(boot_cpu_has(X86_FEATURE_MTRR) ||
- boot_cpu_has(X86_FEATURE_K6_MTRR) ||
- boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
- boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
- (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
- pcm = _PAGE_CACHE_MODE_UC;
- }
-#endif
-
*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
cachemode2protval(pcm));
return 1;
diff --git a/kernel/arch/x86/mm/tlb.c b/kernel/arch/x86/mm/tlb.c
index 8f4cc3dfa..5fb6adaaa 100644
--- a/kernel/arch/x86/mm/tlb.c
+++ b/kernel/arch/x86/mm/tlb.c
@@ -106,8 +106,6 @@ static void flush_tlb_func(void *info)
if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
return;
- if (!f->flush_end)
- f->flush_end = f->flush_start + PAGE_SIZE;
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
@@ -135,12 +133,20 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
unsigned long end)
{
struct flush_tlb_info info;
+
+ if (end == 0)
+ end = start + PAGE_SIZE;
info.flush_mm = mm;
info.flush_start = start;
info.flush_end = end;
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
- trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start);
+ if (end == TLB_FLUSH_ALL)
+ trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
+ else
+ trace_tlb_flush(TLB_REMOTE_SEND_IPI,
+ (end - start) >> PAGE_SHIFT);
+
if (is_uv_system()) {
unsigned int cpu;
diff --git a/kernel/arch/x86/pci/acpi.c b/kernel/arch/x86/pci/acpi.c
index 3cd69832d..3961103e9 100644
--- a/kernel/arch/x86/pci/acpi.c
+++ b/kernel/arch/x86/pci/acpi.c
@@ -114,6 +114,16 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
},
},
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=42606 */
+ {
+ .callback = set_nouse_crs,
+ .ident = "Supermicro X8DTH",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X8DTH-i/6/iF/6F"),
+ DMI_MATCH(DMI_BIOS_VERSION, "2.0a"),
+ },
+ },
/* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
{
diff --git a/kernel/arch/x86/pci/common.c b/kernel/arch/x86/pci/common.c
index eccd4d99e..8fd6f44ae 100644
--- a/kernel/arch/x86/pci/common.c
+++ b/kernel/arch/x86/pci/common.c
@@ -673,28 +673,22 @@ int pcibios_add_device(struct pci_dev *dev)
return 0;
}
-int pcibios_alloc_irq(struct pci_dev *dev)
+int pcibios_enable_device(struct pci_dev *dev, int mask)
{
- /*
- * If the PCI device was already claimed by core code and has
- * MSI enabled, probing of the pcibios IRQ will overwrite
- * dev->irq. So bail out if MSI is already enabled.
- */
- if (pci_dev_msi_enabled(dev))
- return -EBUSY;
+ int err;
- return pcibios_enable_irq(dev);
-}
+ if ((err = pci_enable_resources(dev, mask)) < 0)
+ return err;
-void pcibios_free_irq(struct pci_dev *dev)
-{
- if (pcibios_disable_irq)
- pcibios_disable_irq(dev);
+ if (!pci_dev_msi_enabled(dev))
+ return pcibios_enable_irq(dev);
+ return 0;
}
-int pcibios_enable_device(struct pci_dev *dev, int mask)
+void pcibios_disable_device (struct pci_dev *dev)
{
- return pci_enable_resources(dev, mask);
+ if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+ pcibios_disable_irq(dev);
}
int pci_ext_cfg_avail(void)
diff --git a/kernel/arch/x86/pci/fixup.c b/kernel/arch/x86/pci/fixup.c
index e58565556..0ae7e9fa3 100644
--- a/kernel/arch/x86/pci/fixup.c
+++ b/kernel/arch/x86/pci/fixup.c
@@ -540,3 +540,10 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev)
}
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
+
+static void pci_bdwep_bar(struct pci_dev *dev)
+{
+ dev->non_compliant_bars = 1;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
diff --git a/kernel/arch/x86/pci/intel_mid_pci.c b/kernel/arch/x86/pci/intel_mid_pci.c
index 0d24e7c10..ae97f24a4 100644
--- a/kernel/arch/x86/pci/intel_mid_pci.c
+++ b/kernel/arch/x86/pci/intel_mid_pci.c
@@ -37,6 +37,7 @@
/* Quirks for the listed devices */
#define PCI_DEVICE_ID_INTEL_MRFL_MMC 0x1190
+#define PCI_DEVICE_ID_INTEL_MRFL_HSU 0x1191
/* Fixed BAR fields */
#define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00 /* Fixed BAR (TBD) */
@@ -215,7 +216,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
int polarity;
int ret;
- if (pci_has_managed_irq(dev))
+ if (dev->irq_managed && dev->irq > 0)
return 0;
switch (intel_mid_identify_cpu()) {
@@ -225,13 +226,20 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
/* Special treatment for IRQ0 */
if (dev->irq == 0) {
/*
+ * Skip HS UART common registers device since it has
+ * IRQ0 assigned and not used by the kernel.
