summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/boot/Makefile16
-rw-r--r--arch/alpha/boot/main.c1
-rw-r--r--arch/alpha/boot/stdio.c306
-rw-r--r--arch/alpha/boot/tools/objstrip.c3
-rw-r--r--arch/alpha/include/asm/cmpxchg.h2
-rw-r--r--arch/alpha/include/asm/pci.h16
-rw-r--r--arch/alpha/include/asm/types.h1
-rw-r--r--arch/alpha/include/asm/unistd.h2
-rw-r--r--arch/alpha/include/uapi/asm/unistd.h3
-rw-r--r--arch/alpha/kernel/core_irongate.c1
-rw-r--r--arch/alpha/kernel/err_ev6.c1
-rw-r--r--arch/alpha/kernel/irq.c1
-rw-r--r--arch/alpha/kernel/osf_sys.c3
-rw-r--r--arch/alpha/kernel/process.c7
-rw-r--r--arch/alpha/kernel/smp.c8
-rw-r--r--arch/alpha/kernel/srmcons.c3
-rw-r--r--arch/alpha/kernel/sys_eiger.c1
-rw-r--r--arch/alpha/kernel/sys_marvel.c2
-rw-r--r--arch/alpha/kernel/sys_nautilus.c1
-rw-r--r--arch/alpha/kernel/systbls.S3
-rw-r--r--arch/alpha/kernel/traps.c1
-rw-r--r--arch/alpha/mm/fault.c5
-rw-r--r--arch/alpha/oprofile/op_model_ev4.c1
-rw-r--r--arch/alpha/oprofile/op_model_ev5.c1
-rw-r--r--arch/alpha/oprofile/op_model_ev6.c1
-rw-r--r--arch/alpha/oprofile/op_model_ev67.c1
-rw-r--r--arch/arc/include/asm/futex.h10
-rw-r--r--arch/arc/include/asm/io.h1
-rw-r--r--arch/arc/mm/fault.c2
-rw-r--r--arch/arm/Kconfig2
-rw-r--r--arch/arm/boot/dts/Makefile2
-rw-r--r--arch/arm/boot/dts/am335x-bone-common.dtsi19
-rw-r--r--arch/arm/boot/dts/am335x-boneblack.dts4
-rw-r--r--arch/arm/boot/dts/am335x-evmsk.dts2
-rw-r--r--arch/arm/boot/dts/am35xx-clocks.dtsi14
-rw-r--r--arch/arm/boot/dts/am57xx-beagle-x15.dts81
-rw-r--r--arch/arm/boot/dts/armada-xp-linksys-mamba.dts5
-rw-r--r--arch/arm/boot/dts/dm816x.dtsi4
-rw-r--r--arch/arm/boot/dts/dra7.dtsi43
-rw-r--r--arch/arm/boot/dts/dra72-evm.dts110
-rw-r--r--arch/arm/boot/dts/dra72x.dtsi11
-rw-r--r--arch/arm/boot/dts/dra74x.dtsi15
-rw-r--r--arch/arm/boot/dts/dra7xx-clocks.dtsi11
-rw-r--r--arch/arm/boot/dts/exynos4412-trats2.dts2
-rw-r--r--arch/arm/boot/dts/imx27.dtsi2
-rw-r--r--arch/arm/boot/dts/imx28-cfa10036.dts3
-rw-r--r--arch/arm/boot/dts/omap3-devkit8000.dts2
-rw-r--r--arch/arm/boot/dts/omap3-n900.dts4
-rw-r--r--arch/arm/boot/dts/socfpga_arria10.dtsi11
-rw-r--r--arch/arm/boot/dts/zynq-7000.dtsi4
-rw-r--r--arch/arm/common/sa1111.c7
-rw-r--r--arch/arm/configs/multi_v7_defconfig2
-rw-r--r--arch/arm/crypto/Kconfig15
-rw-r--r--arch/arm/crypto/Makefile10
-rw-r--r--arch/arm/crypto/aes-ce-core.S7
-rw-r--r--arch/arm/crypto/sha512-armv4.pl649
-rw-r--r--arch/arm/crypto/sha512-armv7-neon.S455
-rw-r--r--arch/arm/crypto/sha512-core.S_shipped1861
-rw-r--r--arch/arm/crypto/sha512-glue.c121
-rw-r--r--arch/arm/crypto/sha512-neon-glue.c98
-rw-r--r--arch/arm/crypto/sha512.h8
-rw-r--r--arch/arm/crypto/sha512_neon_glue.c305
-rw-r--r--arch/arm/include/asm/barrier.h2
-rw-r--r--arch/arm/include/asm/edac.h5
-rw-r--r--arch/arm/include/asm/futex.h13
-rw-r--r--arch/arm/include/asm/io.h1
-rw-r--r--arch/arm/include/asm/kvm_asm.h2
-rw-r--r--arch/arm/include/asm/kvm_host.h5
-rw-r--r--arch/arm/include/asm/pci.h10
-rw-r--r--arch/arm/include/asm/topology.h2
-rw-r--r--arch/arm/kernel/entry-common.S4
-rw-r--r--arch/arm/kernel/perf_event_cpu.c9
-rw-r--r--arch/arm/kvm/Kconfig1
-rw-r--r--arch/arm/kvm/Makefile2
-rw-r--r--arch/arm/kvm/arm.c24
-rw-r--r--arch/arm/kvm/interrupts.S10
-rw-r--r--arch/arm/kvm/interrupts_head.S23
-rw-r--r--arch/arm/kvm/mmu.c14
-rw-r--r--arch/arm/kvm/psci.c18
-rw-r--r--arch/arm/lib/lib1funcs.S4
-rw-r--r--arch/arm/mach-davinci/da850.c1
-rw-r--r--arch/arm/mach-davinci/pm_domain.c32
-rw-r--r--arch/arm/mach-exynos/suspend.c4
-rw-r--r--arch/arm/mach-gemini/gpio.c4
-rw-r--r--arch/arm/mach-imx/gpc.c16
-rw-r--r--arch/arm/mach-keystone/pm_domain.c33
-rw-r--r--arch/arm/mach-lpc32xx/clock.c5
-rw-r--r--arch/arm/mach-omap1/board-nokia770.c2
-rw-r--r--arch/arm/mach-omap1/pm_bus.c37
-rw-r--r--arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c12
-rw-r--r--arch/arm/mach-omap2/display.c32
-rw-r--r--arch/arm/mach-omap2/omap_device.c31
-rw-r--r--arch/arm/mach-omap2/omap_hwmod_7xx_data.c33
-rw-r--r--arch/arm/mach-omap2/sleep34xx.S22
-rw-r--r--arch/arm/mach-pxa/eseries.c1
-rw-r--r--arch/arm/mach-pxa/lubbock.c1
-rw-r--r--arch/arm/mach-pxa/pxa_cplds_irqs.c2
-rw-r--r--arch/arm/mach-pxa/tosa.c1
-rw-r--r--arch/arm/mach-sa1100/neponset.c3
-rw-r--r--arch/arm/mm/fault.c2
-rw-r--r--arch/arm/mm/highmem.c3
-rw-r--r--arch/arm/mm/init.c1
-rw-r--r--arch/arm/mm/mmu.c20
-rw-r--r--arch/arm/net/bpf_jit_32.c10
-rw-r--r--arch/arm/plat-orion/common.c6
-rw-r--r--arch/arm/xen/enlighten.c1
-rw-r--r--arch/arm64/Kconfig3
-rw-r--r--arch/arm64/boot/dts/apm/apm-storm.dtsi110
-rw-r--r--arch/arm64/boot/dts/mediatek/mt8173-evb.dts3
-rw-r--r--arch/arm64/configs/defconfig1
-rw-r--r--arch/arm64/crypto/aes-ce-ccm-glue.c2
-rw-r--r--arch/arm64/include/asm/acpi.h19
-rw-r--r--arch/arm64/include/asm/alternative-asm.h29
-rw-r--r--arch/arm64/include/asm/alternative.h46
-rw-r--r--arch/arm64/include/asm/barrier.h2
-rw-r--r--arch/arm64/include/asm/boot.h14
-rw-r--r--arch/arm64/include/asm/cacheflush.h5
-rw-r--r--arch/arm64/include/asm/cpu_ops.h27
-rw-r--r--arch/arm64/include/asm/cpufeature.h8
-rw-r--r--arch/arm64/include/asm/cpuidle.h8
-rw-r--r--arch/arm64/include/asm/dma-mapping.h18
-rw-r--r--arch/arm64/include/asm/fixmap.h15
-rw-r--r--arch/arm64/include/asm/futex.h4
-rw-r--r--arch/arm64/include/asm/insn.h3
-rw-r--r--arch/arm64/include/asm/io.h9
-rw-r--r--arch/arm64/include/asm/kvm_asm.h7
-rw-r--r--arch/arm64/include/asm/kvm_host.h23
-rw-r--r--arch/arm64/include/asm/mmu.h1
-rw-r--r--arch/arm64/include/asm/perf_event.h7
-rw-r--r--arch/arm64/include/asm/proc-fns.h4
-rw-r--r--arch/arm64/include/asm/processor.h19
-rw-r--r--arch/arm64/include/asm/psci.h12
-rw-r--r--arch/arm64/include/asm/smp.h2
-rw-r--r--arch/arm64/include/asm/smp_plat.h16
-rw-r--r--arch/arm64/include/asm/suspend.h2
-rw-r--r--arch/arm64/include/asm/system_misc.h14
-rw-r--r--arch/arm64/include/asm/tlbflush.h2
-rw-r--r--arch/arm64/include/asm/topology.h2
-rw-r--r--arch/arm64/kernel/acpi.c123
-rw-r--r--arch/arm64/kernel/alternative.c71
-rw-r--r--arch/arm64/kernel/asm-offsets.c1
-rw-r--r--arch/arm64/kernel/cpu_ops.c72
-rw-r--r--arch/arm64/kernel/cpufeature.c16
-rw-r--r--arch/arm64/kernel/cpuidle.c11
-rw-r--r--arch/arm64/kernel/entry.S37
-rw-r--r--arch/arm64/kernel/fpsimd.c31
-rw-r--r--arch/arm64/kernel/head.S52
-rw-r--r--arch/arm64/kernel/insn.c60
-rw-r--r--arch/arm64/kernel/perf_event.c2
-rw-r--r--arch/arm64/kernel/process.c62
-rw-r--r--arch/arm64/kernel/psci.c244
-rw-r--r--arch/arm64/kernel/setup.c37
-rw-r--r--arch/arm64/kernel/signal32.c4
-rw-r--r--arch/arm64/kernel/sleep.S9
-rw-r--r--arch/arm64/kernel/smp.c246
-rw-r--r--arch/arm64/kernel/smp_spin_table.c8
-rw-r--r--arch/arm64/kernel/suspend.c9
-rw-r--r--arch/arm64/kernel/traps.c5
-rw-r--r--arch/arm64/kernel/vdso/Makefile4
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S11
-rw-r--r--arch/arm64/kvm/Kconfig1
-rw-r--r--arch/arm64/kvm/Makefile2
-rw-r--r--arch/arm64/kvm/hyp.S26
-rw-r--r--arch/arm64/kvm/vgic-v2-switch.S3
-rw-r--r--arch/arm64/kvm/vgic-v3-switch.S2
-rw-r--r--arch/arm64/mm/Makefile2
-rw-r--r--arch/arm64/mm/cache.S75
-rw-r--r--arch/arm64/mm/context.c8
-rw-r--r--arch/arm64/mm/dma-mapping.c92
-rw-r--r--arch/arm64/mm/fault.c14
-rw-r--r--arch/arm64/mm/flush.c1
-rw-r--r--arch/arm64/mm/init.c2
-rw-r--r--arch/arm64/mm/mmu.c66
-rw-r--r--arch/arm64/mm/proc.S46
-rw-r--r--arch/avr32/include/asm/cmpxchg.h2
-rw-r--r--arch/avr32/include/asm/io.h1
-rw-r--r--arch/avr32/include/asm/uaccess.h12
-rw-r--r--arch/avr32/mm/fault.c4
-rw-r--r--arch/blackfin/include/asm/io.h1
-rw-r--r--arch/cris/mm/fault.c6
-rw-r--r--arch/frv/include/asm/io.h4
-rw-r--r--arch/frv/include/asm/pci.h10
-rw-r--r--arch/frv/mm/fault.c4
-rw-r--r--arch/frv/mm/highmem.c2
-rw-r--r--arch/hexagon/include/asm/cmpxchg.h1
-rw-r--r--arch/hexagon/include/asm/uaccess.h3
-rw-r--r--arch/ia64/Kconfig23
-rw-r--r--arch/ia64/include/asm/barrier.h7
-rw-r--r--arch/ia64/include/asm/hw_irq.h8
-rw-r--r--arch/ia64/include/asm/intrinsics.h13
-rw-r--r--arch/ia64/include/asm/iosapic.h4
-rw-r--r--arch/ia64/include/asm/irq_remapping.h2
-rw-r--r--arch/ia64/include/asm/module.h6
-rw-r--r--arch/ia64/include/asm/native/inst.h103
-rw-r--r--arch/ia64/include/asm/native/pvchk_inst.h271
-rw-r--r--arch/ia64/include/asm/paravirt.h321
-rw-r--r--arch/ia64/include/asm/paravirt_patch.h143
-rw-r--r--arch/ia64/include/asm/paravirt_privop.h479
-rw-r--r--arch/ia64/include/asm/pci.h32
-rw-r--r--arch/ia64/include/asm/topology.h2
-rw-r--r--arch/ia64/include/uapi/asm/cmpxchg.h2
-rw-r--r--arch/ia64/kernel/Makefile34
-rw-r--r--arch/ia64/kernel/efi.c1
-rw-r--r--arch/ia64/kernel/entry.S41
-rw-r--r--arch/ia64/kernel/fsys.S18
-rw-r--r--arch/ia64/kernel/gate.S9
-rw-r--r--arch/ia64/kernel/gate.lds.S17
-rw-r--r--arch/ia64/kernel/head.S42
-rw-r--r--arch/ia64/kernel/ivt.S4
-rw-r--r--arch/ia64/kernel/minstate.h2
-rw-r--r--arch/ia64/kernel/module.c32
-rw-r--r--arch/ia64/kernel/msi_ia64.c30
-rw-r--r--arch/ia64/kernel/paravirt.c902
-rw-r--r--arch/ia64/kernel/paravirt_inst.h28
-rw-r--r--arch/ia64/kernel/paravirt_patch.c514
-rw-r--r--arch/ia64/kernel/paravirt_patchlist.c81
-rw-r--r--arch/ia64/kernel/paravirt_patchlist.h24
-rw-r--r--arch/ia64/kernel/paravirtentry.S121
-rw-r--r--arch/ia64/kernel/patch.c38
-rw-r--r--arch/ia64/kernel/setup.c12
-rw-r--r--arch/ia64/kernel/smpboot.c5
-rw-r--r--arch/ia64/kernel/time.c29
-rw-r--r--arch/ia64/kernel/vmlinux.lds.S21
-rw-r--r--arch/ia64/mm/fault.c4
-rw-r--r--arch/ia64/mm/init.c9
-rw-r--r--arch/ia64/pci/pci.c13
-rw-r--r--arch/ia64/scripts/pvcheck.sed33
-rw-r--r--arch/m32r/include/asm/cmpxchg.h2
-rw-r--r--arch/m32r/include/asm/io.h1
-rw-r--r--arch/m32r/include/asm/uaccess.h30
-rw-r--r--arch/m32r/mm/fault.c8
-rw-r--r--arch/m68k/configs/amiga_defconfig8
-rw-r--r--arch/m68k/configs/apollo_defconfig8
-rw-r--r--arch/m68k/configs/atari_defconfig8
-rw-r--r--arch/m68k/configs/bvme6000_defconfig8
-rw-r--r--arch/m68k/configs/hp300_defconfig8
-rw-r--r--arch/m68k/configs/mac_defconfig8
-rw-r--r--arch/m68k/configs/multi_defconfig8
-rw-r--r--arch/m68k/configs/mvme147_defconfig8
-rw-r--r--arch/m68k/configs/mvme16x_defconfig8
-rw-r--r--arch/m68k/configs/q40_defconfig8
-rw-r--r--arch/m68k/configs/sun3_defconfig8
-rw-r--r--arch/m68k/configs/sun3x_defconfig8
-rw-r--r--arch/m68k/include/asm/cmpxchg.h1
-rw-r--r--arch/m68k/include/asm/io_mm.h4
-rw-r--r--arch/m68k/include/asm/io_no.h4
-rw-r--r--arch/m68k/include/asm/irqflags.h3
-rw-r--r--arch/m68k/kernel/dma.c19
-rw-r--r--arch/m68k/mm/fault.c4
-rw-r--r--arch/metag/include/asm/barrier.h2
-rw-r--r--arch/metag/include/asm/cmpxchg.h2
-rw-r--r--arch/metag/include/asm/io.h3
-rw-r--r--arch/metag/mm/fault.c2
-rw-r--r--arch/metag/mm/highmem.c4
-rw-r--r--arch/microblaze/include/asm/io.h2
-rw-r--r--arch/microblaze/include/asm/pci.h40
-rw-r--r--arch/microblaze/include/asm/uaccess.h6
-rw-r--r--arch/microblaze/kernel/cpu/cpuinfo.c2
-rw-r--r--arch/microblaze/kernel/dma.c1
-rw-r--r--arch/microblaze/kernel/kgdb.c2
-rw-r--r--arch/microblaze/mm/fault.c8
-rw-r--r--arch/microblaze/mm/highmem.c4
-rw-r--r--arch/mips/Kconfig1
-rw-r--r--arch/mips/ath79/prom.c3
-rw-r--r--arch/mips/ath79/setup.c2
-rw-r--r--arch/mips/cavium-octeon/crypto/octeon-md5.c8
-rw-r--r--arch/mips/cobalt/Makefile3
-rw-r--r--arch/mips/configs/fuloong2e_defconfig2
-rw-r--r--arch/mips/include/asm/barrier.h4
-rw-r--r--arch/mips/include/asm/cmpxchg.h2
-rw-r--r--arch/mips/include/asm/edac.h4
-rw-r--r--arch/mips/include/asm/kvm_host.h2
-rw-r--r--arch/mips/include/asm/mach-ath79/ath79_spi_platform.h4
-rw-r--r--arch/mips/include/asm/pci.h10
-rw-r--r--arch/mips/include/asm/pgtable-bits.h14
-rw-r--r--arch/mips/include/asm/switch_to.h2
-rw-r--r--arch/mips/include/asm/topology.h2
-rw-r--r--arch/mips/include/asm/uaccess.h45
-rw-r--r--arch/mips/kernel/cpu-probe.c3
-rw-r--r--arch/mips/kernel/irq.c4
-rw-r--r--arch/mips/kernel/signal-common.h9
-rw-r--r--arch/mips/kernel/smp-bmips.c2
-rw-r--r--arch/mips/kvm/emulate.c2
-rw-r--r--arch/mips/kvm/mips.c13
-rw-r--r--arch/mips/lib/strnlen_user.S15
-rw-r--r--arch/mips/loongson/common/Makefile4
-rw-r--r--arch/mips/loongson/loongson-3/smp.c2
-rw-r--r--arch/mips/mm/c-r4k.c2
-rw-r--r--arch/mips/mm/fault.c4
-rw-r--r--arch/mips/mm/highmem.c5
-rw-r--r--arch/mips/mm/init.c2
-rw-r--r--arch/mips/net/bpf_jit.c6
-rw-r--r--arch/mips/pci/fixup-cobalt.c1
-rw-r--r--arch/mips/pci/ops-mace.c1
-rw-r--r--arch/mips/pci/pci-lantiq.c1
-rw-r--r--arch/mips/ralink/ill_acc.c2
-rw-r--r--arch/mn10300/include/asm/highmem.h3
-rw-r--r--arch/mn10300/include/asm/io.h1
-rw-r--r--arch/mn10300/include/asm/pci.h13
-rw-r--r--arch/mn10300/mm/fault.c4
-rw-r--r--arch/nios2/include/asm/io.h1
-rw-r--r--arch/nios2/kernel/time.c2
-rw-r--r--arch/nios2/mm/fault.c2
-rw-r--r--arch/parisc/include/asm/cacheflush.h2
-rw-r--r--arch/parisc/include/asm/cmpxchg.h2
-rw-r--r--arch/parisc/include/asm/pci.h19
-rw-r--r--arch/parisc/kernel/traps.c4
-rw-r--r--arch/parisc/mm/fault.c4
-rw-r--r--arch/powerpc/Kconfig2
-rw-r--r--arch/powerpc/Kconfig.debug8
-rw-r--r--arch/powerpc/Makefile50
-rw-r--r--arch/powerpc/boot/dts/b4qds.dtsi12
-rw-r--r--arch/powerpc/boot/dts/fsl/b4420si-post.dtsi15
-rw-r--r--arch/powerpc/boot/dts/fsl/b4860si-post.dtsi84
-rw-r--r--arch/powerpc/boot/dts/fsl/b4si-post.dtsi118
-rw-r--r--arch/powerpc/boot/dts/fsl/p1023si-post.dtsi43
-rw-r--r--arch/powerpc/boot/dts/fsl/p2041si-post.dtsi14
-rw-r--r--arch/powerpc/boot/dts/fsl/p3041si-post.dtsi14
-rw-r--r--arch/powerpc/boot/dts/fsl/p4080si-post.dtsi14
-rw-r--r--arch/powerpc/boot/dts/fsl/p5020si-post.dtsi14
-rw-r--r--arch/powerpc/boot/dts/fsl/p5040si-post.dtsi14
-rw-r--r--arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi20
-rw-r--r--arch/powerpc/boot/dts/fsl/t1023si-post.dtsi330
-rw-r--r--arch/powerpc/boot/dts/fsl/t1024si-post.dtsi100
-rw-r--r--arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi87
-rw-r--r--arch/powerpc/boot/dts/fsl/t1040si-post.dtsi78
-rw-r--r--arch/powerpc/boot/dts/fsl/t2081si-post.dtsi130
-rw-r--r--arch/powerpc/boot/dts/fsl/t4240si-post.dtsi318
-rw-r--r--arch/powerpc/boot/dts/kmcoge4.dts12
-rw-r--r--arch/powerpc/boot/dts/oca4080.dts12
-rw-r--r--arch/powerpc/boot/dts/p1023rdb.dts12
-rw-r--r--arch/powerpc/boot/dts/p2041rdb.dts12
-rw-r--r--arch/powerpc/boot/dts/p3041ds.dts12
-rw-r--r--arch/powerpc/boot/dts/p4080ds.dts12
-rw-r--r--arch/powerpc/boot/dts/p5020ds.dts12
-rw-r--r--arch/powerpc/boot/dts/p5040ds.dts12
-rw-r--r--arch/powerpc/boot/dts/t1023rdb.dts151
-rw-r--r--arch/powerpc/boot/dts/t1024qds.dts251
-rw-r--r--arch/powerpc/boot/dts/t1024rdb.dts185
-rw-r--r--arch/powerpc/boot/dts/t104xqds.dtsi12
-rw-r--r--arch/powerpc/boot/dts/t104xrdb.dtsi12
-rw-r--r--arch/powerpc/boot/dts/t208xqds.dtsi12
-rw-r--r--arch/powerpc/boot/dts/t208xrdb.dtsi12
-rw-r--r--arch/powerpc/boot/dts/t4240qds.dts12
-rw-r--r--arch/powerpc/boot/dts/t4240rdb.dts12
-rw-r--r--arch/powerpc/configs/85xx/xes_mpc85xx_defconfig2
-rw-r--r--arch/powerpc/configs/le.config1
-rw-r--r--arch/powerpc/configs/ppc64_defconfig1
-rw-r--r--arch/powerpc/configs/pseries_defconfig2
-rw-r--r--arch/powerpc/configs/pseries_le_defconfig319
-rw-r--r--arch/powerpc/crypto/md5-glue.c8
-rw-r--r--arch/powerpc/include/asm/barrier.h3
-rw-r--r--arch/powerpc/include/asm/cmpxchg.h1
-rw-r--r--arch/powerpc/include/asm/cputable.h12
-rw-r--r--arch/powerpc/include/asm/cputhreads.h13
-rw-r--r--arch/powerpc/include/asm/device.h3
-rw-r--r--arch/powerpc/include/asm/edac.h4
-rw-r--r--arch/powerpc/include/asm/eeh.h9
-rw-r--r--arch/powerpc/include/asm/icswx.h184
-rw-r--r--arch/powerpc/include/asm/iommu.h119
-rw-r--r--arch/powerpc/include/asm/kvm_book3s_64.h2
-rw-r--r--arch/powerpc/include/asm/kvm_host.h2
-rw-r--r--arch/powerpc/include/asm/kvm_ppc.h14
-rw-r--r--arch/powerpc/include/asm/machdep.h31
-rw-r--r--arch/powerpc/include/asm/mmu-8xx.h33
-rw-r--r--arch/powerpc/include/asm/mmu-hash64.h3
-rw-r--r--arch/powerpc/include/asm/mmu_context.h18
-rw-r--r--arch/powerpc/include/asm/opal-api.h28
-rw-r--r--arch/powerpc/include/asm/opal.h8
-rw-r--r--arch/powerpc/include/asm/page.h4
-rw-r--r--arch/powerpc/include/asm/pci-bridge.h16
-rw-r--r--arch/powerpc/include/asm/pci.h30
-rw-r--r--arch/powerpc/include/asm/pgtable-ppc32.h19
-rw-r--r--arch/powerpc/include/asm/pgtable-ppc64.h28
-rw-r--r--arch/powerpc/include/asm/pnv-pci.h2
-rw-r--r--arch/powerpc/include/asm/ppc-opcode.h13
-rw-r--r--arch/powerpc/include/asm/processor.h9
-rw-r--r--arch/powerpc/include/asm/pte-8xx.h31
-rw-r--r--arch/powerpc/include/asm/pte-book3e.h1
-rw-r--r--arch/powerpc/include/asm/pte-common.h2
-rw-r--r--arch/powerpc/include/asm/pte-hash64.h1
-rw-r--r--arch/powerpc/include/asm/systbl.h2
-rw-r--r--arch/powerpc/include/asm/topology.h2
-rw-r--r--arch/powerpc/include/asm/trace.h20
-rw-r--r--arch/powerpc/include/asm/uaccess.h8
-rw-r--r--arch/powerpc/include/uapi/asm/Kbuild1
-rw-r--r--arch/powerpc/include/uapi/asm/cputable.h1
-rw-r--r--arch/powerpc/include/uapi/asm/eeh.h56
-rw-r--r--arch/powerpc/include/uapi/asm/opal-prd.h58
-rw-r--r--arch/powerpc/include/uapi/asm/tm.h2
-rw-r--r--arch/powerpc/kernel/Makefile3
-rw-r--r--arch/powerpc/kernel/asm-offsets.c2
-rw-r--r--arch/powerpc/kernel/cputable.c4
-rw-r--r--arch/powerpc/kernel/dma.c8
-rw-r--r--arch/powerpc/kernel/eeh.c43
-rw-r--r--arch/powerpc/kernel/eeh_cache.c16
-rw-r--r--arch/powerpc/kernel/eeh_driver.c2
-rw-r--r--arch/powerpc/kernel/entry_64.S37
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S16
-rw-r--r--arch/powerpc/kernel/head_8xx.S110
-rw-r--r--arch/powerpc/kernel/idle_e500.S9
-rw-r--r--arch/powerpc/kernel/iommu.c245
-rw-r--r--arch/powerpc/kernel/mce.c4
-rw-r--r--arch/powerpc/kernel/msi.c11
-rw-r--r--arch/powerpc/kernel/pci-common.c11
-rw-r--r--arch/powerpc/kernel/pci-hotplug.c5
-rw-r--r--arch/powerpc/kernel/process.c1
-rw-r--r--arch/powerpc/kernel/prom.c3
-rw-r--r--arch/powerpc/kernel/prom_init.c1
-rw-r--r--arch/powerpc/kernel/setup_64.c6
-rw-r--r--arch/powerpc/kernel/sysfs.c38
-rw-r--r--arch/powerpc/kernel/tm.S4
-rw-r--r--arch/powerpc/kernel/traps.c45
-rw-r--r--arch/powerpc/kernel/vdso.c135
-rw-r--r--arch/powerpc/kernel/vio.c5
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S1
-rw-r--r--arch/powerpc/kvm/book3s.c9
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv.c20
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S2
-rw-r--r--arch/powerpc/kvm/book3s_pr.c11
-rw-r--r--arch/powerpc/kvm/booke.c13
-rw-r--r--arch/powerpc/kvm/powerpc.c9
-rw-r--r--arch/powerpc/lib/Makefile2
-rw-r--r--arch/powerpc/lib/vmx-helper.c11
-rw-r--r--arch/powerpc/mm/Makefile1
-rw-r--r--arch/powerpc/mm/copro_fault.c9
-rw-r--r--arch/powerpc/mm/fault.c9
-rw-r--r--arch/powerpc/mm/hash_native_64.c2
-rw-r--r--arch/powerpc/mm/hash_utils_64.c4
-rw-r--r--arch/powerpc/mm/highmem.c4
-rw-r--r--arch/powerpc/mm/hugetlbpage.c25
-rw-r--r--arch/powerpc/mm/mem.c2
-rw-r--r--arch/powerpc/mm/mmu_context_hash64.c6
-rw-r--r--arch/powerpc/mm/mmu_context_iommu.c316
-rw-r--r--arch/powerpc/mm/pgtable_64.c11
-rw-r--r--arch/powerpc/mm/tlb_low_64e.S51
-rw-r--r--arch/powerpc/mm/tlb_nohash.c2
-rw-r--r--arch/powerpc/perf/core-book3s.c11
-rw-r--r--arch/powerpc/platforms/52xx/mpc52xx_gpt.c2
-rw-r--r--arch/powerpc/platforms/52xx/mpc52xx_pci.c2
-rw-r--r--arch/powerpc/platforms/85xx/Kconfig2
-rw-r--r--arch/powerpc/platforms/85xx/corenet_generic.c3
-rw-r--r--arch/powerpc/platforms/85xx/smp.c51
-rw-r--r--arch/powerpc/platforms/85xx/twr_p102x.c4
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype11
-rw-r--r--arch/powerpc/platforms/cell/axon_msi.c7
-rw-r--r--arch/powerpc/platforms/cell/iommu.c8
-rw-r--r--arch/powerpc/platforms/embedded6xx/hlwd-pic.c2
-rw-r--r--arch/powerpc/platforms/pasemi/Makefile1
-rw-r--r--arch/powerpc/platforms/pasemi/iommu.c7
-rw-r--r--arch/powerpc/platforms/pasemi/msi.c (renamed from arch/powerpc/sysdev/mpic_pasemi_msi.c)13
-rw-r--r--arch/powerpc/platforms/powernv/Kconfig7
-rw-r--r--arch/powerpc/platforms/powernv/Makefile5
-rw-r--r--arch/powerpc/platforms/powernv/eeh-powernv.c62
-rw-r--r--arch/powerpc/platforms/powernv/idle.c293
-rw-r--r--arch/powerpc/platforms/powernv/opal-async.c3
-rw-r--r--arch/powerpc/platforms/powernv/opal-dump.c56
-rw-r--r--arch/powerpc/platforms/powernv/opal-elog.c32
-rw-r--r--arch/powerpc/platforms/powernv/opal-hmi.c3
-rw-r--r--arch/powerpc/platforms/powernv/opal-irqchip.c253
-rw-r--r--arch/powerpc/platforms/powernv/opal-memory-errors.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal-prd.c449
-rw-r--r--arch/powerpc/platforms/powernv/opal-sensor.c3
-rw-r--r--arch/powerpc/platforms/powernv/opal-sysparam.c43
-rw-r--r--arch/powerpc/platforms/powernv/opal-wrappers.S2
-rw-r--r--arch/powerpc/platforms/powernv/opal.c221
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda.c790
-rw-r--r--arch/powerpc/platforms/powernv/pci-p5ioc2.c45
-rw-r--r--arch/powerpc/platforms/powernv/pci.c204
-rw-r--r--arch/powerpc/platforms/powernv/pci.h31
-rw-r--r--arch/powerpc/platforms/powernv/powernv.h11
-rw-r--r--arch/powerpc/platforms/powernv/setup.c181
-rw-r--r--arch/powerpc/platforms/pseries/dlpar.c3
-rw-r--r--arch/powerpc/platforms/pseries/eeh_pseries.c2
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c179
-rw-r--r--arch/powerpc/platforms/pseries/msi.c16
-rw-r--r--arch/powerpc/sysdev/Makefile2
-rw-r--r--arch/powerpc/sysdev/dart_iommu.c12
-rw-r--r--arch/powerpc/sysdev/fsl_msi.c23
-rw-r--r--arch/powerpc/sysdev/i8259.c2
-rw-r--r--arch/powerpc/sysdev/ipic.c2
-rw-r--r--arch/powerpc/sysdev/mpc8xx_pic.c2
-rw-r--r--arch/powerpc/sysdev/mpic.c2
-rw-r--r--arch/powerpc/sysdev/mpic.h10
-rw-r--r--arch/powerpc/sysdev/mpic_u3msi.c9
-rw-r--r--arch/powerpc/sysdev/mv64x60_pic.c2
-rw-r--r--arch/powerpc/sysdev/ppc4xx_hsta_msi.c7
-rw-r--r--arch/powerpc/sysdev/ppc4xx_msi.c7
-rw-r--r--arch/powerpc/sysdev/qe_lib/qe_ic.c2
-rw-r--r--arch/powerpc/sysdev/tsi108_pci.c2
-rw-r--r--arch/powerpc/sysdev/uic.c4
-rw-r--r--arch/powerpc/sysdev/xics/icp-native.c14
-rw-r--r--arch/powerpc/sysdev/xics/xics-common.c4
-rw-r--r--arch/powerpc/sysdev/xilinx_intc.c2
-rw-r--r--arch/s390/crypto/ghash_s390.c25
-rw-r--r--arch/s390/crypto/prng.c2
-rw-r--r--arch/s390/hypfs/hypfs_sprp.c4
-rw-r--r--arch/s390/include/asm/barrier.h2
-rw-r--r--arch/s390/include/asm/cmpxchg.h2
-rw-r--r--arch/s390/include/asm/io.h1
-rw-r--r--arch/s390/include/asm/kvm_host.h6
-rw-r--r--arch/s390/include/asm/pgtable.h6
-rw-r--r--arch/s390/include/asm/sclp.h34
-rw-r--r--arch/s390/include/asm/timex.h5
-rw-r--r--arch/s390/include/asm/topology.h3
-rw-r--r--arch/s390/include/asm/uaccess.h15
-rw-r--r--arch/s390/kernel/crash_dump.c8
-rw-r--r--arch/s390/kernel/debug.c11
-rw-r--r--arch/s390/kernel/entry.S2
-rw-r--r--arch/s390/kernel/setup.c23
-rw-r--r--arch/s390/kernel/smp.c13
-rw-r--r--arch/s390/kernel/suspend.c2
-rw-r--r--arch/s390/kernel/time.c6
-rw-r--r--arch/s390/kvm/intercept.c16
-rw-r--r--arch/s390/kvm/interrupt.c94
-rw-r--r--arch/s390/kvm/kvm-s390.c89
-rw-r--r--arch/s390/kvm/kvm-s390.h25
-rw-r--r--arch/s390/kvm/priv.c8
-rw-r--r--arch/s390/mm/fault.c2
-rw-r--r--arch/s390/mm/init.c2
-rw-r--r--arch/s390/mm/mem_detect.c4
-rw-r--r--arch/s390/net/bpf_jit.h12
-rw-r--r--arch/s390/net/bpf_jit_comp.c136
-rw-r--r--arch/s390/pci/pci_event.c8
-rw-r--r--arch/score/include/asm/cmpxchg.h2
-rw-r--r--arch/score/include/asm/uaccess.h15
-rw-r--r--arch/score/lib/string.S2
-rw-r--r--arch/score/mm/fault.c3
-rw-r--r--arch/sh/drivers/pci/ops-sh5.c1
-rw-r--r--arch/sh/drivers/pci/pci-sh5.c1
-rw-r--r--arch/sh/include/asm/barrier.h2
-rw-r--r--arch/sh/include/asm/cmpxchg.h2
-rw-r--r--arch/sh/include/asm/pci.h18
-rw-r--r--arch/sh/kernel/cpu/sh4a/clock-sh7734.c3
-rw-r--r--arch/sh/kernel/cpu/sh4a/clock-sh7757.c4
-rw-r--r--arch/sh/kernel/cpu/sh4a/clock-sh7785.c4
-rw-r--r--arch/sh/kernel/cpu/sh4a/clock-sh7786.c4
-rw-r--r--arch/sh/kernel/cpu/sh4a/clock-shx3.c4
-rw-r--r--arch/sh/mm/fault.c5
-rw-r--r--arch/sparc/crypto/md5_glue.c8
-rw-r--r--arch/sparc/include/asm/barrier_64.h4
-rw-r--r--arch/sparc/include/asm/cmpxchg_32.h1
-rw-r--r--arch/sparc/include/asm/cmpxchg_64.h2
-rw-r--r--arch/sparc/include/asm/cpudata_64.h3
-rw-r--r--arch/sparc/include/asm/io_32.h1
-rw-r--r--arch/sparc/include/asm/io_64.h1
-rw-r--r--arch/sparc/include/asm/pci_32.h10
-rw-r--r--arch/sparc/include/asm/pci_64.h19
-rw-r--r--arch/sparc/include/asm/pgtable_64.h22
-rw-r--r--arch/sparc/include/asm/topology_64.h5
-rw-r--r--arch/sparc/include/asm/trap_block.h2
-rw-r--r--arch/sparc/kernel/entry.h2
-rw-r--r--arch/sparc/kernel/leon_pci_grpci2.c1
-rw-r--r--arch/sparc/kernel/mdesc.c136
-rw-r--r--arch/sparc/kernel/pci.c59
-rw-r--r--arch/sparc/kernel/setup_64.c21
-rw-r--r--arch/sparc/kernel/smp_64.c13
-rw-r--r--arch/sparc/kernel/vmlinux.lds.S5
-rw-r--r--arch/sparc/mm/fault_32.c4
-rw-r--r--arch/sparc/mm/fault_64.c4
-rw-r--r--arch/sparc/mm/highmem.c4
-rw-r--r--arch/sparc/mm/init_64.c76
-rw-r--r--arch/tile/Kconfig1
-rw-r--r--arch/tile/include/asm/atomic_64.h3
-rw-r--r--arch/tile/include/asm/edac.h29
-rw-r--r--arch/tile/include/asm/io.h2
-rw-r--r--arch/tile/include/asm/topology.h2
-rw-r--r--arch/tile/include/asm/uaccess.h18
-rw-r--r--arch/tile/mm/fault.c4
-rw-r--r--arch/tile/mm/highmem.c3
-rw-r--r--arch/um/kernel/trap.c5
-rw-r--r--arch/unicore32/include/asm/pci.h10
-rw-r--r--arch/unicore32/mm/fault.c2
-rw-r--r--arch/x86/Kbuild5
-rw-r--r--arch/x86/Kconfig234
-rw-r--r--arch/x86/Kconfig.debug23
-rw-r--r--arch/x86/Makefile23
-rw-r--r--arch/x86/boot/compressed/misc.h11
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c425
-rw-r--r--arch/x86/crypto/camellia_aesni_avx2_glue.c10
-rw-r--r--arch/x86/crypto/camellia_aesni_avx_glue.c15
-rw-r--r--arch/x86/crypto/cast5_avx_glue.c15
-rw-r--r--arch/x86/crypto/cast6_avx_glue.c15
-rw-r--r--arch/x86/crypto/crc32-pclmul_glue.c2
-rw-r--r--arch/x86/crypto/crc32c-intel_glue.c3
-rw-r--r--arch/x86/crypto/crct10dif-pclmul_glue.c2
-rw-r--r--arch/x86/crypto/fpu.c4
-rw-r--r--arch/x86/crypto/ghash-clmulni-intel_glue.c2
-rw-r--r--arch/x86/crypto/serpent_avx2_glue.c11
-rw-r--r--arch/x86/crypto/serpent_avx_glue.c15
-rw-r--r--arch/x86/crypto/sha-mb/sha1_mb.c8
-rw-r--r--arch/x86/crypto/sha1_ssse3_glue.c16
-rw-r--r--arch/x86/crypto/sha256_ssse3_glue.c16
-rw-r--r--arch/x86/crypto/sha512_ssse3_glue.c16
-rw-r--r--arch/x86/crypto/twofish_avx_glue.c16
-rw-r--r--arch/x86/entry/Makefile10
-rw-r--r--arch/x86/entry/calling.h (renamed from arch/x86/include/asm/calling.h)98
-rw-r--r--arch/x86/entry/entry_32.S1248
-rw-r--r--arch/x86/entry/entry_64.S (renamed from arch/x86/kernel/entry_64.S)1125
-rw-r--r--arch/x86/entry/entry_64_compat.S556
-rw-r--r--arch/x86/entry/syscall_32.c (renamed from arch/x86/kernel/syscall_32.c)6
-rw-r--r--arch/x86/entry/syscall_64.c (renamed from arch/x86/kernel/syscall_64.c)0
-rw-r--r--arch/x86/entry/syscalls/Makefile (renamed from arch/x86/syscalls/Makefile)4
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl (renamed from arch/x86/syscalls/syscall_32.tbl)0
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl (renamed from arch/x86/syscalls/syscall_64.tbl)0
-rw-r--r--arch/x86/entry/syscalls/syscallhdr.sh (renamed from arch/x86/syscalls/syscallhdr.sh)0
-rw-r--r--arch/x86/entry/syscalls/syscalltbl.sh (renamed from arch/x86/syscalls/syscalltbl.sh)0
-rw-r--r--arch/x86/entry/thunk_32.S (renamed from arch/x86/lib/thunk_32.S)19
-rw-r--r--arch/x86/entry/thunk_64.S (renamed from arch/x86/lib/thunk_64.S)50
-rw-r--r--arch/x86/entry/vdso/.gitignore (renamed from arch/x86/vdso/.gitignore)0
-rw-r--r--arch/x86/entry/vdso/Makefile (renamed from arch/x86/vdso/Makefile)0
-rwxr-xr-xarch/x86/entry/vdso/checkundef.sh (renamed from arch/x86/vdso/checkundef.sh)0
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c (renamed from arch/x86/vdso/vclock_gettime.c)0
-rw-r--r--arch/x86/entry/vdso/vdso-layout.lds.S (renamed from arch/x86/vdso/vdso-layout.lds.S)0
-rw-r--r--arch/x86/entry/vdso/vdso-note.S (renamed from arch/x86/vdso/vdso-note.S)0
-rw-r--r--arch/x86/entry/vdso/vdso.lds.S (renamed from arch/x86/vdso/vdso.lds.S)0
-rw-r--r--arch/x86/entry/vdso/vdso2c.c (renamed from arch/x86/vdso/vdso2c.c)0
-rw-r--r--arch/x86/entry/vdso/vdso2c.h (renamed from arch/x86/vdso/vdso2c.h)0
-rw-r--r--arch/x86/entry/vdso/vdso32-setup.c (renamed from arch/x86/vdso/vdso32-setup.c)0
-rw-r--r--arch/x86/entry/vdso/vdso32/.gitignore (renamed from arch/x86/vdso/vdso32/.gitignore)0
-rw-r--r--arch/x86/entry/vdso/vdso32/int80.S (renamed from arch/x86/vdso/vdso32/int80.S)0
-rw-r--r--arch/x86/entry/vdso/vdso32/note.S (renamed from arch/x86/vdso/vdso32/note.S)0
-rw-r--r--arch/x86/entry/vdso/vdso32/sigreturn.S (renamed from arch/x86/vdso/vdso32/sigreturn.S)0
-rw-r--r--arch/x86/entry/vdso/vdso32/syscall.S (renamed from arch/x86/vdso/vdso32/syscall.S)0
-rw-r--r--arch/x86/entry/vdso/vdso32/sysenter.S (renamed from arch/x86/vdso/vdso32/sysenter.S)0
-rw-r--r--arch/x86/entry/vdso/vdso32/vclock_gettime.c (renamed from arch/x86/vdso/vdso32/vclock_gettime.c)0
-rw-r--r--arch/x86/entry/vdso/vdso32/vdso-fakesections.c (renamed from arch/x86/vdso/vdso32/vdso-fakesections.c)0
-rw-r--r--arch/x86/entry/vdso/vdso32/vdso32.lds.S (renamed from arch/x86/vdso/vdso32/vdso32.lds.S)0
-rw-r--r--arch/x86/entry/vdso/vdsox32.lds.S (renamed from arch/x86/vdso/vdsox32.lds.S)0
-rw-r--r--arch/x86/entry/vdso/vgetcpu.c (renamed from arch/x86/vdso/vgetcpu.c)0
-rw-r--r--arch/x86/entry/vdso/vma.c (renamed from arch/x86/vdso/vma.c)0
-rw-r--r--arch/x86/entry/vsyscall/Makefile7
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c (renamed from arch/x86/kernel/vsyscall_64.c)0
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_emu_64.S (renamed from arch/x86/kernel/vsyscall_emu_64.S)0
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_gtod.c (renamed from arch/x86/kernel/vsyscall_gtod.c)0
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_trace.h (renamed from arch/x86/kernel/vsyscall_trace.h)2
-rw-r--r--arch/x86/ia32/Makefile2
-rw-r--r--arch/x86/ia32/ia32_signal.c13
-rw-r--r--arch/x86/ia32/ia32entry.S611
-rw-r--r--arch/x86/include/asm/alternative-asm.h18
-rw-r--r--arch/x86/include/asm/alternative.h6
-rw-r--r--arch/x86/include/asm/amd_nb.h11
-rw-r--r--arch/x86/include/asm/apic.h6
-rw-r--r--arch/x86/include/asm/asm.h25
-rw-r--r--arch/x86/include/asm/atomic.h30
-rw-r--r--arch/x86/include/asm/atomic64_64.h8
-rw-r--r--arch/x86/include/asm/barrier.h4
-rw-r--r--arch/x86/include/asm/cacheflush.h6
-rw-r--r--arch/x86/include/asm/cmpxchg.h2
-rw-r--r--arch/x86/include/asm/crypto/glue_helper.h2
-rw-r--r--arch/x86/include/asm/dma-mapping.h46
-rw-r--r--arch/x86/include/asm/dwarf2.h170
-rw-r--r--arch/x86/include/asm/edac.h2
-rw-r--r--arch/x86/include/asm/efi.h2
-rw-r--r--arch/x86/include/asm/entry_arch.h5
-rw-r--r--arch/x86/include/asm/fpu-internal.h626
-rw-r--r--arch/x86/include/asm/fpu/api.h48
-rw-r--r--arch/x86/include/asm/fpu/internal.h694
-rw-r--r--arch/x86/include/asm/fpu/regset.h21
-rw-r--r--arch/x86/include/asm/fpu/signal.h33
-rw-r--r--arch/x86/include/asm/fpu/types.h293
-rw-r--r--arch/x86/include/asm/fpu/xstate.h46
-rw-r--r--arch/x86/include/asm/frame.h7
-rw-r--r--arch/x86/include/asm/hardirq.h4
-rw-r--r--arch/x86/include/asm/hpet.h16
-rw-r--r--arch/x86/include/asm/hw_irq.h140
-rw-r--r--arch/x86/include/asm/i387.h108
-rw-r--r--arch/x86/include/asm/io.h9
-rw-r--r--arch/x86/include/asm/io_apic.h114
-rw-r--r--arch/x86/include/asm/irq.h4
-rw-r--r--arch/x86/include/asm/irq_remapping.h80
-rw-r--r--arch/x86/include/asm/irq_vectors.h51
-rw-r--r--arch/x86/include/asm/irqdomain.h63
-rw-r--r--arch/x86/include/asm/kvm_emulate.h9
-rw-r--r--arch/x86/include/asm/kvm_host.h97
-rw-r--r--arch/x86/include/asm/livepatch.h1
-rw-r--r--arch/x86/include/asm/mce.h28
-rw-r--r--arch/x86/include/asm/microcode.h8
-rw-r--r--arch/x86/include/asm/microcode_amd.h4
-rw-r--r--arch/x86/include/asm/microcode_intel.h13
-rw-r--r--arch/x86/include/asm/mmu_context.h13
-rw-r--r--arch/x86/include/asm/mpx.h74
-rw-r--r--arch/x86/include/asm/msi.h7
-rw-r--r--arch/x86/include/asm/msr-index.h (renamed from arch/x86/include/uapi/asm/msr-index.h)3
-rw-r--r--arch/x86/include/asm/msr.h12
-rw-r--r--arch/x86/include/asm/mtrr.h15
-rw-r--r--arch/x86/include/asm/paravirt.h29
-rw-r--r--arch/x86/include/asm/paravirt_types.h17
-rw-r--r--arch/x86/include/asm/pat.h9
-rw-r--r--arch/x86/include/asm/pci.h12
-rw-r--r--arch/x86/include/asm/pgtable.h8
-rw-r--r--arch/x86/include/asm/pgtable_types.h3
-rw-r--r--arch/x86/include/asm/preempt.h8
-rw-r--r--arch/x86/include/asm/processor.h161
-rw-r--r--arch/x86/include/asm/proto.h10
-rw-r--r--arch/x86/include/asm/ptrace.h2
-rw-r--r--arch/x86/include/asm/pvclock-abi.h1
-rw-r--r--arch/x86/include/asm/pvclock.h1
-rw-r--r--arch/x86/include/asm/qspinlock.h57
-rw-r--r--arch/x86/include/asm/qspinlock_paravirt.h6
-rw-r--r--arch/x86/include/asm/segment.h14
-rw-r--r--arch/x86/include/asm/setup.h7
-rw-r--r--arch/x86/include/asm/simd.h2
-rw-r--r--arch/x86/include/asm/smp.h10
-rw-r--r--arch/x86/include/asm/special_insns.h38
-rw-r--r--arch/x86/include/asm/spinlock.h5
-rw-r--r--arch/x86/include/asm/spinlock_types.h4
-rw-r--r--arch/x86/include/asm/stackprotector.h2
-rw-r--r--arch/x86/include/asm/suspend_32.h2
-rw-r--r--arch/x86/include/asm/suspend_64.h2
-rw-r--r--arch/x86/include/asm/thread_info.h8
-rw-r--r--arch/x86/include/asm/topology.h4
-rw-r--r--arch/x86/include/asm/trace/irq_vectors.h6
-rw-r--r--arch/x86/include/asm/trace/mpx.h132
-rw-r--r--arch/x86/include/asm/traps.h3
-rw-r--r--arch/x86/include/asm/uaccess.h15
-rw-r--r--arch/x86/include/asm/uaccess_32.h10
-rw-r--r--arch/x86/include/asm/user.h12
-rw-r--r--arch/x86/include/asm/x86_init.h21
-rw-r--r--arch/x86/include/asm/xcr.h49
-rw-r--r--arch/x86/include/asm/xor.h2
-rw-r--r--arch/x86/include/asm/xor_32.h2
-rw-r--r--arch/x86/include/asm/xor_avx.h2
-rw-r--r--arch/x86/include/asm/xsave.h257
-rw-r--r--arch/x86/include/uapi/asm/kvm.h14
-rw-r--r--arch/x86/include/uapi/asm/msr.h2
-rw-r--r--arch/x86/include/uapi/asm/mtrr.h8
-rw-r--r--arch/x86/include/uapi/asm/sigcontext.h8
-rw-r--r--arch/x86/kernel/Makefile7
-rw-r--r--arch/x86/kernel/acpi/boot.c73
-rw-r--r--arch/x86/kernel/acpi/wakeup_32.S6
-rw-r--r--arch/x86/kernel/acpi/wakeup_64.S6
-rw-r--r--arch/x86/kernel/alternative.c14
-rw-r--r--arch/x86/kernel/amd_nb.c4
-rw-r--r--arch/x86/kernel/apb_timer.c4
-rw-r--r--arch/x86/kernel/aperture_64.c8
-rw-r--r--arch/x86/kernel/apic/htirq.c173
-rw-r--r--arch/x86/kernel/apic/io_apic.c1303
-rw-r--r--arch/x86/kernel/apic/msi.c417
-rw-r--r--arch/x86/kernel/apic/vector.c448
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c2
-rw-r--r--arch/x86/kernel/asm-offsets.c21
-rw-r--r--arch/x86/kernel/asm-offsets_32.c18
-rw-r--r--arch/x86/kernel/asm-offsets_64.c23
-rw-r--r--arch/x86/kernel/cpu/amd.c41
-rw-r--r--arch/x86/kernel/cpu/bugs.c55
-rw-r--r--arch/x86/kernel/cpu/common.c90
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c8
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c72
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c141
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c44
-rw-r--r--arch/x86/kernel/cpu/microcode/amd_early.c24
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c76
-rw-r--r--arch/x86/kernel/cpu/microcode/core_early.c26
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c79
-rw-r--r--arch/x86/kernel/cpu/microcode/intel_early.c42
-rw-r--r--arch/x86/kernel/cpu/microcode/intel_lib.c45
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c6
-rw-r--r--arch/x86/kernel/cpu/mtrr/cleanup.c3
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c209
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c48
-rw-r--r--arch/x86/kernel/cpu/mtrr/mtrr.h2
-rw-r--r--arch/x86/kernel/cpu/perf_event.c174
-rw-r--r--arch/x86/kernel/cpu/perf_event.h47
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c275
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_bts.c9
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_cqm.c108
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c321
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c13
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_pt.c74
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_rapl.c5
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c26
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h20
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c20
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c6
-rw-r--r--arch/x86/kernel/cpu/proc.c3
-rw-r--r--arch/x86/kernel/crash.c1
-rw-r--r--arch/x86/kernel/devicetree.c41
-rw-r--r--arch/x86/kernel/early-quirks.c8
-rw-r--r--arch/x86/kernel/entry_32.S1401
-rw-r--r--arch/x86/kernel/fpu/Makefile5
-rw-r--r--arch/x86/kernel/fpu/bugs.c71
-rw-r--r--arch/x86/kernel/fpu/core.c523
-rw-r--r--arch/x86/kernel/fpu/init.c354
-rw-r--r--arch/x86/kernel/fpu/regset.c356
-rw-r--r--arch/x86/kernel/fpu/signal.c404
-rw-r--r--arch/x86/kernel/fpu/xstate.c461
-rw-r--r--arch/x86/kernel/head64.c2
-rw-r--r--arch/x86/kernel/head_32.S50
-rw-r--r--arch/x86/kernel/head_64.S24
-rw-r--r--arch/x86/kernel/hpet.c50
-rw-r--r--arch/x86/kernel/i386_ksyms_32.c4
-rw-r--r--arch/x86/kernel/i387.c656
-rw-r--r--arch/x86/kernel/i8259.c8
-rw-r--r--arch/x86/kernel/irq.c62
-rw-r--r--arch/x86/kernel/irq_32.c6
-rw-r--r--arch/x86/kernel/irq_64.c6
-rw-r--r--arch/x86/kernel/irq_work.c10
-rw-r--r--arch/x86/kernel/irqinit.c10
-rw-r--r--arch/x86/kernel/kvm.c47
-rw-r--r--arch/x86/kernel/kvmclock.c14
-rw-r--r--arch/x86/kernel/machine_kexec_64.c4
-rw-r--r--arch/x86/kernel/mpparse.c7
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c24
-rw-r--r--arch/x86/kernel/paravirt.c4
-rw-r--r--arch/x86/kernel/paravirt_patch_32.c22
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c23
-rw-r--r--arch/x86/kernel/pci-dma.c45
-rw-r--r--arch/x86/kernel/pci-swiotlb.c7
-rw-r--r--arch/x86/kernel/process.c61
-rw-r--r--arch/x86/kernel/process_32.c20
-rw-r--r--arch/x86/kernel/process_64.c16
-rw-r--r--arch/x86/kernel/ptrace.c12
-rw-r--r--arch/x86/kernel/setup.c17
-rw-r--r--arch/x86/kernel/signal.c38
-rw-r--r--arch/x86/kernel/smp.c19
-rw-r--r--arch/x86/kernel/smpboot.c88
-rw-r--r--arch/x86/kernel/traps.c155
-rw-r--r--arch/x86/kernel/tsc_sync.c2
-rw-r--r--arch/x86/kernel/uprobes.c10
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c4
-rw-r--r--arch/x86/kernel/x86_init.c10
-rw-r--r--arch/x86/kernel/xsave.c724
-rw-r--r--arch/x86/kvm/Kconfig9
-rw-r--r--arch/x86/kvm/Makefile6
-rw-r--r--arch/x86/kvm/cpuid.c15
-rw-r--r--arch/x86/kvm/cpuid.h16
-rw-r--r--arch/x86/kvm/emulate.c303
-rw-r--r--arch/x86/kvm/ioapic.c9
-rw-r--r--arch/x86/kvm/irq_comm.c14
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h5
-rw-r--r--arch/x86/kvm/lapic.c85
-rw-r--r--arch/x86/kvm/lapic.h15
-rw-r--r--arch/x86/kvm/mmu.c694
-rw-r--r--arch/x86/kvm/mmu.h6
-rw-r--r--arch/x86/kvm/mmu_audit.c20
-rw-r--r--arch/x86/kvm/mtrr.c699
-rw-r--r--arch/x86/kvm/paging_tmpl.h25
-rw-r--r--arch/x86/kvm/pmu.c553
-rw-r--r--arch/x86/kvm/pmu.h118
-rw-r--r--arch/x86/kvm/pmu_amd.c207
-rw-r--r--arch/x86/kvm/pmu_intel.c358
-rw-r--r--arch/x86/kvm/svm.c117
-rw-r--r--arch/x86/kvm/trace.h22
-rw-r--r--arch/x86/kvm/vmx.c369
-rw-r--r--arch/x86/kvm/x86.c978
-rw-r--r--arch/x86/kvm/x86.h8
-rw-r--r--arch/x86/lguest/boot.c6
-rw-r--r--arch/x86/lib/Makefile3
-rw-r--r--arch/x86/lib/atomic64_386_32.S7
-rw-r--r--arch/x86/lib/atomic64_cx8_32.S61
-rw-r--r--arch/x86/lib/checksum_32.S52
-rw-r--r--arch/x86/lib/clear_page_64.S7
-rw-r--r--arch/x86/lib/cmpxchg16b_emu.S12
-rw-r--r--arch/x86/lib/cmpxchg8b_emu.S11
-rw-r--r--arch/x86/lib/copy_page_64.S11
-rw-r--r--arch/x86/lib/copy_user_64.S127
-rw-r--r--arch/x86/lib/copy_user_nocache_64.S136
-rw-r--r--arch/x86/lib/csum-copy_64.S17
-rw-r--r--arch/x86/lib/getuser.S13
-rw-r--r--arch/x86/lib/iomap_copy_64.S3
-rw-r--r--arch/x86/lib/memcpy_64.S3
-rw-r--r--arch/x86/lib/memmove_64.S3
-rw-r--r--arch/x86/lib/memset_64.S5
-rw-r--r--arch/x86/lib/mmx_32.c2
-rw-r--r--arch/x86/lib/msr-reg.S44
-rw-r--r--arch/x86/lib/putuser.S8
-rw-r--r--arch/x86/lib/rwsem.S49
-rw-r--r--arch/x86/lib/usercopy_32.c6
-rw-r--r--arch/x86/math-emu/fpu_aux.c4
-rw-r--r--arch/x86/math-emu/fpu_entry.c20
-rw-r--r--arch/x86/math-emu/fpu_system.h2
-rw-r--r--arch/x86/mm/fault.c5
-rw-r--r--arch/x86/mm/highmem_32.c3
-rw-r--r--arch/x86/mm/init.c6
-rw-r--r--arch/x86/mm/iomap_32.c14
-rw-r--r--arch/x86/mm/ioremap.c78
-rw-r--r--arch/x86/mm/mpx.c519
-rw-r--r--arch/x86/mm/pageattr-test.c1
-rw-r--r--arch/x86/mm/pageattr.c84
-rw-r--r--arch/x86/mm/pat.c337
-rw-r--r--arch/x86/mm/pat_internal.h2
-rw-r--r--arch/x86/mm/pat_rbtree.c6
-rw-r--r--arch/x86/mm/pgtable.c60
-rw-r--r--arch/x86/net/bpf_jit.S1
-rw-r--r--arch/x86/net/bpf_jit_comp.c157
-rw-r--r--arch/x86/pci/acpi.c30
-rw-r--r--arch/x86/pci/i386.c6
-rw-r--r--arch/x86/pci/intel_mid_pci.c6
-rw-r--r--arch/x86/pci/irq.c13
-rw-r--r--arch/x86/platform/Makefile1
-rw-r--r--arch/x86/platform/atom/Makefile1
-rw-r--r--arch/x86/platform/atom/punit_atom_debug.c183
-rw-r--r--arch/x86/platform/efi/efi.c2
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_wdt.c5
-rw-r--r--arch/x86/platform/intel-mid/intel-mid.c18
-rw-r--r--arch/x86/platform/intel-mid/sfi.c30
-rw-r--r--arch/x86/platform/sfi/sfi.c7
-rw-r--r--arch/x86/platform/uv/uv_irq.c298
-rw-r--r--arch/x86/power/cpu.c11
-rw-r--r--arch/x86/power/hibernate_asm_64.S8
-rw-r--r--arch/x86/um/Makefile2
-rw-r--r--arch/x86/um/asm/barrier.h3
-rw-r--r--arch/x86/xen/enlighten.c10
-rw-r--r--arch/x86/xen/p2m.c1
-rw-r--r--arch/x86/xen/spinlock.c64
-rw-r--r--arch/x86/xen/xen-asm_64.S28
-rw-r--r--arch/x86/xen/xen-ops.h2
-rw-r--r--arch/xtensa/Kconfig2
-rw-r--r--arch/xtensa/include/asm/dma-mapping.h13
-rw-r--r--arch/xtensa/include/asm/io.h1
-rw-r--r--arch/xtensa/mm/fault.c4
-rw-r--r--arch/xtensa/mm/highmem.c2
914 files changed, 26715 insertions, 19234 deletions
diff --git a/arch/alpha/boot/Makefile b/arch/alpha/boot/Makefile
index cd143887380a..8399bd0e68e8 100644
--- a/arch/alpha/boot/Makefile
+++ b/arch/alpha/boot/Makefile
@@ -14,6 +14,9 @@ targets := vmlinux.gz vmlinux \
tools/bootpzh bootloader bootpheader bootpzheader
OBJSTRIP := $(obj)/tools/objstrip
+HOSTCFLAGS := -Wall -I$(objtree)/usr/include
+BOOTCFLAGS += -I$(obj) -I$(srctree)/$(obj)
+
# SRM bootable image. Copy to offset 512 of a partition.
$(obj)/bootimage: $(addprefix $(obj)/tools/,mkbb lxboot bootlx) $(obj)/vmlinux.nh
( cat $(obj)/tools/lxboot $(obj)/tools/bootlx $(obj)/vmlinux.nh ) > $@
@@ -96,13 +99,14 @@ $(obj)/tools/bootph: $(obj)/bootpheader $(OBJSTRIP) FORCE
$(obj)/tools/bootpzh: $(obj)/bootpzheader $(OBJSTRIP) FORCE
$(call if_changed,objstrip)
-LDFLAGS_bootloader := -static -uvsprintf -T #-N -relax
-LDFLAGS_bootpheader := -static -uvsprintf -T #-N -relax
-LDFLAGS_bootpzheader := -static -uvsprintf -T #-N -relax
+LDFLAGS_bootloader := -static -T # -N -relax
+LDFLAGS_bootloader := -static -T # -N -relax
+LDFLAGS_bootpheader := -static -T # -N -relax
+LDFLAGS_bootpzheader := -static -T # -N -relax
-OBJ_bootlx := $(obj)/head.o $(obj)/main.o
-OBJ_bootph := $(obj)/head.o $(obj)/bootp.o
-OBJ_bootpzh := $(obj)/head.o $(obj)/bootpz.o $(obj)/misc.o
+OBJ_bootlx := $(obj)/head.o $(obj)/stdio.o $(obj)/main.o
+OBJ_bootph := $(obj)/head.o $(obj)/stdio.o $(obj)/bootp.o
+OBJ_bootpzh := $(obj)/head.o $(obj)/stdio.o $(obj)/bootpz.o $(obj)/misc.o
$(obj)/bootloader: $(obj)/bootloader.lds $(OBJ_bootlx) $(LIBS_Y) FORCE
$(call if_changed,ld)
diff --git a/arch/alpha/boot/main.c b/arch/alpha/boot/main.c
index 3baf2d1e908d..dd6eb4a33582 100644
--- a/arch/alpha/boot/main.c
+++ b/arch/alpha/boot/main.c
@@ -19,7 +19,6 @@
#include "ksize.h"
-extern int vsprintf(char *, const char *, va_list);
extern unsigned long switch_to_osf_pal(unsigned long nr,
struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa,
unsigned long *vptb);
diff --git a/arch/alpha/boot/stdio.c b/arch/alpha/boot/stdio.c
new file mode 100644
index 000000000000..f844dae8a54a
--- /dev/null
+++ b/arch/alpha/boot/stdio.c
@@ -0,0 +1,306 @@
+/*
+ * Copyright (C) Paul Mackerras 1997.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <stdarg.h>
+#include <stddef.h>
+
+size_t strnlen(const char * s, size_t count)
+{
+ const char *sc;
+
+ for (sc = s; count-- && *sc != '\0'; ++sc)
+ /* nothing */;
+ return sc - s;
+}
+
+# define do_div(n, base) ({ \
+ unsigned int __base = (base); \
+ unsigned int __rem; \
+ __rem = ((unsigned long long)(n)) % __base; \
+ (n) = ((unsigned long long)(n)) / __base; \
+ __rem; \
+})
+
+
+static int skip_atoi(const char **s)
+{
+ int i, c;
+
+ for (i = 0; '0' <= (c = **s) && c <= '9'; ++*s)
+ i = i*10 + c - '0';
+ return i;
+}
+
+#define ZEROPAD 1 /* pad with zero */
+#define SIGN 2 /* unsigned/signed long */
+#define PLUS 4 /* show plus */
+#define SPACE 8 /* space if plus */
+#define LEFT 16 /* left justified */
+#define SPECIAL 32 /* 0x */
+#define LARGE 64 /* use 'ABCDEF' instead of 'abcdef' */
+
+static char * number(char * str, unsigned long long num, int base, int size, int precision, int type)
+{
+ char c,sign,tmp[66];
+ const char *digits="0123456789abcdefghijklmnopqrstuvwxyz";
+ int i;
+
+ if (type & LARGE)
+ digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+ if (type & LEFT)
+ type &= ~ZEROPAD;
+ if (base < 2 || base > 36)
+ return 0;
+ c = (type & ZEROPAD) ? '0' : ' ';
+ sign = 0;
+ if (type & SIGN) {
+ if ((signed long long)num < 0) {
+ sign = '-';
+ num = - (signed long long)num;
+ size--;
+ } else if (type & PLUS) {
+ sign = '+';
+ size--;
+ } else if (type & SPACE) {
+ sign = ' ';
+ size--;
+ }
+ }
+ if (type & SPECIAL) {
+ if (base == 16)
+ size -= 2;
+ else if (base == 8)
+ size--;
+ }
+ i = 0;
+ if (num == 0)
+ tmp[i++]='0';
+ else while (num != 0) {
+ tmp[i++] = digits[do_div(num, base)];
+ }
+ if (i > precision)
+ precision = i;
+ size -= precision;
+ if (!(type&(ZEROPAD+LEFT)))
+ while(size-->0)
+ *str++ = ' ';
+ if (sign)
+ *str++ = sign;
+ if (type & SPECIAL) {
+ if (base==8)
+ *str++ = '0';
+ else if (base==16) {
+ *str++ = '0';
+ *str++ = digits[33];
+ }
+ }
+ if (!(type & LEFT))
+ while (size-- > 0)
+ *str++ = c;
+ while (i < precision--)
+ *str++ = '0';
+ while (i-- > 0)
+ *str++ = tmp[i];
+ while (size-- > 0)
+ *str++ = ' ';
+ return str;
+}
+
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+ int len;
+ unsigned long long num;
+ int i, base;
+ char * str;
+ const char *s;
+
+ int flags; /* flags to number() */
+
+ int field_width; /* width of output field */
+ int precision; /* min. # of digits for integers; max
+ number of chars for from string */
+ int qualifier; /* 'h', 'l', or 'L' for integer fields */
+ /* 'z' support added 23/7/1999 S.H. */
+ /* 'z' changed to 'Z' --davidm 1/25/99 */
+
+
+ for (str=buf ; *fmt ; ++fmt) {
+ if (*fmt != '%') {
+ *str++ = *fmt;
+ continue;
+ }
+
+ /* process flags */
+ flags = 0;
+ repeat:
+ ++fmt; /* this also skips first '%' */
+ switch (*fmt) {
+ case '-': flags |= LEFT; goto repeat;
+ case '+': flags |= PLUS; goto repeat;
+ case ' ': flags |= SPACE; goto repeat;
+ case '#': flags |= SPECIAL; goto repeat;
+ case '0': flags |= ZEROPAD; goto repeat;
+ }
+
+ /* get field width */
+ field_width = -1;
+ if ('0' <= *fmt && *fmt <= '9')
+ field_width = skip_atoi(&fmt);
+ else if (*fmt == '*') {
+ ++fmt;
+ /* it's the next argument */
+ field_width = va_arg(args, int);
+ if (field_width < 0) {
+ field_width = -field_width;
+ flags |= LEFT;
+ }
+ }
+
+ /* get the precision */
+ precision = -1;
+ if (*fmt == '.') {
+ ++fmt;
+ if ('0' <= *fmt && *fmt <= '9')
+ precision = skip_atoi(&fmt);
+ else if (*fmt == '*') {
+ ++fmt;
+ /* it's the next argument */
+ precision = va_arg(args, int);
+ }
+ if (precision < 0)
+ precision = 0;
+ }
+
+ /* get the conversion qualifier */
+ qualifier = -1;
+ if (*fmt == 'l' && *(fmt + 1) == 'l') {
+ qualifier = 'q';
+ fmt += 2;
+ } else if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L'
+ || *fmt == 'Z') {
+ qualifier = *fmt;
+ ++fmt;
+ }
+
+ /* default base */
+ base = 10;
+
+ switch (*fmt) {
+ case 'c':
+ if (!(flags & LEFT))
+ while (--field_width > 0)
+ *str++ = ' ';
+ *str++ = (unsigned char) va_arg(args, int);
+ while (--field_width > 0)
+ *str++ = ' ';
+ continue;
+
+ case 's':
+ s = va_arg(args, char *);
+ if (!s)
+ s = "<NULL>";
+
+ len = strnlen(s, precision);
+
+ if (!(flags & LEFT))
+ while (len < field_width--)
+ *str++ = ' ';
+ for (i = 0; i < len; ++i)
+ *str++ = *s++;
+ while (len < field_width--)
+ *str++ = ' ';
+ continue;
+
+ case 'p':
+ if (field_width == -1) {
+ field_width = 2*sizeof(void *);
+ flags |= ZEROPAD;
+ }
+ str = number(str,
+ (unsigned long) va_arg(args, void *), 16,
+ field_width, precision, flags);
+ continue;
+
+
+ case 'n':
+ if (qualifier == 'l') {
+ long * ip = va_arg(args, long *);
+ *ip = (str - buf);
+ } else if (qualifier == 'Z') {
+ size_t * ip = va_arg(args, size_t *);
+ *ip = (str - buf);
+ } else {
+ int * ip = va_arg(args, int *);
+ *ip = (str - buf);
+ }
+ continue;
+
+ case '%':
+ *str++ = '%';
+ continue;
+
+ /* integer number formats - set up the flags and "break" */
+ case 'o':
+ base = 8;
+ break;
+
+ case 'X':
+ flags |= LARGE;
+ case 'x':
+ base = 16;
+ break;
+
+ case 'd':
+ case 'i':
+ flags |= SIGN;
+ case 'u':
+ break;
+
+ default:
+ *str++ = '%';
+ if (*fmt)
+ *str++ = *fmt;
+ else
+ --fmt;
+ continue;
+ }
+ if (qualifier == 'l') {
+ num = va_arg(args, unsigned long);
+ if (flags & SIGN)
+ num = (signed long) num;
+ } else if (qualifier == 'q') {
+ num = va_arg(args, unsigned long long);
+ if (flags & SIGN)
+ num = (signed long long) num;
+ } else if (qualifier == 'Z') {
+ num = va_arg(args, size_t);
+ } else if (qualifier == 'h') {
+ num = (unsigned short) va_arg(args, int);
+ if (flags & SIGN)
+ num = (signed short) num;
+ } else {
+ num = va_arg(args, unsigned int);
+ if (flags & SIGN)
+ num = (signed int) num;
+ }
+ str = number(str, num, base, field_width, precision, flags);
+ }
+ *str = '\0';
+ return str-buf;
+}
+
+int sprintf(char * buf, const char *fmt, ...)
+{
+ va_list args;
+ int i;
+
+ va_start(args, fmt);
+ i=vsprintf(buf,fmt,args);
+ va_end(args);
+ return i;
+}
diff --git a/arch/alpha/boot/tools/objstrip.c b/arch/alpha/boot/tools/objstrip.c
index 367d53d031fc..dee82695f48b 100644
--- a/arch/alpha/boot/tools/objstrip.c
+++ b/arch/alpha/boot/tools/objstrip.c
@@ -27,6 +27,9 @@
#include <linux/param.h>
#ifdef __ELF__
# include <linux/elf.h>
+# define elfhdr elf64_hdr
+# define elf_phdr elf64_phdr
+# define elf_check_arch(x) ((x)->e_machine == EM_ALPHA)
#endif
/* bootfile size must be multiple of BLOCK_SIZE: */
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 429e8cd0d78e..e5117766529e 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -66,6 +66,4 @@
#undef __ASM__MB
#undef ____cmpxchg
-#define __HAVE_ARCH_CMPXCHG 1
-
#endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index f7f680f7457d..8b02afeb6319 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -71,22 +71,6 @@ extern void pcibios_set_master(struct pci_dev *dev);
/* implement the pci_ DMA API in terms of the generic device dma_ one */
#include <asm-generic/pci-dma-compat.h>
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- unsigned long cacheline_size;
- u8 byte;
-
- pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
- if (byte == 0)
- cacheline_size = 1024;
- else
- cacheline_size = (int) byte * 4;
-
- *strat = PCI_DMA_BURST_BOUNDARY;
- *strategy_parameter = cacheline_size;
-}
#endif
/* TODO: integrate with include/asm-generic/pci.h ? */
diff --git a/arch/alpha/include/asm/types.h b/arch/alpha/include/asm/types.h
index f61e1a56c378..4cb4b6d3452c 100644
--- a/arch/alpha/include/asm/types.h
+++ b/arch/alpha/include/asm/types.h
@@ -2,6 +2,5 @@
#define _ALPHA_TYPES_H
#include <asm-generic/int-ll64.h>
-#include <uapi/asm/types.h>
#endif /* _ALPHA_TYPES_H */
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index c509d306db45..a56e608db2f9 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -3,7 +3,7 @@
#include <uapi/asm/unistd.h>
-#define NR_SYSCALLS 511
+#define NR_SYSCALLS 514
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_STAT64
diff --git a/arch/alpha/include/uapi/asm/unistd.h b/arch/alpha/include/uapi/asm/unistd.h
index d214a0358100..aa33bf5aacb6 100644
--- a/arch/alpha/include/uapi/asm/unistd.h
+++ b/arch/alpha/include/uapi/asm/unistd.h
@@ -472,5 +472,8 @@
#define __NR_sched_setattr 508
#define __NR_sched_getattr 509
#define __NR_renameat2 510
+#define __NR_getrandom 511
+#define __NR_memfd_create 512
+#define __NR_execveat 513
#endif /* _UAPI_ALPHA_UNISTD_H */
diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c
index 00096df0f6ad..83d0a359a1b2 100644
--- a/arch/alpha/kernel/core_irongate.c
+++ b/arch/alpha/kernel/core_irongate.c
@@ -22,7 +22,6 @@
#include <linux/bootmem.h>
#include <asm/ptrace.h>
-#include <asm/pci.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
diff --git a/arch/alpha/kernel/err_ev6.c b/arch/alpha/kernel/err_ev6.c
index 253cf1a87481..51267ac5729b 100644
--- a/arch/alpha/kernel/err_ev6.c
+++ b/arch/alpha/kernel/err_ev6.c
@@ -6,7 +6,6 @@
* Error handling code supporting Alpha systems
*/
-#include <linux/init.h>
#include <linux/sched.h>
#include <asm/io.h>
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 7b2be251c30f..51f2c8654253 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -19,7 +19,6 @@
#include <linux/ptrace.h>
#include <linux/interrupt.h>
#include <linux/random.h>
-#include <linux/init.h>
#include <linux/irq.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index e51f578636a5..36dc91ace83a 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1019,14 +1019,13 @@ SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv,
if (tv) {
if (get_tv32((struct timeval *)&kts, tv))
return -EFAULT;
+ kts.tv_nsec *= 1000;
}
if (tz) {
if (copy_from_user(&ktz, tz, sizeof(*tz)))
return -EFAULT;
}
- kts.tv_nsec *= 1000;
-
return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
}
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 1941a07b5811..84d13263ce46 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -236,12 +236,11 @@ release_thread(struct task_struct *dead_task)
}
/*
- * Copy an alpha thread..
+ * Copy architecture-specific thread state
*/
-
int
copy_thread(unsigned long clone_flags, unsigned long usp,
- unsigned long arg,
+ unsigned long kthread_arg,
struct task_struct *p)
{
extern void ret_from_fork(void);
@@ -262,7 +261,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
sizeof(struct switch_stack) + sizeof(struct pt_regs));
childstack->r26 = (unsigned long) ret_from_kernel_thread;
childstack->r9 = usp; /* function */
- childstack->r10 = arg;
+ childstack->r10 = kthread_arg;
childregs->hae = alpha_mv.hae_cache,
childti->pcb.usp = 0;
return 0;
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 99ac36d5de4e..2f24447fef92 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -63,7 +63,6 @@ static struct {
enum ipi_message_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
- IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
};
@@ -506,7 +505,6 @@ setup_profiling_timer(unsigned int multiplier)
return -EINVAL;
}
-
static void
send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
{
@@ -552,10 +550,6 @@ handle_ipi(struct pt_regs *regs)
generic_smp_call_function_interrupt();
break;
- case IPI_CALL_FUNC_SINGLE:
- generic_smp_call_function_single_interrupt();
- break;
-
case IPI_CPU_STOP:
halt();
@@ -606,7 +600,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
void arch_send_call_function_single_ipi(int cpu)
{
- send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+ send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
}
static void
diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 6f01d9ad7b81..72b59511e59a 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -237,8 +237,7 @@ srmcons_init(void)
return -ENODEV;
}
-
-module_init(srmcons_init);
+device_initcall(srmcons_init);
/*
diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c
index 79d69d7f63f8..15f42083bdb3 100644
--- a/arch/alpha/kernel/sys_eiger.c
+++ b/arch/alpha/kernel/sys_eiger.c
@@ -22,7 +22,6 @@
#include <asm/irq.h>
#include <asm/mmu_context.h>
#include <asm/io.h>
-#include <asm/pci.h>
#include <asm/pgtable.h>
#include <asm/core_tsunami.h>
#include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c
index f21d61fab678..24e41bd7d3c9 100644
--- a/arch/alpha/kernel/sys_marvel.c
+++ b/arch/alpha/kernel/sys_marvel.c
@@ -331,7 +331,7 @@ marvel_map_irq(const struct pci_dev *cdev, u8 slot, u8 pin)
pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &intline);
irq = intline;
- msi_loc = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ msi_loc = dev->msi_cap;
msg_ctl = 0;
if (msi_loc)
pci_read_config_word(dev, msi_loc + PCI_MSI_FLAGS, &msg_ctl);
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 700686d04869..2cfaa0e5c577 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -39,7 +39,6 @@
#include <asm/irq.h>
#include <asm/mmu_context.h>
#include <asm/io.h>
-#include <asm/pci.h>
#include <asm/pgtable.h>
#include <asm/core_irongate.h>
#include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index 24789713f1ea..9b62e3fd4f03 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -529,6 +529,9 @@ sys_call_table:
.quad sys_sched_setattr
.quad sys_sched_getattr
.quad sys_renameat2 /* 510 */
+ .quad sys_getrandom
+ .quad sys_memfd_create
+ .quad sys_execveat
.size sys_call_table, . - sys_call_table
.type sys_call_table, @object
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 9c4c189eb22f..74aceead06e9 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -14,7 +14,6 @@
#include <linux/tty.h>
#include <linux/delay.h>
#include <linux/module.h>
-#include <linux/init.h>
#include <linux/kallsyms.h>
#include <linux/ratelimit.h>
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 9d0ac091a52a..4a905bd667e2 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -23,8 +23,7 @@
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/module.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
@@ -107,7 +106,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
/* If we're in an interrupt context, or have no user context,
we must not take the fault. */
- if (!mm || in_atomic())
+ if (!mm || faulthandler_disabled())
goto no_context;
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
diff --git a/arch/alpha/oprofile/op_model_ev4.c b/arch/alpha/oprofile/op_model_ev4.c
index 18aa9b4f94f1..086a0d5445c5 100644
--- a/arch/alpha/oprofile/op_model_ev4.c
+++ b/arch/alpha/oprofile/op_model_ev4.c
@@ -8,7 +8,6 @@
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
diff --git a/arch/alpha/oprofile/op_model_ev5.c b/arch/alpha/oprofile/op_model_ev5.c
index c32f8a0ad925..c300f5ef3482 100644
--- a/arch/alpha/oprofile/op_model_ev5.c
+++ b/arch/alpha/oprofile/op_model_ev5.c
@@ -8,7 +8,6 @@
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
diff --git a/arch/alpha/oprofile/op_model_ev6.c b/arch/alpha/oprofile/op_model_ev6.c
index 1c84cc257fc7..02edf5971614 100644
--- a/arch/alpha/oprofile/op_model_ev6.c
+++ b/arch/alpha/oprofile/op_model_ev6.c
@@ -8,7 +8,6 @@
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
diff --git a/arch/alpha/oprofile/op_model_ev67.c b/arch/alpha/oprofile/op_model_ev67.c
index 34a57a126553..adb1744d20f3 100644
--- a/arch/alpha/oprofile/op_model_ev67.c
+++ b/arch/alpha/oprofile/op_model_ev67.c
@@ -9,7 +9,6 @@
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 4dc64ddebece..05b5aaf5b0f9 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -53,7 +53,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
+ pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
@@ -75,7 +75,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable(); /* subsumes preempt_enable() */
+ pagefault_enable();
if (!ret) {
switch (cmp) {
@@ -104,7 +104,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
return ret;
}
-/* Compare-xchg with preemption disabled.
+/* Compare-xchg with pagefaults disabled.
* Notes:
* -Best-Effort: Exchg happens only if compare succeeds.
* If compare fails, returns; leaving retry/looping to upper layers
@@ -121,7 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
+ pagefault_disable();
/* TBD : can use llock/scond */
__asm__ __volatile__(
@@ -142,7 +142,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
: "cc", "memory");
- pagefault_enable(); /* subsumes preempt_enable() */
+ pagefault_enable();
*uval = val;
return val;
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index cabd518cb253..7cc4ced5dbf4 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -20,6 +20,7 @@ extern void iounmap(const void __iomem *addr);
#define ioremap_nocache(phy, sz) ioremap(phy, sz)
#define ioremap_wc(phy, sz) ioremap(phy, sz)
+#define ioremap_wt(phy, sz) ioremap(phy, sz)
/* Change struct page to physical address */
#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 6a2e006cbcce..d948e4e9d89c 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -86,7 +86,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 45df48ba0b12..325d6f3a596a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -15,6 +15,8 @@ config ARM
select CLONE_BACKWARDS
select CPU_PM if (SUSPEND || CPU_IDLE)
select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
+ select EDAC_SUPPORT
+ select EDAC_ATOMIC_SCRUB
select GENERIC_ALLOCATOR
select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 86217db2937a..992736b5229b 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -223,7 +223,7 @@ dtb-$(CONFIG_SOC_IMX25) += \
imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \
imx25-karo-tx25.dtb \
imx25-pdk.dtb
-dtb-$(CONFIG_SOC_IMX31) += \
+dtb-$(CONFIG_SOC_IMX27) += \
imx27-apf27.dtb \
imx27-apf27dev.dtb \
imx27-eukrea-mbimxsd27-baseboard.dtb \
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index c3255e0c90aa..dbb3f4d2bf84 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -223,6 +223,25 @@
/include/ "tps65217.dtsi"
&tps {
+ /*
+ * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only
+ * mode") at poweroff. Most BeagleBone versions do not support RTC-only
+ * mode and risk hardware damage if this mode is entered.
+ *
+ * For details, see linux-omap mailing list May 2015 thread
+ * [PATCH] ARM: dts: am335x-bone* enable pmic-shutdown-controller
+ * In particular, messages:
+ * http://www.spinics.net/lists/linux-omap/msg118585.html
+ * http://www.spinics.net/lists/linux-omap/msg118615.html
+ *
+ * You can override this later with
+ * &tps { /delete-property/ ti,pmic-shutdown-controller; }
+ * if you want to use RTC-only mode and made sure you are not affected
+ * by the hardware problems. (Tip: double-check by performing a current
+ * measurement after shutdown: it should be less than 1 mA.)
+ */
+ ti,pmic-shutdown-controller;
+
regulators {
dcdc1_reg: regulator@0 {
regulator-name = "vdds_dpr";
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 5c42d259fa68..901739fcb85a 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -80,7 +80,3 @@
status = "okay";
};
};
-
-&rtc {
- system-power-controller;
-};
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 87fc7a35e802..156d05efcb70 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -654,7 +654,7 @@
wlcore: wlcore@2 {
compatible = "ti,wl1271";
reg = <2>;
- interrupt-parent = <&gpio1>;
+ interrupt-parent = <&gpio0>;
interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; /* gpio 31 */
ref-clock-frequency = <38400000>;
};
diff --git a/arch/arm/boot/dts/am35xx-clocks.dtsi b/arch/arm/boot/dts/am35xx-clocks.dtsi
index 518b8fde88b0..18cc826e9db5 100644
--- a/arch/arm/boot/dts/am35xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am35xx-clocks.dtsi
@@ -12,7 +12,7 @@
#clock-cells = <0>;
compatible = "ti,am35xx-gate-clock";
clocks = <&ipss_ick>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <1>;
};
@@ -20,7 +20,7 @@
#clock-cells = <0>;
compatible = "ti,gate-clock";
clocks = <&rmii_ck>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <9>;
};
@@ -28,7 +28,7 @@
#clock-cells = <0>;
compatible = "ti,am35xx-gate-clock";
clocks = <&ipss_ick>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <2>;
};
@@ -36,7 +36,7 @@
#clock-cells = <0>;
compatible = "ti,gate-clock";
clocks = <&pclk_ck>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <10>;
};
@@ -44,7 +44,7 @@
#clock-cells = <0>;
compatible = "ti,am35xx-gate-clock";
clocks = <&ipss_ick>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <0>;
};
@@ -52,7 +52,7 @@
#clock-cells = <0>;
compatible = "ti,gate-clock";
clocks = <&sys_ck>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <8>;
};
@@ -60,7 +60,7 @@
#clock-cells = <0>;
compatible = "ti,am35xx-gate-clock";
clocks = <&sys_ck>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <3>;
};
};
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 7128fad991ac..a42cc377a862 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -19,6 +19,7 @@
rtc0 = &mcp_rtc;
rtc1 = &tps659038_rtc;
rtc2 = &rtc;
+ display0 = &hdmi0;
};
memory {
@@ -103,6 +104,51 @@
pinctrl-names = "default";
pinctrl-0 = <&extcon_usb2_pins>;
};
+
+ hdmi0: connector {
+ compatible = "hdmi-connector";
+ label = "hdmi";
+
+ type = "a";
+
+ port {
+ hdmi_connector_in: endpoint {
+ remote-endpoint = <&tpd12s015_out>;
+ };
+ };
+ };
+
+ tpd12s015: encoder {
+ compatible = "ti,tpd12s015";
+
+ pinctrl-names = "default";
+ pinctrl-0 = <&tpd12s015_pins>;
+
+ gpios = <&gpio7 10 GPIO_ACTIVE_HIGH>, /* gpio7_10, CT CP HPD */
+ <&gpio6 28 GPIO_ACTIVE_HIGH>, /* gpio6_28, LS OE */
+ <&gpio7 12 GPIO_ACTIVE_HIGH>; /* gpio7_12/sp1_cs2, HPD */
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+
+ tpd12s015_in: endpoint {
+ remote-endpoint = <&hdmi_out>;
+ };
+ };
+
+ port@1 {
+ reg = <1>;
+
+ tpd12s015_out: endpoint {
+ remote-endpoint = <&hdmi_connector_in>;
+ };
+ };
+ };
+ };
};
&dra7_pmx_core {
@@ -122,6 +168,13 @@
>;
};
+ hdmi_pins: pinmux_hdmi_pins {
+ pinctrl-single,pins = <
+ 0x408 (PIN_INPUT | MUX_MODE1) /* i2c2_sda.hdmi1_ddc_scl */
+ 0x40c (PIN_INPUT | MUX_MODE1) /* i2c2_scl.hdmi1_ddc_sda */
+ >;
+ };
+
i2c3_pins_default: i2c3_pins_default {
pinctrl-single,pins = <
0x2a4 (PIN_INPUT| MUX_MODE10) /* mcasp1_aclkx.i2c3_sda */
@@ -278,6 +331,14 @@
0x3e8 (PIN_INPUT_PULLUP | MUX_MODE14) /* uart1_ctsn.gpio7_24 */
>;
};
+
+ tpd12s015_pins: pinmux_tpd12s015_pins {
+ pinctrl-single,pins = <
+ 0x3b0 (PIN_OUTPUT | MUX_MODE14) /* gpio7_10 CT_CP_HPD */
+ 0x3b8 (PIN_INPUT_PULLDOWN | MUX_MODE14) /* gpio7_12 HPD */
+ 0x370 (PIN_OUTPUT | MUX_MODE14) /* gpio6_28 LS_OE */
+ >;
+ };
};
&i2c1 {
@@ -608,3 +669,23 @@
};
};
};
+
+&dss {
+ status = "ok";
+
+ vdda_video-supply = <&ldoln_reg>;
+};
+
+&hdmi {
+ status = "ok";
+ vdda-supply = <&ldo3_reg>;
+
+ pinctrl-names = "default";
+ pinctrl-0 = <&hdmi_pins>;
+
+ port {
+ hdmi_out: endpoint {
+ remote-endpoint = <&tpd12s015_in>;
+ };
+ };
+};
diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
index a2cf2154dcdb..fdd187c55aa5 100644
--- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
+++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
@@ -95,6 +95,11 @@
internal-regs {
+ rtc@10300 {
+ /* No crystal connected to the internal RTC */
+ status = "disabled";
+ };
+
/* J10: VCC, NC, RX, NC, TX, GND */
serial@12000 {
status = "okay";
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index de8427be830a..289806adb343 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -382,7 +382,7 @@
ti,hwmods = "usb_otg_hs";
usb0: usb@47401000 {
- compatible = "ti,musb-am33xx";
+ compatible = "ti,musb-dm816";
reg = <0x47401400 0x400
0x47401000 0x200>;
reg-names = "mc", "control";
@@ -422,7 +422,7 @@
};
usb1: usb@47401800 {
- compatible = "ti,musb-am33xx";
+ compatible = "ti,musb-dm816";
reg = <0x47401c00 0x400
0x47401800 0x200>;
reg-names = "mc", "control";
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index f03a091cd076..8f1e25bcecbd 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -131,6 +131,11 @@
regulator-max-microvolt = <3000000>;
};
};
+
+ scm_conf_clocks: clocks {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ };
};
dra7_pmx_core: pinmux@1400 {
@@ -1469,6 +1474,44 @@
clocks = <&sys_clkin1>;
status = "disabled";
};
+
+ dss: dss@58000000 {
+ compatible = "ti,dra7-dss";
+ /* 'reg' defined in dra72x.dtsi and dra74x.dtsi */
+ /* 'clocks' defined in dra72x.dtsi and dra74x.dtsi */
+ status = "disabled";
+ ti,hwmods = "dss_core";
+ /* CTRL_CORE_DSS_PLL_CONTROL */
+ syscon-pll-ctrl = <&scm_conf 0x538>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges;
+
+ dispc@58001000 {
+ compatible = "ti,dra7-dispc";
+ reg = <0x58001000 0x1000>;
+ interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
+ ti,hwmods = "dss_dispc";
+ clocks = <&dss_dss_clk>;
+ clock-names = "fck";
+ /* CTRL_CORE_SMA_SW_1 */
+ syscon-pol = <&scm_conf 0x534>;
+ };
+
+ hdmi: encoder@58060000 {
+ compatible = "ti,dra7-hdmi";
+ reg = <0x58040000 0x200>,
+ <0x58040200 0x80>,
+ <0x58040300 0x80>,
+ <0x58060000 0x19000>;
+ reg-names = "wp", "pll", "phy", "core";
+ interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ ti,hwmods = "dss_hdmi";
+ clocks = <&dss_48mhz_clk>, <&dss_hdmi_clk>;
+ clock-names = "fck", "sys_clk";
+ };
+ };
};
thermal_zones: thermal-zones {
diff --git a/arch/arm/boot/dts/dra72-evm.dts b/arch/arm/boot/dts/dra72-evm.dts
index ce0390f081d9..4e1b60581782 100644
--- a/arch/arm/boot/dts/dra72-evm.dts
+++ b/arch/arm/boot/dts/dra72-evm.dts
@@ -19,6 +19,10 @@
reg = <0x80000000 0x40000000>; /* 1024 MB */
};
+ aliases {
+ display0 = &hdmi0;
+ };
+
evm_3v3: fixedregulator-evm_3v3 {
compatible = "regulator-fixed";
regulator-name = "evm_3v3";
@@ -35,6 +39,51 @@
compatible = "linux,extcon-usb-gpio";
id-gpio = <&pcf_gpio_21 2 GPIO_ACTIVE_HIGH>;
};
+
+ hdmi0: connector {
+ compatible = "hdmi-connector";
+ label = "hdmi";
+
+ type = "a";
+
+ port {
+ hdmi_connector_in: endpoint {
+ remote-endpoint = <&tpd12s015_out>;
+ };
+ };
+ };
+
+ tpd12s015: encoder {
+ compatible = "ti,tpd12s015";
+
+ pinctrl-names = "default";
+ pinctrl-0 = <&tpd12s015_pins>;
+
+ gpios = <&pcf_hdmi 4 GPIO_ACTIVE_HIGH>, /* P4, CT CP HPD */
+ <&pcf_hdmi 5 GPIO_ACTIVE_HIGH>, /* P5, LS OE */
+ <&gpio7 12 GPIO_ACTIVE_HIGH>; /* gpio7_12/sp1_cs2, HPD */
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+
+ tpd12s015_in: endpoint {
+ remote-endpoint = <&hdmi_out>;
+ };
+ };
+
+ port@1 {
+ reg = <1>;
+
+ tpd12s015_out: endpoint {
+ remote-endpoint = <&hdmi_connector_in>;
+ };
+ };
+ };
+ };
};
&dra7_pmx_core {
@@ -45,6 +94,13 @@
>;
};
+ i2c5_pins: pinmux_i2c5_pins {
+ pinctrl-single,pins = <
+ 0x2b4 (PIN_INPUT | MUX_MODE10) /* mcasp1_axr0.i2c5_sda */
+ 0x2b8 (PIN_INPUT | MUX_MODE10) /* mcasp1_axr1.i2c5_scl */
+ >;
+ };
+
nand_default: nand_default {
pinctrl-single,pins = <
0x0 (PIN_INPUT | MUX_MODE0) /* gpmc_ad0 */
@@ -142,6 +198,19 @@
0xb8 (PIN_OUTPUT | MUX_MODE1) /* gpmc_cs2.qspi1_cs0 */
>;
};
+
+ hdmi_pins: pinmux_hdmi_pins {
+ pinctrl-single,pins = <
+ 0x408 (PIN_INPUT | MUX_MODE1) /* i2c2_sda.hdmi1_ddc_scl */
+ 0x40c (PIN_INPUT | MUX_MODE1) /* i2c2_scl.hdmi1_ddc_sda */
+ >;
+ };
+
+ tpd12s015_pins: pinmux_tpd12s015_pins {
+ pinctrl-single,pins = <
+ 0x3b8 (PIN_INPUT_PULLDOWN | MUX_MODE14) /* gpio7_12 HPD */
+ >;
+ };
};
&i2c1 {
@@ -277,6 +346,27 @@
};
};
+&i2c5 {
+ status = "okay";
+ pinctrl-names = "default";
+ pinctrl-0 = <&i2c5_pins>;
+ clock-frequency = <400000>;
+
+ pcf_hdmi: pcf8575@26 {
+ compatible = "nxp,pcf8575";
+ reg = <0x26>;
+ gpio-controller;
+ #gpio-cells = <2>;
+ /*
+ * initial state is used here to keep the mdio interface
+ * selected on RU89 through SEL_VIN4_MUX_S0, VIN2_S1 and
+ * VIN2_S0 driven high otherwise Ethernet stops working
+ * VIN6_SEL_S0 is low, thus selecting McASP3 over VIN6
+ */
+ lines-initial-states = <0x0f2b>;
+ };
+};
+
&uart1 {
status = "okay";
};
@@ -566,3 +656,23 @@
};
};
};
+
+&dss {
+ status = "ok";
+
+ vdda_video-supply = <&ldo5_reg>;
+};
+
+&hdmi {
+ status = "ok";
+ vdda-supply = <&ldo3_reg>;
+
+ pinctrl-names = "default";
+ pinctrl-0 = <&hdmi_pins>;
+
+ port {
+ hdmi_out: endpoint {
+ remote-endpoint = <&tpd12s015_in>;
+ };
+ };
+};
diff --git a/arch/arm/boot/dts/dra72x.dtsi b/arch/arm/boot/dts/dra72x.dtsi
index 03d742f8d572..eaca143faa77 100644
--- a/arch/arm/boot/dts/dra72x.dtsi
+++ b/arch/arm/boot/dts/dra72x.dtsi
@@ -34,3 +34,14 @@
interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
};
};
+
+&dss {
+ reg = <0x58000000 0x80>,
+ <0x58004054 0x4>,
+ <0x58004300 0x20>;
+ reg-names = "dss", "pll1_clkctrl", "pll1";
+
+ clocks = <&dss_dss_clk>,
+ <&dss_video1_clk>;
+ clock-names = "fck", "video1_clk";
+};
diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi
index cc560a70926f..fa995d0ca1f2 100644
--- a/arch/arm/boot/dts/dra74x.dtsi
+++ b/arch/arm/boot/dts/dra74x.dtsi
@@ -73,3 +73,18 @@
};
};
};
+
+&dss {
+ reg = <0x58000000 0x80>,
+ <0x58004054 0x4>,
+ <0x58004300 0x20>,
+ <0x58005054 0x4>,
+ <0x58005300 0x20>;
+ reg-names = "dss", "pll1_clkctrl", "pll1",
+ "pll2_clkctrl", "pll2";
+
+ clocks = <&dss_dss_clk>,
+ <&dss_video1_clk>,
+ <&dss_video2_clk>;
+ clock-names = "fck", "video1_clk", "video2_clk";
+};
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index 3b933f74d000..357bedeebfac 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -1531,6 +1531,7 @@
clocks = <&dpll_per_h12x2_ck>;
ti,bit-shift = <8>;
reg = <0x1120>;
+ ti,set-rate-parent;
};
dss_hdmi_clk: dss_hdmi_clk {
@@ -2136,3 +2137,13 @@
clocks = <&dpll_usb_ck>;
};
};
+
+&scm_conf_clocks {
+ dss_deshdcp_clk: dss_deshdcp_clk {
+ #clock-cells = <0>;
+ compatible = "ti,gate-clock";
+ clocks = <&l3_iclk_div>;
+ ti,bit-shift = <0>;
+ reg = <0x558>;
+ };
+};
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 173ffa479ad3..792394dd0f2a 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -736,7 +736,7 @@
display-timings {
timing-0 {
- clock-frequency = <0>;
+ clock-frequency = <57153600>;
hactive = <720>;
vactive = <1280>;
hfront-porch = <5>;
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 6951b66d1ab7..bc215e4b75fd 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -533,7 +533,7 @@
fec: ethernet@1002b000 {
compatible = "fsl,imx27-fec";
- reg = <0x1002b000 0x4000>;
+ reg = <0x1002b000 0x1000>;
interrupts = <50>;
clocks = <&clks IMX27_CLK_FEC_IPG_GATE>,
<&clks IMX27_CLK_FEC_AHB_GATE>;
diff --git a/arch/arm/boot/dts/imx28-cfa10036.dts b/arch/arm/boot/dts/imx28-cfa10036.dts
index b04b6b8850a7..570aa339a05e 100644
--- a/arch/arm/boot/dts/imx28-cfa10036.dts
+++ b/arch/arm/boot/dts/imx28-cfa10036.dts
@@ -99,6 +99,9 @@
solomon,height = <32>;
solomon,width = <128>;
solomon,page-offset = <0>;
+ solomon,com-lrremap;
+ solomon,com-invdir;
+ solomon,com-offset = <32>;
};
};
diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts
index 134d3f27a8ec..921de6605f07 100644
--- a/arch/arm/boot/dts/omap3-devkit8000.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000.dts
@@ -110,6 +110,8 @@
nand@0,0 {
reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
nand-bus-width = <16>;
+ gpmc,device-width = <2>;
+ ti,nand-ecc-opt = "sw";
gpmc,sync-clk-ps = <0>;
gpmc,cs-on-ns = <0>;
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 5c16145920ea..5f5e0f3d5b64 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -832,8 +832,8 @@
touchscreen-fuzz-x = <4>;
touchscreen-fuzz-y = <7>;
touchscreen-fuzz-pressure = <2>;
- touchscreen-max-x = <4096>;
- touchscreen-max-y = <4096>;
+ touchscreen-size-x = <4096>;
+ touchscreen-size-y = <4096>;
touchscreen-max-pressure = <2048>;
ti,x-plate-ohms = <280>;
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index 8a05c47fd57f..4be75960a603 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -253,6 +253,17 @@
status = "disabled";
};
+ sdr: sdr@ffc25000 {
+ compatible = "syscon";
+ reg = <0xffcfb100 0x80>;
+ };
+
+ sdramedac {
+ compatible = "altr,sdram-edac-a10";
+ altr,sdr-syscon = <&sdr>;
+ interrupts = <0 2 4>, <0 0 4>;
+ };
+
L2: l2-cache@fffff000 {
compatible = "arm,pl310-cache";
reg = <0xfffff000 0x1000>;
diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi
index a5cd2eda3edf..9ea54b3dba09 100644
--- a/arch/arm/boot/dts/zynq-7000.dtsi
+++ b/arch/arm/boot/dts/zynq-7000.dtsi
@@ -193,7 +193,7 @@
};
gem0: ethernet@e000b000 {
- compatible = "cdns,gem";
+ compatible = "cdns,zynq-gem";
reg = <0xe000b000 0x1000>;
status = "disabled";
interrupts = <0 22 4>;
@@ -204,7 +204,7 @@
};
gem1: ethernet@e000c000 {
- compatible = "cdns,gem";
+ compatible = "cdns,zynq-gem";
reg = <0xe000c000 0x1000>;
status = "disabled";
interrupts = <0 45 4>;
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 5cc779c8e9c6..93ee70dbbdd3 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -501,8 +501,8 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
* Register SA1111 interrupt
*/
irq_set_irq_type(sachip->irq, IRQ_TYPE_EDGE_RISING);
- irq_set_handler_data(sachip->irq, sachip);
- irq_set_chained_handler(sachip->irq, sa1111_irq_handler);
+ irq_set_chained_handler_and_data(sachip->irq, sa1111_irq_handler,
+ sachip);
dev_info(sachip->dev, "Providing IRQ%u-%u\n",
sachip->irq_base, sachip->irq_base + SA1111_IRQ_NR - 1);
@@ -836,8 +836,7 @@ static void __sa1111_remove(struct sa1111 *sachip)
clk_unprepare(sachip->clk);
if (sachip->irq != NO_IRQ) {
- irq_set_chained_handler(sachip->irq, NULL);
- irq_set_handler_data(sachip->irq, NULL);
+ irq_set_chained_handler_and_data(sachip->irq, NULL, NULL);
irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
release_mem_region(sachip->phys + SA1111_INTC, 512);
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 0ca4a3eaf65d..fbbb1915c6a9 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -429,7 +429,7 @@ CONFIG_USB_EHCI_EXYNOS=y
CONFIG_USB_EHCI_TEGRA=y
CONFIG_USB_EHCI_HCD_STI=y
CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_ISP1760=y
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_OHCI_HCD_STI=y
CONFIG_USB_OHCI_HCD_PLATFORM=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 8da2207b0072..27ed1b1cd1d7 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -53,20 +53,13 @@ config CRYPTO_SHA256_ARM
SHA-256 secure hash standard (DFIPS 180-2) implemented
using optimized ARM assembler and NEON, when available.
-config CRYPTO_SHA512_ARM_NEON
- tristate "SHA384 and SHA512 digest algorithm (ARM NEON)"
- depends on KERNEL_MODE_NEON
- select CRYPTO_SHA512
+config CRYPTO_SHA512_ARM
+ tristate "SHA-384/512 digest algorithm (ARM-asm and NEON)"
select CRYPTO_HASH
+ depends on !CPU_V7M
help
SHA-512 secure hash standard (DFIPS 180-2) implemented
- using ARM NEON instructions, when available.
-
- This version of SHA implements a 512 bit hash with 256 bits of
- security against collision attacks.
-
- This code also includes SHA-384, a 384 bit hash with 192 bits
- of security against collision attacks.
+ using optimized ARM assembler and NEON, when available.
config CRYPTO_AES_ARM
tristate "AES cipher algorithms (ARM-asm)"
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 6ea828241fcb..fc5150702b64 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
-obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -30,7 +30,8 @@ sha1-arm-y := sha1-armv4-large.o sha1_glue.o
sha1-arm-neon-y := sha1-armv7-neon.o sha1_neon_glue.o
sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
sha256-arm-y := sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
-sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
+sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
+sha512-arm-y := sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
sha1-arm-ce-y := sha1-ce-core.o sha1-ce-glue.o
sha2-arm-ce-y := sha2-ce-core.o sha2-ce-glue.o
aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o
@@ -45,4 +46,7 @@ $(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl
$(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
$(call cmd,perl)
-.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S
+$(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
+ $(call cmd,perl)
+
+.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S $(obj)/sha512-core.S
diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S
index 8cfa468ee570..987aa632c9f0 100644
--- a/arch/arm/crypto/aes-ce-core.S
+++ b/arch/arm/crypto/aes-ce-core.S
@@ -101,15 +101,14 @@
\dround q10, q11
blo 0f @ AES-128: 10 rounds
vld1.8 {q10-q11}, [ip]!
- beq 1f @ AES-192: 12 rounds
\dround q12, q13
+ beq 1f @ AES-192: 12 rounds
vld1.8 {q12-q13}, [ip]
\dround q10, q11
0: \fround q12, q13, q14
bx lr
-1: \dround q12, q13
- \fround q10, q11, q14
+1: \fround q10, q11, q14
bx lr
.endm
@@ -122,8 +121,8 @@
* q2 : third in/output block (_3x version only)
* q8 : first round key
* q9 : secound round key
- * ip : address of 3rd round key
* q14 : final round key
+ * r2 : address of round key array
* r3 : number of rounds
*/
.align 6
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
new file mode 100644
index 000000000000..a2b11a844357
--- /dev/null
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -0,0 +1,649 @@
+#!/usr/bin/env perl
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+#
+# Permission to use under GPL terms is granted.
+# ====================================================================
+
+# SHA512 block procedure for ARMv4. September 2007.
+
+# This code is ~4.5 (four and a half) times faster than code generated
+# by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
+# Xscale PXA250 core].
+#
+# July 2010.
+#
+# Rescheduling for dual-issue pipeline resulted in 6% improvement on
+# Cortex A8 core and ~40 cycles per processed byte.
+
+# February 2011.
+#
+# Profiler-assisted and platform-specific optimization resulted in 7%
+# improvement on Coxtex A8 core and ~38 cycles per byte.
+
+# March 2011.
+#
+# Add NEON implementation. On Cortex A8 it was measured to process
+# one byte in 23.3 cycles or ~60% faster than integer-only code.
+
+# August 2012.
+#
+# Improve NEON performance by 12% on Snapdragon S4. In absolute
+# terms it's 22.6 cycles per byte, which is disappointing result.
+# Technical writers asserted that 3-way S4 pipeline can sustain
+# multiple NEON instructions per cycle, but dual NEON issue could
+# not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+# for further details. On side note Cortex-A15 processes one byte in
+# 16 cycles.
+
+# Byte order [in]dependence. =========================================
+#
+# Originally caller was expected to maintain specific *dword* order in
+# h[0-7], namely with most significant dword at *lower* address, which
+# was reflected in below two parameters as 0 and 4. Now caller is
+# expected to maintain native byte order for whole 64-bit values.
+$hi="HI";
+$lo="LO";
+# ====================================================================
+
+while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+$ctx="r0"; # parameter block
+$inp="r1";
+$len="r2";
+
+$Tlo="r3";
+$Thi="r4";
+$Alo="r5";
+$Ahi="r6";
+$Elo="r7";
+$Ehi="r8";
+$t0="r9";
+$t1="r10";
+$t2="r11";
+$t3="r12";
+############ r13 is stack pointer
+$Ktbl="r14";
+############ r15 is program counter
+
+$Aoff=8*0;
+$Boff=8*1;
+$Coff=8*2;
+$Doff=8*3;
+$Eoff=8*4;
+$Foff=8*5;
+$Goff=8*6;
+$Hoff=8*7;
+$Xoff=8*8;
+
+sub BODY_00_15() {
+my $magic = shift;
+$code.=<<___;
+ @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
+ @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+ @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+ mov $t0,$Elo,lsr#14
+ str $Tlo,[sp,#$Xoff+0]
+ mov $t1,$Ehi,lsr#14
+ str $Thi,[sp,#$Xoff+4]
+ eor $t0,$t0,$Ehi,lsl#18
+ ldr $t2,[sp,#$Hoff+0] @ h.lo
+ eor $t1,$t1,$Elo,lsl#18
+ ldr $t3,[sp,#$Hoff+4] @ h.hi
+ eor $t0,$t0,$Elo,lsr#18
+ eor $t1,$t1,$Ehi,lsr#18
+ eor $t0,$t0,$Ehi,lsl#14
+ eor $t1,$t1,$Elo,lsl#14
+ eor $t0,$t0,$Ehi,lsr#9
+ eor $t1,$t1,$Elo,lsr#9
+ eor $t0,$t0,$Elo,lsl#23
+ eor $t1,$t1,$Ehi,lsl#23 @ Sigma1(e)
+ adds $Tlo,$Tlo,$t0
+ ldr $t0,[sp,#$Foff+0] @ f.lo
+ adc $Thi,$Thi,$t1 @ T += Sigma1(e)
+ ldr $t1,[sp,#$Foff+4] @ f.hi
+ adds $Tlo,$Tlo,$t2
+ ldr $t2,[sp,#$Goff+0] @ g.lo
+ adc $Thi,$Thi,$t3 @ T += h
+ ldr $t3,[sp,#$Goff+4] @ g.hi
+
+ eor $t0,$t0,$t2
+ str $Elo,[sp,#$Eoff+0]
+ eor $t1,$t1,$t3
+ str $Ehi,[sp,#$Eoff+4]
+ and $t0,$t0,$Elo
+ str $Alo,[sp,#$Aoff+0]
+ and $t1,$t1,$Ehi
+ str $Ahi,[sp,#$Aoff+4]
+ eor $t0,$t0,$t2
+ ldr $t2,[$Ktbl,#$lo] @ K[i].lo
+ eor $t1,$t1,$t3 @ Ch(e,f,g)
+ ldr $t3,[$Ktbl,#$hi] @ K[i].hi
+
+ adds $Tlo,$Tlo,$t0
+ ldr $Elo,[sp,#$Doff+0] @ d.lo
+ adc $Thi,$Thi,$t1 @ T += Ch(e,f,g)
+ ldr $Ehi,[sp,#$Doff+4] @ d.hi
+ adds $Tlo,$Tlo,$t2
+ and $t0,$t2,#0xff
+ adc $Thi,$Thi,$t3 @ T += K[i]
+ adds $Elo,$Elo,$Tlo
+ ldr $t2,[sp,#$Boff+0] @ b.lo
+ adc $Ehi,$Ehi,$Thi @ d += T
+ teq $t0,#$magic
+
+ ldr $t3,[sp,#$Coff+0] @ c.lo
+#if __ARM_ARCH__>=7
+ it eq @ Thumb2 thing, sanity check in ARM
+#endif
+ orreq $Ktbl,$Ktbl,#1
+ @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+ @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+ @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+ mov $t0,$Alo,lsr#28
+ mov $t1,$Ahi,lsr#28
+ eor $t0,$t0,$Ahi,lsl#4
+ eor $t1,$t1,$Alo,lsl#4
+ eor $t0,$t0,$Ahi,lsr#2
+ eor $t1,$t1,$Alo,lsr#2
+ eor $t0,$t0,$Alo,lsl#30
+ eor $t1,$t1,$Ahi,lsl#30
+ eor $t0,$t0,$Ahi,lsr#7
+ eor $t1,$t1,$Alo,lsr#7
+ eor $t0,$t0,$Alo,lsl#25
+ eor $t1,$t1,$Ahi,lsl#25 @ Sigma0(a)
+ adds $Tlo,$Tlo,$t0
+ and $t0,$Alo,$t2
+ adc $Thi,$Thi,$t1 @ T += Sigma0(a)
+
+ ldr $t1,[sp,#$Boff+4] @ b.hi
+ orr $Alo,$Alo,$t2
+ ldr $t2,[sp,#$Coff+4] @ c.hi
+ and $Alo,$Alo,$t3
+ and $t3,$Ahi,$t1
+ orr $Ahi,$Ahi,$t1
+ orr $Alo,$Alo,$t0 @ Maj(a,b,c).lo
+ and $Ahi,$Ahi,$t2
+ adds $Alo,$Alo,$Tlo
+ orr $Ahi,$Ahi,$t3 @ Maj(a,b,c).hi
+ sub sp,sp,#8
+ adc $Ahi,$Ahi,$Thi @ h += T
+ tst $Ktbl,#1
+ add $Ktbl,$Ktbl,#8
+___
+}
+$code=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH vstmdb sp!,{d8-d15}
+# define VFP_ABI_POP vldmia sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
+#ifdef __ARMEL__
+# define LO 0
+# define HI 4
+# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1
+#else
+# define HI 0
+# define LO 4
+# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code 32
+#else
+.syntax unified
+# ifdef __thumb2__
+# define adrl adr
+.thumb
+# else
+.code 32
+# endif
+#endif
+
+.type K512,%object
+.align 5
+K512:
+WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
+WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
+WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
+WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
+WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
+WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
+WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
+WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
+WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
+WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
+WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
+WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
+WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
+WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
+WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
+WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
+WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
+WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
+WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
+WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
+WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
+WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
+WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
+WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
+WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
+WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
+WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
+WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
+WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
+WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
+WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
+WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
+WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
+WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
+WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
+WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
+WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
+WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
+WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
+WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
+.size K512,.-K512
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word OPENSSL_armcap_P-sha512_block_data_order
+.skip 32-4
+#else
+.skip 32
+#endif
+
+.global sha512_block_data_order
+.type sha512_block_data_order,%function
+sha512_block_data_order:
+#if __ARM_ARCH__<7
+ sub r3,pc,#8 @ sha512_block_data_order
+#else
+ adr r3,sha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ ldr r12,.LOPENSSL_armcap
+ ldr r12,[r3,r12] @ OPENSSL_armcap_P
+ tst r12,#1
+ bne .LNEON
+#endif
+ add $len,$inp,$len,lsl#7 @ len to point at the end of inp
+ stmdb sp!,{r4-r12,lr}
+ sub $Ktbl,r3,#672 @ K512
+ sub sp,sp,#9*8
+
+ ldr $Elo,[$ctx,#$Eoff+$lo]
+ ldr $Ehi,[$ctx,#$Eoff+$hi]
+ ldr $t0, [$ctx,#$Goff+$lo]
+ ldr $t1, [$ctx,#$Goff+$hi]
+ ldr $t2, [$ctx,#$Hoff+$lo]
+ ldr $t3, [$ctx,#$Hoff+$hi]
+.Loop:
+ str $t0, [sp,#$Goff+0]
+ str $t1, [sp,#$Goff+4]
+ str $t2, [sp,#$Hoff+0]
+ str $t3, [sp,#$Hoff+4]
+ ldr $Alo,[$ctx,#$Aoff+$lo]
+ ldr $Ahi,[$ctx,#$Aoff+$hi]
+ ldr $Tlo,[$ctx,#$Boff+$lo]
+ ldr $Thi,[$ctx,#$Boff+$hi]
+ ldr $t0, [$ctx,#$Coff+$lo]
+ ldr $t1, [$ctx,#$Coff+$hi]
+ ldr $t2, [$ctx,#$Doff+$lo]
+ ldr $t3, [$ctx,#$Doff+$hi]
+ str $Tlo,[sp,#$Boff+0]
+ str $Thi,[sp,#$Boff+4]
+ str $t0, [sp,#$Coff+0]
+ str $t1, [sp,#$Coff+4]
+ str $t2, [sp,#$Doff+0]
+ str $t3, [sp,#$Doff+4]
+ ldr $Tlo,[$ctx,#$Foff+$lo]
+ ldr $Thi,[$ctx,#$Foff+$hi]
+ str $Tlo,[sp,#$Foff+0]
+ str $Thi,[sp,#$Foff+4]
+
+.L00_15:
+#if __ARM_ARCH__<7
+ ldrb $Tlo,[$inp,#7]
+ ldrb $t0, [$inp,#6]
+ ldrb $t1, [$inp,#5]
+ ldrb $t2, [$inp,#4]
+ ldrb $Thi,[$inp,#3]
+ ldrb $t3, [$inp,#2]
+ orr $Tlo,$Tlo,$t0,lsl#8
+ ldrb $t0, [$inp,#1]
+ orr $Tlo,$Tlo,$t1,lsl#16
+ ldrb $t1, [$inp],#8
+ orr $Tlo,$Tlo,$t2,lsl#24
+ orr $Thi,$Thi,$t3,lsl#8
+ orr $Thi,$Thi,$t0,lsl#16
+ orr $Thi,$Thi,$t1,lsl#24
+#else
+ ldr $Tlo,[$inp,#4]
+ ldr $Thi,[$inp],#8
+#ifdef __ARMEL__
+ rev $Tlo,$Tlo
+ rev $Thi,$Thi
+#endif
+#endif
+___
+ &BODY_00_15(0x94);
+$code.=<<___;
+ tst $Ktbl,#1
+ beq .L00_15
+ ldr $t0,[sp,#`$Xoff+8*(16-1)`+0]
+ ldr $t1,[sp,#`$Xoff+8*(16-1)`+4]
+ bic $Ktbl,$Ktbl,#1
+.L16_79:
+ @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
+ @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
+ @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7
+ mov $Tlo,$t0,lsr#1
+ ldr $t2,[sp,#`$Xoff+8*(16-14)`+0]
+ mov $Thi,$t1,lsr#1
+ ldr $t3,[sp,#`$Xoff+8*(16-14)`+4]
+ eor $Tlo,$Tlo,$t1,lsl#31
+ eor $Thi,$Thi,$t0,lsl#31
+ eor $Tlo,$Tlo,$t0,lsr#8
+ eor $Thi,$Thi,$t1,lsr#8
+ eor $Tlo,$Tlo,$t1,lsl#24
+ eor $Thi,$Thi,$t0,lsl#24
+ eor $Tlo,$Tlo,$t0,lsr#7
+ eor $Thi,$Thi,$t1,lsr#7
+ eor $Tlo,$Tlo,$t1,lsl#25
+
+ @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+ @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
+ @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
+ mov $t0,$t2,lsr#19
+ mov $t1,$t3,lsr#19
+ eor $t0,$t0,$t3,lsl#13
+ eor $t1,$t1,$t2,lsl#13
+ eor $t0,$t0,$t3,lsr#29
+ eor $t1,$t1,$t2,lsr#29
+ eor $t0,$t0,$t2,lsl#3
+ eor $t1,$t1,$t3,lsl#3
+ eor $t0,$t0,$t2,lsr#6
+ eor $t1,$t1,$t3,lsr#6
+ ldr $t2,[sp,#`$Xoff+8*(16-9)`+0]
+ eor $t0,$t0,$t3,lsl#26
+
+ ldr $t3,[sp,#`$Xoff+8*(16-9)`+4]
+ adds $Tlo,$Tlo,$t0
+ ldr $t0,[sp,#`$Xoff+8*16`+0]
+ adc $Thi,$Thi,$t1
+
+ ldr $t1,[sp,#`$Xoff+8*16`+4]
+ adds $Tlo,$Tlo,$t2
+ adc $Thi,$Thi,$t3
+ adds $Tlo,$Tlo,$t0
+ adc $Thi,$Thi,$t1
+___
+ &BODY_00_15(0x17);
+$code.=<<___;
+#if __ARM_ARCH__>=7
+ ittt eq @ Thumb2 thing, sanity check in ARM
+#endif
+ ldreq $t0,[sp,#`$Xoff+8*(16-1)`+0]
+ ldreq $t1,[sp,#`$Xoff+8*(16-1)`+4]
+ beq .L16_79
+ bic $Ktbl,$Ktbl,#1
+
+ ldr $Tlo,[sp,#$Boff+0]
+ ldr $Thi,[sp,#$Boff+4]
+ ldr $t0, [$ctx,#$Aoff+$lo]
+ ldr $t1, [$ctx,#$Aoff+$hi]
+ ldr $t2, [$ctx,#$Boff+$lo]
+ ldr $t3, [$ctx,#$Boff+$hi]
+ adds $t0,$Alo,$t0
+ str $t0, [$ctx,#$Aoff+$lo]
+ adc $t1,$Ahi,$t1
+ str $t1, [$ctx,#$Aoff+$hi]
+ adds $t2,$Tlo,$t2
+ str $t2, [$ctx,#$Boff+$lo]
+ adc $t3,$Thi,$t3
+ str $t3, [$ctx,#$Boff+$hi]
+
+ ldr $Alo,[sp,#$Coff+0]
+ ldr $Ahi,[sp,#$Coff+4]
+ ldr $Tlo,[sp,#$Doff+0]
+ ldr $Thi,[sp,#$Doff+4]
+ ldr $t0, [$ctx,#$Coff+$lo]
+ ldr $t1, [$ctx,#$Coff+$hi]
+ ldr $t2, [$ctx,#$Doff+$lo]
+ ldr $t3, [$ctx,#$Doff+$hi]
+ adds $t0,$Alo,$t0
+ str $t0, [$ctx,#$Coff+$lo]
+ adc $t1,$Ahi,$t1
+ str $t1, [$ctx,#$Coff+$hi]
+ adds $t2,$Tlo,$t2
+ str $t2, [$ctx,#$Doff+$lo]
+ adc $t3,$Thi,$t3
+ str $t3, [$ctx,#$Doff+$hi]
+
+ ldr $Tlo,[sp,#$Foff+0]
+ ldr $Thi,[sp,#$Foff+4]
+ ldr $t0, [$ctx,#$Eoff+$lo]
+ ldr $t1, [$ctx,#$Eoff+$hi]
+ ldr $t2, [$ctx,#$Foff+$lo]
+ ldr $t3, [$ctx,#$Foff+$hi]
+ adds $Elo,$Elo,$t0
+ str $Elo,[$ctx,#$Eoff+$lo]
+ adc $Ehi,$Ehi,$t1
+ str $Ehi,[$ctx,#$Eoff+$hi]
+ adds $t2,$Tlo,$t2
+ str $t2, [$ctx,#$Foff+$lo]
+ adc $t3,$Thi,$t3
+ str $t3, [$ctx,#$Foff+$hi]
+
+ ldr $Alo,[sp,#$Goff+0]
+ ldr $Ahi,[sp,#$Goff+4]
+ ldr $Tlo,[sp,#$Hoff+0]
+ ldr $Thi,[sp,#$Hoff+4]
+ ldr $t0, [$ctx,#$Goff+$lo]
+ ldr $t1, [$ctx,#$Goff+$hi]
+ ldr $t2, [$ctx,#$Hoff+$lo]
+ ldr $t3, [$ctx,#$Hoff+$hi]
+ adds $t0,$Alo,$t0
+ str $t0, [$ctx,#$Goff+$lo]
+ adc $t1,$Ahi,$t1
+ str $t1, [$ctx,#$Goff+$hi]
+ adds $t2,$Tlo,$t2
+ str $t2, [$ctx,#$Hoff+$lo]
+ adc $t3,$Thi,$t3
+ str $t3, [$ctx,#$Hoff+$hi]
+
+ add sp,sp,#640
+ sub $Ktbl,$Ktbl,#640
+
+ teq $inp,$len
+ bne .Loop
+
+ add sp,sp,#8*9 @ destroy frame
+#if __ARM_ARCH__>=5
+ ldmia sp!,{r4-r12,pc}
+#else
+ ldmia sp!,{r4-r12,lr}
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size sha512_block_data_order,.-sha512_block_data_order
+___
+
+{
+my @Sigma0=(28,34,39);
+my @Sigma1=(14,18,41);
+my @sigma0=(1, 8, 7);
+my @sigma1=(19,61,6);
+
+my $Ktbl="r3";
+my $cnt="r12"; # volatile register known as ip, intra-procedure-call scratch
+
+my @X=map("d$_",(0..15));
+my @V=($A,$B,$C,$D,$E,$F,$G,$H)=map("d$_",(16..23));
+
+sub NEON_00_15() {
+my $i=shift;
+my ($a,$b,$c,$d,$e,$f,$g,$h)=@_;
+my ($t0,$t1,$t2,$T1,$K,$Ch,$Maj)=map("d$_",(24..31)); # temps
+
+$code.=<<___ if ($i<16 || $i&1);
+ vshr.u64 $t0,$e,#@Sigma1[0] @ $i
+#if $i<16
+ vld1.64 {@X[$i%16]},[$inp]! @ handles unaligned
+#endif
+ vshr.u64 $t1,$e,#@Sigma1[1]
+#if $i>0
+ vadd.i64 $a,$Maj @ h+=Maj from the past
+#endif
+ vshr.u64 $t2,$e,#@Sigma1[2]
+___
+$code.=<<___;
+ vld1.64 {$K},[$Ktbl,:64]! @ K[i++]
+ vsli.64 $t0,$e,#`64-@Sigma1[0]`
+ vsli.64 $t1,$e,#`64-@Sigma1[1]`
+ vmov $Ch,$e
+ vsli.64 $t2,$e,#`64-@Sigma1[2]`
+#if $i<16 && defined(__ARMEL__)
+ vrev64.8 @X[$i],@X[$i]
+#endif
+ veor $t1,$t0
+ vbsl $Ch,$f,$g @ Ch(e,f,g)
+ vshr.u64 $t0,$a,#@Sigma0[0]
+ veor $t2,$t1 @ Sigma1(e)
+ vadd.i64 $T1,$Ch,$h
+ vshr.u64 $t1,$a,#@Sigma0[1]
+ vsli.64 $t0,$a,#`64-@Sigma0[0]`
+ vadd.i64 $T1,$t2
+ vshr.u64 $t2,$a,#@Sigma0[2]
+ vadd.i64 $K,@X[$i%16]
+ vsli.64 $t1,$a,#`64-@Sigma0[1]`
+ veor $Maj,$a,$b
+ vsli.64 $t2,$a,#`64-@Sigma0[2]`
+ veor $h,$t0,$t1
+ vadd.i64 $T1,$K
+ vbsl $Maj,$c,$b @ Maj(a,b,c)
+ veor $h,$t2 @ Sigma0(a)
+ vadd.i64 $d,$T1
+ vadd.i64 $Maj,$T1
+ @ vadd.i64 $h,$Maj
+___
+}
+
+sub NEON_16_79() {
+my $i=shift;
+
+if ($i&1) { &NEON_00_15($i,@_); return; }
+
+# 2x-vectorized, therefore runs every 2nd round
+my @X=map("q$_",(0..7)); # view @X as 128-bit vector
+my ($t0,$t1,$s0,$s1) = map("q$_",(12..15)); # temps
+my ($d0,$d1,$d2) = map("d$_",(24..26)); # temps from NEON_00_15
+my $e=@_[4]; # $e from NEON_00_15
+$i /= 2;
+$code.=<<___;
+ vshr.u64 $t0,@X[($i+7)%8],#@sigma1[0]
+ vshr.u64 $t1,@X[($i+7)%8],#@sigma1[1]
+ vadd.i64 @_[0],d30 @ h+=Maj from the past
+ vshr.u64 $s1,@X[($i+7)%8],#@sigma1[2]
+ vsli.64 $t0,@X[($i+7)%8],#`64-@sigma1[0]`
+ vext.8 $s0,@X[$i%8],@X[($i+1)%8],#8 @ X[i+1]
+ vsli.64 $t1,@X[($i+7)%8],#`64-@sigma1[1]`
+ veor $s1,$t0
+ vshr.u64 $t0,$s0,#@sigma0[0]
+ veor $s1,$t1 @ sigma1(X[i+14])
+ vshr.u64 $t1,$s0,#@sigma0[1]
+ vadd.i64 @X[$i%8],$s1
+ vshr.u64 $s1,$s0,#@sigma0[2]
+ vsli.64 $t0,$s0,#`64-@sigma0[0]`
+ vsli.64 $t1,$s0,#`64-@sigma0[1]`
+ vext.8 $s0,@X[($i+4)%8],@X[($i+5)%8],#8 @ X[i+9]
+ veor $s1,$t0
+ vshr.u64 $d0,$e,#@Sigma1[0] @ from NEON_00_15
+ vadd.i64 @X[$i%8],$s0
+ vshr.u64 $d1,$e,#@Sigma1[1] @ from NEON_00_15
+ veor $s1,$t1 @ sigma0(X[i+1])
+ vshr.u64 $d2,$e,#@Sigma1[2] @ from NEON_00_15
+ vadd.i64 @X[$i%8],$s1
+___
+ &NEON_00_15(2*$i,@_);
+}
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.arch armv7-a
+.fpu neon
+
+.global sha512_block_data_order_neon
+.type sha512_block_data_order_neon,%function
+.align 4
+sha512_block_data_order_neon:
+.LNEON:
+ dmb @ errata #451034 on early Cortex A8
+ add $len,$inp,$len,lsl#7 @ len to point at the end of inp
+ VFP_ABI_PUSH
+ adrl $Ktbl,K512
+ vldmia $ctx,{$A-$H} @ load context
+.Loop_neon:
+___
+for($i=0;$i<16;$i++) { &NEON_00_15($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+ mov $cnt,#4
+.L16_79_neon:
+ subs $cnt,#1
+___
+for(;$i<32;$i++) { &NEON_16_79($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+ bne .L16_79_neon
+
+ vadd.i64 $A,d30 @ h+=Maj from the past
+ vldmia $ctx,{d24-d31} @ load context to temp
+ vadd.i64 q8,q12 @ vectorized accumulate
+ vadd.i64 q9,q13
+ vadd.i64 q10,q14
+ vadd.i64 q11,q15
+ vstmia $ctx,{$A-$H} @ save context
+ teq $inp,$len
+ sub $Ktbl,#640 @ rewind K512
+ bne .Loop_neon
+
+ VFP_ABI_POP
+ ret @ bx lr
+.size sha512_block_data_order_neon,.-sha512_block_data_order_neon
+#endif
+___
+}
+$code.=<<___;
+.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>"
+.align 2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm OPENSSL_armcap_P,4,4
+#endif
+___
+
+$code =~ s/\`([^\`]*)\`/eval $1/gem;
+$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm; # make it possible to compile with -march=armv4
+$code =~ s/\bret\b/bx lr/gm;
+
+open SELF,$0;
+while(<SELF>) {
+ next if (/^#!/);
+ last if (!s/^#/@/ and !/^$/);
+ print;
+}
+close SELF;
+
+print $code;
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/sha512-armv7-neon.S b/arch/arm/crypto/sha512-armv7-neon.S
deleted file mode 100644
index fe99472e507c..000000000000
--- a/arch/arm/crypto/sha512-armv7-neon.S
+++ /dev/null
@@ -1,455 +0,0 @@
-/* sha512-armv7-neon.S - ARM/NEON assembly implementation of SHA-512 transform
- *
- * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
-#include <linux/linkage.h>
-
-
-.syntax unified
-.code 32
-.fpu neon
-
-.text
-
-/* structure of SHA512_CONTEXT */
-#define hd_a 0
-#define hd_b ((hd_a) + 8)
-#define hd_c ((hd_b) + 8)
-#define hd_d ((hd_c) + 8)
-#define hd_e ((hd_d) + 8)
-#define hd_f ((hd_e) + 8)
-#define hd_g ((hd_f) + 8)
-
-/* register macros */
-#define RK %r2
-
-#define RA d0
-#define RB d1
-#define RC d2
-#define RD d3
-#define RE d4
-#define RF d5
-#define RG d6
-#define RH d7
-
-#define RT0 d8
-#define RT1 d9
-#define RT2 d10
-#define RT3 d11
-#define RT4 d12
-#define RT5 d13
-#define RT6 d14
-#define RT7 d15
-
-#define RT01q q4
-#define RT23q q5
-#define RT45q q6
-#define RT67q q7
-
-#define RW0 d16
-#define RW1 d17
-#define RW2 d18
-#define RW3 d19
-#define RW4 d20
-#define RW5 d21
-#define RW6 d22
-#define RW7 d23
-#define RW8 d24
-#define RW9 d25
-#define RW10 d26
-#define RW11 d27
-#define RW12 d28
-#define RW13 d29
-#define RW14 d30
-#define RW15 d31
-
-#define RW01q q8
-#define RW23q q9
-#define RW45q q10
-#define RW67q q11
-#define RW89q q12
-#define RW1011q q13
-#define RW1213q q14
-#define RW1415q q15
-
-/***********************************************************************
- * ARM assembly implementation of sha512 transform
- ***********************************************************************/
-#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \
- rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \
- /* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
- vshr.u64 RT2, re, #14; \
- vshl.u64 RT3, re, #64 - 14; \
- interleave_op(arg1); \
- vshr.u64 RT4, re, #18; \
- vshl.u64 RT5, re, #64 - 18; \
- vld1.64 {RT0}, [RK]!; \
- veor.64 RT23q, RT23q, RT45q; \
- vshr.u64 RT4, re, #41; \
- vshl.u64 RT5, re, #64 - 41; \
- vadd.u64 RT0, RT0, rw0; \
- veor.64 RT23q, RT23q, RT45q; \
- vmov.64 RT7, re; \
- veor.64 RT1, RT2, RT3; \
- vbsl.64 RT7, rf, rg; \
- \
- vadd.u64 RT1, RT1, rh; \
- vshr.u64 RT2, ra, #28; \
- vshl.u64 RT3, ra, #64 - 28; \
- vadd.u64 RT1, RT1, RT0; \
- vshr.u64 RT4, ra, #34; \
- vshl.u64 RT5, ra, #64 - 34; \
- vadd.u64 RT1, RT1, RT7; \
- \
- /* h = Sum0 (a) + Maj (a, b, c); */ \
- veor.64 RT23q, RT23q, RT45q; \
- vshr.u64 RT4, ra, #39; \
- vshl.u64 RT5, ra, #64 - 39; \
- veor.64 RT0, ra, rb; \
- veor.64 RT23q, RT23q, RT45q; \
- vbsl.64 RT0, rc, rb; \
- vadd.u64 rd, rd, RT1; /* d+=t1; */ \
- veor.64 rh, RT2, RT3; \
- \
- /* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
- vshr.u64 RT2, rd, #14; \
- vshl.u64 RT3, rd, #64 - 14; \
- vadd.u64 rh, rh, RT0; \
- vshr.u64 RT4, rd, #18; \
- vshl.u64 RT5, rd, #64 - 18; \
- vadd.u64 rh, rh, RT1; /* h+=t1; */ \
- vld1.64 {RT0}, [RK]!; \
- veor.64 RT23q, RT23q, RT45q; \
- vshr.u64 RT4, rd, #41; \
- vshl.u64 RT5, rd, #64 - 41; \
- vadd.u64 RT0, RT0, rw1; \
- veor.64 RT23q, RT23q, RT45q; \
- vmov.64 RT7, rd; \
- veor.64 RT1, RT2, RT3; \
- vbsl.64 RT7, re, rf; \
- \
- vadd.u64 RT1, RT1, rg; \
- vshr.u64 RT2, rh, #28; \
- vshl.u64 RT3, rh, #64 - 28; \
- vadd.u64 RT1, RT1, RT0; \
- vshr.u64 RT4, rh, #34; \
- vshl.u64 RT5, rh, #64 - 34; \
- vadd.u64 RT1, RT1, RT7; \
- \
- /* g = Sum0 (h) + Maj (h, a, b); */ \
- veor.64 RT23q, RT23q, RT45q; \
- vshr.u64 RT4, rh, #39; \
- vshl.u64 RT5, rh, #64 - 39; \
- veor.64 RT0, rh, ra; \
- veor.64 RT23q, RT23q, RT45q; \
- vbsl.64 RT0, rb, ra; \
- vadd.u64 rc, rc, RT1; /* c+=t1; */ \
- veor.64 rg, RT2, RT3; \
- \
- /* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \
- /* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \
- \
- /**** S0(w[1:2]) */ \
- \
- /* w[0:1] += w[9:10] */ \
- /* RT23q = rw1:rw2 */ \
- vext.u64 RT23q, rw01q, rw23q, #1; \
- vadd.u64 rw0, rw9; \
- vadd.u64 rg, rg, RT0; \
- vadd.u64 rw1, rw10;\
- vadd.u64 rg, rg, RT1; /* g+=t1; */ \
- \
- vshr.u64 RT45q, RT23q, #1; \
- vshl.u64 RT67q, RT23q, #64 - 1; \
- vshr.u64 RT01q, RT23q, #8; \
- veor.u64 RT45q, RT45q, RT67q; \
- vshl.u64 RT67q, RT23q, #64 - 8; \
- veor.u64 RT45q, RT45q, RT01q; \
- vshr.u64 RT01q, RT23q, #7; \
- veor.u64 RT45q, RT45q, RT67q; \
- \
- /**** S1(w[14:15]) */ \
- vshr.u64 RT23q, rw1415q, #6; \
- veor.u64 RT01q, RT01q, RT45q; \
- vshr.u64 RT45q, rw1415q, #19; \
- vshl.u64 RT67q, rw1415q, #64 - 19; \
- veor.u64 RT23q, RT23q, RT45q; \
- vshr.u64 RT45q, rw1415q, #61; \
- veor.u64 RT23q, RT23q, RT67q; \
- vshl.u64 RT67q, rw1415q, #64 - 61; \
- veor.u64 RT23q, RT23q, RT45q; \
- vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \
- veor.u64 RT01q, RT23q, RT67q;
-#define vadd_RT01q(rw01q) \
- /* w[0:1] += S(w[14:15]) */ \
- vadd.u64 rw01q, RT01q;
-
-#define dummy(_) /*_*/
-
-#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \
- interleave_op1, arg1, interleave_op2, arg2) \
- /* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
- vshr.u64 RT2, re, #14; \
- vshl.u64 RT3, re, #64 - 14; \
- interleave_op1(arg1); \
- vshr.u64 RT4, re, #18; \
- vshl.u64 RT5, re, #64 - 18; \
- interleave_op2(arg2); \
- vld1.64 {RT0}, [RK]!; \
- veor.64 RT23q, RT23q, RT45q; \
- vshr.u64 RT4, re, #41; \
- vshl.u64 RT5, re, #64 - 41; \
- vadd.u64 RT0, RT0, rw0; \
- veor.64 RT23q, RT23q, RT45q; \
- vmov.64 RT7, re; \
- veor.64 RT1, RT2, RT3; \
- vbsl.64 RT7, rf, rg; \
- \
- vadd.u64 RT1, RT1, rh; \
- vshr.u64 RT2, ra, #28; \
- vshl.u64 RT3, ra, #64 - 28; \
- vadd.u64 RT1, RT1, RT0; \
- vshr.u64 RT4, ra, #34; \
- vshl.u64 RT5, ra, #64 - 34; \
- vadd.u64 RT1, RT1, RT7; \
- \
- /* h = Sum0 (a) + Maj (a, b, c); */ \
- veor.64 RT23q, RT23q, RT45q; \
- vshr.u64 RT4, ra, #39; \
- vshl.u64 RT5, ra, #64 - 39; \
- veor.64 RT0, ra, rb; \
- veor.64 RT23q, RT23q, RT45q; \
- vbsl.64 RT0, rc, rb; \
- vadd.u64 rd, rd, RT1; /* d+=t1; */ \
- veor.64 rh, RT2, RT3; \
- \
- /* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
- vshr.u64 RT2, rd, #14; \
- vshl.u64 RT3, rd, #64 - 14; \
- vadd.u64 rh, rh, RT0; \
- vshr.u64 RT4, rd, #18; \
- vshl.u64 RT5, rd, #64 - 18; \
- vadd.u64 rh, rh, RT1; /* h+=t1; */ \
- vld1.64 {RT0}, [RK]!; \
- veor.64 RT23q, RT23q, RT45q; \
- vshr.u64 RT4, rd, #41; \
- vshl.u64 RT5, rd, #64 - 41; \
- vadd.u64 RT0, RT0, rw1; \
- veor.64 RT23q, RT23q, RT45q; \
- vmov.64 RT7, rd; \
- veor.64 RT1, RT2, RT3; \
- vbsl.64 RT7, re, rf; \
- \
- vadd.u64 RT1, RT1, rg; \
- vshr.u64 RT2, rh, #28; \
- vshl.u64 RT3, rh, #64 - 28; \
- vadd.u64 RT1, RT1, RT0; \
- vshr.u64 RT4, rh, #34; \
- vshl.u64 RT5, rh, #64 - 34; \
- vadd.u64 RT1, RT1, RT7; \
- \
- /* g = Sum0 (h) + Maj (h, a, b); */ \
- veor.64 RT23q, RT23q, RT45q; \
- vshr.u64 RT4, rh, #39; \
- vshl.u64 RT5, rh, #64 - 39; \
- veor.64 RT0, rh, ra; \
- veor.64 RT23q, RT23q, RT45q; \
- vbsl.64 RT0, rb, ra; \
- vadd.u64 rc, rc, RT1; /* c+=t1; */ \
- veor.64 rg, RT2, RT3;
-#define vadd_rg_RT0(rg) \
- vadd.u64 rg, rg, RT0;
-#define vadd_rg_RT1(rg) \
- vadd.u64 rg, rg, RT1; /* g+=t1; */
-
-.align 3
-ENTRY(sha512_transform_neon)
- /* Input:
- * %r0: SHA512_CONTEXT
- * %r1: data
- * %r2: u64 k[] constants
- * %r3: nblks
- */
- push {%lr};
-
- mov %lr, #0;
-
- /* Load context to d0-d7 */
- vld1.64 {RA-RD}, [%r0]!;
- vld1.64 {RE-RH}, [%r0];
- sub %r0, #(4*8);
-
- /* Load input to w[16], d16-d31 */
- /* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */
- vld1.64 {RW0-RW3}, [%r1]!;
- vld1.64 {RW4-RW7}, [%r1]!;
- vld1.64 {RW8-RW11}, [%r1]!;
- vld1.64 {RW12-RW15}, [%r1]!;
-#ifdef __ARMEL__
- /* byteswap */
- vrev64.8 RW01q, RW01q;
- vrev64.8 RW23q, RW23q;
- vrev64.8 RW45q, RW45q;
- vrev64.8 RW67q, RW67q;
- vrev64.8 RW89q, RW89q;
- vrev64.8 RW1011q, RW1011q;
- vrev64.8 RW1213q, RW1213q;
- vrev64.8 RW1415q, RW1415q;
-#endif
-
- /* EABI says that d8-d15 must be preserved by callee. */
- /*vpush {RT0-RT7};*/
-
-.Loop:
- rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
- RW23q, RW1415q, RW9, RW10, dummy, _);
- b .Lenter_rounds;
-
-.Loop_rounds:
- rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
- RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q);
-.Lenter_rounds:
- rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4,
- RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q);
- rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6,
- RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q);
- rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8,
- RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q);
- rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10,
- RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q);
- rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12,
- RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q);
- add %lr, #16;
- rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14,
- RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q);
- cmp %lr, #64;
- rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0,
- RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q);
- bne .Loop_rounds;
-
- subs %r3, #1;
-
- rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1,
- vadd_RT01q, RW1415q, dummy, _);
- rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3,
- vadd_rg_RT0, RG, vadd_rg_RT1, RG);
- beq .Lhandle_tail;
- vld1.64 {RW0-RW3}, [%r1]!;
- rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
- vadd_rg_RT0, RE, vadd_rg_RT1, RE);
- rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
- vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-#ifdef __ARMEL__
- vrev64.8 RW01q, RW01q;
- vrev64.8 RW23q, RW23q;
-#endif
- vld1.64 {RW4-RW7}, [%r1]!;
- rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
- vadd_rg_RT0, RA, vadd_rg_RT1, RA);
- rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
- vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-#ifdef __ARMEL__
- vrev64.8 RW45q, RW45q;
- vrev64.8 RW67q, RW67q;
-#endif
- vld1.64 {RW8-RW11}, [%r1]!;
- rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
- vadd_rg_RT0, RE, vadd_rg_RT1, RE);
- rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
- vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-#ifdef __ARMEL__
- vrev64.8 RW89q, RW89q;
- vrev64.8 RW1011q, RW1011q;
-#endif
- vld1.64 {RW12-RW15}, [%r1]!;
- vadd_rg_RT0(RA);
- vadd_rg_RT1(RA);
-
- /* Load context */
- vld1.64 {RT0-RT3}, [%r0]!;
- vld1.64 {RT4-RT7}, [%r0];
- sub %r0, #(4*8);
-
-#ifdef __ARMEL__
- vrev64.8 RW1213q, RW1213q;
- vrev64.8 RW1415q, RW1415q;
-#endif
-
- vadd.u64 RA, RT0;
- vadd.u64 RB, RT1;
- vadd.u64 RC, RT2;
- vadd.u64 RD, RT3;
- vadd.u64 RE, RT4;
- vadd.u64 RF, RT5;
- vadd.u64 RG, RT6;
- vadd.u64 RH, RT7;
-
- /* Store the first half of context */
- vst1.64 {RA-RD}, [%r0]!;
- sub RK, $(8*80);
- vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
- mov %lr, #0;
- sub %r0, #(4*8);
-
- b .Loop;
-
-.Lhandle_tail:
- rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
- vadd_rg_RT0, RE, vadd_rg_RT1, RE);
- rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
- vadd_rg_RT0, RC, vadd_rg_RT1, RC);
- rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
- vadd_rg_RT0, RA, vadd_rg_RT1, RA);
- rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
- vadd_rg_RT0, RG, vadd_rg_RT1, RG);
- rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
- vadd_rg_RT0, RE, vadd_rg_RT1, RE);
- rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
- vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-
- /* Load context to d16-d23 */
- vld1.64 {RW0-RW3}, [%r0]!;
- vadd_rg_RT0(RA);
- vld1.64 {RW4-RW7}, [%r0];
- vadd_rg_RT1(RA);
- sub %r0, #(4*8);
-
- vadd.u64 RA, RW0;
- vadd.u64 RB, RW1;
- vadd.u64 RC, RW2;
- vadd.u64 RD, RW3;
- vadd.u64 RE, RW4;
- vadd.u64 RF, RW5;
- vadd.u64 RG, RW6;
- vadd.u64 RH, RW7;
-
- /* Store the first half of context */
- vst1.64 {RA-RD}, [%r0]!;
-
- /* Clear used registers */
- /* d16-d31 */
- veor.u64 RW01q, RW01q;
- veor.u64 RW23q, RW23q;
- veor.u64 RW45q, RW45q;
- veor.u64 RW67q, RW67q;
- vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
- veor.u64 RW89q, RW89q;
- veor.u64 RW1011q, RW1011q;
- veor.u64 RW1213q, RW1213q;
- veor.u64 RW1415q, RW1415q;
- /* d8-d15 */
- /*vpop {RT0-RT7};*/
- /* d0-d7 (q0-q3) */
- veor.u64 %q0, %q0;
- veor.u64 %q1, %q1;
- veor.u64 %q2, %q2;
- veor.u64 %q3, %q3;
-
- pop {%pc};
-ENDPROC(sha512_transform_neon)
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
new file mode 100644
index 000000000000..3694c4d4ca2b
--- /dev/null
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -0,0 +1,1861 @@
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@
+@ Permission to use under GPL terms is granted.
+@ ====================================================================
+
+@ SHA512 block procedure for ARMv4. September 2007.
+
+@ This code is ~4.5 (four and a half) times faster than code generated
+@ by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
+@ Xscale PXA250 core].
+@
+@ July 2010.
+@
+@ Rescheduling for dual-issue pipeline resulted in 6% improvement on
+@ Cortex A8 core and ~40 cycles per processed byte.
+
+@ February 2011.
+@
+@ Profiler-assisted and platform-specific optimization resulted in 7%
+@ improvement on Coxtex A8 core and ~38 cycles per byte.
+
+@ March 2011.
+@
+@ Add NEON implementation. On Cortex A8 it was measured to process
+@ one byte in 23.3 cycles or ~60% faster than integer-only code.
+
+@ August 2012.
+@
+@ Improve NEON performance by 12% on Snapdragon S4. In absolute
+@ terms it's 22.6 cycles per byte, which is disappointing result.
+@ Technical writers asserted that 3-way S4 pipeline can sustain
+@ multiple NEON instructions per cycle, but dual NEON issue could
+@ not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+@ for further details. On side note Cortex-A15 processes one byte in
+@ 16 cycles.
+
+@ Byte order [in]dependence. =========================================
+@
+@ Originally caller was expected to maintain specific *dword* order in
+@ h[0-7], namely with most significant dword at *lower* address, which
+@ was reflected in below two parameters as 0 and 4. Now caller is
+@ expected to maintain native byte order for whole 64-bit values.
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH vstmdb sp!,{d8-d15}
+# define VFP_ABI_POP vldmia sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
+#ifdef __ARMEL__
+# define LO 0
+# define HI 4
+# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1
+#else
+# define HI 0
+# define LO 4
+# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code 32
+#else
+.syntax unified
+# ifdef __thumb2__
+# define adrl adr
+.thumb
+# else
+.code 32
+# endif
+#endif
+
+.type K512,%object
+.align 5
+K512:
+WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
+WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
+WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
+WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
+WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
+WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
+WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
+WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
+WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
+WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
+WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
+WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
+WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
+WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
+WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
+WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
+WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
+WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
+WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
+WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
+WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
+WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
+WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
+WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
+WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
+WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
+WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
+WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
+WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
+WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
+WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
+WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
+WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
+WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
+WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
+WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
+WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
+WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
+WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
+WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
+.size K512,.-K512
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word OPENSSL_armcap_P-sha512_block_data_order
+.skip 32-4
+#else
+.skip 32
+#endif
+
+.global sha512_block_data_order
+.type sha512_block_data_order,%function
+sha512_block_data_order:
+#if __ARM_ARCH__<7
+ sub r3,pc,#8 @ sha512_block_data_order
+#else
+ adr r3,sha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ ldr r12,.LOPENSSL_armcap
+ ldr r12,[r3,r12] @ OPENSSL_armcap_P
+ tst r12,#1
+ bne .LNEON
+#endif
+ add r2,r1,r2,lsl#7 @ len to point at the end of inp
+ stmdb sp!,{r4-r12,lr}
+ sub r14,r3,#672 @ K512
+ sub sp,sp,#9*8
+
+ ldr r7,[r0,#32+LO]
+ ldr r8,[r0,#32+HI]
+ ldr r9, [r0,#48+LO]
+ ldr r10, [r0,#48+HI]
+ ldr r11, [r0,#56+LO]
+ ldr r12, [r0,#56+HI]
+.Loop:
+ str r9, [sp,#48+0]
+ str r10, [sp,#48+4]
+ str r11, [sp,#56+0]
+ str r12, [sp,#56+4]
+ ldr r5,[r0,#0+LO]
+ ldr r6,[r0,#0+HI]
+ ldr r3,[r0,#8+LO]
+ ldr r4,[r0,#8+HI]
+ ldr r9, [r0,#16+LO]
+ ldr r10, [r0,#16+HI]
+ ldr r11, [r0,#24+LO]
+ ldr r12, [r0,#24+HI]
+ str r3,[sp,#8+0]
+ str r4,[sp,#8+4]
+ str r9, [sp,#16+0]
+ str r10, [sp,#16+4]
+ str r11, [sp,#24+0]
+ str r12, [sp,#24+4]
+ ldr r3,[r0,#40+LO]
+ ldr r4,[r0,#40+HI]
+ str r3,[sp,#40+0]
+ str r4,[sp,#40+4]
+
+.L00_15:
+#if __ARM_ARCH__<7
+ ldrb r3,[r1,#7]
+ ldrb r9, [r1,#6]
+ ldrb r10, [r1,#5]
+ ldrb r11, [r1,#4]
+ ldrb r4,[r1,#3]
+ ldrb r12, [r1,#2]
+ orr r3,r3,r9,lsl#8
+ ldrb r9, [r1,#1]
+ orr r3,r3,r10,lsl#16
+ ldrb r10, [r1],#8
+ orr r3,r3,r11,lsl#24
+ orr r4,r4,r12,lsl#8
+ orr r4,r4,r9,lsl#16
+ orr r4,r4,r10,lsl#24
+#else
+ ldr r3,[r1,#4]
+ ldr r4,[r1],#8
+#ifdef __ARMEL__
+ rev r3,r3
+ rev r4,r4
+#endif
+#endif
+ @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
+ @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+ @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+ mov r9,r7,lsr#14
+ str r3,[sp,#64+0]
+ mov r10,r8,lsr#14
+ str r4,[sp,#64+4]
+ eor r9,r9,r8,lsl#18
+ ldr r11,[sp,#56+0] @ h.lo
+ eor r10,r10,r7,lsl#18
+ ldr r12,[sp,#56+4] @ h.hi
+ eor r9,r9,r7,lsr#18
+ eor r10,r10,r8,lsr#18
+ eor r9,r9,r8,lsl#14
+ eor r10,r10,r7,lsl#14
+ eor r9,r9,r8,lsr#9
+ eor r10,r10,r7,lsr#9
+ eor r9,r9,r7,lsl#23
+ eor r10,r10,r8,lsl#23 @ Sigma1(e)
+ adds r3,r3,r9
+ ldr r9,[sp,#40+0] @ f.lo
+ adc r4,r4,r10 @ T += Sigma1(e)
+ ldr r10,[sp,#40+4] @ f.hi
+ adds r3,r3,r11
+ ldr r11,[sp,#48+0] @ g.lo
+ adc r4,r4,r12 @ T += h
+ ldr r12,[sp,#48+4] @ g.hi
+
+ eor r9,r9,r11
+ str r7,[sp,#32+0]
+ eor r10,r10,r12
+ str r8,[sp,#32+4]
+ and r9,r9,r7
+ str r5,[sp,#0+0]
+ and r10,r10,r8
+ str r6,[sp,#0+4]
+ eor r9,r9,r11
+ ldr r11,[r14,#LO] @ K[i].lo
+ eor r10,r10,r12 @ Ch(e,f,g)
+ ldr r12,[r14,#HI] @ K[i].hi
+
+ adds r3,r3,r9
+ ldr r7,[sp,#24+0] @ d.lo
+ adc r4,r4,r10 @ T += Ch(e,f,g)
+ ldr r8,[sp,#24+4] @ d.hi
+ adds r3,r3,r11
+ and r9,r11,#0xff
+ adc r4,r4,r12 @ T += K[i]
+ adds r7,r7,r3
+ ldr r11,[sp,#8+0] @ b.lo
+ adc r8,r8,r4 @ d += T
+ teq r9,#148
+
+ ldr r12,[sp,#16+0] @ c.lo
+#if __ARM_ARCH__>=7
+ it eq @ Thumb2 thing, sanity check in ARM
+#endif
+ orreq r14,r14,#1
+ @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+ @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+ @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+ mov r9,r5,lsr#28
+ mov r10,r6,lsr#28
+ eor r9,r9,r6,lsl#4
+ eor r10,r10,r5,lsl#4
+ eor r9,r9,r6,lsr#2
+ eor r10,r10,r5,lsr#2
+ eor r9,r9,r5,lsl#30
+ eor r10,r10,r6,lsl#30
+ eor r9,r9,r6,lsr#7
+ eor r10,r10,r5,lsr#7
+ eor r9,r9,r5,lsl#25
+ eor r10,r10,r6,lsl#25 @ Sigma0(a)
+ adds r3,r3,r9
+ and r9,r5,r11
+ adc r4,r4,r10 @ T += Sigma0(a)
+
+ ldr r10,[sp,#8+4] @ b.hi
+ orr r5,r5,r11
+ ldr r11,[sp,#16+4] @ c.hi
+ and r5,r5,r12
+ and r12,r6,r10
+ orr r6,r6,r10
+ orr r5,r5,r9 @ Maj(a,b,c).lo
+ and r6,r6,r11
+ adds r5,r5,r3
+ orr r6,r6,r12 @ Maj(a,b,c).hi
+ sub sp,sp,#8
+ adc r6,r6,r4 @ h += T
+ tst r14,#1
+ add r14,r14,#8
+ tst r14,#1
+ beq .L00_15
+ ldr r9,[sp,#184+0]
+ ldr r10,[sp,#184+4]
+ bic r14,r14,#1
+.L16_79:
+ @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
+ @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
+ @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7
+ mov r3,r9,lsr#1
+ ldr r11,[sp,#80+0]
+ mov r4,r10,lsr#1
+ ldr r12,[sp,#80+4]
+ eor r3,r3,r10,lsl#31
+ eor r4,r4,r9,lsl#31
+ eor r3,r3,r9,lsr#8
+ eor r4,r4,r10,lsr#8
+ eor r3,r3,r10,lsl#24
+ eor r4,r4,r9,lsl#24
+ eor r3,r3,r9,lsr#7
+ eor r4,r4,r10,lsr#7
+ eor r3,r3,r10,lsl#25
+
+ @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+ @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
+ @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
+ mov r9,r11,lsr#19
+ mov r10,r12,lsr#19
+ eor r9,r9,r12,lsl#13
+ eor r10,r10,r11,lsl#13
+ eor r9,r9,r12,lsr#29
+ eor r10,r10,r11,lsr#29
+ eor r9,r9,r11,lsl#3
+ eor r10,r10,r12,lsl#3
+ eor r9,r9,r11,lsr#6
+ eor r10,r10,r12,lsr#6
+ ldr r11,[sp,#120+0]
+ eor r9,r9,r12,lsl#26
+
+ ldr r12,[sp,#120+4]
+ adds r3,r3,r9
+ ldr r9,[sp,#192+0]
+ adc r4,r4,r10
+
+ ldr r10,[sp,#192+4]
+ adds r3,r3,r11
+ adc r4,r4,r12
+ adds r3,r3,r9
+ adc r4,r4,r10
+ @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
+ @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+ @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+ mov r9,r7,lsr#14
+ str r3,[sp,#64+0]
+ mov r10,r8,lsr#14
+ str r4,[sp,#64+4]
+ eor r9,r9,r8,lsl#18
+ ldr r11,[sp,#56+0] @ h.lo
+ eor r10,r10,r7,lsl#18
+ ldr r12,[sp,#56+4] @ h.hi
+ eor r9,r9,r7,lsr#18
+ eor r10,r10,r8,lsr#18
+ eor r9,r9,r8,lsl#14
+ eor r10,r10,r7,lsl#14
+ eor r9,r9,r8,lsr#9
+ eor r10,r10,r7,lsr#9
+ eor r9,r9,r7,lsl#23
+ eor r10,r10,r8,lsl#23 @ Sigma1(e)
+ adds r3,r3,r9
+ ldr r9,[sp,#40+0] @ f.lo
+ adc r4,r4,r10 @ T += Sigma1(e)
+ ldr r10,[sp,#40+4] @ f.hi
+ adds r3,r3,r11
+ ldr r11,[sp,#48+0] @ g.lo
+ adc r4,r4,r12 @ T += h
+ ldr r12,[sp,#48+4] @ g.hi
+
+ eor r9,r9,r11
+ str r7,[sp,#32+0]
+ eor r10,r10,r12
+ str r8,[sp,#32+4]
+ and r9,r9,r7
+ str r5,[sp,#0+0]
+ and r10,r10,r8
+ str r6,[sp,#0+4]
+ eor r9,r9,r11
+ ldr r11,[r14,#LO] @ K[i].lo
+ eor r10,r10,r12 @ Ch(e,f,g)
+ ldr r12,[r14,#HI] @ K[i].hi
+
+ adds r3,r3,r9
+ ldr r7,[sp,#24+0] @ d.lo
+ adc r4,r4,r10 @ T += Ch(e,f,g)
+ ldr r8,[sp,#24+4] @ d.hi
+ adds r3,r3,r11
+ and r9,r11,#0xff
+ adc r4,r4,r12 @ T += K[i]
+ adds r7,r7,r3
+ ldr r11,[sp,#8+0] @ b.lo
+ adc r8,r8,r4 @ d += T
+ teq r9,#23
+
+ ldr r12,[sp,#16+0] @ c.lo
+#if __ARM_ARCH__>=7
+ it eq @ Thumb2 thing, sanity check in ARM
+#endif
+ orreq r14,r14,#1
+ @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+ @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+ @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+ mov r9,r5,lsr#28
+ mov r10,r6,lsr#28
+ eor r9,r9,r6,lsl#4
+ eor r10,r10,r5,lsl#4
+ eor r9,r9,r6,lsr#2
+ eor r10,r10,r5,lsr#2
+ eor r9,r9,r5,lsl#30
+ eor r10,r10,r6,lsl#30
+ eor r9,r9,r6,lsr#7
+ eor r10,r10,r5,lsr#7
+ eor r9,r9,r5,lsl#25
+ eor r10,r10,r6,lsl#25 @ Sigma0(a)
+ adds r3,r3,r9
+ and r9,r5,r11
+ adc r4,r4,r10 @ T += Sigma0(a)
+
+ ldr r10,[sp,#8+4] @ b.hi
+ orr r5,r5,r11
+ ldr r11,[sp,#16+4] @ c.hi
+ and r5,r5,r12
+ and r12,r6,r10
+ orr r6,r6,r10
+ orr r5,r5,r9 @ Maj(a,b,c).lo
+ and r6,r6,r11
+ adds r5,r5,r3
+ orr r6,r6,r12 @ Maj(a,b,c).hi
+ sub sp,sp,#8
+ adc r6,r6,r4 @ h += T
+ tst r14,#1
+ add r14,r14,#8
+#if __ARM_ARCH__>=7
+ ittt eq @ Thumb2 thing, sanity check in ARM
+#endif
+ ldreq r9,[sp,#184+0]
+ ldreq r10,[sp,#184+4]
+ beq .L16_79
+ bic r14,r14,#1
+
+ ldr r3,[sp,#8+0]
+ ldr r4,[sp,#8+4]
+ ldr r9, [r0,#0+LO]
+ ldr r10, [r0,#0+HI]
+ ldr r11, [r0,#8+LO]
+ ldr r12, [r0,#8+HI]
+ adds r9,r5,r9
+ str r9, [r0,#0+LO]
+ adc r10,r6,r10
+ str r10, [r0,#0+HI]
+ adds r11,r3,r11
+ str r11, [r0,#8+LO]
+ adc r12,r4,r12
+ str r12, [r0,#8+HI]
+
+ ldr r5,[sp,#16+0]
+ ldr r6,[sp,#16+4]
+ ldr r3,[sp,#24+0]
+ ldr r4,[sp,#24+4]
+ ldr r9, [r0,#16+LO]
+ ldr r10, [r0,#16+HI]
+ ldr r11, [r0,#24+LO]
+ ldr r12, [r0,#24+HI]
+ adds r9,r5,r9
+ str r9, [r0,#16+LO]
+ adc r10,r6,r10
+ str r10, [r0,#16+HI]
+ adds r11,r3,r11
+ str r11, [r0,#24+LO]
+ adc r12,r4,r12
+ str r12, [r0,#24+HI]
+
+ ldr r3,[sp,#40+0]
+ ldr r4,[sp,#40+4]
+ ldr r9, [r0,#32+LO]
+ ldr r10, [r0,#32+HI]
+ ldr r11, [r0,#40+LO]
+ ldr r12, [r0,#40+HI]
+ adds r7,r7,r9
+ str r7,[r0,#32+LO]
+ adc r8,r8,r10
+ str r8,[r0,#32+HI]
+ adds r11,r3,r11
+ str r11, [r0,#40+LO]
+ adc r12,r4,r12
+ str r12, [r0,#40+HI]
+
+ ldr r5,[sp,#48+0]
+ ldr r6,[sp,#48+4]
+ ldr r3,[sp,#56+0]
+ ldr r4,[sp,#56+4]
+ ldr r9, [r0,#48+LO]
+ ldr r10, [r0,#48+HI]
+ ldr r11, [r0,#56+LO]
+ ldr r12, [r0,#56+HI]
+ adds r9,r5,r9
+ str r9, [r0,#48+LO]
+ adc r10,r6,r10
+ str r10, [r0,#48+HI]
+ adds r11,r3,r11
+ str r11, [r0,#56+LO]
+ adc r12,r4,r12
+ str r12, [r0,#56+HI]
+
+ add sp,sp,#640
+ sub r14,r14,#640
+
+ teq r1,r2
+ bne .Loop
+
+ add sp,sp,#8*9 @ destroy frame
+#if __ARM_ARCH__>=5
+ ldmia sp!,{r4-r12,pc}
+#else
+ ldmia sp!,{r4-r12,lr}
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ .word 0xe12fff1e @ interoperable with Thumb ISA:-)
+#endif
+.size sha512_block_data_order,.-sha512_block_data_order
+#if __ARM_MAX_ARCH__>=7
+.arch armv7-a
+.fpu neon
+
+.global sha512_block_data_order_neon
+.type sha512_block_data_order_neon,%function
+.align 4
+sha512_block_data_order_neon:
+.LNEON:
+ dmb @ errata #451034 on early Cortex A8
+ add r2,r1,r2,lsl#7 @ len to point at the end of inp
+ VFP_ABI_PUSH
+ adrl r3,K512
+ vldmia r0,{d16-d23} @ load context
+.Loop_neon:
+ vshr.u64 d24,d20,#14 @ 0
+#if 0<16
+ vld1.64 {d0},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d20,#18
+#if 0>0
+ vadd.i64 d16,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d20,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d20,#50
+ vsli.64 d25,d20,#46
+ vmov d29,d20
+ vsli.64 d26,d20,#23
+#if 0<16 && defined(__ARMEL__)
+ vrev64.8 d0,d0
+#endif
+ veor d25,d24
+ vbsl d29,d21,d22 @ Ch(e,f,g)
+ vshr.u64 d24,d16,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d23
+ vshr.u64 d25,d16,#34
+ vsli.64 d24,d16,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d16,#39
+ vadd.i64 d28,d0
+ vsli.64 d25,d16,#30
+ veor d30,d16,d17
+ vsli.64 d26,d16,#25
+ veor d23,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d18,d17 @ Maj(a,b,c)
+ veor d23,d26 @ Sigma0(a)
+ vadd.i64 d19,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d23,d30
+ vshr.u64 d24,d19,#14 @ 1
+#if 1<16
+ vld1.64 {d1},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d19,#18
+#if 1>0
+ vadd.i64 d23,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d19,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d19,#50
+ vsli.64 d25,d19,#46
+ vmov d29,d19
+ vsli.64 d26,d19,#23
+#if 1<16 && defined(__ARMEL__)
+ vrev64.8 d1,d1
+#endif
+ veor d25,d24
+ vbsl d29,d20,d21 @ Ch(e,f,g)
+ vshr.u64 d24,d23,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d22
+ vshr.u64 d25,d23,#34
+ vsli.64 d24,d23,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d23,#39
+ vadd.i64 d28,d1
+ vsli.64 d25,d23,#30
+ veor d30,d23,d16
+ vsli.64 d26,d23,#25
+ veor d22,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d17,d16 @ Maj(a,b,c)
+ veor d22,d26 @ Sigma0(a)
+ vadd.i64 d18,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d22,d30
+ vshr.u64 d24,d18,#14 @ 2
+#if 2<16
+ vld1.64 {d2},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d18,#18
+#if 2>0
+ vadd.i64 d22,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d18,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d18,#50
+ vsli.64 d25,d18,#46
+ vmov d29,d18
+ vsli.64 d26,d18,#23
+#if 2<16 && defined(__ARMEL__)
+ vrev64.8 d2,d2
+#endif
+ veor d25,d24
+ vbsl d29,d19,d20 @ Ch(e,f,g)
+ vshr.u64 d24,d22,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d21
+ vshr.u64 d25,d22,#34
+ vsli.64 d24,d22,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d22,#39
+ vadd.i64 d28,d2
+ vsli.64 d25,d22,#30
+ veor d30,d22,d23
+ vsli.64 d26,d22,#25
+ veor d21,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d16,d23 @ Maj(a,b,c)
+ veor d21,d26 @ Sigma0(a)
+ vadd.i64 d17,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d21,d30
+ vshr.u64 d24,d17,#14 @ 3
+#if 3<16
+ vld1.64 {d3},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d17,#18
+#if 3>0
+ vadd.i64 d21,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d17,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d17,#50
+ vsli.64 d25,d17,#46
+ vmov d29,d17
+ vsli.64 d26,d17,#23
+#if 3<16 && defined(__ARMEL__)
+ vrev64.8 d3,d3
+#endif
+ veor d25,d24
+ vbsl d29,d18,d19 @ Ch(e,f,g)
+ vshr.u64 d24,d21,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d20
+ vshr.u64 d25,d21,#34
+ vsli.64 d24,d21,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d21,#39
+ vadd.i64 d28,d3
+ vsli.64 d25,d21,#30
+ veor d30,d21,d22
+ vsli.64 d26,d21,#25
+ veor d20,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d23,d22 @ Maj(a,b,c)
+ veor d20,d26 @ Sigma0(a)
+ vadd.i64 d16,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d20,d30
+ vshr.u64 d24,d16,#14 @ 4
+#if 4<16
+ vld1.64 {d4},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d16,#18
+#if 4>0
+ vadd.i64 d20,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d16,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d16,#50
+ vsli.64 d25,d16,#46
+ vmov d29,d16
+ vsli.64 d26,d16,#23
+#if 4<16 && defined(__ARMEL__)
+ vrev64.8 d4,d4
+#endif
+ veor d25,d24
+ vbsl d29,d17,d18 @ Ch(e,f,g)
+ vshr.u64 d24,d20,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d19
+ vshr.u64 d25,d20,#34
+ vsli.64 d24,d20,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d20,#39
+ vadd.i64 d28,d4
+ vsli.64 d25,d20,#30
+ veor d30,d20,d21
+ vsli.64 d26,d20,#25
+ veor d19,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d22,d21 @ Maj(a,b,c)
+ veor d19,d26 @ Sigma0(a)
+ vadd.i64 d23,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d19,d30
+ vshr.u64 d24,d23,#14 @ 5
+#if 5<16
+ vld1.64 {d5},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d23,#18
+#if 5>0
+ vadd.i64 d19,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d23,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d23,#50
+ vsli.64 d25,d23,#46
+ vmov d29,d23
+ vsli.64 d26,d23,#23
+#if 5<16 && defined(__ARMEL__)
+ vrev64.8 d5,d5
+#endif
+ veor d25,d24
+ vbsl d29,d16,d17 @ Ch(e,f,g)
+ vshr.u64 d24,d19,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d18
+ vshr.u64 d25,d19,#34
+ vsli.64 d24,d19,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d19,#39
+ vadd.i64 d28,d5
+ vsli.64 d25,d19,#30
+ veor d30,d19,d20
+ vsli.64 d26,d19,#25
+ veor d18,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d21,d20 @ Maj(a,b,c)
+ veor d18,d26 @ Sigma0(a)
+ vadd.i64 d22,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d18,d30
+ vshr.u64 d24,d22,#14 @ 6
+#if 6<16
+ vld1.64 {d6},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d22,#18
+#if 6>0
+ vadd.i64 d18,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d22,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d22,#50
+ vsli.64 d25,d22,#46
+ vmov d29,d22
+ vsli.64 d26,d22,#23
+#if 6<16 && defined(__ARMEL__)
+ vrev64.8 d6,d6
+#endif
+ veor d25,d24
+ vbsl d29,d23,d16 @ Ch(e,f,g)
+ vshr.u64 d24,d18,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d17
+ vshr.u64 d25,d18,#34
+ vsli.64 d24,d18,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d18,#39
+ vadd.i64 d28,d6
+ vsli.64 d25,d18,#30
+ veor d30,d18,d19
+ vsli.64 d26,d18,#25
+ veor d17,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d20,d19 @ Maj(a,b,c)
+ veor d17,d26 @ Sigma0(a)
+ vadd.i64 d21,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d17,d30
+ vshr.u64 d24,d21,#14 @ 7
+#if 7<16
+ vld1.64 {d7},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d21,#18
+#if 7>0
+ vadd.i64 d17,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d21,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d21,#50
+ vsli.64 d25,d21,#46
+ vmov d29,d21
+ vsli.64 d26,d21,#23
+#if 7<16 && defined(__ARMEL__)
+ vrev64.8 d7,d7
+#endif
+ veor d25,d24
+ vbsl d29,d22,d23 @ Ch(e,f,g)
+ vshr.u64 d24,d17,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d16
+ vshr.u64 d25,d17,#34
+ vsli.64 d24,d17,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d17,#39
+ vadd.i64 d28,d7
+ vsli.64 d25,d17,#30
+ veor d30,d17,d18
+ vsli.64 d26,d17,#25
+ veor d16,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d19,d18 @ Maj(a,b,c)
+ veor d16,d26 @ Sigma0(a)
+ vadd.i64 d20,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d16,d30
+ vshr.u64 d24,d20,#14 @ 8
+#if 8<16
+ vld1.64 {d8},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d20,#18
+#if 8>0
+ vadd.i64 d16,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d20,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d20,#50
+ vsli.64 d25,d20,#46
+ vmov d29,d20
+ vsli.64 d26,d20,#23
+#if 8<16 && defined(__ARMEL__)
+ vrev64.8 d8,d8
+#endif
+ veor d25,d24
+ vbsl d29,d21,d22 @ Ch(e,f,g)
+ vshr.u64 d24,d16,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d23
+ vshr.u64 d25,d16,#34
+ vsli.64 d24,d16,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d16,#39
+ vadd.i64 d28,d8
+ vsli.64 d25,d16,#30
+ veor d30,d16,d17
+ vsli.64 d26,d16,#25
+ veor d23,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d18,d17 @ Maj(a,b,c)
+ veor d23,d26 @ Sigma0(a)
+ vadd.i64 d19,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d23,d30
+ vshr.u64 d24,d19,#14 @ 9
+#if 9<16
+ vld1.64 {d9},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d19,#18
+#if 9>0
+ vadd.i64 d23,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d19,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d19,#50
+ vsli.64 d25,d19,#46
+ vmov d29,d19
+ vsli.64 d26,d19,#23
+#if 9<16 && defined(__ARMEL__)
+ vrev64.8 d9,d9
+#endif
+ veor d25,d24
+ vbsl d29,d20,d21 @ Ch(e,f,g)
+ vshr.u64 d24,d23,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d22
+ vshr.u64 d25,d23,#34
+ vsli.64 d24,d23,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d23,#39
+ vadd.i64 d28,d9
+ vsli.64 d25,d23,#30
+ veor d30,d23,d16
+ vsli.64 d26,d23,#25
+ veor d22,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d17,d16 @ Maj(a,b,c)
+ veor d22,d26 @ Sigma0(a)
+ vadd.i64 d18,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d22,d30
+ vshr.u64 d24,d18,#14 @ 10
+#if 10<16
+ vld1.64 {d10},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d18,#18
+#if 10>0
+ vadd.i64 d22,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d18,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d18,#50
+ vsli.64 d25,d18,#46
+ vmov d29,d18
+ vsli.64 d26,d18,#23
+#if 10<16 && defined(__ARMEL__)
+ vrev64.8 d10,d10
+#endif
+ veor d25,d24
+ vbsl d29,d19,d20 @ Ch(e,f,g)
+ vshr.u64 d24,d22,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d21
+ vshr.u64 d25,d22,#34
+ vsli.64 d24,d22,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d22,#39
+ vadd.i64 d28,d10
+ vsli.64 d25,d22,#30
+ veor d30,d22,d23
+ vsli.64 d26,d22,#25
+ veor d21,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d16,d23 @ Maj(a,b,c)
+ veor d21,d26 @ Sigma0(a)
+ vadd.i64 d17,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d21,d30
+ vshr.u64 d24,d17,#14 @ 11
+#if 11<16
+ vld1.64 {d11},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d17,#18
+#if 11>0
+ vadd.i64 d21,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d17,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d17,#50
+ vsli.64 d25,d17,#46
+ vmov d29,d17
+ vsli.64 d26,d17,#23
+#if 11<16 && defined(__ARMEL__)
+ vrev64.8 d11,d11
+#endif
+ veor d25,d24
+ vbsl d29,d18,d19 @ Ch(e,f,g)
+ vshr.u64 d24,d21,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d20
+ vshr.u64 d25,d21,#34
+ vsli.64 d24,d21,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d21,#39
+ vadd.i64 d28,d11
+ vsli.64 d25,d21,#30
+ veor d30,d21,d22
+ vsli.64 d26,d21,#25
+ veor d20,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d23,d22 @ Maj(a,b,c)
+ veor d20,d26 @ Sigma0(a)
+ vadd.i64 d16,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d20,d30
+ vshr.u64 d24,d16,#14 @ 12
+#if 12<16
+ vld1.64 {d12},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d16,#18
+#if 12>0
+ vadd.i64 d20,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d16,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d16,#50
+ vsli.64 d25,d16,#46
+ vmov d29,d16
+ vsli.64 d26,d16,#23
+#if 12<16 && defined(__ARMEL__)
+ vrev64.8 d12,d12
+#endif
+ veor d25,d24
+ vbsl d29,d17,d18 @ Ch(e,f,g)
+ vshr.u64 d24,d20,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d19
+ vshr.u64 d25,d20,#34
+ vsli.64 d24,d20,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d20,#39
+ vadd.i64 d28,d12
+ vsli.64 d25,d20,#30
+ veor d30,d20,d21
+ vsli.64 d26,d20,#25
+ veor d19,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d22,d21 @ Maj(a,b,c)
+ veor d19,d26 @ Sigma0(a)
+ vadd.i64 d23,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d19,d30
+ vshr.u64 d24,d23,#14 @ 13
+#if 13<16
+ vld1.64 {d13},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d23,#18
+#if 13>0
+ vadd.i64 d19,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d23,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d23,#50
+ vsli.64 d25,d23,#46
+ vmov d29,d23
+ vsli.64 d26,d23,#23
+#if 13<16 && defined(__ARMEL__)
+ vrev64.8 d13,d13
+#endif
+ veor d25,d24
+ vbsl d29,d16,d17 @ Ch(e,f,g)
+ vshr.u64 d24,d19,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d18
+ vshr.u64 d25,d19,#34
+ vsli.64 d24,d19,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d19,#39
+ vadd.i64 d28,d13
+ vsli.64 d25,d19,#30
+ veor d30,d19,d20
+ vsli.64 d26,d19,#25
+ veor d18,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d21,d20 @ Maj(a,b,c)
+ veor d18,d26 @ Sigma0(a)
+ vadd.i64 d22,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d18,d30
+ vshr.u64 d24,d22,#14 @ 14
+#if 14<16
+ vld1.64 {d14},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d22,#18
+#if 14>0
+ vadd.i64 d18,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d22,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d22,#50
+ vsli.64 d25,d22,#46
+ vmov d29,d22
+ vsli.64 d26,d22,#23
+#if 14<16 && defined(__ARMEL__)
+ vrev64.8 d14,d14
+#endif
+ veor d25,d24
+ vbsl d29,d23,d16 @ Ch(e,f,g)
+ vshr.u64 d24,d18,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d17
+ vshr.u64 d25,d18,#34
+ vsli.64 d24,d18,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d18,#39
+ vadd.i64 d28,d14
+ vsli.64 d25,d18,#30
+ veor d30,d18,d19
+ vsli.64 d26,d18,#25
+ veor d17,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d20,d19 @ Maj(a,b,c)
+ veor d17,d26 @ Sigma0(a)
+ vadd.i64 d21,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d17,d30
+ vshr.u64 d24,d21,#14 @ 15
+#if 15<16
+ vld1.64 {d15},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d21,#18
+#if 15>0
+ vadd.i64 d17,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d21,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d21,#50
+ vsli.64 d25,d21,#46
+ vmov d29,d21
+ vsli.64 d26,d21,#23
+#if 15<16 && defined(__ARMEL__)
+ vrev64.8 d15,d15
+#endif
+ veor d25,d24
+ vbsl d29,d22,d23 @ Ch(e,f,g)
+ vshr.u64 d24,d17,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d16
+ vshr.u64 d25,d17,#34
+ vsli.64 d24,d17,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d17,#39
+ vadd.i64 d28,d15
+ vsli.64 d25,d17,#30
+ veor d30,d17,d18
+ vsli.64 d26,d17,#25
+ veor d16,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d19,d18 @ Maj(a,b,c)
+ veor d16,d26 @ Sigma0(a)
+ vadd.i64 d20,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d16,d30
+ mov r12,#4
+.L16_79_neon:
+ subs r12,#1
+ vshr.u64 q12,q7,#19
+ vshr.u64 q13,q7,#61
+ vadd.i64 d16,d30 @ h+=Maj from the past
+ vshr.u64 q15,q7,#6
+ vsli.64 q12,q7,#45
+ vext.8 q14,q0,q1,#8 @ X[i+1]
+ vsli.64 q13,q7,#3
+ veor q15,q12
+ vshr.u64 q12,q14,#1
+ veor q15,q13 @ sigma1(X[i+14])
+ vshr.u64 q13,q14,#8
+ vadd.i64 q0,q15
+ vshr.u64 q15,q14,#7
+ vsli.64 q12,q14,#63
+ vsli.64 q13,q14,#56
+ vext.8 q14,q4,q5,#8 @ X[i+9]
+ veor q15,q12
+ vshr.u64 d24,d20,#14 @ from NEON_00_15
+ vadd.i64 q0,q14
+ vshr.u64 d25,d20,#18 @ from NEON_00_15
+ veor q15,q13 @ sigma0(X[i+1])
+ vshr.u64 d26,d20,#41 @ from NEON_00_15
+ vadd.i64 q0,q15
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d20,#50
+ vsli.64 d25,d20,#46
+ vmov d29,d20
+ vsli.64 d26,d20,#23
+#if 16<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d21,d22 @ Ch(e,f,g)
+ vshr.u64 d24,d16,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d23
+ vshr.u64 d25,d16,#34
+ vsli.64 d24,d16,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d16,#39
+ vadd.i64 d28,d0
+ vsli.64 d25,d16,#30
+ veor d30,d16,d17
+ vsli.64 d26,d16,#25
+ veor d23,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d18,d17 @ Maj(a,b,c)
+ veor d23,d26 @ Sigma0(a)
+ vadd.i64 d19,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d23,d30
+ vshr.u64 d24,d19,#14 @ 17
+#if 17<16
+ vld1.64 {d1},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d19,#18
+#if 17>0
+ vadd.i64 d23,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d19,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d19,#50
+ vsli.64 d25,d19,#46
+ vmov d29,d19
+ vsli.64 d26,d19,#23
+#if 17<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d20,d21 @ Ch(e,f,g)
+ vshr.u64 d24,d23,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d22
+ vshr.u64 d25,d23,#34
+ vsli.64 d24,d23,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d23,#39
+ vadd.i64 d28,d1
+ vsli.64 d25,d23,#30
+ veor d30,d23,d16
+ vsli.64 d26,d23,#25
+ veor d22,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d17,d16 @ Maj(a,b,c)
+ veor d22,d26 @ Sigma0(a)
+ vadd.i64 d18,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d22,d30
+ vshr.u64 q12,q0,#19
+ vshr.u64 q13,q0,#61
+ vadd.i64 d22,d30 @ h+=Maj from the past
+ vshr.u64 q15,q0,#6
+ vsli.64 q12,q0,#45
+ vext.8 q14,q1,q2,#8 @ X[i+1]
+ vsli.64 q13,q0,#3
+ veor q15,q12
+ vshr.u64 q12,q14,#1
+ veor q15,q13 @ sigma1(X[i+14])
+ vshr.u64 q13,q14,#8
+ vadd.i64 q1,q15
+ vshr.u64 q15,q14,#7
+ vsli.64 q12,q14,#63
+ vsli.64 q13,q14,#56
+ vext.8 q14,q5,q6,#8 @ X[i+9]
+ veor q15,q12
+ vshr.u64 d24,d18,#14 @ from NEON_00_15
+ vadd.i64 q1,q14
+ vshr.u64 d25,d18,#18 @ from NEON_00_15
+ veor q15,q13 @ sigma0(X[i+1])
+ vshr.u64 d26,d18,#41 @ from NEON_00_15
+ vadd.i64 q1,q15
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d18,#50
+ vsli.64 d25,d18,#46
+ vmov d29,d18
+ vsli.64 d26,d18,#23
+#if 18<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d19,d20 @ Ch(e,f,g)
+ vshr.u64 d24,d22,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d21
+ vshr.u64 d25,d22,#34
+ vsli.64 d24,d22,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d22,#39
+ vadd.i64 d28,d2
+ vsli.64 d25,d22,#30
+ veor d30,d22,d23
+ vsli.64 d26,d22,#25
+ veor d21,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d16,d23 @ Maj(a,b,c)
+ veor d21,d26 @ Sigma0(a)
+ vadd.i64 d17,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d21,d30
+ vshr.u64 d24,d17,#14 @ 19
+#if 19<16
+ vld1.64 {d3},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d17,#18
+#if 19>0
+ vadd.i64 d21,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d17,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d17,#50
+ vsli.64 d25,d17,#46
+ vmov d29,d17
+ vsli.64 d26,d17,#23
+#if 19<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d18,d19 @ Ch(e,f,g)
+ vshr.u64 d24,d21,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d20
+ vshr.u64 d25,d21,#34
+ vsli.64 d24,d21,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d21,#39
+ vadd.i64 d28,d3
+ vsli.64 d25,d21,#30
+ veor d30,d21,d22
+ vsli.64 d26,d21,#25
+ veor d20,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d23,d22 @ Maj(a,b,c)
+ veor d20,d26 @ Sigma0(a)
+ vadd.i64 d16,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d20,d30
+ vshr.u64 q12,q1,#19
+ vshr.u64 q13,q1,#61
+ vadd.i64 d20,d30 @ h+=Maj from the past
+ vshr.u64 q15,q1,#6
+ vsli.64 q12,q1,#45
+ vext.8 q14,q2,q3,#8 @ X[i+1]
+ vsli.64 q13,q1,#3
+ veor q15,q12
+ vshr.u64 q12,q14,#1
+ veor q15,q13 @ sigma1(X[i+14])
+ vshr.u64 q13,q14,#8
+ vadd.i64 q2,q15
+ vshr.u64 q15,q14,#7
+ vsli.64 q12,q14,#63
+ vsli.64 q13,q14,#56
+ vext.8 q14,q6,q7,#8 @ X[i+9]
+ veor q15,q12
+ vshr.u64 d24,d16,#14 @ from NEON_00_15
+ vadd.i64 q2,q14
+ vshr.u64 d25,d16,#18 @ from NEON_00_15
+ veor q15,q13 @ sigma0(X[i+1])
+ vshr.u64 d26,d16,#41 @ from NEON_00_15
+ vadd.i64 q2,q15
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d16,#50
+ vsli.64 d25,d16,#46
+ vmov d29,d16
+ vsli.64 d26,d16,#23
+#if 20<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d17,d18 @ Ch(e,f,g)
+ vshr.u64 d24,d20,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d19
+ vshr.u64 d25,d20,#34
+ vsli.64 d24,d20,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d20,#39
+ vadd.i64 d28,d4
+ vsli.64 d25,d20,#30
+ veor d30,d20,d21
+ vsli.64 d26,d20,#25
+ veor d19,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d22,d21 @ Maj(a,b,c)
+ veor d19,d26 @ Sigma0(a)
+ vadd.i64 d23,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d19,d30
+ vshr.u64 d24,d23,#14 @ 21
+#if 21<16
+ vld1.64 {d5},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d23,#18
+#if 21>0
+ vadd.i64 d19,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d23,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d23,#50
+ vsli.64 d25,d23,#46
+ vmov d29,d23
+ vsli.64 d26,d23,#23
+#if 21<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d16,d17 @ Ch(e,f,g)
+ vshr.u64 d24,d19,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d18
+ vshr.u64 d25,d19,#34
+ vsli.64 d24,d19,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d19,#39
+ vadd.i64 d28,d5
+ vsli.64 d25,d19,#30
+ veor d30,d19,d20
+ vsli.64 d26,d19,#25
+ veor d18,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d21,d20 @ Maj(a,b,c)
+ veor d18,d26 @ Sigma0(a)
+ vadd.i64 d22,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d18,d30
+ vshr.u64 q12,q2,#19
+ vshr.u64 q13,q2,#61
+ vadd.i64 d18,d30 @ h+=Maj from the past
+ vshr.u64 q15,q2,#6
+ vsli.64 q12,q2,#45
+ vext.8 q14,q3,q4,#8 @ X[i+1]
+ vsli.64 q13,q2,#3
+ veor q15,q12
+ vshr.u64 q12,q14,#1
+ veor q15,q13 @ sigma1(X[i+14])
+ vshr.u64 q13,q14,#8
+ vadd.i64 q3,q15
+ vshr.u64 q15,q14,#7
+ vsli.64 q12,q14,#63
+ vsli.64 q13,q14,#56
+ vext.8 q14,q7,q0,#8 @ X[i+9]
+ veor q15,q12
+ vshr.u64 d24,d22,#14 @ from NEON_00_15
+ vadd.i64 q3,q14
+ vshr.u64 d25,d22,#18 @ from NEON_00_15
+ veor q15,q13 @ sigma0(X[i+1])
+ vshr.u64 d26,d22,#41 @ from NEON_00_15
+ vadd.i64 q3,q15
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d22,#50
+ vsli.64 d25,d22,#46
+ vmov d29,d22
+ vsli.64 d26,d22,#23
+#if 22<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d23,d16 @ Ch(e,f,g)
+ vshr.u64 d24,d18,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d17
+ vshr.u64 d25,d18,#34
+ vsli.64 d24,d18,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d18,#39
+ vadd.i64 d28,d6
+ vsli.64 d25,d18,#30
+ veor d30,d18,d19
+ vsli.64 d26,d18,#25
+ veor d17,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d20,d19 @ Maj(a,b,c)
+ veor d17,d26 @ Sigma0(a)
+ vadd.i64 d21,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d17,d30
+ vshr.u64 d24,d21,#14 @ 23
+#if 23<16
+ vld1.64 {d7},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d21,#18
+#if 23>0
+ vadd.i64 d17,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d21,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d21,#50
+ vsli.64 d25,d21,#46
+ vmov d29,d21
+ vsli.64 d26,d21,#23
+#if 23<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d22,d23 @ Ch(e,f,g)
+ vshr.u64 d24,d17,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d16
+ vshr.u64 d25,d17,#34
+ vsli.64 d24,d17,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d17,#39
+ vadd.i64 d28,d7
+ vsli.64 d25,d17,#30
+ veor d30,d17,d18
+ vsli.64 d26,d17,#25
+ veor d16,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d19,d18 @ Maj(a,b,c)
+ veor d16,d26 @ Sigma0(a)
+ vadd.i64 d20,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d16,d30
+ vshr.u64 q12,q3,#19
+ vshr.u64 q13,q3,#61
+ vadd.i64 d16,d30 @ h+=Maj from the past
+ vshr.u64 q15,q3,#6
+ vsli.64 q12,q3,#45
+ vext.8 q14,q4,q5,#8 @ X[i+1]
+ vsli.64 q13,q3,#3
+ veor q15,q12
+ vshr.u64 q12,q14,#1
+ veor q15,q13 @ sigma1(X[i+14])
+ vshr.u64 q13,q14,#8
+ vadd.i64 q4,q15
+ vshr.u64 q15,q14,#7
+ vsli.64 q12,q14,#63
+ vsli.64 q13,q14,#56
+ vext.8 q14,q0,q1,#8 @ X[i+9]
+ veor q15,q12
+ vshr.u64 d24,d20,#14 @ from NEON_00_15
+ vadd.i64 q4,q14
+ vshr.u64 d25,d20,#18 @ from NEON_00_15
+ veor q15,q13 @ sigma0(X[i+1])
+ vshr.u64 d26,d20,#41 @ from NEON_00_15
+ vadd.i64 q4,q15
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d20,#50
+ vsli.64 d25,d20,#46
+ vmov d29,d20
+ vsli.64 d26,d20,#23
+#if 24<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d21,d22 @ Ch(e,f,g)
+ vshr.u64 d24,d16,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d23
+ vshr.u64 d25,d16,#34
+ vsli.64 d24,d16,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d16,#39
+ vadd.i64 d28,d8
+ vsli.64 d25,d16,#30
+ veor d30,d16,d17
+ vsli.64 d26,d16,#25
+ veor d23,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d18,d17 @ Maj(a,b,c)
+ veor d23,d26 @ Sigma0(a)
+ vadd.i64 d19,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d23,d30
+ vshr.u64 d24,d19,#14 @ 25
+#if 25<16
+ vld1.64 {d9},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d19,#18
+#if 25>0
+ vadd.i64 d23,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d19,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d19,#50
+ vsli.64 d25,d19,#46
+ vmov d29,d19
+ vsli.64 d26,d19,#23
+#if 25<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d20,d21 @ Ch(e,f,g)
+ vshr.u64 d24,d23,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d22
+ vshr.u64 d25,d23,#34
+ vsli.64 d24,d23,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d23,#39
+ vadd.i64 d28,d9
+ vsli.64 d25,d23,#30
+ veor d30,d23,d16
+ vsli.64 d26,d23,#25
+ veor d22,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d17,d16 @ Maj(a,b,c)
+ veor d22,d26 @ Sigma0(a)
+ vadd.i64 d18,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d22,d30
+ vshr.u64 q12,q4,#19
+ vshr.u64 q13,q4,#61
+ vadd.i64 d22,d30 @ h+=Maj from the past
+ vshr.u64 q15,q4,#6
+ vsli.64 q12,q4,#45
+ vext.8 q14,q5,q6,#8 @ X[i+1]
+ vsli.64 q13,q4,#3
+ veor q15,q12
+ vshr.u64 q12,q14,#1
+ veor q15,q13 @ sigma1(X[i+14])
+ vshr.u64 q13,q14,#8
+ vadd.i64 q5,q15
+ vshr.u64 q15,q14,#7
+ vsli.64 q12,q14,#63
+ vsli.64 q13,q14,#56
+ vext.8 q14,q1,q2,#8 @ X[i+9]
+ veor q15,q12
+ vshr.u64 d24,d18,#14 @ from NEON_00_15
+ vadd.i64 q5,q14
+ vshr.u64 d25,d18,#18 @ from NEON_00_15
+ veor q15,q13 @ sigma0(X[i+1])
+ vshr.u64 d26,d18,#41 @ from NEON_00_15
+ vadd.i64 q5,q15
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d18,#50
+ vsli.64 d25,d18,#46
+ vmov d29,d18
+ vsli.64 d26,d18,#23
+#if 26<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d19,d20 @ Ch(e,f,g)
+ vshr.u64 d24,d22,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d21
+ vshr.u64 d25,d22,#34
+ vsli.64 d24,d22,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d22,#39
+ vadd.i64 d28,d10
+ vsli.64 d25,d22,#30
+ veor d30,d22,d23
+ vsli.64 d26,d22,#25
+ veor d21,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d16,d23 @ Maj(a,b,c)
+ veor d21,d26 @ Sigma0(a)
+ vadd.i64 d17,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d21,d30
+ vshr.u64 d24,d17,#14 @ 27
+#if 27<16
+ vld1.64 {d11},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d17,#18
+#if 27>0
+ vadd.i64 d21,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d17,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d17,#50
+ vsli.64 d25,d17,#46
+ vmov d29,d17
+ vsli.64 d26,d17,#23
+#if 27<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d18,d19 @ Ch(e,f,g)
+ vshr.u64 d24,d21,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d20
+ vshr.u64 d25,d21,#34
+ vsli.64 d24,d21,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d21,#39
+ vadd.i64 d28,d11
+ vsli.64 d25,d21,#30
+ veor d30,d21,d22
+ vsli.64 d26,d21,#25
+ veor d20,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d23,d22 @ Maj(a,b,c)
+ veor d20,d26 @ Sigma0(a)
+ vadd.i64 d16,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d20,d30
+ vshr.u64 q12,q5,#19
+ vshr.u64 q13,q5,#61
+ vadd.i64 d20,d30 @ h+=Maj from the past
+ vshr.u64 q15,q5,#6
+ vsli.64 q12,q5,#45
+ vext.8 q14,q6,q7,#8 @ X[i+1]
+ vsli.64 q13,q5,#3
+ veor q15,q12
+ vshr.u64 q12,q14,#1
+ veor q15,q13 @ sigma1(X[i+14])
+ vshr.u64 q13,q14,#8
+ vadd.i64 q6,q15
+ vshr.u64 q15,q14,#7
+ vsli.64 q12,q14,#63
+ vsli.64 q13,q14,#56
+ vext.8 q14,q2,q3,#8 @ X[i+9]
+ veor q15,q12
+ vshr.u64 d24,d16,#14 @ from NEON_00_15
+ vadd.i64 q6,q14
+ vshr.u64 d25,d16,#18 @ from NEON_00_15
+ veor q15,q13 @ sigma0(X[i+1])
+ vshr.u64 d26,d16,#41 @ from NEON_00_15
+ vadd.i64 q6,q15
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d16,#50
+ vsli.64 d25,d16,#46
+ vmov d29,d16
+ vsli.64 d26,d16,#23
+#if 28<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d17,d18 @ Ch(e,f,g)
+ vshr.u64 d24,d20,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d19
+ vshr.u64 d25,d20,#34
+ vsli.64 d24,d20,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d20,#39
+ vadd.i64 d28,d12
+ vsli.64 d25,d20,#30
+ veor d30,d20,d21
+ vsli.64 d26,d20,#25
+ veor d19,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d22,d21 @ Maj(a,b,c)
+ veor d19,d26 @ Sigma0(a)
+ vadd.i64 d23,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d19,d30
+ vshr.u64 d24,d23,#14 @ 29
+#if 29<16
+ vld1.64 {d13},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d23,#18
+#if 29>0
+ vadd.i64 d19,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d23,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d23,#50
+ vsli.64 d25,d23,#46
+ vmov d29,d23
+ vsli.64 d26,d23,#23
+#if 29<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d16,d17 @ Ch(e,f,g)
+ vshr.u64 d24,d19,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d18
+ vshr.u64 d25,d19,#34
+ vsli.64 d24,d19,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d19,#39
+ vadd.i64 d28,d13
+ vsli.64 d25,d19,#30
+ veor d30,d19,d20
+ vsli.64 d26,d19,#25
+ veor d18,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d21,d20 @ Maj(a,b,c)
+ veor d18,d26 @ Sigma0(a)
+ vadd.i64 d22,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d18,d30
+ vshr.u64 q12,q6,#19
+ vshr.u64 q13,q6,#61
+ vadd.i64 d18,d30 @ h+=Maj from the past
+ vshr.u64 q15,q6,#6
+ vsli.64 q12,q6,#45
+ vext.8 q14,q7,q0,#8 @ X[i+1]
+ vsli.64 q13,q6,#3
+ veor q15,q12
+ vshr.u64 q12,q14,#1
+ veor q15,q13 @ sigma1(X[i+14])
+ vshr.u64 q13,q14,#8
+ vadd.i64 q7,q15
+ vshr.u64 q15,q14,#7
+ vsli.64 q12,q14,#63
+ vsli.64 q13,q14,#56
+ vext.8 q14,q3,q4,#8 @ X[i+9]
+ veor q15,q12
+ vshr.u64 d24,d22,#14 @ from NEON_00_15
+ vadd.i64 q7,q14
+ vshr.u64 d25,d22,#18 @ from NEON_00_15
+ veor q15,q13 @ sigma0(X[i+1])
+ vshr.u64 d26,d22,#41 @ from NEON_00_15
+ vadd.i64 q7,q15
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d22,#50
+ vsli.64 d25,d22,#46
+ vmov d29,d22
+ vsli.64 d26,d22,#23
+#if 30<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d23,d16 @ Ch(e,f,g)
+ vshr.u64 d24,d18,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d17
+ vshr.u64 d25,d18,#34
+ vsli.64 d24,d18,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d18,#39
+ vadd.i64 d28,d14
+ vsli.64 d25,d18,#30
+ veor d30,d18,d19
+ vsli.64 d26,d18,#25
+ veor d17,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d20,d19 @ Maj(a,b,c)
+ veor d17,d26 @ Sigma0(a)
+ vadd.i64 d21,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d17,d30
+ vshr.u64 d24,d21,#14 @ 31
+#if 31<16
+ vld1.64 {d15},[r1]! @ handles unaligned
+#endif
+ vshr.u64 d25,d21,#18
+#if 31>0
+ vadd.i64 d17,d30 @ h+=Maj from the past
+#endif
+ vshr.u64 d26,d21,#41
+ vld1.64 {d28},[r3,:64]! @ K[i++]
+ vsli.64 d24,d21,#50
+ vsli.64 d25,d21,#46
+ vmov d29,d21
+ vsli.64 d26,d21,#23
+#if 31<16 && defined(__ARMEL__)
+ vrev64.8 ,
+#endif
+ veor d25,d24
+ vbsl d29,d22,d23 @ Ch(e,f,g)
+ vshr.u64 d24,d17,#28
+ veor d26,d25 @ Sigma1(e)
+ vadd.i64 d27,d29,d16
+ vshr.u64 d25,d17,#34
+ vsli.64 d24,d17,#36
+ vadd.i64 d27,d26
+ vshr.u64 d26,d17,#39
+ vadd.i64 d28,d15
+ vsli.64 d25,d17,#30
+ veor d30,d17,d18
+ vsli.64 d26,d17,#25
+ veor d16,d24,d25
+ vadd.i64 d27,d28
+ vbsl d30,d19,d18 @ Maj(a,b,c)
+ veor d16,d26 @ Sigma0(a)
+ vadd.i64 d20,d27
+ vadd.i64 d30,d27
+ @ vadd.i64 d16,d30
+ bne .L16_79_neon
+
+ vadd.i64 d16,d30 @ h+=Maj from the past
+ vldmia r0,{d24-d31} @ load context to temp
+ vadd.i64 q8,q12 @ vectorized accumulate
+ vadd.i64 q9,q13
+ vadd.i64 q10,q14
+ vadd.i64 q11,q15
+ vstmia r0,{d16-d23} @ save context
+ teq r1,r2
+ sub r3,#640 @ rewind K512
+ bne .Loop_neon
+
+ VFP_ABI_POP
+ bx lr @ .word 0xe12fff1e
+.size sha512_block_data_order_neon,.-sha512_block_data_order_neon
+#endif
+.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@openssl.org>"
+.align 2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm OPENSSL_armcap_P,4,4
+#endif
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
new file mode 100644
index 000000000000..269a394e4a53
--- /dev/null
+++ b/arch/arm/crypto/sha512-glue.c
@@ -0,0 +1,121 @@
+/*
+ * sha512-glue.c - accelerated SHA-384/512 for ARM
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_DESCRIPTION("Accelerated SHA-384/SHA-512 secure hash for ARM");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384-arm");
+MODULE_ALIAS_CRYPTO("sha512-arm");
+
+asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks);
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ return sha512_base_do_update(desc, data, len,
+ (sha512_block_fn *)sha512_block_data_order);
+}
+
+int sha512_arm_final(struct shash_desc *desc, u8 *out)
+{
+ sha512_base_do_finalize(desc,
+ (sha512_block_fn *)sha512_block_data_order);
+ return sha512_base_finish(desc, out);
+}
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ sha512_base_do_update(desc, data, len,
+ (sha512_block_fn *)sha512_block_data_order);
+ return sha512_arm_final(desc, out);
+}
+
+static struct shash_alg sha512_arm_algs[] = { {
+ .init = sha384_base_init,
+ .update = sha512_arm_update,
+ .final = sha512_arm_final,
+ .finup = sha512_arm_finup,
+ .descsize = sizeof(struct sha512_state),
+ .digestsize = SHA384_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha384",
+ .cra_driver_name = "sha384-arm",
+ .cra_priority = 250,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA512_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .init = sha512_base_init,
+ .update = sha512_arm_update,
+ .final = sha512_arm_final,
+ .finup = sha512_arm_finup,
+ .descsize = sizeof(struct sha512_state),
+ .digestsize = SHA512_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha512",
+ .cra_driver_name = "sha512-arm",
+ .cra_priority = 250,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA512_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
+
+static int __init sha512_arm_mod_init(void)
+{
+ int err;
+
+ err = crypto_register_shashes(sha512_arm_algs,
+ ARRAY_SIZE(sha512_arm_algs));
+ if (err)
+ return err;
+
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
+ err = crypto_register_shashes(sha512_neon_algs,
+ ARRAY_SIZE(sha512_neon_algs));
+ if (err)
+ goto err_unregister;
+ }
+ return 0;
+
+err_unregister:
+ crypto_unregister_shashes(sha512_arm_algs,
+ ARRAY_SIZE(sha512_arm_algs));
+
+ return err;
+}
+
+static void __exit sha512_arm_mod_fini(void)
+{
+ crypto_unregister_shashes(sha512_arm_algs,
+ ARRAY_SIZE(sha512_arm_algs));
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
+ crypto_unregister_shashes(sha512_neon_algs,
+ ARRAY_SIZE(sha512_neon_algs));
+}
+
+module_init(sha512_arm_mod_init);
+module_exit(sha512_arm_mod_fini);
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
new file mode 100644
index 000000000000..32693684a3ab
--- /dev/null
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -0,0 +1,98 @@
+/*
+ * sha512-neon-glue.c - accelerated SHA-384/512 for ARM NEON
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_ALIAS_CRYPTO("sha384-neon");
+MODULE_ALIAS_CRYPTO("sha512-neon");
+
+asmlinkage void sha512_block_data_order_neon(u64 *state, u8 const *src,
+ int blocks);
+
+static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+
+ if (!may_use_simd() ||
+ (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
+ return sha512_arm_update(desc, data, len);
+
+ kernel_neon_begin();
+ sha512_base_do_update(desc, data, len,
+ (sha512_block_fn *)sha512_block_data_order_neon);
+ kernel_neon_end();
+
+ return 0;
+}
+
+static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ if (!may_use_simd())
+ return sha512_arm_finup(desc, data, len, out);
+
+ kernel_neon_begin();
+ if (len)
+ sha512_base_do_update(desc, data, len,
+ (sha512_block_fn *)sha512_block_data_order_neon);
+ sha512_base_do_finalize(desc,
+ (sha512_block_fn *)sha512_block_data_order_neon);
+ kernel_neon_end();
+
+ return sha512_base_finish(desc, out);
+}
+
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+ return sha512_neon_finup(desc, NULL, 0, out);
+}
+
+struct shash_alg sha512_neon_algs[] = { {
+ .init = sha384_base_init,
+ .update = sha512_neon_update,
+ .final = sha512_neon_final,
+ .finup = sha512_neon_finup,
+ .descsize = sizeof(struct sha512_state),
+ .digestsize = SHA384_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha384",
+ .cra_driver_name = "sha384-neon",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA384_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+
+ }
+}, {
+ .init = sha512_base_init,
+ .update = sha512_neon_update,
+ .final = sha512_neon_final,
+ .finup = sha512_neon_finup,
+ .descsize = sizeof(struct sha512_state),
+ .digestsize = SHA512_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha512",
+ .cra_driver_name = "sha512-neon",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA512_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h
new file mode 100644
index 000000000000..a75d9a82988a
--- /dev/null
+++ b/arch/arm/crypto/sha512.h
@@ -0,0 +1,8 @@
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len);
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out);
+
+extern struct shash_alg sha512_neon_algs[2];
diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c
deleted file mode 100644
index b124dce838d6..000000000000
--- a/arch/arm/crypto/sha512_neon_glue.c
+++ /dev/null
@@ -1,305 +0,0 @@
-/*
- * Glue code for the SHA512 Secure Hash Algorithm assembly implementation
- * using NEON instructions.
- *
- * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This file is based on sha512_ssse3_glue.c:
- * Copyright (C) 2013 Intel Corporation
- * Author: Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/cryptohash.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <crypto/sha.h>
-#include <asm/byteorder.h>
-#include <asm/simd.h>
-#include <asm/neon.h>
-
-
-static const u64 sha512_k[] = {
- 0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,
- 0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,
- 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
- 0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,
- 0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,
- 0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
- 0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,
- 0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,
- 0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
- 0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,
- 0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,
- 0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
- 0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,
- 0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,
- 0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
- 0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,
- 0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,
- 0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
- 0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,
- 0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,
- 0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
- 0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,
- 0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,
- 0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
- 0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,
- 0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,
- 0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
- 0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,
- 0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,
- 0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
- 0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,
- 0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,
- 0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
- 0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,
- 0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,
- 0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
- 0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,
- 0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,
- 0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
- 0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
-};
-
-
-asmlinkage void sha512_transform_neon(u64 *digest, const void *data,
- const u64 k[], unsigned int num_blks);
-
-
-static int sha512_neon_init(struct shash_desc *desc)
-{
- struct sha512_state *sctx = shash_desc_ctx(desc);
-
- sctx->state[0] = SHA512_H0;
- sctx->state[1] = SHA512_H1;
- sctx->state[2] = SHA512_H2;
- sctx->state[3] = SHA512_H3;
- sctx->state[4] = SHA512_H4;
- sctx->state[5] = SHA512_H5;
- sctx->state[6] = SHA512_H6;
- sctx->state[7] = SHA512_H7;
- sctx->count[0] = sctx->count[1] = 0;
-
- return 0;
-}
-
-static int __sha512_neon_update(struct shash_desc *desc, const u8 *data,
- unsigned int len, unsigned int partial)
-{
- struct sha512_state *sctx = shash_desc_ctx(desc);
- unsigned int done = 0;
-
- sctx->count[0] += len;
- if (sctx->count[0] < len)
- sctx->count[1]++;
-
- if (partial) {
- done = SHA512_BLOCK_SIZE - partial;
- memcpy(sctx->buf + partial, data, done);
- sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1);
- }
-
- if (len - done >= SHA512_BLOCK_SIZE) {
- const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
-
- sha512_transform_neon(sctx->state, data + done, sha512_k,
- rounds);
-
- done += rounds * SHA512_BLOCK_SIZE;
- }
-
- memcpy(sctx->buf, data + done, len - done);
-
- return 0;
-}
-
-static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- struct sha512_state *sctx = shash_desc_ctx(desc);
- unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
- int res;
-
- /* Handle the fast case right here */
- if (partial + len < SHA512_BLOCK_SIZE) {
- sctx->count[0] += len;
- if (sctx->count[0] < len)
- sctx->count[1]++;
- memcpy(sctx->buf + partial, data, len);
-
- return 0;
- }
-
- if (!may_use_simd()) {
- res = crypto_sha512_update(desc, data, len);
- } else {
- kernel_neon_begin();
- res = __sha512_neon_update(desc, data, len, partial);
- kernel_neon_end();
- }
-
- return res;
-}
-
-
-/* Add padding and return the message digest. */
-static int sha512_neon_final(struct shash_desc *desc, u8 *out)
-{
- struct sha512_state *sctx = shash_desc_ctx(desc);
- unsigned int i, index, padlen;
- __be64 *dst = (__be64 *)out;
- __be64 bits[2];
- static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
-
- /* save number of bits */
- bits[1] = cpu_to_be64(sctx->count[0] << 3);
- bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
-
- /* Pad out to 112 mod 128 and append length */
- index = sctx->count[0] & 0x7f;
- padlen = (index < 112) ? (112 - index) : ((128+112) - index);
-
- if (!may_use_simd()) {
- crypto_sha512_update(desc, padding, padlen);
- crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits));
- } else {
- kernel_neon_begin();
- /* We need to fill a whole block for __sha512_neon_update() */
- if (padlen <= 112) {
- sctx->count[0] += padlen;
- if (sctx->count[0] < padlen)
- sctx->count[1]++;
- memcpy(sctx->buf + index, padding, padlen);
- } else {
- __sha512_neon_update(desc, padding, padlen, index);
- }
- __sha512_neon_update(desc, (const u8 *)&bits,
- sizeof(bits), 112);
- kernel_neon_end();
- }
-
- /* Store state in digest */
- for (i = 0; i < 8; i++)
- dst[i] = cpu_to_be64(sctx->state[i]);
-
- /* Wipe context */
- memset(sctx, 0, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha512_neon_export(struct shash_desc *desc, void *out)
-{
- struct sha512_state *sctx = shash_desc_ctx(desc);
-
- memcpy(out, sctx, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha512_neon_import(struct shash_desc *desc, const void *in)
-{
- struct sha512_state *sctx = shash_desc_ctx(desc);
-
- memcpy(sctx, in, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha384_neon_init(struct shash_desc *desc)
-{
- struct sha512_state *sctx = shash_desc_ctx(desc);
-
- sctx->state[0] = SHA384_H0;
- sctx->state[1] = SHA384_H1;
- sctx->state[2] = SHA384_H2;
- sctx->state[3] = SHA384_H3;
- sctx->state[4] = SHA384_H4;
- sctx->state[5] = SHA384_H5;
- sctx->state[6] = SHA384_H6;
- sctx->state[7] = SHA384_H7;
-
- sctx->count[0] = sctx->count[1] = 0;
-
- return 0;
-}
-
-static int sha384_neon_final(struct shash_desc *desc, u8 *hash)
-{
- u8 D[SHA512_DIGEST_SIZE];
-
- sha512_neon_final(desc, D);
-
- memcpy(hash, D, SHA384_DIGEST_SIZE);
- memzero_explicit(D, SHA512_DIGEST_SIZE);
-
- return 0;
-}
-
-static struct shash_alg algs[] = { {
- .digestsize = SHA512_DIGEST_SIZE,
- .init = sha512_neon_init,
- .update = sha512_neon_update,
- .final = sha512_neon_final,
- .export = sha512_neon_export,
- .import = sha512_neon_import,
- .descsize = sizeof(struct sha512_state),
- .statesize = sizeof(struct sha512_state),
- .base = {
- .cra_name = "sha512",
- .cra_driver_name = "sha512-neon",
- .cra_priority = 250,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .digestsize = SHA384_DIGEST_SIZE,
- .init = sha384_neon_init,
- .update = sha512_neon_update,
- .final = sha384_neon_final,
- .export = sha512_neon_export,
- .import = sha512_neon_import,
- .descsize = sizeof(struct sha512_state),
- .statesize = sizeof(struct sha512_state),
- .base = {
- .cra_name = "sha384",
- .cra_driver_name = "sha384-neon",
- .cra_priority = 250,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
- .cra_blocksize = SHA384_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static int __init sha512_neon_mod_init(void)
-{
- if (!cpu_has_neon())
- return -ENODEV;
-
- return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit sha512_neon_mod_fini(void)
-{
- crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_init(sha512_neon_mod_init);
-module_exit(sha512_neon_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
-
-MODULE_ALIAS_CRYPTO("sha512");
-MODULE_ALIAS_CRYPTO("sha384");
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index d2f81e6b8c1c..6c2327e1c732 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -81,7 +81,7 @@ do { \
#define read_barrier_depends() do { } while(0)
#define smp_read_barrier_depends() do { } while(0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
diff --git a/arch/arm/include/asm/edac.h b/arch/arm/include/asm/edac.h
index 0df7a2c1fc3d..5189fa819b60 100644
--- a/arch/arm/include/asm/edac.h
+++ b/arch/arm/include/asm/edac.h
@@ -18,11 +18,12 @@
#define ASM_EDAC_H
/*
* ECC atomic, DMA, SMP and interrupt safe scrub function.