+ */
+ if (dev->device == PCI_DEVICE_ID_INTEL_MRFL_HSU)
+ return -EBUSY;
+ /*
* TNG has IRQ0 assigned to eMMC controller. But there
* are also other devices with bogus PCI configuration
* that have IRQ0 assigned. This check ensures that
- * eMMC gets it.
+ * eMMC gets it. The rest of devices still could be
+ * enabled without interrupt line being allocated.
*/
if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC)
- return -EBUSY;
+ return 0;
}
break;
default:
@@ -256,13 +264,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
static void intel_mid_pci_irq_disable(struct pci_dev *dev)
{
- if (pci_has_managed_irq(dev)) {
+ if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+ dev->irq > 0) {
mp_unmap_irq(dev->irq);
dev->irq_managed = 0;
- /*
- * Don't reset dev->irq here, otherwise
- * intel_mid_pci_irq_enable() will fail on next call.
- */
}
}
diff --git a/kernel/arch/x86/pci/irq.c b/kernel/arch/x86/pci/irq.c
index 32e70343e..9bd115484 100644
--- a/kernel/arch/x86/pci/irq.c
+++ b/kernel/arch/x86/pci/irq.c
@@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
struct pci_dev *temp_dev;
int irq;
- if (pci_has_managed_irq(dev))
+ if (dev->irq_managed && dev->irq > 0)
return 0;
irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
@@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev)
}
dev = temp_dev;
if (irq >= 0) {
- pci_set_managed_irq(dev, irq);
+ dev->irq_managed = 1;
+ dev->irq = irq;
dev_info(&dev->dev, "PCI->APIC IRQ transform: "
"INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
return 0;
@@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev)
return 0;
}
+bool mp_should_keep_irq(struct device *dev)
+{
+ if (dev->power.is_prepared)
+ return true;
+#ifdef CONFIG_PM
+ if (dev->power.runtime_status == RPM_SUSPENDING)
+ return true;
+#endif
+
+ return false;
+}
+
static void pirq_disable_irq(struct pci_dev *dev)
{
- if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) {
+ if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
+ dev->irq_managed && dev->irq) {
mp_unmap_irq(dev->irq);
- pci_reset_managed_irq(dev);
+ dev->irq = 0;
+ dev->irq_managed = 0;
}
}
diff --git a/kernel/arch/x86/pci/xen.c b/kernel/arch/x86/pci/xen.c
index ff31ab464..c6d6efed3 100644
--- a/kernel/arch/x86/pci/xen.c
+++ b/kernel/arch/x86/pci/xen.c
@@ -488,8 +488,11 @@ int __init pci_xen_initial_domain(void)
#endif
__acpi_register_gsi = acpi_register_gsi_xen;
__acpi_unregister_gsi = NULL;
- /* Pre-allocate legacy irqs */
- for (irq = 0; irq < nr_legacy_irqs(); irq++) {
+ /*
+ * Pre-allocate the legacy IRQs. Use NR_LEGACY_IRQS here
+ * because we don't have a PIC and thus nr_legacy_irqs() is zero.