- * Implements the per arch atomic_scrub() that EDAC use for software
+ * Implements the per arch edac_atomic_scrub() that EDAC use for software
* ECC scrubbing. It reads memory and then writes back the original
* value, allowing the hardware to detect and correct memory errors.
*/
-static inline void atomic_scrub(void *va, u32 size)
+
+static inline void edac_atomic_scrub(void *va, u32 size)
{
#if __LINUX_ARM_ARCH__ >= 6
unsigned int *virt_addr = va;
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 4e78065a16aa..5eed82809d82 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
+ preempt_disable();
__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
"1: " TUSER(ldr) " %1, [%4]\n"
" teq %1, %2\n"
@@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
: "cc", "memory");
*uval = val;
+ preempt_enable();
+
return ret;
}
@@ -124,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
+#ifndef CONFIG_SMP
+ preempt_disable();
+#endif
+ pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
@@ -146,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable(); /* subsumes preempt_enable() */
+ pagefault_enable();
+#ifndef CONFIG_SMP
+ preempt_enable();
+#endif
if (!ret) {
switch (cmp) {
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index db58deb00aa7..1b7677d1e5e1 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -336,6 +336,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
#define ioremap_nocache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
#define ioremap_cache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
#define ioremap_wc(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_WC)
+#define ioremap_wt(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
#define iounmap __arm_iounmap
/*
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 25410b2d8bc1..194c91b610ff 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -23,7 +23,7 @@
#define c0_MPIDR 1 /* MultiProcessor ID Register */
#define c0_CSSELR 2 /* Cache Size Selection Register */
#define c1_SCTLR 3 /* System Control Register */
-#define c1_ACTLR 4 /* Auxilliary Control Register */
+#define c1_ACTLR 4 /* Auxiliary Control Register */
#define c1_CPACR 5 /* Coprocessor Access Control */
#define c2_TTBR0 6 /* Translation Table Base Register 0 */
#define c2_TTBR0_high 7 /* TTBR0 top 32 bits */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index d71607c16601..e896d2c196e6 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -218,11 +218,6 @@ static inline int kvm_arch_dev_ioctl_check_extension(long ext)
return 0;
}
-static inline void vgic_arch_setup(const struct vgic_params *vgic)
-{
- BUG_ON(vgic->type != VGIC_V2);
-}
-
int kvm_perf_init(void);
int kvm_perf_teardown(void);
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index 585dc33a7a24..a5635444ca41 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -31,16 +31,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
*/
#define PCI_DMA_BUS_IS_PHYS (1)
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- *strat = PCI_DMA_BURST_INFINITY;
- *strategy_parameter = ~0UL;
-}
-#endif
-
#define HAVE_PCI_MMAP
extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
enum pci_mmap_state mmap_state, int write_combine);
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 2fe85fff5cca..370f7a732900 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -18,7 +18,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id)
#define topology_core_id(cpu) (cpu_topology[cpu].core_id)
#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index f8ccc21fa032..4e7f40c577e6 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -33,7 +33,9 @@ ret_fast_syscall:
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq @ disable interrupts
- ldr r1, [tsk, #TI_FLAGS]
+ ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
+ tst r1, #_TIF_SYSCALL_WORK
+ bne __sys_trace_return
tst r1, #_TIF_WORK_MASK
bne fast_work_pending
asm_trace_hardirqs_on
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 213919ba326f..3b8c2833c537 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -304,16 +304,17 @@ static int probe_current_pmu(struct arm_pmu *pmu)
static int of_pmu_irq_cfg(struct platform_device *pdev)
{
int i, irq;
- int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
-
- if (!irqs)
- return -ENOMEM;
+ int *irqs;
/* Don't bother with PPIs; they're already affine */
irq = platform_get_irq(pdev, 0);
if (irq >= 0 && irq_is_percpu(irq))
return 0;
+ irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+ if (!irqs)
+ return -ENOMEM;
+
for (i = 0; i < pdev->num_resources; ++i) {
struct device_node *dn;
int cpu;
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index f1f79d104309..bfb915d05665 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -28,6 +28,7 @@ config KVM
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
select SRCU
select MMU_NOTIFIER
+ select KVM_VFIO
select HAVE_KVM_EVENTFD
select HAVE_KVM_IRQFD
depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 139e46c08b6e..c5eef02c52ba 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -15,7 +15,7 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
KVM := ../../../virt/kvm
-kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o
+kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
obj-y += kvm-arm.o init.o interrupts.o
obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index d9631ecddd56..bc738d2b8392 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -171,7 +171,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
int r;
switch (ext) {
case KVM_CAP_IRQCHIP:
- case KVM_CAP_IRQFD:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_DEVICE_CTRL:
case KVM_CAP_USER_MEMORY:
@@ -532,6 +531,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
kvm_vgic_flush_hwstate(vcpu);
kvm_timer_flush_hwstate(vcpu);
+ preempt_disable();
local_irq_disable();
/*
@@ -544,6 +544,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
local_irq_enable();
+ preempt_enable();
kvm_timer_sync_hwstate(vcpu);
kvm_vgic_sync_hwstate(vcpu);
continue;
@@ -553,14 +554,16 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
* Enter the guest
*/
trace_kvm_entry(*vcpu_pc(vcpu));
- kvm_guest_enter();
+ __kvm_guest_enter();
vcpu->mode = IN_GUEST_MODE;
ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
vcpu->mode = OUTSIDE_GUEST_MODE;
- kvm_guest_exit();
- trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+ /*
+ * Back from guest
+ *************************************************************/
+
/*
* We may have taken a host interrupt in HYP mode (ie
* while executing the guest). This interrupt is still
@@ -574,8 +577,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
local_irq_enable();
/*
- * Back from guest
- *************************************************************/
+ * We do local_irq_enable() before calling kvm_guest_exit() so
+ * that if a timer interrupt hits while running the guest we
+ * account that tick as being spent in the guest. We enable
+ * preemption after calling kvm_guest_exit() so that if we get
+ * preempted we make sure ticks after that is not counted as
+ * guest time.
+ */
+ kvm_guest_exit();
+ trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+ preempt_enable();
+
kvm_timer_sync_hwstate(vcpu);
kvm_vgic_sync_hwstate(vcpu);
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 79caf79b304a..f7db3a5d80e3 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -170,13 +170,9 @@ __kvm_vcpu_return:
@ Don't trap coprocessor accesses for host kernel
set_hstr vmexit
set_hdcr vmexit
- set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+ set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
#ifdef CONFIG_VFPv3
- @ Save floating point registers we if let guest use them.
- tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
- bne after_vfp_restore
-
@ Switch VFP/NEON hardware state to the host's
add r7, vcpu, #VCPU_VFP_GUEST
store_vfp_state r7
@@ -188,6 +184,8 @@ after_vfp_restore:
@ Restore FPEXC_EN which we clobbered on entry
pop {r2}
VFPFMXR FPEXC, r2
+#else
+after_vfp_restore:
#endif
@ Reset Hyp-role
@@ -483,7 +481,7 @@ switch_to_guest_vfp:
push {r3-r7}
@ NEON/VFP used. Turn on VFP access.
- set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
+ set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
@ Switch VFP/NEON hardware state to the guest's
add r7, r0, #VCPU_VFP_HOST
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 35e4a3a0c476..702740d37465 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -412,7 +412,6 @@ vcpu .req r0 @ vcpu pointer always in r0
add r11, vcpu, #VCPU_VGIC_CPU
/* Save all interesting registers */
- ldr r3, [r2, #GICH_HCR]
ldr r4, [r2, #GICH_VMCR]
ldr r5, [r2, #GICH_MISR]
ldr r6, [r2, #GICH_EISR0]
@@ -420,7 +419,6 @@ vcpu .req r0 @ vcpu pointer always in r0
ldr r8, [r2, #GICH_ELRSR0]
ldr r9, [r2, #GICH_ELRSR1]
ldr r10, [r2, #GICH_APR]
-ARM_BE8(rev r3, r3 )
ARM_BE8(rev r4, r4 )
ARM_BE8(rev r5, r5 )
ARM_BE8(rev r6, r6 )
@@ -429,7 +427,6 @@ ARM_BE8(rev r8, r8 )
ARM_BE8(rev r9, r9 )
ARM_BE8(rev r10, r10 )
- str r3, [r11, #VGIC_V2_CPU_HCR]
str r4, [r11, #VGIC_V2_CPU_VMCR]
str r5, [r11, #VGIC_V2_CPU_MISR]
#ifdef CONFIG_CPU_ENDIAN_BE8
@@ -591,8 +588,13 @@ ARM_BE8(rev r6, r6 )
.endm
/* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2. */
-.macro set_hcptr operation, mask
+ * (hardware reset value is 0). Keep previous value in r2.
+ * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
+ * VFP wasn't already enabled (always executed on vmtrap).
+ * If a label is specified with vmexit, it is branched to if VFP wasn't
+ * enabled.
+ */
+.macro set_hcptr operation, mask, label = none
mrc p15, 4, r2, c1, c1, 2
ldr r3, =\mask
.if \operation == vmentry
@@ -601,6 +603,17 @@ ARM_BE8(rev r6, r6 )
bic r3, r2, r3 @ Don't trap defined coproc-accesses
.endif
mcr p15, 4, r3, c1, c1, 2
+ .if \operation != vmentry
+ .if \operation == vmexit
+ tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+ beq 1f
+ .endif
+ isb
+ .if \label != none
+ b \label
+ .endif
+1:
+ .endif
.endm
/* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 1d5accbd3dcf..7b4201294187 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -691,8 +691,8 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
* work. This is not used by the hardware and we have no
* alignment requirement for this allocation.
*/
- pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
- GFP_KERNEL | __GFP_ZERO);
+ pgd = kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
+ GFP_KERNEL | __GFP_ZERO);
if (!pgd) {
kvm_free_hwpgd(hwpgd);
@@ -1155,7 +1155,8 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
*/
void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
{
- struct kvm_memory_slot *memslot = id_to_memslot(kvm->memslots, slot);
+ struct kvm_memslots *slots = kvm_memslots(kvm);
+ struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
@@ -1718,8 +1719,9 @@ out:
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
/*
@@ -1733,7 +1735,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
hva_t hva = mem->userspace_addr;
@@ -1838,7 +1840,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
return 0;
}
-void kvm_arch_memslots_updated(struct kvm *kvm)
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
{
}
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 02fa8eff6ae1..4b94b513168d 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -24,6 +24,8 @@
#include <asm/kvm_psci.h>
#include <asm/kvm_host.h>
+#include <uapi/linux/psci.h>
+
/*
* This is an implementation of the Power State Coordination Interface
* as described in ARM document number ARM DEN 0022A.
@@ -230,10 +232,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
case PSCI_0_2_FN64_AFFINITY_INFO:
val = kvm_psci_vcpu_affinity_info(vcpu);
break;
- case PSCI_0_2_FN_MIGRATE:
- case PSCI_0_2_FN64_MIGRATE:
- val = PSCI_RET_NOT_SUPPORTED;
- break;
case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
/*
* Trusted OS is MP hence does not require migration
@@ -242,10 +240,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
*/
val = PSCI_0_2_TOS_MP;
break;
- case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
- case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
- val = PSCI_RET_NOT_SUPPORTED;
- break;
case PSCI_0_2_FN_SYSTEM_OFF:
kvm_psci_system_off(vcpu);
/*
@@ -271,7 +265,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
ret = 0;
break;
default:
- return -EINVAL;
+ val = PSCI_RET_NOT_SUPPORTED;
+ break;
}
*vcpu_reg(vcpu, 0) = val;
@@ -291,12 +286,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
case KVM_PSCI_FN_CPU_ON:
val = kvm_psci_vcpu_on(vcpu);
break;
- case KVM_PSCI_FN_CPU_SUSPEND:
- case KVM_PSCI_FN_MIGRATE:
+ default:
val = PSCI_RET_NOT_SUPPORTED;
break;
- default:
- return -EINVAL;
}
*vcpu_reg(vcpu, 0) = val;
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 947567ff67f9..af2267f6a529 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -167,7 +167,7 @@ Boston, MA 02111-1307, USA. */
#endif
- @ Perform all needed substractions to keep only the reminder.
+ @ Perform all needed subtractions to keep only the reminder.
@ Do comparisons in batch of 4 first.
subs \order, \order, #3 @ yes, 3 is intended here
blt 2f
@@ -189,7 +189,7 @@ Boston, MA 02111-1307, USA. */
teqne \dividend, #0
beq 5f
- @ Either 1, 2 or 3 comparison/substractions are left.
+ @ Either 1, 2 or 3 comparison/subtractions are left.
2: cmn \order, #2
blt 4f
beq 3f
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 45ce065e7170..3b8740c083c4 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -11,6 +11,7 @@
* is licensed "as is" without any warranty of any kind, whether express
* or implied.
*/
+#include <linux/clkdev.h>
#include <linux/gpio.h>
#include <linux/init.h>
#include <linux/clk.h>
diff --git a/arch/arm/mach-davinci/pm_domain.c b/arch/arm/mach-davinci/pm_domain.c
index 641edc313938..78eac2c0c146 100644
--- a/arch/arm/mach-davinci/pm_domain.c
+++ b/arch/arm/mach-davinci/pm_domain.c
@@ -14,39 +14,9 @@
#include <linux/pm_clock.h>
#include <linux/platform_device.h>
-#ifdef CONFIG_PM
-static int davinci_pm_runtime_suspend(struct device *dev)
-{
- int ret;
-
- dev_dbg(dev, "%s\n", __func__);
-
- ret = pm_generic_runtime_suspend(dev);
- if (ret)
- return ret;
-
- ret = pm_clk_suspend(dev);
- if (ret) {
- pm_generic_runtime_resume(dev);
- return ret;
- }
-
- return 0;
-}
-
-static int davinci_pm_runtime_resume(struct device *dev)
-{
- dev_dbg(dev, "%s\n", __func__);
-
- pm_clk_resume(dev);
- return pm_generic_runtime_resume(dev);
-}
-#endif
-
static struct dev_pm_domain davinci_pm_domain = {
.ops = {
- SET_RUNTIME_PM_OPS(davinci_pm_runtime_suspend,
- davinci_pm_runtime_resume, NULL)
+ USE_PM_CLK_RUNTIME_OPS
USE_PLATFORM_PM_SLEEP_OPS
},
};
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index c0b6dccbf7bd..7d23ce04cad5 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -87,8 +87,8 @@ static unsigned int exynos_pmu_spare3;
static u32 exynos_irqwake_intmask = 0xffffffff;
static const struct exynos_wkup_irq exynos3250_wkup_irq[] = {
- { 105, BIT(1) }, /* RTC alarm */
- { 106, BIT(2) }, /* RTC tick */
+ { 73, BIT(1) }, /* RTC alarm */
+ { 74, BIT(2) }, /* RTC tick */
{ /* sentinel */ },
};
diff --git a/arch/arm/mach-gemini/gpio.c b/arch/arm/mach-gemini/gpio.c
index f8cb5710d6ee..3292f2e6ed6f 100644
--- a/arch/arm/mach-gemini/gpio.c
+++ b/arch/arm/mach-gemini/gpio.c
@@ -223,8 +223,8 @@ void __init gemini_gpio_init(void)
set_irq_flags(j, IRQF_VALID);
}
- irq_set_chained_handler(IRQ_GPIO(i), gpio_irq_handler);
- irq_set_handler_data(IRQ_GPIO(i), (void *)i);
+ irq_set_chained_handler_and_data(IRQ_GPIO(i), gpio_irq_handler,
+ (void *)i);
}
BUG_ON(gpiochip_add(&gemini_gpio_chip));
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 4d60005e9277..6d0893a3828e 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -280,9 +280,15 @@ void __init imx_gpc_check_dt(void)
struct device_node *np;
np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpc");
- if (WARN_ON(!np ||
- !of_find_property(np, "interrupt-controller", NULL)))
- pr_warn("Outdated DT detected, system is about to crash!!!\n");
+ if (WARN_ON(!np))
+ return;
+
+ if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
+ pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+
+ /* map GPC, so that at least CPUidle and WARs keep working */
+ gpc_base = of_iomap(np, 0);
+ }
}
#ifdef CONFIG_PM_GENERIC_DOMAINS
@@ -443,6 +449,10 @@ static int imx_gpc_probe(struct platform_device *pdev)
struct regulator *pu_reg;
int ret;
+ /* bail out if DT too old and doesn't provide the necessary info */
+ if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells"))
+ return 0;
+
pu_reg = devm_regulator_get_optional(&pdev->dev, "pu");
if (PTR_ERR(pu_reg) == -ENODEV)
pu_reg = NULL;
diff --git a/arch/arm/mach-keystone/pm_domain.c b/arch/arm/mach-keystone/pm_domain.c
index 41bebfd296dc..edea697e8253 100644
--- a/arch/arm/mach-keystone/pm_domain.c
+++ b/arch/arm/mach-keystone/pm_domain.c
@@ -19,40 +19,9 @@
#include <linux/clk-provider.h>
#include <linux/of.h>
-#ifdef CONFIG_PM
-static int keystone_pm_runtime_suspend(struct device *dev)
-{
- int ret;
-
- dev_dbg(dev, "%s\n", __func__);
-
- ret = pm_generic_runtime_suspend(dev);
- if (ret)
- return ret;
-
- ret = pm_clk_suspend(dev);
- if (ret) {
- pm_generic_runtime_resume(dev);
- return ret;
- }
-
- return 0;
-}
-
-static int keystone_pm_runtime_resume(struct device *dev)
-{
- dev_dbg(dev, "%s\n", __func__);
-
- pm_clk_resume(dev);
-
- return pm_generic_runtime_resume(dev);
-}
-#endif
-
static struct dev_pm_domain keystone_pm_domain = {
.ops = {
- SET_RUNTIME_PM_OPS(keystone_pm_runtime_suspend,
- keystone_pm_runtime_resume, NULL)
+ USE_PM_CLK_RUNTIME_OPS
USE_PLATFORM_PM_SLEEP_OPS
},
};
diff --git a/arch/arm/mach-lpc32xx/clock.c b/arch/arm/mach-lpc32xx/clock.c
index dd5d6f532e8c..661c8f4b2310 100644
--- a/arch/arm/mach-lpc32xx/clock.c
+++ b/arch/arm/mach-lpc32xx/clock.c
@@ -1238,10 +1238,7 @@ static struct clk_lookup lookups[] = {
static int __init clk_init(void)
{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(lookups); i++)
- clkdev_add(&lookups[i]);
+ clkdev_add_table(lookups, ARRAY_SIZE(lookups));
/*
* Setup muxed SYSCLK for HCLK PLL base -this selects the
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 85089d821982..3bc59390a943 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -7,6 +7,7 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+#include <linux/clkdev.h>
#include <linux/irq.h>
#include <linux/gpio.h>
#include <linux/kernel.h>
@@ -14,7 +15,6 @@
#include <linux/mutex.h>
#include <linux/platform_device.h>
#include <linux/input.h>
-#include <linux/clk.h>
#include <linux/omapfb.h>
#include <linux/spi/spi.h>
diff --git a/arch/arm/mach-omap1/pm_bus.c b/arch/arm/mach-omap1/pm_bus.c
index c40e209de65c..667c1637ff91 100644
--- a/arch/arm/mach-omap1/pm_bus.c
+++ b/arch/arm/mach-omap1/pm_bus.c
@@ -21,48 +21,15 @@
#include "soc.h"
-#ifdef CONFIG_PM
-static int omap1_pm_runtime_suspend(struct device *dev)
-{
- int ret;
-
- dev_dbg(dev, "%s\n", __func__);
-
- ret = pm_generic_runtime_suspend(dev);
- if (ret)
- return ret;
-
- ret = pm_clk_suspend(dev);
- if (ret) {
- pm_generic_runtime_resume(dev);
- return ret;
- }
-
- return 0;
-}
-
-static int omap1_pm_runtime_resume(struct device *dev)
-{
- dev_dbg(dev, "%s\n", __func__);
-
- pm_clk_resume(dev);
- return pm_generic_runtime_resume(dev);
-}
-
static struct dev_pm_domain default_pm_domain = {
.ops = {
- .runtime_suspend = omap1_pm_runtime_suspend,
- .runtime_resume = omap1_pm_runtime_resume,
+ USE_PM_CLK_RUNTIME_OPS
USE_PLATFORM_PM_SLEEP_OPS
},
};
-#define OMAP1_PM_DOMAIN (&default_pm_domain)
-#else
-#define OMAP1_PM_DOMAIN NULL
-#endif /* CONFIG_PM */
static struct pm_clk_notifier_block platform_bus_notifier = {
- .pm_domain = OMAP1_PM_DOMAIN,
+ .pm_domain = &default_pm_domain,
.con_ids = { "ick", "fck", NULL, },
};
diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
index 85e0b0c06718..b64d717bfab6 100644
--- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
+++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
@@ -232,14 +232,12 @@ void omap2xxx_clkt_vps_init(void)
struct clk_hw_omap *hw = NULL;
struct clk *clk;
const char *parent_name = "mpu_ck";
- struct clk_lookup *lookup = NULL;
omap2xxx_clkt_vps_late_init();
omap2xxx_clkt_vps_check_bootloader_rates();
hw = kzalloc(sizeof(*hw), GFP_KERNEL);
- lookup = kzalloc(sizeof(*lookup), GFP_KERNEL);
- if (!hw || !lookup)
+ if (!hw)
goto cleanup;
init.name = "virt_prcm_set";
init.ops = &virt_prcm_set_ops;
@@ -249,15 +247,9 @@ void omap2xxx_clkt_vps_init(void)
hw->hw.init = &init;
clk = clk_register(NULL, &hw->hw);
-
- lookup->dev_id = NULL;
- lookup->con_id = "cpufreq_ck";
- lookup->clk = clk;
-
- clkdev_add(lookup);
+ clkdev_create(clk, "cpufreq_ck", NULL);
return;
cleanup:
kfree(hw);
- kfree(lookup);
}
#endif
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index f492ae147c6a..6ab13d18c636 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -287,6 +287,8 @@ static enum omapdss_version __init omap_display_get_version(void)
return OMAPDSS_VER_OMAP5;
else if (soc_is_am43xx())
return OMAPDSS_VER_AM43xx;
+ else if (soc_is_dra7xx())
+ return OMAPDSS_VER_DRA7xx;
else
return OMAPDSS_VER_UNKNOWN;
}
@@ -568,25 +570,25 @@ void __init omapdss_early_init_of(void)
}
+static const char * const omapdss_compat_names[] __initconst = {
+ "ti,omap2-dss",
+ "ti,omap3-dss",
+ "ti,omap4-dss",
+ "ti,omap5-dss",
+ "ti,dra7-dss",
+};
+
struct device_node * __init omapdss_find_dss_of_node(void)
{
struct device_node *node;
+ int i;
- node = of_find_compatible_node(NULL, NULL, "ti,omap2-dss");
- if (node)
- return node;
-
- node = of_find_compatible_node(NULL, NULL, "ti,omap3-dss");
- if (node)
- return node;
-
- node = of_find_compatible_node(NULL, NULL, "ti,omap4-dss");
- if (node)
- return node;
-
- node = of_find_compatible_node(NULL, NULL, "ti,omap5-dss");
- if (node)
- return node;
+ for (i = 0; i < ARRAY_SIZE(omapdss_compat_names); ++i) {
+ node = of_find_compatible_node(NULL, NULL,
+ omapdss_compat_names[i]);
+ if (node)
+ return node;
+ }
return NULL;
}
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 166b18f515a2..e417f7fcb2ba 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -47,7 +47,7 @@ static void _add_clkdev(struct omap_device *od, const char *clk_alias,
const char *clk_name)
{
struct clk *r;
- struct clk_lookup *l;
+ int rc;
if (!clk_alias || !clk_name)
return;
@@ -62,21 +62,15 @@ static void _add_clkdev(struct omap_device *od, const char *clk_alias,
return;
}
- r = clk_get(NULL, clk_name);
- if (IS_ERR(r)) {
- dev_err(&od->pdev->dev,
- "clk_get for %s failed\n", clk_name);
- return;
+ rc = clk_add_alias(clk_alias, dev_name(&od->pdev->dev), clk_name, NULL);
+ if (rc) {
+ if (rc == -ENODEV || rc == -ENOMEM)
+ dev_err(&od->pdev->dev,
+ "clkdev_alloc for %s failed\n", clk_alias);
+ else
+ dev_err(&od->pdev->dev,
+ "clk_get for %s failed\n", clk_name);
}
-
- l = clkdev_alloc(r, clk_alias, dev_name(&od->pdev->dev));
- if (!l) {
- dev_err(&od->pdev->dev,
- "clkdev_alloc for %s failed\n", clk_alias);
- return;
- }
-
- clkdev_add(l);
}
/**
@@ -688,11 +682,8 @@ struct dev_pm_domain omap_device_pm_domain = {
SET_RUNTIME_PM_OPS(_od_runtime_suspend, _od_runtime_resume,
NULL)
USE_PLATFORM_PM_SLEEP_OPS
- .suspend_noirq = _od_suspend_noirq,
- .resume_noirq = _od_resume_noirq,
- .freeze_noirq = _od_suspend_noirq,
- .thaw_noirq = _od_resume_noirq,
- .restore_noirq = _od_resume_noirq,
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(_od_suspend_noirq,
+ _od_resume_noirq)
}
};
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 0e64c2fac0b5..9961f95f52ae 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -49,6 +49,27 @@
*/
/*
+ * 'dmm' class
+ * instance(s): dmm
+ */
+static struct omap_hwmod_class dra7xx_dmm_hwmod_class = {
+ .name = "dmm",
+};
+
+/* dmm */
+static struct omap_hwmod dra7xx_dmm_hwmod = {
+ .name = "dmm",
+ .class = &dra7xx_dmm_hwmod_class,
+ .clkdm_name = "emif_clkdm",
+ .prcm = {
+ .omap4 = {
+ .clkctrl_offs = DRA7XX_CM_EMIF_DMM_CLKCTRL_OFFSET,
+ .context_offs = DRA7XX_RM_EMIF_DMM_CONTEXT_OFFSET,
+ },
+ },
+};
+
+/*
* 'l3' class
* instance(s): l3_instr, l3_main_1, l3_main_2
*/
@@ -438,6 +459,7 @@ static struct omap_hwmod_opt_clk dss_opt_clks[] = {
{ .role = "video2_clk", .clk = "dss_video2_clk" },
{ .role = "video1_clk", .clk = "dss_video1_clk" },
{ .role = "hdmi_clk", .clk = "dss_hdmi_clk" },
+ { .role = "hdcp_clk", .clk = "dss_deshdcp_clk" },
};
static struct omap_hwmod dra7xx_dss_hwmod = {
@@ -500,6 +522,7 @@ static struct omap_hwmod dra7xx_dss_dispc_hwmod = {
},
},
.dev_attr = &dss_dispc_dev_attr,
+ .parent_hwmod = &dra7xx_dss_hwmod,
};
/*
@@ -541,6 +564,7 @@ static struct omap_hwmod dra7xx_dss_hdmi_hwmod = {
},
.opt_clks = dss_hdmi_opt_clks,
.opt_clks_cnt = ARRAY_SIZE(dss_hdmi_opt_clks),
+ .parent_hwmod = &dra7xx_dss_hwmod,
};
/*
@@ -2321,6 +2345,14 @@ static struct omap_hwmod dra7xx_wd_timer2_hwmod = {
* Interfaces
*/
+/* l3_main_1 -> dmm */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__dmm = {
+ .master = &dra7xx_l3_main_1_hwmod,
+ .slave = &dra7xx_dmm_hwmod,
+ .clk = "l3_iclk_div",
+ .user = OCP_USER_SDMA,
+};
+
/* l3_main_2 -> l3_instr */
static struct omap_hwmod_ocp_if dra7xx_l3_main_2__l3_instr = {
.master = &dra7xx_l3_main_2_hwmod,
@@ -3289,6 +3321,7 @@ static struct omap_hwmod_ocp_if dra7xx_l4_wkup__wd_timer2 = {
};
static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
+ &dra7xx_l3_main_1__dmm,
&dra7xx_l3_main_2__l3_instr,
&dra7xx_l4_cfg__l3_main_1,
&dra7xx_mpu__l3_main_1,
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index d1dedc8195ed..eafd120b53f1 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -203,23 +203,8 @@ save_context_wfi:
*/
ldr r1, kernel_flush
blx r1
- /*
- * The kernel doesn't interwork: v7_flush_dcache_all in particluar will
- * always return in Thumb state when CONFIG_THUMB2_KERNEL is enabled.
- * This sequence switches back to ARM. Note that .align may insert a
- * nop: bx pc needs to be word-aligned in order to work.
- */
- THUMB( .thumb )
- THUMB( .align )
- THUMB( bx pc )
- THUMB( nop )
- .arm
-
b omap3_do_wfi
-
-/*
- * Local variables
- */
+ENDPROC(omap34xx_cpu_suspend)
omap3_do_wfi_sram_addr:
.word omap3_do_wfi_sram
kernel_flush:
@@ -364,10 +349,7 @@ exit_nonoff_modes:
* ===================================
*/
ldmfd sp!, {r4 - r11, pc} @ restore regs and return
-
-/*
- * Local variables
- */
+ENDPROC(omap3_do_wfi)
sdrc_power:
.word SDRC_POWER_V
cm_idlest1_core:
diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index cfb864173ce3..4427bf26ea47 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -10,6 +10,7 @@
*
*/
+#include <linux/clkdev.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/gpio.h>
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index 4ac9ab80d24b..7518310c9015 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -11,6 +11,7 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+#include <linux/clkdev.h>
#include <linux/gpio.h>
#include <linux/gpio/machine.h>
#include <linux/module.h>
diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c
index f1aeb54fabe3..2385052b0ce1 100644
--- a/arch/arm/mach-pxa/pxa_cplds_irqs.c
+++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c
@@ -107,7 +107,7 @@ static int cplds_probe(struct platform_device *pdev)
struct resource *res;
struct cplds *fpga;
int ret;
- unsigned int base_irq = 0;
+ int base_irq;
unsigned long irqflags = 0;
fpga = devm_kzalloc(&pdev->dev, sizeof(*fpga), GFP_KERNEL);
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 7780d1faa06f..92e56d8a24d8 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -12,6 +12,7 @@
*
*/
+#include <linux/clkdev.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/platform_device.h>
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index af868d258e66..99d9a3b1bf34 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -327,8 +327,7 @@ static int neponset_probe(struct platform_device *dev)
irq_set_chip(d->irq_base + NEP_IRQ_SA1111, &nochip);
irq_set_irq_type(irq, IRQ_TYPE_EDGE_RISING);
- irq_set_handler_data(irq, d);
- irq_set_chained_handler(irq, neponset_irq_handler);
+ irq_set_chained_handler_and_data(irq, neponset_irq_handler, d);
/*
* We would set IRQ_GPIO25 to be a wake-up IRQ, but unfortunately
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 6333d9c17875..0d629b8f973f 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -276,7 +276,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index b98895d9fe57..ee8dfa793989 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -59,6 +59,7 @@ void *kmap_atomic(struct page *page)
void *kmap;
int type;
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
@@ -121,6 +122,7 @@ void __kunmap_atomic(void *kvaddr)
kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
@@ -130,6 +132,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
int idx, type;
struct page *page = pfn_to_page(pfn);
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index be92fa0f2f35..8a63b4cdc0f2 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -268,6 +268,7 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
if (mdesc->reserve)
mdesc->reserve();
+ early_init_fdt_reserve_self();
early_init_fdt_scan_reserved_mem();
/* reserve memory for DMA contiguous allocations */
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4e6ef896c619..7186382672b5 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1112,22 +1112,22 @@ void __init sanity_check_meminfo(void)
}
/*
- * Find the first non-section-aligned page, and point
+ * Find the first non-pmd-aligned page, and point
* memblock_limit at it. This relies on rounding the
- * limit down to be section-aligned, which happens at
- * the end of this function.
+ * limit down to be pmd-aligned, which happens at the
+ * end of this function.
*
* With this algorithm, the start or end of almost any
- * bank can be non-section-aligned. The only exception
- * is that the start of the bank 0 must be section-
+ * bank can be non-pmd-aligned. The only exception is
+ * that the start of the bank 0 must be section-
* aligned, since otherwise memory would need to be
* allocated when mapping the start of bank 0, which
* occurs before any free memory is mapped.
*/
if (!memblock_limit) {
- if (!IS_ALIGNED(block_start, SECTION_SIZE))
+ if (!IS_ALIGNED(block_start, PMD_SIZE))
memblock_limit = block_start;
- else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+ else if (!IS_ALIGNED(block_end, PMD_SIZE))
memblock_limit = arm_lowmem_limit;
}
@@ -1137,12 +1137,12 @@ void __init sanity_check_meminfo(void)
high_memory = __va(arm_lowmem_limit - 1) + 1;
/*
- * Round the memblock limit down to a section size. This
+ * Round the memblock limit down to a pmd size. This
* helps to ensure that we will allocate memory from the
- * last full section, which should be mapped.
+ * last full pmd, which should be mapped.
*/
if (memblock_limit)
- memblock_limit = round_down(memblock_limit, SECTION_SIZE);
+ memblock_limit = round_down(memblock_limit, PMD_SIZE);
if (!memblock_limit)
memblock_limit = arm_lowmem_limit;
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index e0e23582c8b4..4550d247e308 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -873,6 +873,16 @@ b_epilogue:
off = offsetof(struct sk_buff, queue_mapping);
emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
break;
+ case BPF_LDX | BPF_W | BPF_ABS:
+ /*
+ * load a 32bit word from struct seccomp_data.
+ * seccomp_check_filter() will already have checked
+ * that k is 32bit aligned and lies within the
+ * struct seccomp_data.
+ */
+ ctx->seen |= SEEN_SKB;
+ emit(ARM_LDR_I(r_A, r_skb, k), ctx);
+ break;
default:
return -1;
}
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index f5b00f41c4f6..2235081a04ee 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -28,11 +28,7 @@
void __init orion_clkdev_add(const char *con_id, const char *dev_id,
struct clk *clk)
{
- struct clk_lookup *cl;
-
- cl = clkdev_alloc(clk, con_id, dev_id);
- if (cl)
- clkdev_add(cl);
+ clkdev_create(clk, con_id, "%s", dev_id);
}
/* Create clkdev entries for all orion platforms except kirkwood.
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 224081ccc92f..7d0f07020c80 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -272,6 +272,7 @@ void xen_arch_pre_suspend(void) { }
void xen_arch_post_suspend(int suspend_cancelled) { }
void xen_timer_resume(void) { }
void xen_arch_resume(void) { }
+void xen_arch_suspend(void) { }
/* In the hypervisor.S file. */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7796af4b1d6f..290ed648aa11 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,5 +1,6 @@
config ARM64
def_bool y
+ select ACPI_CCA_REQUIRED if ACPI
select ACPI_GENERIC_GSI if ACPI
select ACPI_REDUCED_HARDWARE_ONLY if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -22,6 +23,7 @@ config ARM64
select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS
select COMMON_CLK
+ select EDAC_SUPPORT
select CPU_PM if (SUSPEND || CPU_IDLE)
select DCACHE_WORD_ACCESS
select GENERIC_ALLOCATOR
@@ -71,6 +73,7 @@ config ARM64
select HAVE_RCU_TABLE_FREE
select HAVE_SYSCALL_TRACEPOINTS
select IRQ_DOMAIN
+ select IRQ_FORCED_THREADING
select MODULES_USE_ELF_RELA
select NO_BOOTMEM
select OF
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index c8d3e0e86678..0bb287ca0a98 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -374,6 +374,111 @@
};
};
+ msi: msi@79000000 {
+ compatible = "apm,xgene1-msi";
+ msi-controller;
+ reg = <0x00 0x79000000 0x0 0x900000>;
+ interrupts = < 0x0 0x10 0x4
+ 0x0 0x11 0x4
+ 0x0 0x12 0x4
+ 0x0 0x13 0x4
+ 0x0 0x14 0x4
+ 0x0 0x15 0x4
+ 0x0 0x16 0x4
+ 0x0 0x17 0x4
+ 0x0 0x18 0x4
+ 0x0 0x19 0x4
+ 0x0 0x1a 0x4
+ 0x0 0x1b 0x4
+ 0x0 0x1c 0x4
+ 0x0 0x1d 0x4
+ 0x0 0x1e 0x4
+ 0x0 0x1f 0x4>;
+ };
+
+ csw: csw@7e200000 {
+ compatible = "apm,xgene-csw", "syscon";
+ reg = <0x0 0x7e200000 0x0 0x1000>;
+ };
+
+ mcba: mcba@7e700000 {
+ compatible = "apm,xgene-mcb", "syscon";
+ reg = <0x0 0x7e700000 0x0 0x1000>;
+ };
+
+ mcbb: mcbb@7e720000 {
+ compatible = "apm,xgene-mcb", "syscon";
+ reg = <0x0 0x7e720000 0x0 0x1000>;
+ };
+
+ efuse: efuse@1054a000 {
+ compatible = "apm,xgene-efuse", "syscon";
+ reg = <0x0 0x1054a000 0x0 0x20>;
+ };
+
+ edac@78800000 {
+ compatible = "apm,xgene-edac";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+ regmap-csw = <&csw>;
+ regmap-mcba = <&mcba>;
+ regmap-mcbb = <&mcbb>;
+ regmap-efuse = <&efuse>;
+ reg = <0x0 0x78800000 0x0 0x100>;
+ interrupts = <0x0 0x20 0x4>,
+ <0x0 0x21 0x4>,
+ <0x0 0x27 0x4>;
+
+ edacmc@7e800000 {
+ compatible = "apm,xgene-edac-mc";
+ reg = <0x0 0x7e800000 0x0 0x1000>;
+ memory-controller = <0>;
+ };
+
+ edacmc@7e840000 {
+ compatible = "apm,xgene-edac-mc";
+ reg = <0x0 0x7e840000 0x0 0x1000>;
+ memory-controller = <1>;
+ };
+
+ edacmc@7e880000 {
+ compatible = "apm,xgene-edac-mc";
+ reg = <0x0 0x7e880000 0x0 0x1000>;
+ memory-controller = <2>;
+ };
+
+ edacmc@7e8c0000 {
+ compatible = "apm,xgene-edac-mc";
+ reg = <0x0 0x7e8c0000 0x0 0x1000>;
+ memory-controller = <3>;
+ };
+
+ edacpmd@7c000000 {
+ compatible = "apm,xgene-edac-pmd";
+ reg = <0x0 0x7c000000 0x0 0x200000>;
+ pmd-controller = <0>;
+ };
+
+ edacpmd@7c200000 {
+ compatible = "apm,xgene-edac-pmd";
+ reg = <0x0 0x7c200000 0x0 0x200000>;
+ pmd-controller = <1>;
+ };
+
+ edacpmd@7c400000 {
+ compatible = "apm,xgene-edac-pmd";
+ reg = <0x0 0x7c400000 0x0 0x200000>;
+ pmd-controller = <2>;
+ };
+
+ edacpmd@7c600000 {
+ compatible = "apm,xgene-edac-pmd";
+ reg = <0x0 0x7c600000 0x0 0x200000>;
+ pmd-controller = <3>;
+ };
+ };
+
pcie0: pcie@1f2b0000 {
status = "disabled";
device_type = "pci";
@@ -395,6 +500,7 @@
0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
dma-coherent;
clocks = <&pcie0clk 0>;
+ msi-parent = <&msi>;
};
pcie1: pcie@1f2c0000 {
@@ -418,6 +524,7 @@
0x0 0x0 0x0 0x4 &gic 0x0 0xcb 0x1>;
dma-coherent;
clocks = <&pcie1clk 0>;
+ msi-parent = <&msi>;
};
pcie2: pcie@1f2d0000 {
@@ -441,6 +548,7 @@
0x0 0x0 0x0 0x4 &gic 0x0 0xd1 0x1>;
dma-coherent;
clocks = <&pcie2clk 0>;
+ msi-parent = <&msi>;
};
pcie3: pcie@1f500000 {
@@ -464,6 +572,7 @@
0x0 0x0 0x0 0x4 &gic 0x0 0xd7 0x1>;
dma-coherent;
clocks = <&pcie3clk 0>;
+ msi-parent = <&msi>;
};
pcie4: pcie@1f510000 {
@@ -487,6 +596,7 @@
0x0 0x0 0x0 0x4 &gic 0x0 0xdd 0x1>;
dma-coherent;
clocks = <&pcie4clk 0>;
+ msi-parent = <&msi>;
};
serial0: serial@1c020000 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
index 43d54017b779..d0ab012fa379 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
@@ -16,7 +16,8 @@
#include "mt8173.dtsi"
/ {
- model = "mediatek,mt8173-evb";
+ model = "MediaTek MT8173 evaluation board";
+ compatible = "mediatek,mt8173-evb", "mediatek,mt8173";
aliases {
serial0 = &uart0;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 2ed7449d9273..daefbf0329a6 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -180,6 +180,7 @@ CONFIG_LOCKUP_DETECTOR=y
# CONFIG_SCHED_DEBUG is not set
# CONFIG_DEBUG_PREEMPT is not set
# CONFIG_FTRACE is not set
+CONFIG_MEMTEST=y
CONFIG_SECURITY=y
CONFIG_CRYPTO_ANSI_CPRNG=y
CONFIG_ARM64_CRYPTO=y
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 6c348df5bf36..3303e8a7b837 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -13,7 +13,7 @@
#include <crypto/aes.h>
#include <crypto/algapi.h>
#include <crypto/scatterwalk.h>
-#include <linux/crypto.h>
+#include <crypto/internal/aead.h>
#include <linux/module.h>
#include "aes-ce-setkey.h"
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 59c05d8ea4a0..39248d3adf5d 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -16,6 +16,7 @@
#include <linux/irqchip/arm-gic-acpi.h>
#include <asm/cputype.h>
+#include <asm/psci.h>
#include <asm/smp_plat.h>
/* Basic configuration for ACPI */
@@ -39,18 +40,6 @@ extern int acpi_disabled;
extern int acpi_noirq;
extern int acpi_pci_disabled;
-/* 1 to indicate PSCI 0.2+ is implemented */
-static inline bool acpi_psci_present(void)
-{
- return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT;
-}
-
-/* 1 to indicate HVC must be used instead of SMC as the PSCI conduit */
-static inline bool acpi_psci_use_hvc(void)
-{
- return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
-}
-
static inline void disable_acpi(void)
{
acpi_disabled = 1;
@@ -88,9 +77,11 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { }
void __init acpi_init_cpus(void);
#else
-static inline bool acpi_psci_present(void) { return false; }
-static inline bool acpi_psci_use_hvc(void) { return false; }
static inline void acpi_init_cpus(void) { }
#endif /* CONFIG_ACPI */
+static inline const char *acpi_get_enable_method(int cpu)
+{
+ return acpi_psci_present() ? "psci" : NULL;
+}
#endif /*_ASM_ACPI_H*/
diff --git a/arch/arm64/include/asm/alternative-asm.h b/arch/arm64/include/asm/alternative-asm.h
deleted file mode 100644
index 919a67855b63..000000000000
--- a/arch/arm64/include/asm/alternative-asm.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __ASM_ALTERNATIVE_ASM_H
-#define __ASM_ALTERNATIVE_ASM_H
-
-#ifdef __ASSEMBLY__
-
-.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
- .word \orig_offset - .
- .word \alt_offset - .
- .hword \feature
- .byte \orig_len
- .byte \alt_len
-.endm
-
-.macro alternative_insn insn1 insn2 cap
-661: \insn1
-662: .pushsection .altinstructions, "a"
- altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
- .popsection
- .pushsection .altinstr_replacement, "ax"
-663: \insn2
-664: .popsection
- .if ((664b-663b) != (662b-661b))
- .error "Alternatives instruction length mismatch"
- .endif
-.endm
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_ALTERNATIVE_ASM_H */
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index d261f01e2bae..c385a0c4057f 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -1,6 +1,8 @@
#ifndef __ASM_ALTERNATIVE_H
#define __ASM_ALTERNATIVE_H
+#ifndef __ASSEMBLY__
+
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/stringify.h>
@@ -24,7 +26,20 @@ void free_alternatives_memory(void);
" .byte 662b-661b\n" /* source len */ \
" .byte 664f-663f\n" /* replacement len */
-/* alternative assembly primitive: */
+/*
+ * alternative assembly primitive:
+ *
+ * If any of these .org directive fail, it means that insn1 and insn2
+ * don't have the same length. This used to be written as
+ *
+ * .if ((664b-663b) != (662b-661b))
+ * .error "Alternatives instruction length mismatch"
+ * .endif
+ *
+ * but most assemblers die if insn1 or insn2 have a .inst. This should
+ * be fixed in a binutils release posterior to 2.25.51.0.2 (anything
+ * containing commit 4e4d08cf7399b606 or c1baaddf8861).
+ */
#define ALTERNATIVE(oldinstr, newinstr, feature) \
"661:\n\t" \
oldinstr "\n" \
@@ -37,8 +52,31 @@ void free_alternatives_memory(void);
newinstr "\n" \
"664:\n\t" \
".popsection\n\t" \
- ".if ((664b-663b) != (662b-661b))\n\t" \
- " .error \"Alternatives instruction length mismatch\"\n\t"\
- ".endif\n"
+ ".org . - (664b-663b) + (662b-661b)\n\t" \
+ ".org . - (662b-661b) + (664b-663b)\n"
+
+#else
+
+.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
+ .word \orig_offset - .
+ .word \alt_offset - .
+ .hword \feature
+ .byte \orig_len
+ .byte \alt_len
+.endm
+
+.macro alternative_insn insn1 insn2 cap
+661: \insn1
+662: .pushsection .altinstructions, "a"
+ altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
+ .popsection
+ .pushsection .altinstr_replacement, "ax"
+663: \insn2
+664: .popsection
+ .org . - (664b-663b) + (662b-661b)
+ .org . - (662b-661b) + (664b-663b)
+.endm
+
+#endif /* __ASSEMBLY__ */
#endif /* __ASM_ALTERNATIVE_H */
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 71f19c4dc0de..0fa47c4275cb 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -114,7 +114,7 @@ do { \
#define read_barrier_depends() do { } while(0)
#define smp_read_barrier_depends() do { } while(0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define nop() asm volatile("nop");
#define smp_mb__before_atomic() smp_mb()
diff --git a/arch/arm64/include/asm/boot.h b/arch/arm64/include/asm/boot.h
new file mode 100644
index 000000000000..81151b67b26b
--- /dev/null
+++ b/arch/arm64/include/asm/boot.h
@@ -0,0 +1,14 @@
+
+#ifndef __ASM_BOOT_H
+#define __ASM_BOOT_H
+
+#include <asm/sizes.h>
+
+/*
+ * arm64 requires the DTB to be 8 byte aligned and
+ * not exceed 2MB in size.
+ */
+#define MIN_FDT_ALIGN 8
+#define MAX_FDT_SIZE SZ_2M
+
+#endif
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 67d309cc3b6b..c75b8d027eb1 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -40,10 +40,6 @@
* the implementation assumes non-aliasing VIPT D-cache and (aliasing)
* VIPT or ASID-tagged VIVT I-cache.
*
- * flush_cache_all()
- *
- * Unconditionally clean and invalidate the entire cache.
- *
* flush_cache_mm(mm)
*
* Clean and invalidate all user space cache entries
@@ -69,7 +65,6 @@
* - kaddr - page address
* - size - region size
*/
-extern void flush_cache_all(void);
extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void flush_icache_range(unsigned long start, unsigned long end);
extern void __flush_dcache_area(void *addr, size_t len);
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index 5a31d6716914..8f03446cf89f 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -19,15 +19,15 @@
#include <linux/init.h>
#include <linux/threads.h>
-struct device_node;
-
/**
* struct cpu_operations - Callback operations for hotplugging CPUs.
*
* @name: Name of the property as appears in a devicetree cpu node's
- * enable-method property.
- * @cpu_init: Reads any data necessary for a specific enable-method from the
- * devicetree, for a given cpu node and proposed logical id.
+ * enable-method property. On systems booting with ACPI, @name
+ * identifies the struct cpu_operations entry corresponding to
+ * the boot protocol specified in the ACPI MADT table.
+ * @cpu_init: Reads any data necessary for a specific enable-method for a
+ * proposed logical id.
* @cpu_prepare: Early one-time preparation step for a cpu. If there is a
* mechanism for doing so, tests whether it is possible to boot
* the given CPU.
@@ -40,15 +40,15 @@ struct device_node;
* @cpu_die: Makes a cpu leave the kernel. Must not fail. Called from the
* cpu being killed.
* @cpu_kill: Ensures a cpu has left the kernel. Called from another cpu.
- * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
- * devicetree, for a given cpu node and proposed logical id.
+ * @cpu_init_idle: Reads any data necessary to initialize CPU idle states for
+ * a proposed logical id.
* @cpu_suspend: Suspends a cpu and saves the required context. May fail owing
* to wrong parameters or error conditions. Called from the
* CPU being suspended. Must be called with IRQs disabled.
*/
struct cpu_operations {
const char *name;
- int (*cpu_init)(struct device_node *, unsigned int);
+ int (*cpu_init)(unsigned int);
int (*cpu_prepare)(unsigned int);
int (*cpu_boot)(unsigned int);
void (*cpu_postboot)(void);
@@ -58,14 +58,17 @@ struct cpu_operations {
int (*cpu_kill)(unsigned int cpu);
#endif
#ifdef CONFIG_CPU_IDLE
- int (*cpu_init_idle)(struct device_node *, unsigned int);
+ int (*cpu_init_idle)(unsigned int);
int (*cpu_suspend)(unsigned long);
#endif
};
extern const struct cpu_operations *cpu_ops[NR_CPUS];
-int __init cpu_read_ops(struct device_node *dn, int cpu);
-void __init cpu_read_bootcpu_ops(void);
-const struct cpu_operations *cpu_get_ops(const char *name);
+int __init cpu_read_ops(int cpu);
+
+static inline void __init cpu_read_bootcpu_ops(void)
+{
+ cpu_read_ops(0);
+}
#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 82cb9f98ba1a..c1044218a63a 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -24,8 +24,9 @@
#define ARM64_WORKAROUND_CLEAN_CACHE 0
#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1
#define ARM64_WORKAROUND_845719 2
+#define ARM64_HAS_SYSREG_GIC_CPUIF 3
-#define ARM64_NCAPS 3
+#define ARM64_NCAPS 4
#ifndef __ASSEMBLY__
@@ -38,6 +39,11 @@ struct arm64_cpu_capabilities {
u32 midr_model;
u32 midr_range_min, midr_range_max;
};
+
+ struct { /* Feature register checking */
+ u64 register_mask;
+ u64 register_value;
+ };
};
};
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
index 141b2fcabaa6..0f74f05d662a 100644
--- a/arch/arm64/include/asm/cpuidle.h
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -5,20 +5,16 @@
#ifdef CONFIG_CPU_IDLE
extern int arm_cpuidle_init(unsigned int cpu);
-extern int cpu_suspend(unsigned long arg);
+extern int arm_cpuidle_suspend(int index);
#else
static inline int arm_cpuidle_init(unsigned int cpu)
{
return -EOPNOTSUPP;
}
-static inline int cpu_suspend(unsigned long arg)
+static inline int arm_cpuidle_suspend(int index)
{
return -EOPNOTSUPP;
}
#endif
-static inline int arm_cpuidle_suspend(int index)
-{
- return cpu_suspend(index);
-}
#endif
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 9437e3dc5833..f0d6d0bfe55c 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -18,6 +18,7 @@
#ifdef __KERNEL__
+#include <linux/acpi.h>
#include <linux/types.h>
#include <linux/vmalloc.h>
@@ -28,13 +29,23 @@
#define DMA_ERROR_CODE (~(dma_addr_t)0)
extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops dummy_dma_ops;
static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
{
- if (unlikely(!dev) || !dev->archdata.dma_ops)
+ if (unlikely(!dev))
return dma_ops;
- else
+ else if (dev->archdata.dma_ops)
return dev->archdata.dma_ops;
+ else if (acpi_disabled)
+ return dma_ops;
+
+ /*
+ * When ACPI is enabled, if arch_set_dma_ops is not called,
+ * we will disable device DMA capability by setting it
+ * to dummy_dma_ops.
+ */
+ return &dummy_dma_ops;
}
static inline struct dma_map_ops *get_dma_ops(struct device *dev)
@@ -48,6 +59,9 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
struct iommu_ops *iommu, bool coherent)
{
+ if (!acpi_disabled && !dev->archdata.dma_ops)
+ dev->archdata.dma_ops = dma_ops;
+
dev->archdata.dma_coherent = coherent;
}
#define arch_setup_dma_ops arch_setup_dma_ops
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 95e6b6dcbe37..c0739187a920 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -17,6 +17,7 @@
#ifndef __ASSEMBLY__
#include <linux/kernel.h>
+#include <asm/boot.h>
#include <asm/page.h>
/*
@@ -32,6 +33,20 @@
*/
enum fixed_addresses {
FIX_HOLE,
+
+ /*
+ * Reserve a virtual window for the FDT that is 2 MB larger than the
+ * maximum supported size, and put it at the top of the fixmap region.
+ * The additional space ensures that any FDT that does not exceed
+ * MAX_FDT_SIZE can be mapped regardless of whether it crosses any
+ * 2 MB alignment boundaries.
+ *
+ * Keep this at the top so it remains 2 MB aligned.
+ */
+#define FIX_FDT_SIZE (MAX_FDT_SIZE + SZ_2M)
+ FIX_FDT_END,
+ FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
+
FIX_EARLYCON_MEM_BASE,
FIX_TEXT_POKE0,
__end_of_permanent_fixed_addresses,
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 5f750dc96e0f..74069b3bd919 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -58,7 +58,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
+ pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
@@ -85,7 +85,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable(); /* subsumes preempt_enable() */
+ pagefault_enable();
if (!ret) {
switch (cmp) {
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index f81b328d9cf4..30e50eb54a67 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -281,6 +281,7 @@ __AARCH64_INSN_FUNCS(ret, 0xFFFFFC1F, 0xD65F0000)
#undef __AARCH64_INSN_FUNCS
bool aarch64_insn_is_nop(u32 insn);
+bool aarch64_insn_is_branch_imm(u32 insn);
int aarch64_insn_read(void *addr, u32 *insnp);
int aarch64_insn_write(void *addr, u32 insn);
@@ -351,6 +352,8 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
int shift,
enum aarch64_insn_variant variant,
enum aarch64_insn_logic_type type);
+s32 aarch64_get_branch_offset(u32 insn);
+u32 aarch64_set_branch_offset(u32 insn, s32 offset);
bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 540f7c0aea82..44be1e03ed65 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -117,10 +117,10 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
* ordering rules but do not guarantee any ordering relative to Normal memory
* accesses.
*/
-#define readb_relaxed(c) ({ u8 __v = __raw_readb(c); __v; })
-#define readw_relaxed(c) ({ u16 __v = le16_to_cpu((__force __le16)__raw_readw(c)); __v; })
-#define readl_relaxed(c) ({ u32 __v = le32_to_cpu((__force __le32)__raw_readl(c)); __v; })
-#define readq_relaxed(c) ({ u64 __v = le64_to_cpu((__force __le64)__raw_readq(c)); __v; })
+#define readb_relaxed(c) ({ u8 __r = __raw_readb(c); __r; })
+#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 readq_relaxed(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; })
#define writeb_relaxed(v,c) ((void)__raw_writeb((v),(c)))
#define writew_relaxed(v,c) ((void)__raw_writew((__force u16)cpu_to_le16(v),(c)))
@@ -170,6 +170,7 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
#define ioremap(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define ioremap_nocache(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
+#define ioremap_wt(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define iounmap __iounmap
/*
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 4f7310fa77f0..3c5fe685a2d6 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -27,7 +27,7 @@
#define MPIDR_EL1 1 /* MultiProcessor Affinity Register */
#define CSSELR_EL1 2 /* Cache Size Selection Register */
#define SCTLR_EL1 3 /* System Control Register */
-#define ACTLR_EL1 4 /* Auxilliary Control Register */
+#define ACTLR_EL1 4 /* Auxiliary Control Register */
#define CPACR_EL1 5 /* Coprocessor Access Control */
#define TTBR0_EL1 6 /* Translation Table Base Register 0 */
#define TTBR1_EL1 7 /* Translation Table Base Register 1 */
@@ -132,11 +132,6 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
extern u64 __vgic_v3_get_ich_vtr_el2(void);
-extern char __save_vgic_v2_state[];
-extern char __restore_vgic_v2_state[];
-extern char __save_vgic_v3_state[];
-extern char __restore_vgic_v3_state[];
-
#endif
#endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f0f58c9beec0..2709db2a7eac 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -221,29 +221,6 @@ struct vgic_sr_vectors {
void *restore_vgic;
};
-static inline void vgic_arch_setup(const struct vgic_params *vgic)
-{
- extern struct vgic_sr_vectors __vgic_sr_vectors;
-
- switch(vgic->type)
- {
- case VGIC_V2:
- __vgic_sr_vectors.save_vgic = __save_vgic_v2_state;
- __vgic_sr_vectors.restore_vgic = __restore_vgic_v2_state;
- break;
-
-#ifdef CONFIG_ARM_GIC_V3
- case VGIC_V3:
- __vgic_sr_vectors.save_vgic = __save_vgic_v3_state;
- __vgic_sr_vectors.restore_vgic = __restore_vgic_v3_state;
- break;
-#endif
-
- default:
- BUG();
- }
-}
-
static inline void kvm_arch_hardware_disable(void) {}
static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 3d311761e3c2..79fcfb048884 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -34,5 +34,6 @@ extern void init_mem_pgprot(void);
extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot);
+extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
#endif
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index d26d1d53c0d7..6471773db6fd 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -24,4 +24,11 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
#endif
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+ (regs)->pc = (__ip); \
+ (regs)->regs[29] = (unsigned long) __builtin_frame_address(0); \
+ (regs)->sp = current_stack_pointer; \
+ (regs)->pstate = PSR_MODE_EL1h; \
+}
+
#endif
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 220633b791b8..14ad6e4e87d1 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -28,12 +28,8 @@
struct mm_struct;
struct cpu_suspend_ctx;
-extern void cpu_cache_off(void);
extern void cpu_do_idle(void);
extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
-extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
-void cpu_soft_restart(phys_addr_t cpu_reset,
- unsigned long addr) __attribute__((noreturn));
extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index d2c37a1df0eb..e4c893e54f01 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -78,13 +78,30 @@ struct cpu_context {
struct thread_struct {
struct cpu_context cpu_context; /* cpu context */
- unsigned long tp_value;
+ unsigned long tp_value; /* TLS register */
+#ifdef CONFIG_COMPAT
+ unsigned long tp2_value;
+#endif
struct fpsimd_state fpsimd_state;
unsigned long fault_address; /* fault info */
unsigned long fault_code; /* ESR_EL1 value */
struct debug_info debug; /* debugging */
};
+#ifdef CONFIG_COMPAT
+#define task_user_tls(t) \
+({ \
+ unsigned long *__tls; \
+ if (is_compat_thread(task_thread_info(t))) \
+ __tls = &(t)->thread.tp2_value; \
+ else \
+ __tls = &(t)->thread.tp_value; \
+ __tls; \
+ })
+#else
+#define task_user_tls(t) (&(t)->thread.tp_value)
+#endif
+
#define INIT_THREAD { }
static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h
index 2454bc59c916..49d7e1aaebdc 100644
--- a/arch/arm64/include/asm/psci.h
+++ b/arch/arm64/include/asm/psci.h
@@ -14,7 +14,15 @@
#ifndef __ASM_PSCI_H
#define __ASM_PSCI_H
-int psci_dt_init(void);
-int psci_acpi_init(void);
+int __init psci_dt_init(void);
+
+#ifdef CONFIG_ACPI
+int __init psci_acpi_init(void);
+bool __init acpi_psci_present(void);
+bool __init acpi_psci_use_hvc(void);
+#else
+static inline int psci_acpi_init(void) { return 0; }
+static inline bool acpi_psci_present(void) { return false; }
+#endif
#endif /* __ASM_PSCI_H */
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index bf22650b1a78..db02be81b90a 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -42,7 +42,7 @@ extern void handle_IPI(int ipinr, struct pt_regs *regs);
* Discover the set of possible CPUs and determine their
* SMP operations.
*/
-extern void of_smp_init_cpus(void);
+extern void smp_init_cpus(void);
/*
* Provide a function to raise an IPI cross call on CPUs in callmap.
diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h
index 8dcd61e32176..7abf7570c00f 100644
--- a/arch/arm64/include/asm/smp_plat.h
+++ b/arch/arm64/include/asm/smp_plat.h
@@ -19,6 +19,8 @@
#ifndef __ASM_SMP_PLAT_H
#define __ASM_SMP_PLAT_H
+#include <linux/cpumask.h>
+
#include <asm/types.h>
struct mpidr_hash {
@@ -39,6 +41,20 @@ static inline u32 mpidr_hash_size(void)
*/
extern u64 __cpu_logical_map[NR_CPUS];
#define cpu_logical_map(cpu) __cpu_logical_map[cpu]
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR.Aff*
+ * - mpidr: MPIDR.Aff* bits to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u64 mpidr)
+{
+ int cpu;
+ for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+ if (cpu_logical_map(cpu) == mpidr)
+ return cpu;
+ return -EINVAL;
+}
void __init do_post_cpus_up_work(void);
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index 003802f58963..59a5b0f1e81c 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -21,6 +21,6 @@ struct sleep_save_sp {
phys_addr_t save_ptr_stash_phys;
};
-extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
+extern int cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
extern void cpu_resume(void);
#endif
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 7a18fabbe0f6..57f110bea6a8 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -23,6 +23,8 @@
#include <linux/compiler.h>
#include <linux/linkage.h>
#include <linux/irqflags.h>
+#include <linux/signal.h>
+#include <linux/ratelimit.h>
#include <linux/reboot.h>
struct pt_regs;
@@ -41,9 +43,19 @@ struct mm_struct;
extern void show_pte(struct mm_struct *mm, unsigned long addr);
extern void __show_regs(struct pt_regs *);
-void soft_restart(unsigned long);
extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
+#define show_unhandled_signals_ratelimited() \
+({ \
+ static DEFINE_RATELIMIT_STATE(_rs, \
+ DEFAULT_RATELIMIT_INTERVAL, \
+ DEFAULT_RATELIMIT_BURST); \
+ bool __show_ratelimited = false; \
+ if (show_unhandled_signals && __ratelimit(&_rs)) \
+ __show_ratelimited = true; \
+ __show_ratelimited; \
+})
+
#define UDBG_UNDEFINED (1 << 0)
#define UDBG_SYSCALL (1 << 1)
#define UDBG_BADABORT (1 << 2)
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index c3bb05b98616..934815d45eda 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -28,8 +28,6 @@
* TLB Management
* ==============
*
- * The arch/arm64/mm/tlb.S files implement these methods.
- *
* The TLB specific code is expected to perform whatever tests it needs
* to determine if it should invalidate the TLB for each call. Start
* addresses are inclusive and end addresses are exclusive; it is safe to
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 7ebcd31ce51c..225ec3524fbf 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -18,7 +18,7 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
#define topology_physical_package_id(cpu) (cpu_topology[cpu].cluster_id)
#define topology_core_id(cpu) (cpu_topology[cpu].core_id)
#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 8b839558838e..19de7537e7d3 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -36,12 +36,6 @@ EXPORT_SYMBOL(acpi_disabled);
int acpi_pci_disabled = 1; /* skip ACPI PCI scan and IRQ initialization */
EXPORT_SYMBOL(acpi_pci_disabled);
-/* Processors with enabled flag and sane MPIDR */
-static int enabled_cpus;
-
-/* Boot CPU is valid or not in MADT */
-static bool bootcpu_valid __initdata;
-
static bool param_acpi_off __initdata;
static bool param_acpi_force __initdata;
@@ -95,122 +89,15 @@ void __init __acpi_unmap_table(char *map, unsigned long size)
early_memunmap(map, size);
}
-/**
- * acpi_map_gic_cpu_interface - generates a logical cpu number
- * and map to MPIDR represented by GICC structure
- */
-static void __init
-acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
+bool __init acpi_psci_present(void)
{
- int i;
- u64 mpidr = processor->arm_mpidr & MPIDR_HWID_BITMASK;
- bool enabled = !!(processor->flags & ACPI_MADT_ENABLED);
-
- if (mpidr == INVALID_HWID) {
- pr_info("Skip MADT cpu entry with invalid MPIDR\n");
- return;
- }
-
- total_cpus++;
- if (!enabled)
- return;
-
- if (enabled_cpus >= NR_CPUS) {
- pr_warn("NR_CPUS limit of %d reached, Processor %d/0x%llx ignored.\n",
- NR_CPUS, total_cpus, mpidr);
- return;
- }
-
- /* Check if GICC structure of boot CPU is available in the MADT */
- if (cpu_logical_map(0) == mpidr) {
- if (bootcpu_valid) {
- pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n",
- mpidr);
- return;
- }
-
- bootcpu_valid = true;
- }
-
- /*
- * Duplicate MPIDRs are a recipe for disaster. Scan
- * all initialized entries and check for
- * duplicates. If any is found just ignore the CPU.
- */
- for (i = 1; i < enabled_cpus; i++) {
- if (cpu_logical_map(i) == mpidr) {
- pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n",
- mpidr);
- return;
- }
- }
-
- if (!acpi_psci_present())
- return;
-
- cpu_ops[enabled_cpus] = cpu_get_ops("psci");
- /* CPU 0 was already initialized */
- if (enabled_cpus) {
- if (!cpu_ops[enabled_cpus])
- return;
-
- if (cpu_ops[enabled_cpus]->cpu_init(NULL, enabled_cpus))
- return;
-
- /* map the logical cpu id to cpu MPIDR */
- cpu_logical_map(enabled_cpus) = mpidr;
- }
-
- enabled_cpus++;
+ return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT;
}
-static int __init
-acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
- const unsigned long end)
+/* Whether HVC must be used instead of SMC as the PSCI conduit */
+bool __init acpi_psci_use_hvc(void)
{
- struct acpi_madt_generic_interrupt *processor;
-
- processor = (struct acpi_madt_generic_interrupt *)header;
-
- if (BAD_MADT_ENTRY(processor, end))
- return -EINVAL;
-
- acpi_table_print_madt_entry(header);
- acpi_map_gic_cpu_interface(processor);
- return 0;
-}
-
-/* Parse GIC cpu interface entries in MADT for SMP init */
-void __init acpi_init_cpus(void)
-{
- int count, i;
-
- /*
- * do a partial walk of MADT to determine how many CPUs
- * we have including disabled CPUs, and get information
- * we need for SMP init
- */
- count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
- acpi_parse_gic_cpu_interface, 0);
-
- if (!count) {
- pr_err("No GIC CPU interface entries present\n");
- return;
- } else if (count < 0) {
- pr_err("Error parsing GIC CPU interface entry\n");
- return;
- }
-
- if (!bootcpu_valid) {
- pr_err("MADT missing boot CPU MPIDR, not enabling secondaries\n");
- return;
- }
-
- for (i = 0; i < enabled_cpus; i++)
- set_cpu_possible(i, true);
-
- /* Make boot-up look pretty */
- pr_info("%d CPUs enabled, %d CPUs total\n", enabled_cpus, total_cpus);
+ return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
}
/*
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 28f8365edc4c..221b98312f0c 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -24,8 +24,13 @@
#include <asm/cacheflush.h>
#include <asm/alternative.h>
#include <asm/cpufeature.h>
+#include <asm/insn.h>
#include <linux/stop_machine.h>
+#define __ALT_PTR(a,f) (u32 *)((void *)&(a)->f + (a)->f)
+#define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset)
+#define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset)
+
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
struct alt_region {
@@ -33,13 +38,63 @@ struct alt_region {
struct alt_instr *end;
};
+/*
+ * Check if the target PC is within an alternative block.
+ */
+static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
+{
+ unsigned long replptr;
+
+ if (kernel_text_address(pc))
+ return 1;
+
+ replptr = (unsigned long)ALT_REPL_PTR(alt);
+ if (pc >= replptr && pc <= (replptr + alt->alt_len))
+ return 0;
+
+ /*
+ * Branching into *another* alternate sequence is doomed, and
+ * we're not even trying to fix it up.
+ */
+ BUG();
+}
+
+static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
+{
+ u32 insn;
+
+ insn = le32_to_cpu(*altinsnptr);
+
+ if (aarch64_insn_is_branch_imm(insn)) {
+ s32 offset = aarch64_get_branch_offset(insn);
+ unsigned long target;
+
+ target = (unsigned long)altinsnptr + offset;
+
+ /*
+ * If we're branching inside the alternate sequence,
+ * do not rewrite the instruction, as it is already
+ * correct. Otherwise, generate the new instruction.
+ */
+ if (branch_insn_requires_update(alt, target)) {
+ offset = target - (unsigned long)insnptr;
+ insn = aarch64_set_branch_offset(insn, offset);
+ }
+ }
+
+ return insn;
+}
+
static int __apply_alternatives(void *alt_region)
{
struct alt_instr *alt;
struct alt_region *region = alt_region;
- u8 *origptr, *replptr;
+ u32 *origptr, *replptr;
for (alt = region->begin; alt < region->end; alt++) {
+ u32 insn;
+ int i, nr_inst;
+
if (!cpus_have_cap(alt->cpufeature))
continue;
@@ -47,11 +102,17 @@ static int __apply_alternatives(void *alt_region)
pr_info_once("patching kernel code\n");
- origptr = (u8 *)&alt->orig_offset + alt->orig_offset;
- replptr = (u8 *)&alt->alt_offset + alt->alt_offset;
- memcpy(origptr, replptr, alt->alt_len);
+ origptr = ALT_ORIG_PTR(alt);
+ replptr = ALT_REPL_PTR(alt);
+ nr_inst = alt->alt_len / sizeof(insn);
+
+ for (i = 0; i < nr_inst; i++) {
+ insn = get_alt_insn(alt, origptr + i, replptr + i);
+ *(origptr + i) = cpu_to_le32(insn);
+ }
+
flush_icache_range((uintptr_t)origptr,
- (uintptr_t)(origptr + alt->alt_len));
+ (uintptr_t)(origptr + nr_inst));
}
return 0;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index da675cc5dfae..c99701a34d7b 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -127,7 +127,6 @@ int main(void)
DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu));
DEFINE(VGIC_SAVE_FN, offsetof(struct vgic_sr_vectors, save_vgic));
DEFINE(VGIC_RESTORE_FN, offsetof(struct vgic_sr_vectors, restore_vgic));
- DEFINE(VGIC_SR_VECTOR_SZ, sizeof(struct vgic_sr_vectors));
DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
DEFINE(VGIC_V2_CPU_MISR, offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index fb8ff9ba467a..5ea337dd2f15 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -16,11 +16,13 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
-#include <asm/cpu_ops.h>
-#include <asm/smp_plat.h>
+#include <linux/acpi.h>
#include <linux/errno.h>
#include <linux/of.h>
#include <linux/string.h>
+#include <asm/acpi.h>
+#include <asm/cpu_ops.h>
+#include <asm/smp_plat.h>
extern const struct cpu_operations smp_spin_table_ops;
extern const struct cpu_operations cpu_psci_ops;
@@ -35,7 +37,7 @@ static const struct cpu_operations *supported_cpu_ops[] __initconst = {
NULL,
};
-const struct cpu_operations * __init cpu_get_ops(const char *name)
+static const struct cpu_operations * __init cpu_get_ops(const char *name)
{
const struct cpu_operations **ops = supported_cpu_ops;
@@ -49,39 +51,53 @@ const struct cpu_operations * __init cpu_get_ops(const char *name)
return NULL;
}
+static const char *__init cpu_read_enable_method(int cpu)
+{
+ const char *enable_method;
+
+ if (acpi_disabled) {
+ struct device_node *dn = of_get_cpu_node(cpu, NULL);
+
+ if (!dn) {
+ if (!cpu)
+ pr_err("Failed to find device node for boot cpu\n");
+ return NULL;
+ }
+
+ enable_method = of_get_property(dn, "enable-method", NULL);
+ if (!enable_method) {
+ /*
+ * The boot CPU may not have an enable method (e.g.
+ * when spin-table is used for secondaries).
+ * Don't warn spuriously.
+ */
+ if (cpu != 0)
+ pr_err("%s: missing enable-method property\n",
+ dn->full_name);
+ }
+ } else {
+ enable_method = acpi_get_enable_method(cpu);
+ if (!enable_method)
+ pr_err("Unsupported ACPI enable-method\n");
+ }
+
+ return enable_method;
+}
/*
- * Read a cpu's enable method from the device tree and record it in cpu_ops.
+ * Read a cpu's enable method and record it in cpu_ops.
*/
-int __init cpu_read_ops(struct device_node *dn, int cpu)
+int __init cpu_read_ops(int cpu)
{
- const char *enable_method = of_get_property(dn, "enable-method", NULL);
- if (!enable_method) {
- /*
- * The boot CPU may not have an enable method (e.g. when
- * spin-table is used for secondaries). Don't warn spuriously.
- */
- if (cpu != 0)
- pr_err("%s: missing enable-method property\n",
- dn->full_name);
- return -ENOENT;
- }
+ const char *enable_method = cpu_read_enable_method(cpu);
+
+ if (!enable_method)
+ return -ENODEV;
cpu_ops[cpu] = cpu_get_ops(enable_method);
if (!cpu_ops[cpu]) {
- pr_warn("%s: unsupported enable-method property: %s\n",
- dn->full_name, enable_method);
+ pr_warn("Unsupported enable-method: %s\n", enable_method);
return -EOPNOTSUPP;
}
return 0;
}
-
-void __init cpu_read_bootcpu_ops(void)
-{
- struct device_node *dn = of_get_cpu_node(0, NULL);
- if (!dn) {
- pr_err("Failed to find device node for boot cpu\n");
- return;
- }
- cpu_read_ops(dn, 0);
-}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 3d9967e43d89..5ad86ceac010 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -22,7 +22,23 @@
#include <asm/cpu.h>
#include <asm/cpufeature.h>
+static bool
+has_id_aa64pfr0_feature(const struct arm64_cpu_capabilities *entry)
+{
+ u64 val;
+
+ val = read_cpuid(id_aa64pfr0_el1);
+ return (val & entry->register_mask) == entry->register_value;
+}
+
static const struct arm64_cpu_capabilities arm64_features[] = {
+ {
+ .desc = "GIC system register CPU interface",
+ .capability = ARM64_HAS_SYSREG_GIC_CPUIF,
+ .matches = has_id_aa64pfr0_feature,
+ .register_mask = (0xf << 24),
+ .register_value = (1 << 24),
+ },
{},
};
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index a78143a5c99f..7ce589ca54a4 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -18,15 +18,10 @@
int arm_cpuidle_init(unsigned int cpu)
{
int ret = -EOPNOTSUPP;
- struct device_node *cpu_node = of_cpu_device_node_get(cpu);
-
- if (!cpu_node)
- return -ENODEV;
if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle)
- ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu);
+ ret = cpu_ops[cpu]->cpu_init_idle(cpu);
- of_node_put(cpu_node);
return ret;
}
@@ -37,7 +32,7 @@ int arm_cpuidle_init(unsigned int cpu)
* Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
* operations back-end error code otherwise.
*/
-int cpu_suspend(unsigned long arg)
+int arm_cpuidle_suspend(int index)
{
int cpu = smp_processor_id();
@@ -47,5 +42,5 @@ int cpu_suspend(unsigned long arg)
*/
if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
return -EOPNOTSUPP;
- return cpu_ops[cpu]->cpu_suspend(arg);
+ return cpu_ops[cpu]->cpu_suspend(index);
}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 959fe8733560..a7691a378668 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -21,7 +21,7 @@
#include <linux/init.h>
#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
#include <asm/cpufeature.h>
@@ -124,21 +124,24 @@
msr sp_el0, x23
#ifdef CONFIG_ARM64_ERRATUM_845719
- alternative_insn \
- "nop", \
- "tbz x22, #4, 1f", \
- ARM64_WORKAROUND_845719
+
+#undef SEQUENCE_ORG
+#undef SEQUENCE_ALT
+
#ifdef CONFIG_PID_IN_CONTEXTIDR
- alternative_insn \
- "nop; nop", \
- "mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:", \
- ARM64_WORKAROUND_845719
+
+#define SEQUENCE_ORG "nop ; nop ; nop"
+#define SEQUENCE_ALT "tbz x22, #4, 1f ; mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:"
+
#else
- alternative_insn \
- "nop", \
- "msr contextidr_el1, xzr; 1:", \
- ARM64_WORKAROUND_845719
+
+#define SEQUENCE_ORG "nop ; nop"
+#define SEQUENCE_ALT "tbz x22, #4, 1f ; msr contextidr_el1, xzr; 1:"
+
#endif
+
+ alternative_insn SEQUENCE_ORG, SEQUENCE_ALT, ARM64_WORKAROUND_845719
+
#endif
.endif
msr elr_el1, x21 // set up the return data
@@ -517,6 +520,7 @@ el0_sp_pc:
mrs x26, far_el1
// enable interrupts before calling the main handler
enable_dbg_and_irq
+ ct_user_exit
mov x0, x26
mov x1, x25
mov x2, sp
@@ -608,11 +612,16 @@ ENDPROC(cpu_switch_to)
*/
ret_fast_syscall:
disable_irq // disable interrupts
- ldr x1, [tsk, #TI_FLAGS]
+ ldr x1, [tsk, #TI_FLAGS] // re-check for syscall tracing
+ and x2, x1, #_TIF_SYSCALL_WORK
+ cbnz x2, ret_fast_syscall_trace
and x2, x1, #_TIF_WORK_MASK
cbnz x2, fast_work_pending
enable_step_tsk x1, x2
kernel_exit 0, ret = 1
+ret_fast_syscall_trace:
+ enable_irq // enable interrupts
+ b __sys_trace_return
/*
* Ok, we need to do extra processing, enter the slow path.
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 3dca15634e69..44d6f7545505 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/cpu.h>
#include <linux/cpu_pm.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -296,6 +297,35 @@ static void fpsimd_pm_init(void)
static inline void fpsimd_pm_init(void) { }
#endif /* CONFIG_CPU_PM */
+#ifdef CONFIG_HOTPLUG_CPU
+static int fpsimd_cpu_hotplug_notifier(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
+{
+ unsigned int cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ per_cpu(fpsimd_last_state, cpu) = NULL;
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block fpsimd_cpu_hotplug_notifier_block = {
+ .notifier_call = fpsimd_cpu_hotplug_notifier,
+};
+
+static inline void fpsimd_hotplug_init(void)
+{
+ register_cpu_notifier(&fpsimd_cpu_hotplug_notifier_block);
+}
+
+#else
+static inline void fpsimd_hotplug_init(void) { }
+#endif
+
/*
* FP/SIMD support code initialisation.
*/
@@ -315,6 +345,7 @@ static int __init fpsimd_init(void)
elf_hwcap |= HWCAP_ASIMD;
fpsimd_pm_init();
+ fpsimd_hotplug_init();
return 0;
}
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 19f915e8f6e0..c0ff3ce4299e 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -237,8 +237,6 @@ ENTRY(stext)
bl el2_setup // Drop to EL1, w20=cpu_boot_mode
adrp x24, __PHYS_OFFSET
bl set_cpu_boot_mode_flag
-
- bl __vet_fdt
bl __create_page_tables // x25=TTBR0, x26=TTBR1
/*
* The following calls CPU setup code, see arch/arm64/mm/proc.S for
@@ -270,24 +268,6 @@ preserve_boot_args:
ENDPROC(preserve_boot_args)
/*
- * Determine validity of the x21 FDT pointer.
- * The dtb must be 8-byte aligned and live in the first 512M of memory.
- */
-__vet_fdt:
- tst x21, #0x7
- b.ne 1f
- cmp x21, x24
- b.lt 1f
- mov x0, #(1 << 29)
- add x0, x0, x24
- cmp x21, x0
- b.ge 1f
- ret
-1:
- mov x21, #0
- ret
-ENDPROC(__vet_fdt)
-/*
* Macro to create a table entry to the next page.
*
* tbl: page table address
@@ -348,8 +328,7 @@ ENDPROC(__vet_fdt)
* required to get the kernel running. The following sections are required:
* - identity mapping to enable the MMU (low address, TTBR0)
* - first few MB of the kernel linear mapping to jump to once the MMU has
- * been enabled, including the FDT blob (TTBR1)
- * - pgd entry for fixed mappings (TTBR1)
+ * been enabled
*/
__create_page_tables:
adrp x25, idmap_pg_dir
@@ -382,7 +361,7 @@ __create_page_tables:
* Create the identity mapping.
*/
mov x0, x25 // idmap_pg_dir
- adrp x3, KERNEL_START // __pa(KERNEL_START)
+ adrp x3, __idmap_text_start // __pa(__idmap_text_start)
#ifndef CONFIG_ARM64_VA_BITS_48
#define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3)
@@ -405,11 +384,11 @@ __create_page_tables:
/*
* Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
- * entire kernel image can be ID mapped. As T0SZ == (64 - #bits used),
+ * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
* this number conveniently equals the number of leading zeroes in
- * the physical address of KERNEL_END.
+ * the physical address of __idmap_text_end.
*/
- adrp x5, KERNEL_END
+ adrp x5, __idmap_text_end
clz x5, x5
cmp x5, TCR_T0SZ(VA_BITS) // default T0SZ small enough?
b.ge 1f // .. then skip additional level
@@ -424,8 +403,8 @@ __create_page_tables:
#endif
create_pgd_entry x0, x3, x5, x6
- mov x5, x3 // __pa(KERNEL_START)
- adr_l x6, KERNEL_END // __pa(KERNEL_END)
+ mov x5, x3 // __pa(__idmap_text_start)
+ adr_l x6, __idmap_text_end // __pa(__idmap_text_end)
create_block_map x0, x7, x3, x5, x6
/*
@@ -439,22 +418,6 @@ __create_page_tables:
create_block_map x0, x7, x3, x5, x6
/*
- * Map the FDT blob (maximum 2MB; must be within 512MB of
- * PHYS_OFFSET).
- */
- mov x3, x21 // FDT phys address
- and x3, x3, #~((1 << 21) - 1) // 2MB aligned
- mov x6, #PAGE_OFFSET
- sub x5, x3, x24 // subtract PHYS_OFFSET
- tst x5, #~((1 << 29) - 1) // within 512MB?
- csel x21, xzr, x21, ne // zero the FDT pointer
- b.ne 1f
- add x5, x5, x6 // __va(FDT blob)
- add x6, x5, #1 << 21 // 2MB for the FDT blob
- sub x6, x6, #1 // inclusive range
- create_block_map x0, x7, x3, x5, x6
-1:
- /*
* Since the page tables have been populated with non-cacheable
* accesses (MMU disabled), invalidate the idmap and swapper page
* tables again to remove any speculatively loaded cache lines.
@@ -669,6 +632,7 @@ ENDPROC(__secondary_switched)
*
* other registers depend on the function called upon completion
*/
+ .section ".idmap.text", "ax"
__enable_mmu:
ldr x5, =vectors
msr vbar_el1, x5
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 924902083e47..dd9671cd0bb2 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -77,6 +77,14 @@ bool __kprobes aarch64_insn_is_nop(u32 insn)
}
}
+bool aarch64_insn_is_branch_imm(u32 insn)
+{
+ return (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn) ||
+ aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn) ||
+ aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+ aarch64_insn_is_bcond(insn));
+}
+
static DEFINE_SPINLOCK(patch_lock);
static void __kprobes *patch_map(void *addr, int fixmap)
@@ -1057,6 +1065,58 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
}
+/*
+ * Decode the imm field of a branch, and return the byte offset as a
+ * signed value (so it can be used when computing a new branch
+ * target).
+ */
+s32 aarch64_get_branch_offset(u32 insn)
+{
+ s32 imm;
+
+ if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) {
+ imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn);
+ return (imm << 6) >> 4;
+ }
+
+ if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+ aarch64_insn_is_bcond(insn)) {
+ imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_19, insn);
+ return (imm << 13) >> 11;
+ }
+
+ if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn)) {
+ imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_14, insn);
+ return (imm << 18) >> 16;
+ }
+
+ /* Unhandled instruction */
+ BUG();
+}
+
+/*
+ * Encode the displacement of a branch in the imm field and return the
+ * updated instruction.
+ */
+u32 aarch64_set_branch_offset(u32 insn, s32 offset)
+{
+ if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn))
+ return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn,
+ offset >> 2);
+
+ if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+ aarch64_insn_is_bcond(insn))
+ return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+ offset >> 2);
+
+ if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn))
+ return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_14, insn,
+ offset >> 2);
+
+ /* Unhandled instruction */
+ BUG();
+}
+
bool aarch32_insn_is_wide(u32 insn)
{
return insn >= 0xe800;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index cce18c85d2e8..702591f6180a 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -488,7 +488,7 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
}
err = request_irq(irq, armpmu->handle_irq,
- IRQF_NOBALANCING,
+ IRQF_NOBALANCING | IRQF_NO_THREAD,
"arm-pmu", armpmu);
if (err) {
pr_err("unable to request IRQ%d for ARM PMU counters\n",
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index c6b1f3b96f45..223b093c9440 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -58,14 +58,6 @@ unsigned long __stack_chk_guard __read_mostly;
EXPORT_SYMBOL(__stack_chk_guard);
#endif
-void soft_restart(unsigned long addr)
-{
- setup_mm_for_reboot();
- cpu_soft_restart(virt_to_phys(cpu_reset), addr);
- /* Should never get here */
- BUG();
-}
-
/*
* Function pointers to optional machine specific functions
*/
@@ -136,9 +128,7 @@ void machine_power_off(void)
/*
* Restart requires that the secondary CPUs stop performing any activity
- * while the primary CPU resets the system. Systems with a single CPU can
- * use soft_restart() as their machine descriptor's .restart hook, since that
- * will cause the only available CPU to reset. Systems with multiple CPUs must
+ * while the primary CPU resets the system. Systems with multiple CPUs must
* provide a HW restart implementation, to ensure that all CPUs reset at once.
* This is required so that any code running after reset on the primary CPU
* doesn't have to co-ordinate with other CPUs to ensure they aren't still
@@ -243,7 +233,8 @@ void release_thread(struct task_struct *dead_task)
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
- fpsimd_preserve_current_state();
+ if (current->mm)
+ fpsimd_preserve_current_state();
*dst = *src;
return 0;
}
@@ -254,35 +245,35 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
unsigned long stk_sz, struct task_struct *p)
{
struct pt_regs *childregs = task_pt_regs(p);
- unsigned long tls = p->thread.tp_value;
memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
if (likely(!(p->flags & PF_KTHREAD))) {
*childregs = *current_pt_regs();
childregs->regs[0] = 0;
- if (is_compat_thread(task_thread_info(p))) {
- if (stack_start)
+
+ /*
+ * Read the current TLS pointer from tpidr_el0 as it may be
+ * out-of-sync with the saved value.
+ */
+ asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p)));
+
+ if (stack_start) {
+ if (is_compat_thread(task_thread_info(p)))
childregs->compat_sp = stack_start;
- } else {
- /*
- * Read the current TLS pointer from tpidr_el0 as it may be
- * out-of-sync with the saved value.
- */
- asm("mrs %0, tpidr_el0" : "=r" (tls));
- if (stack_start) {
- /* 16-byte aligned stack mandatory on AArch64 */
- if (stack_start & 15)
- return -EINVAL;
+ /* 16-byte aligned stack mandatory on AArch64 */
+ else if (stack_start & 15)
+ return -EINVAL;
+ else
childregs->sp = stack_start;
- }
}
+
/*
* If a TLS pointer was passed to clone (4th argument), use it
* for the new thread.
*/
if (clone_flags & CLONE_SETTLS)
- tls = childregs->regs[3];
+ p->thread.tp_value = childregs->regs[3];
} else {
memset(childregs, 0, sizeof(struct pt_regs));
childregs->pstate = PSR_MODE_EL1h;
@@ -291,7 +282,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
}
p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
p->thread.cpu_context.sp = (unsigned long)childregs;
- p->thread.tp_value = tls;
ptrace_hw_copy_thread(p);
@@ -302,18 +292,12 @@ static void tls_thread_switch(struct task_struct *next)
{
unsigned long tpidr, tpidrro;
- if (!is_compat_task()) {
- asm("mrs %0, tpidr_el0" : "=r" (tpidr));
- current->thread.tp_value = tpidr;
- }
+ asm("mrs %0, tpidr_el0" : "=r" (tpidr));
+ *task_user_tls(current) = tpidr;
- if (is_compat_thread(task_thread_info(next))) {
- tpidr = 0;
- tpidrro = next->thread.tp_value;
- } else {
- tpidr = next->thread.tp_value;
- tpidrro = 0;
- }
+ tpidr = *task_user_tls(next);
+ tpidrro = is_compat_thread(task_thread_info(next)) ?
+ next->thread.tp_value : 0;
asm(
" msr tpidr_el0, %0\n"
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index ea18cb53921e..869f202748e8 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -15,7 +15,6 @@
#define pr_fmt(fmt) "psci: " fmt
-#include <linux/acpi.h>
#include <linux/init.h>
#include <linux/of.h>
#include <linux/smp.h>
@@ -25,8 +24,8 @@
#include <linux/slab.h>
#include <uapi/linux/psci.h>
-#include <asm/acpi.h>
#include <asm/compiler.h>
+#include <asm/cputype.h>
#include <asm/cpu_ops.h>
#include <asm/errno.h>
#include <asm/psci.h>
@@ -37,16 +36,31 @@
#define PSCI_POWER_STATE_TYPE_STANDBY 0
#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1
-struct psci_power_state {
- u16 id;
- u8 type;
- u8 affinity_level;
-};
+static bool psci_power_state_loses_context(u32 state)
+{
+ return state & PSCI_0_2_POWER_STATE_TYPE_MASK;
+}
+
+static bool psci_power_state_is_valid(u32 state)
+{
+ const u32 valid_mask = PSCI_0_2_POWER_STATE_ID_MASK |
+ PSCI_0_2_POWER_STATE_TYPE_MASK |
+ PSCI_0_2_POWER_STATE_AFFL_MASK;
+
+ return !(state & ~valid_mask);
+}
+
+/*
+ * The CPU any Trusted OS is resident on. The trusted OS may reject CPU_OFF
+ * calls to its resident CPU, so we must avoid issuing those. We never migrate
+ * a Trusted OS even if it claims to be capable of migration -- doing so will
+ * require cooperation with a Trusted OS driver.
+ */
+static int resident_cpu = -1;
struct psci_operations {
- int (*cpu_suspend)(struct psci_power_state state,
- unsigned long entry_point);
- int (*cpu_off)(struct psci_power_state state);
+ int (*cpu_suspend)(u32 state, unsigned long entry_point);
+ int (*cpu_off)(u32 state);
int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
int (*migrate)(unsigned long cpuid);
int (*affinity_info)(unsigned long target_affinity,
@@ -56,23 +70,21 @@ struct psci_operations {
static struct psci_operations psci_ops;
-static int (*invoke_psci_fn)(u64, u64, u64, u64);
-typedef int (*psci_initcall_t)(const struct device_node *);
-
-asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64);
-asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64);
+typedef unsigned long (psci_fn)(unsigned long, unsigned long,
+ unsigned long, unsigned long);
+asmlinkage psci_fn __invoke_psci_fn_hvc;
+asmlinkage psci_fn __invoke_psci_fn_smc;
+static psci_fn *invoke_psci_fn;
enum psci_function {
PSCI_FN_CPU_SUSPEND,
PSCI_FN_CPU_ON,
PSCI_FN_CPU_OFF,
PSCI_FN_MIGRATE,
- PSCI_FN_AFFINITY_INFO,
- PSCI_FN_MIGRATE_INFO_TYPE,
PSCI_FN_MAX,
};
-static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state);
+static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
static u32 psci_function_id[PSCI_FN_MAX];
@@ -92,56 +104,28 @@ static int psci_to_linux_errno(int errno)
return -EINVAL;
}
-static u32 psci_power_state_pack(struct psci_power_state state)
-{
- return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
- & PSCI_0_2_POWER_STATE_ID_MASK) |
- ((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
- & PSCI_0_2_POWER_STATE_TYPE_MASK) |
- ((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
- & PSCI_0_2_POWER_STATE_AFFL_MASK);
-}
-
-static void psci_power_state_unpack(u32 power_state,
- struct psci_power_state *state)
-{
- state->id = (power_state & PSCI_0_2_POWER_STATE_ID_MASK) >>
- PSCI_0_2_POWER_STATE_ID_SHIFT;
- state->type = (power_state & PSCI_0_2_POWER_STATE_TYPE_MASK) >>
- PSCI_0_2_POWER_STATE_TYPE_SHIFT;
- state->affinity_level =
- (power_state & PSCI_0_2_POWER_STATE_AFFL_MASK) >>
- PSCI_0_2_POWER_STATE_AFFL_SHIFT;
-}
-
-static int psci_get_version(void)
+static u32 psci_get_version(void)
{
- int err;
-
- err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
- return err;
+ return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
}
-static int psci_cpu_suspend(struct psci_power_state state,
- unsigned long entry_point)
+static int psci_cpu_suspend(u32 state, unsigned long entry_point)
{
int err;
- u32 fn, power_state;
+ u32 fn;
fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
- power_state = psci_power_state_pack(state);
- err = invoke_psci_fn(fn, power_state, entry_point, 0);
+ err = invoke_psci_fn(fn, state, entry_point, 0);
return psci_to_linux_errno(err);
}
-static int psci_cpu_off(struct psci_power_state state)
+static int psci_cpu_off(u32 state)
{
int err;
- u32 fn, power_state;
+ u32 fn;
fn = psci_function_id[PSCI_FN_CPU_OFF];
- power_state = psci_power_state_pack(state);
- err = invoke_psci_fn(fn, power_state, 0, 0);
+ err = invoke_psci_fn(fn, state, 0, 0);
return psci_to_linux_errno(err);
}
@@ -168,30 +152,29 @@ static int psci_migrate(unsigned long cpuid)
static int psci_affinity_info(unsigned long target_affinity,
unsigned long lowest_affinity_level)
{
- int err;
- u32 fn;
-
- fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
- err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
- return err;
+ return invoke_psci_fn(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity,
+ lowest_affinity_level, 0);
}
static int psci_migrate_info_type(void)
{
- int err;
- u32 fn;
+ return invoke_psci_fn(PSCI_0_2_FN_MIGRATE_INFO_TYPE, 0, 0, 0);
+}
- fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
- err = invoke_psci_fn(fn, 0, 0, 0);
- return err;
+static unsigned long psci_migrate_info_up_cpu(void)
+{
+ return invoke_psci_fn(PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU, 0, 0, 0);
}
-static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
- unsigned int cpu)
+static int __maybe_unused cpu_psci_cpu_init_idle(unsigned int cpu)
{
int i, ret, count = 0;
- struct psci_power_state *psci_states;
- struct device_node *state_node;
+ u32 *psci_states;
+ struct device_node *state_node, *cpu_node;
+
+ cpu_node = of_get_cpu_node(cpu, NULL);
+ if (!cpu_node)
+ return -ENODEV;
/*
* If the PSCI cpu_suspend function hook has not been initialized
@@ -215,13 +198,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
return -ENOMEM;
for (i = 0; i < count; i++) {
- u32 psci_power_state;
+ u32 state;
state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
ret = of_property_read_u32(state_node,
"arm,psci-suspend-param",
- &psci_power_state);
+ &state);
if (ret) {
pr_warn(" * %s missing arm,psci-suspend-param property\n",
state_node->full_name);
@@ -230,9 +213,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
}
of_node_put(state_node);
- pr_debug("psci-power-state %#x index %d\n", psci_power_state,
- i);
- psci_power_state_unpack(psci_power_state, &psci_states[i]);
+ pr_debug("psci-power-state %#x index %d\n", state, i);
+ if (!psci_power_state_is_valid(state)) {
+ pr_warn("Invalid PSCI power state %#x\n", state);
+ ret = -EINVAL;
+ goto free_mem;
+ }
+ psci_states[i] = state;
}
/* Idle states parsed correctly, initialize per-cpu pointer */
per_cpu(psci_power_state, cpu) = psci_states;
@@ -275,6 +262,46 @@ static void psci_sys_poweroff(void)
invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
}
+/*
+ * Detect the presence of a resident Trusted OS which may cause CPU_OFF to
+ * return DENIED (which would be fatal).
+ */
+static void __init psci_init_migrate(void)
+{
+ unsigned long cpuid;
+ int type, cpu;
+
+ type = psci_ops.migrate_info_type();
+
+ if (type == PSCI_0_2_TOS_MP) {
+ pr_info("Trusted OS migration not required\n");
+ return;
+ }
+
+ if (type == PSCI_RET_NOT_SUPPORTED) {
+ pr_info("MIGRATE_INFO_TYPE not supported.\n");
+ return;
+ }
+
+ if (type != PSCI_0_2_TOS_UP_MIGRATE &&
+ type != PSCI_0_2_TOS_UP_NO_MIGRATE) {
+ pr_err("MIGRATE_INFO_TYPE returned unknown type (%d)\n", type);
+ return;
+ }
+
+ cpuid = psci_migrate_info_up_cpu();
+ if (cpuid & ~MPIDR_HWID_BITMASK) {
+ pr_warn("MIGRATE_INFO_UP_CPU reported invalid physical ID (0x%lx)\n",
+ cpuid);
+ return;
+ }
+
+ cpu = get_logical_index(cpuid);
+ resident_cpu = cpu >= 0 ? cpu : -1;
+
+ pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
+}
+
static void __init psci_0_2_set_functions(void)
{
pr_info("Using standard PSCI v0.2 function IDs\n");
@@ -290,11 +317,8 @@ static void __init psci_0_2_set_functions(void)
psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN64_MIGRATE;
psci_ops.migrate = psci_migrate;
- psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN64_AFFINITY_INFO;
psci_ops.affinity_info = psci_affinity_info;
- psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
- PSCI_0_2_FN_MIGRATE_INFO_TYPE;
psci_ops.migrate_info_type = psci_migrate_info_type;
arm_pm_restart = psci_sys_reset;
@@ -307,32 +331,26 @@ static void __init psci_0_2_set_functions(void)
*/
static int __init psci_probe(void)
{
- int ver = psci_get_version();
-
- if (ver == PSCI_RET_NOT_SUPPORTED) {
- /*
- * PSCI versions >=0.2 mandates implementation of
- * PSCI_VERSION.
- */
- pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
- return -EOPNOTSUPP;
- } else {
- pr_info("PSCIv%d.%d detected in firmware.\n",
- PSCI_VERSION_MAJOR(ver),
- PSCI_VERSION_MINOR(ver));
-
- if (PSCI_VERSION_MAJOR(ver) == 0 &&
- PSCI_VERSION_MINOR(ver) < 2) {
- pr_err("Conflicting PSCI version detected.\n");
- return -EINVAL;
- }
+ u32 ver = psci_get_version();
+
+ pr_info("PSCIv%d.%d detected in firmware.\n",
+ PSCI_VERSION_MAJOR(ver),
+ PSCI_VERSION_MINOR(ver));
+
+ if (PSCI_VERSION_MAJOR(ver) == 0 && PSCI_VERSION_MINOR(ver) < 2) {
+ pr_err("Conflicting PSCI version detected.\n");
+ return -EINVAL;
}
psci_0_2_set_functions();
+ psci_init_migrate();
+
return 0;
}
+typedef int (*psci_initcall_t)(const struct device_node *);
+
/*
* PSCI init function for PSCI versions >=0.2
*
@@ -421,6 +439,7 @@ int __init psci_dt_init(void)
return init_fn(np);
}
+#ifdef CONFIG_ACPI
/*
* We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's
* explicitly clarified in SBBR
@@ -441,10 +460,11 @@ int __init psci_acpi_init(void)
return psci_probe();
}
+#endif
#ifdef CONFIG_SMP
-static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu)
+static int __init cpu_psci_cpu_init(unsigned int cpu)
{
return 0;
}
@@ -469,11 +489,21 @@ static int cpu_psci_cpu_boot(unsigned int cpu)
}
#ifdef CONFIG_HOTPLUG_CPU
+static bool psci_tos_resident_on(int cpu)
+{
+ return cpu == resident_cpu;
+}
+
static int cpu_psci_cpu_disable(unsigned int cpu)
{
/* Fail early if we don't have CPU_OFF support */
if (!psci_ops.cpu_off)
return -EOPNOTSUPP;
+
+ /* Trusted OS will deny CPU_OFF */
+ if (psci_tos_resident_on(cpu))
+ return -EPERM;
+
return 0;
}
@@ -484,9 +514,8 @@ static void cpu_psci_cpu_die(unsigned int cpu)
* There are no known implementations of PSCI actually using the
* power state field, pass a sensible default for now.
*/
- struct psci_power_state state = {
- .type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
- };
+ u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
+ PSCI_0_2_POWER_STATE_TYPE_SHIFT;
ret = psci_ops.cpu_off(state);
@@ -498,7 +527,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
int err, i;
if (!psci_ops.affinity_info)
- return 1;
+ return 0;
/*
* cpu_kill could race with cpu_die and we can
* potentially end up declaring this cpu undead
@@ -509,7 +538,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
pr_info("CPU%d killed.\n", cpu);
- return 1;
+ return 0;
}
msleep(10);
@@ -518,15 +547,14 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
cpu, err);
- /* Make op_cpu_kill() fail. */
- return 0;
+ return -ETIMEDOUT;
}
#endif
#endif
static int psci_suspend_finisher(unsigned long index)
{
- struct psci_power_state *state = __this_cpu_read(psci_power_state);
+ u32 *state = __this_cpu_read(psci_power_state);
return psci_ops.cpu_suspend(state[index - 1],
virt_to_phys(cpu_resume));
@@ -535,7 +563,7 @@ static int psci_suspend_finisher(unsigned long index)
static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index)
{
int ret;
- struct psci_power_state *state = __this_cpu_read(psci_power_state);
+ u32 *state = __this_cpu_read(psci_power_state);
/*
* idle state index 0 corresponds to wfi, should never be called
* from the cpu_suspend operations
@@ -543,10 +571,10 @@ static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index)
if (WARN_ON_ONCE(!index))
return -EINVAL;
- if (state[index - 1].type == PSCI_POWER_STATE_TYPE_STANDBY)
+ if (!psci_power_state_loses_context(state[index - 1]))
ret = psci_ops.cpu_suspend(state[index - 1], 0);
else
- ret = __cpu_suspend(index, psci_suspend_finisher);
+ ret = cpu_suspend(index, psci_suspend_finisher);
return ret;
}
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 74753132c3ac..ffd3970721bf 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -105,18 +105,6 @@ static struct resource mem_res[] = {
#define kernel_code mem_res[0]
#define kernel_data mem_res[1]
-void __init early_print(const char *str, ...)
-{
- char buf[256];
- va_list ap;
-
- va_start(ap, str);
- vsnprintf(buf, sizeof(buf), str, ap);
- va_end(ap);
-
- printk("%s", buf);
-}
-
/*
* The recorded values of x0 .. x3 upon kernel entry.
*/
@@ -326,12 +314,14 @@ static void __init setup_processor(void)
static void __init setup_machine_fdt(phys_addr_t dt_phys)
{
- if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys))) {
- early_print("\n"
- "Error: invalid device tree blob at physical address 0x%p (virtual address 0x%p)\n"
- "The dtb must be 8-byte aligned and passed in the first 512MB of memory\n"
- "\nPlease check your bootloader.\n",
- dt_phys, phys_to_virt(dt_phys));
+ void *dt_virt = fixmap_remap_fdt(dt_phys);
+
+ if (!dt_virt || !early_init_dt_scan(dt_virt)) {
+ pr_crit("\n"
+ "Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
+ "The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
+ "\nPlease check your bootloader.",
+ &dt_phys, dt_virt);
while (true)
cpu_relax();
@@ -374,8 +364,6 @@ void __init setup_arch(char **cmdline_p)
{
setup_processor();
- setup_machine_fdt(__fdt_pointer);
-
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
@@ -386,6 +374,8 @@ void __init setup_arch(char **cmdline_p)
early_fixmap_init();
early_ioremap_init();
+ setup_machine_fdt(__fdt_pointer);
+
parse_early_param();
/*
@@ -408,16 +398,13 @@ void __init setup_arch(char **cmdline_p)
if (acpi_disabled) {
unflatten_device_tree();
psci_dt_init();
- cpu_read_bootcpu_ops();
-#ifdef CONFIG_SMP
- of_smp_init_cpus();
-#endif
} else {
psci_acpi_init();
- acpi_init_cpus();
}
+ cpu_read_bootcpu_ops();
#ifdef CONFIG_SMP
+ smp_init_cpus();
smp_build_mpidr_hash();
#endif
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index d26fcd4cd6e6..1670f15ef69e 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -370,7 +370,7 @@ badframe:
if (show_unhandled_signals)
pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n",
current->comm, task_pid_nr(current), __func__,
- regs->pc, regs->sp);
+ regs->pc, regs->compat_sp);
force_sig(SIGSEGV, current);
return 0;
}
@@ -407,7 +407,7 @@ badframe:
if (show_unhandled_signals)
pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n",
current->comm, task_pid_nr(current), __func__,
- regs->pc, regs->sp);
+ regs->pc, regs->compat_sp);
force_sig(SIGSEGV, current);
return 0;
}
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index ede186cdd452..803cfea41962 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -130,12 +130,14 @@ ENDPROC(__cpu_suspend_enter)
/*
* x0 must contain the sctlr value retrieved from restored context
*/
+ .pushsection ".idmap.text", "ax"
ENTRY(cpu_resume_mmu)
ldr x3, =cpu_resume_after_mmu
msr sctlr_el1, x0 // restore sctlr_el1
isb
br x3 // global jump to virtual address
ENDPROC(cpu_resume_mmu)
+ .popsection
cpu_resume_after_mmu:
mov x0, #0 // return zero on success
ldp x19, x20, [sp, #16]
@@ -162,15 +164,12 @@ ENTRY(cpu_resume)
#else
mov x7, xzr
#endif
- adrp x0, sleep_save_sp
- add x0, x0, #:lo12:sleep_save_sp
- ldr x0, [x0, #SLEEP_SAVE_SP_PHYS]
+ ldr_l x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
ldr x0, [x0, x7, lsl #3]
/* load sp from context */
ldr x2, [x0, #CPU_CTX_SP]
- adrp x1, sleep_idmap_phys
/* load physical address of identity map page table in x1 */
- ldr x1, [x1, #:lo12:sleep_idmap_phys]
+ adrp x1, idmap_pg_dir
mov sp, x2
/*
* cpu_do_resume expects x0 to contain context physical address
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2cb008177252..4b2121bd7f9c 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/acpi.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
@@ -248,20 +249,20 @@ static int op_cpu_kill(unsigned int cpu)
* time and hope that it's dead, so let's skip the wait and just hope.
*/
if (!cpu_ops[cpu]->cpu_kill)
- return 1;
+ return 0;
return cpu_ops[cpu]->cpu_kill(cpu);
}
-static DECLARE_COMPLETION(cpu_died);
-
/*
* called on the thread which is asking for a CPU to be shutdown -
* waits until shutdown has completed, or it is timed out.
*/
void __cpu_die(unsigned int cpu)
{
- if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+ int err;
+
+ if (!cpu_wait_death(cpu, 5)) {
pr_crit("CPU%u: cpu didn't die\n", cpu);
return;
}
@@ -273,8 +274,10 @@ void __cpu_die(unsigned int cpu)
* verify that it has really left the kernel before we consider
* clobbering anything it might still be using.
*/
- if (!op_cpu_kill(cpu))
- pr_warn("CPU%d may not have shut down cleanly\n", cpu);
+ err = op_cpu_kill(cpu);
+ if (err)
+ pr_warn("CPU%d may not have shut down cleanly: %d\n",
+ cpu, err);
}
/*
@@ -294,7 +297,7 @@ void cpu_die(void)
local_irq_disable();
/* Tell __cpu_die() that this CPU is now safe to dispose of */
- complete(&cpu_died);
+ (void)cpu_report_death();
/*
* Actually shutdown the CPU. This must never fail. The specific hotplug
@@ -318,57 +321,158 @@ void __init smp_prepare_boot_cpu(void)
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
}
+static u64 __init of_get_cpu_mpidr(struct device_node *dn)
+{
+ const __be32 *cell;
+ u64 hwid;
+
+ /*
+ * A cpu node with missing "reg" property is
+ * considered invalid to build a cpu_logical_map
+ * entry.
+ */
+ cell = of_get_property(dn, "reg", NULL);
+ if (!cell) {
+ pr_err("%s: missing reg property\n", dn->full_name);
+ return INVALID_HWID;
+ }
+
+ hwid = of_read_number(cell, of_n_addr_cells(dn));
+ /*
+ * Non affinity bits must be set to 0 in the DT
+ */
+ if (hwid & ~MPIDR_HWID_BITMASK) {
+ pr_err("%s: invalid reg property\n", dn->full_name);
+ return INVALID_HWID;
+ }
+ return hwid;
+}
+
+/*
+ * Duplicate MPIDRs are a recipe for disaster. Scan all initialized
+ * entries and check for duplicates. If any is found just ignore the
+ * cpu. cpu_logical_map was initialized to INVALID_HWID to avoid
+ * matching valid MPIDR values.
+ */
+static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
+{
+ unsigned int i;
+
+ for (i = 1; (i < cpu) && (i < NR_CPUS); i++)
+ if (cpu_logical_map(i) == hwid)
+ return true;
+ return false;
+}
+
+/*
+ * Initialize cpu operations for a logical cpu and
+ * set it in the possible mask on success
+ */
+static int __init smp_cpu_setup(int cpu)
+{
+ if (cpu_read_ops(cpu))
+ return -ENODEV;
+
+ if (cpu_ops[cpu]->cpu_init(cpu))
+ return -ENODEV;
+
+ set_cpu_possible(cpu, true);
+
+ return 0;
+}
+
+static bool bootcpu_valid __initdata;
+static unsigned int cpu_count = 1;
+
+#ifdef CONFIG_ACPI
+/*
+ * acpi_map_gic_cpu_interface - parse processor MADT entry
+ *
+ * Carry out sanity checks on MADT processor entry and initialize
+ * cpu_logical_map on success
+ */
+static void __init
+acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
+{
+ u64 hwid = processor->arm_mpidr;
+
+ if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
+ pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
+ return;
+ }
+
+ if (!(processor->flags & ACPI_MADT_ENABLED)) {
+ pr_err("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
+ return;
+ }
+
+ if (is_mpidr_duplicate(cpu_count, hwid)) {
+ pr_err("duplicate CPU MPIDR 0x%llx in MADT\n", hwid);
+ return;
+ }
+
+ /* Check if GICC structure of boot CPU is available in the MADT */
+ if (cpu_logical_map(0) == hwid) {
+ if (bootcpu_valid) {
+ pr_err("duplicate boot CPU MPIDR: 0x%llx in MADT\n",
+ hwid);
+ return;
+ }
+ bootcpu_valid = true;
+ return;
+ }
+
+ if (cpu_count >= NR_CPUS)
+ return;
+
+ /* map the logical cpu id to cpu MPIDR */
+ cpu_logical_map(cpu_count) = hwid;
+
+ cpu_count++;
+}
+
+static int __init
+acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+ struct acpi_madt_generic_interrupt *processor;
+
+ processor = (struct acpi_madt_generic_interrupt *)header;
+ if (BAD_MADT_ENTRY(processor, end))
+ return -EINVAL;
+
+ acpi_table_print_madt_entry(header);
+
+ acpi_map_gic_cpu_interface(processor);
+
+ return 0;
+}
+#else
+#define acpi_table_parse_madt(...) do { } while (0)
+#endif
+
/*
* Enumerate the possible CPU set from the device tree and build the
* cpu logical map array containing MPIDR values related to logical
* cpus. Assumes that cpu_logical_map(0) has already been initialized.
*/
-void __init of_smp_init_cpus(void)
+void __init of_parse_and_init_cpus(void)
{
struct device_node *dn = NULL;
- unsigned int i, cpu = 1;
- bool bootcpu_valid = false;
while ((dn = of_find_node_by_type(dn, "cpu"))) {
- const u32 *cell;
- u64 hwid;
+ u64 hwid = of_get_cpu_mpidr(dn);
- /*
- * A cpu node with missing "reg" property is
- * considered invalid to build a cpu_logical_map
- * entry.
- */
- cell = of_get_property(dn, "reg", NULL);
- if (!cell) {
- pr_err("%s: missing reg property\n", dn->full_name);
+ if (hwid == INVALID_HWID)
goto next;
- }
- hwid = of_read_number(cell, of_n_addr_cells(dn));
- /*
- * Non affinity bits must be set to 0 in the DT
- */
- if (hwid & ~MPIDR_HWID_BITMASK) {
- pr_err("%s: invalid reg property\n", dn->full_name);
+ if (is_mpidr_duplicate(cpu_count, hwid)) {
+ pr_err("%s: duplicate cpu reg properties in the DT\n",
+ dn->full_name);
goto next;
}
/*
- * Duplicate MPIDRs are a recipe for disaster. Scan
- * all initialized entries and check for
- * duplicates. If any is found just ignore the cpu.
- * cpu_logical_map was initialized to INVALID_HWID to
- * avoid matching valid MPIDR values.
- */
- for (i = 1; (i < cpu) && (i < NR_CPUS); i++) {
- if (cpu_logical_map(i) == hwid) {
- pr_err("%s: duplicate cpu reg properties in the DT\n",
- dn->full_name);
- goto next;
- }
- }
-
- /*
* The numbering scheme requires that the boot CPU
* must be assigned logical id 0. Record it so that
* the logical map built from DT is validated and can
@@ -392,38 +496,58 @@ void __init of_smp_init_cpus(void)
continue;
}
- if (cpu >= NR_CPUS)
- goto next;
-
- if (cpu_read_ops(dn, cpu) != 0)
- goto next;
-
- if (cpu_ops[cpu]->cpu_init(dn, cpu))
+ if (cpu_count >= NR_CPUS)
goto next;
pr_debug("cpu logical map 0x%llx\n", hwid);
- cpu_logical_map(cpu) = hwid;
+ cpu_logical_map(cpu_count) = hwid;
next:
- cpu++;
+ cpu_count++;
}
+}
+
+/*
+ * Enumerate the possible CPU set from the device tree or ACPI and build the
+ * cpu logical map array containing MPIDR values related to logical
+ * cpus. Assumes that cpu_logical_map(0) has already been initialized.
+ */
+void __init smp_init_cpus(void)
+{
+ int i;
- /* sanity check */
- if (cpu > NR_CPUS)
- pr_warning("no. of cores (%d) greater than configured maximum of %d - clipping\n",
- cpu, NR_CPUS);
+ if (acpi_disabled)
+ of_parse_and_init_cpus();
+ else
+ /*
+ * do a walk of MADT to determine how many CPUs
+ * we have including disabled CPUs, and get information
+ * we need for SMP init
+ */
+ acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
+ acpi_parse_gic_cpu_interface, 0);
+
+ if (cpu_count > NR_CPUS)
+ pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n",
+ cpu_count, NR_CPUS);
if (!bootcpu_valid) {
- pr_err("DT missing boot CPU MPIDR, not enabling secondaries\n");
+ pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
return;
}
/*
- * All the cpus that made it to the cpu_logical_map have been
- * validated so set them as possible cpus.
+ * We need to set the cpu_logical_map entries before enabling
+ * the cpus so that cpu processor description entries (DT cpu nodes
+ * and ACPI MADT entries) can be retrieved by matching the cpu hwid
+ * with entries in cpu_logical_map while initializing the cpus.
+ * If the cpu set-up fails, invalidate the cpu_logical_map entry.
*/
- for (i = 0; i < NR_CPUS; i++)
- if (cpu_logical_map(i) != INVALID_HWID)
- set_cpu_possible(i, true);
+ for (i = 1; i < NR_CPUS; i++) {
+ if (cpu_logical_map(i) != INVALID_HWID) {
+ if (smp_cpu_setup(i))
+ cpu_logical_map(i) = INVALID_HWID;
+ }
+ }
}
void __init smp_prepare_cpus(unsigned int max_cpus)
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 14944e5b28da..aef3605a8c47 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -49,8 +49,14 @@ static void write_pen_release(u64 val)
}
-static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
+static int smp_spin_table_cpu_init(unsigned int cpu)
{
+ struct device_node *dn;
+
+ dn = of_get_cpu_node(cpu, NULL);
+ if (!dn)
+ return -ENODEV;
+
/*
* Determine the address from which the CPU is polling.
*/
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index d7daf45ae7a2..8297d502217e 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -51,13 +51,13 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
}
/*
- * __cpu_suspend
+ * cpu_suspend
*
* arg: argument to pass to the finisher function
* fn: finisher function pointer
*
*/
-int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
{
struct mm_struct *mm = current->active_mm;
int ret;
@@ -82,7 +82,7 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
* We are resuming from reset with TTBR0_EL1 set to the
* idmap to enable the MMU; restore the active_mm mappings in
* TTBR0_EL1 unless the active_mm == &init_mm, in which case
- * the thread entered __cpu_suspend with TTBR0_EL1 set to
+ * the thread entered cpu_suspend with TTBR0_EL1 set to
* reserved TTBR0 page tables and should be restored as such.
*/
if (mm == &init_mm)
@@ -118,7 +118,6 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
}
struct sleep_save_sp sleep_save_sp;
-phys_addr_t sleep_idmap_phys;
static int __init cpu_suspend_init(void)
{
@@ -132,9 +131,7 @@ static int __init cpu_suspend_init(void)
sleep_save_sp.save_ptr_stash = ctx_ptr;
sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
- sleep_idmap_phys = virt_to_phys(idmap_pg_dir);
__flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
- __flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys));
return 0;
}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 1ef2940df13c..a12251c074a8 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -335,8 +335,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
if (call_undef_hook(regs) == 0)
return;
- if (show_unhandled_signals && unhandled_signal(current, SIGILL) &&
- printk_ratelimit()) {
+ if (show_unhandled_signals_ratelimited() && unhandled_signal(current, SIGILL)) {
pr_info("%s[%d]: undefined instruction: pc=%p\n",
current->comm, task_pid_nr(current), pc);
dump_instr(KERN_INFO, regs);
@@ -363,7 +362,7 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
}
#endif
- if (show_unhandled_signals && printk_ratelimit()) {
+ if (show_unhandled_signals_ratelimited()) {
pr_info("%s[%d]: syscall %d\n", current->comm,
task_pid_nr(current), (int)regs->syscallno);
dump_instr("", regs);
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index ff3bddea482d..f6fe17d88da5 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -15,6 +15,10 @@ ccflags-y := -shared -fno-common -fno-builtin
ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
+# down to collect2, resulting in silent corruption of the vDSO image.
+ccflags-y += -Wl,-shared
+
obj-y += vdso.o
extra-y += vdso.lds vdso-offsets.h
CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index a2c29865c3fe..98073332e2d0 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -38,6 +38,12 @@ jiffies = jiffies_64;
*(.hyp.text) \
VMLINUX_SYMBOL(__hyp_text_end) = .;
+#define IDMAP_TEXT \
+ . = ALIGN(SZ_4K); \
+ VMLINUX_SYMBOL(__idmap_text_start) = .; \
+ *(.idmap.text) \
+ VMLINUX_SYMBOL(__idmap_text_end) = .;
+
/*
* The size of the PE/COFF section that covers the kernel image, which
* runs from stext to _edata, must be a round multiple of the PE/COFF
@@ -95,6 +101,7 @@ SECTIONS
SCHED_TEXT
LOCK_TEXT
HYPERVISOR_TEXT
+ IDMAP_TEXT
*(.fixup)
*(.gnu.warning)
. = ALIGN(16);
@@ -167,11 +174,13 @@ SECTIONS
}
/*
- * The HYP init code can't be more than a page long,
+ * The HYP init code and ID map text can't be longer than a page each,
* and should not cross a page boundary.
*/
ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
"HYP init code too big or misaligned")
+ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
+ "ID map text too big or misaligned")
/*
* If padding is applied before .head.text, virt<->phys conversions will fail.
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 5105e297ed5f..bfffe8f4bd53 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -28,6 +28,7 @@ config KVM
select KVM_ARM_HOST
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
select SRCU
+ select KVM_VFIO
select HAVE_KVM_EVENTFD
select HAVE_KVM_IRQFD
---help---
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index d5904f876cdb..f90f4aa7f88d 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm
obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 5befd010e232..17a8fb14f428 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -17,8 +17,10 @@
#include <linux/linkage.h>
+#include <asm/alternative.h>
#include <asm/asm-offsets.h>
#include <asm/assembler.h>
+#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/fpsimdmacros.h>
@@ -50,8 +52,8 @@
stp x29, lr, [x3, #80]
mrs x19, sp_el0
- mrs x20, elr_el2 // EL1 PC
- mrs x21, spsr_el2 // EL1 pstate
+ mrs x20, elr_el2 // pc before entering el2
+ mrs x21, spsr_el2 // pstate before entering el2
stp x19, x20, [x3, #96]
str x21, [x3, #112]
@@ -82,8 +84,8 @@
ldr x21, [x3, #16]
msr sp_el0, x19
- msr elr_el2, x20 // EL1 PC
- msr spsr_el2, x21 // EL1 pstate
+ msr elr_el2, x20 // pc on return from el2
+ msr spsr_el2, x21 // pstate on return from el2
add x3, x2, #CPU_XREG_OFFSET(19)
ldp x19, x20, [x3]
@@ -808,10 +810,7 @@
* Call into the vgic backend for state saving
*/
.macro save_vgic_state
- adr x24, __vgic_sr_vectors
- ldr x24, [x24, VGIC_SAVE_FN]
- kern_hyp_va x24
- blr x24
+ alternative_insn "bl __save_vgic_v2_state", "bl __save_vgic_v3_state", ARM64_HAS_SYSREG_GIC_CPUIF
mrs x24, hcr_el2
mov x25, #HCR_INT_OVERRIDE
neg x25, x25
@@ -828,10 +827,7 @@
orr x24, x24, #HCR_INT_OVERRIDE
orr x24, x24, x25
msr hcr_el2, x24
- adr x24, __vgic_sr_vectors
- ldr x24, [x24, #VGIC_RESTORE_FN]
- kern_hyp_va x24
- blr x24
+ alternative_insn "bl __restore_vgic_v2_state", "bl __restore_vgic_v3_state", ARM64_HAS_SYSREG_GIC_CPUIF
.endm
.macro save_timer_state
@@ -1062,12 +1058,6 @@ ENTRY(__kvm_flush_vm_context)
ret
ENDPROC(__kvm_flush_vm_context)
- // struct vgic_sr_vectors __vgi_sr_vectors;
- .align 3
-ENTRY(__vgic_sr_vectors)
- .skip VGIC_SR_VECTOR_SZ
-ENDPROC(__vgic_sr_vectors)
-
__kvm_hyp_panic:
// Guess the context by looking at VTTBR:
// If zero, then we're already a host.
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
index f002fe1c3700..3f000712a85d 100644
--- a/arch/arm64/kvm/vgic-v2-switch.S
+++ b/arch/arm64/kvm/vgic-v2-switch.S
@@ -47,7 +47,6 @@ __save_vgic_v2_state:
add x3, x0, #VCPU_VGIC_CPU
/* Save all interesting registers */
- ldr w4, [x2, #GICH_HCR]
ldr w5, [x2, #GICH_VMCR]
ldr w6, [x2, #GICH_MISR]
ldr w7, [x2, #GICH_EISR0]
@@ -55,7 +54,6 @@ __save_vgic_v2_state:
ldr w9, [x2, #GICH_ELRSR0]
ldr w10, [x2, #GICH_ELRSR1]
ldr w11, [x2, #GICH_APR]
-CPU_BE( rev w4, w4 )
CPU_BE( rev w5, w5 )
CPU_BE( rev w6, w6 )
CPU_BE( rev w7, w7 )
@@ -64,7 +62,6 @@ CPU_BE( rev w9, w9 )
CPU_BE( rev w10, w10 )
CPU_BE( rev w11, w11 )
- str w4, [x3, #VGIC_V2_CPU_HCR]
str w5, [x3, #VGIC_V2_CPU_VMCR]
str w6, [x3, #VGIC_V2_CPU_MISR]
CPU_LE( str w7, [x3, #VGIC_V2_CPU_EISR] )
diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S
index 617a012a0107..3c20730ddff5 100644
--- a/arch/arm64/kvm/vgic-v3-switch.S
+++ b/arch/arm64/kvm/vgic-v3-switch.S
@@ -48,13 +48,11 @@
dsb st
// Save all interesting registers
- mrs_s x4, ICH_HCR_EL2
mrs_s x5, ICH_VMCR_EL2
mrs_s x6, ICH_MISR_EL2
mrs_s x7, ICH_EISR_EL2
mrs_s x8, ICH_ELSR_EL2
- str w4, [x3, #VGIC_V3_CPU_HCR]
str w5, [x3, #VGIC_V3_CPU_VMCR]
str w6, [x3, #VGIC_V3_CPU_MISR]
str w7, [x3, #VGIC_V3_CPU_EISR]
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 773d37a14039..9d84feb41a16 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,3 +4,5 @@ obj-y := dma-mapping.o extable.o fault.o init.o \
context.o proc.o pageattr.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_ARM64_PTDUMP) += dump.o
+
+CFLAGS_mmu.o := -I$(srctree)/scripts/dtc/libfdt/
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 2560e1e1562e..bdeb5d38c2dd 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -22,84 +22,11 @@
#include <linux/init.h>
#include <asm/assembler.h>
#include <asm/cpufeature.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include "proc-macros.S"
/*
- * __flush_dcache_all()
- *
- * Flush the whole D-cache.
- *
- * Corrupted registers: x0-x7, x9-x11
- */
-__flush_dcache_all:
- dmb sy // ensure ordering with previous memory accesses
- mrs x0, clidr_el1 // read clidr
- and x3, x0, #0x7000000 // extract loc from clidr
- lsr x3, x3, #23 // left align loc bit field
- cbz x3, finished // if loc is 0, then no need to clean
- mov x10, #0 // start clean at cache level 0
-loop1:
- add x2, x10, x10, lsr #1 // work out 3x current cache level
- lsr x1, x0, x2 // extract cache type bits from clidr
- and x1, x1, #7 // mask of the bits for current cache only
- cmp x1, #2 // see what cache we have at this level
- b.lt skip // skip if no cache, or just i-cache
- save_and_disable_irqs x9 // make CSSELR and CCSIDR access atomic
- msr csselr_el1, x10 // select current cache level in csselr
- isb // isb to sych the new cssr&csidr
- mrs x1, ccsidr_el1 // read the new ccsidr
- restore_irqs x9
- and x2, x1, #7 // extract the length of the cache lines
- add x2, x2, #4 // add 4 (line length offset)
- mov x4, #0x3ff
- and x4, x4, x1, lsr #3 // find maximum number on the way size
- clz w5, w4 // find bit position of way size increment
- mov x7, #0x7fff
- and x7, x7, x1, lsr #13 // extract max number of the index size
-loop2:
- mov x9, x4 // create working copy of max way size
-loop3:
- lsl x6, x9, x5
- orr x11, x10, x6 // factor way and cache number into x11
- lsl x6, x7, x2
- orr x11, x11, x6 // factor index number into x11
- dc cisw, x11 // clean & invalidate by set/way
- subs x9, x9, #1 // decrement the way
- b.ge loop3
- subs x7, x7, #1 // decrement the index
- b.ge loop2
-skip:
- add x10, x10, #2 // increment cache number
- cmp x3, x10
- b.gt loop1
-finished:
- mov x10, #0 // swith back to cache level 0
- msr csselr_el1, x10 // select current cache level in csselr
- dsb sy
- isb
- ret
-ENDPROC(__flush_dcache_all)
-
-/*
- * flush_cache_all()
- *
- * Flush the entire cache system. The data cache flush is now achieved
- * using atomic clean / invalidates working outwards from L1 cache. This
- * is done using Set/Way based cache maintainance instructions. The
- * instruction cache can still be invalidated back to the point of
- * unification in a single instruction.
- */
-ENTRY(flush_cache_all)
- mov x12, lr
- bl __flush_dcache_all
- mov x0, #0
- ic ialluis // I+BTB cache invalidate
- ret x12
-ENDPROC(flush_cache_all)
-
-/*
* flush_icache_range(start,end)
*
* Ensure that the I and D caches are coherent within specified region.
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index baa758d37021..76c1e6cd36fc 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -92,6 +92,14 @@ static void reset_context(void *info)
unsigned int cpu = smp_processor_id();
struct mm_struct *mm = current->active_mm;
+ /*
+ * current->active_mm could be init_mm for the idle thread immediately
+ * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to
+ * the reserved value, so no need to reset any context.
+ */
+ if (mm == &init_mm)
+ return;
+
smp_rmb();
asid = cpu_last_asid + cpu;
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index b0bd4e5fd5cf..d16a1cead23f 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -414,6 +414,98 @@ out:
return -ENOMEM;
}
+/********************************************
+ * The following APIs are for dummy DMA ops *
+ ********************************************/
+
+static void *__dummy_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags,
+ struct dma_attrs *attrs)
+{
+ return NULL;
+}
+
+static void __dummy_free(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
+{
+}
+
+static int __dummy_mmap(struct device *dev,
+ struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ struct dma_attrs *attrs)
+{
+ return -ENXIO;
+}
+
+static dma_addr_t __dummy_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ return DMA_ERROR_CODE;
+}
+
+static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+}
+
+static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ return 0;
+}
+
+static void __dummy_unmap_sg(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+}
+
+static void __dummy_sync_single(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+}
+
+static void __dummy_sync_sg(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+}
+
+static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+ return 1;
+}
+
+static int __dummy_dma_supported(struct device *hwdev, u64 mask)
+{
+ return 0;
+}
+
+struct dma_map_ops dummy_dma_ops = {
+ .alloc = __dummy_alloc,
+ .free = __dummy_free,
+ .mmap = __dummy_mmap,
+ .map_page = __dummy_map_page,
+ .unmap_page = __dummy_unmap_page,
+ .map_sg = __dummy_map_sg,
+ .unmap_sg = __dummy_unmap_sg,
+ .sync_single_for_cpu = __dummy_sync_single,
+ .sync_single_for_device = __dummy_sync_single,
+ .sync_sg_for_cpu = __dummy_sync_sg,
+ .sync_sg_for_device = __dummy_sync_sg,
+ .mapping_error = __dummy_mapping_error,
+ .dma_supported = __dummy_dma_supported,
+};
+EXPORT_SYMBOL(dummy_dma_ops);
+
static int __init arm64_dma_init(void)
{
int ret;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 96da13167d4a..b1fc69cd1499 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -115,8 +115,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
{
struct siginfo si;
- if (show_unhandled_signals && unhandled_signal(tsk, sig) &&
- printk_ratelimit()) {
+ if (show_unhandled_signals_ratelimited() && unhandled_signal(tsk, sig)) {
pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
addr, esr);
@@ -211,7 +210,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
* If we're in an interrupt or have no user context, we must not take
* the fault.
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
@@ -478,12 +477,19 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
struct pt_regs *regs)
{
struct siginfo info;
+ struct task_struct *tsk = current;
+
+ if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
+ pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
+ tsk->comm, task_pid_nr(tsk),
+ esr_get_class_string(esr), (void *)regs->pc,
+ (void *)regs->sp);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRALN;
info.si_addr = (void __user *)addr;
- arm64_notify_die("", regs, &info, esr);
+ arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
}
static struct fault_info debug_fault_info[] = {
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index b6f14e8d2121..4dfa3975ce5b 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -102,7 +102,6 @@ EXPORT_SYMBOL(flush_dcache_page);
/*
* Additional functions defined in assembly.
*/
-EXPORT_SYMBOL(flush_cache_all);
EXPORT_SYMBOL(flush_icache_range);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 597831bdddf3..ad87ce826cce 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -262,7 +262,7 @@ static void __init free_unused_memmap(void)
* memmap entries are valid from the bank end aligned to
* MAX_ORDER_NR_PAGES.
*/
- prev_end = ALIGN(start + __phys_to_pfn(reg->size),
+ prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
MAX_ORDER_NR_PAGES);
}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 5b8b664422d3..82d3435bf14f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -21,6 +21,7 @@
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/init.h>
+#include <linux/libfdt.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/memblock.h>
@@ -643,3 +644,68 @@ void __set_fixmap(enum fixed_addresses idx,
flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
}
}
+
+void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
+{
+ const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
+ pgprot_t prot = PAGE_KERNEL | PTE_RDONLY;
+ int granularity, size, offset;
+ void *dt_virt;
+
+ /*
+ * 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.
+ */
+ BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
+ if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
+ return NULL;
+
+ /*
+ * Make sure that the FDT region can be mapped without the need to
+ * allocate additional translation table pages, so that it is safe
+ * to call create_mapping() this early.
+ *
+ * On 64k pages, the FDT will be mapped using PTEs, so we need to
+ * be in the same PMD as the rest of the fixmap.
+ * On 4k pages, we'll use section mappings for the FDT so we only
+ * have to be in the same PUD.
+ */
+ BUILD_BUG_ON(dt_virt_base % SZ_2M);
+
+ if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) {
+ BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PMD_SHIFT !=
+ __fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT);
+
+ granularity = PAGE_SIZE;
+ } else {
+ BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PUD_SHIFT !=
+ __fix_to_virt(FIX_BTMAP_BEGIN) >> PUD_SHIFT);
+
+ granularity = PMD_SIZE;
+ }
+
+ offset = dt_phys % granularity;
+ dt_virt = (void *)dt_virt_base + offset;
+
+ /* map the first chunk so we can read the size from the header */
+ create_mapping(round_down(dt_phys, granularity), dt_virt_base,
+ granularity, prot);
+
+ if (fdt_check_header(dt_virt) != 0)
+ return NULL;
+
+ size = fdt_totalsize(dt_virt);
+ if (size > MAX_FDT_SIZE)
+ return NULL;
+
+ if (offset + size > granularity)
+ create_mapping(round_down(dt_phys, granularity), dt_virt_base,
+ round_up(offset + size, granularity), prot);
+
+ memblock_reserve(dt_phys, size);
+
+ return dt_virt;
+}
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index cdd754e19b9b..39139a3aa16d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -46,52 +46,6 @@
#define MAIR(attr, mt) ((attr) << ((mt) * 8))
/*
- * cpu_cache_off()
- *
- * Turn the CPU D-cache off.
- */
-ENTRY(cpu_cache_off)
- mrs x0, sctlr_el1
- bic x0, x0, #1 << 2 // clear SCTLR.C
- msr sctlr_el1, x0
- isb
- ret
-ENDPROC(cpu_cache_off)
-
-/*
- * cpu_reset(loc)
- *
- * Perform a soft reset of the system. Put the CPU into the same state
- * as it would be if it had been reset, and branch to what would be the
- * reset vector. It must be executed with the flat identity mapping.
- *
- * - loc - location to jump to for soft reset
- */
- .align 5
-ENTRY(cpu_reset)
- mrs x1, sctlr_el1
- bic x1, x1, #1
- msr sctlr_el1, x1 // disable the MMU
- isb
- ret x0
-ENDPROC(cpu_reset)
-
-ENTRY(cpu_soft_restart)
- /* Save address of cpu_reset() and reset address */
- mov x19, x0
- mov x20, x1
-
- /* Turn D-cache off */
- bl cpu_cache_off
-
- /* Push out all dirty data, and ensure cache is empty */
- bl flush_cache_all
-
- mov x0, x20
- ret x19
-ENDPROC(cpu_soft_restart)
-
-/*
* cpu_do_idle()
*
* Idle the processor (wait for interrupt).
diff --git a/arch/avr32/include/asm/cmpxchg.h b/arch/avr32/include/asm/cmpxchg.h
index 962a6aeab787..366bbeaeb405 100644
--- a/arch/avr32/include/asm/cmpxchg.h
+++ b/arch/avr32/include/asm/cmpxchg.h
@@ -70,8 +70,6 @@ extern unsigned long __cmpxchg_u64_unsupported_on_32bit_kernels(
if something tries to do an invalid cmpxchg(). */
extern void __cmpxchg_called_with_bad_pointer(void);
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
index 4f5ec2bb7172..e998ff5d8e1a 100644
--- a/arch/avr32/include/asm/io.h
+++ b/arch/avr32/include/asm/io.h
@@ -296,6 +296,7 @@ extern void __iounmap(void __iomem *addr);
__iounmap(addr)
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
#define cached(addr) P1SEGADDR(addr)
#define uncached(addr) P2SEGADDR(addr)
diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h
index a46f7cf3e1ea..68cf638faf48 100644
--- a/arch/avr32/include/asm/uaccess.h
+++ b/arch/avr32/include/asm/uaccess.h
@@ -97,7 +97,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -116,7 +117,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -136,7 +138,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -158,7 +161,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index d223a8b57c1e..c03533937a9f 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -14,11 +14,11 @@
#include <linux/pagemap.h>
#include <linux/kdebug.h>
#include <linux/kprobes.h>
+#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/sysreg.h>
#include <asm/tlb.h>
-#include <asm/uaccess.h>
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, int trap)
@@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
* If we're in an interrupt or have no user context, we must
* not take the fault...
*/
- if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
+ if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM))
goto no_context;
local_irq_enable();
diff --git a/arch/blackfin/include/asm/io.h b/arch/blackfin/include/asm/io.h
index 4e8ad0523118..6abebe82d4e9 100644
--- a/arch/blackfin/include/asm/io.h
+++ b/arch/blackfin/include/asm/io.h
@@ -10,6 +10,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/byteorder.h>
+#include <asm/def_LPBlackfin.h>
#define __raw_readb bfin_read8
#define __raw_readw bfin_read16
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 83f12f2ed9e3..3066d40a6db1 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -8,7 +8,7 @@
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <arch/system.h>
extern int find_fixup_code(struct pt_regs *);
@@ -109,11 +109,11 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
info.si_code = SEGV_MAPERR;
/*
- * If we're in an interrupt or "atomic" operation or have no
+ * If we're in an interrupt, have pagefaults disabled or have no
* user context, we must not take the fault.
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
diff --git a/arch/frv/include/asm/io.h b/arch/frv/include/asm/io.h
index 0b78bc89e840..a31b63ec4930 100644
--- a/arch/frv/include/asm/io.h
+++ b/arch/frv/include/asm/io.h
@@ -17,6 +17,8 @@
#ifdef __KERNEL__
+#define ARCH_HAS_IOREMAP_WT
+
#include <linux/types.h>
#include <asm/virtconvert.h>
#include <asm/string.h>
@@ -265,7 +267,7 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned lon
return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
}
-static inline void __iomem *ioremap_writethrough(unsigned long physaddr, unsigned long size)
+static inline void __iomem *ioremap_wt(unsigned long physaddr, unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
}
diff --git a/arch/frv/include/asm/pci.h b/arch/frv/include/asm/pci.h
index 2035a4d3f9b9..a6d4ed042c70 100644
--- a/arch/frv/include/asm/pci.h
+++ b/arch/frv/include/asm/pci.h
@@ -41,16 +41,6 @@ extern void pci_free_consistent(struct pci_dev *hwdev, size_t size,
/* Return the index of the PCI controller for device PDEV. */
#define pci_controller_num(PDEV) (0)
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- *strat = PCI_DMA_BURST_INFINITY;
- *strategy_parameter = ~0UL;
-}
-#endif
-
/*
* These are pretty much arbitrary with the CoMEM implementation.
* We have the whole address space to ourselves.
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index ec4917ddf678..61d99767fe16 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -19,9 +19,9 @@
#include <linux/kernel.h>
#include <linux/ptrace.h>
#include <linux/hardirq.h>
+#include <linux/uaccess.h>
#include <asm/pgtable.h>
-#include <asm/uaccess.h>
#include <asm/gdb-stub.h>
/*****************************************************************************/
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(__frame))
diff --git a/arch/frv/mm/highmem.c b/arch/frv/mm/highmem.c
index bed9a9bd3c10..785344bbdc07 100644
--- a/arch/frv/mm/highmem.c
+++ b/arch/frv/mm/highmem.c
@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page)
unsigned long paddr;
int type;
+ preempt_disable();
pagefault_disable();
type = kmap_atomic_idx_push();
paddr = page_to_phys(page);
@@ -85,5 +86,6 @@ void __kunmap_atomic(void *kvaddr)
}
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h
index 9e7802911a57..a6e34e2acbba 100644
--- a/arch/hexagon/include/asm/cmpxchg.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -64,7 +64,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
* looks just like atomic_cmpxchg on our arch currently with a bunch of
* variable casting.
*/
-#define __HAVE_ARCH_CMPXCHG 1
#define cmpxchg(ptr, old, new) \
({ \
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index e4127e4d6a5b..f000a382bc7f 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -36,7 +36,8 @@
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 76d25b2cfbbe..42a91a7aa2b0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -137,29 +137,6 @@ config AUDIT_ARCH
bool
default y
-menuconfig PARAVIRT_GUEST
- bool "Paravirtualized guest support"
- depends on BROKEN
- help
- Say Y here to get to see options related to running Linux under
- various hypervisors. This option alone does not add any kernel code.
-
- If you say N, all options in this submenu will be skipped and disabled.
-
-if PARAVIRT_GUEST
-
-config PARAVIRT
- bool "Enable paravirtualization code"
- depends on PARAVIRT_GUEST
- default y
- help
- This changes the kernel so it can modify itself when it is run
- under a hypervisor, potentially improving performance significantly
- over full virtualization. However, when run without a hypervisor
- the kernel is theoretically slower and slightly larger.
-
-endif
-
choice
prompt "System type"
default IA64_GENERIC
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index f6769eb2bbf9..843ba435e43b 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -77,12 +77,7 @@ do { \
___p1; \
})
-/*
- * XXX check on this ---I suspect what Linus really wants here is
- * acquire vs release semantics but we can't discuss this stuff with
- * Linus just yet. Grrr...
- */
-#define set_mb(var, value) do { (var) = (value); mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
/*
* The group barrier in front of the rsm & ssm are necessary to ensure
diff --git a/arch/ia64/include/asm/hw_irq.h b/arch/ia64/include/asm/hw_irq.h
index 668786e84af8..74347ebf7d68 100644
--- a/arch/ia64/include/asm/hw_irq.h
+++ b/arch/ia64/include/asm/hw_irq.h
@@ -15,11 +15,7 @@
#include <asm/ptrace.h>
#include <asm/smp.h>
-#ifndef CONFIG_PARAVIRT
typedef u8 ia64_vector;
-#else
-typedef u16 ia64_vector;
-#endif
/*
* 0 special
@@ -114,15 +110,11 @@ DECLARE_PER_CPU(int[IA64_NUM_VECTORS], vector_irq);
extern struct irq_chip irq_type_ia64_lsapic; /* CPU-internal interrupt controller */
-#ifdef CONFIG_PARAVIRT_GUEST
-#include <asm/paravirt.h>
-#else
#define ia64_register_ipi ia64_native_register_ipi
#define assign_irq_vector ia64_native_assign_irq_vector
#define free_irq_vector ia64_native_free_irq_vector
#define register_percpu_irq ia64_native_register_percpu_irq
#define ia64_resend_irq ia64_native_resend_irq
-#endif
extern void ia64_native_register_ipi(void);
extern int bind_irq_vector(int irq, int vector, cpumask_t domain);
diff --git a/arch/ia64/include/asm/intrinsics.h b/arch/ia64/include/asm/intrinsics.h
index 20477ea111ba..ec970a920132 100644
--- a/arch/ia64/include/asm/intrinsics.h
+++ b/arch/ia64/include/asm/intrinsics.h
@@ -7,19 +7,6 @@
#ifndef _ASM_IA64_INTRINSICS_H
#define _ASM_IA64_INTRINSICS_H
-#include <asm/paravirt_privop.h>
#include <uapi/asm/intrinsics.h>
-#ifndef __ASSEMBLY__
-#if defined(CONFIG_PARAVIRT)
-# undef IA64_INTRINSIC_API
-# undef IA64_INTRINSIC_MACRO
-# ifdef ASM_SUPPORTED
-# define IA64_INTRINSIC_API(name) paravirt_ ## name
-# else
-# define IA64_INTRINSIC_API(name) pv_cpu_ops.name
-# endif
-#define IA64_INTRINSIC_MACRO(name) paravirt_ ## name
-#endif
-#endif /* !__ASSEMBLY__ */
#endif /* _ASM_IA64_INTRINSICS_H */
diff --git a/arch/ia64/include/asm/iosapic.h b/arch/ia64/include/asm/iosapic.h
index 94c89a2d97fe..4ae1fbd7f10e 100644
--- a/arch/ia64/include/asm/iosapic.h
+++ b/arch/ia64/include/asm/iosapic.h
@@ -55,14 +55,10 @@
#define NR_IOSAPICS 256
-#ifdef CONFIG_PARAVIRT_GUEST
-#include <asm/paravirt.h>
-#else
#define iosapic_pcat_compat_init ia64_native_iosapic_pcat_compat_init
#define __iosapic_read __ia64_native_iosapic_read
#define __iosapic_write __ia64_native_iosapic_write
#define iosapic_get_irq_chip ia64_native_iosapic_get_irq_chip
-#endif
extern void __init ia64_native_iosapic_pcat_compat_init(void);
extern struct irq_chip *ia64_native_iosapic_get_irq_chip(unsigned long trigger);
diff --git a/arch/ia64/include/asm/irq_remapping.h b/arch/ia64/include/asm/irq_remapping.h
index e3b3556e2e1b..a8687b1d8906 100644
--- a/arch/ia64/include/asm/irq_remapping.h
+++ b/arch/ia64/include/asm/irq_remapping.h
@@ -1,6 +1,4 @@
#ifndef __IA64_INTR_REMAPPING_H
#define __IA64_INTR_REMAPPING_H
#define irq_remapping_enabled 0
-#define dmar_alloc_hwirq create_irq
-#define dmar_free_hwirq destroy_irq
#endif
diff --git a/arch/ia64/include/asm/module.h b/arch/ia64/include/asm/module.h
index dfba22a872c3..f31894b2a354 100644
--- a/arch/ia64/include/asm/module.h
+++ b/arch/ia64/include/asm/module.h
@@ -18,12 +18,6 @@ struct mod_arch_specific {
struct elf64_shdr *got; /* global offset table */
struct elf64_shdr *opd; /* official procedure descriptors */
struct elf64_shdr *unwind; /* unwind-table section */
-#ifdef CONFIG_PARAVIRT
- struct elf64_shdr *paravirt_bundles;
- /* paravirt_alt_bundle_patch table */
- struct elf64_shdr *paravirt_insts;
- /* paravirt_alt_inst_patch table */
-#endif
unsigned long gp; /* global-pointer for module */
void *core_unw_table; /* core unwind-table cookie returned by unwinder */
diff --git a/arch/ia64/include/asm/native/inst.h b/arch/ia64/include/asm/native/inst.h
index d2d46efb3e6e..7e08f17accd5 100644
--- a/arch/ia64/include/asm/native/inst.h
+++ b/arch/ia64/include/asm/native/inst.h
@@ -22,32 +22,6 @@
#define DO_SAVE_MIN IA64_NATIVE_DO_SAVE_MIN
-#define __paravirt_switch_to ia64_native_switch_to
-#define __paravirt_leave_syscall ia64_native_leave_syscall
-#define __paravirt_work_processed_syscall ia64_native_work_processed_syscall
-#define __paravirt_leave_kernel ia64_native_leave_kernel
-#define __paravirt_pending_syscall_end ia64_work_pending_syscall_end
-#define __paravirt_work_processed_syscall_target \
- ia64_work_processed_syscall
-
-#define paravirt_fsyscall_table ia64_native_fsyscall_table
-#define paravirt_fsys_bubble_down ia64_native_fsys_bubble_down
-
-#ifdef CONFIG_PARAVIRT_GUEST_ASM_CLOBBER_CHECK
-# define PARAVIRT_POISON 0xdeadbeefbaadf00d
-# define CLOBBER(clob) \
- ;; \
- movl clob = PARAVIRT_POISON; \
- ;;
-# define CLOBBER_PRED(pred_clob) \
- ;; \
- cmp.eq pred_clob, p0 = r0, r0 \
- ;;
-#else
-# define CLOBBER(clob) /* nothing */
-# define CLOBBER_PRED(pred_clob) /* nothing */
-#endif
-
#define MOV_FROM_IFA(reg) \
mov reg = cr.ifa
@@ -70,106 +44,76 @@
mov reg = cr.iip
#define MOV_FROM_IVR(reg, clob) \
- mov reg = cr.ivr \
- CLOBBER(clob)
+ mov reg = cr.ivr
#define MOV_FROM_PSR(pred, reg, clob) \
-(pred) mov reg = psr \
- CLOBBER(clob)
+(pred) mov reg = psr
#define MOV_FROM_ITC(pred, pred_clob, reg, clob) \
-(pred) mov reg = ar.itc \
- CLOBBER(clob) \
- CLOBBER_PRED(pred_clob)
+(pred) mov reg = ar.itc
#define MOV_TO_IFA(reg, clob) \
- mov cr.ifa = reg \
- CLOBBER(clob)
+ mov cr.ifa = reg
#define MOV_TO_ITIR(pred, reg, clob) \
-(pred) mov cr.itir = reg \
- CLOBBER(clob)
+(pred) mov cr.itir = reg
#define MOV_TO_IHA(pred, reg, clob) \
-(pred) mov cr.iha = reg \
- CLOBBER(clob)
+(pred) mov cr.iha = reg
#define MOV_TO_IPSR(pred, reg, clob) \
-(pred) mov cr.ipsr = reg \
- CLOBBER(clob)
+(pred) mov cr.ipsr = reg
#define MOV_TO_IFS(pred, reg, clob) \
-(pred) mov cr.ifs = reg \
- CLOBBER(clob)
+(pred) mov cr.ifs = reg
#define MOV_TO_IIP(reg, clob) \
- mov cr.iip = reg \
- CLOBBER(clob)
+ mov cr.iip = reg
#define MOV_TO_KR(kr, reg, clob0, clob1) \
- mov IA64_KR(kr) = reg \
- CLOBBER(clob0) \
- CLOBBER(clob1)
+ mov IA64_KR(kr) = reg
#define ITC_I(pred, reg, clob) \
-(pred) itc.i reg \
- CLOBBER(clob)
+(pred) itc.i reg
#define ITC_D(pred, reg, clob) \
-(pred) itc.d reg \
- CLOBBER(clob)
+(pred) itc.d reg
#define ITC_I_AND_D(pred_i, pred_d, reg, clob) \
(pred_i) itc.i reg; \
-(pred_d) itc.d reg \
- CLOBBER(clob)
+(pred_d) itc.d reg
#define THASH(pred, reg0, reg1, clob) \
-(pred) thash reg0 = reg1 \
- CLOBBER(clob)
+(pred) thash reg0 = reg1
#define SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(clob0, clob1) \
ssm psr.ic | PSR_DEFAULT_BITS \
- CLOBBER(clob0) \
- CLOBBER(clob1) \
;; \
srlz.i /* guarantee that interruption collectin is on */ \
;;
#define SSM_PSR_IC_AND_SRLZ_D(clob0, clob1) \
ssm psr.ic \
- CLOBBER(clob0) \
- CLOBBER(clob1) \
;; \
srlz.d
#define RSM_PSR_IC(clob) \
- rsm psr.ic \
- CLOBBER(clob)
+ rsm psr.ic
#define SSM_PSR_I(pred, pred_clob, clob) \
-(pred) ssm psr.i \
- CLOBBER(clob) \
- CLOBBER_PRED(pred_clob)
+(pred) ssm psr.i
#define RSM_PSR_I(pred, clob0, clob1) \
-(pred) rsm psr.i \
- CLOBBER(clob0) \
- CLOBBER(clob1)
+(pred) rsm psr.i
#define RSM_PSR_I_IC(clob0, clob1, clob2) \
- rsm psr.i | psr.ic \
- CLOBBER(clob0) \
- CLOBBER(clob1) \
- CLOBBER(clob2)
+ rsm psr.i | psr.ic
#define RSM_PSR_DT \
rsm psr.dt
#define RSM_PSR_BE_I(clob0, clob1) \
- rsm psr.be | psr.i \
- CLOBBER(clob0) \
- CLOBBER(clob1)
+ rsm psr.be | psr.i
#define SSM_PSR_DT_AND_SRLZ_I \
ssm psr.dt \
@@ -177,15 +121,10 @@
srlz.i
#define BSW_0(clob0, clob1, clob2) \
- bsw.0 \
- CLOBBER(clob0) \
- CLOBBER(clob1) \
- CLOBBER(clob2)
+ bsw.0
#define BSW_1(clob0, clob1) \
- bsw.1 \
- CLOBBER(clob0) \
- CLOBBER(clob1)
+ bsw.1
#define COVER \
cover
diff --git a/arch/ia64/include/asm/native/pvchk_inst.h b/arch/ia64/include/asm/native/pvchk_inst.h
deleted file mode 100644
index 8d72962ec838..000000000000
--- a/arch/ia64/include/asm/native/pvchk_inst.h
+++ /dev/null
@@ -1,271 +0,0 @@
-#ifndef _ASM_NATIVE_PVCHK_INST_H
-#define _ASM_NATIVE_PVCHK_INST_H
-
-/******************************************************************************
- * arch/ia64/include/asm/native/pvchk_inst.h
- * Checker for paravirtualizations of privileged operations.
- *
- * Copyright (C) 2005 Hewlett-Packard Co
- * Dan Magenheimer <dan.magenheimer@hp.com>
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-/**********************************************
- * Instructions paravirtualized for correctness
- **********************************************/
-
-/* "fc" and "thash" are privilege-sensitive instructions, meaning they
- * may have different semantics depending on whether they are executed
- * at PL0 vs PL!=0. When paravirtualized, these instructions mustn't
- * be allowed to execute directly, lest incorrect semantics result.
- */
-
-#define fc .error "fc should not be used directly."
-#define thash .error "thash should not be used directly."
-
-/* Note that "ttag" and "cover" are also privilege-sensitive; "ttag"
- * is not currently used (though it may be in a long-format VHPT system!)
- * and the semantics of cover only change if psr.ic is off which is very
- * rare (and currently non-existent outside of assembly code
- */
-#define ttag .error "ttag should not be used directly."
-#define cover .error "cover should not be used directly."
-
-/* There are also privilege-sensitive registers. These registers are
- * readable at any privilege level but only writable at PL0.
- */
-#define cpuid .error "cpuid should not be used directly."
-#define pmd .error "pmd should not be used directly."
-
-/*
- * mov ar.eflag =
- * mov = ar.eflag
- */
-
-/**********************************************
- * Instructions paravirtualized for performance
- **********************************************/
-/*
- * Those instructions include '.' which can't be handled by cpp.
- * or can't be handled by cpp easily.
- * They are handled by sed instead of cpp.
- */
-
-/* for .S
- * itc.i
- * itc.d
- *
- * bsw.0
- * bsw.1
- *
- * ssm psr.ic | PSR_DEFAULT_BITS
- * ssm psr.ic
- * rsm psr.ic
- * ssm psr.i
- * rsm psr.i
- * rsm psr.i | psr.ic
- * rsm psr.dt
- * ssm psr.dt
- *
- * mov = cr.ifa
- * mov = cr.itir
- * mov = cr.isr
- * mov = cr.iha
- * mov = cr.ipsr
- * mov = cr.iim
- * mov = cr.iip
- * mov = cr.ivr
- * mov = psr
- *
- * mov cr.ifa =
- * mov cr.itir =
- * mov cr.iha =
- * mov cr.ipsr =
- * mov cr.ifs =
- * mov cr.iip =
- * mov cr.kr =
- */
-
-/* for intrinsics
- * ssm psr.i
- * rsm psr.i
- * mov = psr
- * mov = ivr
- * mov = tpr
- * mov cr.itm =
- * mov eoi =
- * mov rr[] =
- * mov = rr[]
- * mov = kr
- * mov kr =
- * ptc.ga
- */
-
-/*************************************************************
- * define paravirtualized instrcution macros as nop to ingore.
- * and check whether arguments are appropriate.
- *************************************************************/
-
-/* check whether reg is a regular register */
-.macro is_rreg_in reg
- .ifc "\reg", "r0"
- nop 0
- .exitm
- .endif
- ;;
- mov \reg = r0
- ;;
-.endm
-#define IS_RREG_IN(reg) is_rreg_in reg ;
-
-#define IS_RREG_OUT(reg) \
- ;; \
- mov reg = r0 \
- ;;
-
-#define IS_RREG_CLOB(reg) IS_RREG_OUT(reg)
-
-/* check whether pred is a predicate register */
-#define IS_PRED_IN(pred) \
- ;; \
- (pred) nop 0 \
- ;;
-
-#define IS_PRED_OUT(pred) \
- ;; \
- cmp.eq pred, p0 = r0, r0 \
- ;;
-
-#define IS_PRED_CLOB(pred) IS_PRED_OUT(pred)
-
-
-#define DO_SAVE_MIN(__COVER, SAVE_IFS, EXTRA, WORKAROUND) \
- nop 0
-#define MOV_FROM_IFA(reg) \
- IS_RREG_OUT(reg)
-#define MOV_FROM_ITIR(reg) \
- IS_RREG_OUT(reg)
-#define MOV_FROM_ISR(reg) \
- IS_RREG_OUT(reg)
-#define MOV_FROM_IHA(reg) \
- IS_RREG_OUT(reg)
-#define MOV_FROM_IPSR(pred, reg) \
- IS_PRED_IN(pred) \
- IS_RREG_OUT(reg)
-#define MOV_FROM_IIM(reg) \
- IS_RREG_OUT(reg)
-#define MOV_FROM_IIP(reg) \
- IS_RREG_OUT(reg)
-#define MOV_FROM_IVR(reg, clob) \
- IS_RREG_OUT(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_FROM_PSR(pred, reg, clob) \
- IS_PRED_IN(pred) \
- IS_RREG_OUT(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_FROM_ITC(pred, pred_clob, reg, clob) \
- IS_PRED_IN(pred) \
- IS_PRED_CLOB(pred_clob) \
- IS_RREG_OUT(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_TO_IFA(reg, clob) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_TO_ITIR(pred, reg, clob) \
- IS_PRED_IN(pred) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_TO_IHA(pred, reg, clob) \
- IS_PRED_IN(pred) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_TO_IPSR(pred, reg, clob) \
- IS_PRED_IN(pred) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_TO_IFS(pred, reg, clob) \
- IS_PRED_IN(pred) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_TO_IIP(reg, clob) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define MOV_TO_KR(kr, reg, clob0, clob1) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob0) \
- IS_RREG_CLOB(clob1)
-#define ITC_I(pred, reg, clob) \
- IS_PRED_IN(pred) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define ITC_D(pred, reg, clob) \
- IS_PRED_IN(pred) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define ITC_I_AND_D(pred_i, pred_d, reg, clob) \
- IS_PRED_IN(pred_i) \
- IS_PRED_IN(pred_d) \
- IS_RREG_IN(reg) \
- IS_RREG_CLOB(clob)
-#define THASH(pred, reg0, reg1, clob) \
- IS_PRED_IN(pred) \
- IS_RREG_OUT(reg0) \
- IS_RREG_IN(reg1) \
- IS_RREG_CLOB(clob)
-#define SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(clob0, clob1) \
- IS_RREG_CLOB(clob0) \
- IS_RREG_CLOB(clob1)
-#define SSM_PSR_IC_AND_SRLZ_D(clob0, clob1) \
- IS_RREG_CLOB(clob0) \
- IS_RREG_CLOB(clob1)
-#define RSM_PSR_IC(clob) \
- IS_RREG_CLOB(clob)
-#define SSM_PSR_I(pred, pred_clob, clob) \
- IS_PRED_IN(pred) \
- IS_PRED_CLOB(pred_clob) \
- IS_RREG_CLOB(clob)
-#define RSM_PSR_I(pred, clob0, clob1) \
- IS_PRED_IN(pred) \
- IS_RREG_CLOB(clob0) \
- IS_RREG_CLOB(clob1)
-#define RSM_PSR_I_IC(clob0, clob1, clob2) \
- IS_RREG_CLOB(clob0) \
- IS_RREG_CLOB(clob1) \
- IS_RREG_CLOB(clob2)
-#define RSM_PSR_DT \
- nop 0
-#define RSM_PSR_BE_I(clob0, clob1) \
- IS_RREG_CLOB(clob0) \
- IS_RREG_CLOB(clob1)
-#define SSM_PSR_DT_AND_SRLZ_I \
- nop 0
-#define BSW_0(clob0, clob1, clob2) \
- IS_RREG_CLOB(clob0) \
- IS_RREG_CLOB(clob1) \
- IS_RREG_CLOB(clob2)
-#define BSW_1(clob0, clob1) \
- IS_RREG_CLOB(clob0) \
- IS_RREG_CLOB(clob1)
-#define COVER \
- nop 0
-#define RFI \
- br.ret.sptk.many rp /* defining nop causes dependency error */
-
-#endif /* _ASM_NATIVE_PVCHK_INST_H */
diff --git a/arch/ia64/include/asm/paravirt.h b/arch/ia64/include/asm/paravirt.h
deleted file mode 100644
index b53518a98026..000000000000
--- a/arch/ia64/include/asm/paravirt.h
+++ /dev/null
@@ -1,321 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-
-#ifndef __ASM_PARAVIRT_H
-#define __ASM_PARAVIRT_H
-
-#ifndef __ASSEMBLY__
-/******************************************************************************
- * fsys related addresses
- */
-struct pv_fsys_data {
- unsigned long *fsyscall_table;
- void *fsys_bubble_down;
-};
-
-extern struct pv_fsys_data pv_fsys_data;
-
-unsigned long *paravirt_get_fsyscall_table(void);
-char *paravirt_get_fsys_bubble_down(void);
-
-/******************************************************************************
- * patchlist addresses for gate page
- */
-enum pv_gate_patchlist {
- PV_GATE_START_FSYSCALL,
- PV_GATE_END_FSYSCALL,
-
- PV_GATE_START_BRL_FSYS_BUBBLE_DOWN,
- PV_GATE_END_BRL_FSYS_BUBBLE_DOWN,
-
- PV_GATE_START_VTOP,
- PV_GATE_END_VTOP,
-
- PV_GATE_START_MCKINLEY_E9,
- PV_GATE_END_MCKINLEY_E9,
-};
-
-struct pv_patchdata {
- unsigned long start_fsyscall_patchlist;
- unsigned long end_fsyscall_patchlist;
- unsigned long start_brl_fsys_bubble_down_patchlist;
- unsigned long end_brl_fsys_bubble_down_patchlist;
- unsigned long start_vtop_patchlist;
- unsigned long end_vtop_patchlist;
- unsigned long start_mckinley_e9_patchlist;
- unsigned long end_mckinley_e9_patchlist;
-
- void *gate_section;
-};
-
-extern struct pv_patchdata pv_patchdata;
-
-unsigned long paravirt_get_gate_patchlist(enum pv_gate_patchlist type);
-void *paravirt_get_gate_section(void);
-#endif
-
-#ifdef CONFIG_PARAVIRT_GUEST
-
-#define PARAVIRT_HYPERVISOR_TYPE_DEFAULT 0
-
-#ifndef __ASSEMBLY__
-
-#include <asm/hw_irq.h>
-#include <asm/meminit.h>
-
-/******************************************************************************
- * general info
- */
-struct pv_info {
- unsigned int kernel_rpl;
- int paravirt_enabled;
- const char *name;
-};
-
-extern struct pv_info pv_info;
-
-static inline int paravirt_enabled(void)
-{
- return pv_info.paravirt_enabled;
-}
-
-static inline unsigned int get_kernel_rpl(void)
-{
- return pv_info.kernel_rpl;
-}
-
-/******************************************************************************
- * initialization hooks.
- */
-struct rsvd_region;
-
-struct pv_init_ops {
- void (*banner)(void);
-
- int (*reserve_memory)(struct rsvd_region *region);
-
- void (*arch_setup_early)(void);
- void (*arch_setup_console)(char **cmdline_p);
- int (*arch_setup_nomca)(void);
-
- void (*post_smp_prepare_boot_cpu)(void);
-
-#ifdef ASM_SUPPORTED
- unsigned long (*patch_bundle)(void *sbundle, void *ebundle,
- unsigned long type);
- unsigned long (*patch_inst)(unsigned long stag, unsigned long etag,
- unsigned long type);
-#endif
- void (*patch_branch)(unsigned long tag, unsigned long type);
-};
-
-extern struct pv_init_ops pv_init_ops;
-
-static inline void paravirt_banner(void)
-{
- if (pv_init_ops.banner)
- pv_init_ops.banner();
-}
-
-static inline int paravirt_reserve_memory(struct rsvd_region *region)
-{
- if (pv_init_ops.reserve_memory)
- return pv_init_ops.reserve_memory(region);
- return 0;
-}
-
-static inline void paravirt_arch_setup_early(void)
-{
- if (pv_init_ops.arch_setup_early)
- pv_init_ops.arch_setup_early();
-}
-
-static inline void paravirt_arch_setup_console(char **cmdline_p)
-{
- if (pv_init_ops.arch_setup_console)
- pv_init_ops.arch_setup_console(cmdline_p);
-}
-
-static inline int paravirt_arch_setup_nomca(void)
-{
- if (pv_init_ops.arch_setup_nomca)
- return pv_init_ops.arch_setup_nomca();
- return 0;
-}
-
-static inline void paravirt_post_smp_prepare_boot_cpu(void)
-{
- if (pv_init_ops.post_smp_prepare_boot_cpu)
- pv_init_ops.post_smp_prepare_boot_cpu();
-}
-
-/******************************************************************************
- * replacement of iosapic operations.
- */
-
-struct pv_iosapic_ops {
- void (*pcat_compat_init)(void);
-
- struct irq_chip *(*__get_irq_chip)(unsigned long trigger);
-
- unsigned int (*__read)(char __iomem *iosapic, unsigned int reg);
- void (*__write)(char __iomem *iosapic, unsigned int reg, u32 val);
-};
-
-extern struct pv_iosapic_ops pv_iosapic_ops;
-
-static inline void
-iosapic_pcat_compat_init(void)
-{
- if (pv_iosapic_ops.pcat_compat_init)
- pv_iosapic_ops.pcat_compat_init();
-}
-
-static inline struct irq_chip*
-iosapic_get_irq_chip(unsigned long trigger)
-{
- return pv_iosapic_ops.__get_irq_chip(trigger);
-}
-
-static inline unsigned int
-__iosapic_read(char __iomem *iosapic, unsigned int reg)
-{
- return pv_iosapic_ops.__read(iosapic, reg);
-}
-
-static inline void
-__iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
-{
- return pv_iosapic_ops.__write(iosapic, reg, val);
-}
-
-/******************************************************************************
- * replacement of irq operations.
- */
-
-struct pv_irq_ops {
- void (*register_ipi)(void);
-
- int (*assign_irq_vector)(int irq);
- void (*free_irq_vector)(int vector);
-
- void (*register_percpu_irq)(ia64_vector vec,
- struct irqaction *action);
-
- void (*resend_irq)(unsigned int vector);
-};
-
-extern struct pv_irq_ops pv_irq_ops;
-
-static inline void
-ia64_register_ipi(void)
-{
- pv_irq_ops.register_ipi();
-}
-
-static inline int
-assign_irq_vector(int irq)
-{
- return pv_irq_ops.assign_irq_vector(irq);
-}
-
-static inline void
-free_irq_vector(int vector)
-{
- return pv_irq_ops.free_irq_vector(vector);
-}
-
-static inline void
-register_percpu_irq(ia64_vector vec, struct irqaction *action)
-{
- pv_irq_ops.register_percpu_irq(vec, action);
-}
-
-static inline void
-ia64_resend_irq(unsigned int vector)
-{
- pv_irq_ops.resend_irq(vector);
-}
-
-/******************************************************************************
- * replacement of time operations.
- */
-
-extern struct itc_jitter_data_t itc_jitter_data;
-extern volatile int time_keeper_id;
-
-struct pv_time_ops {
- void (*init_missing_ticks_accounting)(int cpu);
- int (*do_steal_accounting)(unsigned long *new_itm);
-
- void (*clocksource_resume)(void);
-
- unsigned long long (*sched_clock)(void);
-};
-
-extern struct pv_time_ops pv_time_ops;
-
-static inline void
-paravirt_init_missing_ticks_accounting(int cpu)
-{
- if (pv_time_ops.init_missing_ticks_accounting)
- pv_time_ops.init_missing_ticks_accounting(cpu);
-}
-
-struct static_key;
-extern struct static_key paravirt_steal_enabled;
-extern struct static_key paravirt_steal_rq_enabled;
-
-static inline int
-paravirt_do_steal_accounting(unsigned long *new_itm)
-{
- return pv_time_ops.do_steal_accounting(new_itm);
-}
-
-static inline unsigned long long paravirt_sched_clock(void)
-{
- return pv_time_ops.sched_clock();
-}
-
-#endif /* !__ASSEMBLY__ */
-
-#else
-/* fallback for native case */
-
-#ifndef __ASSEMBLY__
-
-#define paravirt_banner() do { } while (0)
-#define paravirt_reserve_memory(region) 0
-
-#define paravirt_arch_setup_early() do { } while (0)
-#define paravirt_arch_setup_console(cmdline_p) do { } while (0)
-#define paravirt_arch_setup_nomca() 0
-#define paravirt_post_smp_prepare_boot_cpu() do { } while (0)
-
-#define paravirt_init_missing_ticks_accounting(cpu) do { } while (0)
-#define paravirt_do_steal_accounting(new_itm) 0
-
-#endif /* __ASSEMBLY__ */
-
-
-#endif /* CONFIG_PARAVIRT_GUEST */
-
-#endif /* __ASM_PARAVIRT_H */
diff --git a/arch/ia64/include/asm/paravirt_patch.h b/arch/ia64/include/asm/paravirt_patch.h
deleted file mode 100644
index 128ff5db6e67..000000000000
--- a/arch/ia64/include/asm/paravirt_patch.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#ifndef __ASM_PARAVIRT_PATCH_H
-#define __ASM_PARAVIRT_PATCH_H
-
-#ifdef __ASSEMBLY__
-
- .section .paravirt_branches, "a"
- .previous
-#define PARAVIRT_PATCH_SITE_BR(type) \
- { \
- [1:] ; \
- br.cond.sptk.many 2f ; \
- nop.b 0 ; \
- nop.b 0;; ; \
- } ; \
- 2: \
- .xdata8 ".paravirt_branches", 1b, type
-
-#else
-
-#include <linux/stringify.h>
-#include <asm/intrinsics.h>
-
-/* for binary patch */
-struct paravirt_patch_site_bundle {
- void *sbundle;
- void *ebundle;
- unsigned long type;
-};
-
-/* label means the beginning of new bundle */
-#define paravirt_alt_bundle(instr, privop) \
- "\t998:\n" \
- "\t" instr "\n" \
- "\t999:\n" \
- "\t.pushsection .paravirt_bundles, \"a\"\n" \
- "\t.popsection\n" \
- "\t.xdata8 \".paravirt_bundles\", 998b, 999b, " \
- __stringify(privop) "\n"
-
-
-struct paravirt_patch_bundle_elem {
- const void *sbundle;
- const void *ebundle;
- unsigned long type;
-};
-
-
-struct paravirt_patch_site_inst {
- unsigned long stag;
- unsigned long etag;
- unsigned long type;
-};
-
-#define paravirt_alt_inst(instr, privop) \
- "\t[998:]\n" \
- "\t" instr "\n" \
- "\t[999:]\n" \
- "\t.pushsection .paravirt_insts, \"a\"\n" \
- "\t.popsection\n" \
- "\t.xdata8 \".paravirt_insts\", 998b, 999b, " \
- __stringify(privop) "\n"
-
-struct paravirt_patch_site_branch {
- unsigned long tag;
- unsigned long type;
-};
-
-struct paravirt_patch_branch_target {
- const void *entry;
- unsigned long type;
-};
-
-void
-__paravirt_patch_apply_branch(
- unsigned long tag, unsigned long type,
- const struct paravirt_patch_branch_target *entries,
- unsigned int nr_entries);
-
-void
-paravirt_patch_reloc_br(unsigned long tag, const void *target);
-
-void
-paravirt_patch_reloc_brl(unsigned long tag, const void *target);
-
-
-#if defined(ASM_SUPPORTED) && defined(CONFIG_PARAVIRT)
-unsigned long
-ia64_native_patch_bundle(void *sbundle, void *ebundle, unsigned long type);
-
-unsigned long
-__paravirt_patch_apply_bundle(void *sbundle, void *ebundle, unsigned long type,
- const struct paravirt_patch_bundle_elem *elems,
- unsigned long nelems,
- const struct paravirt_patch_bundle_elem **found);
-
-void
-paravirt_patch_apply_bundle(const struct paravirt_patch_site_bundle *start,
- const struct paravirt_patch_site_bundle *end);
-
-void
-paravirt_patch_apply_inst(const struct paravirt_patch_site_inst *start,
- const struct paravirt_patch_site_inst *end);
-
-void paravirt_patch_apply(void);
-#else
-#define paravirt_patch_apply_bundle(start, end) do { } while (0)
-#define paravirt_patch_apply_inst(start, end) do { } while (0)
-#define paravirt_patch_apply() do { } while (0)
-#endif
-
-#endif /* !__ASSEMBLEY__ */
-
-#endif /* __ASM_PARAVIRT_PATCH_H */
-
-/*
- * Local variables:
- * mode: C
- * c-set-style: "linux"
- * c-basic-offset: 8
- * tab-width: 8
- * indent-tabs-mode: t
- * End:
- */
diff --git a/arch/ia64/include/asm/paravirt_privop.h b/arch/ia64/include/asm/paravirt_privop.h
deleted file mode 100644
index 8f6cb11c9fae..000000000000
--- a/arch/ia64/include/asm/paravirt_privop.h
+++ /dev/null
@@ -1,479 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#ifndef _ASM_IA64_PARAVIRT_PRIVOP_H
-#define _ASM_IA64_PARAVIRT_PRIVOP_H
-
-#ifdef CONFIG_PARAVIRT
-
-#ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-#include <asm/kregs.h> /* for IA64_PSR_I */
-
-/******************************************************************************
- * replacement of intrinsics operations.
- */
-
-struct pv_cpu_ops {
- void (*fc)(void *addr);
- unsigned long (*thash)(unsigned long addr);
- unsigned long (*get_cpuid)(int index);
- unsigned long (*get_pmd)(int index);
- unsigned long (*getreg)(int reg);
- void (*setreg)(int reg, unsigned long val);
- void (*ptcga)(unsigned long addr, unsigned long size);
- unsigned long (*get_rr)(unsigned long index);
- void (*set_rr)(unsigned long index, unsigned long val);
- void (*set_rr0_to_rr4)(unsigned long val0, unsigned long val1,
- unsigned long val2, unsigned long val3,
- unsigned long val4);
- void (*ssm_i)(void);
- void (*rsm_i)(void);
- unsigned long (*get_psr_i)(void);
- void (*intrin_local_irq_restore)(unsigned long flags);
-};
-
-extern struct pv_cpu_ops pv_cpu_ops;
-
-extern void ia64_native_setreg_func(int regnum, unsigned long val);
-extern unsigned long ia64_native_getreg_func(int regnum);
-
-/************************************************/
-/* Instructions paravirtualized for performance */
-/************************************************/
-
-#ifndef ASM_SUPPORTED
-#define paravirt_ssm_i() pv_cpu_ops.ssm_i()
-#define paravirt_rsm_i() pv_cpu_ops.rsm_i()
-#define __paravirt_getreg() pv_cpu_ops.getreg()
-#endif
-
-/* mask for ia64_native_ssm/rsm() must be constant.("i" constraing).
- * static inline function doesn't satisfy it. */
-#define paravirt_ssm(mask) \
- do { \
- if ((mask) == IA64_PSR_I) \
- paravirt_ssm_i(); \
- else \
- ia64_native_ssm(mask); \
- } while (0)
-
-#define paravirt_rsm(mask) \
- do { \
- if ((mask) == IA64_PSR_I) \
- paravirt_rsm_i(); \
- else \
- ia64_native_rsm(mask); \
- } while (0)
-
-/* returned ip value should be the one in the caller,
- * not in __paravirt_getreg() */
-#define paravirt_getreg(reg) \
- ({ \
- unsigned long res; \
- if ((reg) == _IA64_REG_IP) \
- res = ia64_native_getreg(_IA64_REG_IP); \
- else \
- res = __paravirt_getreg(reg); \
- res; \
- })
-
-/******************************************************************************
- * replacement of hand written assembly codes.
- */
-struct pv_cpu_asm_switch {
- unsigned long switch_to;
- unsigned long leave_syscall;
- unsigned long work_processed_syscall;
- unsigned long leave_kernel;
-};
-void paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch);
-
-#endif /* __ASSEMBLY__ */
-
-#define IA64_PARAVIRT_ASM_FUNC(name) paravirt_ ## name
-
-#else
-
-/* fallback for native case */
-#define IA64_PARAVIRT_ASM_FUNC(name) ia64_native_ ## name
-
-#endif /* CONFIG_PARAVIRT */
-
-#if defined(CONFIG_PARAVIRT) && defined(ASM_SUPPORTED)
-#define paravirt_dv_serialize_data() ia64_dv_serialize_data()
-#else
-#define paravirt_dv_serialize_data() /* nothing */
-#endif
-
-/* these routines utilize privilege-sensitive or performance-sensitive
- * privileged instructions so the code must be replaced with
- * paravirtualized versions */
-#define ia64_switch_to IA64_PARAVIRT_ASM_FUNC(switch_to)
-#define ia64_leave_syscall IA64_PARAVIRT_ASM_FUNC(leave_syscall)
-#define ia64_work_processed_syscall \
- IA64_PARAVIRT_ASM_FUNC(work_processed_syscall)
-#define ia64_leave_kernel IA64_PARAVIRT_ASM_FUNC(leave_kernel)
-
-
-#if defined(CONFIG_PARAVIRT)
-/******************************************************************************
- * binary patching infrastructure
- */
-#define PARAVIRT_PATCH_TYPE_FC 1
-#define PARAVIRT_PATCH_TYPE_THASH 2
-#define PARAVIRT_PATCH_TYPE_GET_CPUID 3
-#define PARAVIRT_PATCH_TYPE_GET_PMD 4
-#define PARAVIRT_PATCH_TYPE_PTCGA 5
-#define PARAVIRT_PATCH_TYPE_GET_RR 6
-#define PARAVIRT_PATCH_TYPE_SET_RR 7
-#define PARAVIRT_PATCH_TYPE_SET_RR0_TO_RR4 8
-#define PARAVIRT_PATCH_TYPE_SSM_I 9
-#define PARAVIRT_PATCH_TYPE_RSM_I 10
-#define PARAVIRT_PATCH_TYPE_GET_PSR_I 11
-#define PARAVIRT_PATCH_TYPE_INTRIN_LOCAL_IRQ_RESTORE 12
-
-/* PARAVIRT_PATY_TYPE_[GS]ETREG + _IA64_REG_xxx */
-#define PARAVIRT_PATCH_TYPE_GETREG 0x10000000
-#define PARAVIRT_PATCH_TYPE_SETREG 0x20000000
-
-/*
- * struct task_struct* (*ia64_switch_to)(void* next_task);
- * void *ia64_leave_syscall;
- * void *ia64_work_processed_syscall
- * void *ia64_leave_kernel;
- */
-
-#define PARAVIRT_PATCH_TYPE_BR_START 0x30000000
-#define PARAVIRT_PATCH_TYPE_BR_SWITCH_TO \
- (PARAVIRT_PATCH_TYPE_BR_START + 0)
-#define PARAVIRT_PATCH_TYPE_BR_LEAVE_SYSCALL \
- (PARAVIRT_PATCH_TYPE_BR_START + 1)
-#define PARAVIRT_PATCH_TYPE_BR_WORK_PROCESSED_SYSCALL \
- (PARAVIRT_PATCH_TYPE_BR_START + 2)
-#define PARAVIRT_PATCH_TYPE_BR_LEAVE_KERNEL \
- (PARAVIRT_PATCH_TYPE_BR_START + 3)
-
-#ifdef ASM_SUPPORTED
-#include <asm/paravirt_patch.h>
-
-/*
- * pv_cpu_ops calling stub.
- * normal function call convension can't be written by gcc
- * inline assembly.
- *
- * from the caller's point of view,
- * the following registers will be clobbered.
- * r2, r3
- * r8-r15
- * r16, r17
- * b6, b7
- * p6-p15
- * ar.ccv
- *
- * from the callee's point of view ,
- * the following registers can be used.
- * r2, r3: scratch
- * r8: scratch, input argument0 and return value
- * r0-r15: scratch, input argument1-5
- * b6: return pointer
- * b7: scratch
- * p6-p15: scratch
- * ar.ccv: scratch
- *
- * other registers must not be changed. especially
- * b0: rp: preserved. gcc ignores b0 in clobbered register.
- * r16: saved gp
- */
-/* 5 bundles */
-#define __PARAVIRT_BR \
- ";;\n" \
- "{ .mlx\n" \
- "nop 0\n" \
- "movl r2 = %[op_addr]\n"/* get function pointer address */ \
- ";;\n" \
- "}\n" \
- "1:\n" \
- "{ .mii\n" \
- "ld8 r2 = [r2]\n" /* load function descriptor address */ \
- "mov r17 = ip\n" /* get ip to calc return address */ \
- "mov r16 = gp\n" /* save gp */ \
- ";;\n" \
- "}\n" \
- "{ .mii\n" \
- "ld8 r3 = [r2], 8\n" /* load entry address */ \
- "adds r17 = 1f - 1b, r17\n" /* calculate return address */ \
- ";;\n" \
- "mov b7 = r3\n" /* set entry address */ \
- "}\n" \
- "{ .mib\n" \
- "ld8 gp = [r2]\n" /* load gp value */ \
- "mov b6 = r17\n" /* set return address */ \
- "br.cond.sptk.few b7\n" /* intrinsics are very short isns */ \
- "}\n" \
- "1:\n" \
- "{ .mii\n" \
- "mov gp = r16\n" /* restore gp value */ \
- "nop 0\n" \
- "nop 0\n" \
- ";;\n" \
- "}\n"
-
-#define PARAVIRT_OP(op) \
- [op_addr] "i"(&pv_cpu_ops.op)
-
-#define PARAVIRT_TYPE(type) \
- PARAVIRT_PATCH_TYPE_ ## type
-
-#define PARAVIRT_REG_CLOBBERS0 \
- "r2", "r3", /*"r8",*/ "r9", "r10", "r11", "r14", \
- "r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS1 \
- "r2","r3", /*"r8",*/ "r9", "r10", "r11", "r14", \
- "r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS2 \
- "r2", "r3", /*"r8", "r9",*/ "r10", "r11", "r14", \
- "r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS5 \
- "r2", "r3", /*"r8", "r9", "r10", "r11", "r14",*/ \
- "r15", "r16", "r17"
-
-#define PARAVIRT_BR_CLOBBERS \
- "b6", "b7"
-
-#define PARAVIRT_PR_CLOBBERS \
- "p6", "p7", "p8", "p9", "p10", "p11", "p12", "p13", "p14", "p15"
-
-#define PARAVIRT_AR_CLOBBERS \
- "ar.ccv"
-
-#define PARAVIRT_CLOBBERS0 \
- PARAVIRT_REG_CLOBBERS0, \
- PARAVIRT_BR_CLOBBERS, \
- PARAVIRT_PR_CLOBBERS, \
- PARAVIRT_AR_CLOBBERS, \
- "memory"
-
-#define PARAVIRT_CLOBBERS1 \
- PARAVIRT_REG_CLOBBERS1, \
- PARAVIRT_BR_CLOBBERS, \
- PARAVIRT_PR_CLOBBERS, \
- PARAVIRT_AR_CLOBBERS, \
- "memory"
-
-#define PARAVIRT_CLOBBERS2 \
- PARAVIRT_REG_CLOBBERS2, \
- PARAVIRT_BR_CLOBBERS, \
- PARAVIRT_PR_CLOBBERS, \
- PARAVIRT_AR_CLOBBERS, \
- "memory"
-
-#define PARAVIRT_CLOBBERS5 \
- PARAVIRT_REG_CLOBBERS5, \
- PARAVIRT_BR_CLOBBERS, \
- PARAVIRT_PR_CLOBBERS, \
- PARAVIRT_AR_CLOBBERS, \
- "memory"
-
-#define PARAVIRT_BR0(op, type) \
- register unsigned long ia64_clobber asm ("r8"); \
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR, \
- PARAVIRT_TYPE(type)) \
- : "=r"(ia64_clobber) \
- : PARAVIRT_OP(op) \
- : PARAVIRT_CLOBBERS0)
-
-#define PARAVIRT_BR0_RET(op, type) \
- register unsigned long ia64_intri_res asm ("r8"); \
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR, \
- PARAVIRT_TYPE(type)) \
- : "=r"(ia64_intri_res) \
- : PARAVIRT_OP(op) \
- : PARAVIRT_CLOBBERS0)
-
-#define PARAVIRT_BR1(op, type, arg1) \
- register unsigned long __##arg1 asm ("r8") = arg1; \
- register unsigned long ia64_clobber asm ("r8"); \
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR, \
- PARAVIRT_TYPE(type)) \
- : "=r"(ia64_clobber) \
- : PARAVIRT_OP(op), "0"(__##arg1) \
- : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR1_RET(op, type, arg1) \
- register unsigned long ia64_intri_res asm ("r8"); \
- register unsigned long __##arg1 asm ("r8") = arg1; \
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR, \
- PARAVIRT_TYPE(type)) \
- : "=r"(ia64_intri_res) \
- : PARAVIRT_OP(op), "0"(__##arg1) \
- : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR1_VOID(op, type, arg1) \
- register void *__##arg1 asm ("r8") = arg1; \
- register unsigned long ia64_clobber asm ("r8"); \
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR, \
- PARAVIRT_TYPE(type)) \
- : "=r"(ia64_clobber) \
- : PARAVIRT_OP(op), "0"(__##arg1) \
- : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR2(op, type, arg1, arg2) \
- register unsigned long __##arg1 asm ("r8") = arg1; \
- register unsigned long __##arg2 asm ("r9") = arg2; \
- register unsigned long ia64_clobber1 asm ("r8"); \
- register unsigned long ia64_clobber2 asm ("r9"); \
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR, \
- PARAVIRT_TYPE(type)) \
- : "=r"(ia64_clobber1), "=r"(ia64_clobber2) \
- : PARAVIRT_OP(op), "0"(__##arg1), "1"(__##arg2) \
- : PARAVIRT_CLOBBERS2)
-
-
-#define PARAVIRT_DEFINE_CPU_OP0(op, type) \
- static inline void \
- paravirt_ ## op (void) \
- { \
- PARAVIRT_BR0(op, type); \
- }
-
-#define PARAVIRT_DEFINE_CPU_OP0_RET(op, type) \
- static inline unsigned long \
- paravirt_ ## op (void) \
- { \
- PARAVIRT_BR0_RET(op, type); \
- return ia64_intri_res; \
- }
-
-#define PARAVIRT_DEFINE_CPU_OP1_VOID(op, type) \
- static inline void \
- paravirt_ ## op (void *arg1) \
- { \
- PARAVIRT_BR1_VOID(op, type, arg1); \
- }
-
-#define PARAVIRT_DEFINE_CPU_OP1(op, type) \
- static inline void \
- paravirt_ ## op (unsigned long arg1) \
- { \
- PARAVIRT_BR1(op, type, arg1); \
- }
-
-#define PARAVIRT_DEFINE_CPU_OP1_RET(op, type) \
- static inline unsigned long \
- paravirt_ ## op (unsigned long arg1) \
- { \
- PARAVIRT_BR1_RET(op, type, arg1); \
- return ia64_intri_res; \
- }
-
-#define PARAVIRT_DEFINE_CPU_OP2(op, type) \
- static inline void \
- paravirt_ ## op (unsigned long arg1, \
- unsigned long arg2) \
- { \
- PARAVIRT_BR2(op, type, arg1, arg2); \
- }
-
-
-PARAVIRT_DEFINE_CPU_OP1_VOID(fc, FC);
-PARAVIRT_DEFINE_CPU_OP1_RET(thash, THASH)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_cpuid, GET_CPUID)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_pmd, GET_PMD)
-PARAVIRT_DEFINE_CPU_OP2(ptcga, PTCGA)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_rr, GET_RR)
-PARAVIRT_DEFINE_CPU_OP2(set_rr, SET_RR)
-PARAVIRT_DEFINE_CPU_OP0(ssm_i, SSM_I)
-PARAVIRT_DEFINE_CPU_OP0(rsm_i, RSM_I)
-PARAVIRT_DEFINE_CPU_OP0_RET(get_psr_i, GET_PSR_I)
-PARAVIRT_DEFINE_CPU_OP1(intrin_local_irq_restore, INTRIN_LOCAL_IRQ_RESTORE)
-
-static inline void
-paravirt_set_rr0_to_rr4(unsigned long val0, unsigned long val1,
- unsigned long val2, unsigned long val3,
- unsigned long val4)
-{
- register unsigned long __val0 asm ("r8") = val0;
- register unsigned long __val1 asm ("r9") = val1;
- register unsigned long __val2 asm ("r10") = val2;
- register unsigned long __val3 asm ("r11") = val3;
- register unsigned long __val4 asm ("r14") = val4;
-
- register unsigned long ia64_clobber0 asm ("r8");
- register unsigned long ia64_clobber1 asm ("r9");
- register unsigned long ia64_clobber2 asm ("r10");
- register unsigned long ia64_clobber3 asm ("r11");
- register unsigned long ia64_clobber4 asm ("r14");
-
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,
- PARAVIRT_TYPE(SET_RR0_TO_RR4))
- : "=r"(ia64_clobber0),
- "=r"(ia64_clobber1),
- "=r"(ia64_clobber2),
- "=r"(ia64_clobber3),
- "=r"(ia64_clobber4)
- : PARAVIRT_OP(set_rr0_to_rr4),
- "0"(__val0), "1"(__val1), "2"(__val2),
- "3"(__val3), "4"(__val4)
- : PARAVIRT_CLOBBERS5);
-}
-
-/* unsigned long paravirt_getreg(int reg) */
-#define __paravirt_getreg(reg) \
- ({ \
- register unsigned long ia64_intri_res asm ("r8"); \
- register unsigned long __reg asm ("r8") = (reg); \
- \
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR, \
- PARAVIRT_TYPE(GETREG) \
- + (reg)) \
- : "=r"(ia64_intri_res) \
- : PARAVIRT_OP(getreg), "0"(__reg) \
- : PARAVIRT_CLOBBERS1); \
- \
- ia64_intri_res; \
- })
-
-/* void paravirt_setreg(int reg, unsigned long val) */
-#define paravirt_setreg(reg, val) \
- do { \
- register unsigned long __val asm ("r8") = val; \
- register unsigned long __reg asm ("r9") = reg; \
- register unsigned long ia64_clobber1 asm ("r8"); \
- register unsigned long ia64_clobber2 asm ("r9"); \
- \
- asm volatile (paravirt_alt_bundle(__PARAVIRT_BR, \
- PARAVIRT_TYPE(SETREG) \
- + (reg)) \
- : "=r"(ia64_clobber1), \
- "=r"(ia64_clobber2) \
- : PARAVIRT_OP(setreg), \
- "1"(__reg), "0"(__val) \
- : PARAVIRT_CLOBBERS2); \
- } while (0)
-
-#endif /* ASM_SUPPORTED */
-#endif /* CONFIG_PARAVIRT && ASM_SUPPOTED */
-
-#endif /* _ASM_IA64_PARAVIRT_PRIVOP_H */
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index 52af5ed9f60b..b897fae1f0ca 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -52,25 +52,6 @@ extern unsigned long ia64_max_iommu_merge_mask;
#include <asm-generic/pci-dma-compat.h>
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- unsigned long cacheline_size;
- u8 byte;
-
- pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
- if (byte == 0)
- cacheline_size = 1024;
- else
- cacheline_size = (int) byte * 4;
-
- *strat = PCI_DMA_BURST_MULTIPLE;
- *strategy_parameter = cacheline_size;
-}
-#endif
-
#define HAVE_PCI_MMAP
extern int pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
enum pci_mmap_state mmap_state, int write_combine);
@@ -108,19 +89,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
return (pci_domain_nr(bus) != 0);
}
-static inline struct resource *
-pcibios_select_root(struct pci_dev *pdev, struct resource *res)
-{
- struct resource *root = NULL;
-
- if (res->flags & IORESOURCE_IO)
- root = &ioport_resource;
- if (res->flags & IORESOURCE_MEM)
- root = &iomem_resource;
-
- return root;
-}
-
#define HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ
static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
{
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 6437ca21f61b..3ad8f6988363 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -53,7 +53,7 @@ void build_cpu_to_node_map(void);
#define topology_physical_package_id(cpu) (cpu_data(cpu)->socket_id)
#define topology_core_id(cpu) (cpu_data(cpu)->core_id)
#define topology_core_cpumask(cpu) (&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
#endif
extern void arch_fix_phys_package_id(int num, u32 slot);
diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h
index f35109b1d907..a0e3620f8f13 100644
--- a/arch/ia64/include/uapi/asm/cmpxchg.h
+++ b/arch/ia64/include/uapi/asm/cmpxchg.h
@@ -61,8 +61,6 @@ extern void ia64_xchg_called_with_bad_pointer(void);
* indicated by comparing RETURN with OLD.
*/
-#define __HAVE_ARCH_CMPXCHG 1
-
/*
* This function doesn't exist, so you'll get a linker error
* if something tries to do an invalid cmpxchg().
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index d68b5cf81e31..3686d6abafde 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -9,7 +9,7 @@ endif
extra-y := head.o init_task.o vmlinux.lds
obj-y := entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \
- irq_lsapic.o ivt.o machvec.o pal.o paravirt_patchlist.o patch.o process.o perfmon.o ptrace.o sal.o \
+ irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o \
salinfo.o setup.o signal.o sys_ia64.o time.o traps.o unaligned.o \
unwind.o mca.o mca_asm.o topology.o dma-mapping.o
@@ -35,9 +35,6 @@ mca_recovery-y += mca_drv.o mca_drv_asm.o
obj-$(CONFIG_IA64_MC_ERR_INJECT)+= err_inject.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
-obj-$(CONFIG_PARAVIRT) += paravirt.o paravirtentry.o \
- paravirt_patch.o
-
obj-$(CONFIG_IA64_ESI) += esi.o
ifneq ($(CONFIG_IA64_ESI),)
obj-y += esi_stub.o # must be in kernel proper
@@ -52,8 +49,6 @@ CFLAGS_traps.o += -mfixed-range=f2-f5,f16-f31
# The gate DSO image is built using a special linker script.
include $(src)/Makefile.gate
-# tell compiled for native
-CPPFLAGS_gate.lds += -D__IA64_GATE_PARAVIRTUALIZED_NATIVE
# Calculate NR_IRQ = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, ...) based on config
define sed-y
@@ -84,30 +79,3 @@ arch/$(SRCARCH)/kernel/nr-irqs.s: arch/$(SRCARCH)/kernel/nr-irqs.c
include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
$(Q)mkdir -p $(dir $@)
$(call cmd,nr_irqs)
-
-#
-# native ivt.S, entry.S and fsys.S
-#
-ASM_PARAVIRT_OBJS = ivt.o entry.o fsys.o
-define paravirtualized_native
-AFLAGS_$(1) += -D__IA64_ASM_PARAVIRTUALIZED_NATIVE
-AFLAGS_pvchk-sed-$(1) += -D__IA64_ASM_PARAVIRTUALIZED_PVCHECK
-extra-y += pvchk-$(1)
-endef
-$(foreach obj,$(ASM_PARAVIRT_OBJS),$(eval $(call paravirtualized_native,$(obj))))
-
-#
-# Checker for paravirtualizations of privileged operations.
-#
-quiet_cmd_pv_check_sed = PVCHK $@
-define cmd_pv_check_sed
- sed -f $(srctree)/arch/$(SRCARCH)/scripts/pvcheck.sed $< > $@
-endef
-
-$(obj)/pvchk-sed-%.s: $(src)/%.S $(srctree)/arch/$(SRCARCH)/scripts/pvcheck.sed FORCE
- $(call if_changed_dep,as_s_S)
-$(obj)/pvchk-%.s: $(obj)/pvchk-sed-%.s FORCE
- $(call if_changed,pv_check_sed)
-$(obj)/pvchk-%.o: $(obj)/pvchk-%.s FORCE
- $(call if_changed,as_o_S)
-.PRECIOUS: $(obj)/pvchk-sed-%.s $(obj)/pvchk-%.s $(obj)/pvchk-%.o
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index c52d7540dc05..47e962f7ed5a 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -464,7 +464,6 @@ efi_map_pal_code (void)
GRANULEROUNDDOWN((unsigned long) pal_vaddr),
pte_val(pfn_pte(__pa(pal_vaddr) >> PAGE_SHIFT, PAGE_KERNEL)),
IA64_GRANULE_SHIFT);
- paravirt_dv_serialize_data();
ia64_set_psr(psr); /* restore psr */
}
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index fcf8b8cbca0b..ae0de7bf5525 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -51,7 +51,6 @@
#include "minstate.h"
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
/*
* execve() is special because in case of success, we need to
* setup a null register window frame.
@@ -161,7 +160,6 @@ GLOBAL_ENTRY(sys_clone)
mov rp=loc0
br.ret.sptk.many rp
END(sys_clone)
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
/*
* prev_task <- ia64_switch_to(struct task_struct *next)
@@ -169,7 +167,7 @@ END(sys_clone)
* called. The code starting at .map relies on this. The rest of the code
* doesn't care about the interrupt masking status.
*/
-GLOBAL_ENTRY(__paravirt_switch_to)
+GLOBAL_ENTRY(ia64_switch_to)
.prologue
alloc r16=ar.pfs,1,0,0,0
DO_SAVE_SWITCH_STACK
@@ -221,9 +219,8 @@ GLOBAL_ENTRY(__paravirt_switch_to)
itr.d dtr[r25]=r23 // wire in new mapping...
SSM_PSR_IC_AND_SRLZ_D(r8, r9) // reenable the psr.ic bit
br.cond.sptk .done
-END(__paravirt_switch_to)
+END(ia64_switch_to)
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
/*
* Note that interrupts are enabled during save_switch_stack and load_switch_stack. This
* means that we may get an interrupt with "sp" pointing to the new kernel stack while
@@ -639,16 +636,8 @@ GLOBAL_ENTRY(ia64_ret_from_syscall)
adds r2=PT(R8)+16,sp // r2 = &pt_regs.r8
mov r10=r0 // clear error indication in r10
(p7) br.cond.spnt handle_syscall_error // handle potential syscall failure
-#ifdef CONFIG_PARAVIRT
- ;;
- br.cond.sptk.few ia64_leave_syscall
- ;;
-#endif /* CONFIG_PARAVIRT */
END(ia64_ret_from_syscall)
-#ifndef CONFIG_PARAVIRT
// fall through
-#endif
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
/*
* ia64_leave_syscall(): Same as ia64_leave_kernel, except that it doesn't
@@ -694,7 +683,7 @@ END(ia64_ret_from_syscall)
* ar.csd: cleared
* ar.ssd: cleared
*/
-GLOBAL_ENTRY(__paravirt_leave_syscall)
+GLOBAL_ENTRY(ia64_leave_syscall)
PT_REGS_UNWIND_INFO(0)
/*
* work.need_resched etc. mustn't get changed by this CPU before it returns to
@@ -722,8 +711,8 @@ GLOBAL_ENTRY(__paravirt_leave_syscall)
cmp.eq pLvSys,p0=r0,r0 // pLvSys=1: leave from syscall
(pUStk) cmp.eq.unc p6,p0=r0,r0 // p6 <- pUStk
#endif
-.global __paravirt_work_processed_syscall;
-__paravirt_work_processed_syscall:
+.global ia64_work_processed_syscall;
+ia64_work_processed_syscall:
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
adds r2=PT(LOADRS)+16,r12
MOV_FROM_ITC(pUStk, p9, r22, r19) // fetch time at leave
@@ -836,9 +825,9 @@ __paravirt_work_processed_syscall:
mov.m ar.ssd=r0 // M2 clear ar.ssd
mov f11=f0 // F clear f11
br.cond.sptk.many rbs_switch // B
-END(__paravirt_leave_syscall)
+END(ia64_leave_syscall)
-GLOBAL_ENTRY(__paravirt_leave_kernel)
+GLOBAL_ENTRY(ia64_leave_kernel)
PT_REGS_UNWIND_INFO(0)
/*
* work.need_resched etc. mustn't get changed by this CPU before it returns to
@@ -1171,26 +1160,25 @@ skip_rbs_switch:
(p6) br.cond.sptk.few .notify
br.call.spnt.many rp=preempt_schedule_irq
.ret9: cmp.eq p6,p0=r0,r0 // p6 <- 1 (re-check)
-(pLvSys)br.cond.sptk.few __paravirt_pending_syscall_end
+(pLvSys)br.cond.sptk.few ia64_work_pending_syscall_end
br.cond.sptk.many .work_processed_kernel
.notify:
(pUStk) br.call.spnt.many rp=notify_resume_user
.ret10: cmp.ne p6,p0=r0,r0 // p6 <- 0 (don't re-check)
-(pLvSys)br.cond.sptk.few __paravirt_pending_syscall_end
+(pLvSys)br.cond.sptk.few ia64_work_pending_syscall_end
br.cond.sptk.many .work_processed_kernel
-.global __paravirt_pending_syscall_end;
-__paravirt_pending_syscall_end:
+.global ia64_work_pending_syscall_end;
+ia64_work_pending_syscall_end:
adds r2=PT(R8)+16,r12
adds r3=PT(R10)+16,r12
;;
ld8 r8=[r2]
ld8 r10=[r3]
- br.cond.sptk.many __paravirt_work_processed_syscall_target
-END(__paravirt_leave_kernel)
+ br.cond.sptk.many ia64_work_processed_syscall
+END(ia64_leave_kernel)
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
ENTRY(handle_syscall_error)
/*
* Some system calls (e.g., ptrace, mmap) can return arbitrary values which could
@@ -1294,7 +1282,7 @@ ENTRY(sys_rt_sigreturn)
adds sp=16,sp
;;
ld8 r9=[sp] // load new ar.unat
- mov.sptk b7=r8,ia64_native_leave_kernel
+ mov.sptk b7=r8,ia64_leave_kernel
;;
mov ar.unat=r9
br.many b7
@@ -1782,4 +1770,3 @@ sys_call_table:
data8 sys_execveat
.org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index abc6dee3799c..edbf7af95849 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -24,7 +24,7 @@
#include <asm/unistd.h>
#include "entry.h"
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
/*
* See Documentation/ia64/fsys.txt for details on fsyscalls.
@@ -402,7 +402,7 @@ ENTRY(fsys_fallback_syscall)
mov r26=ar.pfs
END(fsys_fallback_syscall)
/* FALL THROUGH */
-GLOBAL_ENTRY(paravirt_fsys_bubble_down)
+GLOBAL_ENTRY(fsys_bubble_down)
.prologue
.altrp b6
.body
@@ -440,7 +440,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
*
* PSR.BE : already is turned off in __kernel_syscall_via_epc()
* PSR.AC : don't care (kernel normally turns PSR.AC on)
- * PSR.I : already turned off by the time paravirt_fsys_bubble_down gets
+ * PSR.I : already turned off by the time fsys_bubble_down gets
* invoked
* PSR.DFL: always 0 (kernel never turns it on)
* PSR.DFH: don't care --- kernel never touches f32-f127 on its own
@@ -450,7 +450,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
* PSR.DB : don't care --- kernel never enables kernel-level
* breakpoints
* PSR.TB : must be 0 already; if it wasn't zero on entry to
- * __kernel_syscall_via_epc, the branch to paravirt_fsys_bubble_down
+ * __kernel_syscall_via_epc, the branch to fsys_bubble_down
* will trigger a taken branch; the taken-trap-handler then
* converts the syscall into a break-based system-call.
*/
@@ -541,14 +541,14 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
nop.m 0
(p8) br.call.sptk.many b6=b6 // B (ignore return address)
br.cond.spnt ia64_trace_syscall // B
-END(paravirt_fsys_bubble_down)
+END(fsys_bubble_down)
.rodata
.align 8
- .globl paravirt_fsyscall_table
+ .globl fsyscall_table
- data8 paravirt_fsys_bubble_down
-paravirt_fsyscall_table:
+ data8 fsys_bubble_down
+fsyscall_table:
data8 fsys_ni_syscall
data8 0 // exit // 1025
data8 0 // read
@@ -833,4 +833,4 @@ paravirt_fsyscall_table:
// fill in zeros for the remaining entries
.zero:
- .space paravirt_fsyscall_table + 8*NR_syscalls - .zero, 0
+ .space fsyscall_table + 8*NR_syscalls - .zero, 0
diff --git a/arch/ia64/kernel/gate.S b/arch/ia64/kernel/gate.S
index b5f8bdd8618e..0bd1b3bfaf1c 100644
--- a/arch/ia64/kernel/gate.S
+++ b/arch/ia64/kernel/gate.S
@@ -14,7 +14,7 @@
#include <asm/unistd.h>
#include <asm/kregs.h>
#include <asm/page.h>
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
/*
* We can't easily refer to symbols inside the kernel. To avoid full runtime relocation,
@@ -376,11 +376,4 @@ GLOBAL_ENTRY(__kernel_syscall_via_epc)
(p9) mov r8=ENOSYS
FSYS_RETURN
-#ifdef CONFIG_PARAVIRT
- /*
- * padd to make the size of this symbol constant
- * independent of paravirtualization.
- */
- .align PAGE_SIZE / 8
-#endif
END(__kernel_syscall_via_epc)
diff --git a/arch/ia64/kernel/gate.lds.S b/arch/ia64/kernel/gate.lds.S
index e518f7902af6..3e8271e85a1e 100644
--- a/arch/ia64/kernel/gate.lds.S
+++ b/arch/ia64/kernel/gate.lds.S
@@ -6,7 +6,6 @@
*/
#include <asm/page.h>
-#include "paravirt_patchlist.h"
SECTIONS
{
@@ -33,21 +32,21 @@ SECTIONS
. = GATE_ADDR + 0x600;
.data..patch : {
- __paravirt_start_gate_mckinley_e9_patchlist = .;
+ __start_gate_mckinley_e9_patchlist = .;
*(.data..patch.mckinley_e9)
- __paravirt_end_gate_mckinley_e9_patchlist = .;
+ __end_gate_mckinley_e9_patchlist = .;
- __paravirt_start_gate_vtop_patchlist = .;
+ __start_gate_vtop_patchlist = .;
*(.data..patch.vtop)
- __paravirt_end_gate_vtop_patchlist = .;
+ __end_gate_vtop_patchlist = .;
- __paravirt_start_gate_fsyscall_patchlist = .;
+ __start_gate_fsyscall_patchlist = .;
*(.data..patch.fsyscall_table)
- __paravirt_end_gate_fsyscall_patchlist = .;
+ __end_gate_fsyscall_patchlist = .;
- __paravirt_start_gate_brl_fsys_bubble_down_patchlist = .;
+ __start_gate_brl_fsys_bubble_down_patchlist = .;
*(.data..patch.brl_fsys_bubble_down)
- __paravirt_end_gate_brl_fsys_bubble_down_patchlist = .;
+ __end_gate_brl_fsys_bubble_down_patchlist = .;
} :readable
.IA_64.unwind_info : { *(.IA_64.unwind_info*) }
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index a4acddad0c78..bb748c596443 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -26,7 +26,6 @@
#include <asm/mmu_context.h>
#include <asm/asm-offsets.h>
#include <asm/pal.h>
-#include <asm/paravirt.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
@@ -394,41 +393,6 @@ start_ap:
;;
(isBP) st8 [r2]=r28 // save the address of the boot param area passed by the bootloader
-#ifdef CONFIG_PARAVIRT
-
- movl r14=hypervisor_setup_hooks
- movl r15=hypervisor_type
- mov r16=num_hypervisor_hooks
- ;;
- ld8 r2=[r15]
- ;;
- cmp.ltu p7,p0=r2,r16 // array size check
- shladd r8=r2,3,r14
- ;;
-(p7) ld8 r9=[r8]
- ;;
-(p7) mov b1=r9
-(p7) cmp.ne.unc p7,p0=r9,r0 // no actual branch to NULL
- ;;
-(p7) br.call.sptk.many rp=b1
-
- __INITDATA
-
-default_setup_hook = 0 // Currently nothing needs to be done.