+ */
+ for (irq = 0; irq < NR_IRQS_LEGACY; irq++) {
int trigger, polarity;
if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
diff --git a/kernel/arch/x86/purgatory/Makefile b/kernel/arch/x86/purgatory/Makefile
index 2c835e356..d445c5f1a 100644
--- a/kernel/arch/x86/purgatory/Makefile
+++ b/kernel/arch/x86/purgatory/Makefile
@@ -12,6 +12,7 @@ targets += purgatory.ro
KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large
KBUILD_CFLAGS += -m$(BITS)
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
$(call if_changed,ld)
diff --git a/kernel/arch/x86/xen/enlighten.c b/kernel/arch/x86/xen/enlighten.c
index b7de78bdc..ffa41591b 100644
--- a/kernel/arch/x86/xen/enlighten.c
+++ b/kernel/arch/x86/xen/enlighten.c
@@ -74,7 +74,6 @@
#include <asm/mach_traps.h>
#include <asm/mwait.h>
#include <asm/pci_x86.h>
-#include <asm/pat.h>
#include <asm/cpu.h>
#ifdef CONFIG_ACPI
@@ -961,7 +960,7 @@ static void xen_load_sp0(struct tss_struct *tss,
tss->x86_tss.sp0 = thread->sp0;
}
-static void xen_set_iopl_mask(unsigned mask)
+void xen_set_iopl_mask(unsigned mask)
{
struct physdev_set_iopl set_iopl;
@@ -1519,7 +1518,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
{
struct physdev_set_iopl set_iopl;
unsigned long initrd_start = 0;
- u64 pat;
int rc;
if (!xen_start_info)
@@ -1627,13 +1625,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
xen_start_info->nr_pages);
xen_reserve_special_pages();
- /*
- * Modify the cache mode translation tables to match Xen's PAT
- * configuration.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- pat_init_cache_modes(pat);
-
/* keep using Xen gdt for now; no urgent need to change it */
#ifdef CONFIG_X86_32
diff --git a/kernel/arch/x86/xen/mmu.c b/kernel/arch/x86/xen/mmu.c
index cb5e266a8..1e56ff583 100644
--- a/kernel/arch/x86/xen/mmu.c
+++ b/kernel/arch/x86/xen/mmu.c
@@ -1113,7 +1113,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
/* NOTE: The loop is more greedy than the cleanup_highmap variant.
* We include the PMD passed in on _both_ boundaries. */
- for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+ for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
pmd++, vaddr += PMD_SIZE) {
if (pmd_none(*pmd))
continue;
diff --git a/kernel/arch/x86/xen/setup.c b/kernel/arch/x86/xen/setup.c
index 7ab29518a..e34589145 100644
--- a/kernel/arch/x86/xen/setup.c
+++ b/kernel/arch/x86/xen/setup.c
@@ -393,6 +393,9 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
unsigned long i = 0;
unsigned long n = end_pfn - start_pfn;
+ if (remap_pfn == 0)
+ remap_pfn = nr_pages;
+
while (i < n) {
unsigned long cur_pfn = start_pfn + i;
unsigned long left = n - i;
@@ -438,17 +441,29 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
return remap_pfn;
}
-static void __init xen_set_identity_and_remap(unsigned long nr_pages)
+static unsigned long __init xen_count_remap_pages(
+ unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+ unsigned long remap_pages)
+{
+ if (start_pfn >= nr_pages)
+ return remap_pages;
+
+ return remap_pages + min(end_pfn, nr_pages) - start_pfn;
+}
+
+static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
+ unsigned long (*func)(unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long nr_pages, unsigned long last_val))
{
phys_addr_t start = 0;
- unsigned long last_pfn = nr_pages;
+ unsigned long ret_val = 0;
const struct e820entry *entry = xen_e820_map;
int i;
/*
* Combine non-RAM regions and gaps until a RAM region (or the
- * end of the map) is reached, then set the 1:1 map and
- * remap the memory in those non-RAM regions.
+ * end of the map) is reached, then call the provided function
+ * to perform its duty on the non-RAM region.