-
- .global hypervisor_type
-hypervisor_type:
- data8 PARAVIRT_HYPERVISOR_TYPE_DEFAULT
-
- // must have the same order with PARAVIRT_HYPERVISOR_TYPE_xxx
-
-hypervisor_setup_hooks:
- data8 default_setup_hook
-num_hypervisor_hooks = (. - hypervisor_setup_hooks) / 8
- .previous
-
-#endif
-
#ifdef CONFIG_SMP
(isAP) br.call.sptk.many rp=start_secondary
.ret0:
@@ -1063,12 +1027,6 @@ GLOBAL_ENTRY(ia64_native_sched_clock)
shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
br.ret.sptk.many rp
END(ia64_native_sched_clock)
-#ifndef CONFIG_PARAVIRT
- //unsigned long long
- //sched_clock(void) __attribute__((alias("ia64_native_sched_clock")));
- .global sched_clock
-sched_clock = ia64_native_sched_clock
-#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
GLOBAL_ENTRY(cycle_to_cputime)
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index e42bf7a913f3..b1c3cfc93e71 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -937,7 +937,6 @@ END(interrupt)
* - ar.fpsr: set to kernel settings
* - b6: preserved (same as on entry)
*/
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
GLOBAL_ENTRY(ia64_syscall_setup)
#if PT(B6) != 0
# error This code assumes that b6 is the first field in pt_regs.
@@ -1029,7 +1028,6 @@ GLOBAL_ENTRY(ia64_syscall_setup)
(p10) mov r8=-EINVAL
br.ret.sptk.many b7
END(ia64_syscall_setup)
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
.org ia64_ivt+0x3c00
/////////////////////////////////////////////////////////////////////////////////////////
@@ -1043,7 +1041,7 @@ END(ia64_syscall_setup)
DBG_FAULT(16)
FAULT(16)
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE)
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE)
/*
* There is no particular reason for this code to be here, other than
* that there happens to be space here that would go unused otherwise.
diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h
index cc82a7d744c9..5704700fb703 100644
--- a/arch/ia64/kernel/minstate.h
+++ b/arch/ia64/kernel/minstate.h
@@ -2,7 +2,7 @@
#include <asm/cache.h>
#include "entry.h"
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
/* read ar.itc in advance, and use it before leaving bank 0 */
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 29754aae5177..b15933c31b2f 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -439,14 +439,6 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings,
mod->arch.opd = s;
else if (strcmp(".IA_64.unwind", secstrings + s->sh_name) == 0)
mod->arch.unwind = s;
-#ifdef CONFIG_PARAVIRT
- else if (strcmp(".paravirt_bundles",
- secstrings + s->sh_name) == 0)
- mod->arch.paravirt_bundles = s;
- else if (strcmp(".paravirt_insts",
- secstrings + s->sh_name) == 0)
- mod->arch.paravirt_insts = s;
-#endif
if (!mod->arch.core_plt || !mod->arch.init_plt || !mod->arch.got || !mod->arch.opd) {
printk(KERN_ERR "%s: sections missing\n", mod->name);
@@ -914,30 +906,6 @@ module_finalize (const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mo
DEBUGP("%s: init: entry=%p\n", __func__, mod->init);
if (mod->arch.unwind)
register_unwind_table(mod);
-#ifdef CONFIG_PARAVIRT
- if (mod->arch.paravirt_bundles) {
- struct paravirt_patch_site_bundle *start =
- (struct paravirt_patch_site_bundle *)
- mod->arch.paravirt_bundles->sh_addr;
- struct paravirt_patch_site_bundle *end =
- (struct paravirt_patch_site_bundle *)
- (mod->arch.paravirt_bundles->sh_addr +
- mod->arch.paravirt_bundles->sh_size);
-
- paravirt_patch_apply_bundle(start, end);
- }
- if (mod->arch.paravirt_insts) {
- struct paravirt_patch_site_inst *start =
- (struct paravirt_patch_site_inst *)
- mod->arch.paravirt_insts->sh_addr;
- struct paravirt_patch_site_inst *end =
- (struct paravirt_patch_site_inst *)
- (mod->arch.paravirt_insts->sh_addr +
- mod->arch.paravirt_insts->sh_size);
-
- paravirt_patch_apply_inst(start, end);
- }
-#endif
return 0;
}
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 9dd7464f8c17..d70bf15c690a 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -165,7 +165,7 @@ static struct irq_chip dmar_msi_type = {
.irq_retrigger = ia64_msi_retrigger_irq,
};
-static int
+static void
msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
{
struct irq_cfg *cfg = irq_cfg + irq;
@@ -186,21 +186,29 @@ msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
MSI_DATA_LEVEL_ASSERT |
MSI_DATA_DELIVERY_FIXED |
MSI_DATA_VECTOR(cfg->vector);
- return 0;
}
-int arch_setup_dmar_msi(unsigned int irq)
+int dmar_alloc_hwirq(int id, int node, void *arg)
{
- int ret;
+ int irq;
struct msi_msg msg;
- ret = msi_compose_msg(NULL, irq, &msg);
- if (ret < 0)
- return ret;
- dmar_msi_write(irq, &msg);
- irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
- return 0;
+ irq = create_irq();
+ if (irq > 0) {
+ irq_set_handler_data(irq, arg);
+ irq_set_chip_and_handler_name(irq, &dmar_msi_type,
+ handle_edge_irq, "edge");
+ msi_compose_msg(NULL, irq, &msg);
+ dmar_msi_write(irq, &msg);
+ }
+
+ return irq;
+}
+
+void dmar_free_hwirq(int irq)
+{
+ irq_set_handler_data(irq, NULL);
+ destroy_irq(irq);
}
#endif /* CONFIG_INTEL_IOMMU */
diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c
deleted file mode 100644
index 1b22f6de2932..000000000000
--- a/arch/ia64/kernel/paravirt.c
+++ /dev/null
@@ -1,902 +0,0 @@
-/******************************************************************************
- * arch/ia64/kernel/paravirt.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- * Yaozu (Eddie) Dong <eddie.dong@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#include <linux/init.h>
-
-#include <linux/compiler.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/module.h>
-#include <linux/types.h>
-
-#include <asm/iosapic.h>
-#include <asm/paravirt.h>
-
-/***************************************************************************
- * general info
- */
-struct pv_info pv_info = {
- .kernel_rpl = 0,
- .paravirt_enabled = 0,
- .name = "bare hardware"
-};
-
-/***************************************************************************
- * pv_init_ops
- * initialization hooks.
- */
-
-static void __init
-ia64_native_patch_branch(unsigned long tag, unsigned long type);
-
-struct pv_init_ops pv_init_ops =
-{
-#ifdef ASM_SUPPORTED
- .patch_bundle = ia64_native_patch_bundle,
-#endif
- .patch_branch = ia64_native_patch_branch,
-};
-
-/***************************************************************************
- * pv_cpu_ops
- * intrinsics hooks.
- */
-
-#ifndef ASM_SUPPORTED
-/* ia64_native_xxx are macros so that we have to make them real functions */
-
-#define DEFINE_VOID_FUNC1(name) \
- static void \
- ia64_native_ ## name ## _func(unsigned long arg) \
- { \
- ia64_native_ ## name(arg); \
- }
-
-#define DEFINE_VOID_FUNC1_VOID(name) \
- static void \
- ia64_native_ ## name ## _func(void *arg) \
- { \
- ia64_native_ ## name(arg); \
- }
-
-#define DEFINE_VOID_FUNC2(name) \
- static void \
- ia64_native_ ## name ## _func(unsigned long arg0, \
- unsigned long arg1) \
- { \
- ia64_native_ ## name(arg0, arg1); \
- }
-
-#define DEFINE_FUNC0(name) \
- static unsigned long \
- ia64_native_ ## name ## _func(void) \
- { \
- return ia64_native_ ## name(); \
- }
-
-#define DEFINE_FUNC1(name, type) \
- static unsigned long \
- ia64_native_ ## name ## _func(type arg) \
- { \
- return ia64_native_ ## name(arg); \
- } \
-
-DEFINE_VOID_FUNC1_VOID(fc);
-DEFINE_VOID_FUNC1(intrin_local_irq_restore);
-
-DEFINE_VOID_FUNC2(ptcga);
-DEFINE_VOID_FUNC2(set_rr);
-
-DEFINE_FUNC0(get_psr_i);
-
-DEFINE_FUNC1(thash, unsigned long);
-DEFINE_FUNC1(get_cpuid, int);
-DEFINE_FUNC1(get_pmd, int);
-DEFINE_FUNC1(get_rr, unsigned long);
-
-static void
-ia64_native_ssm_i_func(void)
-{
- ia64_native_ssm(IA64_PSR_I);
-}
-
-static void
-ia64_native_rsm_i_func(void)
-{
- ia64_native_rsm(IA64_PSR_I);
-}
-
-static void
-ia64_native_set_rr0_to_rr4_func(unsigned long val0, unsigned long val1,
- unsigned long val2, unsigned long val3,
- unsigned long val4)
-{
- ia64_native_set_rr0_to_rr4(val0, val1, val2, val3, val4);
-}
-
-#define CASE_GET_REG(id) \
- case _IA64_REG_ ## id: \
- res = ia64_native_getreg(_IA64_REG_ ## id); \
- break;
-#define CASE_GET_AR(id) CASE_GET_REG(AR_ ## id)
-#define CASE_GET_CR(id) CASE_GET_REG(CR_ ## id)
-
-unsigned long
-ia64_native_getreg_func(int regnum)
-{
- unsigned long res = -1;
- switch (regnum) {
- CASE_GET_REG(GP);
- /*CASE_GET_REG(IP);*/ /* returned ip value shouldn't be constant */
- CASE_GET_REG(PSR);
- CASE_GET_REG(TP);
- CASE_GET_REG(SP);
-
- CASE_GET_AR(KR0);
- CASE_GET_AR(KR1);
- CASE_GET_AR(KR2);
- CASE_GET_AR(KR3);
- CASE_GET_AR(KR4);
- CASE_GET_AR(KR5);
- CASE_GET_AR(KR6);
- CASE_GET_AR(KR7);
- CASE_GET_AR(RSC);
- CASE_GET_AR(BSP);
- CASE_GET_AR(BSPSTORE);
- CASE_GET_AR(RNAT);
- CASE_GET_AR(FCR);
- CASE_GET_AR(EFLAG);
- CASE_GET_AR(CSD);
- CASE_GET_AR(SSD);
- CASE_GET_AR(CFLAG);
- CASE_GET_AR(FSR);
- CASE_GET_AR(FIR);
- CASE_GET_AR(FDR);
- CASE_GET_AR(CCV);
- CASE_GET_AR(UNAT);
- CASE_GET_AR(FPSR);
- CASE_GET_AR(ITC);
- CASE_GET_AR(PFS);
- CASE_GET_AR(LC);
- CASE_GET_AR(EC);
-
- CASE_GET_CR(DCR);
- CASE_GET_CR(ITM);
- CASE_GET_CR(IVA);
- CASE_GET_CR(PTA);
- CASE_GET_CR(IPSR);
- CASE_GET_CR(ISR);
- CASE_GET_CR(IIP);
- CASE_GET_CR(IFA);
- CASE_GET_CR(ITIR);
- CASE_GET_CR(IIPA);
- CASE_GET_CR(IFS);
- CASE_GET_CR(IIM);
- CASE_GET_CR(IHA);
- CASE_GET_CR(LID);
- CASE_GET_CR(IVR);
- CASE_GET_CR(TPR);
- CASE_GET_CR(EOI);
- CASE_GET_CR(IRR0);
- CASE_GET_CR(IRR1);
- CASE_GET_CR(IRR2);
- CASE_GET_CR(IRR3);
- CASE_GET_CR(ITV);
- CASE_GET_CR(PMV);
- CASE_GET_CR(CMCV);
- CASE_GET_CR(LRR0);
- CASE_GET_CR(LRR1);
-
- default:
- printk(KERN_CRIT "wrong_getreg %d\n", regnum);
- break;
- }
- return res;
-}
-
-#define CASE_SET_REG(id) \
- case _IA64_REG_ ## id: \
- ia64_native_setreg(_IA64_REG_ ## id, val); \
- break;
-#define CASE_SET_AR(id) CASE_SET_REG(AR_ ## id)
-#define CASE_SET_CR(id) CASE_SET_REG(CR_ ## id)
-
-void
-ia64_native_setreg_func(int regnum, unsigned long val)
-{
- switch (regnum) {
- case _IA64_REG_PSR_L:
- ia64_native_setreg(_IA64_REG_PSR_L, val);
- ia64_dv_serialize_data();
- break;
- CASE_SET_REG(SP);
- CASE_SET_REG(GP);
-
- CASE_SET_AR(KR0);
- CASE_SET_AR(KR1);
- CASE_SET_AR(KR2);
- CASE_SET_AR(KR3);
- CASE_SET_AR(KR4);
- CASE_SET_AR(KR5);
- CASE_SET_AR(KR6);
- CASE_SET_AR(KR7);
- CASE_SET_AR(RSC);
- CASE_SET_AR(BSP);
- CASE_SET_AR(BSPSTORE);
- CASE_SET_AR(RNAT);
- CASE_SET_AR(FCR);
- CASE_SET_AR(EFLAG);
- CASE_SET_AR(CSD);
- CASE_SET_AR(SSD);
- CASE_SET_AR(CFLAG);
- CASE_SET_AR(FSR);
- CASE_SET_AR(FIR);
- CASE_SET_AR(FDR);
- CASE_SET_AR(CCV);
- CASE_SET_AR(UNAT);
- CASE_SET_AR(FPSR);
- CASE_SET_AR(ITC);
- CASE_SET_AR(PFS);
- CASE_SET_AR(LC);
- CASE_SET_AR(EC);
-
- CASE_SET_CR(DCR);
- CASE_SET_CR(ITM);
- CASE_SET_CR(IVA);
- CASE_SET_CR(PTA);
- CASE_SET_CR(IPSR);
- CASE_SET_CR(ISR);
- CASE_SET_CR(IIP);
- CASE_SET_CR(IFA);
- CASE_SET_CR(ITIR);
- CASE_SET_CR(IIPA);
- CASE_SET_CR(IFS);
- CASE_SET_CR(IIM);
- CASE_SET_CR(IHA);
- CASE_SET_CR(LID);
- CASE_SET_CR(IVR);
- CASE_SET_CR(TPR);
- CASE_SET_CR(EOI);
- CASE_SET_CR(IRR0);
- CASE_SET_CR(IRR1);
- CASE_SET_CR(IRR2);
- CASE_SET_CR(IRR3);
- CASE_SET_CR(ITV);
- CASE_SET_CR(PMV);
- CASE_SET_CR(CMCV);
- CASE_SET_CR(LRR0);
- CASE_SET_CR(LRR1);
- default:
- printk(KERN_CRIT "wrong setreg %d\n", regnum);
- break;
- }
-}
-#else
-
-#define __DEFINE_FUNC(name, code) \
- extern const char ia64_native_ ## name ## _direct_start[]; \
- extern const char ia64_native_ ## name ## _direct_end[]; \
- asm (".align 32\n" \
- ".proc ia64_native_" #name "_func\n" \
- "ia64_native_" #name "_func:\n" \
- "ia64_native_" #name "_direct_start:\n" \
- code \
- "ia64_native_" #name "_direct_end:\n" \
- "br.cond.sptk.many b6\n" \
- ".endp ia64_native_" #name "_func\n")
-
-#define DEFINE_VOID_FUNC0(name, code) \
- extern void \
- ia64_native_ ## name ## _func(void); \
- __DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC1(name, code) \
- extern void \
- ia64_native_ ## name ## _func(unsigned long arg); \
- __DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC1_VOID(name, code) \
- extern void \
- ia64_native_ ## name ## _func(void *arg); \
- __DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC2(name, code) \
- extern void \
- ia64_native_ ## name ## _func(unsigned long arg0, \
- unsigned long arg1); \
- __DEFINE_FUNC(name, code)
-
-#define DEFINE_FUNC0(name, code) \
- extern unsigned long \
- ia64_native_ ## name ## _func(void); \
- __DEFINE_FUNC(name, code)
-
-#define DEFINE_FUNC1(name, type, code) \
- extern unsigned long \
- ia64_native_ ## name ## _func(type arg); \
- __DEFINE_FUNC(name, code)
-
-DEFINE_VOID_FUNC1_VOID(fc,
- "fc r8\n");
-DEFINE_VOID_FUNC1(intrin_local_irq_restore,
- ";;\n"
- " cmp.ne p6, p7 = r8, r0\n"
- ";;\n"
- "(p6) ssm psr.i\n"
- "(p7) rsm psr.i\n"
- ";;\n"
- "(p6) srlz.d\n");
-
-DEFINE_VOID_FUNC2(ptcga,
- "ptc.ga r8, r9\n");
-DEFINE_VOID_FUNC2(set_rr,
- "mov rr[r8] = r9\n");
-
-/* ia64_native_getreg(_IA64_REG_PSR) & IA64_PSR_I */
-DEFINE_FUNC0(get_psr_i,
- "mov r2 = " __stringify(1 << IA64_PSR_I_BIT) "\n"
- "mov r8 = psr\n"
- ";;\n"
- "and r8 = r2, r8\n");
-
-DEFINE_FUNC1(thash, unsigned long,
- "thash r8 = r8\n");
-DEFINE_FUNC1(get_cpuid, int,
- "mov r8 = cpuid[r8]\n");
-DEFINE_FUNC1(get_pmd, int,
- "mov r8 = pmd[r8]\n");
-DEFINE_FUNC1(get_rr, unsigned long,
- "mov r8 = rr[r8]\n");
-
-DEFINE_VOID_FUNC0(ssm_i,
- "ssm psr.i\n");
-DEFINE_VOID_FUNC0(rsm_i,
- "rsm psr.i\n");
-
-extern void
-ia64_native_set_rr0_to_rr4_func(unsigned long val0, unsigned long val1,
- unsigned long val2, unsigned long val3,
- unsigned long val4);
-__DEFINE_FUNC(set_rr0_to_rr4,
- "mov rr[r0] = r8\n"
- "movl r2 = 0x2000000000000000\n"
- ";;\n"
- "mov rr[r2] = r9\n"
- "shl r3 = r2, 1\n" /* movl r3 = 0x4000000000000000 */
- ";;\n"
- "add r2 = r2, r3\n" /* movl r2 = 0x6000000000000000 */
- "mov rr[r3] = r10\n"
- ";;\n"
- "mov rr[r2] = r11\n"
- "shl r3 = r3, 1\n" /* movl r3 = 0x8000000000000000 */
- ";;\n"
- "mov rr[r3] = r14\n");
-
-extern unsigned long ia64_native_getreg_func(int regnum);
-asm(".global ia64_native_getreg_func\n");
-#define __DEFINE_GET_REG(id, reg) \
- "mov r2 = " __stringify(_IA64_REG_ ## id) "\n" \
- ";;\n" \
- "cmp.eq p6, p0 = r2, r8\n" \
- ";;\n" \
- "(p6) mov r8 = " #reg "\n" \
- "(p6) br.cond.sptk.many b6\n" \
- ";;\n"
-#define __DEFINE_GET_AR(id, reg) __DEFINE_GET_REG(AR_ ## id, ar.reg)
-#define __DEFINE_GET_CR(id, reg) __DEFINE_GET_REG(CR_ ## id, cr.reg)
-
-__DEFINE_FUNC(getreg,
- __DEFINE_GET_REG(GP, gp)
- /*__DEFINE_GET_REG(IP, ip)*/ /* returned ip value shouldn't be constant */
- __DEFINE_GET_REG(PSR, psr)
- __DEFINE_GET_REG(TP, tp)
- __DEFINE_GET_REG(SP, sp)
-
- __DEFINE_GET_REG(AR_KR0, ar0)
- __DEFINE_GET_REG(AR_KR1, ar1)
- __DEFINE_GET_REG(AR_KR2, ar2)
- __DEFINE_GET_REG(AR_KR3, ar3)
- __DEFINE_GET_REG(AR_KR4, ar4)
- __DEFINE_GET_REG(AR_KR5, ar5)
- __DEFINE_GET_REG(AR_KR6, ar6)
- __DEFINE_GET_REG(AR_KR7, ar7)
- __DEFINE_GET_AR(RSC, rsc)
- __DEFINE_GET_AR(BSP, bsp)
- __DEFINE_GET_AR(BSPSTORE, bspstore)
- __DEFINE_GET_AR(RNAT, rnat)
- __DEFINE_GET_AR(FCR, fcr)
- __DEFINE_GET_AR(EFLAG, eflag)
- __DEFINE_GET_AR(CSD, csd)
- __DEFINE_GET_AR(SSD, ssd)
- __DEFINE_GET_REG(AR_CFLAG, ar27)
- __DEFINE_GET_AR(FSR, fsr)
- __DEFINE_GET_AR(FIR, fir)
- __DEFINE_GET_AR(FDR, fdr)
- __DEFINE_GET_AR(CCV, ccv)
- __DEFINE_GET_AR(UNAT, unat)
- __DEFINE_GET_AR(FPSR, fpsr)
- __DEFINE_GET_AR(ITC, itc)
- __DEFINE_GET_AR(PFS, pfs)
- __DEFINE_GET_AR(LC, lc)
- __DEFINE_GET_AR(EC, ec)
-
- __DEFINE_GET_CR(DCR, dcr)
- __DEFINE_GET_CR(ITM, itm)
- __DEFINE_GET_CR(IVA, iva)
- __DEFINE_GET_CR(PTA, pta)
- __DEFINE_GET_CR(IPSR, ipsr)
- __DEFINE_GET_CR(ISR, isr)
- __DEFINE_GET_CR(IIP, iip)
- __DEFINE_GET_CR(IFA, ifa)
- __DEFINE_GET_CR(ITIR, itir)
- __DEFINE_GET_CR(IIPA, iipa)
- __DEFINE_GET_CR(IFS, ifs)
- __DEFINE_GET_CR(IIM, iim)
- __DEFINE_GET_CR(IHA, iha)
- __DEFINE_GET_CR(LID, lid)
- __DEFINE_GET_CR(IVR, ivr)
- __DEFINE_GET_CR(TPR, tpr)
- __DEFINE_GET_CR(EOI, eoi)
- __DEFINE_GET_CR(IRR0, irr0)
- __DEFINE_GET_CR(IRR1, irr1)
- __DEFINE_GET_CR(IRR2, irr2)
- __DEFINE_GET_CR(IRR3, irr3)
- __DEFINE_GET_CR(ITV, itv)
- __DEFINE_GET_CR(PMV, pmv)
- __DEFINE_GET_CR(CMCV, cmcv)
- __DEFINE_GET_CR(LRR0, lrr0)
- __DEFINE_GET_CR(LRR1, lrr1)
-
- "mov r8 = -1\n" /* unsupported case */
- );
-
-extern void ia64_native_setreg_func(int regnum, unsigned long val);
-asm(".global ia64_native_setreg_func\n");
-#define __DEFINE_SET_REG(id, reg) \
- "mov r2 = " __stringify(_IA64_REG_ ## id) "\n" \
- ";;\n" \
- "cmp.eq p6, p0 = r2, r9\n" \
- ";;\n" \
- "(p6) mov " #reg " = r8\n" \
- "(p6) br.cond.sptk.many b6\n" \
- ";;\n"
-#define __DEFINE_SET_AR(id, reg) __DEFINE_SET_REG(AR_ ## id, ar.reg)
-#define __DEFINE_SET_CR(id, reg) __DEFINE_SET_REG(CR_ ## id, cr.reg)
-__DEFINE_FUNC(setreg,
- "mov r2 = " __stringify(_IA64_REG_PSR_L) "\n"
- ";;\n"
- "cmp.eq p6, p0 = r2, r9\n"
- ";;\n"
- "(p6) mov psr.l = r8\n"
-#ifdef HAVE_SERIALIZE_DIRECTIVE
- ".serialize.data\n"
-#endif
- "(p6) br.cond.sptk.many b6\n"
- __DEFINE_SET_REG(GP, gp)
- __DEFINE_SET_REG(SP, sp)
-
- __DEFINE_SET_REG(AR_KR0, ar0)
- __DEFINE_SET_REG(AR_KR1, ar1)
- __DEFINE_SET_REG(AR_KR2, ar2)
- __DEFINE_SET_REG(AR_KR3, ar3)
- __DEFINE_SET_REG(AR_KR4, ar4)
- __DEFINE_SET_REG(AR_KR5, ar5)
- __DEFINE_SET_REG(AR_KR6, ar6)
- __DEFINE_SET_REG(AR_KR7, ar7)
- __DEFINE_SET_AR(RSC, rsc)
- __DEFINE_SET_AR(BSP, bsp)
- __DEFINE_SET_AR(BSPSTORE, bspstore)
- __DEFINE_SET_AR(RNAT, rnat)
- __DEFINE_SET_AR(FCR, fcr)
- __DEFINE_SET_AR(EFLAG, eflag)
- __DEFINE_SET_AR(CSD, csd)
- __DEFINE_SET_AR(SSD, ssd)
- __DEFINE_SET_REG(AR_CFLAG, ar27)
- __DEFINE_SET_AR(FSR, fsr)
- __DEFINE_SET_AR(FIR, fir)
- __DEFINE_SET_AR(FDR, fdr)
- __DEFINE_SET_AR(CCV, ccv)
- __DEFINE_SET_AR(UNAT, unat)
- __DEFINE_SET_AR(FPSR, fpsr)
- __DEFINE_SET_AR(ITC, itc)
- __DEFINE_SET_AR(PFS, pfs)
- __DEFINE_SET_AR(LC, lc)
- __DEFINE_SET_AR(EC, ec)
-
- __DEFINE_SET_CR(DCR, dcr)
- __DEFINE_SET_CR(ITM, itm)
- __DEFINE_SET_CR(IVA, iva)
- __DEFINE_SET_CR(PTA, pta)
- __DEFINE_SET_CR(IPSR, ipsr)
- __DEFINE_SET_CR(ISR, isr)
- __DEFINE_SET_CR(IIP, iip)
- __DEFINE_SET_CR(IFA, ifa)
- __DEFINE_SET_CR(ITIR, itir)
- __DEFINE_SET_CR(IIPA, iipa)
- __DEFINE_SET_CR(IFS, ifs)
- __DEFINE_SET_CR(IIM, iim)
- __DEFINE_SET_CR(IHA, iha)
- __DEFINE_SET_CR(LID, lid)
- __DEFINE_SET_CR(IVR, ivr)
- __DEFINE_SET_CR(TPR, tpr)
- __DEFINE_SET_CR(EOI, eoi)
- __DEFINE_SET_CR(IRR0, irr0)
- __DEFINE_SET_CR(IRR1, irr1)
- __DEFINE_SET_CR(IRR2, irr2)
- __DEFINE_SET_CR(IRR3, irr3)
- __DEFINE_SET_CR(ITV, itv)
- __DEFINE_SET_CR(PMV, pmv)
- __DEFINE_SET_CR(CMCV, cmcv)
- __DEFINE_SET_CR(LRR0, lrr0)
- __DEFINE_SET_CR(LRR1, lrr1)
- );
-#endif
-
-struct pv_cpu_ops pv_cpu_ops = {
- .fc = ia64_native_fc_func,
- .thash = ia64_native_thash_func,
- .get_cpuid = ia64_native_get_cpuid_func,
- .get_pmd = ia64_native_get_pmd_func,
- .ptcga = ia64_native_ptcga_func,
- .get_rr = ia64_native_get_rr_func,
- .set_rr = ia64_native_set_rr_func,
- .set_rr0_to_rr4 = ia64_native_set_rr0_to_rr4_func,
- .ssm_i = ia64_native_ssm_i_func,
- .getreg = ia64_native_getreg_func,
- .setreg = ia64_native_setreg_func,
- .rsm_i = ia64_native_rsm_i_func,
- .get_psr_i = ia64_native_get_psr_i_func,
- .intrin_local_irq_restore
- = ia64_native_intrin_local_irq_restore_func,
-};
-EXPORT_SYMBOL(pv_cpu_ops);
-
-/******************************************************************************
- * replacement of hand written assembly codes.
- */
-
-void
-paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch)
-{
- extern unsigned long paravirt_switch_to_targ;
- extern unsigned long paravirt_leave_syscall_targ;
- extern unsigned long paravirt_work_processed_syscall_targ;
- extern unsigned long paravirt_leave_kernel_targ;
-
- paravirt_switch_to_targ = cpu_asm_switch->switch_to;
- paravirt_leave_syscall_targ = cpu_asm_switch->leave_syscall;
- paravirt_work_processed_syscall_targ =
- cpu_asm_switch->work_processed_syscall;
- paravirt_leave_kernel_targ = cpu_asm_switch->leave_kernel;
-}
-
-/***************************************************************************
- * pv_iosapic_ops
- * iosapic read/write hooks.
- */
-
-static unsigned int
-ia64_native_iosapic_read(char __iomem *iosapic, unsigned int reg)
-{
- return __ia64_native_iosapic_read(iosapic, reg);
-}
-
-static void
-ia64_native_iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
-{
- __ia64_native_iosapic_write(iosapic, reg, val);
-}
-
-struct pv_iosapic_ops pv_iosapic_ops = {
- .pcat_compat_init = ia64_native_iosapic_pcat_compat_init,
- .__get_irq_chip = ia64_native_iosapic_get_irq_chip,
-
- .__read = ia64_native_iosapic_read,
- .__write = ia64_native_iosapic_write,
-};
-
-/***************************************************************************
- * pv_irq_ops
- * irq operations
- */
-
-struct pv_irq_ops pv_irq_ops = {
- .register_ipi = ia64_native_register_ipi,
-
- .assign_irq_vector = ia64_native_assign_irq_vector,
- .free_irq_vector = ia64_native_free_irq_vector,
- .register_percpu_irq = ia64_native_register_percpu_irq,
-
- .resend_irq = ia64_native_resend_irq,
-};
-
-/***************************************************************************
- * pv_time_ops
- * time operations
- */
-struct static_key paravirt_steal_enabled;
-struct static_key paravirt_steal_rq_enabled;
-
-static int
-ia64_native_do_steal_accounting(unsigned long *new_itm)
-{
- return 0;
-}
-
-struct pv_time_ops pv_time_ops = {
- .do_steal_accounting = ia64_native_do_steal_accounting,
- .sched_clock = ia64_native_sched_clock,
-};
-
-/***************************************************************************
- * binary pacthing
- * pv_init_ops.patch_bundle
- */
-
-#ifdef ASM_SUPPORTED
-#define IA64_NATIVE_PATCH_DEFINE_GET_REG(name, reg) \
- __DEFINE_FUNC(get_ ## name, \
- ";;\n" \
- "mov r8 = " #reg "\n" \
- ";;\n")
-
-#define IA64_NATIVE_PATCH_DEFINE_SET_REG(name, reg) \
- __DEFINE_FUNC(set_ ## name, \
- ";;\n" \
- "mov " #reg " = r8\n" \
- ";;\n")
-
-#define IA64_NATIVE_PATCH_DEFINE_REG(name, reg) \
- IA64_NATIVE_PATCH_DEFINE_GET_REG(name, reg); \
- IA64_NATIVE_PATCH_DEFINE_SET_REG(name, reg) \
-
-#define IA64_NATIVE_PATCH_DEFINE_AR(name, reg) \
- IA64_NATIVE_PATCH_DEFINE_REG(ar_ ## name, ar.reg)
-
-#define IA64_NATIVE_PATCH_DEFINE_CR(name, reg) \
- IA64_NATIVE_PATCH_DEFINE_REG(cr_ ## name, cr.reg)
-
-
-IA64_NATIVE_PATCH_DEFINE_GET_REG(psr, psr);
-IA64_NATIVE_PATCH_DEFINE_GET_REG(tp, tp);
-
-/* IA64_NATIVE_PATCH_DEFINE_SET_REG(psr_l, psr.l); */
-__DEFINE_FUNC(set_psr_l,
- ";;\n"
- "mov psr.l = r8\n"
-#ifdef HAVE_SERIALIZE_DIRECTIVE
- ".serialize.data\n"
-#endif
- ";;\n");
-
-IA64_NATIVE_PATCH_DEFINE_REG(gp, gp);
-IA64_NATIVE_PATCH_DEFINE_REG(sp, sp);
-
-IA64_NATIVE_PATCH_DEFINE_REG(kr0, ar0);
-IA64_NATIVE_PATCH_DEFINE_REG(kr1, ar1);
-IA64_NATIVE_PATCH_DEFINE_REG(kr2, ar2);
-IA64_NATIVE_PATCH_DEFINE_REG(kr3, ar3);
-IA64_NATIVE_PATCH_DEFINE_REG(kr4, ar4);
-IA64_NATIVE_PATCH_DEFINE_REG(kr5, ar5);
-IA64_NATIVE_PATCH_DEFINE_REG(kr6, ar6);
-IA64_NATIVE_PATCH_DEFINE_REG(kr7, ar7);
-
-IA64_NATIVE_PATCH_DEFINE_AR(rsc, rsc);
-IA64_NATIVE_PATCH_DEFINE_AR(bsp, bsp);
-IA64_NATIVE_PATCH_DEFINE_AR(bspstore, bspstore);
-IA64_NATIVE_PATCH_DEFINE_AR(rnat, rnat);
-IA64_NATIVE_PATCH_DEFINE_AR(fcr, fcr);
-IA64_NATIVE_PATCH_DEFINE_AR(eflag, eflag);
-IA64_NATIVE_PATCH_DEFINE_AR(csd, csd);
-IA64_NATIVE_PATCH_DEFINE_AR(ssd, ssd);
-IA64_NATIVE_PATCH_DEFINE_REG(ar27, ar27);
-IA64_NATIVE_PATCH_DEFINE_AR(fsr, fsr);
-IA64_NATIVE_PATCH_DEFINE_AR(fir, fir);
-IA64_NATIVE_PATCH_DEFINE_AR(fdr, fdr);
-IA64_NATIVE_PATCH_DEFINE_AR(ccv, ccv);
-IA64_NATIVE_PATCH_DEFINE_AR(unat, unat);
-IA64_NATIVE_PATCH_DEFINE_AR(fpsr, fpsr);
-IA64_NATIVE_PATCH_DEFINE_AR(itc, itc);
-IA64_NATIVE_PATCH_DEFINE_AR(pfs, pfs);
-IA64_NATIVE_PATCH_DEFINE_AR(lc, lc);
-IA64_NATIVE_PATCH_DEFINE_AR(ec, ec);
-
-IA64_NATIVE_PATCH_DEFINE_CR(dcr, dcr);
-IA64_NATIVE_PATCH_DEFINE_CR(itm, itm);
-IA64_NATIVE_PATCH_DEFINE_CR(iva, iva);
-IA64_NATIVE_PATCH_DEFINE_CR(pta, pta);
-IA64_NATIVE_PATCH_DEFINE_CR(ipsr, ipsr);
-IA64_NATIVE_PATCH_DEFINE_CR(isr, isr);
-IA64_NATIVE_PATCH_DEFINE_CR(iip, iip);
-IA64_NATIVE_PATCH_DEFINE_CR(ifa, ifa);
-IA64_NATIVE_PATCH_DEFINE_CR(itir, itir);
-IA64_NATIVE_PATCH_DEFINE_CR(iipa, iipa);
-IA64_NATIVE_PATCH_DEFINE_CR(ifs, ifs);
-IA64_NATIVE_PATCH_DEFINE_CR(iim, iim);
-IA64_NATIVE_PATCH_DEFINE_CR(iha, iha);
-IA64_NATIVE_PATCH_DEFINE_CR(lid, lid);
-IA64_NATIVE_PATCH_DEFINE_CR(ivr, ivr);
-IA64_NATIVE_PATCH_DEFINE_CR(tpr, tpr);
-IA64_NATIVE_PATCH_DEFINE_CR(eoi, eoi);
-IA64_NATIVE_PATCH_DEFINE_CR(irr0, irr0);
-IA64_NATIVE_PATCH_DEFINE_CR(irr1, irr1);
-IA64_NATIVE_PATCH_DEFINE_CR(irr2, irr2);
-IA64_NATIVE_PATCH_DEFINE_CR(irr3, irr3);
-IA64_NATIVE_PATCH_DEFINE_CR(itv, itv);
-IA64_NATIVE_PATCH_DEFINE_CR(pmv, pmv);
-IA64_NATIVE_PATCH_DEFINE_CR(cmcv, cmcv);
-IA64_NATIVE_PATCH_DEFINE_CR(lrr0, lrr0);
-IA64_NATIVE_PATCH_DEFINE_CR(lrr1, lrr1);
-
-static const struct paravirt_patch_bundle_elem ia64_native_patch_bundle_elems[]
-__initdata_or_module =
-{
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM(name, type) \
- { \
- (void*)ia64_native_ ## name ## _direct_start, \
- (void*)ia64_native_ ## name ## _direct_end, \
- PARAVIRT_PATCH_TYPE_ ## type, \
- }
-
- IA64_NATIVE_PATCH_BUNDLE_ELEM(fc, FC),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(thash, THASH),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(get_cpuid, GET_CPUID),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(get_pmd, GET_PMD),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(ptcga, PTCGA),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(get_rr, GET_RR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(set_rr, SET_RR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(set_rr0_to_rr4, SET_RR0_TO_RR4),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(ssm_i, SSM_I),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(rsm_i, RSM_I),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(get_psr_i, GET_PSR_I),
- IA64_NATIVE_PATCH_BUNDLE_ELEM(intrin_local_irq_restore,
- INTRIN_LOCAL_IRQ_RESTORE),
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(name, reg) \
- { \
- (void*)ia64_native_get_ ## name ## _direct_start, \
- (void*)ia64_native_get_ ## name ## _direct_end, \
- PARAVIRT_PATCH_TYPE_GETREG + _IA64_REG_ ## reg, \
- }
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(name, reg) \
- { \
- (void*)ia64_native_set_ ## name ## _direct_start, \
- (void*)ia64_native_set_ ## name ## _direct_end, \
- PARAVIRT_PATCH_TYPE_SETREG + _IA64_REG_ ## reg, \
- }
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(name, reg) \
- IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(name, reg), \
- IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(name, reg) \
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(name, reg) \
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(ar_ ## name, AR_ ## reg)
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(name, reg) \
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(cr_ ## name, CR_ ## reg)
-
- IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(psr, PSR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(tp, TP),
-
- IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(psr_l, PSR_L),
-
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(gp, GP),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(sp, SP),
-
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr0, AR_KR0),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr1, AR_KR1),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr2, AR_KR2),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr3, AR_KR3),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr4, AR_KR4),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr5, AR_KR5),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr6, AR_KR6),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr7, AR_KR7),
-
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(rsc, RSC),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(bsp, BSP),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(bspstore, BSPSTORE),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(rnat, RNAT),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fcr, FCR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(eflag, EFLAG),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(csd, CSD),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ssd, SSD),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(ar27, AR_CFLAG),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fsr, FSR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fir, FIR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fdr, FDR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ccv, CCV),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(unat, UNAT),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fpsr, FPSR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(itc, ITC),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(pfs, PFS),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(lc, LC),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ec, EC),
-
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(dcr, DCR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itm, ITM),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iva, IVA),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(pta, PTA),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ipsr, IPSR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(isr, ISR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iip, IIP),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ifa, IFA),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itir, ITIR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iipa, IIPA),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ifs, IFS),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iim, IIM),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iha, IHA),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lid, LID),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ivr, IVR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(tpr, TPR),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(eoi, EOI),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr0, IRR0),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr1, IRR1),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr2, IRR2),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr3, IRR3),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itv, ITV),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(pmv, PMV),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(cmcv, CMCV),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lrr0, LRR0),
- IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lrr1, LRR1),
-};
-
-unsigned long __init_or_module
-ia64_native_patch_bundle(void *sbundle, void *ebundle, unsigned long type)
-{
- const unsigned long nelems = sizeof(ia64_native_patch_bundle_elems) /
- sizeof(ia64_native_patch_bundle_elems[0]);
-
- return __paravirt_patch_apply_bundle(sbundle, ebundle, type,
- ia64_native_patch_bundle_elems,
- nelems, NULL);
-}
-#endif /* ASM_SUPPOTED */
-
-extern const char ia64_native_switch_to[];
-extern const char ia64_native_leave_syscall[];
-extern const char ia64_native_work_processed_syscall[];
-extern const char ia64_native_leave_kernel[];
-
-const struct paravirt_patch_branch_target ia64_native_branch_target[]
-__initconst = {
-#define PARAVIRT_BR_TARGET(name, type) \
- { \
- ia64_native_ ## name, \
- PARAVIRT_PATCH_TYPE_BR_ ## type, \
- }
- PARAVIRT_BR_TARGET(switch_to, SWITCH_TO),
- PARAVIRT_BR_TARGET(leave_syscall, LEAVE_SYSCALL),
- PARAVIRT_BR_TARGET(work_processed_syscall, WORK_PROCESSED_SYSCALL),
- PARAVIRT_BR_TARGET(leave_kernel, LEAVE_KERNEL),
-};
-
-static void __init
-ia64_native_patch_branch(unsigned long tag, unsigned long type)
-{
- const unsigned long nelem =
- sizeof(ia64_native_branch_target) /
- sizeof(ia64_native_branch_target[0]);
- __paravirt_patch_apply_branch(tag, type,
- ia64_native_branch_target, nelem);
-}
diff --git a/arch/ia64/kernel/paravirt_inst.h b/arch/ia64/kernel/paravirt_inst.h
deleted file mode 100644
index 1ad7512b5f65..000000000000
--- a/arch/ia64/kernel/paravirt_inst.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_inst.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#ifdef __IA64_ASM_PARAVIRTUALIZED_PVCHECK
-#include <asm/native/pvchk_inst.h>
-#else
-#include <asm/native/inst.h>
-#endif
-
diff --git a/arch/ia64/kernel/paravirt_patch.c b/arch/ia64/kernel/paravirt_patch.c
deleted file mode 100644
index bfdfef1b1ffd..000000000000
--- a/arch/ia64/kernel/paravirt_patch.c
+++ /dev/null
@@ -1,514 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_patch.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#include <linux/init.h>
-#include <asm/intrinsics.h>
-#include <asm/kprobes.h>
-#include <asm/paravirt.h>
-#include <asm/paravirt_patch.h>
-
-typedef union ia64_inst {
- struct {
- unsigned long long qp : 6;
- unsigned long long : 31;
- unsigned long long opcode : 4;
- unsigned long long reserved : 23;
- } generic;
- unsigned long long l;
-} ia64_inst_t;
-
-/*
- * flush_icache_range() can't be used here.
- * we are here before cpu_init() which initializes
- * ia64_i_cache_stride_shift. flush_icache_range() uses it.
- */
-void __init_or_module
-paravirt_flush_i_cache_range(const void *instr, unsigned long size)
-{
- extern void paravirt_fc_i(const void *addr);
- unsigned long i;
-
- for (i = 0; i < size; i += sizeof(bundle_t))
- paravirt_fc_i(instr + i);
-}
-
-bundle_t* __init_or_module
-paravirt_get_bundle(unsigned long tag)
-{
- return (bundle_t *)(tag & ~3UL);
-}
-
-unsigned long __init_or_module
-paravirt_get_slot(unsigned long tag)
-{
- return tag & 3UL;
-}
-
-unsigned long __init_or_module
-paravirt_get_num_inst(unsigned long stag, unsigned long etag)
-{
- bundle_t *sbundle = paravirt_get_bundle(stag);
- unsigned long sslot = paravirt_get_slot(stag);
- bundle_t *ebundle = paravirt_get_bundle(etag);
- unsigned long eslot = paravirt_get_slot(etag);
-
- return (ebundle - sbundle) * 3 + eslot - sslot + 1;
-}
-
-unsigned long __init_or_module
-paravirt_get_next_tag(unsigned long tag)
-{
- unsigned long slot = paravirt_get_slot(tag);
-
- switch (slot) {
- case 0:
- case 1:
- return tag + 1;
- case 2: {
- bundle_t *bundle = paravirt_get_bundle(tag);
- return (unsigned long)(bundle + 1);
- }
- default:
- BUG();
- }
- /* NOTREACHED */
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot0(const bundle_t *bundle)
-{
- ia64_inst_t inst;
- inst.l = bundle->quad0.slot0;
- return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot1(const bundle_t *bundle)
-{
- ia64_inst_t inst;
- inst.l = bundle->quad0.slot1_p0 |
- ((unsigned long long)bundle->quad1.slot1_p1 << 18UL);
- return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot2(const bundle_t *bundle)
-{
- ia64_inst_t inst;
- inst.l = bundle->quad1.slot2;
- return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_inst(unsigned long tag)
-{
- bundle_t *bundle = paravirt_get_bundle(tag);
- unsigned long slot = paravirt_get_slot(tag);
-
- switch (slot) {
- case 0:
- return paravirt_read_slot0(bundle);
- case 1:
- return paravirt_read_slot1(bundle);
- case 2:
- return paravirt_read_slot2(bundle);
- default:
- BUG();
- }
- /* NOTREACHED */
-}
-
-void __init_or_module
-paravirt_write_slot0(bundle_t *bundle, ia64_inst_t inst)
-{
- bundle->quad0.slot0 = inst.l;
-}
-
-void __init_or_module
-paravirt_write_slot1(bundle_t *bundle, ia64_inst_t inst)
-{
- bundle->quad0.slot1_p0 = inst.l;
- bundle->quad1.slot1_p1 = inst.l >> 18UL;
-}
-
-void __init_or_module
-paravirt_write_slot2(bundle_t *bundle, ia64_inst_t inst)
-{
- bundle->quad1.slot2 = inst.l;
-}
-
-void __init_or_module
-paravirt_write_inst(unsigned long tag, ia64_inst_t inst)
-{
- bundle_t *bundle = paravirt_get_bundle(tag);
- unsigned long slot = paravirt_get_slot(tag);
-
- switch (slot) {
- case 0:
- paravirt_write_slot0(bundle, inst);
- break;
- case 1:
- paravirt_write_slot1(bundle, inst);
- break;
- case 2:
- paravirt_write_slot2(bundle, inst);
- break;
- default:
- BUG();
- break;
- }
- paravirt_flush_i_cache_range(bundle, sizeof(*bundle));
-}
-
-/* for debug */
-void
-paravirt_print_bundle(const bundle_t *bundle)
-{
- const unsigned long *quad = (const unsigned long *)bundle;
- ia64_inst_t slot0 = paravirt_read_slot0(bundle);
- ia64_inst_t slot1 = paravirt_read_slot1(bundle);
- ia64_inst_t slot2 = paravirt_read_slot2(bundle);
-
- printk(KERN_DEBUG
- "bundle 0x%p 0x%016lx 0x%016lx\n", bundle, quad[0], quad[1]);
- printk(KERN_DEBUG
- "bundle template 0x%x\n",
- bundle->quad0.template);
- printk(KERN_DEBUG
- "slot0 0x%lx slot1_p0 0x%lx slot1_p1 0x%lx slot2 0x%lx\n",
- (unsigned long)bundle->quad0.slot0,
- (unsigned long)bundle->quad0.slot1_p0,
- (unsigned long)bundle->quad1.slot1_p1,
- (unsigned long)bundle->quad1.slot2);
- printk(KERN_DEBUG
- "slot0 0x%016llx slot1 0x%016llx slot2 0x%016llx\n",
- slot0.l, slot1.l, slot2.l);
-}
-
-static int noreplace_paravirt __init_or_module = 0;
-
-static int __init setup_noreplace_paravirt(char *str)
-{
- noreplace_paravirt = 1;
- return 1;
-}
-__setup("noreplace-paravirt", setup_noreplace_paravirt);
-
-#ifdef ASM_SUPPORTED
-static void __init_or_module
-fill_nop_bundle(void *sbundle, void *ebundle)
-{
- extern const char paravirt_nop_bundle[];
- extern const unsigned long paravirt_nop_bundle_size;
-
- void *bundle = sbundle;
-
- BUG_ON((((unsigned long)sbundle) % sizeof(bundle_t)) != 0);
- BUG_ON((((unsigned long)ebundle) % sizeof(bundle_t)) != 0);
-
- while (bundle < ebundle) {
- memcpy(bundle, paravirt_nop_bundle, paravirt_nop_bundle_size);
-
- bundle += paravirt_nop_bundle_size;
- }
-}
-
-/* helper function */
-unsigned long __init_or_module
-__paravirt_patch_apply_bundle(void *sbundle, void *ebundle, unsigned long type,
- const struct paravirt_patch_bundle_elem *elems,
- unsigned long nelems,
- const struct paravirt_patch_bundle_elem **found)
-{
- unsigned long used = 0;
- unsigned long i;
-
- BUG_ON((((unsigned long)sbundle) % sizeof(bundle_t)) != 0);
- BUG_ON((((unsigned long)ebundle) % sizeof(bundle_t)) != 0);
-
- found = NULL;
- for (i = 0; i < nelems; i++) {
- const struct paravirt_patch_bundle_elem *p = &elems[i];
- if (p->type == type) {
- unsigned long need = p->ebundle - p->sbundle;
- unsigned long room = ebundle - sbundle;
-
- if (found != NULL)
- *found = p;
-
- if (room < need) {
- /* no room to replace. skip it */
- printk(KERN_DEBUG
- "the space is too small to put "
- "bundles. type %ld need %ld room %ld\n",
- type, need, room);
- break;
- }
-
- used = need;
- memcpy(sbundle, p->sbundle, used);
- break;
- }
- }
-
- return used;
-}
-
-void __init_or_module
-paravirt_patch_apply_bundle(const struct paravirt_patch_site_bundle *start,
- const struct paravirt_patch_site_bundle *end)
-{
- const struct paravirt_patch_site_bundle *p;
-
- if (noreplace_paravirt)
- return;
- if (pv_init_ops.patch_bundle == NULL)
- return;
-
- for (p = start; p < end; p++) {
- unsigned long used;
-
- used = (*pv_init_ops.patch_bundle)(p->sbundle, p->ebundle,
- p->type);
- if (used == 0)
- continue;
-
- fill_nop_bundle(p->sbundle + used, p->ebundle);
- paravirt_flush_i_cache_range(p->sbundle,
- p->ebundle - p->sbundle);
- }
- ia64_sync_i();
- ia64_srlz_i();
-}
-
-/*
- * nop.i, nop.m, nop.f instruction are same format.
- * but nop.b has differennt format.
- * This doesn't support nop.b for now.
- */
-static void __init_or_module
-fill_nop_inst(unsigned long stag, unsigned long etag)
-{
- extern const bundle_t paravirt_nop_mfi_inst_bundle[];
- unsigned long tag;
- const ia64_inst_t nop_inst =
- paravirt_read_slot0(paravirt_nop_mfi_inst_bundle);
-
- for (tag = stag; tag < etag; tag = paravirt_get_next_tag(tag))
- paravirt_write_inst(tag, nop_inst);
-}
-
-void __init_or_module
-paravirt_patch_apply_inst(const struct paravirt_patch_site_inst *start,
- const struct paravirt_patch_site_inst *end)
-{
- const struct paravirt_patch_site_inst *p;
-
- if (noreplace_paravirt)
- return;
- if (pv_init_ops.patch_inst == NULL)
- return;
-
- for (p = start; p < end; p++) {
- unsigned long tag;
- bundle_t *sbundle;
- bundle_t *ebundle;
-
- tag = (*pv_init_ops.patch_inst)(p->stag, p->etag, p->type);
- if (tag == p->stag)
- continue;
-
- fill_nop_inst(tag, p->etag);
- sbundle = paravirt_get_bundle(p->stag);
- ebundle = paravirt_get_bundle(p->etag) + 1;
- paravirt_flush_i_cache_range(sbundle, (ebundle - sbundle) *
- sizeof(bundle_t));
- }
- ia64_sync_i();
- ia64_srlz_i();
-}
-#endif /* ASM_SUPPOTED */
-
-/* brl.cond.sptk.many <target64> X3 */
-typedef union inst_x3_op {
- ia64_inst_t inst;
- struct {
- unsigned long qp: 6;
- unsigned long btyp: 3;
- unsigned long unused: 3;
- unsigned long p: 1;
- unsigned long imm20b: 20;
- unsigned long wh: 2;
- unsigned long d: 1;
- unsigned long i: 1;
- unsigned long opcode: 4;
- };
- unsigned long l;
-} inst_x3_op_t;
-
-typedef union inst_x3_imm {
- ia64_inst_t inst;
- struct {
- unsigned long unused: 2;
- unsigned long imm39: 39;
- };
- unsigned long l;
-} inst_x3_imm_t;
-
-void __init_or_module
-paravirt_patch_reloc_brl(unsigned long tag, const void *target)
-{
- unsigned long tag_op = paravirt_get_next_tag(tag);
- unsigned long tag_imm = tag;
- bundle_t *bundle = paravirt_get_bundle(tag);
-
- ia64_inst_t inst_op = paravirt_read_inst(tag_op);
- ia64_inst_t inst_imm = paravirt_read_inst(tag_imm);
-
- inst_x3_op_t inst_x3_op = { .l = inst_op.l };
- inst_x3_imm_t inst_x3_imm = { .l = inst_imm.l };
-
- unsigned long imm60 =
- ((unsigned long)target - (unsigned long)bundle) >> 4;
-
- BUG_ON(paravirt_get_slot(tag) != 1); /* MLX */
- BUG_ON(((unsigned long)target & (sizeof(bundle_t) - 1)) != 0);
-
- /* imm60[59] 1bit */
- inst_x3_op.i = (imm60 >> 59) & 1;
- /* imm60[19:0] 20bit */
- inst_x3_op.imm20b = imm60 & ((1UL << 20) - 1);
- /* imm60[58:20] 39bit */
- inst_x3_imm.imm39 = (imm60 >> 20) & ((1UL << 39) - 1);
-
- inst_op.l = inst_x3_op.l;
- inst_imm.l = inst_x3_imm.l;
-
- paravirt_write_inst(tag_op, inst_op);
- paravirt_write_inst(tag_imm, inst_imm);
-}
-
-/* br.cond.sptk.many <target25> B1 */
-typedef union inst_b1 {
- ia64_inst_t inst;
- struct {
- unsigned long qp: 6;
- unsigned long btype: 3;
- unsigned long unused: 3;
- unsigned long p: 1;
- unsigned long imm20b: 20;
- unsigned long wh: 2;
- unsigned long d: 1;
- unsigned long s: 1;
- unsigned long opcode: 4;
- };
- unsigned long l;
-} inst_b1_t;
-
-void __init
-paravirt_patch_reloc_br(unsigned long tag, const void *target)
-{
- bundle_t *bundle = paravirt_get_bundle(tag);
- ia64_inst_t inst = paravirt_read_inst(tag);
- unsigned long target25 = (unsigned long)target - (unsigned long)bundle;
- inst_b1_t inst_b1;
-
- BUG_ON(((unsigned long)target & (sizeof(bundle_t) - 1)) != 0);
-
- inst_b1.l = inst.l;
- if (target25 & (1UL << 63))
- inst_b1.s = 1;
- else
- inst_b1.s = 0;
-
- inst_b1.imm20b = target25 >> 4;
- inst.l = inst_b1.l;
-
- paravirt_write_inst(tag, inst);
-}
-
-void __init
-__paravirt_patch_apply_branch(
- unsigned long tag, unsigned long type,
- const struct paravirt_patch_branch_target *entries,
- unsigned int nr_entries)
-{
- unsigned int i;
- for (i = 0; i < nr_entries; i++) {
- if (entries[i].type == type) {
- paravirt_patch_reloc_br(tag, entries[i].entry);
- break;
- }
- }
-}
-
-static void __init
-paravirt_patch_apply_branch(const struct paravirt_patch_site_branch *start,
- const struct paravirt_patch_site_branch *end)
-{
- const struct paravirt_patch_site_branch *p;
-
- if (noreplace_paravirt)
- return;
- if (pv_init_ops.patch_branch == NULL)
- return;
-
- for (p = start; p < end; p++)
- (*pv_init_ops.patch_branch)(p->tag, p->type);
-
- ia64_sync_i();
- ia64_srlz_i();
-}
-
-void __init
-paravirt_patch_apply(void)
-{
- extern const char __start_paravirt_bundles[];
- extern const char __stop_paravirt_bundles[];
- extern const char __start_paravirt_insts[];
- extern const char __stop_paravirt_insts[];
- extern const char __start_paravirt_branches[];
- extern const char __stop_paravirt_branches[];
-
- paravirt_patch_apply_bundle((const struct paravirt_patch_site_bundle *)
- __start_paravirt_bundles,
- (const struct paravirt_patch_site_bundle *)
- __stop_paravirt_bundles);
- paravirt_patch_apply_inst((const struct paravirt_patch_site_inst *)
- __start_paravirt_insts,
- (const struct paravirt_patch_site_inst *)
- __stop_paravirt_insts);
- paravirt_patch_apply_branch((const struct paravirt_patch_site_branch *)
- __start_paravirt_branches,
- (const struct paravirt_patch_site_branch *)
- __stop_paravirt_branches);
-}
-
-/*
- * Local variables:
- * mode: C
- * c-set-style: "linux"
- * c-basic-offset: 8
- * tab-width: 8
- * indent-tabs-mode: t
- * End:
- */
diff --git a/arch/ia64/kernel/paravirt_patchlist.c b/arch/ia64/kernel/paravirt_patchlist.c
deleted file mode 100644
index 0a70720662ed..000000000000
--- a/arch/ia64/kernel/paravirt_patchlist.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#include <linux/bug.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <asm/paravirt.h>
-
-#define DECLARE(name) \
- extern unsigned long \
- __ia64_native_start_gate_##name##_patchlist[]; \
- extern unsigned long \
- __ia64_native_end_gate_##name##_patchlist[]
-
-DECLARE(fsyscall);
-DECLARE(brl_fsys_bubble_down);
-DECLARE(vtop);
-DECLARE(mckinley_e9);
-
-extern unsigned long __start_gate_section[];
-
-#define ASSIGN(name) \
- .start_##name##_patchlist = \
- (unsigned long)__ia64_native_start_gate_##name##_patchlist, \
- .end_##name##_patchlist = \
- (unsigned long)__ia64_native_end_gate_##name##_patchlist
-
-struct pv_patchdata pv_patchdata __initdata = {
- ASSIGN(fsyscall),
- ASSIGN(brl_fsys_bubble_down),
- ASSIGN(vtop),
- ASSIGN(mckinley_e9),
-
- .gate_section = (void*)__start_gate_section,
-};
-
-
-unsigned long __init
-paravirt_get_gate_patchlist(enum pv_gate_patchlist type)
-{
-
-#define CASE(NAME, name) \
- case PV_GATE_START_##NAME: \
- return pv_patchdata.start_##name##_patchlist; \
- case PV_GATE_END_##NAME: \
- return pv_patchdata.end_##name##_patchlist; \
-
- switch (type) {
- CASE(FSYSCALL, fsyscall);
- CASE(BRL_FSYS_BUBBLE_DOWN, brl_fsys_bubble_down);
- CASE(VTOP, vtop);
- CASE(MCKINLEY_E9, mckinley_e9);
- default:
- BUG();
- break;
- }
- return 0;
-}
-
-void * __init
-paravirt_get_gate_section(void)
-{
- return pv_patchdata.gate_section;
-}
diff --git a/arch/ia64/kernel/paravirt_patchlist.h b/arch/ia64/kernel/paravirt_patchlist.h
deleted file mode 100644
index 67cffc3643a3..000000000000
--- a/arch/ia64/kernel/paravirt_patchlist.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_patchlist.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#include <asm/native/patchlist.h>
-
diff --git a/arch/ia64/kernel/paravirtentry.S b/arch/ia64/kernel/paravirtentry.S
deleted file mode 100644
index 92d880c4d3d1..000000000000
--- a/arch/ia64/kernel/paravirtentry.S
+++ /dev/null
@@ -1,121 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirtentry.S
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- * VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#include <linux/init.h>
-#include <asm/asmmacro.h>
-#include <asm/asm-offsets.h>
-#include <asm/paravirt_privop.h>
-#include <asm/paravirt_patch.h>
-#include "entry.h"
-
-#define DATA8(sym, init_value) \
- .pushsection .data..read_mostly ; \
- .align 8 ; \
- .global sym ; \
- sym: ; \
- data8 init_value ; \
- .popsection
-
-#define BRANCH(targ, reg, breg, type) \
- PARAVIRT_PATCH_SITE_BR(PARAVIRT_PATCH_TYPE_BR_ ## type) ; \
- ;; \
- movl reg=targ ; \
- ;; \
- ld8 reg=[reg] ; \
- ;; \
- mov breg=reg ; \
- br.cond.sptk.many breg
-
-#define BRANCH_PROC(sym, reg, breg, type) \
- DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ; \
- GLOBAL_ENTRY(paravirt_ ## sym) ; \
- BRANCH(paravirt_ ## sym ## _targ, reg, breg, type) ; \
- END(paravirt_ ## sym)
-
-#define BRANCH_PROC_UNWINFO(sym, reg, breg, type) \
- DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ; \
- GLOBAL_ENTRY(paravirt_ ## sym) ; \
- PT_REGS_UNWIND_INFO(0) ; \
- BRANCH(paravirt_ ## sym ## _targ, reg, breg, type) ; \
- END(paravirt_ ## sym)
-
-
-BRANCH_PROC(switch_to, r22, b7, SWITCH_TO)
-BRANCH_PROC_UNWINFO(leave_syscall, r22, b7, LEAVE_SYSCALL)
-BRANCH_PROC(work_processed_syscall, r2, b7, WORK_PROCESSED_SYSCALL)
-BRANCH_PROC_UNWINFO(leave_kernel, r22, b7, LEAVE_KERNEL)
-
-
-#ifdef CONFIG_MODULES
-#define __INIT_OR_MODULE .text
-#define __INITDATA_OR_MODULE .data
-#else
-#define __INIT_OR_MODULE __INIT
-#define __INITDATA_OR_MODULE __INITDATA
-#endif /* CONFIG_MODULES */
-
- __INIT_OR_MODULE
- GLOBAL_ENTRY(paravirt_fc_i)
- fc.i r32
- br.ret.sptk.many rp
- END(paravirt_fc_i)
- __FINIT
-
- __INIT_OR_MODULE
- .align 32
- GLOBAL_ENTRY(paravirt_nop_b_inst_bundle)
- {
- nop.b 0
- nop.b 0
- nop.b 0
- }
- END(paravirt_nop_b_inst_bundle)
- __FINIT
-
- /* NOTE: nop.[mfi] has same format */
- __INIT_OR_MODULE
- GLOBAL_ENTRY(paravirt_nop_mfi_inst_bundle)
- {
- nop.m 0
- nop.f 0
- nop.i 0
- }
- END(paravirt_nop_mfi_inst_bundle)
- __FINIT
-
- __INIT_OR_MODULE
- GLOBAL_ENTRY(paravirt_nop_bundle)
-paravirt_nop_bundle_start:
- {
- nop 0
- nop 0
- nop 0
- }
-paravirt_nop_bundle_end:
- END(paravirt_nop_bundle)
- __FINIT
-
- __INITDATA_OR_MODULE
- .align 8
- .global paravirt_nop_bundle_size
-paravirt_nop_bundle_size:
- data8 paravirt_nop_bundle_end - paravirt_nop_bundle_start
diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c
index 1cf091793714..944a8e2438a6 100644
--- a/arch/ia64/kernel/patch.c
+++ b/arch/ia64/kernel/patch.c
@@ -7,7 +7,6 @@
#include <linux/init.h>
#include <linux/string.h>
-#include <asm/paravirt.h>
#include <asm/patch.h>
#include <asm/processor.h>
#include <asm/sections.h>
@@ -169,35 +168,16 @@ ia64_patch_mckinley_e9 (unsigned long start, unsigned long end)
ia64_srlz_i();
}
-extern unsigned long ia64_native_fsyscall_table[NR_syscalls];
-extern char ia64_native_fsys_bubble_down[];
-struct pv_fsys_data pv_fsys_data __initdata = {
- .fsyscall_table = (unsigned long *)ia64_native_fsyscall_table,
- .fsys_bubble_down = (void *)ia64_native_fsys_bubble_down,
-};
-
-unsigned long * __init
-paravirt_get_fsyscall_table(void)
-{
- return pv_fsys_data.fsyscall_table;
-}
-
-char * __init
-paravirt_get_fsys_bubble_down(void)
-{
- return pv_fsys_data.fsys_bubble_down;
-}
-
static void __init
patch_fsyscall_table (unsigned long start, unsigned long end)
{
- u64 fsyscall_table = (u64)paravirt_get_fsyscall_table();
+ extern unsigned long fsyscall_table[NR_syscalls];
s32 *offp = (s32 *) start;
u64 ip;
while (offp < (s32 *) end) {
ip = (u64) ia64_imva((char *) offp + *offp);
- ia64_patch_imm64(ip, fsyscall_table);
+ ia64_patch_imm64(ip, (u64) fsyscall_table);
ia64_fc((void *) ip);
++offp;
}
@@ -208,7 +188,7 @@ patch_fsyscall_table (unsigned long start, unsigned long end)
static void __init
patch_brl_fsys_bubble_down (unsigned long start, unsigned long end)
{
- u64 fsys_bubble_down = (u64)paravirt_get_fsys_bubble_down();
+ extern char fsys_bubble_down[];
s32 *offp = (s32 *) start;
u64 ip;
@@ -226,13 +206,13 @@ patch_brl_fsys_bubble_down (unsigned long start, unsigned long end)
void __init
ia64_patch_gate (void)
{
-# define START(name) paravirt_get_gate_patchlist(PV_GATE_START_##name)
-# define END(name) paravirt_get_gate_patchlist(PV_GATE_END_##name)
+# define START(name) ((unsigned long) __start_gate_##name##_patchlist)
+# define END(name) ((unsigned long)__end_gate_##name##_patchlist)
- patch_fsyscall_table(START(FSYSCALL), END(FSYSCALL));
- patch_brl_fsys_bubble_down(START(BRL_FSYS_BUBBLE_DOWN), END(BRL_FSYS_BUBBLE_DOWN));
- ia64_patch_vtop(START(VTOP), END(VTOP));
- ia64_patch_mckinley_e9(START(MCKINLEY_E9), END(MCKINLEY_E9));
+ patch_fsyscall_table(START(fsyscall), END(fsyscall));
+ patch_brl_fsys_bubble_down(START(brl_fsys_bubble_down), END(brl_fsys_bubble_down));
+ ia64_patch_vtop(START(vtop), END(vtop));
+ ia64_patch_mckinley_e9(START(mckinley_e9), END(mckinley_e9));
}
void ia64_patch_phys_stack_reg(unsigned long val)
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index b9761389cb8d..4f118b0d3091 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -50,8 +50,6 @@
#include <asm/mca.h>
#include <asm/meminit.h>
#include <asm/page.h>
-#include <asm/paravirt.h>
-#include <asm/paravirt_patch.h>
#include <asm/patch.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
@@ -360,8 +358,6 @@ reserve_memory (void)
rsvd_region[n].end = (unsigned long) ia64_imva(_end);
n++;
- n += paravirt_reserve_memory(&rsvd_region[n]);
-
#ifdef CONFIG_BLK_DEV_INITRD
if (ia64_boot_param->initrd_start) {
rsvd_region[n].start = (unsigned long)__va(ia64_boot_param->initrd_start);
@@ -528,10 +524,7 @@ setup_arch (char **cmdline_p)
{
unw_init();
- paravirt_arch_setup_early();
-
ia64_patch_vtop((u64) __start___vtop_patchlist, (u64) __end___vtop_patchlist);
- paravirt_patch_apply();
*cmdline_p = __va(ia64_boot_param->command_line);
strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
@@ -594,9 +587,6 @@ setup_arch (char **cmdline_p)
cpu_init(); /* initialize the bootstrap CPU */
mmu_context_init(); /* initialize context_id bitmap */
- paravirt_banner();
- paravirt_arch_setup_console(cmdline_p);
-
#ifdef CONFIG_VT
if (!conswitchp) {
# if defined(CONFIG_DUMMY_CONSOLE)
@@ -616,8 +606,6 @@ setup_arch (char **cmdline_p)
#endif
/* enable IA-64 Machine Check Abort Handling unless disabled */
- if (paravirt_arch_setup_nomca())
- nomca = 1;
if (!nomca)
ia64_mca_init();
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 15051e9c2c6f..0e76fad27975 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -49,7 +49,6 @@
#include <asm/machvec.h>
#include <asm/mca.h>
#include <asm/page.h>
-#include <asm/paravirt.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
@@ -127,7 +126,7 @@ int smp_num_siblings = 1;
volatile int ia64_cpu_to_sapicid[NR_CPUS];
EXPORT_SYMBOL(ia64_cpu_to_sapicid);
-static volatile cpumask_t cpu_callin_map;
+static cpumask_t cpu_callin_map;
struct smp_boot_data smp_boot_data __initdata;
@@ -477,6 +476,7 @@ do_boot_cpu (int sapicid, int cpu, struct task_struct *idle)
for (timeout = 0; timeout < 100000; timeout++) {
if (cpumask_test_cpu(cpu, &cpu_callin_map))
break; /* It has booted */
+ barrier(); /* Make sure we re-read cpu_callin_map */
udelay(100);
}
Dprintk("\n");
@@ -568,7 +568,6 @@ void smp_prepare_boot_cpu(void)
cpumask_set_cpu(smp_processor_id(), &cpu_callin_map);
set_numa_node(cpu_to_node_map[smp_processor_id()]);
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
- paravirt_post_smp_prepare_boot_cpu();
}
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 9a0104a38cd3..c8dbe2acd735 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -25,7 +25,6 @@
#include <asm/machvec.h>
#include <asm/delay.h>
#include <asm/hw_irq.h>
-#include <asm/paravirt.h>
#include <asm/ptrace.h>
#include <asm/sal.h>
#include <asm/sections.h>
@@ -47,33 +46,12 @@ EXPORT_SYMBOL(last_cli_ip);
#endif
-#ifdef CONFIG_PARAVIRT
-/* We need to define a real function for sched_clock, to override the
- weak default version */
-unsigned long long sched_clock(void)
-{
- return paravirt_sched_clock();
-}
-#endif
-
-#ifdef CONFIG_PARAVIRT
-static void
-paravirt_clocksource_resume(struct clocksource *cs)
-{
- if (pv_time_ops.clocksource_resume)
- pv_time_ops.clocksource_resume();
-}
-#endif
-
static struct clocksource clocksource_itc = {
.name = "itc",
.rating = 350,
.read = itc_get_cycles,
.mask = CLOCKSOURCE_MASK(64),
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
-#ifdef CONFIG_PARAVIRT
- .resume = paravirt_clocksource_resume,
-#endif
};
static struct clocksource *itc_clocksource;
@@ -164,9 +142,6 @@ timer_interrupt (int irq, void *dev_id)
profile_tick(CPU_PROFILING);
- if (paravirt_do_steal_accounting(&new_itm))
- goto skip_process_time_accounting;
-
while (1) {
update_process_times(user_mode(get_irq_regs()));
@@ -187,8 +162,6 @@ timer_interrupt (int irq, void *dev_id)
local_irq_disable();
}
-skip_process_time_accounting:
-
do {
/*
* If we're too close to the next clock tick for
@@ -337,8 +310,6 @@ void ia64_init_itm(void)
*/
clocksource_itc.rating = 50;
- paravirt_init_missing_ticks_accounting(smp_processor_id());
-
/* avoid softlock up message when cpu is unplug and plugged again. */
touch_softlockup_watchdog();
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 84f8a52ac5ae..dc506b05ffbd 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -136,27 +136,6 @@ SECTIONS {
__end___mckinley_e9_bundles = .;
}
-#if defined(CONFIG_PARAVIRT)
- . = ALIGN(16);
- .paravirt_bundles : AT(ADDR(.paravirt_bundles) - LOAD_OFFSET) {
- __start_paravirt_bundles = .;
- *(.paravirt_bundles)
- __stop_paravirt_bundles = .;
- }
- . = ALIGN(16);
- .paravirt_insts : AT(ADDR(.paravirt_insts) - LOAD_OFFSET) {
- __start_paravirt_insts = .;
- *(.paravirt_insts)
- __stop_paravirt_insts = .;
- }
- . = ALIGN(16);
- .paravirt_branches : AT(ADDR(.paravirt_branches) - LOAD_OFFSET) {
- __start_paravirt_branches = .;
- *(.paravirt_branches)
- __stop_paravirt_branches = .;
- }
-#endif
-
#if defined(CONFIG_IA64_GENERIC)
/* Machine Vector */
. = ALIGN(16);
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index ba5ba7accd0d..70b40d1205a6 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -11,10 +11,10 @@
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/prefetch.h>
+#include <linux/uaccess.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
-#include <asm/uaccess.h>
extern int die(char *, struct pt_regs *, long);
@@ -96,7 +96,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
/*
* If we're in an interrupt or have no user context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
#ifdef CONFIG_VIRTUAL_MEM_MAP
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index a9b65cf7b34a..7f3028965064 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -34,7 +34,6 @@
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/mca.h>
-#include <asm/paravirt.h>
extern void ia64_tlb_init (void);
@@ -244,7 +243,6 @@ put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot)
static void __init
setup_gate (void)
{
- void *gate_section;
struct page *page;
/*
@@ -252,11 +250,10 @@ setup_gate (void)
* headers etc. and once execute-only page to enable
* privilege-promotion via "epc":
*/
- gate_section = paravirt_get_gate_section();
- page = virt_to_page(ia64_imva(gate_section));
+ page = virt_to_page(ia64_imva(__start_gate_section));
put_kernel_page(page, GATE_ADDR, PAGE_READONLY);
#ifdef HAVE_BUGGY_SEGREL
- page = virt_to_page(ia64_imva(gate_section + PAGE_SIZE));
+ page = virt_to_page(ia64_imva(__start_gate_section + PAGE_SIZE));
put_kernel_page(page, GATE_ADDR + PAGE_SIZE, PAGE_GATE);
#else
put_kernel_page(page, GATE_ADDR + PERCPU_PAGE_SIZE, PAGE_GATE);
@@ -642,8 +639,8 @@ mem_init (void)
* code can tell them apart.
*/
for (i = 0; i < NR_syscalls; ++i) {
+ extern unsigned long fsyscall_table[NR_syscalls];
extern unsigned long sys_call_table[NR_syscalls];
- unsigned long *fsyscall_table = paravirt_get_fsyscall_table();
if (!fsyscall_table[i] || nolwsys)
fsyscall_table[i] = sys_call_table[i] | 1;
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index d4e162d35b34..7cc3be9fa7c6 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -478,9 +478,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
{
- struct pci_controller *controller = bridge->bus->sysdata;
-
- ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+ /*
+ * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+ * here, pci_create_root_bus() has been called by someone else and
+ * sysdata is likely to be different from what we expect. Let it go in
+ * that case.
+ */
+ if (!bridge->dev.parent) {
+ struct pci_controller *controller = bridge->bus->sysdata;
+ ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+ }
return 0;
}
diff --git a/arch/ia64/scripts/pvcheck.sed b/arch/ia64/scripts/pvcheck.sed
deleted file mode 100644
index e59809a3fc01..000000000000
--- a/arch/ia64/scripts/pvcheck.sed
+++ /dev/null
@@ -1,33 +0,0 @@
-#
-# Checker for paravirtualizations of privileged operations.
-#
-s/ssm.*psr\.ic.*/.warning \"ssm psr.ic should not be used directly\"/g
-s/rsm.*psr\.ic.*/.warning \"rsm psr.ic should not be used directly\"/g
-s/ssm.*psr\.i.*/.warning \"ssm psr.i should not be used directly\"/g
-s/rsm.*psr\.i.*/.warning \"rsm psr.i should not be used directly\"/g
-s/ssm.*psr\.dt.*/.warning \"ssm psr.dt should not be used directly\"/g
-s/rsm.*psr\.dt.*/.warning \"rsm psr.dt should not be used directly\"/g
-s/mov.*=.*cr\.ifa/.warning \"cr.ifa should not used directly\"/g
-s/mov.*=.*cr\.itir/.warning \"cr.itir should not used directly\"/g
-s/mov.*=.*cr\.isr/.warning \"cr.isr should not used directly\"/g
-s/mov.*=.*cr\.iha/.warning \"cr.iha should not used directly\"/g
-s/mov.*=.*cr\.ipsr/.warning \"cr.ipsr should not used directly\"/g
-s/mov.*=.*cr\.iim/.warning \"cr.iim should not used directly\"/g
-s/mov.*=.*cr\.iip/.warning \"cr.iip should not used directly\"/g
-s/mov.*=.*cr\.ivr/.warning \"cr.ivr should not used directly\"/g
-s/mov.*=[^\.]*psr/.warning \"psr should not used directly\"/g # avoid ar.fpsr
-s/mov.*=.*ar\.eflags/.warning \"ar.eflags should not used directly\"/g
-s/mov.*=.*ar\.itc.*/.warning \"ar.itc should not used directly\"/g
-s/mov.*cr\.ifa.*=.*/.warning \"cr.ifa should not used directly\"/g
-s/mov.*cr\.itir.*=.*/.warning \"cr.itir should not used directly\"/g
-s/mov.*cr\.iha.*=.*/.warning \"cr.iha should not used directly\"/g
-s/mov.*cr\.ipsr.*=.*/.warning \"cr.ipsr should not used directly\"/g
-s/mov.*cr\.ifs.*=.*/.warning \"cr.ifs should not used directly\"/g
-s/mov.*cr\.iip.*=.*/.warning \"cr.iip should not used directly\"/g
-s/mov.*cr\.kr.*=.*/.warning \"cr.kr should not used directly\"/g
-s/mov.*ar\.eflags.*=.*/.warning \"ar.eflags should not used directly\"/g
-s/itc\.i.*/.warning \"itc.i should not be used directly.\"/g
-s/itc\.d.*/.warning \"itc.d should not be used directly.\"/g
-s/bsw\.0/.warning \"bsw.0 should not be used directly.\"/g
-s/bsw\.1/.warning \"bsw.1 should not be used directly.\"/g
-s/ptc\.ga.*/.warning \"ptc.ga should not be used directly.\"/g
diff --git a/arch/m32r/include/asm/cmpxchg.h b/arch/m32r/include/asm/cmpxchg.h
index de651db20b43..14bf9b739dd2 100644
--- a/arch/m32r/include/asm/cmpxchg.h
+++ b/arch/m32r/include/asm/cmpxchg.h
@@ -107,8 +107,6 @@ __xchg_local(unsigned long x, volatile void *ptr, int size)
((__typeof__(*(ptr)))__xchg_local((unsigned long)(x), (ptr), \
sizeof(*(ptr))))
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long
__cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new)
{
diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 9cc00dbd59ce..0c3f25ee3381 100644
--- a/arch/m32r/include/asm/io.h
+++ b/arch/m32r/include/asm/io.h
@@ -68,6 +68,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
extern void iounmap(volatile void __iomem *addr);
#define ioremap_nocache(off,size) ioremap(off,size)
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
/*
* IO bus memory addresses are also 1:1 with the physical address
diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h
index 71adff209405..cac7014daef3 100644
--- a/arch/m32r/include/asm/uaccess.h
+++ b/arch/m32r/include/asm/uaccess.h
@@ -91,7 +91,8 @@ static inline void set_fs(mm_segment_t s)
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
@@ -155,7 +156,8 @@ extern int fixup_exception(struct pt_regs *regs);
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -175,7 +177,8 @@ extern int fixup_exception(struct pt_regs *regs);
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -194,7 +197,8 @@ extern int fixup_exception(struct pt_regs *regs);
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -274,7 +278,8 @@ do { \
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -568,7 +573,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -588,7 +594,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space.
*
@@ -606,7 +613,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -626,7 +634,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space.
*
@@ -677,7 +686,8 @@ unsigned long clear_user(void __user *mem, unsigned long len);
* strlen_user: - Get the size of a string in user space.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index e3d4d4890104..8f9875b7933d 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -24,9 +24,9 @@
#include <linux/vt_kern.h> /* For unblank_screen() */
#include <linux/highmem.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
#include <asm/m32r.h>
-#include <asm/uaccess.h>
#include <asm/hardirq.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
@@ -111,10 +111,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
mm = tsk->mm;
/*
- * If we're in an interrupt or have no user context or are running in an
- * atomic region then we must not take the fault..
+ * If we're in an interrupt or have no user context or have pagefaults
+ * disabled then we must not take the fault.
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto bad_area_nosemaphore;
if (error_code & ACE_USERMODE)
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index ed1643b4c678..753a6237f99a 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -177,9 +177,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -267,7 +267,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -285,6 +287,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -324,6 +327,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -348,6 +352,7 @@ CONFIG_VETH=m
CONFIG_A2065=y
CONFIG_ARIADNE=y
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_CIRRUS is not set
# CONFIG_NET_VENDOR_HP is not set
@@ -414,7 +419,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_MSM6242=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index d38822b1847e..1f93dcaf02e5 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -277,6 +279,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -306,6 +309,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -327,6 +331,7 @@ CONFIG_NETCONSOLE=m
CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
@@ -375,7 +380,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index c429199cf4a9..831b8b8b92ad 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -281,6 +283,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -315,6 +318,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -337,6 +341,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
CONFIG_ATARILANCE=y
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
@@ -391,7 +396,6 @@ CONFIG_DMASOUND_ATARI=m
CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
-# CONFIG_HID_PLANTRONICS is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_IOMMU_SUPPORT is not set
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 9b880371d642..91fd187c16d5 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -275,6 +277,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -305,6 +308,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE=m
CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
CONFIG_BVME6000_NET=y
# CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 49ae3376e993..9d4934f1d2c3 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -277,6 +279,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -306,6 +309,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -328,6 +332,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
CONFIG_HPLANCE=y
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
@@ -378,7 +383,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index ee143a57058c..72bc187ca995 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -174,9 +174,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -267,7 +267,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -280,6 +282,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -315,6 +318,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -344,6 +348,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
CONFIG_MACMACE=y
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
CONFIG_MAC89x0=y
# CONFIG_NET_VENDOR_INTEL is not set
@@ -400,7 +405,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index c777aa05048f..8fb65535597f 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -184,9 +184,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -277,7 +277,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -299,6 +301,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -348,6 +351,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -384,6 +388,7 @@ CONFIG_MVME147_NET=y
CONFIG_SUN3LANCE=y
CONFIG_MACMACE=y
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
CONFIG_MAC89x0=y
# CONFIG_NET_VENDOR_HP is not set
@@ -468,7 +473,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_MSM6242=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index a7628a85e260..f34491ec0126 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -172,9 +172,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -262,7 +262,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -274,6 +276,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -304,6 +307,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
CONFIG_MVME147_NET=y
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index ebaa68268a4a..3d3614d1b041 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -275,6 +277,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -305,6 +308,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE=m
CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
CONFIG_MVME16x_NET=y
# CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 2c16853aedd3..643e9c93bea7 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -278,6 +280,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -311,6 +314,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -334,6 +338,7 @@ CONFIG_VETH=m
# CONFIG_NET_VENDOR_3COM is not set
# CONFIG_NET_VENDOR_AMD is not set
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_CIRRUS is not set
# CONFIG_NET_VENDOR_HP is not set
@@ -390,7 +395,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index e3056bf0f65b..8fecc5aa166c 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -170,9 +170,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -260,7 +260,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -272,6 +274,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -302,6 +305,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -324,6 +328,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
CONFIG_SUN3LANCE=y
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
CONFIG_SUN3_82586=y
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
@@ -370,7 +375,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 73c36b7a0009..9902c5bfbdc8 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -170,9 +170,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_NFT_MASQ_IPV4=m
CONFIG_NFT_REDIR_IPV4=m
@@ -260,7 +260,9 @@ CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -272,6 +274,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
@@ -302,6 +305,7 @@ CONFIG_DM_RAID=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=m
@@ -324,6 +328,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_VETH=m
CONFIG_SUN3LANCE=y
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
@@ -370,7 +375,6 @@ CONFIG_HID=m
CONFIG_HIDRAW=y
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h
index bc755bc620ad..83b1df80f0ac 100644
--- a/arch/m68k/include/asm/cmpxchg.h
+++ b/arch/m68k/include/asm/cmpxchg.h
@@ -90,7 +90,6 @@ extern unsigned long __invalid_cmpxchg_size(volatile void *,
* indicated by comparing RETURN with OLD.
*/
#ifdef CONFIG_RMW_INSNS
-#define __HAVE_ARCH_CMPXCHG 1
static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
unsigned long new, int size)
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 8955b40a5dc4..618c85d3c786 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -20,6 +20,8 @@
#ifdef __KERNEL__
+#define ARCH_HAS_IOREMAP_WT
+
#include <linux/compiler.h>
#include <asm/raw_io.h>
#include <asm/virtconvert.h>
@@ -465,7 +467,7 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned lon
{
return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
}
-static inline void __iomem *ioremap_writethrough(unsigned long physaddr,
+static inline void __iomem *ioremap_wt(unsigned long physaddr,
unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index a93c8cde4d38..ad7bd40e6742 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -3,6 +3,8 @@
#ifdef __KERNEL__
+#define ARCH_HAS_IOREMAP_WT
+
#include <asm/virtconvert.h>
#include <asm-generic/iomap.h>
@@ -153,7 +155,7 @@ static inline void *ioremap_nocache(unsigned long physaddr, unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
}
-static inline void *ioremap_writethrough(unsigned long physaddr, unsigned long size)
+static inline void *ioremap_wt(unsigned long physaddr, unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
}
diff --git a/arch/m68k/include/asm/irqflags.h b/arch/m68k/include/asm/irqflags.h
index a823cd73dc09..b5941818346f 100644
--- a/arch/m68k/include/asm/irqflags.h
+++ b/arch/m68k/include/asm/irqflags.h
@@ -2,9 +2,6 @@
#define _M68K_IRQFLAGS_H
#include <linux/types.h>
-#ifdef CONFIG_MMU
-#include <linux/preempt_mask.h>
-#endif
#include <linux/preempt.h>
#include <asm/thread_info.h>
#include <asm/entry.h>
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index e546a5534dd4..564665f9af30 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -120,13 +120,16 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
}
EXPORT_SYMBOL(dma_sync_single_for_device);
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir)
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+ int nents, enum dma_data_direction dir)
{
int i;
+ struct scatterlist *sg;
- for (i = 0; i < nents; sg++, i++)
- dma_sync_single_for_device(dev, sg->dma_address, sg->length, dir);
+ for_each_sg(sglist, sg, nents, i) {
+ dma_sync_single_for_device(dev, sg->dma_address, sg->length,
+ dir);
+ }
}
EXPORT_SYMBOL(dma_sync_sg_for_device);
@@ -151,14 +154,16 @@ dma_addr_t dma_map_page(struct device *dev, struct page *page,
}
EXPORT_SYMBOL(dma_map_page);
-int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
enum dma_data_direction dir)
{
int i;
+ struct scatterlist *sg;
- for (i = 0; i < nents; sg++, i++) {
+ for_each_sg(sglist, sg, nents, i) {
sg->dma_address = sg_phys(sg);
- dma_sync_single_for_device(dev, sg->dma_address, sg->length, dir);
+ dma_sync_single_for_device(dev, sg->dma_address, sg->length,
+ dir);
}
return nents;
}
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index b2f04aee46ec..6a94cdd0c830 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -10,10 +10,10 @@
#include <linux/ptrace.h>
#include <linux/interrupt.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
#include <asm/setup.h>
#include <asm/traps.h>
-#include <asm/uaccess.h>
#include <asm/pgalloc.h>
extern void die_if_kernel(char *, struct pt_regs *, long);
@@ -81,7 +81,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index d703d8e26a65..5a696e507930 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -84,7 +84,7 @@ static inline void fence(void)
#define read_barrier_depends() do { } while (0)
#define smp_read_barrier_depends() do { } while (0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_store_release(p, v) \
do { \
diff --git a/arch/metag/include/asm/cmpxchg.h b/arch/metag/include/asm/cmpxchg.h
index b1bc1be8540f..be29e3e44321 100644
--- a/arch/metag/include/asm/cmpxchg.h
+++ b/arch/metag/include/asm/cmpxchg.h
@@ -51,8 +51,6 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
return old;
}
-#define __HAVE_ARCH_CMPXCHG 1
-
#define cmpxchg(ptr, o, n) \
({ \
__typeof__(*(ptr)) _o_ = (o); \
diff --git a/arch/metag/include/asm/io.h b/arch/metag/include/asm/io.h
index d5779b0ec573..9890f21eadbe 100644
--- a/arch/metag/include/asm/io.h
+++ b/arch/metag/include/asm/io.h
@@ -160,6 +160,9 @@ extern void __iounmap(void __iomem *addr);
#define ioremap_wc(offset, size) \
__ioremap((offset), (size), _PAGE_WR_COMBINE)
+#define ioremap_wt(offset, size) \
+ __ioremap((offset), (size), 0)
+
#define iounmap(addr) \
__iounmap(addr)
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 2de5dc695a87..f57edca63609 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -105,7 +105,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
mm = tsk->mm;
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
diff --git a/arch/metag/mm/highmem.c b/arch/metag/mm/highmem.c
index d71f621a2c0b..807f1b1c4e65 100644
--- a/arch/metag/mm/highmem.c
+++ b/arch/metag/mm/highmem.c
@@ -43,7 +43,7 @@ void *kmap_atomic(struct page *page)
unsigned long vaddr;
int type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
@@ -82,6 +82,7 @@ void __kunmap_atomic(void *kvaddr)
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
@@ -95,6 +96,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
unsigned long vaddr;
int type;
+ preempt_disable();
pagefault_disable();
type = kmap_atomic_idx_push();
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index 940f5fc1d1da..39b6315db82e 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -39,10 +39,10 @@ extern resource_size_t isa_mem_base;
extern void iounmap(void __iomem *addr);
extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
-#define ioremap_writethrough(addr, size) ioremap((addr), (size))
#define ioremap_nocache(addr, size) ioremap((addr), (size))
#define ioremap_fullcache(addr, size) ioremap((addr), (size))
#define ioremap_wc(addr, size) ioremap((addr), (size))
+#define ioremap_wt(addr, size) ioremap((addr), (size))
#endif /* CONFIG_MMU */
diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index 468aca8cec0d..b42ed684b945 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -27,8 +27,6 @@
#define PCIBIOS_MIN_IO 0x1000
#define PCIBIOS_MIN_MEM 0x10000000
-struct pci_dev;
-
/* Values for the `which' argument to sys_pciconfig_iobase syscall. */
#define IOBASE_BRIDGE_NUMBER 0
#define IOBASE_MEMORY 1
@@ -44,16 +42,6 @@ struct pci_dev;
*/
#define pcibios_assign_all_busses() 0
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- *strat = PCI_DMA_BURST_INFINITY;
- *strategy_parameter = ~0UL;
-}
-#endif
-
extern int pci_domain_nr(struct pci_bus *bus);
/* Decide whether to display the domain number in /proc */
@@ -83,40 +71,12 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
*/
#define PCI_DMA_BUS_IS_PHYS (1)
-static inline struct resource *pcibios_select_root(struct pci_dev *pdev,
- struct resource *res)
-{
- struct resource *root = NULL;
-
- if (res->flags & IORESOURCE_IO)
- root = &ioport_resource;
- if (res->flags & IORESOURCE_MEM)
- root = &iomem_resource;
-
- return root;
-}
-
extern void pcibios_claim_one_bus(struct pci_bus *b);
extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
extern void pcibios_resource_survey(void);
-extern struct pci_controller *init_phb_dynamic(struct device_node *dn);
-extern int remove_phb_dynamic(struct pci_controller *phb);
-
-extern struct pci_dev *of_create_pci_dev(struct device_node *node,
- struct pci_bus *bus, int devfn);
-
-extern void of_scan_pci_bridge(struct device_node *node,
- struct pci_dev *dev);
-
-extern void of_scan_bus(struct device_node *node, struct pci_bus *bus);
-extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus);
-
-extern int pci_bus_find_capability(struct pci_bus *bus,
- unsigned int devfn, int cap);
-
struct file;
extern pgprot_t pci_phys_mem_access_prot(struct file *file,
unsigned long pfn,
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 62942fd12672..331b0d35f89c 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -178,7 +178,8 @@ extern long __user_bad(void);
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -290,7 +291,8 @@ extern long __user_bad(void);
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
diff --git a/arch/microblaze/kernel/cpu/cpuinfo.c b/arch/microblaze/kernel/cpu/cpuinfo.c
index d1dd6e83d59b..b70bb538f001 100644
--- a/arch/microblaze/kernel/cpu/cpuinfo.c
+++ b/arch/microblaze/kernel/cpu/cpuinfo.c
@@ -47,6 +47,8 @@ const struct cpu_ver_key cpu_ver_lookup[] = {
{"9.1", 0x1d},
{"9.2", 0x1f},
{"9.3", 0x20},
+ {"9.4", 0x21},
+ {"9.5", 0x22},
{NULL, 0},
};
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index ed7ba8a11822..bf4dec229437 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -154,6 +154,7 @@ dma_direct_sync_sg_for_device(struct device *dev,
__dma_sync(sg->dma_address, sg->length, direction);
}
+static
int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t handle, size_t size,
struct dma_attrs *attrs)
diff --git a/arch/microblaze/kernel/kgdb.c b/arch/microblaze/kernel/kgdb.c
index 8736af5806ae..6366f69d118e 100644
--- a/arch/microblaze/kernel/kgdb.c
+++ b/arch/microblaze/kernel/kgdb.c
@@ -32,7 +32,7 @@
#define GDB_RTLBHI 56
/* keep pvr separately because it is unchangeble */
-struct pvr_s pvr;
+static struct pvr_s pvr;
void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
{
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index d46a5ebb7570..177dfc003643 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -107,14 +107,14 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
is_write = 0;
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(faulthandler_disabled() || !mm)) {
if (kernel_mode(regs))
goto bad_area_nosemaphore;
- /* in_atomic() in user mode is really bad,
+ /* faulthandler_disabled() in user mode is really bad,
as is current->mm == NULL. */
- pr_emerg("Page fault in user mode with in_atomic(), mm = %p\n",
- mm);
+ pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n",
+ mm);
pr_emerg("r15 = %lx MSR = %lx\n",
regs->r15, regs->msr);
die("Weird page fault", regs, SIGSEGV);
diff --git a/arch/microblaze/mm/highmem.c b/arch/microblaze/mm/highmem.c
index 5a92576fad92..2fcc5a52d84d 100644
--- a/arch/microblaze/mm/highmem.c
+++ b/arch/microblaze/mm/highmem.c
@@ -37,7 +37,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
unsigned long vaddr;
int idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
@@ -63,6 +63,7 @@ void __kunmap_atomic(void *kvaddr)
if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
pagefault_enable();
+ preempt_enable();
return;
}
@@ -84,5 +85,6 @@ void __kunmap_atomic(void *kvaddr)
#endif
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index f5016656494f..b65edf514b40 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -819,6 +819,7 @@ config CAVIUM_OCTEON_SOC
select SYS_SUPPORTS_64BIT_KERNEL
select SYS_SUPPORTS_BIG_ENDIAN
select EDAC_SUPPORT
+ select EDAC_ATOMIC_SCRUB
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_SUPPORTS_HOTPLUG_CPU if CPU_BIG_ENDIAN
select SYS_HAS_EARLY_PRINTK
diff --git a/arch/mips/ath79/prom.c b/arch/mips/ath79/prom.c
index e1fe63051136..597899ad5438 100644
--- a/arch/mips/ath79/prom.c
+++ b/arch/mips/ath79/prom.c
@@ -1,6 +1,7 @@
/*
* Atheros AR71XX/AR724X/AR913X specific prom routines
*
+ * Copyright (C) 2015 Laurent Fasnacht <l@libres.ch>
* Copyright (C) 2008-2010 Gabor Juhos <juhosg@openwrt.org>
* Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
*
@@ -25,12 +26,14 @@ void __init prom_init(void)
{
fw_init_cmdline();
+#ifdef CONFIG_BLK_DEV_INITRD
/* Read the initrd address from the firmware environment */
initrd_start = fw_getenvl("initrd_start");
if (initrd_start) {
initrd_start = KSEG0ADDR(initrd_start);
initrd_end = initrd_start + fw_getenvl("initrd_size");
}
+#endif
}
void __init prom_free_prom_memory(void)
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index a73c93c3d44a..7fc8397d16f2 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -225,7 +225,7 @@ void __init plat_time_init(void)
ddr_clk_rate = ath79_get_sys_clk_rate("ddr");
ref_clk_rate = ath79_get_sys_clk_rate("ref");
- pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz",
+ pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz\n",
cpu_clk_rate / 1000000, (cpu_clk_rate / 1000) % 1000,
ddr_clk_rate / 1000000, (ddr_clk_rate / 1000) % 1000,
ahb_clk_rate / 1000000, (ahb_clk_rate / 1000) % 1000,
diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c
index 12dccdb38286..af4c712f7afc 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-md5.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c
@@ -69,10 +69,10 @@ static int octeon_md5_init(struct shash_desc *desc)
{
struct md5_state *mctx = shash_desc_ctx(desc);
- mctx->hash[0] = cpu_to_le32(0x67452301);
- mctx->hash[1] = cpu_to_le32(0xefcdab89);
- mctx->hash[2] = cpu_to_le32(0x98badcfe);
- mctx->hash[3] = cpu_to_le32(0x10325476);
+ mctx->hash[0] = cpu_to_le32(MD5_H0);
+ mctx->hash[1] = cpu_to_le32(MD5_H1);
+ mctx->hash[2] = cpu_to_le32(MD5_H2);
+ mctx->hash[3] = cpu_to_le32(MD5_H3);
mctx->byte_count = 0;
return 0;
diff --git a/arch/mips/cobalt/Makefile b/arch/mips/cobalt/Makefile
index 558e94977942..68f0c5871adc 100644
--- a/arch/mips/cobalt/Makefile
+++ b/arch/mips/cobalt/Makefile
@@ -2,7 +2,6 @@
# Makefile for the Cobalt micro systems family specific parts of the kernel
#
-obj-y := buttons.o irq.o lcd.o led.o reset.o rtc.o serial.o setup.o time.o
+obj-y := buttons.o irq.o lcd.o led.o mtd.o reset.o rtc.o serial.o setup.o time.o
obj-$(CONFIG_PCI) += pci.o
-obj-$(CONFIG_MTD_PHYSMAP) += mtd.o
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 002680648dcb..b2a577ebce0b 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -194,7 +194,7 @@ CONFIG_USB_WUSB_CBAF=m
CONFIG_USB_C67X00_HCD=m
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_ROOT_HUB_TT=y
-CONFIG_USB_ISP1760_HCD=m
+CONFIG_USB_ISP1760=m
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_UHCI_HCD=m
CONFIG_USB_R8A66597_HCD=m
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 2b8bbbcb9be0..7ecba84656d4 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -112,8 +112,8 @@
#define __WEAK_LLSC_MB " \n"
#endif
-#define set_mb(var, value) \
- do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) \
+ do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_llsc_mb() __asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 412f945f1f5e..b71ab4a5fd50 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -138,8 +138,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))); \
})
-#define __HAVE_ARCH_CMPXCHG 1
-
#define __cmpxchg_asm(ld, st, m, old, new) \
({ \
__typeof(*(m)) __ret; \
diff --git a/arch/mips/include/asm/edac.h b/arch/mips/include/asm/edac.h
index 94105d3f58f4..980b16527374 100644
--- a/arch/mips/include/asm/edac.h
+++ b/arch/mips/include/asm/edac.h
@@ -5,7 +5,7 @@
/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-static inline void atomic_scrub(void *va, u32 size)
+static inline void edac_atomic_scrub(void *va, u32 size)
{
unsigned long *virt_addr = va;
unsigned long temp;
@@ -21,7 +21,7 @@ static inline void atomic_scrub(void *va, u32 size)
__asm__ __volatile__ (
" .set mips2 \n"
- "1: ll %0, %1 # atomic_scrub \n"
+ "1: ll %0, %1 # edac_atomic_scrub \n"
" addu %0, $0 \n"
" sc %0, %1 \n"
" beqz %0, 1b \n"
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 4c25823563fe..e8c8d9d0c45f 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -839,7 +839,7 @@ static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_free_memslot(struct kvm *kvm,
struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot) {}
diff --git a/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h b/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h
index aa2283e602fc..aa71216edf99 100644
--- a/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h
+++ b/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h
@@ -16,8 +16,4 @@ struct ath79_spi_platform_data {
unsigned num_chipselect;
};
-struct ath79_spi_controller_data {
- unsigned gpio;
-};
-
#endif /* _ATH79_SPI_PLATFORM_H */
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index d9692993fc83..70dcc5498128 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -113,16 +113,6 @@ struct pci_dev;
*/
extern unsigned int PCI_DMA_BUS_IS_PHYS;
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- *strat = PCI_DMA_BURST_INFINITY;
- *strategy_parameter = ~0UL;
-}
-#endif
-
#ifdef CONFIG_PCI_DOMAINS
#define pci_domain_nr(bus) ((struct pci_controller *)(bus)->sysdata)->index
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index 18ae5ddef118..c28a8499aec7 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -113,7 +113,7 @@
#define _PAGE_PRESENT_SHIFT 0
#define _PAGE_PRESENT (1 << _PAGE_PRESENT_SHIFT)
/* R2 or later cores check for RI/XI support to determine _PAGE_READ */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
#define _PAGE_WRITE_SHIFT (_PAGE_PRESENT_SHIFT + 1)
#define _PAGE_WRITE (1 << _PAGE_WRITE_SHIFT)
#else
@@ -135,16 +135,16 @@
#define _PAGE_SPLITTING (1 << _PAGE_SPLITTING_SHIFT)
/* Only R2 or newer cores have the XI bit */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
#define _PAGE_NO_EXEC_SHIFT (_PAGE_SPLITTING_SHIFT + 1)
#else
#define _PAGE_GLOBAL_SHIFT (_PAGE_SPLITTING_SHIFT + 1)
#define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT)
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
#endif /* CONFIG_64BIT && CONFIG_MIPS_HUGE_TLB_SUPPORT */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
/* XI - page cannot be executed */
#ifndef _PAGE_NO_EXEC_SHIFT
#define _PAGE_NO_EXEC_SHIFT (_PAGE_MODIFIED_SHIFT + 1)
@@ -160,10 +160,10 @@
#define _PAGE_GLOBAL_SHIFT (_PAGE_NO_READ_SHIFT + 1)
#define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT)
-#else /* !CONFIG_CPU_MIPSR2 */
+#else /* !CONFIG_CPU_MIPSR2 && !CONFIG_CPU_MIPSR6 */
#define _PAGE_GLOBAL_SHIFT (_PAGE_MODIFIED_SHIFT + 1)
#define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT)
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
#define _PAGE_VALID_SHIFT (_PAGE_GLOBAL_SHIFT + 1)
#define _PAGE_VALID (1 << _PAGE_VALID_SHIFT)
@@ -205,7 +205,7 @@
*/
static inline uint64_t pte_to_entrylo(unsigned long pte_val)
{
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
if (cpu_has_rixi) {
int sa;
#ifdef CONFIG_32BIT
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index e92d6c4b5ed1..7163cd7fdd69 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -104,7 +104,6 @@ do { \
if (test_and_clear_tsk_thread_flag(prev, TIF_USEDMSA)) \
__fpsave = FP_SAVE_VECTOR; \
(last) = resume(prev, next, task_thread_info(next), __fpsave); \
- disable_msa(); \
} while (0)
#define finish_arch_switch(prev) \
@@ -122,6 +121,7 @@ do { \
if (cpu_has_userlocal) \
write_c0_userlocal(current_thread_info()->tp_value); \
__restore_watch(); \
+ disable_msa(); \
} while (0)
#endif /* _ASM_SWITCH_TO_H */
diff --git a/arch/mips/include/asm/topology.h b/arch/mips/include/asm/topology.h
index 3e307ec2afba..7afda4150a59 100644
--- a/arch/mips/include/asm/topology.h
+++ b/arch/mips/include/asm/topology.h
@@ -15,7 +15,7 @@
#define topology_physical_package_id(cpu) (cpu_data[cpu].package)
#define topology_core_id(cpu) (cpu_data[cpu].core)
#define topology_core_cpumask(cpu) (&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu) (&cpu_sibling_map[cpu])
+#define topology_sibling_cpumask(cpu) (&cpu_sibling_map[cpu])
#endif
#endif /* __ASM_TOPOLOGY_H */
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index bf8b32450ef6..9722357d2854 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -103,7 +103,8 @@ extern u64 __ua_limit;
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
@@ -138,7 +139,8 @@ extern u64 __ua_limit;
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -157,7 +159,8 @@ extern u64 __ua_limit;
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -177,7 +180,8 @@ extern u64 __ua_limit;
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -199,7 +203,8 @@ extern u64 __ua_limit;
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -498,7 +503,8 @@ extern void __put_user_unknown(void);
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -517,7 +523,8 @@ extern void __put_user_unknown(void);
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -537,7 +544,8 @@ extern void __put_user_unknown(void);
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -559,7 +567,8 @@ extern void __put_user_unknown(void);
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -815,7 +824,8 @@ extern size_t __copy_user(void *__to, const void *__from, size_t __n);
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -888,7 +898,8 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space.
*
@@ -1075,7 +1086,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -1107,7 +1119,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space.
*
@@ -1329,7 +1342,8 @@ strncpy_from_user(char *__to, const char __user *__from, long __len)
* strlen_user: - Get the size of a string in user space.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
@@ -1398,7 +1412,8 @@ static inline long __strnlen_user(const char __user *s, long n)
* strnlen_user: - Get the size of a string in user space.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index e36515dcd3b2..209e5b76c1bc 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -74,13 +74,12 @@ static inline void cpu_set_fpu_fcsr_mask(struct cpuinfo_mips *c)
{
unsigned long sr, mask, fcsr, fcsr0, fcsr1;
+ fcsr = c->fpu_csr31;
mask = FPU_CSR_ALL_X | FPU_CSR_ALL_E | FPU_CSR_ALL_S | FPU_CSR_RM;
sr = read_c0_status();
__enable_fpu(FPU_AS_IS);
- fcsr = read_32bit_cp1_register(CP1_STATUS);
-
fcsr0 = fcsr & mask;
write_32bit_cp1_register(CP1_STATUS, fcsr0);
fcsr0 = read_32bit_cp1_register(CP1_STATUS);
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index d2bfbc2e8995..3c8a18a00a65 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -29,7 +29,7 @@
int kgdb_early_setup;
#endif
-static unsigned long irq_map[NR_IRQS / BITS_PER_LONG];
+static DECLARE_BITMAP(irq_map, NR_IRQS);
int allocate_irqno(void)
{
@@ -109,7 +109,7 @@ void __init init_IRQ(void)
#endif
}
-#ifdef DEBUG_STACKOVERFLOW
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
static inline void check_stack_overflow(void)
{
unsigned long sp;
diff --git a/arch/mips/kernel/signal-common.h b/arch/mips/kernel/signal-common.h
index 06805e09bcd3..0b85f827cd18 100644
--- a/arch/mips/kernel/signal-common.h
+++ b/arch/mips/kernel/signal-common.h
@@ -28,12 +28,7 @@ extern void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
extern int fpcsr_pending(unsigned int __user *fpcsr);
/* Make sure we will not lose FPU ownership */
-#ifdef CONFIG_PREEMPT
-#define lock_fpu_owner() preempt_disable()
-#define unlock_fpu_owner() preempt_enable()
-#else
-#define lock_fpu_owner() pagefault_disable()
-#define unlock_fpu_owner() pagefault_enable()
-#endif
+#define lock_fpu_owner() ({ preempt_disable(); pagefault_disable(); })
+#define unlock_fpu_owner() ({ pagefault_enable(); preempt_enable(); })
#endif /* __SIGNAL_COMMON_H */
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index fd528d7ea278..336708ae5c5b 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -444,7 +444,7 @@ struct plat_smp_ops bmips5000_smp_ops = {
static void bmips_wr_vec(unsigned long dst, char *start, char *end)
{
memcpy((void *)dst, start, end - start);
- dma_cache_wback((unsigned long)start, end - start);
+ dma_cache_wback(dst, end - start);
local_flush_icache_range(dst, dst + (end - start));
instruction_hazard();
}
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 4b50c5787e25..d5fa3eaf39a1 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -2409,7 +2409,7 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
if (vcpu->mmio_needed == 2)
*gpr = *(int16_t *) run->mmio.data;
else
- *gpr = *(int16_t *) run->mmio.data;
+ *gpr = *(uint16_t *)run->mmio.data;
break;
case 1:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index bb68e8d520e8..cd4c129ce743 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -198,15 +198,16 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
return 0;
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
unsigned long npages = 0;
@@ -393,7 +394,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
kvm_mips_deliver_interrupts(vcpu,
kvm_read_c0_guest_cause(vcpu->arch.cop0));
- kvm_guest_enter();
+ __kvm_guest_enter();
/* Disable hardware page table walking while in guest */
htw_stop();
@@ -403,7 +404,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
/* Re-enable HTW before enabling interrupts */
htw_start();
- kvm_guest_exit();
+ __kvm_guest_exit();
local_irq_enable();
if (vcpu->sigset_active)
@@ -968,6 +969,7 @@ out:
/* Get (and clear) the dirty memory log for a memory slot. */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
unsigned long ga, ga_end;
int is_dirty = 0;
@@ -982,7 +984,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
/* If nothing is dirty, don't bother messing with page tables. */
if (is_dirty) {
- memslot = &kvm->memslots->memslots[log->slot];
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
ga = memslot->base_gfn << PAGE_SHIFT;
ga_end = ga + (memslot->npages << PAGE_SHIFT);
diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S
index 7d12c0dded3d..77e64942f004 100644
--- a/arch/mips/lib/strnlen_user.S
+++ b/arch/mips/lib/strnlen_user.S
@@ -34,7 +34,12 @@ LEAF(__strnlen_\func\()_asm)
FEXPORT(__strnlen_\func\()_nocheck_asm)
move v0, a0
PTR_ADDU a1, a0 # stop pointer
-1: beq v0, a1, 1f # limit reached?
+1:
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
+ .set noat
+ li AT, 1
+#endif
+ beq v0, a1, 1f # limit reached?
.ifeqs "\func", "kernel"
EX(lb, t0, (v0), .Lfault\@)
.else
@@ -42,7 +47,13 @@ FEXPORT(__strnlen_\func\()_nocheck_asm)
.endif
.set noreorder
bnez t0, 1b
-1: PTR_ADDIU v0, 1
+1:
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+ PTR_ADDIU v0, 1
+#else
+ PTR_ADDU v0, AT
+ .set at
+#endif
.set reorder
PTR_SUBU v0, a0
jr ra
diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile
index e70c33fdb881..f2e8153e44f5 100644
--- a/arch/mips/loongson/common/Makefile
+++ b/arch/mips/loongson/common/Makefile
@@ -3,15 +3,13 @@
#
obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
- bonito-irq.o mem.o machtype.o platform.o
+ bonito-irq.o mem.o machtype.o platform.o serial.o
obj-$(CONFIG_PCI) += pci.o
#
# Serial port support
#
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-loongson-serial-$(CONFIG_SERIAL_8250) := serial.o
-obj-y += $(loongson-serial-m) $(loongson-serial-y)
obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o
obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index e3c68b5da18d..509877c6e9d9 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -272,7 +272,7 @@ void loongson3_ipi_interrupt(struct pt_regs *regs)
if (action & SMP_ASK_C0COUNT) {
BUG_ON(cpu != 0);
c0count = read_c0_count();
- for (i = 1; i < loongson_sysconf.nr_cpus; i++)
+ for (i = 1; i < num_possible_cpus(); i++)
per_cpu(core0_c0count, i) = c0count;
}
}
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 0dbb65a51ce5..2e03ab173591 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1372,7 +1372,7 @@ static int probe_scache(void)
scache_size = addr;
c->scache.linesz = 16 << ((config & R4K_CONF_SB) >> 22);
c->scache.ways = 1;
- c->dcache.waybit = 0; /* does not matter */
+ c->scache.waybit = 0; /* does not matter */
return 1;
}
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 7ff8637e530d..36c0f26fac6b 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -21,10 +21,10 @@
#include <linux/module.h>
#include <linux/kprobes.h>
#include <linux/perf_event.h>
+#include <linux/uaccess.h>
#include <asm/branch.h>
#include <asm/mmu_context.h>
-#include <asm/uaccess.h>
#include <asm/ptrace.h>
#include <asm/highmem.h> /* For VMALLOC_END */
#include <linux/kdebug.h>
@@ -94,7 +94,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index da815d295239..11661cbc11a8 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -47,7 +47,7 @@ void *kmap_atomic(struct page *page)
unsigned long vaddr;
int idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
@@ -72,6 +72,7 @@ void __kunmap_atomic(void *kvaddr)
if (vaddr < FIXADDR_START) { // FIXME
pagefault_enable();
+ preempt_enable();
return;
}
@@ -92,6 +93,7 @@ void __kunmap_atomic(void *kvaddr)
#endif
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
@@ -104,6 +106,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
unsigned long vaddr;
int idx, type;
+ preempt_disable();
pagefault_disable();
type = kmap_atomic_idx_push();
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index faa5c9822ecc..198a3147dd7d 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -90,6 +90,7 @@ static void *__kmap_pgprot(struct page *page, unsigned long addr, pgprot_t prot)
BUG_ON(Page_dcache_dirty(page));
+ preempt_disable();
pagefault_disable();
idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
idx += in_interrupt() ? FIX_N_COLOURS : 0;
@@ -152,6 +153,7 @@ void kunmap_coherent(void)
write_c0_entryhi(old_ctx);
local_irq_restore(flags);
pagefault_enable();
+ preempt_enable();
}
void copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 5d6139390bf8..e23fdf2a9c80 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -681,11 +681,7 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx)
sp_off += config_enabled(CONFIG_64BIT) ?
(ARGS_USED_BY_JIT + 1) * RSIZE : RSIZE;
- /*
- * Subtract the bytes for the last registers since we only care about
- * the location on the stack pointer.
- */
- return sp_off - RSIZE;
+ return sp_off;
}
static void build_prologue(struct jit_ctx *ctx)
diff --git a/arch/mips/pci/fixup-cobalt.c b/arch/mips/pci/fixup-cobalt.c
index a138e8ee5cfc..b3ab59318d91 100644
--- a/arch/mips/pci/fixup-cobalt.c
+++ b/arch/mips/pci/fixup-cobalt.c
@@ -13,7 +13,6 @@
#include <linux/kernel.h>
#include <linux/init.h>
-#include <asm/pci.h>
#include <asm/io.h>
#include <asm/gt64120.h>
diff --git a/arch/mips/pci/ops-mace.c b/arch/mips/pci/ops-mace.c
index 6b5821febc38..951d8070fb48 100644
--- a/arch/mips/pci/ops-mace.c
+++ b/arch/mips/pci/ops-mace.c
@@ -8,7 +8,6 @@
#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/types.h>
-#include <asm/pci.h>
#include <asm/ip32/mace.h>
#if 0
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 8b117e638306..c5347d99cf3a 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -20,7 +20,6 @@
#include <linux/of_irq.h>
#include <linux/of_pci.h>
-#include <asm/pci.h>
#include <asm/gpio.h>
#include <asm/addrspace.h>
diff --git a/arch/mips/ralink/ill_acc.c b/arch/mips/ralink/ill_acc.c
index e20b02e3ae28..e10d10b9e82a 100644
--- a/arch/mips/ralink/ill_acc.c
+++ b/arch/mips/ralink/ill_acc.c
@@ -41,7 +41,7 @@ static irqreturn_t ill_acc_irq_handler(int irq, void *_priv)
addr, (type >> ILL_ACC_OFF_S) & ILL_ACC_OFF_M,
type & ILL_ACC_LEN_M);
- rt_memc_w32(REG_ILL_ACC_TYPE, REG_ILL_ACC_TYPE);
+ rt_memc_w32(ILL_INT_STATUS, REG_ILL_ACC_TYPE);
return IRQ_HANDLED;
}
diff --git a/arch/mn10300/include/asm/highmem.h b/arch/mn10300/include/asm/highmem.h
index 2fbbe4d920aa..1ddea5afba09 100644
--- a/arch/mn10300/include/asm/highmem.h
+++ b/arch/mn10300/include/asm/highmem.h
@@ -75,6 +75,7 @@ static inline void *kmap_atomic(struct page *page)
unsigned long vaddr;
int idx, type;
+ preempt_disable();
pagefault_disable();
if (page < highmem_start_page)
return page_address(page);
@@ -98,6 +99,7 @@ static inline void __kunmap_atomic(unsigned long vaddr)
if (vaddr < FIXADDR_START) { /* FIXME */
pagefault_enable();
+ preempt_enable();
return;
}
@@ -122,6 +124,7 @@ static inline void __kunmap_atomic(unsigned long vaddr)
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
#endif /* __KERNEL__ */
diff --git a/arch/mn10300/include/asm/io.h b/arch/mn10300/include/asm/io.h
index cc4a2ba9e228..07c5b4a3903b 100644
--- a/arch/mn10300/include/asm/io.h
+++ b/arch/mn10300/include/asm/io.h
@@ -282,6 +282,7 @@ static inline void __iomem *ioremap_nocache(unsigned long offset, unsigned long
}
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
static inline void iounmap(void __iomem *addr)
{
diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h
index 5f70af25c7d0..c222d1792d5b 100644
--- a/arch/mn10300/include/asm/pci.h
+++ b/arch/mn10300/include/asm/pci.h
@@ -83,19 +83,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
/* implement the pci_ DMA API in terms of the generic device dma_ one */
#include <asm-generic/pci-dma-compat.h>
-static inline struct resource *
-pcibios_select_root(struct pci_dev *pdev, struct resource *res)
-{
- struct resource *root = NULL;
-
- if (res->flags & IORESOURCE_IO)
- root = &ioport_resource;
- if (res->flags & IORESOURCE_MEM)
- root = &iomem_resource;
-
- return root;
-}
-
static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
{
return channel ? 15 : 14;
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 0c2cc5d39c8e..4a1d181ed32f 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -23,8 +23,8 @@
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/vt_kern.h> /* For unblank_screen() */
+#include <linux/uaccess.h>
-#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/hardirq.h>
#include <asm/cpu-regs.h>
@@ -168,7 +168,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
diff --git a/arch/nios2/include/asm/io.h b/arch/nios2/include/asm/io.h
index 6e24d7cceb0c..c5a62da22cd2 100644
--- a/arch/nios2/include/asm/io.h
+++ b/arch/nios2/include/asm/io.h
@@ -46,6 +46,7 @@ static inline void iounmap(void __iomem *addr)
}
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
/* Pages to physical address... */
#define page_to_phys(page) virt_to_phys(page_to_virt(page))
diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c
index 7f4547418ee1..be186a75f622 100644
--- a/arch/nios2/kernel/time.c
+++ b/arch/nios2/kernel/time.c
@@ -8,6 +8,7 @@
* for more details.
*/
+#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/clockchips.h>
#include <linux/clocksource.h>
@@ -106,6 +107,7 @@ cycles_t get_cycles(void)
{
return nios2_timer_read(&nios2_cs.cs);
}
+EXPORT_SYMBOL(get_cycles);
static void nios2_timer_start(struct nios2_timer *timer)
{
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 0c9b6afe69e9..b51878b0c6b8 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -77,7 +77,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index de65f66ea64e..ec2df4bab302 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -142,6 +142,7 @@ static inline void kunmap(struct page *page)
static inline void *kmap_atomic(struct page *page)
{
+ preempt_disable();
pagefault_disable();
return page_address(page);
}
@@ -150,6 +151,7 @@ static inline void __kunmap_atomic(void *addr)
{
flush_kernel_dcache_page_addr(addr);
pagefault_enable();
+ preempt_enable();
}
#define kmap_atomic_prot(page, prot) kmap_atomic(page)
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index dbd13354ec41..0a90b965cccb 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size)
#define xchg(ptr, x) \
((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-#define __HAVE_ARCH_CMPXCHG 1
-
/* bug catcher for when unsupported size is used - won't link */
extern void __cmpxchg_called_with_bad_pointer(void);
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 20df2b04fc09..bf5e044281d6 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -196,25 +196,6 @@ static inline void pcibios_register_hba(struct pci_hba_data *x)
/* export the pci_ DMA API in terms of the dma_ one */
#include <asm-generic/pci-dma-compat.h>
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- unsigned long cacheline_size;
- u8 byte;
-
- pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
- if (byte == 0)
- cacheline_size = 1024;
- else
- cacheline_size = (int) byte * 4;
-
- *strat = PCI_DMA_BURST_MULTIPLE;
- *strategy_parameter = cacheline_size;
-}
-#endif
-
static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
{
return channel ? 15 : 14;
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 47ee620d15d2..6548fd1d2e62 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -26,9 +26,9 @@
#include <linux/console.h>
#include <linux/bug.h>
#include <linux/ratelimit.h>
+#include <linux/uaccess.h>
#include <asm/assembly.h>
-#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/traps.h>
@@ -800,7 +800,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
* unless pagefault_disable() was called before.
*/
- if (fault_space == 0 && !in_atomic())
+ if (fault_space == 0 && !faulthandler_disabled())
{
pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
parisc_terminate("Kernel Fault", regs, code, fault_address);
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index e5120e653240..15503adddf4f 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -15,8 +15,8 @@
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
-#include <asm/uaccess.h>
#include <asm/traps.h>
/* Various important other fields */
@@ -207,7 +207,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
int fault;
unsigned int flags;
- if (in_atomic())
+ if (pagefault_disabled())
goto no_context;
tsk = current;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 190cc48abc0c..5ef27113b898 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -153,6 +153,8 @@ config PPC
select NO_BOOTMEM
select HAVE_GENERIC_RCU_GUP
select HAVE_PERF_EVENTS_NMI if PPC64
+ select EDAC_SUPPORT
+ select EDAC_ATOMIC_SCRUB
config GENERIC_CSUM
def_bool CPU_LITTLE_ENDIAN
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 0efa8f90a8f1..3a510f4a6b68 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -19,6 +19,14 @@ config PPC_WERROR
depends on !PPC_DISABLE_WERROR
default y
+config STRICT_MM_TYPECHECKS
+ bool "Do extra type checking on mm types"
+ default n
+ help
+ This option turns on extra type checking for some mm related types.
+
+ If you don't know what this means, say N.
+
config PRINT_STACK_DEPTH
int "Stack depth to print" if DEBUG_KERNEL
default 64
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 07a480861f78..05f464eb6952 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -66,7 +66,10 @@ endif
UTS_MACHINE := $(OLDARCH)
ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-override CC += -mlittle-endian -mno-strict-align
+override CC += -mlittle-endian
+ifneq ($(COMPILER),clang)
+override CC += -mno-strict-align
+endif
override AS += -mlittle-endian
override LD += -EL
override CROSS32CC += -mlittle-endian
@@ -113,14 +116,14 @@ else
endif
endif
-CFLAGS-$(CONFIG_PPC64) := -mtraceback=no
+CFLAGS-$(CONFIG_PPC64) := $(call cc-option,-mtraceback=no)
ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,-mcall-aixdesc)
+CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2)
else
-CFLAGS-$(CONFIG_PPC64) += -mcall-aixdesc
+CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc)
endif
-CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,-mminimal-toc)
+CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions)
CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 $(MULTIPLEWORD)
@@ -160,7 +163,8 @@ asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
KBUILD_CPPFLAGS += -Iarch/$(ARCH) $(asinstr)
KBUILD_AFLAGS += -Iarch/$(ARCH) $(AFLAGS-y)
-KBUILD_CFLAGS += -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y)
+KBUILD_CFLAGS += $(call cc-option,-msoft-float)
+KBUILD_CFLAGS += -pipe -Iarch/$(ARCH) $(CFLAGS-y)
CPP = $(CC) -E $(KBUILD_CFLAGS)
CHECKFLAGS += -m$(CONFIG_WORD_SIZE) -D__powerpc__ -D__powerpc$(CONFIG_WORD_SIZE)__
@@ -192,7 +196,7 @@ KBUILD_CFLAGS += $(call cc-option,-fno-dwarf2-cfi-asm)
# Never use string load/store instructions as they are
# often slow when they are implemented at all
-KBUILD_CFLAGS += -mno-string
+KBUILD_CFLAGS += $(call cc-option,-mno-string)
ifeq ($(CONFIG_6xx),y)
KBUILD_CFLAGS += -mcpu=powerpc
@@ -269,6 +273,21 @@ bootwrapper_install:
%.dtb: scripts
$(Q)$(MAKE) ARCH=ppc64 $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
+# Used to create 'merged defconfigs'
+# To use it $(call) it with the first argument as the base defconfig
+# and the second argument as a space separated list of .config files to merge,
+# without the .config suffix.
+define merge_into_defconfig
+ $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
+ -m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
+ $(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
+ +$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
+endef
+
+PHONY += pseries_le_defconfig
+pseries_le_defconfig:
+ $(call merge_into_defconfig,pseries_defconfig,le)
+
define archhelp
@echo '* zImage - Build default images selected by kernel config'
@echo ' zImage.* - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)'
@@ -314,7 +333,8 @@ TOUT := .tmp_gas_check
# - Require gcc 4.0 or above on 64-bit
# - gcc-4.2.0 has issues compiling modules on 64-bit
checkbin:
- @if test "$(cc-version)" = "0304" ; then \
+ @if test "${COMPILER}" != "clang" \
+ && test "$(cc-version)" = "0304" ; then \
if ! /bin/echo mftb 5 | $(AS) -v -mppc -many -o $(TOUT) >/dev/null 2>&1 ; then \
echo -n '*** ${VERSION}.${PATCHLEVEL} kernels no longer build '; \
echo 'correctly with gcc-3.4 and your version of binutils.'; \
@@ -322,13 +342,15 @@ checkbin:
false; \
fi ; \
fi
- @if test "$(cc-version)" -lt "0400" \
+ @if test "${COMPILER}" != "clang" \
+ && test "$(cc-version)" -lt "0400" \
&& test "x${CONFIG_PPC64}" = "xy" ; then \
echo -n "Sorry, GCC v4.0 or above is required to build " ; \
echo "the 64-bit powerpc kernel." ; \
false ; \
fi
- @if test "$(cc-fullversion)" = "040200" \
+ @if test "${COMPILER}" != "clang" \
+ && test "$(cc-fullversion)" = "040200" \
&& test "x${CONFIG_MODULES}${CONFIG_PPC64}" = "xyy" ; then \
echo -n '*** GCC-4.2.0 cannot compile the 64-bit powerpc ' ; \
echo 'kernel with modules enabled.' ; \
@@ -336,6 +358,14 @@ checkbin:
echo 'disable kernel modules' ; \
false ; \
fi
+ @if test "x${CONFIG_CPU_LITTLE_ENDIAN}" = "xy" \
+ && $(LD) --version | head -1 | grep ' 2\.24$$' >/dev/null ; then \
+ echo -n '*** binutils 2.24 miscompiles weak symbols ' ; \
+ echo 'in some circumstances.' ; \
+ echo -n '*** Please use a different binutils version.' ; \
+ false ; \
+ fi
+
CLEAN_FILES += $(TOUT)
diff --git a/arch/powerpc/boot/dts/b4qds.dtsi b/arch/powerpc/boot/dts/b4qds.dtsi
index 24ed80dc2120..559d00657fb5 100644
--- a/arch/powerpc/boot/dts/b4qds.dtsi
+++ b/arch/powerpc/boot/dts/b4qds.dtsi
@@ -106,6 +106,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -116,6 +124,10 @@
ranges = <0x0 0xf 0xf4000000 0x2000000>;
};
+ qportals: qman-portals@ff6000000 {
+ ranges = <0x0 0xf 0xf6000000 0x2000000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
index 86161ae6c966..1ea8602e4345 100644
--- a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
@@ -80,20 +80,9 @@
compatible = "fsl,b4420-device-config", "fsl,qoriq-device-config-2.0";
};
-/include/ "qoriq-clockgen2.dtsi"
global-utilities@e1000 {
- compatible = "fsl,b4420-clockgen", "fsl,qoriq-clockgen-2.0";
-
- mux0: mux0@0 {
- #clock-cells = <0>;
- reg = <0x0 0x4>;
- compatible = "fsl,qoriq-core-mux-2.0";
- clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
- <&pll1 0>, <&pll1 1>, <&pll1 2>;
- clock-names = "pll0", "pll0-div2", "pll0-div4",
- "pll1", "pll1-div2", "pll1-div4";
- clock-output-names = "cmux0";
- };
+ compatible = "fsl,b4420-clockgen", "fsl,b4-clockgen",
+ "fsl,qoriq-clockgen-2.0";
};
rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
index f35e9e0a5445..9ba904be39ee 100644
--- a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
@@ -167,6 +167,75 @@
};
};
+&qportals {
+ qportal14: qman-portal@38000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x38000 0x4000>, <0x100e000 0x1000>;
+ interrupts = <132 0x2 0 0>;
+ cell-index = <0xe>;
+ };
+ qportal15: qman-portal@3c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x3c000 0x4000>, <0x100f000 0x1000>;
+ interrupts = <134 0x2 0 0>;
+ cell-index = <0xf>;
+ };
+ qportal16: qman-portal@40000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x40000 0x4000>, <0x1010000 0x1000>;
+ interrupts = <136 0x2 0 0>;
+ cell-index = <0x10>;
+ };
+ qportal17: qman-portal@44000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x44000 0x4000>, <0x1011000 0x1000>;
+ interrupts = <138 0x2 0 0>;
+ cell-index = <0x11>;
+ };
+ qportal18: qman-portal@48000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x48000 0x4000>, <0x1012000 0x1000>;
+ interrupts = <140 0x2 0 0>;
+ cell-index = <0x12>;
+ };
+ qportal19: qman-portal@4c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x4c000 0x4000>, <0x1013000 0x1000>;
+ interrupts = <142 0x2 0 0>;
+ cell-index = <0x13>;
+ };
+ qportal20: qman-portal@50000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x50000 0x4000>, <0x1014000 0x1000>;
+ interrupts = <144 0x2 0 0>;
+ cell-index = <0x14>;
+ };
+ qportal21: qman-portal@54000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x54000 0x4000>, <0x1015000 0x1000>;
+ interrupts = <146 0x2 0 0>;
+ cell-index = <0x15>;
+ };
+ qportal22: qman-portal@58000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x58000 0x4000>, <0x1016000 0x1000>;
+ interrupts = <148 0x2 0 0>;
+ cell-index = <0x16>;
+ };
+ qportal23: qman-portal@5c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x5c000 0x4000>, <0x1017000 0x1000>;
+ interrupts = <150 0x2 0 0>;
+ cell-index = <0x17>;
+ };
+ qportal24: qman-portal@60000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x60000 0x4000>, <0x1018000 0x1000>;
+ interrupts = <152 0x2 0 0>;
+ cell-index = <0x18>;
+ };
+};
+
&soc {
ddr2: memory-controller@9000 {
compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller";
@@ -182,20 +251,9 @@
compatible = "fsl,b4860-device-config", "fsl,qoriq-device-config-2.0";
};
-/include/ "qoriq-clockgen2.dtsi"
global-utilities@e1000 {
- compatible = "fsl,b4860-clockgen", "fsl,qoriq-clockgen-2.0";
-
- mux0: mux0@0 {
- #clock-cells = <0>;
- reg = <0x0 0x4>;
- compatible = "fsl,qoriq-core-mux-2.0";
- clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
- <&pll1 0>, <&pll1 1>, <&pll1 2>;
- clock-names = "pll0", "pll0-div2", "pll0-div4",
- "pll1", "pll1-div2", "pll1-div4";
- clock-output-names = "cmux0";
- };
+ compatible = "fsl,b4860-clockgen", "fsl,b4-clockgen",
+ "fsl,qoriq-clockgen-2.0";
};
rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
index 73136c0029d2..603910ac1db0 100644
--- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10000 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
&ifc {
#address-cells = <2>;
#size-cells = <1>;
@@ -210,6 +220,97 @@
};
};
+&qportals {
+ #address-cells = <0x1>;
+ #size-cells = <0x1>;
+ compatible = "simple-bus";
+
+ qportal0: qman-portal@0 {
+ compatible = "fsl,qman-portal";
+ reg = <0x0 0x4000>, <0x1000000 0x1000>;
+ interrupts = <104 0x2 0 0>;
+ cell-index = <0x0>;
+ };
+ qportal1: qman-portal@4000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+ interrupts = <106 0x2 0 0>;
+ cell-index = <0x1>;
+ };
+ qportal2: qman-portal@8000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+ interrupts = <108 0x2 0 0>;
+ cell-index = <0x2>;
+ };
+ qportal3: qman-portal@c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+ interrupts = <110 0x2 0 0>;
+ cell-index = <0x3>;
+ };
+ qportal4: qman-portal@10000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+ interrupts = <112 0x2 0 0>;
+ cell-index = <0x4>;
+ };
+ qportal5: qman-portal@14000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+ interrupts = <114 0x2 0 0>;
+ cell-index = <0x5>;
+ };
+ qportal6: qman-portal@18000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x18000 0x4000>, <0x1006000 0x1000>;
+ interrupts = <116 0x2 0 0>;
+ cell-index = <0x6>;
+ };
+ qportal7: qman-portal@1c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x1c000 0x4000>, <0x1007000 0x1000>;
+ interrupts = <118 0x2 0 0>;
+ cell-index = <0x7>;
+ };
+ qportal8: qman-portal@20000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x20000 0x4000>, <0x1008000 0x1000>;
+ interrupts = <120 0x2 0 0>;
+ cell-index = <0x8>;
+ };
+ qportal9: qman-portal@24000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x24000 0x4000>, <0x1009000 0x1000>;
+ interrupts = <122 0x2 0 0>;
+ cell-index = <0x9>;
+ };
+ qportal10: qman-portal@28000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x28000 0x4000>, <0x100a000 0x1000>;
+ interrupts = <124 0x2 0 0>;
+ cell-index = <0xa>;
+ };
+ qportal11: qman-portal@2c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x2c000 0x4000>, <0x100b000 0x1000>;
+ interrupts = <126 0x2 0 0>;
+ cell-index = <0xb>;
+ };
+ qportal12: qman-portal@30000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x30000 0x4000>, <0x100c000 0x1000>;
+ interrupts = <128 0x2 0 0>;
+ cell-index = <0xc>;
+ };
+ qportal13: qman-portal@34000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x34000 0x4000>, <0x100d000 0x1000>;
+ interrupts = <130 0x2 0 0>;
+ cell-index = <0xd>;
+ };
+};
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -296,9 +397,21 @@
fsl,liodn-bits = <12>;
};
+/include/ "qoriq-clockgen2.dtsi"
clockgen: global-utilities@e1000 {
compatible = "fsl,b4-clockgen", "fsl,qoriq-clockgen-2.0";
reg = <0xe1000 0x1000>;
+
+ mux0: mux0@0 {
+ #clock-cells = <0>;
+ reg = <0x0 0x4>;
+ compatible = "fsl,qoriq-core-mux-2.0";
+ clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+ <&pll1 0>, <&pll1 1>, <&pll1 2>;
+ clock-names = "pll0", "pll0-div2", "pll0-div4",
+ "pll1", "pll1-div2", "pll1-div4";
+ clock-output-names = "cmux0";
+ };
};
rcpm: global-utilities@e2000 {
@@ -343,6 +456,11 @@
/include/ "qoriq-duart-1.dtsi"
/include/ "qoriq-sec5.3-0.dtsi"
+/include/ "qoriq-qman3.dtsi"
+ qman: qman@318000 {
+ interrupts = <16 2 1 28>;
+ };
+
/include/ "qoriq-bman1.dtsi"
bman: bman@31a000 {
interrupts = <16 2 1 29>;
diff --git a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
index 7780f21430cb..da6d3fc6ba41 100644
--- a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10 0>;
+};
+
&lbc {
#address-cells = <2>;
#size-cells = <1>;
@@ -102,6 +112,31 @@
};
};
+&qportals {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "simple-bus";
+
+ qportal0: qman-portal@0 {
+ compatible = "fsl,qman-portal";
+ reg = <0x0 0x4000>, <0x100000 0x1000>;
+ interrupts = <29 2 0 0>;
+ cell-index = <0>;
+ };
+ qportal1: qman-portal@4000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x4000 0x4000>, <0x101000 0x1000>;
+ interrupts = <31 2 0 0>;
+ cell-index = <1>;
+ };
+ qportal2: qman-portal@8000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x8000 0x4000>, <0x102000 0x1000>;
+ interrupts = <33 2 0 0>;
+ cell-index = <2>;
+ };
+};
+
&bportals {
#address-cells = <1>;
#size-cells = <1>;
@@ -248,6 +283,14 @@
/include/ "pq3-mpic.dtsi"
/include/ "pq3-mpic-timer-B.dtsi"
+ qman: qman@88000 {
+ compatible = "fsl,qman";
+ reg = <0x88000 0x1000>;
+ interrupts = <16 2 0 0>;
+ fsl,qman-portals = <&qportals>;
+ memory-region = <&qman_fqd &qman_pfdr>;
+ };
+
bman: bman@8a000 {
compatible = "fsl,bman";
reg = <0x8a000 0x1000>;
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
index f2feacfd9a25..04ad177b6a12 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10 0>;
+};
+
&lbc {
compatible = "fsl,p2041-elbc", "fsl,elbc", "simple-bus";
interrupts = <25 2 0 0>;
@@ -223,6 +233,8 @@
/include/ "qoriq-bman1-portals.dtsi"
+/include/ "qoriq-qman1-portals.dtsi"
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -370,6 +382,7 @@
/include/ "qoriq-esdhc-0.dtsi"
sdhc@114000 {
+ compatible = "fsl,p2041-esdhc", "fsl,esdhc";
fsl,iommu-parent = <&pamu1>;
fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
sdhci,auto-cmd12;
@@ -415,5 +428,6 @@ crypto: crypto@300000 {
fsl,iommu-parent = <&pamu1>;
};
+/include/ "qoriq-qman1.dtsi"
/include/ "qoriq-bman1.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
index d6fea37395ad..2cab18af6df2 100644
--- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10 0>;
+};
+
&lbc {
compatible = "fsl,p3041-elbc", "fsl,elbc", "simple-bus";
interrupts = <25 2 0 0>;
@@ -250,6 +260,8 @@
/include/ "qoriq-bman1-portals.dtsi"
+/include/ "qoriq-qman1-portals.dtsi"
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -397,6 +409,7 @@
/include/ "qoriq-esdhc-0.dtsi"
sdhc@114000 {
+ compatible = "fsl,p3041-esdhc", "fsl,esdhc";
fsl,iommu-parent = <&pamu1>;
fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
sdhci,auto-cmd12;
@@ -442,5 +455,6 @@ crypto: crypto@300000 {
fsl,iommu-parent = <&pamu1>;
};
+/include/ "qoriq-qman1.dtsi"
/include/ "qoriq-bman1.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
index 89482c9b2301..dfc76bc41cb2 100644
--- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10 0>;
+};
+
&lbc {
compatible = "fsl,p4080-elbc", "fsl,elbc", "simple-bus";
interrupts = <25 2 0 0>;
@@ -250,6 +260,8 @@
/include/ "qoriq-bman1-portals.dtsi"
+/include/ "qoriq-qman1-portals.dtsi"
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -469,6 +481,7 @@
/include/ "qoriq-esdhc-0.dtsi"
sdhc@114000 {
+ compatible = "fsl,p4080-esdhc", "fsl,esdhc";
fsl,iommu-parent = <&pamu1>;
fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
voltage-ranges = <3300 3300>;
@@ -498,5 +511,6 @@ crypto: crypto@300000 {
fsl,iommu-parent = <&pamu1>;
};
+/include/ "qoriq-qman1.dtsi"
/include/ "qoriq-bman1.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
index 6e04851e2fc9..b77923ad72cf 100644
--- a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10000 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
&lbc {
compatible = "fsl,p5020-elbc", "fsl,elbc", "simple-bus";
interrupts = <25 2 0 0>;
@@ -247,6 +257,8 @@
/include/ "qoriq-bman1-portals.dtsi"
+/include/ "qoriq-qman1-portals.dtsi"
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -384,6 +396,7 @@
/include/ "qoriq-esdhc-0.dtsi"
sdhc@114000 {
+ compatible = "fsl,p5020-esdhc", "fsl,esdhc";
fsl,iommu-parent = <&pamu1>;
fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
sdhci,auto-cmd12;
@@ -428,6 +441,7 @@
fsl,iommu-parent = <&pamu1>;
};
+/include/ "qoriq-qman1.dtsi"
/include/ "qoriq-bman1.dtsi"
/include/ "qoriq-raid1.0-0.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
index 5e44dfa1e1a5..6d214526b81b 100644
--- a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10000 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
&lbc {
compatible = "fsl,p5040-elbc", "fsl,elbc", "simple-bus";
interrupts = <25 2 0 0>;
@@ -202,6 +212,8 @@
/include/ "qoriq-bman1-portals.dtsi"
+/include/ "qoriq-qman1-portals.dtsi"
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -362,6 +374,7 @@
/include/ "qoriq-esdhc-0.dtsi"
sdhc@114000 {
+ compatible = "fsl,p5040-esdhc", "fsl,esdhc";
fsl,iommu-parent = <&pamu2>;
fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
sdhci,auto-cmd12;
@@ -407,5 +420,6 @@
fsl,iommu-parent = <&pamu4>;
};
+/include/ "qoriq-qman1.dtsi"
/include/ "qoriq-bman1.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi
index 05d51acafa67..e77e4b4ed53b 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi
@@ -41,61 +41,61 @@
compatible = "fsl,qman-portal";
reg = <0x0 0x4000>, <0x100000 0x1000>;
interrupts = <104 2 0 0>;
- fsl,qman-channel-id = <0x0>;
+ cell-index = <0x0>;
};
qportal1: qman-portal@4000 {
compatible = "fsl,qman-portal";
reg = <0x4000 0x4000>, <0x101000 0x1000>;
interrupts = <106 2 0 0>;
- fsl,qman-channel-id = <1>;
+ cell-index = <1>;
};
qportal2: qman-portal@8000 {
compatible = "fsl,qman-portal";
reg = <0x8000 0x4000>, <0x102000 0x1000>;
interrupts = <108 2 0 0>;
- fsl,qman-channel-id = <2>;
+ cell-index = <2>;
};
qportal3: qman-portal@c000 {
compatible = "fsl,qman-portal";
reg = <0xc000 0x4000>, <0x103000 0x1000>;
interrupts = <110 2 0 0>;
- fsl,qman-channel-id = <3>;
+ cell-index = <3>;
};
qportal4: qman-portal@10000 {
compatible = "fsl,qman-portal";
reg = <0x10000 0x4000>, <0x104000 0x1000>;
interrupts = <112 2 0 0>;
- fsl,qman-channel-id = <4>;
+ cell-index = <4>;
};
qportal5: qman-portal@14000 {
compatible = "fsl,qman-portal";
reg = <0x14000 0x4000>, <0x105000 0x1000>;
interrupts = <114 2 0 0>;
- fsl,qman-channel-id = <5>;
+ cell-index = <5>;
};
qportal6: qman-portal@18000 {
compatible = "fsl,qman-portal";
reg = <0x18000 0x4000>, <0x106000 0x1000>;
interrupts = <116 2 0 0>;
- fsl,qman-channel-id = <6>;
+ cell-index = <6>;
};
qportal7: qman-portal@1c000 {
compatible = "fsl,qman-portal";
reg = <0x1c000 0x4000>, <0x107000 0x1000>;
interrupts = <118 2 0 0>;
- fsl,qman-channel-id = <7>;
+ cell-index = <7>;
};
qportal8: qman-portal@20000 {
compatible = "fsl,qman-portal";
reg = <0x20000 0x4000>, <0x108000 0x1000>;
interrupts = <120 2 0 0>;
- fsl,qman-channel-id = <8>;
+ cell-index = <8>;
};
qportal9: qman-portal@24000 {
compatible = "fsl,qman-portal";
reg = <0x24000 0x4000>, <0x109000 0x1000>;
interrupts = <122 2 0 0>;
- fsl,qman-channel-id = <9>;
+ cell-index = <9>;
};
};
diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
new file mode 100644
index 000000000000..df1f068a5376
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
@@ -0,0 +1,330 @@
+/*
+ * T1023 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&ifc {
+ #address-cells = <2>;
+ #size-cells = <1>;
+ compatible = "fsl,ifc", "simple-bus";
+ interrupts = <25 2 0 0>;
+};
+
+&pci0 {
+ compatible = "fsl,t1023-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+ device_type = "pci";
+ #size-cells = <2>;
+ #address-cells = <3>;
+ bus-range = <0x0 0xff>;
+ interrupts = <20 2 0 0>;
+ fsl,iommu-parent = <&pamu0>;
+ pcie@0 {
+ reg = <0 0 0 0 0>;
+ #interrupt-cells = <1>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ device_type = "pci";
+ interrupts = <20 2 0 0>;
+ interrupt-map-mask = <0xf800 0 0 7>;
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ 0000 0 0 1 &mpic 40 1 0 0
+ 0000 0 0 2 &mpic 1 1 0 0
+ 0000 0 0 3 &mpic 2 1 0 0
+ 0000 0 0 4 &mpic 3 1 0 0
+ >;
+ };
+};
+
+&pci1 {
+ compatible = "fsl,t1023-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+ device_type = "pci";
+ #size-cells = <2>;
+ #address-cells = <3>;
+ bus-range = <0 0xff>;
+ interrupts = <21 2 0 0>;
+ fsl,iommu-parent = <&pamu0>;
+ pcie@0 {
+ reg = <0 0 0 0 0>;
+ #interrupt-cells = <1>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ device_type = "pci";
+ interrupts = <21 2 0 0>;
+ interrupt-map-mask = <0xf800 0 0 7>;
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ 0000 0 0 1 &mpic 41 1 0 0
+ 0000 0 0 2 &mpic 5 1 0 0
+ 0000 0 0 3 &mpic 6 1 0 0
+ 0000 0 0 4 &mpic 7 1 0 0
+ >;
+ };
+};
+
+&pci2 {
+ compatible = "fsl,t1023-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+ device_type = "pci";
+ #size-cells = <2>;
+ #address-cells = <3>;
+ bus-range = <0x0 0xff>;
+ interrupts = <22 2 0 0>;
+ fsl,iommu-parent = <&pamu0>;
+ pcie@0 {
+ reg = <0 0 0 0 0>;
+ #interrupt-cells = <1>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ device_type = "pci";
+ interrupts = <22 2 0 0>;
+ interrupt-map-mask = <0xf800 0 0 7>;
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ 0000 0 0 1 &mpic 42 1 0 0
+ 0000 0 0 2 &mpic 9 1 0 0
+ 0000 0 0 3 &mpic 10 1 0 0
+ 0000 0 0 4 &mpic 11 1 0 0
+ >;
+ };
+};
+
+&dcsr {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,dcsr", "simple-bus";
+
+ dcsr-epu@0 {
+ compatible = "fsl,t1023-dcsr-epu", "fsl,dcsr-epu";
+ interrupts = <52 2 0 0
+ 84 2 0 0
+ 85 2 0 0>;
+ reg = <0x0 0x1000>;
+ };
+ dcsr-npc {
+ compatible = "fsl,t1023-dcsr-cnpc", "fsl,dcsr-cnpc";
+ reg = <0x1000 0x1000 0x1002000 0x10000>;
+ };
+ dcsr-nxc@2000 {
+ compatible = "fsl,dcsr-nxc";
+ reg = <0x2000 0x1000>;
+ };
+ dcsr-corenet {
+ compatible = "fsl,dcsr-corenet";
+ reg = <0x8000 0x1000 0x1A000 0x1000>;
+ };
+ dcsr-ocn@11000 {
+ compatible = "fsl,t1023-dcsr-ocn", "fsl,dcsr-ocn";
+ reg = <0x11000 0x1000>;
+ };
+ dcsr-ddr@12000 {
+ compatible = "fsl,dcsr-ddr";
+ dev-handle = <&ddr1>;
+ reg = <0x12000 0x1000>;
+ };
+ dcsr-nal@18000 {
+ compatible = "fsl,t1023-dcsr-nal", "fsl,dcsr-nal";
+ reg = <0x18000 0x1000>;
+ };
+ dcsr-rcpm@22000 {
+ compatible = "fsl,t1023-dcsr-rcpm", "fsl,dcsr-rcpm";
+ reg = <0x22000 0x1000>;
+ };
+ dcsr-snpc@30000 {
+ compatible = "fsl,t1023-dcsr-snpc", "fsl,dcsr-snpc";
+ reg = <0x30000 0x1000 0x1022000 0x10000>;
+ };
+ dcsr-snpc@31000 {
+ compatible = "fsl,t1023-dcsr-snpc", "fsl,dcsr-snpc";
+ reg = <0x31000 0x1000 0x1042000 0x10000>;
+ };
+ dcsr-cpu-sb-proxy@100000 {
+ compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+ cpu-handle = <&cpu0>;
+ reg = <0x100000 0x1000 0x101000 0x1000>;
+ };
+ dcsr-cpu-sb-proxy@108000 {
+ compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+ cpu-handle = <&cpu1>;
+ reg = <0x108000 0x1000 0x109000 0x1000>;
+ };
+};
+
+&soc {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ device_type = "soc";
+ compatible = "simple-bus";
+
+ soc-sram-error {
+ compatible = "fsl,soc-sram-error";
+ interrupts = <16 2 1 29>;
+ };
+
+ corenet-law@0 {
+ compatible = "fsl,corenet-law";
+ reg = <0x0 0x1000>;
+ fsl,num-laws = <16>;
+ };
+
+ ddr1: memory-controller@8000 {
+ compatible = "fsl,qoriq-memory-controller-v5.0",
+ "fsl,qoriq-memory-controller";
+ reg = <0x8000 0x1000>;
+ interrupts = <16 2 1 23>;
+ };
+
+ cpc: l3-cache-controller@10000 {
+ compatible = "fsl,t1023-l3-cache-controller", "cache";
+ reg = <0x10000 0x1000>;
+ interrupts = <16 2 1 27>;
+ };
+
+ corenet-cf@18000 {
+ compatible = "fsl,corenet2-cf";
+ reg = <0x18000 0x1000>;
+ interrupts = <16 2 1 31>;
+ };
+
+ iommu@20000 {
+ compatible = "fsl,pamu-v1.0", "fsl,pamu";
+ reg = <0x20000 0x1000>;
+ ranges = <0 0x20000 0x1000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ interrupts = <
+ 24 2 0 0
+ 16 2 1 30>;
+ pamu0: pamu@0 {
+ reg = <0 0x1000>;
+ fsl,primary-cache-geometry = <128 1>;
+ fsl,secondary-cache-geometry = <32 2>;
+ };
+ };
+
+/include/ "qoriq-mpic.dtsi"
+
+ guts: global-utilities@e0000 {
+ compatible = "fsl,t1023-device-config", "fsl,qoriq-device-config-2.0";
+ reg = <0xe0000 0xe00>;
+ fsl,has-rstcr;
+ fsl,liodn-bits = <12>;
+ };
+
+/include/ "qoriq-clockgen2.dtsi"
+ global-utilities@e1000 {
+ compatible = "fsl,t1023-clockgen", "fsl,qoriq-clockgen-2.0";
+ mux0: mux0@0 {
+ #clock-cells = <0>;
+ reg = <0x0 4>;
+ compatible = "fsl,core-mux-clock";
+ clocks = <&pll0 0>, <&pll0 1>;
+ clock-names = "pll0_0", "pll0_1";
+ clock-output-names = "cmux0";
+ };
+ mux1: mux1@20 {
+ #clock-cells = <0>;
+ reg = <0x20 4>;
+ compatible = "fsl,core-mux-clock";
+ clocks = <&pll0 0>, <&pll0 1>;
+ clock-names = "pll0_0", "pll0_1";
+ clock-output-names = "cmux1";
+ };
+ };
+
+ rcpm: global-utilities@e2000 {
+ compatible = "fsl,t1023-rcpm", "fsl,qoriq-rcpm-2.0";
+ reg = <0xe2000 0x1000>;
+ };
+
+ sfp: sfp@e8000 {
+ compatible = "fsl,t1023-sfp";
+ reg = <0xe8000 0x1000>;
+ };
+
+ serdes: serdes@ea000 {
+ compatible = "fsl,t1023-serdes";
+ reg = <0xea000 0x4000>;
+ };
+
+ scfg: global-utilities@fc000 {
+ compatible = "fsl,t1023-scfg";
+ reg = <0xfc000 0x1000>;
+ };
+
+/include/ "elo3-dma-0.dtsi"
+/include/ "elo3-dma-1.dtsi"
+
+/include/ "qoriq-espi-0.dtsi"
+ spi@110000 {
+ fsl,espi-num-chipselects = <4>;
+ };
+
+/include/ "qoriq-esdhc-0.dtsi"
+ sdhc@114000 {
+ compatible = "fsl,t1023-esdhc", "fsl,esdhc";
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
+ sdhci,auto-cmd12;
+ no-1-8-v;
+ };
+/include/ "qoriq-i2c-0.dtsi"
+/include/ "qoriq-i2c-1.dtsi"
+/include/ "qoriq-duart-0.dtsi"
+/include/ "qoriq-duart-1.dtsi"
+/include/ "qoriq-gpio-0.dtsi"
+/include/ "qoriq-gpio-1.dtsi"
+/include/ "qoriq-gpio-2.dtsi"
+/include/ "qoriq-gpio-3.dtsi"
+/include/ "qoriq-usb2-mph-0.dtsi"
+ usb0: usb@210000 {
+ compatible = "fsl-usb2-mph-v2.5", "fsl-usb2-mph";
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x520>; /* USB1LIODNR */
+ phy_type = "utmi";
+ port0;
+ };
+/include/ "qoriq-usb2-dr-0.dtsi"
+ usb1: usb@211000 {
+ compatible = "fsl-usb2-dr-v2.5", "fsl-usb2-dr";
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x524>; /* USB2LIODNR */
+ dr_mode = "host";
+ phy_type = "utmi";
+ };
+/include/ "qoriq-sata2-0.dtsi"
+ sata@220000 {
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x550>; /* SATA1LIODNR */
+ };
+
+/include/ "qoriq-sec5.0-0.dtsi"
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi
new file mode 100644
index 000000000000..95e3af8d768e
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi
@@ -0,0 +1,100 @@
+/*
+ * T1024 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "t1023si-post.dtsi"
+
+/ {
+ aliases {
+ vga = &display;
+ display = &display;
+ };
+
+ qe:qe@ffe140000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ device_type = "qe";
+ compatible = "fsl,qe";
+ ranges = <0x0 0xf 0xfe140000 0x40000>;
+ reg = <0xf 0xfe140000 0 0x480>;
+ fsl,qe-num-riscs = <1>;
+ fsl,qe-num-snums = <28>;
+ brg-frequency = <0>;
+ bus-frequency = <0>;
+ };
+};
+
+&soc {
+ display:display@180000 {
+ compatible = "fsl,t1024-diu", "fsl,diu";
+ reg = <0x180000 1000>;
+ interrupts = <74 2 0 0>;
+ };
+};
+
+&qe {
+ qeic: interrupt-controller@80 {
+ interrupt-controller;
+ compatible = "fsl,qe-ic";
+ #address-cells = <0>;
+ #interrupt-cells = <1>;
+ reg = <0x80 0x80>;
+ interrupts = <95 2 0 0 94 2 0 0>; //high:79 low:78
+ };
+
+ ucc@2000 {
+ cell-index = <1>;
+ reg = <0x2000 0x200>;
+ interrupts = <32>;
+ interrupt-parent = <&qeic>;
+ };
+
+ ucc@2200 {
+ cell-index = <3>;
+ reg = <0x2200 0x200>;
+ interrupts = <34>;
+ interrupt-parent = <&qeic>;
+ };
+
+ muram@10000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,qe-muram", "fsl,cpm-muram";
+ ranges = <0x0 0x10000 0x6000>;
+
+ data-only@0 {
+ compatible = "fsl,qe-muram-data", "fsl,cpm-muram-data";
+ reg = <0x0 0x6000>;
+ };
+ };
+};
diff --git a/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi
new file mode 100644
index 000000000000..1f1a9f8474d5
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi
@@ -0,0 +1,87 @@
+/*
+ * T1024/T1023 Silicon/SoC Device Tree Source (pre include)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/include/ "e5500_power_isa.dtsi"
+
+/ {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ interrupt-parent = <&mpic>;
+
+ aliases {
+ ccsr = &soc;
+ dcsr = &dcsr;
+
+ dma0 = &dma0;
+ dma1 = &dma1;
+ serial0 = &serial0;
+ serial1 = &serial1;
+ serial2 = &serial2;
+ serial3 = &serial3;
+ pci0 = &pci0;
+ pci1 = &pci1;
+ pci2 = &pci2;
+ usb0 = &usb0;
+ usb1 = &usb1;
+ sdhc = &sdhc;
+
+ crypto = &crypto;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: PowerPC,e5500@0 {
+ device_type = "cpu";
+ reg = <0>;
+ clocks = <&mux0>;
+ next-level-cache = <&L2_1>;
+ L2_1: l2-cache {
+ next-level-cache = <&cpc>;
+ };
+ };
+ cpu1: PowerPC,e5500@1 {
+ device_type = "cpu";
+ reg = <1>;
+ clocks = <&mux1>;
+ next-level-cache = <&L2_2>;
+ L2_2: l2-cache {
+ next-level-cache = <&cpc>;
+ };
+ };
+ };
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index 5cc01be5b152..9e9f7e201d43 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10000 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
&ifc {
#address-cells = <2>;
#size-cells = <1>;
@@ -280,6 +290,73 @@
};
};
+&qportals {
+ #address-cells = <0x1>;
+ #size-cells = <0x1>;
+ compatible = "simple-bus";
+
+ qportal0: qman-portal@0 {
+ compatible = "fsl,qman-portal";
+ reg = <0x0 0x4000>, <0x1000000 0x1000>;
+ interrupts = <104 0x2 0 0>;
+ cell-index = <0x0>;
+ };
+ qportal1: qman-portal@4000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+ interrupts = <106 0x2 0 0>;
+ cell-index = <0x1>;
+ };
+ qportal2: qman-portal@8000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+ interrupts = <108 0x2 0 0>;
+ cell-index = <0x2>;
+ };
+ qportal3: qman-portal@c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+ interrupts = <110 0x2 0 0>;
+ cell-index = <0x3>;
+ };
+ qportal4: qman-portal@10000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+ interrupts = <112 0x2 0 0>;
+ cell-index = <0x4>;
+ };
+ qportal5: qman-portal@14000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+ interrupts = <114 0x2 0 0>;
+ cell-index = <0x5>;
+ };
+ qportal6: qman-portal@18000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x18000 0x4000>, <0x1006000 0x1000>;
+ interrupts = <116 0x2 0 0>;
+ cell-index = <0x6>;
+ };
+ qportal7: qman-portal@1c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x1c000 0x4000>, <0x1007000 0x1000>;
+ interrupts = <118 0x2 0 0>;
+ cell-index = <0x7>;
+ };
+ qportal8: qman-portal@20000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x20000 0x4000>, <0x1008000 0x1000>;
+ interrupts = <120 0x2 0 0>;
+ cell-index = <0x8>;
+ };
+ qportal9: qman-portal@24000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x24000 0x4000>, <0x1009000 0x1000>;
+ interrupts = <122 0x2 0 0>;
+ cell-index = <0x9>;
+ };
+};
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -463,5 +540,6 @@
fsl,liodn-reg = <&guts 0x554>; /* SATA2LIODNR */
};
/include/ "qoriq-sec5.0-0.dtsi"
+/include/ "qoriq-qman3.dtsi"
/include/ "qoriq-bman1.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index 86bdaf6cbd14..32c790ae7fde 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10000 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
&ifc {
#address-cells = <2>;
#size-cells = <1>;
@@ -326,6 +336,121 @@
};
};
+&qportals {
+ #address-cells = <0x1>;
+ #size-cells = <0x1>;
+ compatible = "simple-bus";
+
+ qportal0: qman-portal@0 {
+ compatible = "fsl,qman-portal";
+ reg = <0x0 0x4000>, <0x1000000 0x1000>;
+ interrupts = <104 0x2 0 0>;
+ cell-index = <0x0>;
+ };
+ qportal1: qman-portal@4000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+ interrupts = <106 0x2 0 0>;
+ cell-index = <0x1>;
+ };
+ qportal2: qman-portal@8000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+ interrupts = <108 0x2 0 0>;
+ cell-index = <0x2>;
+ };
+ qportal3: qman-portal@c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+ interrupts = <110 0x2 0 0>;
+ cell-index = <0x3>;
+ };
+ qportal4: qman-portal@10000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+ interrupts = <112 0x2 0 0>;
+ cell-index = <0x4>;
+ };
+ qportal5: qman-portal@14000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+ interrupts = <114 0x2 0 0>;
+ cell-index = <0x5>;
+ };
+ qportal6: qman-portal@18000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x18000 0x4000>, <0x1006000 0x1000>;
+ interrupts = <116 0x2 0 0>;
+ cell-index = <0x6>;
+ };
+ qportal7: qman-portal@1c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x1c000 0x4000>, <0x1007000 0x1000>;
+ interrupts = <118 0x2 0 0>;
+ cell-index = <0x7>;
+ };
+ qportal8: qman-portal@20000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x20000 0x4000>, <0x1008000 0x1000>;
+ interrupts = <120 0x2 0 0>;
+ cell-index = <0x8>;
+ };
+ qportal9: qman-portal@24000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x24000 0x4000>, <0x1009000 0x1000>;
+ interrupts = <122 0x2 0 0>;
+ cell-index = <0x9>;
+ };
+ qportal10: qman-portal@28000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x28000 0x4000>, <0x100a000 0x1000>;
+ interrupts = <124 0x2 0 0>;
+ cell-index = <0xa>;
+ };
+ qportal11: qman-portal@2c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x2c000 0x4000>, <0x100b000 0x1000>;
+ interrupts = <126 0x2 0 0>;
+ cell-index = <0xb>;
+ };
+ qportal12: qman-portal@30000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x30000 0x4000>, <0x100c000 0x1000>;
+ interrupts = <128 0x2 0 0>;
+ cell-index = <0xc>;
+ };
+ qportal13: qman-portal@34000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x34000 0x4000>, <0x100d000 0x1000>;
+ interrupts = <130 0x2 0 0>;
+ cell-index = <0xd>;
+ };
+ qportal14: qman-portal@38000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x38000 0x4000>, <0x100e000 0x1000>;
+ interrupts = <132 0x2 0 0>;
+ cell-index = <0xe>;
+ };
+ qportal15: qman-portal@3c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x3c000 0x4000>, <0x100f000 0x1000>;
+ interrupts = <134 0x2 0 0>;
+ cell-index = <0xf>;
+ };
+ qportal16: qman-portal@40000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x40000 0x4000>, <0x1010000 0x1000>;
+ interrupts = <136 0x2 0 0>;
+ cell-index = <0x10>;
+ };
+ qportal17: qman-portal@44000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x44000 0x4000>, <0x1011000 0x1000>;
+ interrupts = <138 0x2 0 0>;
+ cell-index = <0x11>;
+ };
+};
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -417,7 +542,7 @@
compatible = "fsl,qoriq-core-mux-2.0";
clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
<&pll1 0>, <&pll1 1>, <&pll1 2>;
- clock-names = "pll0", "pll0-div2", "pll1-div4",
+ clock-names = "pll0", "pll0-div2", "pll0-div4",
"pll1", "pll1-div2", "pll1-div4";
clock-output-names = "cmux0";
};
@@ -428,7 +553,7 @@
compatible = "fsl,qoriq-core-mux-2.0";
clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
<&pll1 0>, <&pll1 1>, <&pll1 2>;
- clock-names = "pll0", "pll0-div2", "pll1-div4",
+ clock-names = "pll0", "pll0-div2", "pll0-div4",
"pll1", "pll1-div2", "pll1-div4";
clock-output-names = "cmux1";
};
@@ -502,6 +627,7 @@
phy_type = "utmi";
};
/include/ "qoriq-sec5.2-0.dtsi"
+/include/ "qoriq-qman3.dtsi"
/include/ "qoriq-bman1.dtsi"
L2_1: l2-cache-controller@c20000 {
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index 4d4f25895d8c..d806360d0f64 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -37,6 +37,16 @@
alloc-ranges = <0 0 0x10000 0>;
};
+&qman_fqd {
+ compatible = "fsl,qman-fqd";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+ compatible = "fsl,qman-pfdr";
+ alloc-ranges = <0 0 0x10000 0>;
+};
+
&ifc {
#address-cells = <2>;
#size-cells = <1>;
@@ -556,6 +566,313 @@
};
};
+&qportals {
+ #address-cells = <0x1>;
+ #size-cells = <0x1>;
+ compatible = "simple-bus";
+
+ qportal0: qman-portal@0 {
+ compatible = "fsl,qman-portal";
+ reg = <0x0 0x4000>, <0x1000000 0x1000>;
+ interrupts = <104 0x2 0 0>;
+ cell-index = <0x0>;
+ };
+ qportal1: qman-portal@4000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+ interrupts = <106 0x2 0 0>;
+ cell-index = <0x1>;
+ };
+ qportal2: qman-portal@8000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+ interrupts = <108 0x2 0 0>;
+ cell-index = <0x2>;
+ };
+ qportal3: qman-portal@c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+ interrupts = <110 0x2 0 0>;
+ cell-index = <0x3>;
+ };
+ qportal4: qman-portal@10000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+ interrupts = <112 0x2 0 0>;
+ cell-index = <0x4>;
+ };
+ qportal5: qman-portal@14000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+ interrupts = <114 0x2 0 0>;
+ cell-index = <0x5>;
+ };
+ qportal6: qman-portal@18000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x18000 0x4000>, <0x1006000 0x1000>;
+ interrupts = <116 0x2 0 0>;
+ cell-index = <0x6>;
+ };
+ qportal7: qman-portal@1c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x1c000 0x4000>, <0x1007000 0x1000>;
+ interrupts = <118 0x2 0 0>;
+ cell-index = <0x7>;
+ };
+ qportal8: qman-portal@20000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x20000 0x4000>, <0x1008000 0x1000>;
+ interrupts = <120 0x2 0 0>;
+ cell-index = <0x8>;
+ };
+ qportal9: qman-portal@24000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x24000 0x4000>, <0x1009000 0x1000>;
+ interrupts = <122 0x2 0 0>;
+ cell-index = <0x9>;
+ };
+ qportal10: qman-portal@28000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x28000 0x4000>, <0x100a000 0x1000>;
+ interrupts = <124 0x2 0 0>;
+ cell-index = <0xa>;
+ };
+ qportal11: qman-portal@2c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x2c000 0x4000>, <0x100b000 0x1000>;
+ interrupts = <126 0x2 0 0>;
+ cell-index = <0xb>;
+ };
+ qportal12: qman-portal@30000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x30000 0x4000>, <0x100c000 0x1000>;
+ interrupts = <128 0x2 0 0>;
+ cell-index = <0xc>;
+ };
+ qportal13: qman-portal@34000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x34000 0x4000>, <0x100d000 0x1000>;
+ interrupts = <130 0x2 0 0>;
+ cell-index = <0xd>;
+ };
+ qportal14: qman-portal@38000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x38000 0x4000>, <0x100e000 0x1000>;
+ interrupts = <132 0x2 0 0>;
+ cell-index = <0xe>;
+ };
+ qportal15: qman-portal@3c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x3c000 0x4000>, <0x100f000 0x1000>;
+ interrupts = <134 0x2 0 0>;
+ cell-index = <0xf>;
+ };
+ qportal16: qman-portal@40000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x40000 0x4000>, <0x1010000 0x1000>;
+ interrupts = <136 0x2 0 0>;
+ cell-index = <0x10>;
+ };
+ qportal17: qman-portal@44000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x44000 0x4000>, <0x1011000 0x1000>;
+ interrupts = <138 0x2 0 0>;
+ cell-index = <0x11>;
+ };
+ qportal18: qman-portal@48000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x48000 0x4000>, <0x1012000 0x1000>;
+ interrupts = <140 0x2 0 0>;
+ cell-index = <0x12>;
+ };
+ qportal19: qman-portal@4c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x4c000 0x4000>, <0x1013000 0x1000>;
+ interrupts = <142 0x2 0 0>;
+ cell-index = <0x13>;
+ };
+ qportal20: qman-portal@50000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x50000 0x4000>, <0x1014000 0x1000>;
+ interrupts = <144 0x2 0 0>;
+ cell-index = <0x14>;
+ };
+ qportal21: qman-portal@54000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x54000 0x4000>, <0x1015000 0x1000>;
+ interrupts = <146 0x2 0 0>;
+ cell-index = <0x15>;
+ };
+ qportal22: qman-portal@58000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x58000 0x4000>, <0x1016000 0x1000>;
+ interrupts = <148 0x2 0 0>;
+ cell-index = <0x16>;
+ };
+ qportal23: qman-portal@5c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x5c000 0x4000>, <0x1017000 0x1000>;
+ interrupts = <150 0x2 0 0>;
+ cell-index = <0x17>;
+ };
+ qportal24: qman-portal@60000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x60000 0x4000>, <0x1018000 0x1000>;
+ interrupts = <152 0x2 0 0>;
+ cell-index = <0x18>;
+ };
+ qportal25: qman-portal@64000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x64000 0x4000>, <0x1019000 0x1000>;
+ interrupts = <154 0x2 0 0>;
+ cell-index = <0x19>;
+ };
+ qportal26: qman-portal@68000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x68000 0x4000>, <0x101a000 0x1000>;
+ interrupts = <156 0x2 0 0>;
+ cell-index = <0x1a>;
+ };
+ qportal27: qman-portal@6c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x6c000 0x4000>, <0x101b000 0x1000>;
+ interrupts = <158 0x2 0 0>;
+ cell-index = <0x1b>;
+ };
+ qportal28: qman-portal@70000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x70000 0x4000>, <0x101c000 0x1000>;
+ interrupts = <160 0x2 0 0>;
+ cell-index = <0x1c>;
+ };
+ qportal29: qman-portal@74000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x74000 0x4000>, <0x101d000 0x1000>;
+ interrupts = <162 0x2 0 0>;
+ cell-index = <0x1d>;
+ };
+ qportal30: qman-portal@78000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x78000 0x4000>, <0x101e000 0x1000>;
+ interrupts = <164 0x2 0 0>;
+ cell-index = <0x1e>;
+ };
+ qportal31: qman-portal@7c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x7c000 0x4000>, <0x101f000 0x1000>;
+ interrupts = <166 0x2 0 0>;
+ cell-index = <0x1f>;
+ };
+ qportal32: qman-portal@80000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x80000 0x4000>, <0x1020000 0x1000>;
+ interrupts = <168 0x2 0 0>;
+ cell-index = <0x20>;
+ };
+ qportal33: qman-portal@84000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x84000 0x4000>, <0x1021000 0x1000>;
+ interrupts = <170 0x2 0 0>;
+ cell-index = <0x21>;
+ };
+ qportal34: qman-portal@88000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x88000 0x4000>, <0x1022000 0x1000>;
+ interrupts = <172 0x2 0 0>;
+ cell-index = <0x22>;
+ };
+ qportal35: qman-portal@8c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x8c000 0x4000>, <0x1023000 0x1000>;
+ interrupts = <174 0x2 0 0>;
+ cell-index = <0x23>;
+ };
+ qportal36: qman-portal@90000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x90000 0x4000>, <0x1024000 0x1000>;
+ interrupts = <384 0x2 0 0>;
+ cell-index = <0x24>;
+ };
+ qportal37: qman-portal@94000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x94000 0x4000>, <0x1025000 0x1000>;
+ interrupts = <386 0x2 0 0>;
+ cell-index = <0x25>;
+ };
+ qportal38: qman-portal@98000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x98000 0x4000>, <0x1026000 0x1000>;
+ interrupts = <388 0x2 0 0>;
+ cell-index = <0x26>;
+ };
+ qportal39: qman-portal@9c000 {
+ compatible = "fsl,qman-portal";
+ reg = <0x9c000 0x4000>, <0x1027000 0x1000>;
+ interrupts = <390 0x2 0 0>;
+ cell-index = <0x27>;
+ };
+ qportal40: qman-portal@a0000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xa0000 0x4000>, <0x1028000 0x1000>;
+ interrupts = <392 0x2 0 0>;
+ cell-index = <0x28>;
+ };
+ qportal41: qman-portal@a4000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xa4000 0x4000>, <0x1029000 0x1000>;
+ interrupts = <394 0x2 0 0>;
+ cell-index = <0x29>;
+ };
+ qportal42: qman-portal@a8000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xa8000 0x4000>, <0x102a000 0x1000>;
+ interrupts = <396 0x2 0 0>;
+ cell-index = <0x2a>;
+ };
+ qportal43: qman-portal@ac000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xac000 0x4000>, <0x102b000 0x1000>;
+ interrupts = <398 0x2 0 0>;
+ cell-index = <0x2b>;
+ };
+ qportal44: qman-portal@b0000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xb0000 0x4000>, <0x102c000 0x1000>;
+ interrupts = <400 0x2 0 0>;
+ cell-index = <0x2c>;
+ };
+ qportal45: qman-portal@b4000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xb4000 0x4000>, <0x102d000 0x1000>;
+ interrupts = <402 0x2 0 0>;
+ cell-index = <0x2d>;
+ };
+ qportal46: qman-portal@b8000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xb8000 0x4000>, <0x102e000 0x1000>;
+ interrupts = <404 0x2 0 0>;
+ cell-index = <0x2e>;
+ };
+ qportal47: qman-portal@bc000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xbc000 0x4000>, <0x102f000 0x1000>;
+ interrupts = <406 0x2 0 0>;
+ cell-index = <0x2f>;
+ };
+ qportal48: qman-portal@c0000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xc0000 0x4000>, <0x1030000 0x1000>;
+ interrupts = <408 0x2 0 0>;
+ cell-index = <0x30>;
+ };
+ qportal49: qman-portal@c4000 {
+ compatible = "fsl,qman-portal";
+ reg = <0xc4000 0x4000>, <0x1031000 0x1000>;
+ interrupts = <410 0x2 0 0>;
+ cell-index = <0x31>;
+ };
+};
+
&soc {
#address-cells = <1>;
#size-cells = <1>;
@@ -748,6 +1065,7 @@
/include/ "qoriq-sata2-0.dtsi"
/include/ "qoriq-sata2-1.dtsi"
/include/ "qoriq-sec5.0-0.dtsi"
+/include/ "qoriq-qman3.dtsi"
/include/ "qoriq-bman1.dtsi"
L2_1: l2-cache-controller@c20000 {
diff --git a/arch/powerpc/boot/dts/kmcoge4.dts b/arch/powerpc/boot/dts/kmcoge4.dts
index 97e6d11d1e6d..48dab6a50437 100644
--- a/arch/powerpc/boot/dts/kmcoge4.dts
+++ b/arch/powerpc/boot/dts/kmcoge4.dts
@@ -34,6 +34,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -44,6 +52,10 @@
ranges = <0x0 0xf 0xf4000000 0x200000>;
};
+ qportals: qman-portals@ff4200000 {
+ ranges = <0x0 0xf 0xf4200000 0x200000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/oca4080.dts b/arch/powerpc/boot/dts/oca4080.dts
index eb76caae11d9..42796c5b0561 100644
--- a/arch/powerpc/boot/dts/oca4080.dts
+++ b/arch/powerpc/boot/dts/oca4080.dts
@@ -58,6 +58,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -68,6 +76,10 @@
ranges = <0x0 0xf 0xf4000000 0x200000>;
};
+ qportals: qman-portals@ff4200000 {
+ ranges = <0x0 0xf 0xf4200000 0x200000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p1023rdb.dts b/arch/powerpc/boot/dts/p1023rdb.dts
index 9236e3742a23..05a00a4d2861 100644
--- a/arch/powerpc/boot/dts/p1023rdb.dts
+++ b/arch/powerpc/boot/dts/p1023rdb.dts
@@ -56,6 +56,18 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
+ };
+
+ qportals: qman-portals@ff000000 {
+ ranges = <0x0 0xf 0xff000000 0x200000>;
};
bportals: bman-portals@ff200000 {
diff --git a/arch/powerpc/boot/dts/p2041rdb.dts b/arch/powerpc/boot/dts/p2041rdb.dts
index c1e69dc7188e..d2bb0765bd5a 100644
--- a/arch/powerpc/boot/dts/p2041rdb.dts
+++ b/arch/powerpc/boot/dts/p2041rdb.dts
@@ -54,6 +54,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
ranges = <0x0 0xf 0xf4000000 0x200000>;
};
+ qportals: qman-portals@ff4200000 {
+ ranges = <0x0 0xf 0xf4200000 0x200000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p3041ds.dts b/arch/powerpc/boot/dts/p3041ds.dts
index 2192fe94866d..eca6c697cfd7 100644
--- a/arch/powerpc/boot/dts/p3041ds.dts
+++ b/arch/powerpc/boot/dts/p3041ds.dts
@@ -54,6 +54,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
ranges = <0x0 0xf 0xf4000000 0x200000>;
};
+ qportals: qman-portals@ff4200000 {
+ ranges = <0x0 0xf 0xf4200000 0x200000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p4080ds.dts b/arch/powerpc/boot/dts/p4080ds.dts
index fad441654642..4f80c9d02c27 100644
--- a/arch/powerpc/boot/dts/p4080ds.dts
+++ b/arch/powerpc/boot/dts/p4080ds.dts
@@ -54,6 +54,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
ranges = <0x0 0xf 0xf4000000 0x200000>;
};
+ qportals: qman-portals@ff4200000 {
+ ranges = <0x0 0xf 0xf4200000 0x200000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p5020ds.dts b/arch/powerpc/boot/dts/p5020ds.dts
index 7382636dc560..d0309a8b9749 100644
--- a/arch/powerpc/boot/dts/p5020ds.dts
+++ b/arch/powerpc/boot/dts/p5020ds.dts
@@ -54,6 +54,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
ranges = <0x0 0xf 0xf4000000 0x200000>;
};
+ qportals: qman-portals@ff4200000 {
+ ranges = <0x0 0xf 0xf4200000 0x200000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p5040ds.dts b/arch/powerpc/boot/dts/p5040ds.dts
index 35dabf5b6098..05168236d3ab 100644
--- a/arch/powerpc/boot/dts/p5040ds.dts
+++ b/arch/powerpc/boot/dts/p5040ds.dts
@@ -54,6 +54,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
ranges = <0x0 0xf 0xf4000000 0x200000>;
};
+ qportals: qman-portals@ff4200000 {
+ ranges = <0x0 0xf 0xf4200000 0x200000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t1023rdb.dts b/arch/powerpc/boot/dts/t1023rdb.dts
new file mode 100644
index 000000000000..06b090aba066
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1023rdb.dts
@@ -0,0 +1,151 @@
+/*
+ * T1023 RDB Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t102xsi-pre.dtsi"
+
+/ {
+ model = "fsl,T1023RDB";
+ compatible = "fsl,T1023RDB";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ interrupt-parent = <&mpic>;
+
+ ifc: localbus@ffe124000 {
+ reg = <0xf 0xfe124000 0 0x2000>;
+ ranges = <0 0 0xf 0xe8000000 0x08000000
+ 1 0 0xf 0xff800000 0x00010000>;
+
+ nor@0,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ status = "disabled";
+ compatible = "cfi-flash";
+ reg = <0x0 0x0 0x8000000>;
+ bank-width = <2>;
+ device-width = <1>;
+ };
+
+ nand@1,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,ifc-nand";
+ reg = <0x2 0x0 0x10000>;
+ };
+ };
+
+ memory {
+ device_type = "memory";
+ };
+
+ dcsr: dcsr@f00000000 {
+ ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+ };
+
+ soc: soc@ffe000000 {
+ ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+ reg = <0xf 0xfe000000 0 0x00001000>;
+ spi@110000 {
+ flash@0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "spansion,s25fl512s";
+ reg = <0>;
+ spi-max-frequency = <10000000>; /* input clk */
+ };
+ };
+
+ i2c@118000 {
+ eeprom@50 {
+ compatible = "st,m24256";
+ reg = <0x50>;
+ };
+
+ rtc@68 {
+ compatible = "dallas,ds1339";
+ reg = <0x68>;
+ interrupts = <0x5 0x1 0 0>;
+ };
+ };
+
+ i2c@118100 {
+ };
+ };
+
+ pci0: pcie@ffe240000 {
+ reg = <0xf 0xfe240000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8000000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci1: pcie@ffe250000 {
+ reg = <0xf 0xfe250000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x10000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8010000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci2: pcie@ffe260000 {
+ reg = <0xf 0xfe260000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+};
+
+/include/ "fsl/t1023si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1024qds.dts b/arch/powerpc/boot/dts/t1024qds.dts
new file mode 100644
index 000000000000..f31fabb383b9
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1024qds.dts
@@ -0,0 +1,251 @@
+/*
+ * T1024 QDS Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t102xsi-pre.dtsi"
+
+/ {
+ model = "fsl,T1024QDS";
+ compatible = "fsl,T1024QDS";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ interrupt-parent = <&mpic>;
+
+ ifc: localbus@ffe124000 {
+ reg = <0xf 0xfe124000 0 0x2000>;
+ ranges = <0 0 0xf 0xe8000000 0x08000000
+ 2 0 0xf 0xff800000 0x00010000
+ 3 0 0xf 0xffdf0000 0x00008000>;
+
+ nor@0,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "cfi-flash";
+ reg = <0x0 0x0 0x8000000>;
+ bank-width = <2>;
+ device-width = <1>;
+ };
+
+ nand@2,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,ifc-nand";
+ reg = <0x2 0x0 0x10000>;
+ };
+
+ board-control@3,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,tetra-fpga", "fsl,fpga-qixis";
+ reg = <3 0 0x300>;
+ ranges = <0 3 0 0x300>;
+ };
+ };
+
+ memory {
+ device_type = "memory";
+ };
+
+ dcsr: dcsr@f00000000 {
+ ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+ };
+
+ soc: soc@ffe000000 {
+ ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+ reg = <0xf 0xfe000000 0 0x00001000>;
+ spi@110000 {
+ flash@0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "micron,n25q128a11"; /* 16MB */
+ reg = <0>;
+ spi-max-frequency = <10000000>;
+ };
+
+ flash@1 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "sst,sst25wf040"; /* 512KB */
+ reg = <1>;
+ spi-max-frequency = <10000000>;
+ };
+
+ flash@2 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "eon,en25s64"; /* 8MB */
+ reg = <2>;
+ spi-max-frequency = <10000000>;
+ };
+
+ slic@2 {
+ compatible = "maxim,ds26522";
+ reg = <2>;
+ spi-max-frequency = <2000000>;
+ };
+
+ slic@3 {
+ compatible = "maxim,ds26522";
+ reg = <3>;
+ spi-max-frequency = <2000000>;
+ };
+ };
+
+ i2c@118000 {
+ pca9547@77 {
+ compatible = "nxp,pca9547";
+ reg = <0x77>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ i2c@0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0>;
+
+ eeprom@50 {
+ compatible = "atmel,24c512";
+ reg = <0x50>;
+ };
+
+ eeprom@51 {
+ compatible = "atmel,24c02";
+ reg = <0x51>;
+ };
+
+ eeprom@57 {
+ compatible = "atmel,24c02";
+ reg = <0x57>;
+ };
+ };
+
+ i2c@2 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x2>;
+
+ ina220@40 {
+ compatible = "ti,ina220";
+ reg = <0x40>;
+ shunt-resistor = <1000>;
+ };
+
+ ina220@41 {
+ compatible = "ti,ina220";
+ reg = <0x41>;
+ shunt-resistor = <1000>;
+ };
+ };
+
+ i2c@3 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x3>;
+
+ adt7461@4c {
+ /* Thermal Monitor */
+ compatible = "adi,adt7461";
+ reg = <0x4c>;
+ };
+
+ eeprom@55 {
+ compatible = "atmel,24c02";
+ reg = <0x55>;
+ };
+
+ eeprom@56 {
+ compatible = "atmel,24c512";
+ reg = <0x56>;
+ };
+
+ eeprom@57 {
+ compatible = "atmel,24c512";
+ reg = <0x57>;
+ };
+ };
+ };
+ rtc@68 {
+ compatible = "dallas,ds3232";
+ reg = <0x68>;
+ interrupts = <0x5 0x1 0 0>;
+ };
+ };
+ };
+
+ pci0: pcie@ffe240000 {
+ reg = <0xf 0xfe240000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8000000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci1: pcie@ffe250000 {
+ reg = <0xf 0xfe250000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x10000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8010000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci2: pcie@ffe260000 {
+ reg = <0xf 0xfe260000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+};
+
+/include/ "fsl/t1024si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1024rdb.dts b/arch/powerpc/boot/dts/t1024rdb.dts
new file mode 100644
index 000000000000..733e723ffed6
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1024rdb.dts
@@ -0,0 +1,185 @@
+/*
+ * T1024 RDB Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t102xsi-pre.dtsi"
+
+/ {
+ model = "fsl,T1024RDB";
+ compatible = "fsl,T1024RDB";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ interrupt-parent = <&mpic>;
+
+ ifc: localbus@ffe124000 {
+ reg = <0xf 0xfe124000 0 0x2000>;
+ ranges = <0 0 0xf 0xe8000000 0x08000000
+ 2 0 0xf 0xff800000 0x00010000
+ 3 0 0xf 0xffdf0000 0x00008000>;
+
+ nor@0,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "cfi-flash";
+ reg = <0x0 0x0 0x8000000>;
+ bank-width = <2>;
+ device-width = <1>;
+ };
+
+ nand@1,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,ifc-nand";
+ reg = <0x2 0x0 0x10000>;
+ };
+
+ board-control@2,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,t1024-cpld";
+ reg = <3 0 0x300>;
+ ranges = <0 3 0 0x300>;
+ bank-width = <1>;
+ device-width = <1>;
+ };
+ };
+
+ memory {
+ device_type = "memory";
+ };
+
+ dcsr: dcsr@f00000000 {
+ ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+ };
+
+ soc: soc@ffe000000 {
+ ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+ reg = <0xf 0xfe000000 0 0x00001000>;
+ spi@110000 {
+ flash@0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "micron,n25q512ax3";
+ reg = <0>;
+ spi-max-frequency = <10000000>; /* input clk */
+ };
+
+ slic@1 {
+ compatible = "maxim,ds26522";
+ reg = <1>;
+ spi-max-frequency = <2000000>;
+ };
+
+ slic@2 {
+ compatible = "maxim,ds26522";
+ reg = <2>;
+ spi-max-frequency = <2000000>;
+ };
+ };
+
+ i2c@118000 {
+ adt7461@4c {
+ /* Thermal Monitor */
+ compatible = "adi,adt7461";
+ reg = <0x4c>;
+ };
+
+ eeprom@50 {
+ compatible = "atmel,24c256";
+ reg = <0x50>;
+ };
+
+ rtc@68 {
+ compatible = "dallas,ds1339";
+ reg = <0x68>;
+ interrupts = <0x1 0x1 0 0>;
+ };
+ };
+
+ i2c@118100 {
+ pca9546@77 {
+ compatible = "nxp,pca9546";
+ reg = <0x77>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ };
+ };
+ };
+
+ pci0: pcie@ffe240000 {
+ reg = <0xf 0xfe240000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8000000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci1: pcie@ffe250000 {
+ reg = <0xf 0xfe250000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x10000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8010000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci2: pcie@ffe260000 {
+ reg = <0xf 0xfe260000 0 0x10000>;
+ ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+ pcie@0 {
+ ranges = <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+};
+
+/include/ "fsl/t1024si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t104xqds.dtsi b/arch/powerpc/boot/dts/t104xqds.dtsi
index f7e9bfbeefc7..1498d1e4aecf 100644
--- a/arch/powerpc/boot/dts/t104xqds.dtsi
+++ b/arch/powerpc/boot/dts/t104xqds.dtsi
@@ -47,6 +47,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
ifc: localbus@ffe124000 {
@@ -92,6 +100,10 @@
ranges = <0x0 0xf 0xf4000000 0x2000000>;
};
+ qportals: qman-portals@ff6000000 {
+ ranges = <0x0 0xf 0xf6000000 0x2000000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t104xrdb.dtsi b/arch/powerpc/boot/dts/t104xrdb.dtsi
index 76e07a3f2ca8..830ea484295b 100644
--- a/arch/powerpc/boot/dts/t104xrdb.dtsi
+++ b/arch/powerpc/boot/dts/t104xrdb.dtsi
@@ -42,6 +42,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
ifc: localbus@ffe124000 {
@@ -83,6 +91,10 @@
ranges = <0x0 0xf 0xf4000000 0x2000000>;
};
+ qportals: qman-portals@ff6000000 {
+ ranges = <0x0 0xf 0xf6000000 0x2000000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t208xqds.dtsi b/arch/powerpc/boot/dts/t208xqds.dtsi
index c42e07f4f648..869f9159b4d1 100644
--- a/arch/powerpc/boot/dts/t208xqds.dtsi
+++ b/arch/powerpc/boot/dts/t208xqds.dtsi
@@ -48,6 +48,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
ifc: localbus@ffe124000 {
@@ -93,6 +101,10 @@
ranges = <0x0 0xf 0xf4000000 0x2000000>;
};
+ qportals: qman-portals@ff6000000 {
+ ranges = <0x0 0xf 0xf6000000 0x2000000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t208xrdb.dtsi b/arch/powerpc/boot/dts/t208xrdb.dtsi
index e1463b165d0e..693d2a8fa01c 100644
--- a/arch/powerpc/boot/dts/t208xrdb.dtsi
+++ b/arch/powerpc/boot/dts/t208xrdb.dtsi
@@ -48,6 +48,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
ifc: localbus@ffe124000 {
@@ -94,6 +102,10 @@
ranges = <0x0 0xf 0xf4000000 0x2000000>;
};
+ qportals: qman-portals@ff6000000 {
+ ranges = <0x0 0xf 0xf6000000 0x2000000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t4240qds.dts b/arch/powerpc/boot/dts/t4240qds.dts
index 6df77766410b..93722da10e16 100644
--- a/arch/powerpc/boot/dts/t4240qds.dts
+++ b/arch/powerpc/boot/dts/t4240qds.dts
@@ -109,6 +109,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -119,6 +127,10 @@
ranges = <0x0 0xf 0xf4000000 0x2000000>;
};
+ qportals: qman-portals@ff6000000 {
+ ranges = <0x0 0xf 0xf6000000 0x2000000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t4240rdb.dts b/arch/powerpc/boot/dts/t4240rdb.dts
index 46049cf37f02..993eb4b8a487 100644
--- a/arch/powerpc/boot/dts/t4240rdb.dts
+++ b/arch/powerpc/boot/dts/t4240rdb.dts
@@ -78,6 +78,14 @@
size = <0 0x1000000>;
alignment = <0 0x1000000>;
};
+ qman_fqd: qman-fqd {
+ size = <0 0x400000>;
+ alignment = <0 0x400000>;
+ };
+ qman_pfdr: qman-pfdr {
+ size = <0 0x2000000>;
+ alignment = <0 0x2000000>;
+ };
};
dcsr: dcsr@f00000000 {
@@ -88,6 +96,10 @@
ranges = <0x0 0xf 0xf4000000 0x2000000>;
};
+ qportals: qman-portals@ff6000000 {
+ ranges = <0x0 0xf 0xf6000000 0x2000000>;
+ };
+
soc: soc@ffe000000 {
ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index 34f3ea1729e0..858b539d004b 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -108,7 +108,7 @@ CONFIG_SENSORS_LM90=y
CONFIG_WATCHDOG=y
CONFIG_USB=y
CONFIG_USB_MON=y
-CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_ISP1760=y
CONFIG_USB_STORAGE=y
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
diff --git a/arch/powerpc/configs/le.config b/arch/powerpc/configs/le.config
new file mode 100644
index 000000000000..ee43fdb3b8f4
--- /dev/null
+++ b/arch/powerpc/configs/le.config
@@ -0,0 +1 @@
+CONFIG_CPU_LITTLE_ENDIAN=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index aad501ae3834..a97efc2146fd 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -155,6 +155,7 @@ CONFIG_ACENIC=m
CONFIG_ACENIC_OMIT_TIGON_I=y
CONFIG_PCNET32=y
CONFIG_TIGON3=y
+CONFIG_BNX2X=m
CONFIG_CHELSIO_T1=m
CONFIG_BE2NET=m
CONFIG_S2IO=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index c2e39f66b182..0d9efcedaf34 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -154,6 +154,7 @@ CONFIG_ACENIC=m
CONFIG_ACENIC_OMIT_TIGON_I=y
CONFIG_PCNET32=y
CONFIG_TIGON3=y
+CONFIG_BNX2X=m
CONFIG_CHELSIO_T1=m
CONFIG_BE2NET=m
CONFIG_S2IO=m
@@ -297,7 +298,6 @@ CONFIG_CODE_PATCHING_SELFTEST=y
CONFIG_FTR_FIXUP_SELFTEST=y
CONFIG_MSI_BITMAP_SELFTEST=y
CONFIG_XMON=y
-CONFIG_XMON_DEFAULT=y
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_HMAC=y
diff --git a/arch/powerpc/configs/pseries_le_defconfig b/arch/powerpc/configs/pseries_le_defconfig
deleted file mode 100644
index 09bc96e792cd..000000000000
--- a/arch/powerpc/configs/pseries_le_defconfig
+++ /dev/null
@@ -1,319 +0,0 @@
-CONFIG_PPC64=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=2048
-CONFIG_CPU_LITTLE_ENDIAN=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_FHANDLE=y
-CONFIG_AUDIT=y
-CONFIG_AUDITSYSCALL=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_XACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_NUMA_BALANCING=y
-CONFIG_NUMA_BALANCING_DEFAULT_ENABLED=y
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
-CONFIG_CGROUP_PERF=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_USER_NS=y
-CONFIG_BLK_DEV_INITRD=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
-CONFIG_KPROBES=y
-CONFIG_JUMP_LABEL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_PPC_SPLPAR=y
-CONFIG_SCANLOG=m
-CONFIG_PPC_SMLPAR=y
-CONFIG_DTL=y
-# CONFIG_PPC_PMAC is not set
-CONFIG_RTAS_FLASH=m
-CONFIG_IBMEBUS=y
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_HZ_100=y
-CONFIG_BINFMT_MISC=m
-CONFIG_PPC_TRANSACTIONAL_MEM=y
-CONFIG_KEXEC=y
-CONFIG_IRQ_ALL_CPUS=y
-CONFIG_MEMORY_HOTPLUG=y
-CONFIG_MEMORY_HOTREMOVE=y
-CONFIG_KSM=y
-CONFIG_TRANSPARENT_HUGEPAGE=y
-CONFIG_PPC_64K_PAGES=y
-CONFIG_PPC_SUBPAGE_PROT=y
-CONFIG_SCHED_SMT=y
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_RPA=m
-CONFIG_HOTPLUG_PCI_RPA_DLPAR=m
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_NET_IPIP=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_IPCOMP=m
-# CONFIG_IPV6 is not set
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_PARPORT=m
-CONFIG_PARPORT_PC=m
-CONFIG_BLK_DEV_FD=m
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=65536
-CONFIG_VIRTIO_BLK=m
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_AMD74XX=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_BLK_DEV_SR_VENDOR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_FC_ATTRS=y
-CONFIG_SCSI_CXGB3_ISCSI=m
-CONFIG_SCSI_CXGB4_ISCSI=m
-CONFIG_SCSI_BNX2_ISCSI=m
-CONFIG_BE2ISCSI=m
-CONFIG_SCSI_MPT2SAS=m
-CONFIG_SCSI_IBMVSCSI=y
-CONFIG_SCSI_IBMVFC=m
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0
-CONFIG_SCSI_IPR=y
-CONFIG_SCSI_QLA_FC=m
-CONFIG_SCSI_QLA_ISCSI=m
-CONFIG_SCSI_LPFC=m
-CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
-CONFIG_SCSI_DH_RDAC=m
-CONFIG_SCSI_DH_ALUA=m
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-# CONFIG_ATA_SFF is not set
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_MD_RAID0=y
-CONFIG_MD_RAID1=y
-CONFIG_MD_RAID10=m
-CONFIG_MD_RAID456=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
-CONFIG_BLK_DEV_DM=y
-CONFIG_DM_CRYPT=m
-CONFIG_DM_SNAPSHOT=m
-CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_MIRROR=m
-CONFIG_DM_ZERO=m
-CONFIG_DM_MULTIPATH=m
-CONFIG_DM_MULTIPATH_QL=m
-CONFIG_DM_MULTIPATH_ST=m
-CONFIG_DM_UEVENT=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_MACVLAN=m
-CONFIG_MACVTAP=m
-CONFIG_VXLAN=m
-CONFIG_NETCONSOLE=y
-CONFIG_TUN=m
-CONFIG_VETH=m
-CONFIG_VIRTIO_NET=m
-CONFIG_VHOST_NET=m
-CONFIG_VORTEX=y
-CONFIG_ACENIC=m
-CONFIG_ACENIC_OMIT_TIGON_I=y
-CONFIG_PCNET32=y
-CONFIG_TIGON3=y
-CONFIG_CHELSIO_T1=m
-CONFIG_BE2NET=m
-CONFIG_S2IO=m
-CONFIG_IBMVETH=y
-CONFIG_EHEA=y
-CONFIG_E100=y
-CONFIG_E1000=y
-CONFIG_E1000E=y
-CONFIG_IXGB=m
-CONFIG_IXGBE=m
-CONFIG_MLX4_EN=m
-CONFIG_MYRI10GE=m
-CONFIG_QLGE=m
-CONFIG_NETXEN_NIC=m
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-CONFIG_INPUT_EVDEV=m
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_PCSPKR=m
-# CONFIG_SERIO_SERPORT is not set
-CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_ICOM=m
-CONFIG_SERIAL_JSM=m
-CONFIG_HVC_CONSOLE=y
-CONFIG_HVC_RTAS=y
-CONFIG_HVCS=m
-CONFIG_VIRTIO_CONSOLE=m
-CONFIG_IBM_BSR=m
-CONFIG_GEN_RTC=y
-CONFIG_RAW_DRIVER=y
-CONFIG_MAX_RAW_DEVS=1024
-CONFIG_FB=y
-CONFIG_FIRMWARE_EDID=y
-CONFIG_FB_OF=y
-CONFIG_FB_MATROX=y
-CONFIG_FB_MATROX_MILLENIUM=y
-CONFIG_FB_MATROX_MYSTIQUE=y
-CONFIG_FB_MATROX_G=y
-CONFIG_FB_RADEON=y
-CONFIG_FB_IBM_GXT4500=y
-CONFIG_LCD_PLATFORM=m
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-CONFIG_HID_GYRATION=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_USB_HIDDEV=y
-CONFIG_USB=y
-CONFIG_USB_MON=m
-CONFIG_USB_EHCI_HCD=y
-# CONFIG_USB_EHCI_HCD_PPC_OF is not set
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_STORAGE=m
-CONFIG_INFINIBAND=m
-CONFIG_INFINIBAND_USER_MAD=m
-CONFIG_INFINIBAND_USER_ACCESS=m
-CONFIG_INFINIBAND_MTHCA=m
-CONFIG_INFINIBAND_EHCA=m
-CONFIG_INFINIBAND_CXGB3=m
-CONFIG_INFINIBAND_CXGB4=m
-CONFIG_MLX4_INFINIBAND=m
-CONFIG_INFINIBAND_IPOIB=m
-CONFIG_INFINIBAND_IPOIB_CM=y
-CONFIG_INFINIBAND_SRP=m
-CONFIG_INFINIBAND_ISER=m
-CONFIG_VIRTIO_PCI=m
-CONFIG_VIRTIO_BALLOON=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_EXT4_FS_SECURITY=y
-CONFIG_REISERFS_FS=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
-CONFIG_JFS_FS=m
-CONFIG_JFS_POSIX_ACL=y
-CONFIG_JFS_SECURITY=y
-CONFIG_XFS_FS=m
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_BTRFS_FS=m
-CONFIG_BTRFS_FS_POSIX_ACL=y
-CONFIG_NILFS2_FS=m
-CONFIG_AUTOFS4_FS=m
-CONFIG_FUSE_FS=m
-CONFIG_OVERLAY_FS=m
-CONFIG_ISO9660_FS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_HUGETLBFS=y
-CONFIG_CRAMFS=m
-CONFIG_SQUASHFS=m
-CONFIG_SQUASHFS_XATTR=y
-CONFIG_SQUASHFS_LZO=y
-CONFIG_SQUASHFS_XZ=y
-CONFIG_PSTORE=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3_ACL=y
-CONFIG_NFSD_V4=y
-CONFIG_CIFS=m
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-CONFIG_NLS_DEFAULT="utf8"
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
-CONFIG_LATENCYTOP=y
-CONFIG_SCHED_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_CODE_PATCHING_SELFTEST=y
-CONFIG_FTR_FIXUP_SELFTEST=y
-CONFIG_MSI_BITMAP_SELFTEST=y
-CONFIG_XMON=y
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_LZO=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_VIRTUALIZATION=y
-CONFIG_KVM_BOOK3S_64=m
-CONFIG_KVM_BOOK3S_64_HV=m
diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c
index 452fb4dc575f..92289679b4c4 100644
--- a/arch/powerpc/crypto/md5-glue.c
+++ b/arch/powerpc/crypto/md5-glue.c
@@ -37,10 +37,10 @@ static int ppc_md5_init(struct shash_desc *desc)
{
struct md5_state *sctx = shash_desc_ctx(desc);
- sctx->hash[0] = 0x67452301;
- sctx->hash[1] = 0xefcdab89;
- sctx->hash[2] = 0x98badcfe;
- sctx->hash[3] = 0x10325476;
+ sctx->hash[0] = MD5_H0;
+ sctx->hash[1] = MD5_H1;
+ sctx->hash[2] = MD5_H2;
+ sctx->hash[3] = MD5_H3;
sctx->byte_count = 0;
return 0;
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index a3bf5be111ff..51ccc7232042 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -34,7 +34,7 @@
#define rmb() __asm__ __volatile__ ("sync" : : : "memory")
#define wmb() __asm__ __volatile__ ("sync" : : : "memory")
-#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
#ifdef __SUBARCH_HAS_LWSYNC
# define SMPWMB LWSYNC
@@ -89,5 +89,6 @@ do { \
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
+#define smp_mb__before_spinlock() smp_mb()
#endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index d463c68fe7f0..ad6263cffb0f 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -144,7 +144,6 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
* Compare and exchange - if *p == old, set it to new,
* and return the old value of *p.
*/
-#define __HAVE_ARCH_CMPXCHG 1
static __always_inline unsigned long
__cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 6367b8347dad..b118072670fb 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -242,11 +242,13 @@ enum {
/* We only set the TM feature if the kernel was compiled with TM supprt */
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-#define CPU_FTR_TM_COMP CPU_FTR_TM
-#define PPC_FEATURE2_HTM_COMP PPC_FEATURE2_HTM
+#define CPU_FTR_TM_COMP CPU_FTR_TM
+#define PPC_FEATURE2_HTM_COMP PPC_FEATURE2_HTM
+#define PPC_FEATURE2_HTM_NOSC_COMP PPC_FEATURE2_HTM_NOSC
#else
-#define CPU_FTR_TM_COMP 0
-#define PPC_FEATURE2_HTM_COMP 0
+#define CPU_FTR_TM_COMP 0
+#define PPC_FEATURE2_HTM_COMP 0
+#define PPC_FEATURE2_HTM_NOSC_COMP 0
#endif
/* We need to mark all pages as being coherent if we're SMP or we have a
@@ -366,7 +368,7 @@ enum {
CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \
CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE)
#define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON | CPU_FTR_USE_TB)
-#define CPU_FTRS_8XX (CPU_FTR_USE_TB)
+#define CPU_FTRS_8XX (CPU_FTR_USE_TB | CPU_FTR_NOEXECUTE)
#define CPU_FTRS_40X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
#define CPU_FTRS_44X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
#define CPU_FTRS_440x6 (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 5be6c4753667..ba42e46ea58e 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -31,9 +31,9 @@ extern cpumask_t threads_core_mask;
/* cpu_thread_mask_to_cores - Return a cpumask of one per cores
* hit by the argument
*
- * @threads: a cpumask of threads
+ * @threads: a cpumask of online threads
*
- * This function returns a cpumask which will have one "cpu" (or thread)
+ * This function returns a cpumask which will have one online cpu's
* bit set for each core that has at least one thread set in the argument.
*
* This can typically be used for things like IPI for tlb invalidations
@@ -42,13 +42,16 @@ extern cpumask_t threads_core_mask;
static inline cpumask_t cpu_thread_mask_to_cores(const struct cpumask *threads)
{
cpumask_t tmp, res;
- int i;
+ int i, cpu;
cpumask_clear(&res);
for (i = 0; i < NR_CPUS; i += threads_per_core) {
cpumask_shift_left(&tmp, &threads_core_mask, i);
- if (cpumask_intersects(threads, &tmp))
- cpumask_set_cpu(i, &res);
+ if (cpumask_intersects(threads, &tmp)) {
+ cpu = cpumask_next_and(-1, &tmp, cpu_online_mask);
+ if (cpu < nr_cpu_ids)
+ cpumask_set_cpu(cpu, &res);
+ }
}
return res;
}
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 9f1371bab5fc..e9bdda88f1fb 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -46,6 +46,9 @@ struct dev_archdata {
#ifdef CONFIG_FAIL_IOMMU
int fail_iommu;
#endif
+#ifdef CONFIG_CXL_BASE
+ struct cxl_context *cxl_ctx;
+#endif
};
struct pdev_archdata {
diff --git a/arch/powerpc/include/asm/edac.h b/arch/powerpc/include/asm/edac.h
index 6ead88bbfbb8..5571e23d253e 100644
--- a/arch/powerpc/include/asm/edac.h
+++ b/arch/powerpc/include/asm/edac.h
@@ -12,11 +12,11 @@
#define ASM_EDAC_H
/*
* ECC atomic, DMA, SMP and interrupt safe scrub function.
- * Implements the per arch atomic_scrub() that EDAC use for software
+ * Implements the per arch edac_atomic_scrub() that EDAC use for software
* ECC scrubbing. It reads memory and then writes back the original
* value, allowing the hardware to detect and correct memory errors.
*/
-static __inline__ void atomic_scrub(void *va, u32 size)
+static __inline__ void edac_atomic_scrub(void *va, u32 size)
{
unsigned int *virt_addr = va;
unsigned int temp;
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index a52db28ecc1e..c5eb86f3d452 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -27,6 +27,8 @@
#include <linux/time.h>
#include <linux/atomic.h>
+#include <uapi/asm/eeh.h>
+
struct pci_dev;
struct pci_bus;
struct pci_dn;
@@ -185,11 +187,6 @@ enum {
#define EEH_STATE_DMA_ACTIVE (1 << 4) /* Active DMA */
#define EEH_STATE_MMIO_ENABLED (1 << 5) /* MMIO enabled */
#define EEH_STATE_DMA_ENABLED (1 << 6) /* DMA enabled */
-#define EEH_PE_STATE_NORMAL 0 /* Normal state */
-#define EEH_PE_STATE_RESET 1 /* PE reset asserted */
-#define EEH_PE_STATE_STOPPED_IO_DMA 2 /* Frozen PE */
-#define EEH_PE_STATE_STOPPED_DMA 4 /* Stopped DMA, Enabled IO */
-#define EEH_PE_STATE_UNAVAIL 5 /* Unavailable */
#define EEH_RESET_DEACTIVATE 0 /* Deactivate the PE reset */
#define EEH_RESET_HOT 1 /* Hot reset */
#define EEH_RESET_FUNDAMENTAL 3 /* Fundamental reset */
@@ -294,6 +291,8 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option);
int eeh_pe_get_state(struct eeh_pe *pe);
int eeh_pe_reset(struct eeh_pe *pe, int option);
int eeh_pe_configure(struct eeh_pe *pe);
+int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
+ unsigned long addr, unsigned long mask);
/**
* EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
new file mode 100644
index 000000000000..9f8402b35115
--- /dev/null
+++ b/arch/powerpc/include/asm/icswx.h
@@ -0,0 +1,184 @@
+/*
+ * ICSWX api
+ *
+ * Copyright (C) 2015 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This provides the Initiate Coprocessor Store Word Indexed (ICSWX)
+ * instruction. This instruction is used to communicate with PowerPC
+ * coprocessors. This also provides definitions of the structures used
+ * to communicate with the coprocessor.
+ *
+ * The RFC02130: Coprocessor Architecture document is the reference for
+ * everything in this file unless otherwise noted.
+ */
+#ifndef _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_
+#define _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_
+
+#include <asm/ppc-opcode.h> /* for PPC_ICSWX */
+
+/* Chapter 6.5.8 Coprocessor-Completion Block (CCB) */
+
+#define CCB_VALUE (0x3fffffffffffffff)
+#define CCB_ADDRESS (0xfffffffffffffff8)
+#define CCB_CM (0x0000000000000007)
+#define CCB_CM0 (0x0000000000000004)
+#define CCB_CM12 (0x0000000000000003)
+
+#define CCB_CM0_ALL_COMPLETIONS (0x0)
+#define CCB_CM0_LAST_IN_CHAIN (0x4)
+#define CCB_CM12_STORE (0x0)
+#define CCB_CM12_INTERRUPT (0x1)
+
+#define CCB_SIZE (0x10)
+#define CCB_ALIGN CCB_SIZE
+
+struct coprocessor_completion_block {
+ __be64 value;
+ __be64 address;
+} __packed __aligned(CCB_ALIGN);
+
+
+/* Chapter 6.5.7 Coprocessor-Status Block (CSB) */
+
+#define CSB_V (0x80)
+#define CSB_F (0x04)
+#define CSB_CH (0x03)
+#define CSB_CE_INCOMPLETE (0x80)
+#define CSB_CE_TERMINATION (0x40)
+#define CSB_CE_TPBC (0x20)
+
+#define CSB_CC_SUCCESS (0)
+#define CSB_CC_INVALID_ALIGN (1)
+#define CSB_CC_OPERAND_OVERLAP (2)
+#define CSB_CC_DATA_LENGTH (3)
+#define CSB_CC_TRANSLATION (5)
+#define CSB_CC_PROTECTION (6)
+#define CSB_CC_RD_EXTERNAL (7)
+#define CSB_CC_INVALID_OPERAND (8)
+#define CSB_CC_PRIVILEGE (9)
+#define CSB_CC_INTERNAL (10)
+#define CSB_CC_WR_EXTERNAL (12)
+#define CSB_CC_NOSPC (13)
+#define CSB_CC_EXCESSIVE_DDE (14)
+#define CSB_CC_WR_TRANSLATION (15)
+#define CSB_CC_WR_PROTECTION (16)
+#define CSB_CC_UNKNOWN_CODE (17)
+#define CSB_CC_ABORT (18)
+#define CSB_CC_TRANSPORT (20)
+#define CSB_CC_SEGMENTED_DDL (31)
+#define CSB_CC_PROGRESS_POINT (32)
+#define CSB_CC_DDE_OVERFLOW (33)
+#define CSB_CC_SESSION (34)
+#define CSB_CC_PROVISION (36)
+#define CSB_CC_CHAIN (37)
+#define CSB_CC_SEQUENCE (38)
+#define CSB_CC_HW (39)
+
+#define CSB_SIZE (0x10)
+#define CSB_ALIGN CSB_SIZE
+
+struct coprocessor_status_block {
+ u8 flags;
+ u8 cs;
+ u8 cc;
+ u8 ce;
+ __be32 count;
+ __be64 address;
+} __packed __aligned(CSB_ALIGN);
+
+
+/* Chapter 6.5.10 Data-Descriptor List (DDL)
+ * each list contains one or more Data-Descriptor Entries (DDE)
+ */
+
+#define DDE_P (0x8000)
+
+#define DDE_SIZE (0x10)
+#define DDE_ALIGN DDE_SIZE
+
+struct data_descriptor_entry {
+ __be16 flags;
+ u8 count;
+ u8 index;
+ __be32 length;
+ __be64 address;
+} __packed __aligned(DDE_ALIGN);
+
+
+/* Chapter 6.5.2 Coprocessor-Request Block (CRB) */
+
+#define CRB_SIZE (0x80)
+#define CRB_ALIGN (0x100) /* Errata: requires 256 alignment */
+
+/* Coprocessor Status Block field
+ * ADDRESS address of CSB
+ * C CCB is valid
+ * AT 0 = addrs are virtual, 1 = addrs are phys
+ * M enable perf monitor
+ */
+#define CRB_CSB_ADDRESS (0xfffffffffffffff0)
+#define CRB_CSB_C (0x0000000000000008)
+#define CRB_CSB_AT (0x0000000000000002)
+#define CRB_CSB_M (0x0000000000000001)
+
+struct coprocessor_request_block {
+ __be32 ccw;
+ __be32 flags;
+ __be64 csb_addr;
+
+ struct data_descriptor_entry source;
+ struct data_descriptor_entry target;
+
+ struct coprocessor_completion_block ccb;
+
+ u8 reserved[48];
+
+ struct coprocessor_status_block csb;
+} __packed __aligned(CRB_ALIGN);
+
+
+/* RFC02167 Initiate Coprocessor Instructions document
+ * Chapter 8.2.1.1.1 RS
+ * Chapter 8.2.3 Coprocessor Directive
+ * Chapter 8.2.4 Execution
+ *
+ * The CCW must be converted to BE before passing to icswx()
+ */
+
+#define CCW_PS (0xff000000)
+#define CCW_CT (0x00ff0000)
+#define CCW_CD (0x0000ffff)
+#define CCW_CL (0x0000c000)
+
+
+/* RFC02167 Initiate Coprocessor Instructions document
+ * Chapter 8.2.1 Initiate Coprocessor Store Word Indexed (ICSWX)
+ * Chapter 8.2.4.1 Condition Register 0
+ */
+
+#define ICSWX_INITIATED (0x8)
+#define ICSWX_BUSY (0x4)
+#define ICSWX_REJECTED (0x2)
+
+static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb)
+{
+ __be64 ccw_reg = ccw;
+ u32 cr;
+
+ __asm__ __volatile__(
+ PPC_ICSWX(%1,0,%2) "\n"
+ "mfcr %0\n"
+ : "=r" (cr)
+ : "r" (ccw_reg), "r" (crb)
+ : "cr0", "memory");
+
+ return (int)((cr >> 28) & 0xf);
+}
+
+
+#endif /* _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_ */
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 1e27d6338565..ca18cff90900 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -44,6 +44,39 @@
extern int iommu_is_off;
extern int iommu_force_on;
+struct iommu_table_ops {
+ /*
+ * When called with direction==DMA_NONE, it is equal to clear().
+ * uaddr is a linear map address.
+ */
+ int (*set)(struct iommu_table *tbl,
+ long index, long npages,
+ unsigned long uaddr,
+ enum dma_data_direction direction,
+ struct dma_attrs *attrs);
+#ifdef CONFIG_IOMMU_API
+ /*
+ * Exchanges existing TCE with new TCE plus direction bits;
+ * returns old TCE and DMA direction mask.
+ * @tce is a physical address.