*
* The combined non-RAM regions are rounded to a whole number
* of pages so any partial pages are accessible via the 1:1
@@ -466,14 +481,13 @@ static void __init xen_set_identity_and_remap(unsigned long nr_pages)
end_pfn = PFN_UP(entry->addr);
if (start_pfn < end_pfn)
- last_pfn = xen_set_identity_and_remap_chunk(
- start_pfn, end_pfn, nr_pages,
- last_pfn);
+ ret_val = func(start_pfn, end_pfn, nr_pages,
+ ret_val);
start = end;
}
}
- pr_info("Released %ld page(s)\n", xen_released_pages);
+ return ret_val;
}
/*
@@ -596,35 +610,6 @@ static void __init xen_ignore_unusable(void)
}
}
-static unsigned long __init xen_count_remap_pages(unsigned long max_pfn)
-{
- unsigned long extra = 0;
- unsigned long start_pfn, end_pfn;
- const struct e820entry *entry = xen_e820_map;
- int i;
-
- end_pfn = 0;
- for (i = 0; i < xen_e820_map_entries; i++, entry++) {
- start_pfn = PFN_DOWN(entry->addr);
- /* Adjacent regions on non-page boundaries handling! */
- end_pfn = min(end_pfn, start_pfn);
-
- if (start_pfn >= max_pfn)
- return extra + max_pfn - end_pfn;
-
- /* Add any holes in map to result. */
- extra += start_pfn - end_pfn;
-
- end_pfn = PFN_UP(entry->addr + entry->size);
- end_pfn = min(end_pfn, max_pfn);
-
- if (entry->type != E820_RAM)
- extra += end_pfn - start_pfn;
- }
-
- return extra;
-}
-
bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
{
struct e820entry *entry;
@@ -804,7 +789,7 @@ char * __init xen_memory_setup(void)
max_pages = xen_get_max_pages();
/* How many extra pages do we need due to remapping? */
- max_pages += xen_count_remap_pages(max_pfn);
+ max_pages += xen_foreach_remap_area(max_pfn, xen_count_remap_pages);
if (max_pages > max_pfn)
extra_pages += max_pages - max_pfn;
@@ -922,7 +907,9 @@ char * __init xen_memory_setup(void)
* Set identity map on non-RAM pages and prepare remapping the
* underlying RAM.
*/
- xen_set_identity_and_remap(max_pfn);
+ xen_foreach_remap_area(max_pfn, xen_set_identity_and_remap_chunk);
+
+ pr_info("Released %ld page(s)\n", xen_released_pages);
return "Xen";
}
diff --git a/kernel/arch/xtensa/kernel/head.S b/kernel/arch/xtensa/kernel/head.S
index 9ed55649a..05e1df943 100644
--- a/kernel/arch/xtensa/kernel/head.S
+++ b/kernel/arch/xtensa/kernel/head.S
@@ -128,7 +128,7 @@ ENTRY(_startup)
wsr a0, icountlevel
.set _index, 0
- .rept XCHAL_NUM_DBREAK - 1
+ .rept XCHAL_NUM_DBREAK
wsr a0, SREG_DBREAKC + _index
.set _index, _index + 1
.endr
diff --git a/kernel/arch/xtensa/mm/cache.c b/kernel/arch/xtensa/mm/cache.c
index d75aa1476..1a804a2f9 100644
--- a/kernel/arch/xtensa/mm/cache.c
+++ b/kernel/arch/xtensa/mm/cache.c
@@ -97,11 +97,11 @@ void clear_user_highpage(struct page *page, unsigned long vaddr)
unsigned long paddr;
void *kvaddr = coherent_kvaddr(page, TLBTEMP_BASE_1, vaddr, &paddr);
- pagefault_disable();
+ preempt_disable();
kmap_invalidate_coherent(page, vaddr);
set_bit(PG_arch_1, &page->flags);
clear_page_alias(kvaddr, paddr);
- pagefault_enable();
+ preempt_enable();
}
void copy_user_highpage(struct page *dst, struct page *src,
@@ -113,11 +113,11 @@ void copy_user_highpage(struct page *dst, struct page *src,
void *src_vaddr = coherent_kvaddr(src, TLBTEMP_BASE_2, vaddr,
&src_paddr);
- pagefault_disable();
+ preempt_disable();
kmap_invalidate_coherent(dst, vaddr);
set_bit(PG_arch_1, &dst->flags);
copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr);
- pagefault_enable();
+ preempt_enable();
}
#endif /* DCACHE_WAY_SIZE > PAGE_SIZE */
diff --git a/kernel/arch/xtensa/platforms/iss/console.c b/kernel/arch/xtensa/platforms/iss/console.c
index 70cb408bc..92d785fef 100644
--- a/kernel/arch/xtensa/platforms/iss/console.c
+++ b/kernel/arch/xtensa/platforms/iss/console.c
@@ -100,21 +100,23 @@ static void rs_poll(unsigned long priv)
{
struct tty_port *port = (struct tty_port *)priv;
int i = 0;
+ int rd = 1;
unsigned char c;
spin_lock(&timer_lock);
while (simc_poll(0)) {
- simc_read(0, &c, 1);
+ rd = simc_read(0, &c, 1);
+ if (rd <= 0)
+ break;
tty_insert_flip_char(port, c, TTY_NORMAL);
i++;
}
if (i)
tty_flip_buffer_push(port);
-
-
- mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE);
+ if (rd)
+ mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE);
spin_unlock(&timer_lock);
}