+ */
+ int (*exchange)(struct iommu_table *tbl,
+ long index,
+ unsigned long *hpa,
+ enum dma_data_direction *direction);
+#endif
+ void (*clear)(struct iommu_table *tbl,
+ long index, long npages);
+ /* get() returns a physical address */
+ unsigned long (*get)(struct iommu_table *tbl, long index);
+ void (*flush)(struct iommu_table *tbl);
+ void (*free)(struct iommu_table *tbl);
+};
+
+/* These are used by VIO */
+extern struct iommu_table_ops iommu_table_lpar_multi_ops;
+extern struct iommu_table_ops iommu_table_pseries_ops;
+
/*
* IOMAP_MAX_ORDER defines the largest contiguous block
* of dma space we can get. IOMAP_MAX_ORDER = 13
@@ -64,6 +97,9 @@ struct iommu_pool {
struct iommu_table {
unsigned long it_busno; /* Bus number this table belongs to */
unsigned long it_size; /* Size of iommu table in entries */
+ unsigned long it_indirect_levels;
+ unsigned long it_level_size;
+ unsigned long it_allocated_size;
unsigned long it_offset; /* Offset into global table */
unsigned long it_base; /* mapped address of tce table */
unsigned long it_index; /* which iommu table this is */
@@ -75,15 +111,16 @@ struct iommu_table {
struct iommu_pool pools[IOMMU_NR_POOLS];
unsigned long *it_map; /* A simple allocation bitmap for now */
unsigned long it_page_shift;/* table iommu page size */
-#ifdef CONFIG_IOMMU_API
- struct iommu_group *it_group;
-#endif
- void (*set_bypass)(struct iommu_table *tbl, bool enable);
-#ifdef CONFIG_PPC_POWERNV
- void *data;
-#endif
+ struct list_head it_group_list;/* List of iommu_table_group_link */
+ unsigned long *it_userspace; /* userspace view of the table */
+ struct iommu_table_ops *it_ops;
};
+#define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
+ ((tbl)->it_userspace ? \
+ &((tbl)->it_userspace[(entry) - (tbl)->it_offset]) : \
+ NULL)
+
/* Pure 2^n version of get_order */
static inline __attribute_const__
int get_iommu_order(unsigned long size, struct iommu_table *tbl)
@@ -112,14 +149,62 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
*/
extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
int nid);
+#define IOMMU_TABLE_GROUP_MAX_TABLES 2
+
+struct iommu_table_group;
+
+struct iommu_table_group_ops {
+ unsigned long (*get_table_size)(
+ __u32 page_shift,
+ __u64 window_size,
+ __u32 levels);
+ long (*create_table)(struct iommu_table_group *table_group,
+ int num,
+ __u32 page_shift,
+ __u64 window_size,
+ __u32 levels,
+ struct iommu_table **ptbl);
+ long (*set_window)(struct iommu_table_group *table_group,
+ int num,
+ struct iommu_table *tblnew);
+ long (*unset_window)(struct iommu_table_group *table_group,
+ int num);
+ /* Switch ownership from platform code to external user (e.g. VFIO) */
+ void (*take_ownership)(struct iommu_table_group *table_group);
+ /* Switch ownership from external user (e.g. VFIO) back to core */
+ void (*release_ownership)(struct iommu_table_group *table_group);
+};
+
+struct iommu_table_group_link {
+ struct list_head next;
+ struct rcu_head rcu;
+ struct iommu_table_group *table_group;
+};
+
+struct iommu_table_group {
+ /* IOMMU properties */
+ __u32 tce32_start;
+ __u32 tce32_size;
+ __u64 pgsizes; /* Bitmap of supported page sizes */
+ __u32 max_dynamic_windows_supported;
+ __u32 max_levels;
+
+ struct iommu_group *group;
+ struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
+ struct iommu_table_group_ops *ops;
+};
+
#ifdef CONFIG_IOMMU_API
-extern void iommu_register_group(struct iommu_table *tbl,
+
+extern void iommu_register_group(struct iommu_table_group *table_group,
int pci_domain_number, unsigned long pe_num);
extern int iommu_add_device(struct device *dev);
extern void iommu_del_device(struct device *dev);
extern int __init tce_iommu_bus_notifier_init(void);
+extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
+ unsigned long *hpa, enum dma_data_direction *direction);
#else
-static inline void iommu_register_group(struct iommu_table *tbl,
+static inline void iommu_register_group(struct iommu_table_group *table_group,
int pci_domain_number,
unsigned long pe_num)
{
@@ -140,13 +225,6 @@ static inline int __init tce_iommu_bus_notifier_init(void)
}
#endif /* !CONFIG_IOMMU_API */
-static inline void set_iommu_table_base_and_group(struct device *dev,
- void *base)
-{
- set_iommu_table_base(dev, base);
- iommu_add_device(dev);
-}
-
extern int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
struct scatterlist *sglist, int nelems,
unsigned long mask,
@@ -197,20 +275,13 @@ extern int iommu_tce_clear_param_check(struct iommu_table *tbl,
unsigned long npages);
extern int iommu_tce_put_param_check(struct iommu_table *tbl,
unsigned long ioba, unsigned long tce);
-extern int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
- unsigned long hwaddr, enum dma_data_direction direction);
-extern unsigned long iommu_clear_tce(struct iommu_table *tbl,
- unsigned long entry);
-extern int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
- unsigned long entry, unsigned long pages);
-extern int iommu_put_tce_user_mode(struct iommu_table *tbl,
- unsigned long entry, unsigned long tce);
extern void iommu_flush_tce(struct iommu_table *tbl);
extern int iommu_take_ownership(struct iommu_table *tbl);
extern void iommu_release_ownership(struct iommu_table *tbl);
extern enum dma_data_direction iommu_tce_direction(unsigned long tce);
+extern unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir);
#endif /* __KERNEL__ */
#endif /* _ASM_IOMMU_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 3536d12eb798..2aa79c864e91 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -430,7 +430,7 @@ static inline void note_hpte_modification(struct kvm *kvm,
*/
static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
{
- return rcu_dereference_raw_notrace(kvm->memslots);
+ return rcu_dereference_raw_notrace(kvm->memslots[0]);
}
extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index a193a13cf08b..d91f65b28e32 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -698,7 +698,7 @@ struct kvm_vcpu_arch {
static inline void kvm_arch_hardware_disable(void) {}
static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_exit(void) {}
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index b8475daad884..c6ef05bd0765 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -182,10 +182,11 @@ extern int kvmppc_core_create_memslot(struct kvm *kvm,
unsigned long npages);
extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem);
+ const struct kvm_userspace_memory_region *mem);
extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old);
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new);
extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
struct kvm_ppc_smmu_info *info);
extern void kvmppc_core_flush_memslot(struct kvm *kvm,
@@ -243,10 +244,11 @@ struct kvmppc_ops {
void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot);
int (*prepare_memory_region)(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem);
+ const struct kvm_userspace_memory_region *mem);
void (*commit_memory_region)(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old);
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new);
int (*unmap_hva)(struct kvm *kvm, unsigned long hva);
int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
unsigned long end);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index ef8899432ae7..952579f5e79a 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -65,31 +65,6 @@ struct machdep_calls {
* destroyed as well */
void (*hpte_clear_all)(void);
- int (*tce_build)(struct iommu_table *tbl,
- long index,
- long npages,
- unsigned long uaddr,
- enum dma_data_direction direction,
- struct dma_attrs *attrs);
- void (*tce_free)(struct iommu_table *tbl,
- long index,
- long npages);
- unsigned long (*tce_get)(struct iommu_table *tbl,
- long index);
- void (*tce_flush)(struct iommu_table *tbl);
-
- /* _rm versions are for real mode use only */
- int (*tce_build_rm)(struct iommu_table *tbl,
- long index,
- long npages,
- unsigned long uaddr,
- enum dma_data_direction direction,
- struct dma_attrs *attrs);
- void (*tce_free_rm)(struct iommu_table *tbl,
- long index,
- long npages);
- void (*tce_flush_rm)(struct iommu_table *tbl);
-
void __iomem * (*ioremap)(phys_addr_t addr, unsigned long size,
unsigned long flags, void *caller);
void (*iounmap)(volatile void __iomem *token);
@@ -131,12 +106,6 @@ struct machdep_calls {
/* To setup PHBs when using automatic OF platform driver for PCI */
int (*pci_setup_phb)(struct pci_controller *host);
-#ifdef CONFIG_PCI_MSI
- int (*setup_msi_irqs)(struct pci_dev *dev,
- int nvec, int type);
- void (*teardown_msi_irqs)(struct pci_dev *dev);
-#endif
-
void (*restart)(char *cmd);
void (*halt)(void);
void (*panic)(char *str);
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 986b9e1e1044..f05500a29a60 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -27,6 +27,19 @@
#define MI_Ks 0x80000000 /* Should not be set */
#define MI_Kp 0x40000000 /* Should always be set */
+/*
+ * All pages' PP exec bits are set to 000, which means Execute for Supervisor
+ * and no Execute for User.
+ * Then we use the APG to say whether accesses are according to Page rules,
+ * "all Supervisor" rules (Exec for all) and "all User" rules (Exec for noone)
+ * Therefore, we define 4 APG groups. msb is _PAGE_EXEC, lsb is _PAGE_USER
+ * 0 (00) => Not User, no exec => 11 (all accesses performed as user)
+ * 1 (01) => User but no exec => 11 (all accesses performed as user)
+ * 2 (10) => Not User, exec => 01 (rights according to page definition)
+ * 3 (11) => User, exec => 00 (all accesses performed as supervisor)
+ */
+#define MI_APG_INIT 0xf4ffffff
+
/* The effective page number register. When read, contains the information
* about the last instruction TLB miss. When MI_RPN is written, bits in
* this register are used to create the TLB entry.
@@ -87,6 +100,19 @@
#define MD_Ks 0x80000000 /* Should not be set */
#define MD_Kp 0x40000000 /* Should always be set */
+/*
+ * All pages' PP data bits are set to either 000 or 011, which means
+ * respectively RW for Supervisor and no access for User, or RO for
+ * Supervisor and no access for user.
+ * Then we use the APG to say whether accesses are according to Page rules or
+ * "all Supervisor" rules (Access to all)
+ * Therefore, we define 2 APG groups. lsb is _PAGE_USER
+ * 0 => No user => 01 (all accesses performed according to page definition)
+ * 1 => User => 00 (all accesses performed as supervisor
+ * according to page definition)
+ */
+#define MD_APG_INIT 0x4fffffff
+
/* The effective page number register. When read, contains the information
* about the last instruction TLB miss. When MD_RPN is written, bits in
* this register are used to create the TLB entry.
@@ -145,7 +171,14 @@ typedef struct {
} mm_context_t;
#endif /* !__ASSEMBLY__ */
+#if (PAGE_SHIFT == 12)
#define mmu_virtual_psize MMU_PAGE_4K
+#elif (PAGE_SHIFT == 14)
+#define mmu_virtual_psize MMU_PAGE_16K
+#else
+#error "Unsupported PAGE_SIZE"
+#endif
+
#define mmu_linear_psize MMU_PAGE_8M
#endif /* _ASM_POWERPC_MMU_8XX_H_ */
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 1da6a81ce541..a82f5347540a 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -536,6 +536,9 @@ typedef struct {
/* for 4K PTE fragment support */
void *pte_frag;
#endif
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ struct list_head iommu_group_mem_list;
+#endif
} mm_context_t;
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 73382eba02dc..3e5184210d9b 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -16,6 +16,24 @@
*/
extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
extern void destroy_context(struct mm_struct *mm);
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+struct mm_iommu_table_group_mem_t;
+
+extern bool mm_iommu_preregistered(void);
+extern long mm_iommu_get(unsigned long ua, unsigned long entries,
+ struct mm_iommu_table_group_mem_t **pmem);
+extern long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem);
+extern void mm_iommu_init(mm_context_t *ctx);
+extern void mm_iommu_cleanup(mm_context_t *ctx);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
+ unsigned long size);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
+ unsigned long entries);
+extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
+ unsigned long ua, unsigned long *hpa);
+extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
+extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
+#endif
extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next);
extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 0321a909e663..e9e4c52f3685 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -153,7 +153,8 @@
#define OPAL_FLASH_READ 110
#define OPAL_FLASH_WRITE 111
#define OPAL_FLASH_ERASE 112
-#define OPAL_LAST 112
+#define OPAL_PRD_MSG 113
+#define OPAL_LAST 113
/* Device tree flags */
@@ -165,6 +166,13 @@
#define OPAL_PM_WINKLE_ENABLED 0x00040000
#define OPAL_PM_SLEEP_ENABLED_ER1 0x00080000 /* with workaround */
+/*
+ * OPAL_CONFIG_CPU_IDLE_STATE parameters
+ */
+#define OPAL_CONFIG_IDLE_FASTSLEEP 1
+#define OPAL_CONFIG_IDLE_UNDO 0
+#define OPAL_CONFIG_IDLE_APPLY 1
+
#ifndef __ASSEMBLY__
/* Other enums */
@@ -352,6 +360,7 @@ enum opal_msg_type {
OPAL_MSG_SHUTDOWN, /* params[0] = 1 reboot, 0 shutdown */
OPAL_MSG_HMI_EVT,
OPAL_MSG_DPO,
+ OPAL_MSG_PRD,
OPAL_MSG_TYPE_MAX,
};
@@ -674,6 +683,23 @@ typedef struct oppanel_line {
__be64 line_len;
} oppanel_line_t;
+enum opal_prd_msg_type {
+ OPAL_PRD_MSG_TYPE_INIT = 0, /* HBRT --> OPAL */
+ OPAL_PRD_MSG_TYPE_FINI, /* HBRT/kernel --> OPAL */
+ OPAL_PRD_MSG_TYPE_ATTN, /* HBRT <-- OPAL */
+ OPAL_PRD_MSG_TYPE_ATTN_ACK, /* HBRT --> OPAL */
+ OPAL_PRD_MSG_TYPE_OCC_ERROR, /* HBRT <-- OPAL */
+ OPAL_PRD_MSG_TYPE_OCC_RESET, /* HBRT <-- OPAL */
+};
+
+struct opal_prd_msg_header {
+ uint8_t type;
+ uint8_t pad[1];
+ __be16 size;
+};
+
+struct opal_prd_msg;
+
/*
* SG entries
*
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 042af1abfc4d..958e941c0cda 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -186,6 +186,7 @@ int64_t opal_handle_hmi(void);
int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end);
int64_t opal_unregister_dump_region(uint32_t id);
int64_t opal_slw_set_reg(uint64_t cpu_pir, uint64_t sprn, uint64_t val);
+int64_t opal_config_cpu_idle_state(uint64_t state, uint64_t flag);
int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number);
int64_t opal_ipmi_send(uint64_t interface, struct opal_ipmi_msg *msg,
uint64_t msg_len);
@@ -193,6 +194,7 @@ int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg,
uint64_t *msg_len);
int64_t opal_i2c_request(uint64_t async_token, uint32_t bus_id,
struct opal_i2c_request *oreq);
+int64_t opal_prd_msg(struct opal_prd_msg *msg);
int64_t opal_flash_read(uint64_t id, uint64_t offset, uint64_t buf,
uint64_t size, uint64_t token);
@@ -239,6 +241,10 @@ extern int opal_elog_init(void);
extern void opal_platform_dump_init(void);
extern void opal_sys_param_init(void);
extern void opal_msglog_init(void);
+extern int opal_async_comp_init(void);
+extern int opal_sensor_init(void);
+extern int opal_hmi_handler_init(void);
+extern int opal_event_init(void);
extern int opal_machine_check(struct pt_regs *regs);
extern bool opal_mce_check_early_recovery(struct pt_regs *regs);
@@ -250,6 +256,8 @@ extern int opal_resync_timebase(void);
extern void opal_lpc_init(void);
+extern int opal_event_request(unsigned int opal_event_nr);
+
struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
unsigned long vmalloc_size);
void opal_free_sg_list(struct opal_sg_list *sg);
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 69c059887a2c..71294a6e976e 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -278,9 +278,7 @@ extern long long virt_phys_offset;
#ifndef __ASSEMBLY__
-#undef STRICT_MM_TYPECHECKS
-
-#ifdef STRICT_MM_TYPECHECKS
+#ifdef CONFIG_STRICT_MM_TYPECHECKS
/* These are used to make use of C type-checking. */
/* PTE level */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 1811c44bf34b..712add590445 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -27,9 +27,23 @@ struct pci_controller_ops {
* allow assignment/enabling of the device. */
bool (*enable_device_hook)(struct pci_dev *);
+ void (*disable_device)(struct pci_dev *);
+
+ void (*release_device)(struct pci_dev *);
+
/* Called during PCI resource reassignment */
resource_size_t (*window_alignment)(struct pci_bus *, unsigned long type);
void (*reset_secondary_bus)(struct pci_dev *dev);
+
+#ifdef CONFIG_PCI_MSI
+ int (*setup_msi_irqs)(struct pci_dev *dev,
+ int nvec, int type);
+ void (*teardown_msi_irqs)(struct pci_dev *dev);
+#endif
+
+ int (*dma_set_mask)(struct pci_dev *dev, u64 dma_mask);
+
+ void (*shutdown)(struct pci_controller *);
};
/*
@@ -185,7 +199,7 @@ struct pci_dn {
struct pci_dn *parent;
struct pci_controller *phb; /* for pci devices */
- struct iommu_table *iommu_table; /* for phb's or bridges */
+ struct iommu_table_group *table_group; /* for phb's or bridges */
struct device_node *node; /* back-pointer to the device_node */
int pci_ext_config_space; /* for pci devices */
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 4aef8d660999..99dc432b256a 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -71,36 +71,6 @@ extern struct dma_map_ops *get_pci_dma_ops(void);
*/
#define PCI_DISABLE_MWI
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- unsigned long cacheline_size;
- u8 byte;
-
- pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
- if (byte == 0)
- cacheline_size = 1024;
- else
- cacheline_size = (int) byte * 4;
-
- *strat = PCI_DMA_BURST_MULTIPLE;
- *strategy_parameter = cacheline_size;
-}
-#endif
-
-#else /* 32-bit */
-
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- *strat = PCI_DMA_BURST_INFINITY;
- *strategy_parameter = ~0UL;
-}
-#endif
#endif /* CONFIG_PPC64 */
extern int pci_domain_nr(struct pci_bus *bus);
diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h
index 64b52b1cf542..9c326565d498 100644
--- a/arch/powerpc/include/asm/pgtable-ppc32.h
+++ b/arch/powerpc/include/asm/pgtable-ppc32.h
@@ -170,24 +170,6 @@ static inline unsigned long pte_update(pte_t *p,
#ifdef PTE_ATOMIC_UPDATES
unsigned long old, tmp;
-#ifdef CONFIG_PPC_8xx
- unsigned long tmp2;
-
- __asm__ __volatile__("\
-1: lwarx %0,0,%4\n\
- andc %1,%0,%5\n\
- or %1,%1,%6\n\
- /* 0x200 == Extended encoding, bit 22 */ \
- /* Bit 22 has to be 1 when _PAGE_USER is unset and _PAGE_RO is set */ \
- rlwimi %1,%1,32-1,0x200\n /* get _PAGE_RO */ \
- rlwinm %3,%1,32-2,0x200\n /* get _PAGE_USER */ \
- andc %1,%1,%3\n\
- stwcx. %1,0,%4\n\
- bne- 1b"
- : "=&r" (old), "=&r" (tmp), "=m" (*p), "=&r" (tmp2)
- : "r" (p), "r" (clr), "r" (set), "m" (*p)
- : "cc" );
-#else /* CONFIG_PPC_8xx */
__asm__ __volatile__("\
1: lwarx %0,0,%3\n\
andc %1,%0,%4\n\
@@ -198,7 +180,6 @@ static inline unsigned long pte_update(pte_t *p,
: "=&r" (old), "=&r" (tmp), "=m" (*p)
: "r" (p), "r" (clr), "r" (set), "m" (*p)
: "cc" );
-#endif /* CONFIG_PPC_8xx */
#else /* PTE_ATOMIC_UPDATES */
unsigned long old = pte_val(*p);
*p = __pte((old & ~clr) | set);
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 43e6ad424c7f..f890f7ce1593 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -118,7 +118,7 @@
*/
#ifndef __real_pte
-#ifdef STRICT_MM_TYPECHECKS
+#ifdef CONFIG_STRICT_MM_TYPECHECKS
#define __real_pte(e,p) ((real_pte_t){(e)})
#define __rpte_to_pte(r) ((r).pte)
#else
@@ -347,11 +347,27 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
/* Encode and de-code a swap entry */
-#define __swp_type(entry) (((entry).val >> 1) & 0x3f)
-#define __swp_offset(entry) ((entry).val >> 8)
-#define __swp_entry(type, offset) ((swp_entry_t){((type)<< 1)|((offset)<<8)})
-#define __pte_to_swp_entry(pte) ((swp_entry_t){pte_val(pte) >> PTE_RPN_SHIFT})
-#define __swp_entry_to_pte(x) ((pte_t) { (x).val << PTE_RPN_SHIFT })
+#define MAX_SWAPFILES_CHECK() do { \
+ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
+ /* \
+ * Don't have overlapping bits with _PAGE_HPTEFLAGS \
+ * We filter HPTEFLAGS on set_pte. \
+ */ \
+ BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
+ } while (0)
+/*
+ * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
+ */
+#define SWP_TYPE_BITS 5
+#define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \
+ & ((1UL << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x) ((x).val >> PTE_RPN_SHIFT)
+#define __swp_entry(type, offset) ((swp_entry_t) { \
+ ((type) << _PAGE_BIT_SWAP_TYPE) \
+ | ((offset) << PTE_RPN_SHIFT) })
+
+#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) })
+#define __swp_entry_to_pte(x) __pte((x).val)
void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
void pgtable_cache_init(void);
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index f9b498292a5c..6f77f71ee964 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -11,7 +11,7 @@
#define _ASM_PNV_PCI_H
#include <linux/pci.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode);
int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 5c93f691b495..8452335661a5 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -136,6 +136,8 @@
#define PPC_INST_DCBAL 0x7c2005ec
#define PPC_INST_DCBZL 0x7c2007ec
#define PPC_INST_ICBT 0x7c00002c
+#define PPC_INST_ICSWX 0x7c00032d
+#define PPC_INST_ICSWEPX 0x7c00076d
#define PPC_INST_ISEL 0x7c00001e
#define PPC_INST_ISEL_MASK 0xfc00003e
#define PPC_INST_LDARX 0x7c0000a8
@@ -403,4 +405,15 @@
#define MFTMR(tmr, r) stringify_in_c(.long PPC_INST_MFTMR | \
TMRN(tmr) | ___PPC_RT(r))
+/* Coprocessor instructions */
+#define PPC_ICSWX(s, a, b) stringify_in_c(.long PPC_INST_ICSWX | \
+ ___PPC_RS(s) | \
+ ___PPC_RA(a) | \
+ ___PPC_RB(b))
+#define PPC_ICSWEPX(s, a, b) stringify_in_c(.long PPC_INST_ICSWEPX | \
+ ___PPC_RS(s) | \
+ ___PPC_RA(a) | \
+ ___PPC_RB(b))
+
+
#endif /* _ASM_POWERPC_PPC_OPCODE_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index bf117d8fb45f..28ded5d9b579 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -295,6 +295,15 @@ struct thread_struct {
#endif
#ifdef CONFIG_PPC64
unsigned long dscr;
+ /*
+ * This member element dscr_inherit indicates that the process
+ * has explicitly attempted and changed the DSCR register value
+ * for itself. Hence kernel wont use the default CPU DSCR value
+ * contained in the PACA structure anymore during process context
+ * switch. Once this variable is set, this behaviour will also be
+ * inherited to all the children of this process from that point
+ * onwards.
+ */
int dscr_inherit;
unsigned long ppr; /* used to save/restore SMT priority */
#endif
diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index 97bae64afdaa..a0e2ba960976 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -34,35 +34,32 @@
#define _PAGE_SPECIAL 0x0008 /* SW entry, forced to 0 by the TLB miss */
#define _PAGE_DIRTY 0x0100 /* C: page changed */
-/* These 4 software bits must be masked out when the entry is loaded
- * into the TLB, 1 SW bit left(0x0080).
+/* These 4 software bits must be masked out when the L2 entry is loaded
+ * into the TLB.
*/
-#define _PAGE_GUARDED 0x0010 /* software: guarded access */
-#define _PAGE_ACCESSED 0x0020 /* software: page referenced */
-#define _PAGE_WRITETHRU 0x0040 /* software: caching is write through */
+#define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */
+#define _PAGE_USER 0x0020 /* Copied to L1 APG lsb */
+#define _PAGE_EXEC 0x0040 /* Copied to L1 APG */
+#define _PAGE_WRITETHRU 0x0080 /* software: caching is write through */
+#define _PAGE_ACCESSED 0x0800 /* software: page referenced */
-/* Setting any bits in the nibble with the follow two controls will
- * require a TLB exception handler change. It is assumed unused bits
- * are always zero.
- */
-#define _PAGE_RO 0x0400 /* lsb PP bits */
-#define _PAGE_USER 0x0800 /* msb PP bits */
-/* set when _PAGE_USER is unset and _PAGE_RO is set */
-#define _PAGE_KNLRO 0x0200
+#define _PAGE_RO 0x0600 /* Supervisor RO, User no access */
#define _PMD_PRESENT 0x0001
#define _PMD_BAD 0x0ff0
#define _PMD_PAGE_MASK 0x000c
#define _PMD_PAGE_8M 0x000c
-#define _PTE_NONE_MASK _PAGE_KNLRO
-
/* Until my rework is finished, 8xx still needs atomic PTE updates */
#define PTE_ATOMIC_UPDATES 1
/* We need to add _PAGE_SHARED to kernel pages */
-#define _PAGE_KERNEL_RO (_PAGE_SHARED | _PAGE_RO | _PAGE_KNLRO)
-#define _PAGE_KERNEL_ROX (_PAGE_EXEC | _PAGE_RO | _PAGE_KNLRO)
+#define _PAGE_KERNEL_RO (_PAGE_SHARED | _PAGE_RO)
+#define _PAGE_KERNEL_ROX (_PAGE_SHARED | _PAGE_RO | _PAGE_EXEC)
+#define _PAGE_KERNEL_RW (_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \
+ _PAGE_HWWRITE)
+#define _PAGE_KERNEL_RWX (_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \
+ _PAGE_HWWRITE | _PAGE_EXEC)
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_PTE_8xx_H */
diff --git a/arch/powerpc/include/asm/pte-book3e.h b/arch/powerpc/include/asm/pte-book3e.h
index 91a704952ca1..8d8473278d91 100644
--- a/arch/powerpc/include/asm/pte-book3e.h
+++ b/arch/powerpc/include/asm/pte-book3e.h
@@ -11,6 +11,7 @@
/* Architected bits */
#define _PAGE_PRESENT 0x000001 /* software: pte contains a translation */
#define _PAGE_SW1 0x000002
+#define _PAGE_BIT_SWAP_TYPE 2
#define _PAGE_BAP_SR 0x000004
#define _PAGE_BAP_UR 0x000008
#define _PAGE_BAP_SW 0x000010
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index c5a755ef7011..b7c8d079c121 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -85,10 +85,8 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
* 64-bit PTEs
*/
#if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
-#define PTE_RPN_MAX (1ULL << (64 - PTE_RPN_SHIFT))
#define PTE_RPN_MASK (~((1ULL<<PTE_RPN_SHIFT)-1))
#else
-#define PTE_RPN_MAX (1UL << (32 - PTE_RPN_SHIFT))
#define PTE_RPN_MASK (~((1UL<<PTE_RPN_SHIFT)-1))
#endif
diff --git a/arch/powerpc/include/asm/pte-hash64.h b/arch/powerpc/include/asm/pte-hash64.h
index fc852f7e7b3a..ef612c160da7 100644
--- a/arch/powerpc/include/asm/pte-hash64.h
+++ b/arch/powerpc/include/asm/pte-hash64.h
@@ -16,6 +16,7 @@
*/
#define _PAGE_PRESENT 0x0001 /* software: pte contains a translation */
#define _PAGE_USER 0x0002 /* matches one of the PP bits */
+#define _PAGE_BIT_SWAP_TYPE 2
#define _PAGE_EXEC 0x0004 /* No execute on POWER4 and newer (we invert) */
#define _PAGE_GUARDED 0x0008
/* We can derive Memory coherence from _PAGE_NO_CACHE */
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index f1863a138b4a..71f2b3f02cf8 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -358,7 +358,7 @@ SYSCALL_SPU(setns)
COMPAT_SYS(process_vm_readv)
COMPAT_SYS(process_vm_writev)
SYSCALL(finit_module)
-SYSCALL(ni_syscall) /* sys_kcmp */
+SYSCALL(kcmp) /* sys_kcmp */
SYSCALL_SPU(sched_setattr)
SYSCALL_SPU(sched_getattr)
SYSCALL_SPU(renameat2)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 5f1048eaa5b6..8b3b46b7b0f2 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -87,7 +87,7 @@ static inline int prrn_is_enabled(void)
#include <asm/smp.h>
#define topology_physical_package_id(cpu) (cpu_to_chip_id(cpu))
-#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_core_id(cpu) (cpu_to_core_id(cpu))
#endif
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index c15da6073cb8..8e86b48d0369 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -144,6 +144,26 @@ TRACE_EVENT_FN(opal_exit,
);
#endif
+TRACE_EVENT(hash_fault,
+
+ TP_PROTO(unsigned long addr, unsigned long access, unsigned long trap),
+ TP_ARGS(addr, access, trap),
+ TP_STRUCT__entry(
+ __field(unsigned long, addr)
+ __field(unsigned long, access)
+ __field(unsigned long, trap)
+ ),
+
+ TP_fast_assign(
+ __entry->addr = addr;
+ __entry->access = access;
+ __entry->trap = trap;
+ ),
+
+ TP_printk("hash fault with addr 0x%lx and access = 0x%lx trap = 0x%lx",
+ __entry->addr, __entry->access, __entry->trap)
+);
+
#endif /* _TRACE_POWERPC_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index a0c071d24e0e..2a8ebae0936b 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -265,7 +265,7 @@ do { \
({ \
long __gu_err; \
unsigned long __gu_val; \
- const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
+ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
__chk_user_ptr(ptr); \
if (!is_kernel_addr((unsigned long)__gu_addr)) \
might_fault(); \
@@ -279,7 +279,7 @@ do { \
({ \
long __gu_err; \
long long __gu_val; \
- const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
+ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
__chk_user_ptr(ptr); \
if (!is_kernel_addr((unsigned long)__gu_addr)) \
might_fault(); \
@@ -293,7 +293,7 @@ do { \
({ \
long __gu_err = -EFAULT; \
unsigned long __gu_val = 0; \
- const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
+ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
might_fault(); \
if (access_ok(VERIFY_READ, __gu_addr, (size))) \
__get_user_size(__gu_val, __gu_addr, (size), __gu_err); \
@@ -305,7 +305,7 @@ do { \
({ \
long __gu_err; \
unsigned long __gu_val; \
- const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
+ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
__chk_user_ptr(ptr); \
__get_user_size(__gu_val, __gu_addr, (size), __gu_err); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 79c4068be278..f44a027818af 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -18,6 +18,7 @@ header-y += kvm_para.h
header-y += mman.h
header-y += msgbuf.h
header-y += nvram.h
+header-y += opal-prd.h
header-y += param.h
header-y += perf_event.h
header-y += poll.h
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index de2c0e4ee1aa..43686043e297 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -42,5 +42,6 @@
#define PPC_FEATURE2_ISEL 0x08000000
#define PPC_FEATURE2_TAR 0x04000000
#define PPC_FEATURE2_VEC_CRYPTO 0x02000000
+#define PPC_FEATURE2_HTM_NOSC 0x01000000
#endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/include/uapi/asm/eeh.h b/arch/powerpc/include/uapi/asm/eeh.h
new file mode 100644
index 000000000000..291b7d1814a6
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/eeh.h
@@ -0,0 +1,56 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2015
+ *
+ * Authors: Gavin Shan <gwshan@linux.vnet.ibm.com>
+ */
+
+#ifndef _ASM_POWERPC_EEH_H
+#define _ASM_POWERPC_EEH_H
+
+/* PE states */
+#define EEH_PE_STATE_NORMAL 0 /* Normal state */
+#define EEH_PE_STATE_RESET 1 /* PE reset asserted */
+#define EEH_PE_STATE_STOPPED_IO_DMA 2 /* Frozen PE */
+#define EEH_PE_STATE_STOPPED_DMA 4 /* Stopped DMA only */
+#define EEH_PE_STATE_UNAVAIL 5 /* Unavailable */
+
+/* EEH error types and functions */
+#define EEH_ERR_TYPE_32 0 /* 32-bits error */
+#define EEH_ERR_TYPE_64 1 /* 64-bits error */
+#define EEH_ERR_FUNC_MIN 0
+#define EEH_ERR_FUNC_LD_MEM_ADDR 0 /* Memory load */
+#define EEH_ERR_FUNC_LD_MEM_DATA 1
+#define EEH_ERR_FUNC_LD_IO_ADDR 2 /* IO load */
+#define EEH_ERR_FUNC_LD_IO_DATA 3
+#define EEH_ERR_FUNC_LD_CFG_ADDR 4 /* Config load */
+#define EEH_ERR_FUNC_LD_CFG_DATA 5
+#define EEH_ERR_FUNC_ST_MEM_ADDR 6 /* Memory store */
+#define EEH_ERR_FUNC_ST_MEM_DATA 7
+#define EEH_ERR_FUNC_ST_IO_ADDR 8 /* IO store */
+#define EEH_ERR_FUNC_ST_IO_DATA 9
+#define EEH_ERR_FUNC_ST_CFG_ADDR 10 /* Config store */
+#define EEH_ERR_FUNC_ST_CFG_DATA 11
+#define EEH_ERR_FUNC_DMA_RD_ADDR 12 /* DMA read */
+#define EEH_ERR_FUNC_DMA_RD_DATA 13
+#define EEH_ERR_FUNC_DMA_RD_MASTER 14
+#define EEH_ERR_FUNC_DMA_RD_TARGET 15
+#define EEH_ERR_FUNC_DMA_WR_ADDR 16 /* DMA write */
+#define EEH_ERR_FUNC_DMA_WR_DATA 17
+#define EEH_ERR_FUNC_DMA_WR_MASTER 18
+#define EEH_ERR_FUNC_DMA_WR_TARGET 19
+#define EEH_ERR_FUNC_MAX 19
+
+#endif /* _ASM_POWERPC_EEH_H */
diff --git a/arch/powerpc/include/uapi/asm/opal-prd.h b/arch/powerpc/include/uapi/asm/opal-prd.h
new file mode 100644
index 000000000000..319ff4a26158
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/opal-prd.h
@@ -0,0 +1,58 @@
+/*
+ * OPAL Runtime Diagnostics interface driver
+ * Supported on POWERNV platform
+ *
+ * (C) Copyright IBM 2015
+ *
+ * Author: Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>
+ * Author: Jeremy Kerr <jk@ozlabs.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI_ASM_POWERPC_OPAL_PRD_H_
+#define _UAPI_ASM_POWERPC_OPAL_PRD_H_
+
+#include <linux/types.h>
+
+/**
+ * The version of the kernel interface of the PRD system. This describes the
+ * interface available for the /dev/opal-prd device. The actual PRD message
+ * layout and content is private to the firmware <--> userspace interface, so
+ * is not covered by this versioning.
+ *
+ * Future interface versions are backwards-compatible; if a later kernel
+ * version is encountered, functionality provided in earlier versions
+ * will work.
+ */
+#define OPAL_PRD_KERNEL_VERSION 1
+
+#define OPAL_PRD_GET_INFO _IOR('o', 0x01, struct opal_prd_info)
+#define OPAL_PRD_SCOM_READ _IOR('o', 0x02, struct opal_prd_scom)
+#define OPAL_PRD_SCOM_WRITE _IOW('o', 0x03, struct opal_prd_scom)
+
+#ifndef __ASSEMBLY__
+
+struct opal_prd_info {
+ __u64 version;
+ __u64 reserved[3];
+};
+
+struct opal_prd_scom {
+ __u64 chip;
+ __u64 addr;
+ __u64 data;
+ __s64 rc;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_ASM_POWERPC_OPAL_PRD_H */
diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h
index 5d836b7c1176..5047659815a5 100644
--- a/arch/powerpc/include/uapi/asm/tm.h
+++ b/arch/powerpc/include/uapi/asm/tm.h
@@ -11,7 +11,7 @@
#define TM_CAUSE_RESCHED 0xde
#define TM_CAUSE_TLBI 0xdc
#define TM_CAUSE_FAC_UNAV 0xda
-#define TM_CAUSE_SYSCALL 0xd8 /* future use */
+#define TM_CAUSE_SYSCALL 0xd8
#define TM_CAUSE_MISC 0xd6 /* future use */
#define TM_CAUSE_SIGNAL 0xd4
#define TM_CAUSE_ALIGNMENT 0xd2
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index c1ebbdaac28f..87c7d1473488 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -33,11 +33,12 @@ obj-y := cputable.o ptrace.o syscalls.o \
signal.o sysfs.o cacheinfo.o time.o \
prom.o traps.o setup-common.o \
udbg.o misc.o io.o dma.o \
- misc_$(CONFIG_WORD_SIZE).o vdso32/ \
+ misc_$(CONFIG_WORD_SIZE).o \
of_platform.o prom_parse.o
obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \
signal_64.o ptrace32.o \
paca.o nvram_64.o firmware.o
+obj-$(CONFIG_VDSO32) += vdso32/
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0034b6b3556a..98230579d99c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -247,7 +247,7 @@ int main(void)
#endif
DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
- DEFINE(PACA_DSCR, offsetof(struct paca_struct, dscr_default));
+ DEFINE(PACA_DSCR_DEFAULT, offsetof(struct paca_struct, dscr_default));
DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 60262fdf35ba..7d80bfdfb15e 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -108,7 +108,9 @@ extern void __restore_cpu_e6500(void);
PPC_FEATURE_TRUE_LE | \
PPC_FEATURE_PSERIES_PERFMON_COMPAT)
#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \
- PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
+ PPC_FEATURE2_HTM_COMP | \
+ PPC_FEATURE2_HTM_NOSC_COMP | \
+ PPC_FEATURE2_DSCR | \
PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
PPC_FEATURE2_VEC_CRYPTO)
#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 484b2d4462c1..35e4dcc5dce3 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -248,6 +248,14 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
{
if (ppc_md.dma_set_mask)
return ppc_md.dma_set_mask(dev, dma_mask);
+
+ if (dev_is_pci(dev)) {
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct pci_controller *phb = pci_bus_to_host(pdev->bus);
+ if (phb->controller_ops.dma_set_mask)
+ return phb->controller_ops.dma_set_mask(pdev, dma_mask);
+ }
+
return __dma_set_mask(dev, dma_mask);
}
EXPORT_SYMBOL(dma_set_mask);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 9ee61d15653d..af9b597b10af 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -144,8 +144,6 @@ struct eeh_stats {
static struct eeh_stats eeh_stats;
-#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)
-
static int __init eeh_setup(char *str)
{
if (!strcmp(str, "off"))
@@ -719,7 +717,7 @@ static void *eeh_restore_dev_state(void *data, void *userdata)
/* The caller should restore state for the specified device */
if (pdev != dev)
- pci_save_state(pdev);
+ pci_restore_state(pdev);
return NULL;
}
@@ -1412,13 +1410,11 @@ static int dev_has_iommu_table(struct device *dev, void *data)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct pci_dev **ppdev = data;
- struct iommu_table *tbl;
if (!dev)
return 0;
- tbl = get_iommu_table_base(dev);
- if (tbl && tbl->it_group) {
+ if (dev->iommu_group) {
*ppdev = pdev;
return 1;
}
@@ -1647,6 +1643,41 @@ int eeh_pe_configure(struct eeh_pe *pe)
}
EXPORT_SYMBOL_GPL(eeh_pe_configure);
+/**
+ * eeh_pe_inject_err - Injecting the specified PCI error to the indicated PE
+ * @pe: the indicated PE
+ * @type: error type
+ * @function: error function
+ * @addr: address
+ * @mask: address mask
+ *
+ * The routine is called to inject the specified PCI error, which
+ * is determined by @type and @function, to the indicated PE for
+ * testing purpose.
+ */
+int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
+ unsigned long addr, unsigned long mask)
+{
+ /* Invalid PE ? */
+ if (!pe)
+ return -ENODEV;
+
+ /* Unsupported operation ? */
+ if (!eeh_ops || !eeh_ops->err_inject)
+ return -ENOENT;
+
+ /* Check on PCI error type */
+ if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
+ return -EINVAL;
+
+ /* Check on PCI error function */
+ if (func < EEH_ERR_FUNC_MIN || func > EEH_ERR_FUNC_MAX)
+ return -EINVAL;
+
+ return eeh_ops->err_inject(pe, type, func, addr, mask);
+}
+EXPORT_SYMBOL_GPL(eeh_pe_inject_err);
+
static int proc_eeh_show(struct seq_file *m, void *v)
{
if (!eeh_enabled()) {
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index eeabeabea49c..a1e86e172e3c 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -48,11 +48,11 @@
*/
struct pci_io_addr_range {
struct rb_node rb_node;
- unsigned long addr_lo;
- unsigned long addr_hi;
+ resource_size_t addr_lo;
+ resource_size_t addr_hi;
struct eeh_dev *edev;
struct pci_dev *pcidev;
- unsigned int flags;
+ unsigned long flags;
};
static struct pci_io_addr_cache {
@@ -125,8 +125,8 @@ static void eeh_addr_cache_print(struct pci_io_addr_cache *cache)
/* Insert address range into the rb tree. */
static struct pci_io_addr_range *
-eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
- unsigned long ahi, unsigned int flags)
+eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo,
+ resource_size_t ahi, unsigned long flags)
{
struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node;
struct rb_node *parent = NULL;
@@ -197,9 +197,9 @@ static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
/* Walk resources on this device, poke them into the tree */
for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
- unsigned long start = pci_resource_start(dev,i);
- unsigned long end = pci_resource_end(dev,i);
- unsigned int flags = pci_resource_flags(dev,i);
+ resource_size_t start = pci_resource_start(dev,i);
+ resource_size_t end = pci_resource_end(dev,i);
+ unsigned long flags = pci_resource_flags(dev,i);
/* We are interested only bus addresses, not dma or other stuff */
if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM)))
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 24768ff3cb73..89eb4bc34d3a 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -660,7 +660,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
eeh_pe_dev_traverse(pe, eeh_report_error, &result);
/* Get the current PCI slot state. This can take a long time,
- * sometimes over 3 seconds for certain systems.
+ * sometimes over 300 seconds for certain systems.
*/
rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index afbc20019c2e..579e0f9a2d57 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -34,6 +34,7 @@
#include <asm/ftrace.h>
#include <asm/hw_irq.h>
#include <asm/context_tracking.h>
+#include <asm/tm.h>
/*
* System calls.
@@ -51,6 +52,12 @@ exception_marker:
.globl system_call_common
system_call_common:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+ extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
+ bne tabort_syscall
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
andi. r10,r12,MSR_PR
mr r10,r1
addi r1,r1,-INT_FRAME_SIZE
@@ -311,6 +318,34 @@ syscall_exit_work:
bl do_syscall_trace_leave
b ret_from_except
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+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
+ mtmsrd r10, 0
+
+ /* tabort, this dooms the transaction, nothing else */
+ li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+ TABORT(R13)
+
+ /*
+ * Return directly to userspace. We have corrupted user register state,
+ * but userspace will never see that register state. Execution will
+ * resume after the tbegin of the aborted transaction with the
+ * checkpointed register state.
+ */
+ li r13, MSR_RI
+ andc r10, r10, r13
+ mtmsrd r10, 1
+ mtspr SPRN_SRR0, r11
+ mtspr SPRN_SRR1, r12
+
+ rfid
+ b . /* prevent speculative execution */
+#endif
+
/* Save non-volatile GPRs, if not already saved. */
_GLOBAL(save_nvgprs)
ld r11,_TRAP(r1)
@@ -556,7 +591,7 @@ BEGIN_FTR_SECTION
ld r0,THREAD_DSCR(r4)
cmpwi r6,0
bne 1f
- ld r0,PACA_DSCR(r13)
+ ld r0,PACA_DSCR_DEFAULT(r13)
1:
BEGIN_FTR_SECTION_NESTED(70)
mfspr r8, SPRN_FSCR
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 9519e6bdc6d7..0a0399c2af11 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -59,14 +59,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \
#if defined(CONFIG_RELOCATABLE)
/*
- * We can't branch directly; in the direct case we use LR
- * and system_call_entry restores LR. (We thus need to move
- * LR to r10 in the RFID case too.)
+ * We can't branch directly so we do it via the CTR which
+ * is volatile across system calls.
*/
#define SYSCALL_PSERIES_2_DIRECT \
mflr r10 ; \
ld r12,PACAKBASE(r13) ; \
- LOAD_HANDLER(r12, system_call_entry_direct) ; \
+ LOAD_HANDLER(r12, system_call_entry) ; \
mtctr r12 ; \
mfspr r12,SPRN_SRR1 ; \
/* Re-use of r13... No spare regs to do this */ \
@@ -80,7 +79,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \
mfspr r12,SPRN_SRR1 ; \
li r10,MSR_RI ; \
mtmsrd r10,1 ; /* Set RI (EE=0) */ \
- b system_call_entry_direct ;
+ b system_call_common ;
#endif
/*
@@ -969,13 +968,6 @@ hv_facility_unavailable_relon_trampoline:
__end_interrupts:
.align 7
-system_call_entry_direct:
-#if defined(CONFIG_RELOCATABLE)
- /* The first level prologue may have used LR to get here, saving
- * orig in r10. To save hacking/ifdeffing common code, restore here.
- */
- mtlr r10
-#endif
system_call_entry:
b system_call_common
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 9b53fe139bf6..78c1eba4c04a 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -48,6 +48,19 @@
mtspr spr, reg
#endif
+/* Macro to test if an address is a kernel address */
+#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
+#define IS_KERNEL(tmp, addr) \
+ andis. tmp, addr, 0x8000 /* Address >= 0x80000000 */
+#define BRANCH_UNLESS_KERNEL(label) beq label
+#else
+#define IS_KERNEL(tmp, addr) \
+ rlwinm tmp, addr, 16, 16, 31; \
+ cmpli cr0, tmp, PAGE_OFFSET >> 16
+#define BRANCH_UNLESS_KERNEL(label) blt label
+#endif
+
+
/*
* Value for the bits that have fixed value in RPN entries.
* Also used for tagging DAR for DTLBerror.
@@ -116,13 +129,13 @@ turn_on_mmu:
*/
#define EXCEPTION_PROLOG \
EXCEPTION_PROLOG_0; \
+ mfcr r10; \
EXCEPTION_PROLOG_1; \
EXCEPTION_PROLOG_2
#define EXCEPTION_PROLOG_0 \
mtspr SPRN_SPRG_SCRATCH0,r10; \
- mtspr SPRN_SPRG_SCRATCH1,r11; \
- mfcr r10
+ mtspr SPRN_SPRG_SCRATCH1,r11
#define EXCEPTION_PROLOG_1 \
mfspr r11,SPRN_SRR1; /* check whether user or kernel */ \
@@ -162,7 +175,6 @@ turn_on_mmu:
* Exception exit code.
*/
#define EXCEPTION_EPILOG_0 \
- mtcr r10; \
mfspr r10,SPRN_SPRG_SCRATCH0; \
mfspr r11,SPRN_SPRG_SCRATCH1
@@ -297,19 +309,22 @@ SystemCall:
* We have to use the MD_xxx registers for the tablewalk because the
* equivalent MI_xxx registers only perform the attribute functions.
*/
+
+#ifdef CONFIG_8xx_CPU15
+#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr) \
+ addi tmp, addr, PAGE_SIZE; \
+ tlbie tmp; \
+ addi tmp, addr, -PAGE_SIZE; \
+ tlbie tmp
+#else
+#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr)
+#endif
+
InstructionTLBMiss:
#ifdef CONFIG_8xx_CPU6
- mtspr SPRN_DAR, r3
+ mtspr SPRN_SPRG_SCRATCH2, r3
#endif
EXCEPTION_PROLOG_0
- mtspr SPRN_SPRG_SCRATCH2, r10
- mfspr r10, SPRN_SRR0 /* Get effective address of fault */
-#ifdef CONFIG_8xx_CPU15
- addi r11, r10, PAGE_SIZE
- tlbie r11
- addi r11, r10, -PAGE_SIZE
- tlbie r11
-#endif
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
@@ -317,24 +332,34 @@ InstructionTLBMiss:
#ifdef CONFIG_MODULES
/* Only modules will cause ITLB Misses as we always
* pin the first 8MB of kernel memory */
- andis. r11, r10, 0x8000 /* Address >= 0x80000000 */
-#endif
+ mfspr r11, SPRN_SRR0 /* Get effective address of fault */
+ INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11)
+ mfcr r10
+ IS_KERNEL(r11, r11)
mfspr r11, SPRN_M_TW /* Get level 1 table */
-#ifdef CONFIG_MODULES
- beq 3f
+ BRANCH_UNLESS_KERNEL(3f)
lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha
3:
+ mtcr r10
+ mfspr r10, SPRN_SRR0 /* Get effective address of fault */
+#else
+ mfspr r10, SPRN_SRR0 /* Get effective address of fault */
+ INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10)
+ mfspr r11, SPRN_M_TW /* Get level 1 table base address */
#endif
/* Insert level 1 index */
rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */
- /* Load the MI_TWC with the attributes for this "segment." */
- MTSPR_CPU6(SPRN_MI_TWC, r11, r3) /* Set segment attributes */
- rlwinm r11, r11,0,0,19 /* Extract page descriptor page address */
/* Extract level 2 index */
rlwinm r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
- lwzx r10, r10, r11 /* Get the pte */
+ rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */
+ lwz r10, 0(r10) /* Get the pte */
+
+ /* Insert the APG into the TWC from the Linux PTE. */
+ rlwimi r11, r10, 0, 25, 26
+ /* Load the MI_TWC with the attributes for this "segment." */
+ MTSPR_CPU6(SPRN_MI_TWC, r11, r3) /* Set segment attributes */
#ifdef CONFIG_SWAP
rlwinm r11, r10, 32-5, _PAGE_PRESENT
@@ -343,40 +368,41 @@ InstructionTLBMiss:
#endif
li r11, RPN_PATTERN
/* The Linux PTE won't go exactly into the MMU TLB.
- * Software indicator bits 21 and 28 must be clear.
+ * Software indicator bits 20-23 and 28 must be clear.
* Software indicator bits 24, 25, 26, and 27 must be
* set. All other Linux PTE bits control the behavior
* of the MMU.
*/
- rlwimi r10, r11, 0, 0x07f8 /* Set 24-27, clear 21-23,28 */
+ rlwimi r10, r11, 0, 0x0ff8 /* Set 24-27, clear 20-23,28 */
MTSPR_CPU6(SPRN_MI_RPN, r10, r3) /* Update TLB entry */
/* Restore registers */
#ifdef CONFIG_8xx_CPU6
- mfspr r3, SPRN_DAR
- mtspr SPRN_DAR, r11 /* Tag DAR */
+ mfspr r3, SPRN_SPRG_SCRATCH2
#endif
- mfspr r10, SPRN_SPRG_SCRATCH2
EXCEPTION_EPILOG_0
rfi
. = 0x1200
DataStoreTLBMiss:
#ifdef CONFIG_8xx_CPU6
- mtspr SPRN_DAR, r3
+ mtspr SPRN_SPRG_SCRATCH2, r3
#endif
EXCEPTION_PROLOG_0
- mtspr SPRN_SPRG_SCRATCH2, r10
- mfspr r10, SPRN_MD_EPN
+ mfcr r10
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
- andis. r11, r10, 0x8000
+ mfspr r11, SPRN_MD_EPN
+ IS_KERNEL(r11, r11)
mfspr r11, SPRN_M_TW /* Get level 1 table */
- beq 3f
+ BRANCH_UNLESS_KERNEL(3f)
lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha
3:
+ mtcr r10
+ mfspr r10, SPRN_MD_EPN
+
/* Insert level 1 index */
rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */
@@ -388,13 +414,13 @@ DataStoreTLBMiss:
rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */
lwz r10, 0(r10) /* Get the pte */
- /* Insert the Guarded flag into the TWC from the Linux PTE.
- * It is bit 27 of both the Linux PTE and the TWC (at least
+ /* Insert the Guarded flag and APG into the TWC from the Linux PTE.
+ * It is bit 26-27 of both the Linux PTE and the TWC (at least
* I got that right :-). It will be better when we can put
* this into the Linux pgd/pmd and load it in the operation
* above.
*/
- rlwimi r11, r10, 0, 27, 27
+ rlwimi r11, r10, 0, 26, 27
/* Insert the WriteThru flag into the TWC from the Linux PTE.
* It is bit 25 in the Linux PTE and bit 30 in the TWC
*/
@@ -423,14 +449,14 @@ DataStoreTLBMiss:
*/
li r11, RPN_PATTERN
rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */
+ rlwimi r10, r11, 0, 20, 20 /* clear 20 */
MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */
/* Restore registers */
#ifdef CONFIG_8xx_CPU6
- mfspr r3, SPRN_DAR
+ mfspr r3, SPRN_SPRG_SCRATCH2
#endif
mtspr SPRN_DAR, r11 /* Tag DAR */
- mfspr r10, SPRN_SPRG_SCRATCH2
EXCEPTION_EPILOG_0
rfi
@@ -456,6 +482,7 @@ InstructionTLBError:
. = 0x1400
DataTLBError:
EXCEPTION_PROLOG_0
+ mfcr r10
mfspr r11, SPRN_DAR
cmpwi cr0, r11, RPN_PATTERN
@@ -503,9 +530,9 @@ FixupDAR:/* Entry point for dcbx workaround. */
mtspr SPRN_SPRG_SCRATCH2, r10
/* fetch instruction from memory. */
mfspr r10, SPRN_SRR0
- andis. r11, r10, 0x8000 /* Address >= 0x80000000 */
+ IS_KERNEL(r11, r10)
mfspr r11, SPRN_M_TW /* Get level 1 table */
- beq 3f
+ BRANCH_UNLESS_KERNEL(3f)
lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha
/* Insert level 1 index */
3: rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
@@ -743,15 +770,20 @@ initial_mmu:
ori r8, r8, MI_EVALID /* Mark it valid */
mtspr SPRN_MI_EPN, r8
mtspr SPRN_MD_EPN, r8
- li r8, MI_PS8MEG /* Set 8M byte page */
+ li r8, MI_PS8MEG | (2 << 5) /* Set 8M byte page, APG 2 */
ori r8, r8, MI_SVALID /* Make it valid */
mtspr SPRN_MI_TWC, r8
+ li r8, MI_PS8MEG /* Set 8M byte page, APG 0 */
+ ori r8, r8, MI_SVALID /* Make it valid */
mtspr SPRN_MD_TWC, r8
li r8, MI_BOOTINIT /* Create RPN for address 0 */
mtspr SPRN_MI_RPN, r8 /* Store TLB entry */
mtspr SPRN_MD_RPN, r8
- lis r8, MI_Kp@h /* Set the protection mode */
+ lis r8, MI_APG_INIT@h /* Set protection modes */
+ ori r8, r8, MI_APG_INIT@l
mtspr SPRN_MI_AP, r8
+ lis r8, MD_APG_INIT@h
+ ori r8, r8, MD_APG_INIT@l
mtspr SPRN_MD_AP, r8
/* Map another 8 MByte at the IMMR to get the processor
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 15448668988d..b9b6ef510be1 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -58,15 +58,6 @@ BEGIN_FTR_SECTION
mtlr r0
lis r3,HID0_NAP@h
END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
-BEGIN_FTR_SECTION
- msync
- li r7,L2CSR0_L2FL@l
- mtspr SPRN_L2CSR0,r7
-2:
- mfspr r7,SPRN_L2CSR0
- andi. r4,r7,L2CSR0_L2FL@l
- bne 2b
-END_FTR_SECTION_IFSET(CPU_FTR_L2CSR|CPU_FTR_CAN_NAP)
1:
/* Go to NAP or DOZE now */
mfspr r4,SPRN_HID0
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index b054f33ab1fb..a8e3490b54e3 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -322,11 +322,11 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
ret = entry << tbl->it_page_shift; /* Set the return dma address */
/* Put the TCEs in the HW table */
- build_fail = ppc_md.tce_build(tbl, entry, npages,
+ build_fail = tbl->it_ops->set(tbl, entry, npages,
(unsigned long)page &
IOMMU_PAGE_MASK(tbl), direction, attrs);
- /* ppc_md.tce_build() only returns non-zero for transient errors.
+ /* tbl->it_ops->set() only returns non-zero for transient errors.
* Clean up the table bitmap in this case and return
* DMA_ERROR_CODE. For all other errors the functionality is
* not altered.
@@ -337,8 +337,8 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
}
/* Flush/invalidate TLB caches if necessary */
- if (ppc_md.tce_flush)
- ppc_md.tce_flush(tbl);
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
/* Make sure updates are seen by hardware */
mb();
@@ -408,7 +408,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
if (!iommu_free_check(tbl, dma_addr, npages))
return;
- ppc_md.tce_free(tbl, entry, npages);
+ tbl->it_ops->clear(tbl, entry, npages);
spin_lock_irqsave(&(pool->lock), flags);
bitmap_clear(tbl->it_map, free_entry, npages);
@@ -424,8 +424,8 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
* not do an mb() here on purpose, it is not needed on any of
* the current platforms.
*/
- if (ppc_md.tce_flush)
- ppc_md.tce_flush(tbl);
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
}
int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
@@ -495,7 +495,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
npages, entry, dma_addr);
/* Insert into HW table */
- build_fail = ppc_md.tce_build(tbl, entry, npages,
+ build_fail = tbl->it_ops->set(tbl, entry, npages,
vaddr & IOMMU_PAGE_MASK(tbl),
direction, attrs);
if(unlikely(build_fail))
@@ -534,8 +534,8 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
}
/* Flush/invalidate TLB caches if necessary */
- if (ppc_md.tce_flush)
- ppc_md.tce_flush(tbl);
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
DBG("mapped %d elements:\n", outcount);
@@ -600,8 +600,8 @@ void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
* do not do an mb() here, the affected platforms do not need it
* when freeing.
*/
- if (ppc_md.tce_flush)
- ppc_md.tce_flush(tbl);
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
}
static void iommu_table_clear(struct iommu_table *tbl)
@@ -613,17 +613,17 @@ static void iommu_table_clear(struct iommu_table *tbl)
*/
if (!is_kdump_kernel() || is_fadump_active()) {
/* Clear the table in case firmware left allocations in it */
- ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
+ tbl->it_ops->clear(tbl, tbl->it_offset, tbl->it_size);
return;
}
#ifdef CONFIG_CRASH_DUMP
- if (ppc_md.tce_get) {
+ if (tbl->it_ops->get) {
unsigned long index, tceval, tcecount = 0;
/* Reserve the existing mappings left by the first kernel. */
for (index = 0; index < tbl->it_size; index++) {
- tceval = ppc_md.tce_get(tbl, index + tbl->it_offset);
+ tceval = tbl->it_ops->get(tbl, index + tbl->it_offset);
/*
* Freed TCE entry contains 0x7fffffffffffffff on JS20
*/
@@ -657,6 +657,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
unsigned int i;
struct iommu_pool *p;
+ BUG_ON(!tbl->it_ops);
+
/* number of bytes needed for the bitmap */
sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
@@ -713,9 +715,11 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
unsigned long bitmap_sz;
unsigned int order;
- if (!tbl || !tbl->it_map) {
- printk(KERN_ERR "%s: expected TCE map for %s\n", __func__,
- node_name);
+ if (!tbl)
+ return;
+
+ if (!tbl->it_map) {
+ kfree(tbl);
return;
}
@@ -726,13 +730,6 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
if (tbl->it_offset == 0)
clear_bit(0, tbl->it_map);
-#ifdef CONFIG_IOMMU_API
- if (tbl->it_group) {
- iommu_group_put(tbl->it_group);
- BUG_ON(tbl->it_group);
- }
-#endif
-
/* verify that table contains no entries */
if (!bitmap_empty(tbl->it_map, tbl->it_size))
pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);
@@ -871,17 +868,33 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
}
}
+unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir)
+{
+ switch (dir) {
+ case DMA_BIDIRECTIONAL:
+ return TCE_PCI_READ | TCE_PCI_WRITE;
+ case DMA_FROM_DEVICE:
+ return TCE_PCI_WRITE;
+ case DMA_TO_DEVICE:
+ return TCE_PCI_READ;
+ default:
+ return 0;
+ }
+}
+EXPORT_SYMBOL_GPL(iommu_direction_to_tce_perm);
+
#ifdef CONFIG_IOMMU_API
/*
* SPAPR TCE API
*/
static void group_release(void *iommu_data)
{
- struct iommu_table *tbl = iommu_data;
- tbl->it_group = NULL;
+ struct iommu_table_group *table_group = iommu_data;
+
+ table_group->group = NULL;
}
-void iommu_register_group(struct iommu_table *tbl,
+void iommu_register_group(struct iommu_table_group *table_group,
int pci_domain_number, unsigned long pe_num)
{
struct iommu_group *grp;
@@ -893,8 +906,8 @@ void iommu_register_group(struct iommu_table *tbl,
PTR_ERR(grp));
return;
}
- tbl->it_group = grp;
- iommu_group_set_iommudata(grp, tbl, group_release);
+ table_group->group = grp;
+ iommu_group_set_iommudata(grp, table_group, group_release);
name = kasprintf(GFP_KERNEL, "domain%d-pe%lx",
pci_domain_number, pe_num);
if (!name)
@@ -919,8 +932,8 @@ EXPORT_SYMBOL_GPL(iommu_tce_direction);
void iommu_flush_tce(struct iommu_table *tbl)
{
/* Flush/invalidate TLB caches if necessary */
- if (ppc_md.tce_flush)
- ppc_md.tce_flush(tbl);
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
/* Make sure updates are seen by hardware */
mb();
@@ -931,7 +944,7 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl,
unsigned long ioba, unsigned long tce_value,
unsigned long npages)
{
- /* ppc_md.tce_free() does not support any value but 0 */
+ /* tbl->it_ops->clear() does not support any value but 0 */
if (tce_value)
return -EINVAL;
@@ -952,10 +965,7 @@ EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
int iommu_tce_put_param_check(struct iommu_table *tbl,
unsigned long ioba, unsigned long tce)
{
- if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
- return -EINVAL;
-
- if (tce & ~(IOMMU_PAGE_MASK(tbl) | TCE_PCI_WRITE | TCE_PCI_READ))
+ if (tce & ~IOMMU_PAGE_MASK(tbl))
return -EINVAL;
if (ioba & ~IOMMU_PAGE_MASK(tbl))
@@ -972,68 +982,16 @@ int iommu_tce_put_param_check(struct iommu_table *tbl,
}
EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
-unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry)
-{
- unsigned long oldtce;
- struct iommu_pool *pool = get_pool(tbl, entry);
-
- spin_lock(&(pool->lock));
-
- oldtce = ppc_md.tce_get(tbl, entry);
- if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))
- ppc_md.tce_free(tbl, entry, 1);
- else
- oldtce = 0;
-
- spin_unlock(&(pool->lock));
-
- return oldtce;
-}
-EXPORT_SYMBOL_GPL(iommu_clear_tce);
-
-int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
- unsigned long entry, unsigned long pages)
-{
- unsigned long oldtce;
- struct page *page;
-
- for ( ; pages; --pages, ++entry) {
- oldtce = iommu_clear_tce(tbl, entry);
- if (!oldtce)
- continue;
-
- page = pfn_to_page(oldtce >> PAGE_SHIFT);
- WARN_ON(!page);
- if (page) {
- if (oldtce & TCE_PCI_WRITE)
- SetPageDirty(page);
- put_page(page);
- }
- }
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(iommu_clear_tces_and_put_pages);
-
-/*
- * hwaddr is a kernel virtual address here (0xc... bazillion),
- * tce_build converts it to a physical address.
- */
-int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
- unsigned long hwaddr, enum dma_data_direction direction)
+long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
+ unsigned long *hpa, enum dma_data_direction *direction)
{
- int ret = -EBUSY;
- unsigned long oldtce;
- struct iommu_pool *pool = get_pool(tbl, entry);
-
- spin_lock(&(pool->lock));
+ long ret;
- oldtce = ppc_md.tce_get(tbl, entry);
- /* Add new entry if it is not busy */
- if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)))
- ret = ppc_md.tce_build(tbl, entry, 1, hwaddr, direction, NULL);
+ ret = tbl->it_ops->exchange(tbl, entry, hpa, direction);
- spin_unlock(&(pool->lock));
+ if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+ (*direction == DMA_BIDIRECTIONAL)))
+ SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT));
/* if (unlikely(ret))
pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
@@ -1042,84 +1000,72 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
return ret;
}
-EXPORT_SYMBOL_GPL(iommu_tce_build);
+EXPORT_SYMBOL_GPL(iommu_tce_xchg);
-int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
- unsigned long tce)
+int iommu_take_ownership(struct iommu_table *tbl)
{
- int ret;
- struct page *page = NULL;
- unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
- enum dma_data_direction direction = iommu_tce_direction(tce);
-
- ret = get_user_pages_fast(tce & PAGE_MASK, 1,
- direction != DMA_TO_DEVICE, &page);
- if (unlikely(ret != 1)) {
- /* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
- tce, entry << tbl->it_page_shift, ret); */
- return -EFAULT;
- }
- hwaddr = (unsigned long) page_address(page) + offset;
-
- ret = iommu_tce_build(tbl, entry, hwaddr, direction);
- if (ret)
- put_page(page);
-
- if (ret < 0)
- pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
- __func__, entry << tbl->it_page_shift, tce, ret);
+ unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+ int ret = 0;
- return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_put_tce_user_mode);
+ /*
+ * VFIO does not control TCE entries allocation and the guest
+ * can write new TCEs on top of existing ones so iommu_tce_build()
+ * must be able to release old pages. This functionality
+ * requires exchange() callback defined so if it is not
+ * implemented, we disallow taking ownership over the table.
+ */
+ if (!tbl->it_ops->exchange)
+ return -EINVAL;
-int iommu_take_ownership(struct iommu_table *tbl)
-{
- unsigned long sz = (tbl->it_size + 7) >> 3;
+ spin_lock_irqsave(&tbl->large_pool.lock, flags);
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_lock(&tbl->pools[i].lock);
if (tbl->it_offset == 0)
clear_bit(0, tbl->it_map);
if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
pr_err("iommu_tce: it_map is not empty");
- return -EBUSY;
+ ret = -EBUSY;
+ /* Restore bit#0 set by iommu_init_table() */
+ if (tbl->it_offset == 0)
+ set_bit(0, tbl->it_map);
+ } else {
+ memset(tbl->it_map, 0xff, sz);
}
- memset(tbl->it_map, 0xff, sz);
- iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_unlock(&tbl->pools[i].lock);
+ spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
- /*
- * Disable iommu bypass, otherwise the user can DMA to all of
- * our physical memory via the bypass window instead of just
- * the pages that has been explicitly mapped into the iommu
- */
- if (tbl->set_bypass)
- tbl->set_bypass(tbl, false);
-
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(iommu_take_ownership);
void iommu_release_ownership(struct iommu_table *tbl)
{
- unsigned long sz = (tbl->it_size + 7) >> 3;
+ unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+
+ spin_lock_irqsave(&tbl->large_pool.lock, flags);
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_lock(&tbl->pools[i].lock);
- iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
memset(tbl->it_map, 0, sz);
/* Restore bit#0 set by iommu_init_table() */
if (tbl->it_offset == 0)
set_bit(0, tbl->it_map);
- /* The kernel owns the device now, we can restore the iommu bypass */
- if (tbl->set_bypass)
- tbl->set_bypass(tbl, true);
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_unlock(&tbl->pools[i].lock);
+ spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
}
EXPORT_SYMBOL_GPL(iommu_release_ownership);
int iommu_add_device(struct device *dev)
{
struct iommu_table *tbl;
+ struct iommu_table_group_link *tgl;
/*
* The sysfs entries should be populated before
@@ -1137,15 +1083,22 @@ int iommu_add_device(struct device *dev)
}
tbl = get_iommu_table_base(dev);
- if (!tbl || !tbl->it_group) {
+ if (!tbl) {
pr_debug("%s: Skipping device %s with no tbl\n",
__func__, dev_name(dev));
return 0;
}
+ tgl = list_first_entry_or_null(&tbl->it_group_list,
+ struct iommu_table_group_link, next);
+ if (!tgl) {
+ pr_debug("%s: Skipping device %s with no group\n",
+ __func__, dev_name(dev));
+ return 0;
+ }
pr_debug("%s: Adding %s to iommu group %d\n",
__func__, dev_name(dev),
- iommu_group_id(tbl->it_group));
+ iommu_group_id(tgl->table_group->group));
if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) {
pr_err("%s: Invalid IOMMU page size %lx (%lx) on %s\n",
@@ -1154,7 +1107,7 @@ int iommu_add_device(struct device *dev)
return -EINVAL;
}
- return iommu_group_add_device(tbl->it_group, dev);
+ return iommu_group_add_device(tgl->table_group->group, dev);
}
EXPORT_SYMBOL_GPL(iommu_add_device);
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 15c99b649b04..b2eb4686bd8f 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -73,7 +73,7 @@ void save_mce_event(struct pt_regs *regs, long handled,
uint64_t nip, uint64_t addr)
{
uint64_t srr1;
- int index = __this_cpu_inc_return(mce_nest_count);
+ int index = __this_cpu_inc_return(mce_nest_count) - 1;
struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
/*
@@ -184,7 +184,7 @@ void machine_check_queue_event(void)
if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
return;
- index = __this_cpu_inc_return(mce_queue_count);
+ index = __this_cpu_inc_return(mce_queue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
__this_cpu_dec(mce_queue_count);
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index 71bd161640cf..dab616a33b8d 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -15,7 +15,10 @@
int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
- if (!ppc_md.setup_msi_irqs || !ppc_md.teardown_msi_irqs) {
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+ if (!phb->controller_ops.setup_msi_irqs ||
+ !phb->controller_ops.teardown_msi_irqs) {
pr_debug("msi: Platform doesn't provide MSI callbacks.\n");
return -ENOSYS;
}
@@ -24,10 +27,12 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
if (type == PCI_CAP_ID_MSI && nvec > 1)
return 1;
- return ppc_md.setup_msi_irqs(dev, nvec, type);
+ return phb->controller_ops.setup_msi_irqs(dev, nvec, type);
}
void arch_teardown_msi_irqs(struct pci_dev *dev)
{
- ppc_md.teardown_msi_irqs(dev);
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+ phb->controller_ops.teardown_msi_irqs(dev);
}
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 0d054068a21d..b9de34d44fcb 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -89,6 +89,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
#endif
return phb;
}
+EXPORT_SYMBOL_GPL(pcibios_alloc_controller);
void pcibios_free_controller(struct pci_controller *phb)
{
@@ -1447,6 +1448,7 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
list_for_each_entry(child_bus, &bus->children, node)
pcibios_claim_one_bus(child_bus);
}
+EXPORT_SYMBOL_GPL(pcibios_claim_one_bus);
/* pcibios_finish_adding_to_bus
@@ -1488,6 +1490,14 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
return pci_enable_resources(dev, mask);
}
+void pcibios_disable_device(struct pci_dev *dev)
+{
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+ if (phb->controller_ops.disable_device)
+ phb->controller_ops.disable_device(dev);
+}
+
resource_size_t pcibios_io_space_offset(struct pci_controller *hose)
{
return (unsigned long) hose->io_base_virt - _IO_BASE;
@@ -1680,6 +1690,7 @@ void pcibios_scan_phb(struct pci_controller *hose)
pcie_bus_configure_settings(child);
}
}
+EXPORT_SYMBOL_GPL(pcibios_scan_phb);
static void fixup_hide_host_resource_fsl(struct pci_dev *dev)
{
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 7ed85a69a9c2..7f9ed0c1f6b9 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -29,7 +29,12 @@
*/
void pcibios_release_device(struct pci_dev *dev)
{
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
eeh_remove_device(dev);
+
+ if (phb->controller_ops.release_device)
+ phb->controller_ops.release_device(dev);
}
/**
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index febb50dd5328..8005e18d1b40 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1112,7 +1112,6 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp)
/*
* Copy a thread..
*/
-extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */
/*
* Copy architecture-specific thread state
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 308c5e15676b..8b888b12a475 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -46,7 +46,6 @@
#include <asm/mmu.h>
#include <asm/paca.h>
#include <asm/pgtable.h>
-#include <asm/pci.h>
#include <asm/iommu.h>
#include <asm/btext.h>
#include <asm/sections.h>
@@ -573,6 +572,7 @@ static void __init early_reserve_mem_dt(void)
int len;
const __be32 *prop;
+ early_init_fdt_reserve_self();
early_init_fdt_scan_reserved_mem();
dt_root = of_get_flat_dt_root();
@@ -800,6 +800,7 @@ int of_get_ibm_chip_id(struct device_node *np)
}
return -1;
}
+EXPORT_SYMBOL(of_get_ibm_chip_id);
/**
* cpu_to_chip_id - Return the cpus chip-id
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index fd1fe4c37599..fcca8077e6a2 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -37,7 +37,6 @@
#include <asm/smp.h>
#include <asm/mmu.h>
#include <asm/pgtable.h>
-#include <asm/pci.h>
#include <asm/iommu.h>
#include <asm/btext.h>
#include <asm/sections.h>
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index c69671c03c3b..bdcbb716f4d6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -523,7 +523,8 @@ void __init setup_system(void)
smp_release_cpus();
#endif
- pr_info("Starting Linux PPC64 %s\n", init_utsname()->version);
+ pr_info("Starting Linux %s %s\n", init_utsname()->machine,
+ init_utsname()->version);
pr_info("-----------------------------------------------------\n");
pr_info("ppc64_pft_size = 0x%llx\n", ppc64_pft_size);
@@ -686,6 +687,9 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_PPC_64K_PAGES
init_mm.context.pte_frag = NULL;
#endif
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ mm_iommu_init(&init_mm.context);
+#endif
irqstack_early_init();
exc_lvl_early_init();
emergency_stack_init();
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index fa1fd8a0c867..692873bff334 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -496,13 +496,34 @@ static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
static DEVICE_ATTR(pir, 0400, show_pir, NULL);
+/*
+ * This is the system wide DSCR register default value. Any
+ * change to this default value through the sysfs interface
+ * will update all per cpu DSCR default values across the
+ * system stored in their respective PACA structures.
+ */
static unsigned long dscr_default;
+/**
+ * read_dscr() - Fetch the cpu specific DSCR default
+ * @val: Returned cpu specific DSCR default value
+ *
+ * This function returns the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
static void read_dscr(void *val)
{
*(unsigned long *)val = get_paca()->dscr_default;
}
+
+/**
+ * write_dscr() - Update the cpu specific DSCR default
+ * @val: New cpu specific DSCR default value to update
+ *
+ * This function updates the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
static void write_dscr(void *val)
{
get_paca()->dscr_default = *(unsigned long *)val;
@@ -520,12 +541,29 @@ static void add_write_permission_dev_attr(struct device_attribute *attr)
attr->attr.mode |= 0200;
}
+/**
+ * show_dscr_default() - Fetch the system wide DSCR default
+ * @dev: Device structure
+ * @attr: Device attribute structure
+ * @buf: Interface buffer
+ *
+ * This function returns the system wide DSCR default value.
+ */
static ssize_t show_dscr_default(struct device *dev,
struct device_attribute *attr, char *buf)
{
return sprintf(buf, "%lx\n", dscr_default);
}
+/**
+ * store_dscr_default() - Update the system wide DSCR default
+ * @dev: Device structure
+ * @attr: Device attribute structure
+ * @buf: Interface buffer
+ * @count: Size of the update
+ *
+ * This function updates the system wide DSCR default value.
+ */
static ssize_t __used store_dscr_default(struct device *dev,
struct device_attribute *attr, const char *buf,
size_t count)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 5754b226da7e..bf8f34a58670 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -293,7 +293,7 @@ dont_backup_fp:
ld r2, STK_GOT(r1)
/* Load CPU's default DSCR */
- ld r0, PACA_DSCR(r13)
+ ld r0, PACA_DSCR_DEFAULT(r13)
mtspr SPRN_DSCR, r0
blr
@@ -473,7 +473,7 @@ restore_gprs:
ld r2, STK_GOT(r1)
/* Load CPU's default DSCR */
- ld r0, PACA_DSCR(r13)
+ ld r0, PACA_DSCR_DEFAULT(r13)
mtspr SPRN_DSCR, r0
blr
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 19e4744b6eba..6530f1b8874d 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1377,6 +1377,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
};
char *facility = "unknown";
u64 value;
+ u32 instword, rd;
u8 status;
bool hv;
@@ -1388,12 +1389,46 @@ void facility_unavailable_exception(struct pt_regs *regs)
status = value >> 56;
if (status == FSCR_DSCR_LG) {
- /* User is acessing the DSCR. Set the inherit bit and allow
- * the user to set it directly in future by setting via the
- * FSCR DSCR bit. We always leave HFSCR DSCR set.
+ /*
+ * User is accessing the DSCR register using the problem
+ * state only SPR number (0x03) either through a mfspr or
+ * a mtspr instruction. If it is a write attempt through
+ * a mtspr, then we set the inherit bit. This also allows
+ * the user to write or read the register directly in the
+ * future by setting via the FSCR DSCR bit. But in case it
+ * is a read DSCR attempt through a mfspr instruction, we
+ * just emulate the instruction instead. This code path will
+ * always emulate all the mfspr instructions till the user
+ * has attempted atleast one mtspr instruction. This way it
+ * preserves the same behaviour when the user is accessing
+ * the DSCR through privilege level only SPR number (0x11)
+ * which is emulated through illegal instruction exception.
+ * We always leave HFSCR DSCR set.
*/
- current->thread.dscr_inherit = 1;
- mtspr(SPRN_FSCR, value | FSCR_DSCR);
+ if (get_user(instword, (u32 __user *)(regs->nip))) {
+ pr_err("Failed to fetch the user instruction\n");
+ return;
+ }
+
+ /* Write into DSCR (mtspr 0x03, RS) */
+ if ((instword & PPC_INST_MTSPR_DSCR_USER_MASK)
+ == PPC_INST_MTSPR_DSCR_USER) {
+ rd = (instword >> 21) & 0x1f;
+ current->thread.dscr = regs->gpr[rd];
+ current->thread.dscr_inherit = 1;
+ mtspr(SPRN_FSCR, value | FSCR_DSCR);
+ }
+
+ /* Read from DSCR (mfspr RT, 0x03) */
+ if ((instword & PPC_INST_MFSPR_DSCR_USER_MASK)
+ == PPC_INST_MFSPR_DSCR_USER) {
+ if (emulate_instruction(regs)) {
+ pr_err("DSCR based mfspr emulation failed\n");
+ return;
+ }
+ regs->nip += 4;
+ emulate_single_step(regs);
+ }
return;
}
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 305eb0d9b768..b457bfa28436 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -49,13 +49,16 @@
/* The alignment of the vDSO */
#define VDSO_ALIGNMENT (1 << 16)
-extern char vdso32_start, vdso32_end;
-static void *vdso32_kbase = &vdso32_start;
static unsigned int vdso32_pages;
+static void *vdso32_kbase;
static struct page **vdso32_pagelist;
unsigned long vdso32_sigtramp;
unsigned long vdso32_rt_sigtramp;
+#ifdef CONFIG_VDSO32
+extern char vdso32_start, vdso32_end;
+#endif
+
#ifdef CONFIG_PPC64
extern char vdso64_start, vdso64_end;
static void *vdso64_kbase = &vdso64_start;
@@ -140,50 +143,6 @@ struct lib64_elfinfo
};
-#ifdef __DEBUG
-static void dump_one_vdso_page(struct page *pg, struct page *upg)
-{
- printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT),
- page_count(pg),
- pg->flags);
- if (upg && !IS_ERR(upg) /* && pg != upg*/) {
- printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg)
- << PAGE_SHIFT),
- page_count(upg),
- upg->flags);
- }
- printk("\n");
-}
-
-static void dump_vdso_pages(struct vm_area_struct * vma)
-{
- int i;
-
- if (!vma || is_32bit_task()) {
- printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase);
- for (i=0; i<vdso32_pages; i++) {
- struct page *pg = virt_to_page(vdso32_kbase +
- i*PAGE_SIZE);
- struct page *upg = (vma && vma->vm_mm) ?
- follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0)
- : NULL;
- dump_one_vdso_page(pg, upg);
- }
- }
- if (!vma || !is_32bit_task()) {
- printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase);
- for (i=0; i<vdso64_pages; i++) {
- struct page *pg = virt_to_page(vdso64_kbase +
- i*PAGE_SIZE);
- struct page *upg = (vma && vma->vm_mm) ?
- follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0)
- : NULL;
- dump_one_vdso_page(pg, upg);
- }
- }
-}
-#endif /* DEBUG */
-
/*
* This is called from binfmt_elf, we create the special vma for the
* vDSO and insert it into the mm struct tree
@@ -292,6 +251,7 @@ const char *arch_vma_name(struct vm_area_struct *vma)
+#ifdef CONFIG_VDSO32
static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname,
unsigned long *size)
{
@@ -379,6 +339,20 @@ static int __init vdso_do_func_patch32(struct lib32_elfinfo *v32,
return 0;
}
+#else /* !CONFIG_VDSO32 */
+static unsigned long __init find_function32(struct lib32_elfinfo *lib,
+ const char *symname)
+{
+ return 0;
+}
+
+static int __init vdso_do_func_patch32(struct lib32_elfinfo *v32,
+ struct lib64_elfinfo *v64,
+ const char *orig, const char *fix)
+{
+ return 0;
+}
+#endif /* CONFIG_VDSO32 */
#ifdef CONFIG_PPC64
@@ -489,6 +463,7 @@ static __init int vdso_do_find_sections(struct lib32_elfinfo *v32,
* Locate symbol tables & text section
*/
+#ifdef CONFIG_VDSO32
v32->dynsym = find_section32(v32->hdr, ".dynsym", &v32->dynsymsize);
v32->dynstr = find_section32(v32->hdr, ".dynstr", NULL);
if (v32->dynsym == NULL || v32->dynstr == NULL) {
@@ -501,6 +476,7 @@ static __init int vdso_do_find_sections(struct lib32_elfinfo *v32,
return -1;
}
v32->text = sect - vdso32_kbase;
+#endif
#ifdef CONFIG_PPC64
v64->dynsym = find_section64(v64->hdr, ".dynsym", &v64->dynsymsize);
@@ -537,7 +513,9 @@ static __init void vdso_setup_trampolines(struct lib32_elfinfo *v32,
static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
struct lib64_elfinfo *v64)
{
+#ifdef CONFIG_VDSO32
Elf32_Sym *sym32;
+#endif
#ifdef CONFIG_PPC64
Elf64_Sym *sym64;
@@ -552,6 +530,7 @@ static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
(sym64->st_value - VDSO64_LBASE);
#endif /* CONFIG_PPC64 */
+#ifdef CONFIG_VDSO32
sym32 = find_symbol32(v32, "__kernel_datapage_offset");
if (sym32 == NULL) {
printk(KERN_ERR "vDSO32: Can't find symbol "
@@ -561,6 +540,7 @@ static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
*((int *)(vdso32_kbase + (sym32->st_value - VDSO32_LBASE))) =
(vdso32_pages << PAGE_SHIFT) -
(sym32->st_value - VDSO32_LBASE);
+#endif
return 0;
}
@@ -569,55 +549,54 @@ static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
struct lib64_elfinfo *v64)
{
- void *start32;
- unsigned long size32;
+ unsigned long size;
+ void *start;
#ifdef CONFIG_PPC64
- void *start64;
- unsigned long size64;
-
- start64 = find_section64(v64->hdr, "__ftr_fixup", &size64);
- if (start64)
+ start = find_section64(v64->hdr, "__ftr_fixup", &size);
+ if (start)
do_feature_fixups(cur_cpu_spec->cpu_features,
- start64, start64 + size64);
+ start, start + size);
- start64 = find_section64(v64->hdr, "__mmu_ftr_fixup", &size64);
- if (start64)
+ start = find_section64(v64->hdr, "__mmu_ftr_fixup", &size);
+ if (start)
do_feature_fixups(cur_cpu_spec->mmu_features,
- start64, start64 + size64);
+ start, start + size);
- start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64);
- if (start64)
+ start = find_section64(v64->hdr, "__fw_ftr_fixup", &size);
+ if (start)
do_feature_fixups(powerpc_firmware_features,
- start64, start64 + size64);
+ start, start + size);
- start64 = find_section64(v64->hdr, "__lwsync_fixup", &size64);
- if (start64)
+ start = find_section64(v64->hdr, "__lwsync_fixup", &size);
+ if (start)
do_lwsync_fixups(cur_cpu_spec->cpu_features,
- start64, start64 + size64);
+ start, start + size);
#endif /* CONFIG_PPC64 */
- start32 = find_section32(v32->hdr, "__ftr_fixup", &size32);
- if (start32)
+#ifdef CONFIG_VDSO32
+ start = find_section32(v32->hdr, "__ftr_fixup", &size);
+ if (start)
do_feature_fixups(cur_cpu_spec->cpu_features,
- start32, start32 + size32);
+ start, start + size);
- start32 = find_section32(v32->hdr, "__mmu_ftr_fixup", &size32);
- if (start32)
+ start = find_section32(v32->hdr, "__mmu_ftr_fixup", &size);
+ if (start)
do_feature_fixups(cur_cpu_spec->mmu_features,
- start32, start32 + size32);
+ start, start + size);
#ifdef CONFIG_PPC64
- start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32);
- if (start32)
+ start = find_section32(v32->hdr, "__fw_ftr_fixup", &size);
+ if (start)
do_feature_fixups(powerpc_firmware_features,
- start32, start32 + size32);
+ start, start + size);
#endif /* CONFIG_PPC64 */
- start32 = find_section32(v32->hdr, "__lwsync_fixup", &size32);
- if (start32)
+ start = find_section32(v32->hdr, "__lwsync_fixup", &size);
+ if (start)
do_lwsync_fixups(cur_cpu_spec->cpu_features,
- start32, start32 + size32);
+ start, start + size);
+#endif
return 0;
}
@@ -779,11 +758,15 @@ static int __init vdso_init(void)
#endif /* CONFIG_PPC64 */
+#ifdef CONFIG_VDSO32
+ vdso32_kbase = &vdso32_start;
+
/*
* Calculate the size of the 32 bits vDSO
*/
vdso32_pages = (&vdso32_end - &vdso32_start) >> PAGE_SHIFT;
DBG("vdso32_kbase: %p, 0x%x pages\n", vdso32_kbase, vdso32_pages);
+#endif
/*
@@ -804,6 +787,7 @@ static int __init vdso_init(void)
return 0;
}
+#ifdef CONFIG_VDSO32
/* Make sure pages are in the correct state */
vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 2),
GFP_KERNEL);
@@ -816,6 +800,7 @@ static int __init vdso_init(void)
}
vdso32_pagelist[i++] = virt_to_page(vdso_data);
vdso32_pagelist[i] = NULL;
+#endif
#ifdef CONFIG_PPC64
vdso64_pagelist = kzalloc(sizeof(struct page *) * (vdso64_pages + 2),
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 5bfdab9047be..b41426c60ef6 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1196,6 +1196,11 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
tbl->it_type = TCE_VB;
tbl->it_blocksize = 16;
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ tbl->it_ops = &iommu_table_lpar_multi_ops;
+ else
+ tbl->it_ops = &iommu_table_pseries_ops;
+
return iommu_init_table(tbl, -1);
}
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index f096e72262f4..1db685104ffc 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -213,6 +213,7 @@ SECTIONS
*(.opd)
}
+ . = ALIGN(256);
.got : AT(ADDR(.got) - LOAD_OFFSET) {
__toc_start = .;
#ifndef CONFIG_RELOCATABLE
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 453a8a47a467..05ea8fc7f829 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -757,16 +757,17 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
int kvmppc_core_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem);
}
void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old)
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new)
{
- kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old);
+ kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new);
}
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 1a4acf8bf4f4..dab68b7af3f2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -650,7 +650,7 @@ static void kvmppc_rmap_reset(struct kvm *kvm)
int srcu_idx;
srcu_idx = srcu_read_lock(&kvm->srcu);
- slots = kvm->memslots;
+ slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
/*
* This assumes it is acceptable to lose reference and
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 48d3c5d2ecc9..68d067ad4222 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1952,7 +1952,7 @@ static void post_guest_process(struct kvmppc_vcore *vc)
*/
static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
{
- struct kvm_vcpu *vcpu;
+ struct kvm_vcpu *vcpu, *vnext;
int i;
int srcu_idx;
@@ -1982,7 +1982,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
*/
if ((threads_per_core > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
vcpu->arch.ret = -EBUSY;
kvmppc_remove_runnable(vc, vcpu);
wake_up(&vcpu->arch.cpu_run);
@@ -2320,6 +2321,7 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
struct kvm_dirty_log *log)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int r;
unsigned long n;
@@ -2330,7 +2332,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
if (log->slot >= KVM_USER_MEM_SLOTS)
goto out;
- memslot = id_to_memslot(kvm->memslots, log->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
r = -ENOENT;
if (!memslot->dirty_bitmap)
goto out;
@@ -2373,16 +2376,18 @@ static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
return 0;
}
static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old)
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new)
{
unsigned long npages = mem->memory_size >> PAGE_SHIFT;
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
if (npages && old->npages) {
@@ -2392,7 +2397,8 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
* since the rmap array starts out as all zeroes,
* i.e. no pages are dirty.
*/
- memslot = id_to_memslot(kvm->memslots, mem->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, mem->slot);
kvmppc_hv_get_dirty_log(kvm, memslot, NULL);
}
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 4d70df26c402..faa86e9c0551 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -324,7 +324,7 @@ kvm_start_guest:
kvm_secondary_got_guest:
/* Set HSTATE_DSCR(r13) to something sensible */
- ld r6, PACA_DSCR(r13)
+ ld r6, PACA_DSCR_DEFAULT(r13)
std r6, HSTATE_DSCR(r13)
/* Order load of vcore, ptid etc. after load of vcpu */
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index f57383941d03..64891b081ad5 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1530,6 +1530,7 @@ out:
static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm,
struct kvm_dirty_log *log)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
struct kvm_vcpu *vcpu;
ulong ga, ga_end;
@@ -1545,7 +1546,8 @@ static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm,
/* If nothing is dirty, don't bother messing with page tables. */
if (is_dirty) {
- memslot = id_to_memslot(kvm->memslots, log->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
ga = memslot->base_gfn << PAGE_SHIFT;
ga_end = ga + (memslot->npages << PAGE_SHIFT);
@@ -1571,14 +1573,15 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm,
static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
return 0;
}
static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old)
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new)
{
return;
}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6c1316a15a27..cc5842657161 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1004,10 +1004,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
break;
}
- local_irq_enable();
-
trace_kvm_exit(exit_nr, vcpu);
- kvm_guest_exit();
+ __kvm_guest_exit();
+
+ local_irq_enable();
run->exit_reason = KVM_EXIT_UNKNOWN;
run->ready_for_interrupt_injection = 1;
@@ -1784,14 +1784,15 @@ int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
int kvmppc_core_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem)
+ const struct kvm_userspace_memory_region *mem)
{
return 0;
}
void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old)
+ const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new)
{
}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index ac3ddf115f3d..e5dde32fe71f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -115,7 +115,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
continue;
}
- kvm_guest_enter();
+ __kvm_guest_enter();
return 1;
}
@@ -595,18 +595,19 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
- kvmppc_core_commit_memory_region(kvm, mem, old);
+ kvmppc_core_commit_memory_region(kvm, mem, old, new);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 7902802a19a5..a47e14277fd8 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -33,6 +33,6 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o
obj-$(CONFIG_ALTIVEC) += xor_vmx.o
-CFLAGS_xor_vmx.o += -maltivec -mabi=altivec
+CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec)
obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 3cf529ceec5b..ac93a3bd2730 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -27,11 +27,11 @@ int enter_vmx_usercopy(void)
if (in_interrupt())
return 0;
- /* This acts as preempt_disable() as well and will make
- * enable_kernel_altivec(). We need to disable page faults
- * as they can call schedule and thus make us lose the VMX
- * context. So on page faults, we just fail which will cause
- * a fallback to the normal non-vmx copy.
+ preempt_disable();
+ /*
+ * We need to disable page faults as they can call schedule and
+ * thus make us lose the VMX context. So on page faults, we just
+ * fail which will cause a fallback to the normal non-vmx copy.
*/
pagefault_disable();
@@ -47,6 +47,7 @@ int enter_vmx_usercopy(void)
int exit_vmx_usercopy(void)
{
pagefault_enable();
+ preempt_enable();
return 0;
}
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 9c8770b5f96f..3eb73a38220d 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -36,3 +36,4 @@ obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage-prot.o
obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
obj-$(CONFIG_HIGHMEM) += highmem.o
obj-$(CONFIG_PPC_COPRO_BASE) += copro_fault.o
+obj-$(CONFIG_SPAPR_TCE_IOMMU) += mmu_context_iommu.o
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index f031a47d7701..6527882ce05e 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -26,7 +26,7 @@
#include <asm/reg.h>
#include <asm/copro.h>
#include <asm/spu.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
/*
* This ought to be kept in sync with the powerpc specific do_page_fault
@@ -100,7 +100,7 @@ EXPORT_SYMBOL_GPL(copro_handle_mm_fault);
int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
{
- u64 vsid;
+ u64 vsid, vsidkey;
int psize, ssize;
switch (REGION_ID(ea)) {
@@ -109,6 +109,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
psize = get_slice_psize(mm, ea);
ssize = user_segment_size(ea);
vsid = get_vsid(mm->context.id, ea, ssize);
+ vsidkey = SLB_VSID_USER;
break;
case VMALLOC_REGION_ID:
pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
@@ -118,19 +119,21 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
psize = mmu_io_psize;
ssize = mmu_kernel_ssize;
vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+ vsidkey = SLB_VSID_KERNEL;
break;
case KERNEL_REGION_ID:
pr_devel("%s: 0x%llx -- KERNEL_REGION_ID\n", __func__, ea);
psize = mmu_linear_psize;
ssize = mmu_kernel_ssize;
vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+ vsidkey = SLB_VSID_KERNEL;
break;
default:
pr_debug("%s: invalid region access at %016llx\n", __func__, ea);
return 1;
}
- vsid = (vsid << slb_vsid_shift(ssize)) | SLB_VSID_USER;
+ vsid = (vsid << slb_vsid_shift(ssize)) | vsidkey;
vsid |= mmu_psize_defs[psize].sllp |
((ssize == MMU_SEGSIZE_1T) ? SLB_VSID_B_1T : 0);
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index b396868d2aa7..6d535973b200 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -33,13 +33,13 @@
#include <linux/ratelimit.h>
#include <linux/context_tracking.h>
#include <linux/hugetlb.h>
+#include <linux/uaccess.h>
#include <asm/firmware.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
-#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/siginfo.h>
#include <asm/debug.h>
@@ -272,15 +272,16 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
if (!arch_irq_disabled_regs(regs))
local_irq_enable();
- if (in_atomic() || mm == NULL) {
+ if (faulthandler_disabled() || mm == NULL) {
if (!user_mode(regs)) {
rc = SIGSEGV;
goto bail;
}
- /* in_atomic() in user mode is really bad,
+ /* faulthandler_disabled() in user mode is really bad,
as is current->mm == NULL. */
printk(KERN_EMERG "Page fault in user mode with "
- "in_atomic() = %d mm = %p\n", in_atomic(), mm);
+ "faulthandler_disabled() = %d mm = %p\n",
+ faulthandler_disabled(), mm);
printk(KERN_EMERG "NIP = %lx MSR = %lx\n",
regs->nip, regs->msr);
die("Weird page fault", regs, SIGSEGV);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 9c4880ddecd6..13befa35d8a8 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -29,7 +29,7 @@
#include <asm/kexec.h>
#include <asm/ppc-opcode.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
#ifdef DEBUG_LOW
#define DBG_LOW(fmt...) udbg_printf(fmt)
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index fda236f908eb..5ec987f65b2c 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -57,6 +57,7 @@
#include <asm/fadump.h>
#include <asm/firmware.h>
#include <asm/tm.h>
+#include <asm/trace.h>
#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
@@ -1004,6 +1005,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
ea, access, trap);
+ trace_hash_fault(ea, access, trap);
/* Get region & vsid */
switch (REGION_ID(ea)) {
@@ -1475,7 +1477,7 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
unsigned long hash;
unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
- unsigned long mode = htab_convert_pte_flags(PAGE_KERNEL);
+ unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL));
long ret;
hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c
index e7450bdbe83a..e292c8a60952 100644
--- a/arch/powerpc/mm/highmem.c
+++ b/arch/powerpc/mm/highmem.c
@@ -34,7 +34,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
unsigned long vaddr;
int idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
@@ -59,6 +59,7 @@ void __kunmap_atomic(void *kvaddr)
if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
pagefault_enable();
+ preempt_enable();
return;
}
@@ -82,5 +83,6 @@ void __kunmap_atomic(void *kvaddr)
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0ce968b00b7c..3385e3d0506e 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -689,27 +689,34 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
- pte_t *ptep;
- struct page *page;
+ pte_t *ptep, pte;
unsigned shift;
unsigned long mask, flags;
+ struct page *page = ERR_PTR(-EINVAL);
+
+ local_irq_save(flags);
+ ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+ if (!ptep)
+ goto no_page;
+ pte = READ_ONCE(*ptep);
/*
+ * Verify it is a huge page else bail.
* Transparent hugepages are handled by generic code. We can skip them
* here.
*/
- local_irq_save(flags);
- ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+ if (!shift || pmd_trans_huge(__pmd(pte_val(pte))))
+ goto no_page;
- /* Verify it is a huge page else bail. */
- if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep)) {
- local_irq_restore(flags);
- return ERR_PTR(-EINVAL);
+ if (!pte_present(pte)) {
+ page = NULL;
+ goto no_page;
}
mask = (1UL << shift) - 1;
- page = pte_page(*ptep);
+ page = pte_page(pte);
if (page)
page += (address & mask) / PAGE_SIZE;
+no_page:
local_irq_restore(flags);
return page;
}
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 45fda71feb27..0f11819d8f1d 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -560,7 +560,7 @@ subsys_initcall(add_system_ram_resources);
*/
int devmem_is_allowed(unsigned long pfn)
{
- if (iomem_is_exclusive(pfn << PAGE_SHIFT))
+ if (iomem_is_exclusive(PFN_PHYS(pfn)))
return 0;
if (!page_is_ram(pfn))
return 1;
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 178876aef40f..4e4efbc2658e 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -89,6 +89,9 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
#ifdef CONFIG_PPC_64K_PAGES
mm->context.pte_frag = NULL;
#endif
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ mm_iommu_init(&mm->context);
+#endif
return 0;
}
@@ -132,6 +135,9 @@ static inline void destroy_pagetable_page(struct mm_struct *mm)
void destroy_context(struct mm_struct *mm)
{
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ mm_iommu_cleanup(&mm->context);
+#endif
#ifdef CONFIG_PPC_ICSWX
drop_cop(mm->context.acop, mm);
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
new file mode 100644
index 000000000000..da6a2168ae9e
--- /dev/null
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -0,0 +1,316 @@
+/*
+ * IOMMU helpers in MMU context.
+ *
+ * Copyright (C) 2015 IBM Corp. <aik@ozlabs.ru>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/rculist.h>
+#include <linux/vmalloc.h>
+#include <linux/mutex.h>
+#include <asm/mmu_context.h>
+
+static DEFINE_MUTEX(mem_list_mutex);
+
+struct mm_iommu_table_group_mem_t {
+ struct list_head next;
+ struct rcu_head rcu;
+ unsigned long used;
+ atomic64_t mapped;
+ u64 ua; /* userspace address */
+ u64 entries; /* number of entries in hpas[] */
+ u64 *hpas; /* vmalloc'ed */
+};
+
+static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
+ unsigned long npages, bool incr)
+{
+ long ret = 0, locked, lock_limit;
+
+ if (!npages)
+ return 0;
+
+ down_write(&mm->mmap_sem);
+
+ if (incr) {
+ locked = mm->locked_vm + npages;
+ lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+ ret = -ENOMEM;
+ else
+ mm->locked_vm += npages;
+ } else {
+ if (WARN_ON_ONCE(npages > mm->locked_vm))
+ npages = mm->locked_vm;
+ mm->locked_vm -= npages;
+ }
+
+ pr_debug("[%d] RLIMIT_MEMLOCK HASH64 %c%ld %ld/%ld\n",
+ current->pid,
+ incr ? '+' : '-',
+ npages << PAGE_SHIFT,
+ mm->locked_vm << PAGE_SHIFT,
+ rlimit(RLIMIT_MEMLOCK));
+ up_write(&mm->mmap_sem);
+
+ return ret;
+}
+
+bool mm_iommu_preregistered(void)
+{
+ if (!current || !current->mm)
+ return false;
+
+ return !list_empty(&current->mm->context.iommu_group_mem_list);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
+
+long mm_iommu_get(unsigned long ua, unsigned long entries,
+ struct mm_iommu_table_group_mem_t **pmem)
+{
+ struct mm_iommu_table_group_mem_t *mem;
+ long i, j, ret = 0, locked_entries = 0;
+ struct page *page = NULL;
+
+ if (!current || !current->mm)
+ return -ESRCH; /* process exited */
+
+ mutex_lock(&mem_list_mutex);
+
+ list_for_each_entry_rcu(mem, &current->mm->context.iommu_group_mem_list,
+ next) {
+ if ((mem->ua == ua) && (mem->entries == entries)) {
+ ++mem->used;
+ *pmem = mem;
+ goto unlock_exit;
+ }
+
+ /* Overlap? */
+ if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
+ (ua < (mem->ua +
+ (mem->entries << PAGE_SHIFT)))) {
+ ret = -EINVAL;
+ goto unlock_exit;
+ }
+
+ }
+
+ ret = mm_iommu_adjust_locked_vm(current->mm, entries, true);
+ if (ret)
+ goto unlock_exit;
+
+ locked_entries = entries;
+
+ mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+ if (!mem) {
+ ret = -ENOMEM;
+ goto unlock_exit;
+ }
+
+ mem->hpas = vzalloc(entries * sizeof(mem->hpas[0]));
+ if (!mem->hpas) {
+ kfree(mem);
+ ret = -ENOMEM;
+ goto unlock_exit;
+ }
+
+ for (i = 0; i < entries; ++i) {
+ if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
+ 1/* pages */, 1/* iswrite */, &page)) {
+ for (j = 0; j < i; ++j)
+ put_page(pfn_to_page(
+ mem->hpas[j] >> PAGE_SHIFT));
+ vfree(mem->hpas);
+ kfree(mem);
+ ret = -EFAULT;
+ goto unlock_exit;
+ }
+
+ mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
+ }
+
+ atomic64_set(&mem->mapped, 1);
+ mem->used = 1;
+ mem->ua = ua;
+ mem->entries = entries;
+ *pmem = mem;
+
+ list_add_rcu(&mem->next, &current->mm->context.iommu_group_mem_list);
+
+unlock_exit:
+ if (locked_entries && ret)
+ mm_iommu_adjust_locked_vm(current->mm, locked_entries, false);
+
+ mutex_unlock(&mem_list_mutex);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_get);
+
+static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
+{
+ long i;
+ struct page *page = NULL;
+
+ for (i = 0; i < mem->entries; ++i) {
+ if (!mem->hpas[i])
+ continue;
+
+ page = pfn_to_page(mem->hpas[i] >> PAGE_SHIFT);
+ if (!page)
+ continue;
+
+ put_page(page);
+ mem->hpas[i] = 0;
+ }
+}
+
+static void mm_iommu_do_free(struct mm_iommu_table_group_mem_t *mem)
+{
+
+ mm_iommu_unpin(mem);
+ vfree(mem->hpas);
+ kfree(mem);
+}
+
+static void mm_iommu_free(struct rcu_head *head)
+{
+ struct mm_iommu_table_group_mem_t *mem = container_of(head,
+ struct mm_iommu_table_group_mem_t, rcu);
+
+ mm_iommu_do_free(mem);
+}
+
+static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
+{
+ list_del_rcu(&mem->next);
+ mm_iommu_adjust_locked_vm(current->mm, mem->entries, false);
+ call_rcu(&mem->rcu, mm_iommu_free);
+}
+
+long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
+{
+ long ret = 0;
+
+ if (!current || !current->mm)
+ return -ESRCH; /* process exited */
+
+ mutex_lock(&mem_list_mutex);
+
+ if (mem->used == 0) {
+ ret = -ENOENT;
+ goto unlock_exit;
+ }
+
+ --mem->used;
+ /* There are still users, exit */
+ if (mem->used)
+ goto unlock_exit;
+
+ /* Are there still mappings? */
+ if (atomic_cmpxchg(&mem->mapped, 1, 0) != 1) {
+ ++mem->used;
+ ret = -EBUSY;
+ goto unlock_exit;
+ }
+
+ /* @mapped became 0 so now mappings are disabled, release the region */
+ mm_iommu_release(mem);
+
+unlock_exit:
+ mutex_unlock(&mem_list_mutex);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_put);
+
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
+ unsigned long size)
+{
+ struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+ list_for_each_entry_rcu(mem,
+ &current->mm->context.iommu_group_mem_list,
+ next) {
+ if ((mem->ua <= ua) &&
+ (ua + size <= mem->ua +
+ (mem->entries << PAGE_SHIFT))) {
+ ret = mem;
+ break;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_lookup);
+
+struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
+ unsigned long entries)
+{
+ struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+ list_for_each_entry_rcu(mem,
+ &current->mm->context.iommu_group_mem_list,
+ next) {
+ if ((mem->ua == ua) && (mem->entries == entries)) {
+ ret = mem;
+ break;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_find);
+
+long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
+ unsigned long ua, unsigned long *hpa)
+{
+ const long entry = (ua - mem->ua) >> PAGE_SHIFT;
+ u64 *va = &mem->hpas[entry];
+
+ if (entry >= mem->entries)
+ return -EFAULT;
+
+ *hpa = *va | (ua & ~PAGE_MASK);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
+
+long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
+{
+ if (atomic64_inc_not_zero(&mem->mapped))
+ return 0;
+
+ /* Last mm_iommu_put() has been called, no more mappings allowed() */
+ return -ENXIO;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_mapped_inc);
+
+void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem)
+{
+ atomic64_add_unless(&mem->mapped, -1, 1);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_mapped_dec);
+
+void mm_iommu_init(mm_context_t *ctx)
+{
+ INIT_LIST_HEAD_RCU(&ctx->iommu_group_mem_list);
+}
+
+void mm_iommu_cleanup(mm_context_t *ctx)
+{
+ struct mm_iommu_table_group_mem_t *mem, *tmp;
+
+ list_for_each_entry_safe(mem, tmp, &ctx->iommu_group_mem_list, next) {
+ list_del_rcu(&mem->next);
+ mm_iommu_do_free(mem);
+ }
+}
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 59daa5eeec25..6bfadf1aa5cb 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -839,6 +839,17 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm,
* hash fault look at them.
*/
memset(pgtable, 0, PTE_FRAG_SIZE);
+ /*
+ * Serialize against find_linux_pte_or_hugepte which does lock-less
+ * lookup in page tables with local interrupts disabled. For huge pages
+ * it casts pmd_t to pte_t. Since format of pte_t is different from
+ * pmd_t we want to prevent transit from pmd pointing to page table
+ * to pmd pointing to huge page (and back) while interrupts are disabled.
+ * We clear pmd to possibly replace it with page table pointer in
+ * different code paths. So make sure we wait for the parallel
+ * find_linux_pte_or_hugepage to finish.
+ */
+ kick_all_cpus_sync();
return old_pmd;
}
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 89bf95bd63b1..765b419883f2 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -398,18 +398,18 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_SMT)
rldicl r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3
clrrdi r15,r15,3
cmpdi cr0,r14,0
- bge tlb_miss_fault_e6500 /* Bad pgd entry or hugepage; bail */
+ bge tlb_miss_huge_e6500 /* Bad pgd entry or hugepage; bail */
ldx r14,r14,r15 /* grab pud entry */
rldicl r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3
clrrdi r15,r15,3
cmpdi cr0,r14,0
- bge tlb_miss_fault_e6500
+ bge tlb_miss_huge_e6500
ldx r14,r14,r15 /* Grab pmd entry */
mfspr r10,SPRN_MAS0
cmpdi cr0,r14,0
- bge tlb_miss_fault_e6500
+ bge tlb_miss_huge_e6500
/* Now we build the MAS for a 2M indirect page:
*
@@ -428,6 +428,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_SMT)
clrrdi r15,r16,21 /* make EA 2M-aligned */
mtspr SPRN_MAS2,r15
+tlb_miss_huge_done_e6500:
lbz r15,TCD_ESEL_NEXT(r11)
lbz r16,TCD_ESEL_MAX(r11)
lbz r14,TCD_ESEL_FIRST(r11)
@@ -456,6 +457,50 @@ END_FTR_SECTION_IFSET(CPU_FTR_SMT)
tlb_epilog_bolted
rfi
+tlb_miss_huge_e6500:
+ beq tlb_miss_fault_e6500
+ li r10,1
+ andi. r15,r14,HUGEPD_SHIFT_MASK@l /* r15 = psize */
+ rldimi r14,r10,63,0 /* Set PD_HUGE */
+ xor r14,r14,r15 /* Clear size bits */
+ ldx r14,0,r14
+
+ /*
+ * Now we build the MAS for a huge page.
+ *
+ * MAS 0 : ESEL needs to be filled by software round-robin
+ * - can be handled by indirect code
+ * MAS 1 : Need to clear IND and set TSIZE
+ * MAS 2,3+7: Needs to be redone similar to non-tablewalk handler
+ */
+
+ subi r15,r15,10 /* Convert psize to tsize */
+ mfspr r10,SPRN_MAS1
+ rlwinm r10,r10,0,~MAS1_IND
+ rlwimi r10,r15,MAS1_TSIZE_SHIFT,MAS1_TSIZE_MASK
+ mtspr SPRN_MAS1,r10
+
+ li r10,-0x400
+ sld r15,r10,r15 /* Generate mask based on size */
+ and r10,r16,r15
+ rldicr r15,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
+ rlwimi r10,r14,32-19,27,31 /* Insert WIMGE */
+ clrldi r15,r15,PAGE_SHIFT /* Clear crap at the top */
+ rlwimi r15,r14,32-8,22,25 /* Move in U bits */
+ mtspr SPRN_MAS2,r10
+ andi. r10,r14,_PAGE_DIRTY
+ rlwimi r15,r14,32-2,26,31 /* Move in BAP bits */
+
+ /* Mask out SW and UW if !DIRTY (XXX optimize this !) */
+ bne 1f
+ li r10,MAS3_SW|MAS3_UW
+ andc r15,r15,r10
+1:
+ mtspr SPRN_MAS7_MAS3,r15
+
+ mfspr r10,SPRN_MAS0
+ b tlb_miss_huge_done_e6500
+
tlb_miss_kernel_e6500:
ld r14,PACA_KERNELPGD(r13)
cmpldi cr1,r15,8 /* Check for vmalloc region */
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index cbd3d069897f..723a099f6be3 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -217,7 +217,7 @@ static DEFINE_RAW_SPINLOCK(tlbivax_lock);
static int mm_is_core_local(struct mm_struct *mm)
{
return cpumask_subset(mm_cpumask(mm),
- topology_thread_cpumask(smp_processor_id()));
+ topology_sibling_cpumask(smp_processor_id()));
}
struct tlb_flush_param {
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 12b638425bb9..d90893b76e7c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -131,7 +131,16 @@ static void pmao_restore_workaround(bool ebb) { }
static bool regs_use_siar(struct pt_regs *regs)
{
- return !!regs->result;
+ /*
+ * When we take a performance monitor exception the regs are setup
+ * using perf_read_regs() which overloads some fields, in particular
+ * regs->result to tell us whether to use SIAR.
+ *
+ * However if the regs are from another exception, eg. a syscall, then
+ * they have not been setup using perf_read_regs() and so regs->result
+ * is something random.
+ */
+ return ((TRAP(regs) == 0xf00) && regs->result);
}
/*
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index c949ca055712..63016621aff8 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -193,7 +193,7 @@ static struct irq_chip mpc52xx_gpt_irq_chip = {
void mpc52xx_gpt_irq_cascade(unsigned int virq, struct irq_desc *desc)
{
- struct mpc52xx_gpt_priv *gpt = irq_get_handler_data(virq);
+ struct mpc52xx_gpt_priv *gpt = irq_desc_get_handler_data(desc);
int sub_virq;
u32 status;
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pci.c b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
index e2d401ad8fbb..6eb3b2abae90 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pci.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
@@ -12,7 +12,7 @@
#undef DEBUG
-#include <asm/pci.h>
+#include <linux/pci.h>
#include <asm/mpc52xx.h>
#include <asm/delay.h>
#include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 2fb4b24368a6..97915feffd42 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -282,7 +282,7 @@ config CORENET_GENERIC
For 64bit kernel, the following boards are supported:
T208x QDS/RDB, T4240 QDS/RDB and B4 QDS
The following boards are supported for both 32bit and 64bit kernel:
- P5020 DS, P5040 DS and T104xQDS/RDB
+ P5020 DS, P5040 DS, T102x QDS/RDB, T104x QDS/RDB
endif # FSL_SOC_BOOKE
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index 9824d2cf79bd..bd839dc287fe 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -150,6 +150,9 @@ static const char * const boards[] __initconst = {
"fsl,B4860QDS",
"fsl,B4420QDS",
"fsl,B4220QDS",
+ "fsl,T1023RDB",
+ "fsl,T1024QDS",
+ "fsl,T1024RDB",
"fsl,T1040QDS",
"fsl,T1042QDS",
"fsl,T1040RDB",
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 8631ac5f0e57..b8b821697910 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -345,6 +345,7 @@ void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
local_irq_disable();
if (secondary) {
+ __flush_disable_L1();
atomic_inc(&kexec_down_cpus);
/* loop forever */
while (1);
@@ -357,61 +358,11 @@ static void mpc85xx_smp_kexec_down(void *arg)
ppc_md.kexec_cpu_down(0,1);
}
-static void map_and_flush(unsigned long paddr)
-{
- struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
- unsigned long kaddr = (unsigned long)kmap_atomic(page);
-
- flush_dcache_range(kaddr, kaddr + PAGE_SIZE);
- kunmap_atomic((void *)kaddr);
-}
-
-/**
- * Before we reset the other cores, we need to flush relevant cache
- * out to memory so we don't get anything corrupted, some of these flushes
- * are performed out of an overabundance of caution as interrupts are not
- * disabled yet and we can switch cores
- */
-static void mpc85xx_smp_flush_dcache_kexec(struct kimage *image)
-{
- kimage_entry_t *ptr, entry;
- unsigned long paddr;
- int i;
-
- if (image->type == KEXEC_TYPE_DEFAULT) {
- /* normal kexec images are stored in temporary pages */
- for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE);
- ptr = (entry & IND_INDIRECTION) ?
- phys_to_virt(entry & PAGE_MASK) : ptr + 1) {
- if (!(entry & IND_DESTINATION)) {
- map_and_flush(entry);
- }
- }
- /* flush out last IND_DONE page */
- map_and_flush(entry);
- } else {
- /* crash type kexec images are copied to the crash region */
- for (i = 0; i < image->nr_segments; i++) {
- struct kexec_segment *seg = &image->segment[i];
- for (paddr = seg->mem; paddr < seg->mem + seg->memsz;
- paddr += PAGE_SIZE) {
- map_and_flush(paddr);
- }
- }
- }
-
- /* also flush the kimage struct to be passed in as well */
- flush_dcache_range((unsigned long)image,
- (unsigned long)image + sizeof(*image));
-}
-
static void mpc85xx_smp_machine_kexec(struct kimage *image)
{
int timeout = INT_MAX;
int i, num_cpus = num_present_cpus();
- mpc85xx_smp_flush_dcache_kexec(image);
-
if (image->type == KEXEC_TYPE_DEFAULT)
smp_call_function(mpc85xx_smp_kexec_down, NULL, 0);
diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c
index 1eadb6d0dc64..30e002f4648c 100644
--- a/arch/powerpc/platforms/85xx/twr_p102x.c
+++ b/arch/powerpc/platforms/85xx/twr_p102x.c
@@ -79,7 +79,7 @@ static void __init twr_p1025_setup_arch(void)
mpc85xx_qe_init();
mpc85xx_qe_par_io_init();
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE)
+#if IS_ENABLED(CONFIG_UCC_GETH) || IS_ENABLED(CONFIG_SERIAL_QE)
if (machine_is(twr_p1025)) {
struct ccsr_guts __iomem *guts;
@@ -101,7 +101,7 @@ static void __init twr_p1025_setup_arch(void)
MPC85xx_PMUXCR_QE(12));
iounmap(guts);
-#if defined(CONFIG_SERIAL_QE)
+#if IS_ENABLED(CONFIG_SERIAL_QE)
/* On P1025TWR board, the UCC7 acted as UART port.
* However, The UCC7's CTS pin is low level in default,
* it will impact the transmission in full duplex
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 7264e91190be..c140e94c7c72 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -405,6 +405,16 @@ config PPC_DOORBELL
endmenu
+config VDSO32
+ def_bool y
+ depends on PPC32 || CPU_BIG_ENDIAN
+ help
+ This symbol controls whether we build the 32-bit VDSO. We obviously
+ want to do that if we're building a 32-bit kernel. If we're building
+ a 64-bit kernel then we only want a 32-bit VDSO if we're building for
+ big endian. That is because the only little endian configuration we
+ support is ppc64le which is 64-bit only.
+
choice
prompt "Endianness selection"
default CPU_BIG_ENDIAN
@@ -421,6 +431,7 @@ config CPU_BIG_ENDIAN
config CPU_LITTLE_ENDIAN
bool "Build little endian kernel"
+ depends on PPC_BOOK3S_64
select PPC64_BOOT_WRAPPER
help
Build a little endian kernel.
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 623bd961465a..fe51de4fcf13 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -22,6 +22,7 @@
#include <asm/machdep.h>
#include <asm/prom.h>
+#include "cell.h"
/*
* MSIC registers, specified as offsets from dcr_base
@@ -95,7 +96,7 @@ static void msic_dcr_write(struct axon_msic *msic, unsigned int dcr_n, u32 val)
static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
- struct axon_msic *msic = irq_get_handler_data(irq);
+ struct axon_msic *msic = irq_desc_get_handler_data(desc);
u32 write_offset, msi;
int idx;
int retry = 0;
@@ -406,8 +407,8 @@ static int axon_msi_probe(struct platform_device *device)
dev_set_drvdata(&device->dev, msic);
- ppc_md.setup_msi_irqs = axon_msi_setup_msi_irqs;
- ppc_md.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
+ cell_pci_controller_ops.setup_msi_irqs = axon_msi_setup_msi_irqs;
+ cell_pci_controller_ops.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
axon_msi_debug_setup(dn, msic);
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 21b502398bf3..14a582b21274 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -466,6 +466,11 @@ static inline u32 cell_iommu_get_ioid(struct device_node *np)
return *ioid;
}
+static struct iommu_table_ops cell_iommu_ops = {
+ .set = tce_build_cell,
+ .clear = tce_free_cell
+};
+
static struct iommu_window * __init
cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
unsigned long offset, unsigned long size,
@@ -492,6 +497,7 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
window->table.it_offset =
(offset >> window->table.it_page_shift) + pte_offset;
window->table.it_size = size >> window->table.it_page_shift;
+ window->table.it_ops = &cell_iommu_ops;
iommu_init_table(&window->table, iommu->nid);
@@ -1201,8 +1207,6 @@ static int __init cell_iommu_init(void)
/* Setup various callbacks */
cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
ppc_md.dma_get_required_mask = cell_dma_get_required_mask;
- ppc_md.tce_build = tce_build_cell;
- ppc_md.tce_free = tce_free_cell;
if (!iommu_fixed_disabled && cell_iommu_fixed_mapping_init() == 0)
goto bail;
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index c269caee58f9..9dd154d6f89a 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -124,7 +124,7 @@ static void hlwd_pic_irq_cascade(unsigned int cascade_virq,
struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
- struct irq_domain *irq_domain = irq_get_handler_data(cascade_virq);
+ struct irq_domain *irq_domain = irq_desc_get_handler_data(desc);
unsigned int virq;
raw_spin_lock(&desc->lock);
diff --git a/arch/powerpc/platforms/pasemi/Makefile b/arch/powerpc/platforms/pasemi/Makefile
index 8e8d4cae5ebe..60b4e0fd9808 100644
--- a/arch/powerpc/platforms/pasemi/Makefile
+++ b/arch/powerpc/platforms/pasemi/Makefile
@@ -1,2 +1,3 @@
obj-y += setup.o pci.o time.o idle.o powersave.o iommu.o dma_lib.o misc.o
obj-$(CONFIG_PPC_PASEMI_MDIO) += gpio_mdio.o
+obj-$(CONFIG_PCI_MSI) += msi.o
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index b8f567b2ea19..c929644e74a6 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -134,6 +134,10 @@ static void iobmap_free(struct iommu_table *tbl, long index,
}
}
+static struct iommu_table_ops iommu_table_iobmap_ops = {
+ .set = iobmap_build,
+ .clear = iobmap_free
+};
static void iommu_table_iobmap_setup(void)
{
@@ -153,6 +157,7 @@ static void iommu_table_iobmap_setup(void)
* Should probably be 8 (64 bytes)
*/
iommu_table_iobmap.it_blocksize = 4;
+ iommu_table_iobmap.it_ops = &iommu_table_iobmap_ops;
iommu_init_table(&iommu_table_iobmap, 0);
pr_debug(" <- %s\n", __func__);
}
@@ -252,8 +257,6 @@ void __init iommu_init_early_pasemi(void)
pasemi_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pasemi;
pasemi_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pasemi;
- ppc_md.tce_build = iobmap_build;
- ppc_md.tce_free = iobmap_free;
set_pci_dma_ops(&dma_iommu_ops);
}
diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/platforms/pasemi/msi.c
index a3f660eed6de..27f2b187a91b 100644
--- a/arch/powerpc/sysdev/mpic_pasemi_msi.c
+++ b/arch/powerpc/platforms/pasemi/msi.c
@@ -13,8 +13,6 @@
*
*/
-#undef DEBUG
-
#include <linux/irq.h>
#include <linux/msi.h>
#include <asm/mpic.h>
@@ -23,7 +21,7 @@
#include <asm/ppc-pci.h>
#include <asm/msi_bitmap.h>
-#include "mpic.h"
+#include <sysdev/mpic.h>
/* Allocate 16 interrupts per device, to give an alignment of 16,
* since that's the size of the grouping w.r.t. affinity. If someone
@@ -144,6 +142,7 @@ static int pasemi_msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
int mpic_pasemi_msi_init(struct mpic *mpic)
{
int rc;
+ struct pci_controller *phb;
if (!mpic->irqhost->of_node ||
!of_device_is_compatible(mpic->irqhost->of_node,
@@ -159,9 +158,11 @@ int mpic_pasemi_msi_init(struct mpic *mpic)
pr_debug("pasemi_msi: Registering PA Semi MPIC MSI callbacks\n");
msi_mpic = mpic;
- WARN_ON(ppc_md.setup_msi_irqs);
- ppc_md.setup_msi_irqs = pasemi_msi_setup_msi_irqs;
- ppc_md.teardown_msi_irqs = pasemi_msi_teardown_msi_irqs;
+ list_for_each_entry(phb, &hose_list, list_node) {
+ WARN_ON(phb->controller_ops.setup_msi_irqs);
+ phb->controller_ops.setup_msi_irqs = pasemi_msi_setup_msi_irqs;
+ phb->controller_ops.teardown_msi_irqs = pasemi_msi_teardown_msi_irqs;
+ }
return 0;
}
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 4b044d8cb49a..604190cab522 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -19,3 +19,10 @@ config PPC_POWERNV
select CPU_FREQ_GOV_CONSERVATIVE
select PPC_DOORBELL
default y
+
+config OPAL_PRD
+ tristate 'OPAL PRD driver'
+ depends on PPC_POWERNV
+ help
+ This enables the opal-prd driver, a facility to run processor
+ recovery diagnostics on OpenPower machines
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 33e44f37212f..1c8cdb6250e7 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,7 +1,7 @@
-obj-y += setup.o opal-wrappers.o opal.o opal-async.o
+obj-y += setup.o opal-wrappers.o opal.o opal-async.o idle.o
obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
-obj-y += opal-msglog.o opal-hmi.o opal-power.o
+obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o
obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o
@@ -9,3 +9,4 @@ obj-$(CONFIG_EEH) += eeh-powernv.o
obj-$(CONFIG_PPC_SCOM) += opal-xscom.o
obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o
obj-$(CONFIG_TRACEPOINTS) += opal-tracepoints.o
+obj-$(CONFIG_OPAL_PRD) += opal-prd.o
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index ce738ab3d5a9..5cf5e6ea213b 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -16,6 +16,7 @@
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/init.h>
+#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/msi.h>
#include <linux/of.h>
@@ -40,6 +41,7 @@
#include "pci.h"
static bool pnv_eeh_nb_init = false;
+static int eeh_event_irq = -EINVAL;
/**
* pnv_eeh_init - EEH platform dependent initialization
@@ -88,34 +90,22 @@ static int pnv_eeh_init(void)
return 0;
}
-static int pnv_eeh_event(struct notifier_block *nb,
- unsigned long events, void *change)
+static irqreturn_t pnv_eeh_event(int irq, void *data)
{
- uint64_t changed_evts = (uint64_t)change;
-
/*
- * We simply send special EEH event if EEH has
- * been enabled, or clear pending events in
- * case that we enable EEH soon
+ * We simply send a special EEH event if EEH has been
+ * enabled. We don't care about EEH events until we've
+ * finished processing the outstanding ones. Event processing
+ * gets unmasked in next_error() if EEH is enabled.
*/
- if (!(changed_evts & OPAL_EVENT_PCI_ERROR) ||
- !(events & OPAL_EVENT_PCI_ERROR))
- return 0;
+ disable_irq_nosync(irq);
if (eeh_enabled())
eeh_send_failure_event(NULL);
- else
- opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
- return 0;
+ return IRQ_HANDLED;
}
-static struct notifier_block pnv_eeh_nb = {
- .notifier_call = pnv_eeh_event,
- .next = NULL,
- .priority = 0
-};
-
#ifdef CONFIG_DEBUG_FS
static ssize_t pnv_eeh_ei_write(struct file *filp,
const char __user *user_buf,
@@ -237,16 +227,28 @@ static int pnv_eeh_post_init(void)
/* Register OPAL event notifier */
if (!pnv_eeh_nb_init) {
- ret = opal_notifier_register(&pnv_eeh_nb);
- if (ret) {
- pr_warn("%s: Can't register OPAL event notifier (%d)\n",
- __func__, ret);
+ eeh_event_irq = opal_event_request(ilog2(OPAL_EVENT_PCI_ERROR));
+ if (eeh_event_irq < 0) {
+ pr_err("%s: Can't register OPAL event interrupt (%d)\n",
+ __func__, eeh_event_irq);
+ return eeh_event_irq;
+ }
+
+ ret = request_irq(eeh_event_irq, pnv_eeh_event,
+ IRQ_TYPE_LEVEL_HIGH, "opal-eeh", NULL);
+ if (ret < 0) {
+ irq_dispose_mapping(eeh_event_irq);
+ pr_err("%s: Can't request OPAL event interrupt (%d)\n",
+ __func__, eeh_event_irq);
return ret;
}
pnv_eeh_nb_init = true;
}
+ if (!eeh_enabled())
+ disable_irq(eeh_event_irq);
+
list_for_each_entry(hose, &hose_list, list_node) {
phb = hose->private_data;
@@ -979,7 +981,7 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
/**
* pnv_eeh_wait_state - Wait for PE state
* @pe: EEH PE
- * @max_wait: maximal period in microsecond
+ * @max_wait: maximal period in millisecond
*
* Wait for the state of associated PE. It might take some time
* to retrieve the PE's state.
@@ -1000,13 +1002,13 @@ static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
if (ret != EEH_STATE_UNAVAILABLE)
return ret;
- max_wait -= mwait;
if (max_wait <= 0) {
pr_warn("%s: Timeout getting PE#%x's state (%d)\n",
__func__, pe->addr, max_wait);
return EEH_STATE_NOT_SUPPORT;
}
+ max_wait -= mwait;
msleep(mwait);
}
@@ -1303,12 +1305,10 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
int state, ret = EEH_NEXT_ERR_NONE;
/*
- * While running here, it's safe to purge the event queue.
- * And we should keep the cached OPAL notifier event sychronized
- * between the kernel and firmware.
+ * While running here, it's safe to purge the event queue. The
+ * event should still be masked.
*/
eeh_remove_event(NULL, false);
- opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
list_for_each_entry(hose, &hose_list, list_node) {
/*
@@ -1477,6 +1477,10 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
break;
}
+ /* Unmask the event */
+ if (eeh_enabled())
+ enable_irq(eeh_event_irq);
+
return ret;
}
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
new file mode 100644
index 000000000000..59d735d2e5c0
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -0,0 +1,293 @@
+/*
+ * PowerNV cpuidle code
+ *
+ * Copyright 2015 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/device.h>
+#include <linux/cpu.h>
+
+#include <asm/firmware.h>
+#include <asm/machdep.h>
+#include <asm/opal.h>
+#include <asm/cputhreads.h>
+#include <asm/cpuidle.h>
+#include <asm/code-patching.h>
+#include <asm/smp.h>
+
+#include "powernv.h"
+#include "subcore.h"
+
+static u32 supported_cpuidle_states;
+
+int pnv_save_sprs_for_winkle(void)
+{
+ int cpu;
+ int rc;
+
+ /*
+ * hid0, hid1, hid4, hid5, hmeer and lpcr values are symmetric accross
+ * all cpus at boot. Get these reg values of current cpu and use the
+ * same accross all cpus.
+ */
+ uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
+ uint64_t hid0_val = mfspr(SPRN_HID0);
+ uint64_t hid1_val = mfspr(SPRN_HID1);
+ uint64_t hid4_val = mfspr(SPRN_HID4);
+ uint64_t hid5_val = mfspr(SPRN_HID5);
+ uint64_t hmeer_val = mfspr(SPRN_HMEER);
+
+ for_each_possible_cpu(cpu) {
+ uint64_t pir = get_hard_smp_processor_id(cpu);
+ uint64_t hsprg0_val = (uint64_t)&paca[cpu];
+
+ /*
+ * HSPRG0 is used to store the cpu's pointer to paca. Hence last
+ * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0
+ * with 63rd bit set, so that when a thread wakes up at 0x100 we
+ * can use this bit to distinguish between fastsleep and
+ * deep winkle.
+ */
+ hsprg0_val |= 1;
+
+ rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
+ if (rc != 0)
+ return rc;
+
+ rc = opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
+ if (rc != 0)
+ return rc;
+
+ /* HIDs are per core registers */
+ if (cpu_thread_in_core(cpu) == 0) {
+
+ rc = opal_slw_set_reg(pir, SPRN_HMEER, hmeer_val);
+ if (rc != 0)
+ return rc;
+
+ rc = opal_slw_set_reg(pir, SPRN_HID0, hid0_val);
+ if (rc != 0)
+ return rc;
+
+ rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val);
+ if (rc != 0)
+ return rc;
+
+ rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val);
+ if (rc != 0)
+ return rc;
+
+ rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val);
+ if (rc != 0)
+ return rc;
+ }
+ }
+
+ return 0;
+}
+
+static void pnv_alloc_idle_core_states(void)
+{
+ int i, j;
+ int nr_cores = cpu_nr_cores();
+ u32 *core_idle_state;
+
+ /*
+ * core_idle_state - First 8 bits track the idle state of each thread
+ * of the core. The 8th bit is the lock bit. Initially all thread bits
+ * are set. They are cleared when the thread enters deep idle state
+ * like sleep and winkle. Initially the lock bit is cleared.
+ * The lock bit has 2 purposes
+ * a. While the first thread is restoring core state, it prevents
+ * other threads in the core from switching to process context.
+ * b. While the last thread in the core is saving the core state, it
+ * prevents a different thread from waking up.
+ */
+ for (i = 0; i < nr_cores; i++) {
+ int first_cpu = i * threads_per_core;
+ int node = cpu_to_node(first_cpu);
+
+ core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
+ *core_idle_state = PNV_CORE_IDLE_THREAD_BITS;
+
+ for (j = 0; j < threads_per_core; j++) {
+ int cpu = first_cpu + j;
+
+ paca[cpu].core_idle_state_ptr = core_idle_state;
+ paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
+ paca[cpu].thread_mask = 1 << j;
+ }
+ }
+
+ update_subcore_sibling_mask();
+
+ if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED)
+ pnv_save_sprs_for_winkle();
+}
+
+u32 pnv_get_supported_cpuidle_states(void)
+{
+ return supported_cpuidle_states;
+}
+EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
+
+
+static void pnv_fastsleep_workaround_apply(void *info)
+
+{
+ int rc;
+ int *err = info;
+
+ rc = opal_config_cpu_idle_state(OPAL_CONFIG_IDLE_FASTSLEEP,
+ OPAL_CONFIG_IDLE_APPLY);
+ if (rc)
+ *err = 1;
+}
+
+/*
+ * Used to store fastsleep workaround state
+ * 0 - Workaround applied/undone at fastsleep entry/exit path (Default)
+ * 1 - Workaround applied once, never undone.
+ */
+static u8 fastsleep_workaround_applyonce;
+
+static ssize_t show_fastsleep_workaround_applyonce(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%u\n", fastsleep_workaround_applyonce);
+}
+
+static ssize_t store_fastsleep_workaround_applyonce(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
+{
+ cpumask_t primary_thread_mask;
+ int err;
+ u8 val;
+
+ if (kstrtou8(buf, 0, &val) || val != 1)
+ return -EINVAL;
+
+ if (fastsleep_workaround_applyonce == 1)
+ return count;
+
+ /*
+ * fastsleep_workaround_applyonce = 1 implies
+ * fastsleep workaround needs to be left in 'applied' state on all
+ * the cores. Do this by-
+ * 1. Patching out the call to 'undo' workaround in fastsleep exit path
+ * 2. Sending ipi to all the cores which have atleast one online thread
+ * 3. Patching out the call to 'apply' workaround in fastsleep entry
+ * path
+ * There is no need to send ipi to cores which have all threads
+ * offlined, as last thread of the core entering fastsleep or deeper
+ * state would have applied workaround.
+ */
+ err = patch_instruction(
+ (unsigned int *)pnv_fastsleep_workaround_at_exit,
+ PPC_INST_NOP);
+ if (err) {
+ pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_exit");
+ goto fail;
+ }
+
+ get_online_cpus();
+ primary_thread_mask = cpu_online_cores_map();
+ on_each_cpu_mask(&primary_thread_mask,
+ pnv_fastsleep_workaround_apply,
+ &err, 1);
+ put_online_cpus();
+ if (err) {
+ pr_err("fastsleep_workaround_applyonce change failed while running pnv_fastsleep_workaround_apply");
+ goto fail;
+ }
+
+ err = patch_instruction(
+ (unsigned int *)pnv_fastsleep_workaround_at_entry,
+ PPC_INST_NOP);
+ if (err) {
+ pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_entry");
+ goto fail;
+ }
+
+ fastsleep_workaround_applyonce = 1;
+
+ return count;
+fail:
+ return -EIO;
+}
+
+static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600,
+ show_fastsleep_workaround_applyonce,
+ store_fastsleep_workaround_applyonce);
+
+static int __init pnv_init_idle_states(void)
+{
+ struct device_node *power_mgt;
+ int dt_idle_states;
+ u32 *flags;
+ int i;
+
+ supported_cpuidle_states = 0;
+
+ if (cpuidle_disable != IDLE_NO_OVERRIDE)
+ goto out;
+
+ if (!firmware_has_feature(FW_FEATURE_OPALv3))
+ goto out;
+
+ power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+ if (!power_mgt) {
+ pr_warn("opal: PowerMgmt Node not found\n");
+ goto out;
+ }
+ dt_idle_states = of_property_count_u32_elems(power_mgt,
+ "ibm,cpu-idle-state-flags");
+ if (dt_idle_states < 0) {
+ pr_warn("cpuidle-powernv: no idle states found in the DT\n");
+ goto out;
+ }
+
+ flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
+ if (of_property_read_u32_array(power_mgt,
+ "ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
+ pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
+ goto out_free;
+ }
+
+ for (i = 0; i < dt_idle_states; i++)
+ supported_cpuidle_states |= flags[i];
+
+ if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
+ patch_instruction(
+ (unsigned int *)pnv_fastsleep_workaround_at_entry,
+ PPC_INST_NOP);
+ patch_instruction(
+ (unsigned int *)pnv_fastsleep_workaround_at_exit,
+ PPC_INST_NOP);
+ } else {
+ /*
+ * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that
+ * workaround is needed to use fastsleep. Provide sysfs
+ * control to choose how this workaround has to be applied.
+ */
+ device_create_file(cpu_subsys.dev_root,
+ &dev_attr_fastsleep_workaround_applyonce);
+ }
+
+ pnv_alloc_idle_core_states();
+out_free:
+ kfree(flags);
+out:
+ return 0;
+}
+machine_subsys_initcall(powernv, pnv_init_idle_states);
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
index 693b6cdac691..bdc8c0c71d15 100644
--- a/arch/powerpc/platforms/powernv/opal-async.c
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -151,7 +151,7 @@ static struct notifier_block opal_async_comp_nb = {
.priority = 0,
};
-static int __init opal_async_comp_init(void)
+int __init opal_async_comp_init(void)
{
struct device_node *opal_node;
const __be32 *async;
@@ -205,4 +205,3 @@ out_opal_node:
out:
return err;
}
-machine_subsys_initcall(powernv, opal_async_comp_init);
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 5aa9c1ce4de3..2ee96431f736 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -15,6 +15,7 @@
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/delay.h>
+#include <linux/interrupt.h>
#include <asm/opal.h>
@@ -60,7 +61,7 @@ static ssize_t dump_type_show(struct dump_obj *dump_obj,
struct dump_attribute *attr,
char *buf)
{
-
+
return sprintf(buf, "0x%x %s\n", dump_obj->type,
dump_type_to_string(dump_obj->type));
}
@@ -363,7 +364,7 @@ static struct dump_obj *create_dump_obj(uint32_t id, size_t size,
return dump;
}
-static int process_dump(void)
+static irqreturn_t process_dump(int irq, void *data)
{
int rc;
uint32_t dump_id, dump_size, dump_type;
@@ -387,45 +388,13 @@ static int process_dump(void)
if (!dump)
return -1;
- return 0;
-}
-
-static void dump_work_fn(struct work_struct *work)
-{
- process_dump();
+ return IRQ_HANDLED;
}
-static DECLARE_WORK(dump_work, dump_work_fn);
-
-static void schedule_process_dump(void)
-{
- schedule_work(&dump_work);
-}
-
-/*
- * New dump available notification
- *
- * Once we get notification, we add sysfs entries for it.
- * We only fetch the dump on demand, and create sysfs asynchronously.
- */
-static int dump_event(struct notifier_block *nb,
- unsigned long events, void *change)
-{
- if (events & OPAL_EVENT_DUMP_AVAIL)
- schedule_process_dump();
-
- return 0;
-}
-
-static struct notifier_block dump_nb = {
- .notifier_call = dump_event,
- .next = NULL,
- .priority = 0
-};
-
void __init opal_platform_dump_init(void)
{
int rc;
+ int dump_irq;
/* ELOG not supported by firmware */
if (!opal_check_token(OPAL_DUMP_READ))
@@ -445,10 +414,19 @@ void __init opal_platform_dump_init(void)
return;
}
- rc = opal_notifier_register(&dump_nb);
+ dump_irq = opal_event_request(ilog2(OPAL_EVENT_DUMP_AVAIL));
+ if (!dump_irq) {
+ pr_err("%s: Can't register OPAL event irq (%d)\n",
+ __func__, dump_irq);
+ return;
+ }
+
+ rc = request_threaded_irq(dump_irq, NULL, process_dump,
+ IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+ "opal-dump", NULL);
if (rc) {
- pr_warn("%s: Can't register OPAL event notifier (%d)\n",
- __func__, rc);
+ pr_err("%s: Can't request OPAL event irq (%d)\n",
+ __func__, rc);
return;
}
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 38ce757e5e2a..4949ef0d9400 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -10,6 +10,7 @@
*/
#include <linux/kernel.h>
#include <linux/init.h>
+#include <linux/interrupt.h>
#include <linux/of.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
@@ -276,24 +277,15 @@ static void elog_work_fn(struct work_struct *work)
static DECLARE_WORK(elog_work, elog_work_fn);
-static int elog_event(struct notifier_block *nb,
- unsigned long events, void *change)
+static irqreturn_t elog_event(int irq, void *data)
{
- /* check for error log event */
- if (events & OPAL_EVENT_ERROR_LOG_AVAIL)
- schedule_work(&elog_work);
- return 0;
+ schedule_work(&elog_work);
+ return IRQ_HANDLED;
}
-static struct notifier_block elog_nb = {
- .notifier_call = elog_event,
- .next = NULL,
- .priority = 0
-};
-
int __init opal_elog_init(void)
{
- int rc = 0;
+ int rc = 0, irq;
/* ELOG not supported by firmware */
if (!opal_check_token(OPAL_ELOG_READ))
@@ -305,10 +297,18 @@ int __init opal_elog_init(void)
return -1;
}
- rc = opal_notifier_register(&elog_nb);
+ irq = opal_event_request(ilog2(OPAL_EVENT_ERROR_LOG_AVAIL));
+ if (!irq) {
+ pr_err("%s: Can't register OPAL event irq (%d)\n",
+ __func__, irq);
+ return irq;
+ }
+
+ rc = request_irq(irq, elog_event,
+ IRQ_TYPE_LEVEL_HIGH, "opal-elog", NULL);
if (rc) {
- pr_err("%s: Can't register OPAL event notifier (%d)\n",
- __func__, rc);
+ pr_err("%s: Can't request OPAL event irq (%d)\n",
+ __func__, rc);
return rc;
}
diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c
index b322bfb51343..a8f49d380449 100644
--- a/arch/powerpc/platforms/powernv/opal-hmi.c
+++ b/arch/powerpc/platforms/powernv/opal-hmi.c
@@ -170,7 +170,7 @@ static struct notifier_block opal_hmi_handler_nb = {
.priority = 0,
};
-static int __init opal_hmi_handler_init(void)
+int __init opal_hmi_handler_init(void)
{
int ret;
@@ -186,4 +186,3 @@ static int __init opal_hmi_handler_init(void)
}
return 0;
}
-machine_subsys_initcall(powernv, opal_hmi_handler_init);
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
new file mode 100644
index 000000000000..e2e7d75f52f3
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -0,0 +1,253 @@
+/*
+ * This file implements an irqchip for OPAL events. Whenever there is
+ * an interrupt that is handled by OPAL we get passed a list of events
+ * that Linux needs to do something about. These basically look like
+ * interrupts to Linux so we implement an irqchip to handle them.
+ *
+ * Copyright Alistair Popple, IBM Corporation 2014.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/irq_work.h>
+
+#include <asm/machdep.h>
+#include <asm/opal.h>
+
+#include "powernv.h"
+
+/* Maximum number of events supported by OPAL firmware */
+#define MAX_NUM_EVENTS 64
+
+struct opal_event_irqchip {
+ struct irq_chip irqchip;
+ struct irq_domain *domain;
+ unsigned long mask;
+};
+static struct opal_event_irqchip opal_event_irqchip;
+
+static unsigned int opal_irq_count;
+static unsigned int *opal_irqs;
+
+static void opal_handle_irq_work(struct irq_work *work);
+static __be64 last_outstanding_events;
+static struct irq_work opal_event_irq_work = {
+ .func = opal_handle_irq_work,
+};
+
+static void opal_event_mask(struct irq_data *d)
+{
+ clear_bit(d->hwirq, &opal_event_irqchip.mask);
+}
+
+static void opal_event_unmask(struct irq_data *d)
+{
+ set_bit(d->hwirq, &opal_event_irqchip.mask);
+
+ opal_poll_events(&last_outstanding_events);
+ if (last_outstanding_events & opal_event_irqchip.mask)
+ /* Need to retrigger the interrupt */
+ irq_work_queue(&opal_event_irq_work);
+}
+
+static int opal_event_set_type(struct irq_data *d, unsigned int flow_type)
+{
+ /*
+ * For now we only support level triggered events. The irq
+ * handler will be called continuously until the event has
+ * been cleared in OPAL.
+ */
+ if (flow_type != IRQ_TYPE_LEVEL_HIGH)
+ return -EINVAL;
+
+ return 0;
+}
+
+static struct opal_event_irqchip opal_event_irqchip = {
+ .irqchip = {
+ .name = "OPAL EVT",
+ .irq_mask = opal_event_mask,
+ .irq_unmask = opal_event_unmask,
+ .irq_set_type = opal_event_set_type,
+ },
+ .mask = 0,
+};
+
+static int opal_event_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hwirq)
+{
+ irq_set_chip_data(irq, &opal_event_irqchip);
+ irq_set_chip_and_handler(irq, &opal_event_irqchip.irqchip,
+ handle_level_irq);
+
+ return 0;
+}
+
+void opal_handle_events(uint64_t events)
+{
+ int virq, hwirq = 0;
+ u64 mask = opal_event_irqchip.mask;
+
+ if (!in_irq() && (events & mask)) {
+ last_outstanding_events = events;
+ irq_work_queue(&opal_event_irq_work);
+ return;
+ }
+
+ while (events & mask) {
+ hwirq = fls64(events) - 1;
+ if (BIT_ULL(hwirq) & mask) {
+ virq = irq_find_mapping(opal_event_irqchip.domain,
+ hwirq);
+ if (virq)
+ generic_handle_irq(virq);
+ }
+ events &= ~BIT_ULL(hwirq);
+ }
+}
+
+static irqreturn_t opal_interrupt(int irq, void *data)
+{
+ __be64 events;
+
+ opal_handle_interrupt(virq_to_hw(irq), &events);
+ opal_handle_events(be64_to_cpu(events));
+
+ return IRQ_HANDLED;
+}
+
+static void opal_handle_irq_work(struct irq_work *work)
+{
+ opal_handle_events(be64_to_cpu(last_outstanding_events));
+}
+
+static int opal_event_match(struct irq_domain *h, struct device_node *node)
+{
+ return h->of_node == node;
+}
+
+static int opal_event_xlate(struct irq_domain *h, struct device_node *np,
+ const u32 *intspec, unsigned int intsize,
+ irq_hw_number_t *out_hwirq, unsigned int *out_flags)
+{
+ *out_hwirq = intspec[0];
+ *out_flags = IRQ_TYPE_LEVEL_HIGH;
+
+ return 0;
+}
+
+static const struct irq_domain_ops opal_event_domain_ops = {
+ .match = opal_event_match,
+ .map = opal_event_map,
+ .xlate = opal_event_xlate,
+};
+
+void opal_event_shutdown(void)
+{
+ unsigned int i;
+
+ /* First free interrupts, which will also mask them */
+ for (i = 0; i < opal_irq_count; i++) {
+ if (opal_irqs[i])
+ free_irq(opal_irqs[i], NULL);
+ opal_irqs[i] = 0;
+ }
+}
+
+int __init opal_event_init(void)
+{
+ struct device_node *dn, *opal_node;
+ const __be32 *irqs;
+ int i, irqlen, rc = 0;
+
+ opal_node = of_find_node_by_path("/ibm,opal");
+ if (!opal_node) {
+ pr_warn("opal: Node not found\n");
+ return -ENODEV;
+ }
+
+ /* If dn is NULL it means the domain won't be linked to a DT
+ * node so therefore irq_of_parse_and_map(...) wont work. But
+ * that shouldn't be problem because if we're running a
+ * version of skiboot that doesn't have the dn then the
+ * devices won't have the correct properties and will have to
+ * fall back to the legacy method (opal_event_request(...))
+ * anyway. */
+ dn = of_find_compatible_node(NULL, NULL, "ibm,opal-event");
+ opal_event_irqchip.domain = irq_domain_add_linear(dn, MAX_NUM_EVENTS,
+ &opal_event_domain_ops, &opal_event_irqchip);
+ of_node_put(dn);
+ if (!opal_event_irqchip.domain) {
+ pr_warn("opal: Unable to create irq domain\n");
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ /* Get interrupt property */
+ irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
+ opal_irq_count = irqs ? (irqlen / 4) : 0;
+ pr_debug("Found %d interrupts reserved for OPAL\n", opal_irq_count);
+
+ /* Install interrupt handlers */
+ opal_irqs = kcalloc(opal_irq_count, sizeof(*opal_irqs), GFP_KERNEL);
+ for (i = 0; irqs && i < opal_irq_count; i++, irqs++) {
+ unsigned int irq, virq;
+
+ /* Get hardware and virtual IRQ */
+ irq = be32_to_cpup(irqs);
+ virq = irq_create_mapping(NULL, irq);
+ if (virq == NO_IRQ) {
+ pr_warn("Failed to map irq 0x%x\n", irq);
+ continue;
+ }
+
+ /* Install interrupt handler */
+ rc = request_irq(virq, opal_interrupt, 0, "opal", NULL);
+ if (rc) {
+ irq_dispose_mapping(virq);
+ pr_warn("Error %d requesting irq %d (0x%x)\n",
+ rc, virq, irq);
+ continue;
+ }
+
+ /* Cache IRQ */
+ opal_irqs[i] = virq;
+ }
+
+out:
+ of_node_put(opal_node);
+ return rc;
+}
+machine_arch_initcall(powernv, opal_event_init);
+
+/**
+ * opal_event_request(unsigned int opal_event_nr) - Request an event
+ * @opal_event_nr: the opal event number to request
+ *
+ * This routine can be used to find the linux virq number which can
+ * then be passed to request_irq to assign a handler for a particular
+ * opal event. This should only be used by legacy devices which don't
+ * have proper device tree bindings. Most devices should use
+ * irq_of_parse_and_map() instead.
+ */
+int opal_event_request(unsigned int opal_event_nr)
+{
+ if (WARN_ON_ONCE(!opal_event_irqchip.domain))
+ return NO_IRQ;
+
+ return irq_create_mapping(opal_event_irqchip.domain, opal_event_nr);
+}
+EXPORT_SYMBOL(opal_event_request);
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
index 43db2136dbff..00a29432be39 100644
--- a/arch/powerpc/platforms/powernv/opal-memory-errors.c
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -144,4 +144,4 @@ static int __init opal_mem_err_init(void)
}
return 0;
}
-machine_subsys_initcall(powernv, opal_mem_err_init);
+machine_device_initcall(powernv, opal_mem_err_init);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
new file mode 100644
index 000000000000..46cb3feb0a13
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -0,0 +1,449 @@
+/*
+ * OPAL Runtime Diagnostics interface driver
+ * Supported on POWERNV platform
+ *
+ * Copyright IBM Corporation 2015
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) "opal-prd: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/miscdevice.h>
+#include <linux/fs.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/poll.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/opal-prd.h>
+#include <asm/opal.h>
+#include <asm/io.h>
+#include <asm/uaccess.h>
+
+
+/**
+ * The msg member must be at the end of the struct, as it's followed by the
+ * message data.
+ */
+struct opal_prd_msg_queue_item {
+ struct list_head list;
+ struct opal_prd_msg_header msg;
+};
+
+static struct device_node *prd_node;
+static LIST_HEAD(opal_prd_msg_queue);
+static DEFINE_SPINLOCK(opal_prd_msg_queue_lock);
+static DECLARE_WAIT_QUEUE_HEAD(opal_prd_msg_wait);
+static atomic_t prd_usage;
+
+static bool opal_prd_range_is_valid(uint64_t addr, uint64_t size)
+{
+ struct device_node *parent, *node;
+ bool found;
+
+ if (addr + size < addr)
+ return false;
+
+ parent = of_find_node_by_path("/reserved-memory");
+ if (!parent)
+ return false;
+
+ found = false;
+
+ for_each_child_of_node(parent, node) {
+ uint64_t range_addr, range_size, range_end;
+ const __be32 *addrp;
+ const char *label;
+
+ addrp = of_get_address(node, 0, &range_size, NULL);
+
+ range_addr = of_read_number(addrp, 2);
+ range_end = range_addr + range_size;
+
+ label = of_get_property(node, "ibm,prd-label", NULL);
+
+ /* PRD ranges need a label */
+ if (!label)
+ continue;
+
+ if (range_end <= range_addr)
+ continue;
+
+ if (addr >= range_addr && addr + size <= range_end) {
+ found = true;
+ of_node_put(node);
+ break;
+ }
+ }
+
+ of_node_put(parent);
+ return found;
+}
+
+static int opal_prd_open(struct inode *inode, struct file *file)
+{
+ /*
+ * Prevent multiple (separate) processes from concurrent interactions
+ * with the FW PRD channel
+ */
+ if (atomic_xchg(&prd_usage, 1) == 1)
+ return -EBUSY;
+
+ return 0;
+}
+
+/*
+ * opal_prd_mmap - maps firmware-provided ranges into userspace
+ * @file: file structure for the device
+ * @vma: VMA to map the registers into
+ */
+
+static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ size_t addr, size;
+ int rc;
+
+ pr_devel("opal_prd_mmap(0x%016lx, 0x%016lx, 0x%lx, 0x%lx)\n",
+ vma->vm_start, vma->vm_end, vma->vm_pgoff,
+ vma->vm_flags);
+
+ addr = vma->vm_pgoff << PAGE_SHIFT;
+ size = vma->vm_end - vma->vm_start;
+
+ /* ensure we're mapping within one of the allowable ranges */
+ if (!opal_prd_range_is_valid(addr, size))
+ return -EINVAL;
+
+ vma->vm_page_prot = __pgprot(pgprot_val(phys_mem_access_prot(file,
+ vma->vm_pgoff,
+ size, vma->vm_page_prot))
+ | _PAGE_SPECIAL);
+
+ rc = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, size,
+ vma->vm_page_prot);
+
+ return rc;
+}
+
+static bool opal_msg_queue_empty(void)
+{
+ unsigned long flags;
+ bool ret;
+
+ spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
+ ret = list_empty(&opal_prd_msg_queue);
+ spin_unlock_irqrestore(&opal_prd_msg_queue_lock, flags);
+
+ return ret;
+}
+
+static unsigned int opal_prd_poll(struct file *file,
+ struct poll_table_struct *wait)
+{
+ poll_wait(file, &opal_prd_msg_wait, wait);
+
+ if (!opal_msg_queue_empty())
+ return POLLIN | POLLRDNORM;
+
+ return 0;
+}
+
+static ssize_t opal_prd_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct opal_prd_msg_queue_item *item;
+ unsigned long flags;
+ ssize_t size, err;
+ int rc;
+
+ /* we need at least a header's worth of data */
+ if (count < sizeof(item->msg))
+ return -EINVAL;
+
+ if (*ppos)
+ return -ESPIPE;
+
+ item = NULL;
+
+ for (;;) {
+
+ spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
+ if (!list_empty(&opal_prd_msg_queue)) {
+ item = list_first_entry(&opal_prd_msg_queue,
+ struct opal_prd_msg_queue_item, list);
+ list_del(&item->list);
+ }
+ spin_unlock_irqrestore(&opal_prd_msg_queue_lock, flags);
+
+ if (item)
+ break;
+
+ if (file->f_flags & O_NONBLOCK)
+ return -EAGAIN;
+
+ rc = wait_event_interruptible(opal_prd_msg_wait,
+ !opal_msg_queue_empty());
+ if (rc)
+ return -EINTR;
+ }
+
+ size = be16_to_cpu(item->msg.size);
+ if (size > count) {
+ err = -EINVAL;
+ goto err_requeue;
+ }
+
+ rc = copy_to_user(buf, &item->msg, size);
+ if (rc) {
+ err = -EFAULT;
+ goto err_requeue;
+ }
+
+ kfree(item);
+
+ return size;
+
+err_requeue:
+ /* eep! re-queue at the head of the list */
+ spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
+ list_add(&item->list, &opal_prd_msg_queue);
+ spin_unlock_irqrestore(&opal_prd_msg_queue_lock, flags);
+ return err;
+}
+
+static ssize_t opal_prd_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct opal_prd_msg_header hdr;
+ ssize_t size;
+ void *msg;
+ int rc;
+
+ size = sizeof(hdr);
+
+ if (count < size)
+ return -EINVAL;
+
+ /* grab the header */
+ rc = copy_from_user(&hdr, buf, sizeof(hdr));
+ if (rc)
+ return -EFAULT;
+
+ size = be16_to_cpu(hdr.size);
+
+ msg = kmalloc(size, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ rc = copy_from_user(msg, buf, size);
+ if (rc) {
+ size = -EFAULT;
+ goto out_free;
+ }
+
+ rc = opal_prd_msg(msg);
+ if (rc) {
+ pr_warn("write: opal_prd_msg returned %d\n", rc);
+ size = -EIO;
+ }
+
+out_free:
+ kfree(msg);
+
+ return size;
+}
+
+static int opal_prd_release(struct inode *inode, struct file *file)
+{
+ struct opal_prd_msg_header msg;
+
+ msg.size = cpu_to_be16(sizeof(msg));
+ msg.type = OPAL_PRD_MSG_TYPE_FINI;
+
+ opal_prd_msg((struct opal_prd_msg *)&msg);
+
+ atomic_xchg(&prd_usage, 0);
+
+ return 0;
+}
+
+static long opal_prd_ioctl(struct file *file, unsigned int cmd,
+ unsigned long param)
+{
+ struct opal_prd_info info;
+ struct opal_prd_scom scom;
+ int rc = 0;
+
+ switch (cmd) {
+ case OPAL_PRD_GET_INFO:
+ memset(&info, 0, sizeof(info));
+ info.version = OPAL_PRD_KERNEL_VERSION;
+ rc = copy_to_user((void __user *)param, &info, sizeof(info));
+ if (rc)
+ return -EFAULT;
+ break;
+
+ case OPAL_PRD_SCOM_READ:
+ rc = copy_from_user(&scom, (void __user *)param, sizeof(scom));
+ if (rc)
+ return -EFAULT;
+
+ scom.rc = opal_xscom_read(scom.chip, scom.addr,
+ (__be64 *)&scom.data);
+ scom.data = be64_to_cpu(scom.data);
+ pr_devel("ioctl SCOM_READ: chip %llx addr %016llx data %016llx rc %lld\n",
+ scom.chip, scom.addr, scom.data, scom.rc);
+
+ rc = copy_to_user((void __user *)param, &scom, sizeof(scom));
+ if (rc)
+ return -EFAULT;
+ break;
+
+ case OPAL_PRD_SCOM_WRITE:
+ rc = copy_from_user(&scom, (void __user *)param, sizeof(scom));
+ if (rc)
+ return -EFAULT;
+
+ scom.rc = opal_xscom_write(scom.chip, scom.addr, scom.data);
+ pr_devel("ioctl SCOM_WRITE: chip %llx addr %016llx data %016llx rc %lld\n",
+ scom.chip, scom.addr, scom.data, scom.rc);
+
+ rc = copy_to_user((void __user *)param, &scom, sizeof(scom));
+ if (rc)
+ return -EFAULT;
+ break;
+
+ default:
+ rc = -EINVAL;
+ }
+
+ return rc;
+}
+
+static const struct file_operations opal_prd_fops = {
+ .open = opal_prd_open,
+ .mmap = opal_prd_mmap,
+ .poll = opal_prd_poll,
+ .read = opal_prd_read,
+ .write = opal_prd_write,
+ .unlocked_ioctl = opal_prd_ioctl,
+ .release = opal_prd_release,
+ .owner = THIS_MODULE,
+};
+
+static struct miscdevice opal_prd_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "opal-prd",
+ .fops = &opal_prd_fops,
+};
+
+/* opal interface */
+static int opal_prd_msg_notifier(struct notifier_block *nb,
+ unsigned long msg_type, void *_msg)
+{
+ struct opal_prd_msg_queue_item *item;
+ struct opal_prd_msg_header *hdr;
+ struct opal_msg *msg = _msg;
+ int msg_size, item_size;
+ unsigned long flags;
+
+ if (msg_type != OPAL_MSG_PRD)
+ return 0;
+
+ /* Calculate total size of the message and item we need to store. The
+ * 'size' field in the header includes the header itself. */
+ hdr = (void *)msg->params;
+ msg_size = be16_to_cpu(hdr->size);
+ item_size = msg_size + sizeof(*item) - sizeof(item->msg);
+
+ item = kzalloc(item_size, GFP_ATOMIC);
+ if (!item)
+ return -ENOMEM;
+
+ memcpy(&item->msg, msg->params, msg_size);
+
+ spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
+ list_add_tail(&item->list, &opal_prd_msg_queue);
+ spin_unlock_irqrestore(&opal_prd_msg_queue_lock, flags);
+
+ wake_up_interruptible(&opal_prd_msg_wait);
+
+ return 0;
+}
+
+static struct notifier_block opal_prd_event_nb = {
+ .notifier_call = opal_prd_msg_notifier,
+ .next = NULL,
+ .priority = 0,
+};
+
+static int opal_prd_probe(struct platform_device *pdev)
+{
+ int rc;
+
+ if (!pdev || !pdev->dev.of_node)
+ return -ENODEV;
+
+ /* We should only have one prd driver instance per machine; ensure
+ * that we only get a valid probe on a single OF node.
+ */
+ if (prd_node)
+ return -EBUSY;
+
+ prd_node = pdev->dev.of_node;
+
+ rc = opal_message_notifier_register(OPAL_MSG_PRD, &opal_prd_event_nb);
+ if (rc) {
+ pr_err("Couldn't register event notifier\n");
+ return rc;
+ }
+
+ rc = misc_register(&opal_prd_dev);
+ if (rc) {
+ pr_err("failed to register miscdev\n");
+ opal_message_notifier_unregister(OPAL_MSG_PRD,
+ &opal_prd_event_nb);
+ return rc;
+ }
+
+ return 0;
+}
+
+static int opal_prd_remove(struct platform_device *pdev)
+{
+ misc_deregister(&opal_prd_dev);
+ opal_message_notifier_unregister(OPAL_MSG_PRD, &opal_prd_event_nb);
+ return 0;
+}
+
+static const struct of_device_id opal_prd_match[] = {
+ { .compatible = "ibm,opal-prd" },
+ { },
+};
+
+static struct platform_driver opal_prd_driver = {
+ .driver = {
+ .name = "opal-prd",
+ .owner = THIS_MODULE,
+ .of_match_table = opal_prd_match,
+ },
+ .probe = opal_prd_probe,
+ .remove = opal_prd_remove,
+};
+
+module_platform_driver(opal_prd_driver);
+
+MODULE_DEVICE_TABLE(of, opal_prd_match);
+MODULE_DESCRIPTION("PowerNV OPAL runtime diagnostic driver");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
index 655250499d18..a06059df9239 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -77,7 +77,7 @@ out:
}
EXPORT_SYMBOL_GPL(opal_get_sensor_data);
-static __init int opal_sensor_init(void)
+int __init opal_sensor_init(void)
{
struct platform_device *pdev;
struct device_node *sensor;
@@ -93,4 +93,3 @@ static __init int opal_sensor_init(void)
return PTR_ERR_OR_ZERO(pdev);
}
-machine_subsys_initcall(powernv, opal_sensor_init);
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index 9d1acf22a099..afe66c576a38 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -55,8 +55,10 @@ static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer)
}
ret = opal_get_param(token, param_id, (u64)buffer, length);
- if (ret != OPAL_ASYNC_COMPLETION)
+ if (ret != OPAL_ASYNC_COMPLETION) {
+ ret = opal_error_code(ret);
goto out_token;
+ }
ret = opal_async_wait_response(token, &msg);
if (ret) {
@@ -65,7 +67,7 @@ static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer)
goto out_token;
}
- ret = be64_to_cpu(msg.params[1]);
+ ret = opal_error_code(be64_to_cpu(msg.params[1]));
out_token:
opal_async_release_token(token);
@@ -89,8 +91,10 @@ static int opal_set_sys_param(u32 param_id, u32 length, void *buffer)
ret = opal_set_param(token, param_id, (u64)buffer, length);
- if (ret != OPAL_ASYNC_COMPLETION)
+ if (ret != OPAL_ASYNC_COMPLETION) {
+ ret = opal_error_code(ret);
goto out_token;
+ }
ret = opal_async_wait_response(token, &msg);
if (ret) {
@@ -99,7 +103,7 @@ static int opal_set_sys_param(u32 param_id, u32 length, void *buffer)
goto out_token;
}
- ret = be64_to_cpu(msg.params[1]);
+ ret = opal_error_code(be64_to_cpu(msg.params[1]));
out_token:
opal_async_release_token(token);
@@ -162,10 +166,20 @@ void __init opal_sys_param_init(void)
goto out;
}
+ /* Some systems do not use sysparams; this is not an error */
+ sysparam = of_find_node_by_path("/ibm,opal/sysparams");
+ if (!sysparam)
+ goto out;
+
+ if (!of_device_is_compatible(sysparam, "ibm,opal-sysparams")) {
+ pr_err("SYSPARAM: Opal sysparam node not compatible\n");
+ goto out_node_put;
+ }
+
sysparam_kobj = kobject_create_and_add("sysparams", opal_kobj);
if (!sysparam_kobj) {
pr_err("SYSPARAM: Failed to create sysparam kobject\n");
- goto out;
+ goto out_node_put;
}
/* Allocate big enough buffer for any get/set transactions */
@@ -176,30 +190,19 @@ void __init opal_sys_param_init(void)
goto out_kobj_put;
}
- sysparam = of_find_node_by_path("/ibm,opal/sysparams");
- if (!sysparam) {
- pr_err("SYSPARAM: Opal sysparam node not found\n");
- goto out_param_buf;
- }
-
- if (!of_device_is_compatible(sysparam, "ibm,opal-sysparams")) {
- pr_err("SYSPARAM: Opal sysparam node not compatible\n");
- goto out_node_put;
- }
-
/* Number of parameters exposed through DT */
count = of_property_count_strings(sysparam, "param-name");
if (count < 0) {
pr_err("SYSPARAM: No string found of property param-name in "
"the node %s\n", sysparam->name);
- goto out_node_put;
+ goto out_param_buf;
}
id = kzalloc(sizeof(*id) * count, GFP_KERNEL);
if (!id) {
pr_err("SYSPARAM: Failed to allocate memory to read parameter "
"id\n");
- goto out_node_put;
+ goto out_param_buf;
}
size = kzalloc(sizeof(*size) * count, GFP_KERNEL);
@@ -293,12 +296,12 @@ out_free_size:
kfree(size);
out_free_id:
kfree(id);
-out_node_put:
- of_node_put(sysparam);
out_param_buf:
kfree(param_data_buf);
out_kobj_put:
kobject_put(sysparam_kobj);
+out_node_put:
+ of_node_put(sysparam);
out:
return;
}
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index a7ade94cdf87..d6a7b8252e4d 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -283,6 +283,7 @@ OPAL_CALL(opal_sensor_read, OPAL_SENSOR_READ);
OPAL_CALL(opal_get_param, OPAL_GET_PARAM);
OPAL_CALL(opal_set_param, OPAL_SET_PARAM);
OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI);
+OPAL_CALL(opal_config_cpu_idle_state, OPAL_CONFIG_CPU_IDLE_STATE);
OPAL_CALL(opal_slw_set_reg, OPAL_SLW_SET_REG);
OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION);
OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION);
@@ -295,3 +296,4 @@ OPAL_CALL(opal_i2c_request, OPAL_I2C_REQUEST);
OPAL_CALL(opal_flash_read, OPAL_FLASH_READ);
OPAL_CALL(opal_flash_write, OPAL_FLASH_WRITE);
OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE);
+OPAL_CALL(opal_prd_msg, OPAL_PRD_MSG);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 2241565b0739..f084afa0e3ba 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -53,13 +53,7 @@ static int mc_recoverable_range_len;
struct device_node *opal_node;
static DEFINE_SPINLOCK(opal_write_lock);
-static unsigned int *opal_irqs;
-static unsigned int opal_irq_count;
-static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX];
-static DEFINE_SPINLOCK(opal_notifier_lock);
-static uint64_t last_notified_mask = 0x0ul;
-static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
static uint32_t opal_heartbeat;
static void opal_reinit_cores(void)
@@ -225,82 +219,6 @@ static int __init opal_register_exception_handlers(void)
}
machine_early_initcall(powernv, opal_register_exception_handlers);
-int opal_notifier_register(struct notifier_block *nb)
-{
- if (!nb) {
- pr_warning("%s: Invalid argument (%p)\n",
- __func__, nb);
- return -EINVAL;
- }
-
- atomic_notifier_chain_register(&opal_notifier_head, nb);
- return 0;
-}
-EXPORT_SYMBOL_GPL(opal_notifier_register);
-
-int opal_notifier_unregister(struct notifier_block *nb)
-{
- if (!nb) {
- pr_warning("%s: Invalid argument (%p)\n",
- __func__, nb);
- return -EINVAL;
- }
-
- atomic_notifier_chain_unregister(&opal_notifier_head, nb);
- return 0;
-}
-EXPORT_SYMBOL_GPL(opal_notifier_unregister);
-
-static void opal_do_notifier(uint64_t events)
-{
- unsigned long flags;
- uint64_t changed_mask;
-
- if (atomic_read(&opal_notifier_hold))
- return;
-
- spin_lock_irqsave(&opal_notifier_lock, flags);
- changed_mask = last_notified_mask ^ events;
- last_notified_mask = events;
- spin_unlock_irqrestore(&opal_notifier_lock, flags);
-
- /*
- * We feed with the event bits and changed bits for
- * enough information to the callback.
- */
- atomic_notifier_call_chain(&opal_notifier_head,
- events, (void *)changed_mask);
-}
-
-void opal_notifier_update_evt(uint64_t evt_mask,
- uint64_t evt_val)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&opal_notifier_lock, flags);
- last_notified_mask &= ~evt_mask;
- last_notified_mask |= evt_val;
- spin_unlock_irqrestore(&opal_notifier_lock, flags);
-}
-
-void opal_notifier_enable(void)
-{
- int64_t rc;
- __be64 evt = 0;
-
- atomic_set(&opal_notifier_hold, 0);
-
- /* Process pending events */
- rc = opal_poll_events(&evt);
- if (rc == OPAL_SUCCESS && evt)
- opal_do_notifier(be64_to_cpu(evt));
-}
-
-void opal_notifier_disable(void)
-{
- atomic_set(&opal_notifier_hold, 1);
-}
-
/*
* Opal message notifier based on message type. Allow subscribers to get
* notified for specific messgae type.
@@ -317,6 +235,7 @@ int opal_message_notifier_register(enum opal_msg_type msg_type,
return atomic_notifier_chain_register(
&opal_msg_notifier_head[msg_type], nb);
}
+EXPORT_SYMBOL_GPL(opal_message_notifier_register);
int opal_message_notifier_unregister(enum opal_msg_type msg_type,
struct notifier_block *nb)
@@ -324,6 +243,7 @@ int opal_message_notifier_unregister(enum opal_msg_type msg_type,
return atomic_notifier_chain_unregister(
&opal_msg_notifier_head[msg_type], nb);
}
+EXPORT_SYMBOL_GPL(opal_message_notifier_unregister);
static void opal_message_do_notify(uint32_t msg_type, void *msg)
{
@@ -364,36 +284,36 @@ static void opal_handle_message(void)
opal_message_do_notify(type, (void *)&msg);
}
-static int opal_message_notify(struct notifier_block *nb,
- unsigned long events, void *change)
+static irqreturn_t opal_message_notify(int irq, void *data)
{
- if (events & OPAL_EVENT_MSG_PENDING)
- opal_handle_message();
- return 0;
+ opal_handle_message();
+ return IRQ_HANDLED;
}
-static struct notifier_block opal_message_nb = {
- .notifier_call = opal_message_notify,
- .next = NULL,
- .priority = 0,
-};
-
static int __init opal_message_init(void)
{
- int ret, i;
+ int ret, i, irq;
for (i = 0; i < OPAL_MSG_TYPE_MAX; i++)
ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]);
- ret = opal_notifier_register(&opal_message_nb);
+ irq = opal_event_request(ilog2(OPAL_EVENT_MSG_PENDING));
+ if (!irq) {
+ pr_err("%s: Can't register OPAL event irq (%d)\n",
+ __func__, irq);
+ return irq;
+ }
+
+ ret = request_irq(irq, opal_message_notify,
+ IRQ_TYPE_LEVEL_HIGH, "opal-msg", NULL);
if (ret) {
- pr_err("%s: Can't register OPAL event notifier (%d)\n",
+ pr_err("%s: Can't request OPAL event irq (%d)\n",
__func__, ret);
return ret;
}
+
return 0;
}
-machine_early_initcall(powernv, opal_message_init);
int opal_get_chars(uint32_t vtermno, char *buf, int count)
{
@@ -573,7 +493,7 @@ int opal_handle_hmi_exception(struct pt_regs *regs)
local_paca->hmi_event_available = 0;
rc = opal_poll_events(&evt);
if (rc == OPAL_SUCCESS && evt)
- opal_do_notifier(be64_to_cpu(evt));
+ opal_handle_events(be64_to_cpu(evt));
return 1;
}
@@ -610,17 +530,6 @@ out:
return !!recover_addr;
}
-static irqreturn_t opal_interrupt(int irq, void *data)
-{
- __be64 events;
-
- opal_handle_interrupt(virq_to_hw(irq), &events);
-
- opal_do_notifier(be64_to_cpu(events));
-
- return IRQ_HANDLED;
-}
-
static int opal_sysfs_init(void)
{
opal_kobj = kobject_create_and_add("opal", firmware_kobj);
@@ -693,21 +602,13 @@ static void __init opal_dump_region_init(void)
"rc = %d\n", rc);
}
-static void opal_flash_init(struct device_node *opal_node)
-{
- struct device_node *np;
-
- for_each_child_of_node(opal_node, np)
- if (of_device_is_compatible(np, "ibm,opal-flash"))
- of_platform_device_create(np, NULL, NULL);
-}
-
-static void opal_ipmi_init(struct device_node *opal_node)
+static void opal_pdev_init(struct device_node *opal_node,
+ const char *compatible)
{
struct device_node *np;
for_each_child_of_node(opal_node, np)
- if (of_device_is_compatible(np, "ibm,opal-ipmi"))
+ if (of_device_is_compatible(np, compatible))
of_platform_device_create(np, NULL, NULL);
}
@@ -719,52 +620,15 @@ static void opal_i2c_create_devs(void)
of_platform_device_create(np, NULL, NULL);
}
-static void __init opal_irq_init(struct device_node *dn)
-{
- const __be32 *irqs;
- int i, irqlen;
-
- /* Get interrupt property */
- irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
- opal_irq_count = irqs ? (irqlen / 4) : 0;
- pr_debug("Found %d interrupts reserved for OPAL\n", opal_irq_count);
- if (!opal_irq_count)
- return;
-
- /* Install interrupt handlers */
- opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
- for (i = 0; irqs && i < opal_irq_count; i++, irqs++) {
- unsigned int irq, virq;
- int rc;
-
- /* Get hardware and virtual IRQ */
- irq = be32_to_cpup(irqs);
- virq = irq_create_mapping(NULL, irq);
- if (virq == NO_IRQ) {
- pr_warn("Failed to map irq 0x%x\n", irq);
- continue;
- }
-
- /* Install interrupt handler */
- rc = request_irq(virq, opal_interrupt, 0, "opal", NULL);
- if (rc) {
- irq_dispose_mapping(virq);
- pr_warn("Error %d requesting irq %d (0x%x)\n",
- rc, virq, irq);
- continue;
- }
-
- /* Cache IRQ */
- opal_irqs[i] = virq;
- }
-}
-
static int kopald(void *unused)
{
+ __be64 events;
+
set_freezable();
do {
try_to_freeze();
- opal_poll_events(NULL);
+ opal_poll_events(&events);
+ opal_handle_events(be64_to_cpu(events));
msleep_interruptible(opal_heartbeat);
} while (!kthread_should_stop());
@@ -807,15 +671,24 @@ static int __init opal_init(void)
of_node_put(consoles);
}
+ /* Initialise OPAL messaging system */
+ opal_message_init();
+
+ /* Initialise OPAL asynchronous completion interface */
+ opal_async_comp_init();
+
+ /* Initialise OPAL sensor interface */
+ opal_sensor_init();
+
+ /* Initialise OPAL hypervisor maintainence interrupt handling */
+ opal_hmi_handler_init();
+
/* Create i2c platform devices */
opal_i2c_create_devs();
/* Setup a heatbeat thread if requested by OPAL */
opal_init_heartbeat();
- /* Find all OPAL interrupts and request them */
- opal_irq_init(opal_node);
-
/* Create "opal" kobject under /sys/firmware */
rc = opal_sysfs_init();
if (rc == 0) {
@@ -835,10 +708,10 @@ static int __init opal_init(void)
opal_msglog_init();
}
- /* Initialize OPAL IPMI backend */
- opal_ipmi_init(opal_node);
-
- opal_flash_init(opal_node);
+ /* Initialize platform devices: IPMI backend, PRD & flash interface */
+ opal_pdev_init(opal_node, "ibm,opal-ipmi");
+ opal_pdev_init(opal_node, "ibm,opal-flash");
+ opal_pdev_init(opal_node, "ibm,opal-prd");
return 0;
}
@@ -846,15 +719,9 @@ machine_subsys_initcall(powernv, opal_init);
void opal_shutdown(void)
{
- unsigned int i;
long rc = OPAL_BUSY;
- /* First free interrupts, which will also mask them */
- for (i = 0; i < opal_irq_count; i++) {
- if (opal_irqs[i])
- free_irq(opal_irqs[i], NULL);
- opal_irqs[i] = 0;
- }
+ opal_event_shutdown();
/*
* Then sync with OPAL which ensure anything that can
@@ -876,11 +743,14 @@ void opal_shutdown(void)
/* Export this so that test modules can use it */
EXPORT_SYMBOL_GPL(opal_invalid_call);
+EXPORT_SYMBOL_GPL(opal_xscom_read);
+EXPORT_SYMBOL_GPL(opal_xscom_write);
EXPORT_SYMBOL_GPL(opal_ipmi_send);
EXPORT_SYMBOL_GPL(opal_ipmi_recv);
EXPORT_SYMBOL_GPL(opal_flash_read);
EXPORT_SYMBOL_GPL(opal_flash_write);
EXPORT_SYMBOL_GPL(opal_flash_erase);
+EXPORT_SYMBOL_GPL(opal_prd_msg);
/* Convert a region of vmalloc memory to an opal sg list */
struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
@@ -954,6 +824,7 @@ int opal_error_code(int rc)
case OPAL_ASYNC_COMPLETION: return -EINPROGRESS;
case OPAL_BUSY_EVENT: return -EBUSY;
case OPAL_NO_MEM: return -ENOMEM;
+ case OPAL_PERMISSION: return -EPERM;
case OPAL_UNSUPPORTED: return -EIO;
case OPAL_HARDWARE: return -EIO;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index f8bc950efcae..5738d315248b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -23,6 +23,9 @@
#include <linux/io.h>
#include <linux/msi.h>
#include <linux/memblock.h>
+#include <linux/iommu.h>
+#include <linux/rculist.h>
+#include <linux/sizes.h>
#include <asm/sections.h>
#include <asm/io.h>
@@ -38,8 +41,9 @@
#include <asm/debug.h>
#include <asm/firmware.h>
#include <asm/pnv-pci.h>
+#include <asm/mmzone.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
#include "powernv.h"
#include "pci.h"
@@ -47,6 +51,11 @@
/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8)
+#define POWERNV_IOMMU_DEFAULT_LEVELS 1
+#define POWERNV_IOMMU_MAX_LEVELS 5
+
+static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
+
static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
const char *fmt, ...)
{
@@ -1086,10 +1095,6 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
return;
}
- pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
- GFP_KERNEL, hose->node);
- pe->tce32_table->data = pe;
-
/* Associate it with all child devices */
pnv_ioda_setup_same_PE(bus, pe);
@@ -1283,36 +1288,27 @@ m64_failed:
return -EBUSY;
}
+static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
+ int num);
+static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
+
static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe)
{
- struct pci_bus *bus;
- struct pci_controller *hose;
- struct pnv_phb *phb;
struct iommu_table *tbl;
- unsigned long addr;
int64_t rc;
- bus = dev->bus;
- hose = pci_bus_to_host(bus);
- phb = hose->private_data;
- tbl = pe->tce32_table;
- addr = tbl->it_base;
-
- opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
- pe->pe_number << 1, 1, __pa(addr),
- 0, 0x1000);
-
- rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
- pe->pe_number,
- (pe->pe_number << 1) + 1,
- pe->tce_bypass_base,
- 0);
+ tbl = pe->table_group.tables[0];
+ rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
if (rc)
pe_warn(pe, "OPAL error %ld release DMA window\n", rc);
+ pnv_pci_ioda2_set_bypass(pe, false);
+ if (pe->table_group.group) {
+ iommu_group_put(pe->table_group.group);
+ BUG_ON(pe->table_group.group);
+ }
+ pnv_pci_ioda2_table_free_pages(tbl);
iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
- free_pages(addr, get_order(TCE32_TABLE_SIZE));
- pe->tce32_table = NULL;
}
static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs)
@@ -1460,10 +1456,6 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
continue;
}
- pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
- GFP_KERNEL, hose->node);
- pe->tce32_table->data = pe;
-
/* Put PE to the list */
mutex_lock(&phb->ioda.pe_list_mutex);
list_add_tail(&pe->list, &phb->ioda.pe_list);
@@ -1598,12 +1590,19 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
pe = &phb->ioda.pe_array[pdn->pe_number];
WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
- set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table);
+ set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
+ /*
+ * Note: iommu_add_device() will fail here as
+ * for physical PE: the device is already added by now;
+ * for virtual PE: sysfs entries are not ready yet and
+ * tce_iommu_bus_notifier will add the device to a group later.
+ */
}
-static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
- struct pci_dev *pdev, u64 dma_mask)
+static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
{
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ struct pnv_phb *phb = hose->private_data;
struct pci_dn *pdn = pci_get_pdn(pdev);
struct pnv_ioda_pe *pe;
uint64_t top;
@@ -1625,7 +1624,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
} else {
dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
set_dma_ops(&pdev->dev, &dma_iommu_ops);
- set_iommu_table_base(&pdev->dev, pe->tce32_table);
+ set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
}
*pdev->dev.dma_mask = dma_mask;
return 0;
@@ -1654,36 +1653,36 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pnv_phb *phb,
}
static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
- struct pci_bus *bus,
- bool add_to_iommu_group)
+ struct pci_bus *bus)
{
struct pci_dev *dev;
list_for_each_entry(dev, &bus->devices, bus_list) {
- if (add_to_iommu_group)
- set_iommu_table_base_and_group(&dev->dev,
- pe->tce32_table);
- else
- set_iommu_table_base(&dev->dev, pe->tce32_table);
+ set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
+ iommu_add_device(&dev->dev);
- if (dev->subordinate)
- pnv_ioda_setup_bus_dma(pe, dev->subordinate,
- add_to_iommu_group);
+ if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
+ pnv_ioda_setup_bus_dma(pe, dev->subordinate);
}
}
-static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
- struct iommu_table *tbl,
- __be64 *startp, __be64 *endp, bool rm)
+static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
+ unsigned long index, unsigned long npages, bool rm)
{
+ struct iommu_table_group_link *tgl = list_first_entry_or_null(
+ &tbl->it_group_list, struct iommu_table_group_link,
+ next);
+ struct pnv_ioda_pe *pe = container_of(tgl->table_group,
+ struct pnv_ioda_pe, table_group);
__be64 __iomem *invalidate = rm ?
- (__be64 __iomem *)pe->tce_inval_reg_phys :
- (__be64 __iomem *)tbl->it_index;
+ (__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
+ pe->phb->ioda.tce_inval_reg;
unsigned long start, end, inc;
const unsigned shift = tbl->it_page_shift;
- start = __pa(startp);
- end = __pa(endp);
+ start = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset);
+ end = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset +
+ npages - 1);
/* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */
if (tbl->it_busno) {
@@ -1719,26 +1718,79 @@ static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
*/
}
-static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
- struct iommu_table *tbl,
- __be64 *startp, __be64 *endp, bool rm)
+static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
+ long npages, unsigned long uaddr,
+ enum dma_data_direction direction,
+ struct dma_attrs *attrs)
+{
+ int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
+ attrs);
+
+ if (!ret && (tbl->it_type & TCE_PCI_SWINV_CREATE))
+ pnv_pci_ioda1_tce_invalidate(tbl, index, npages, false);
+
+ return ret;
+}
+
+#ifdef CONFIG_IOMMU_API
+static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
+ unsigned long *hpa, enum dma_data_direction *direction)
+{
+ long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+ if (!ret && (tbl->it_type &
+ (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE)))
+ pnv_pci_ioda1_tce_invalidate(tbl, index, 1, false);
+
+ return ret;
+}
+#endif
+
+static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
+ long npages)
+{
+ pnv_tce_free(tbl, index, npages);
+
+ if (tbl->it_type & TCE_PCI_SWINV_FREE)
+ pnv_pci_ioda1_tce_invalidate(tbl, index, npages, false);
+}
+
+static struct iommu_table_ops pnv_ioda1_iommu_ops = {
+ .set = pnv_ioda1_tce_build,
+#ifdef CONFIG_IOMMU_API
+ .exchange = pnv_ioda1_tce_xchg,
+#endif
+ .clear = pnv_ioda1_tce_free,
+ .get = pnv_tce_get,
+};
+
+static inline void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_ioda_pe *pe)
+{
+ /* 01xb - invalidate TCEs that match the specified PE# */
+ unsigned long val = (0x4ull << 60) | (pe->pe_number & 0xFF);
+ struct pnv_phb *phb = pe->phb;
+
+ if (!phb->ioda.tce_inval_reg)
+ return;
+
+ mb(); /* Ensure above stores are visible */
+ __raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg);
+}
+
+static void pnv_pci_ioda2_do_tce_invalidate(unsigned pe_number, bool rm,
+ __be64 __iomem *invalidate, unsigned shift,
+ unsigned long index, unsigned long npages)
{
unsigned long start, end, inc;
- __be64 __iomem *invalidate = rm ?
- (__be64 __iomem *)pe->tce_inval_reg_phys :
- (__be64 __iomem *)tbl->it_index;
- const unsigned shift = tbl->it_page_shift;
/* We'll invalidate DMA address in PE scope */
start = 0x2ull << 60;
- start |= (pe->pe_number & 0xFF);
+ start |= (pe_number & 0xFF);
end = start;
/* Figure out the start, end and step */
- inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64));
- start |= (inc << shift);
- inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64));
- end |= (inc << shift);
+ start |= (index << shift);
+ end |= ((index + npages - 1) << shift);
inc = (0x1ull << shift);
mb();
@@ -1751,25 +1803,83 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
}
}
-void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
- __be64 *startp, __be64 *endp, bool rm)
+static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
+ unsigned long index, unsigned long npages, bool rm)
{
- struct pnv_ioda_pe *pe = tbl->data;
- struct pnv_phb *phb = pe->phb;
+ struct iommu_table_group_link *tgl;
- if (phb->type == PNV_PHB_IODA1)
- pnv_pci_ioda1_tce_invalidate(pe, tbl, startp, endp, rm);
- else
- pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp, rm);
+ list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+ struct pnv_ioda_pe *pe = container_of(tgl->table_group,
+ struct pnv_ioda_pe, table_group);
+ __be64 __iomem *invalidate = rm ?
+ (__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
+ pe->phb->ioda.tce_inval_reg;
+
+ pnv_pci_ioda2_do_tce_invalidate(pe->pe_number, rm,
+ invalidate, tbl->it_page_shift,
+ index, npages);
+ }
+}
+
+static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
+ long npages, unsigned long uaddr,
+ enum dma_data_direction direction,
+ struct dma_attrs *attrs)
+{
+ int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
+ attrs);
+
+ if (!ret && (tbl->it_type & TCE_PCI_SWINV_CREATE))
+ pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
+
+ return ret;
+}
+
+#ifdef CONFIG_IOMMU_API
+static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
+ unsigned long *hpa, enum dma_data_direction *direction)
+{
+ long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+ if (!ret && (tbl->it_type &
+ (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE)))
+ pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);
+
+ return ret;
+}
+#endif
+
+static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
+ long npages)
+{
+ pnv_tce_free(tbl, index, npages);
+
+ if (tbl->it_type & TCE_PCI_SWINV_FREE)
+ pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
+}
+
+static void pnv_ioda2_table_free(struct iommu_table *tbl)
+{
+ pnv_pci_ioda2_table_free_pages(tbl);
+ iommu_free_table(tbl, "pnv");
}
+static struct iommu_table_ops pnv_ioda2_iommu_ops = {
+ .set = pnv_ioda2_tce_build,
+#ifdef CONFIG_IOMMU_API
+ .exchange = pnv_ioda2_tce_xchg,
+#endif
+ .clear = pnv_ioda2_tce_free,
+ .get = pnv_tce_get,
+ .free = pnv_ioda2_table_free,
+};
+
static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
struct pnv_ioda_pe *pe, unsigned int base,
unsigned int segs)
{
struct page *tce_mem = NULL;
- const __be64 *swinvp;
struct iommu_table *tbl;
unsigned int i;
int64_t rc;
@@ -1783,6 +1893,11 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
if (WARN_ON(pe->tce32_seg >= 0))
return;
+ tbl = pnv_pci_table_alloc(phb->hose->node);
+ iommu_register_group(&pe->table_group, phb->hose->global_number,
+ pe->pe_number);
+ pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
+
/* Grab a 32-bit TCE table */
pe->tce32_seg = base;
pe_info(pe, " Setting up 32-bit TCE table at %08x..%08x\n",
@@ -1817,39 +1932,30 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
}
/* Setup linux iommu table */
- tbl = pe->tce32_table;
pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
base << 28, IOMMU_PAGE_SHIFT_4K);
/* OPAL variant of P7IOC SW invalidated TCEs */
- swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
- if (swinvp) {
- /* We need a couple more fields -- an address and a data
- * to or. Since the bus is only printed out on table free
- * errors, and on the first pass the data will be a relative
- * bus number, print that out instead.
- */
- pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
- tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
- 8);
+ if (phb->ioda.tce_inval_reg)
tbl->it_type |= (TCE_PCI_SWINV_CREATE |
TCE_PCI_SWINV_FREE |
TCE_PCI_SWINV_PAIR);
- }
+
+ tbl->it_ops = &pnv_ioda1_iommu_ops;
+ pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
+ pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
iommu_init_table(tbl, phb->hose->node);
if (pe->flags & PNV_IODA_PE_DEV) {
- iommu_register_group(tbl, phb->hose->global_number,
- pe->pe_number);
- set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
- } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
- iommu_register_group(tbl, phb->hose->global_number,
- pe->pe_number);
- pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
- } else if (pe->flags & PNV_IODA_PE_VF) {
- iommu_register_group(tbl, phb->hose->global_number,
- pe->pe_number);
- }
+ /*
+ * Setting table base here only for carrying iommu_group
+ * further down to let iommu_add_device() do the job.
+ * pnv_pci_ioda_dma_dev_setup will override it later anyway.
+ */
+ set_iommu_table_base(&pe->pdev->dev, tbl);
+ iommu_add_device(&pe->pdev->dev);
+ } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
+ pnv_ioda_setup_bus_dma(pe, pe->pbus);
return;
fail:
@@ -1858,11 +1964,53 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
pe->tce32_seg = -1;
if (tce_mem)
__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
+ if (tbl) {
+ pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
+ iommu_free_table(tbl, "pnv");
+ }
}
-static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
+ int num, struct iommu_table *tbl)
+{
+ struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+ table_group);
+ struct pnv_phb *phb = pe->phb;
+ int64_t rc;
+ const unsigned long size = tbl->it_indirect_levels ?
+ tbl->it_level_size : tbl->it_size;
+ const __u64 start_addr = tbl->it_offset << tbl->it_page_shift;
+ const __u64 win_size = tbl->it_size << tbl->it_page_shift;
+
+ pe_info(pe, "Setting up window#%d %llx..%llx pg=%x\n", num,
+ start_addr, start_addr + win_size - 1,
+ IOMMU_PAGE_SIZE(tbl));
+
+ /*
+ * Map TCE table through TVT. The TVE index is the PE number
+ * shifted by 1 bit for 32-bits DMA space.
+ */
+ rc = opal_pci_map_pe_dma_window(phb->opal_id,
+ pe->pe_number,
+ (pe->pe_number << 1) + num,
+ tbl->it_indirect_levels + 1,
+ __pa(tbl->it_base),
+ size << 3,
+ IOMMU_PAGE_SIZE(tbl));
+ if (rc) {
+ pe_err(pe, "Failed to configure TCE table, err %ld\n", rc);
+ return rc;
+ }
+
+ pnv_pci_link_table_and_group(phb->hose->node, num,
+ tbl, &pe->table_group);
+ pnv_pci_ioda2_tce_invalidate_entire(pe);
+
+ return 0;
+}
+
+static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
{
- struct pnv_ioda_pe *pe = tbl->data;
uint16_t window_id = (pe->pe_number << 1 ) + 1;
int64_t rc;
@@ -1882,17 +2030,6 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
window_id,
pe->tce_bypass_base,
0);
-
- /*
- * EEH needs the mapping between IOMMU table and group
- * of those VFIO/KVM pass-through devices. We can postpone
- * resetting DMA ops until the DMA mask is configured in
- * host side.
- */
- if (pe->pdev)
- set_iommu_table_base(&pe->pdev->dev, tbl);
- else
- pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
}
if (rc)
pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
@@ -1900,106 +2037,363 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
pe->tce_bypass_enabled = enable;
}
-static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
- struct pnv_ioda_pe *pe)
+static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
+ __u32 page_shift, __u64 window_size, __u32 levels,
+ struct iommu_table *tbl);
+
+static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
+ int num, __u32 page_shift, __u64 window_size, __u32 levels,
+ struct iommu_table **ptbl)
{
- /* TVE #1 is selected by PCI address bit 59 */
- pe->tce_bypass_base = 1ull << 59;
+ struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+ table_group);
+ int nid = pe->phb->hose->node;
+ __u64 bus_offset = num ? pe->tce_bypass_base : table_group->tce32_start;
+ long ret;
+ struct iommu_table *tbl;
- /* Install set_bypass callback for VFIO */
- pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass;
+ tbl = pnv_pci_table_alloc(nid);
+ if (!tbl)
+ return -ENOMEM;
- /* Enable bypass by default */
- pnv_pci_ioda2_set_bypass(pe->tce32_table, true);
+ ret = pnv_pci_ioda2_table_alloc_pages(nid,
+ bus_offset, page_shift, window_size,
+ levels, tbl);
+ if (ret) {
+ iommu_free_table(tbl, "pnv");
+ return ret;
+ }
+
+ tbl->it_ops = &pnv_ioda2_iommu_ops;
+ if (pe->phb->ioda.tce_inval_reg)
+ tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
+
+ *ptbl = tbl;
+
+ return 0;
}
-static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
- struct pnv_ioda_pe *pe)
+static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
+{
+ struct iommu_table *tbl = NULL;
+ long rc;
+
+ rc = pnv_pci_ioda2_create_table(&pe->table_group, 0,
+ IOMMU_PAGE_SHIFT_4K,
+ pe->table_group.tce32_size,
+ POWERNV_IOMMU_DEFAULT_LEVELS, &tbl);
+ if (rc) {
+ pe_err(pe, "Failed to create 32-bit TCE table, err %ld",
+ rc);
+ return rc;
+ }
+
+ iommu_init_table(tbl, pe->phb->hose->node);
+
+ rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
+ if (rc) {
+ pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
+ rc);
+ pnv_ioda2_table_free(tbl);
+ return rc;
+ }
+
+ if (!pnv_iommu_bypass_disabled)
+ pnv_pci_ioda2_set_bypass(pe, true);
+
+ /* OPAL variant of PHB3 invalidated TCEs */
+ if (pe->phb->ioda.tce_inval_reg)
+ tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
+
+ /*
+ * Setting table base here only for carrying iommu_group
+ * further down to let iommu_add_device() do the job.
+ * pnv_pci_ioda_dma_dev_setup will override it later anyway.
+ */
+ if (pe->flags & PNV_IODA_PE_DEV)
+ set_iommu_table_base(&pe->pdev->dev, tbl);
+
+ return 0;
+}
+
+#if defined(CONFIG_IOMMU_API) || defined(CONFIG_PCI_IOV)
+static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
+ int num)
+{
+ struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+ table_group);
+ struct pnv_phb *phb = pe->phb;
+ long ret;
+
+ pe_info(pe, "Removing DMA window #%d\n", num);
+
+ ret = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
+ (pe->pe_number << 1) + num,
+ 0/* levels */, 0/* table address */,
+ 0/* table size */, 0/* page size */);
+ if (ret)
+ pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
+ else
+ pnv_pci_ioda2_tce_invalidate_entire(pe);
+
+ pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
+
+ return ret;
+}
+#endif
+
+#ifdef CONFIG_IOMMU_API
+static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
+ __u64 window_size, __u32 levels)
+{
+ unsigned long bytes = 0;
+ const unsigned window_shift = ilog2(window_size);
+ unsigned entries_shift = window_shift - page_shift;
+ unsigned table_shift = entries_shift + 3;
+ unsigned long tce_table_size = max(0x1000UL, 1UL << table_shift);
+ unsigned long direct_table_size;
+
+ if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) ||
+ (window_size > memory_hotplug_max()) ||
+ !is_power_of_2(window_size))
+ return 0;
+
+ /* Calculate a direct table size from window_size and levels */
+ entries_shift = (entries_shift + levels - 1) / levels;
+ table_shift = entries_shift + 3;
+ table_shift = max_t(unsigned, table_shift, PAGE_SHIFT);
+ direct_table_size = 1UL << table_shift;
+
+ for ( ; levels; --levels) {
+ bytes += _ALIGN_UP(tce_table_size, direct_table_size);
+
+ tce_table_size /= direct_table_size;
+ tce_table_size <<= 3;
+ tce_table_size = _ALIGN_UP(tce_table_size, direct_table_size);
+ }
+
+ return bytes;
+}
+
+static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
+{
+ struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+ table_group);
+ /* Store @tbl as pnv_pci_ioda2_unset_window() resets it */
+ struct iommu_table *tbl = pe->table_group.tables[0];
+
+ pnv_pci_ioda2_set_bypass(pe, false);
+ pnv_pci_ioda2_unset_window(&pe->table_group, 0);
+ pnv_ioda2_table_free(tbl);
+}
+
+static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
+{
+ struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+ table_group);
+
+ pnv_pci_ioda2_setup_default_config(pe);
+}
+
+static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
+ .get_table_size = pnv_pci_ioda2_get_table_size,
+ .create_table = pnv_pci_ioda2_create_table,
+ .set_window = pnv_pci_ioda2_set_window,
+ .unset_window = pnv_pci_ioda2_unset_window,
+ .take_ownership = pnv_ioda2_take_ownership,
+ .release_ownership = pnv_ioda2_release_ownership,
+};
+#endif
+
+static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb)
{
- struct page *tce_mem = NULL;
- void *addr;
const __be64 *swinvp;
- struct iommu_table *tbl;
- unsigned int tce_table_size, end;
- int64_t rc;
- /* We shouldn't already have a 32-bit DMA associated */
- if (WARN_ON(pe->tce32_seg >= 0))
+ /* OPAL variant of PHB3 invalidated TCEs */
+ swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
+ if (!swinvp)
return;
- /* The PE will reserve all possible 32-bits space */
- pe->tce32_seg = 0;
- end = (1 << ilog2(phb->ioda.m32_pci_base));
- tce_table_size = (end / 0x1000) * 8;
- pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
- end);
+ phb->ioda.tce_inval_reg_phys = be64_to_cpup(swinvp);
+ phb->ioda.tce_inval_reg = ioremap(phb->ioda.tce_inval_reg_phys, 8);
+}
- /* Allocate TCE table */
- tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
- get_order(tce_table_size));
+static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
+ unsigned levels, unsigned long limit,
+ unsigned long *current_offset)
+{
+ struct page *tce_mem = NULL;
+ __be64 *addr, *tmp;
+ unsigned order = max_t(unsigned, shift, PAGE_SHIFT) - PAGE_SHIFT;
+ unsigned long allocated = 1UL << (order + PAGE_SHIFT);
+ unsigned entries = 1UL << (shift - 3);
+ long i;
+
+ tce_mem = alloc_pages_node(nid, GFP_KERNEL, order);
if (!tce_mem) {
- pe_err(pe, "Failed to allocate a 32-bit TCE memory\n");
- goto fail;
+ pr_err("Failed to allocate a TCE memory, order=%d\n", order);
+ return NULL;
}
addr = page_address(tce_mem);
- memset(addr, 0, tce_table_size);
+ memset(addr, 0, allocated);
+
+ --levels;
+ if (!levels) {
+ *current_offset += allocated;
+ return addr;
+ }
+
+ for (i = 0; i < entries; ++i) {
+ tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift,
+ levels, limit, current_offset);
+ if (!tmp)
+ break;
+
+ addr[i] = cpu_to_be64(__pa(tmp) |
+ TCE_PCI_READ | TCE_PCI_WRITE);
+
+ if (*current_offset >= limit)
+ break;
+ }
+
+ return addr;
+}
+
+static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
+ unsigned long size, unsigned level);
+
+static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
+ __u32 page_shift, __u64 window_size, __u32 levels,
+ struct iommu_table *tbl)
+{
+ void *addr;
+ unsigned long offset = 0, level_shift;
+ const unsigned window_shift = ilog2(window_size);
+ unsigned entries_shift = window_shift - page_shift;
+ unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT);
+ const unsigned long tce_table_size = 1UL << table_shift;
+
+ if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS))
+ return -EINVAL;
+
+ if ((window_size > memory_hotplug_max()) || !is_power_of_2(window_size))
+ return -EINVAL;
+
+ /* Adjust direct table size from window_size and levels */
+ entries_shift = (entries_shift + levels - 1) / levels;
+ level_shift = entries_shift + 3;
+ level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
+
+ /* Allocate TCE table */
+ addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
+ levels, tce_table_size, &offset);
+
+ /* addr==NULL means that the first level allocation failed */
+ if (!addr)
+ return -ENOMEM;
/*
- * Map TCE table through TVT. The TVE index is the PE number
- * shifted by 1 bit for 32-bits DMA space.
+ * First level was allocated but some lower level failed as
+ * we did not allocate as much as we wanted,
+ * release partially allocated table.
*/
- rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
- pe->pe_number << 1, 1, __pa(addr),
- tce_table_size, 0x1000);
- if (rc) {
- pe_err(pe, "Failed to configure 32-bit TCE table,"
- " err %ld\n", rc);
- goto fail;
+ if (offset < tce_table_size) {
+ pnv_pci_ioda2_table_do_free_pages(addr,
+ 1ULL << (level_shift - 3), levels - 1);
+ return -ENOMEM;
}
/* Setup linux iommu table */
- tbl = pe->tce32_table;
- pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
- IOMMU_PAGE_SHIFT_4K);
+ pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset,
+ page_shift);
+ tbl->it_level_size = 1ULL << (level_shift - 3);
+ tbl->it_indirect_levels = levels - 1;
+ tbl->it_allocated_size = offset;
- /* OPAL variant of PHB3 invalidated TCEs */
- swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
- if (swinvp) {
- /* We need a couple more fields -- an address and a data
- * to or. Since the bus is only printed out on table free
- * errors, and on the first pass the data will be a relative
- * bus number, print that out instead.
- */
- pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
- tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
- 8);
- tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
+ pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
+ window_size, tce_table_size, bus_offset);
+
+ return 0;
+}
+
+static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
+ unsigned long size, unsigned level)
+{
+ const unsigned long addr_ul = (unsigned long) addr &
+ ~(TCE_PCI_READ | TCE_PCI_WRITE);
+
+ if (level) {
+ long i;
+ u64 *tmp = (u64 *) addr_ul;
+
+ for (i = 0; i < size; ++i) {
+ unsigned long hpa = be64_to_cpu(tmp[i]);
+
+ if (!(hpa & (TCE_PCI_READ | TCE_PCI_WRITE)))
+ continue;
+
+ pnv_pci_ioda2_table_do_free_pages(__va(hpa), size,
+ level - 1);
+ }
}
- iommu_init_table(tbl, phb->hose->node);
- if (pe->flags & PNV_IODA_PE_DEV) {
- iommu_register_group(tbl, phb->hose->global_number,
- pe->pe_number);
- set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
- } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
- iommu_register_group(tbl, phb->hose->global_number,
- pe->pe_number);
- pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
- } else if (pe->flags & PNV_IODA_PE_VF) {
- iommu_register_group(tbl, phb->hose->global_number,
- pe->pe_number);
- }
-
- /* Also create a bypass window */
- if (!pnv_iommu_bypass_disabled)
- pnv_pci_ioda2_setup_bypass_pe(phb, pe);
+ free_pages(addr_ul, get_order(size << 3));
+}
- return;
-fail:
- if (pe->tce32_seg >= 0)
- pe->tce32_seg = -1;
- if (tce_mem)
- __free_pages(tce_mem, get_order(tce_table_size));
+static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl)
+{
+ const unsigned long size = tbl->it_indirect_levels ?
+ tbl->it_level_size : tbl->it_size;
+
+ if (!tbl->it_size)
+ return;
+
+ pnv_pci_ioda2_table_do_free_pages((__be64 *)tbl->it_base, size,
+ tbl->it_indirect_levels);
+}
+
+static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
+ struct pnv_ioda_pe *pe)
+{
+ int64_t rc;
+
+ /* We shouldn't already have a 32-bit DMA associated */
+ if (WARN_ON(pe->tce32_seg >= 0))
+ return;
+
+ /* TVE #1 is selected by PCI address bit 59 */
+ pe->tce_bypass_base = 1ull << 59;
+
+ iommu_register_group(&pe->table_group, phb->hose->global_number,
+ pe->pe_number);
+
+ /* The PE will reserve all possible 32-bits space */
+ pe->tce32_seg = 0;
+ pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
+ phb->ioda.m32_pci_base);
+
+ /* Setup linux iommu table */
+ pe->table_group.tce32_start = 0;
+ pe->table_group.tce32_size = phb->ioda.m32_pci_base;
+ pe->table_group.max_dynamic_windows_supported =
+ IOMMU_TABLE_GROUP_MAX_TABLES;
+ pe->table_group.max_levels = POWERNV_IOMMU_MAX_LEVELS;
+ pe->table_group.pgsizes = SZ_4K | SZ_64K | SZ_16M;
+#ifdef CONFIG_IOMMU_API
+ pe->table_group.ops = &pnv_pci_ioda2_ops;
+#endif
+
+ rc = pnv_pci_ioda2_setup_default_config(pe);
+ if (rc) {
+ if (pe->tce32_seg >= 0)
+ pe->tce32_seg = -1;
+ return;
+ }
+
+ if (pe->flags & PNV_IODA_PE_DEV)
+ iommu_add_device(&pe->pdev->dev);
+ else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
+ pnv_ioda_setup_bus_dma(pe, pe->pbus);
}
static void pnv_ioda_setup_dma(struct pnv_phb *phb)
@@ -2024,6 +2418,8 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb)
pr_info("PCI: %d PE# for a total weight of %d\n",
phb->ioda.dma_pe_count, phb->ioda.dma_weight);
+ pnv_pci_ioda_setup_opal_tce_kill(phb);
+
/* Walk our PE list and configure their DMA segments, hand them
* out one base segment plus any residual segments based on
* weight
@@ -2642,12 +3038,27 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
}
-static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
+static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
{
+ struct pnv_phb *phb = hose->private_data;
+
opal_pci_reset(phb->opal_id, OPAL_RESET_PCI_IODA_TABLE,
OPAL_ASSERT_RESET);
}
+static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
+ .dma_dev_setup = pnv_pci_dma_dev_setup,
+#ifdef CONFIG_PCI_MSI
+ .setup_msi_irqs = pnv_setup_msi_irqs,
+ .teardown_msi_irqs = pnv_teardown_msi_irqs,
+#endif
+ .enable_device_hook = pnv_pci_enable_device_hook,
+ .window_alignment = pnv_pci_window_alignment,
+ .reset_secondary_bus = pnv_pci_reset_secondary_bus,
+ .dma_set_mask = pnv_pci_ioda_dma_set_mask,
+ .shutdown = pnv_pci_ioda_shutdown,
+};
+
static void __init pnv_pci_init_ioda_phb(struct device_node *np,
u64 hub_id, int ioda_type)
{
@@ -2791,12 +3202,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
/* Setup TCEs */
phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
- phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
phb->dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask;
- /* Setup shutdown function for kexec */
- phb->shutdown = pnv_pci_ioda_shutdown;
-
/* Setup MSI support */
pnv_pci_init_ioda_msis(phb);
@@ -2808,10 +3215,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
* the child P2P bridges) can form individual PE.
*/
ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
- pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook;
- pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment;
- pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus;
- hose->controller_ops = pnv_pci_controller_ops;
+ hose->controller_ops = pnv_pci_ioda_controller_ops;
#ifdef CONFIG_PCI_IOV
ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index 4729ca793813..f2bdfea3b68d 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -83,18 +83,42 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb)
static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { }
#endif /* CONFIG_PCI_MSI */
+static struct iommu_table_ops pnv_p5ioc2_iommu_ops = {
+ .set = pnv_tce_build,
+#ifdef CONFIG_IOMMU_API
+ .exchange = pnv_tce_xchg,
+#endif
+ .clear = pnv_tce_free,
+ .get = pnv_tce_get,
+};
+
static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
struct pci_dev *pdev)
{
- if (phb->p5ioc2.iommu_table.it_map == NULL) {
- iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node);
- iommu_register_group(&phb->p5ioc2.iommu_table,
+ struct iommu_table *tbl = phb->p5ioc2.table_group.tables[0];
+
+ if (!tbl->it_map) {
+ tbl->it_ops = &pnv_p5ioc2_iommu_ops;
+ iommu_init_table(tbl, phb->hose->node);
+ iommu_register_group(&phb->p5ioc2.table_group,
pci_domain_nr(phb->hose->bus), phb->opal_id);
+ INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+ pnv_pci_link_table_and_group(phb->hose->node, 0,
+ tbl, &phb->p5ioc2.table_group);
}
- set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table);
+ set_iommu_table_base(&pdev->dev, tbl);
+ iommu_add_device(&pdev->dev);
}
+static const struct pci_controller_ops pnv_pci_p5ioc2_controller_ops = {
+ .dma_dev_setup = pnv_pci_dma_dev_setup,
+#ifdef CONFIG_PCI_MSI
+ .setup_msi_irqs = pnv_setup_msi_irqs,
+ .teardown_msi_irqs = pnv_teardown_msi_irqs,
+#endif
+};
+
static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
void *tce_mem, u64 tce_size)
{
@@ -103,6 +127,8 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
u64 phb_id;
int64_t rc;
static int primary = 1;
+ struct iommu_table_group *table_group;
+ struct iommu_table *tbl;
pr_info(" Initializing p5ioc2 PHB %s\n", np->full_name);
@@ -133,7 +159,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
phb->hose->first_busno = 0;
phb->hose->last_busno = 0xff;
phb->hose->private_data = phb;
- phb->hose->controller_ops = pnv_pci_controller_ops;
+ phb->hose->controller_ops = pnv_pci_p5ioc2_controller_ops;
phb->hub_id = hub_id;
phb->opal_id = phb_id;
phb->type = PNV_PHB_P5IOC2;
@@ -172,6 +198,15 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
pnv_pci_setup_iommu_table(&phb->p5ioc2.iommu_table,
tce_mem, tce_size, 0,
IOMMU_PAGE_SHIFT_4K);
+ /*
+ * We do not allocate iommu_table as we do not support
+ * hotplug or SRIOV on P5IOC2 and therefore iommu_free_table()
+ * should not be called for phb->p5ioc2.table_group.tables[0] ever.
+ */
+ tbl = phb->p5ioc2.table_group.tables[0] = &phb->p5ioc2.iommu_table;
+ table_group = &phb->p5ioc2.table_group;
+ table_group->tce32_start = tbl->it_offset << tbl->it_page_shift;
+ table_group->tce32_size = tbl->it_size << tbl->it_page_shift;
}
void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index bca2aeb6e4b6..765d8ed558d0 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -45,7 +45,7 @@
//#define cfg_dbg(fmt...) printk(fmt)
#ifdef CONFIG_PCI_MSI
-static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
{
struct pci_controller *hose = pci_bus_to_host(pdev->bus);
struct pnv_phb *phb = hose->private_data;
@@ -94,7 +94,7 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
return 0;
}
-static void pnv_teardown_msi_irqs(struct pci_dev *pdev)
+void pnv_teardown_msi_irqs(struct pci_dev *pdev)
{
struct pci_controller *hose = pci_bus_to_host(pdev->bus);
struct pnv_phb *phb = hose->private_data;
@@ -572,80 +572,152 @@ struct pci_ops pnv_pci_ops = {
.write = pnv_pci_write_config,
};
-static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
- unsigned long uaddr, enum dma_data_direction direction,
- struct dma_attrs *attrs, bool rm)
+static __be64 *pnv_tce(struct iommu_table *tbl, long idx)
{
- u64 proto_tce;
- __be64 *tcep, *tces;
- u64 rpn;
-
- proto_tce = TCE_PCI_READ; // Read allowed
+ __be64 *tmp = ((__be64 *)tbl->it_base);
+ int level = tbl->it_indirect_levels;
+ const long shift = ilog2(tbl->it_level_size);
+ unsigned long mask = (tbl->it_level_size - 1) << (level * shift);
+
+ while (level) {
+ int n = (idx & mask) >> (level * shift);
+ unsigned long tce = be64_to_cpu(tmp[n]);
+
+ tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE));
+ idx &= ~mask;
+ mask >>= shift;
+ --level;
+ }
- if (direction != DMA_TO_DEVICE)
- proto_tce |= TCE_PCI_WRITE;
+ return tmp + idx;
+}
- tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset;
- rpn = __pa(uaddr) >> tbl->it_page_shift;
+int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
+ unsigned long uaddr, enum dma_data_direction direction,
+ struct dma_attrs *attrs)
+{
+ u64 proto_tce = iommu_direction_to_tce_perm(direction);
+ u64 rpn = __pa(uaddr) >> tbl->it_page_shift;
+ long i;
- while (npages--)
- *(tcep++) = cpu_to_be64(proto_tce |
- (rpn++ << tbl->it_page_shift));
+ for (i = 0; i < npages; i++) {
+ unsigned long newtce = proto_tce |
+ ((rpn + i) << tbl->it_page_shift);
+ unsigned long idx = index - tbl->it_offset + i;
- /* Some implementations won't cache invalid TCEs and thus may not
- * need that flush. We'll probably turn it_type into a bit mask
- * of flags if that becomes the case
- */
- if (tbl->it_type & TCE_PCI_SWINV_CREATE)
- pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
+ *(pnv_tce(tbl, idx)) = cpu_to_be64(newtce);
+ }
return 0;
}
-static int pnv_tce_build_vm(struct iommu_table *tbl, long index, long npages,
- unsigned long uaddr,
- enum dma_data_direction direction,
- struct dma_attrs *attrs)
+#ifdef CONFIG_IOMMU_API
+int pnv_tce_xchg(struct iommu_table *tbl, long index,
+ unsigned long *hpa, enum dma_data_direction *direction)
{
- return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs,
- false);
+ u64 proto_tce = iommu_direction_to_tce_perm(*direction);
+ unsigned long newtce = *hpa | proto_tce, oldtce;
+ unsigned long idx = index - tbl->it_offset;
+
+ BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl));
+
+ oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce));
+ *hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+ *direction = iommu_tce_direction(oldtce);
+
+ return 0;
}
+#endif
-static void pnv_tce_free(struct iommu_table *tbl, long index, long npages,
- bool rm)
+void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
{
- __be64 *tcep, *tces;
+ long i;
- tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset;
+ for (i = 0; i < npages; i++) {
+ unsigned long idx = index - tbl->it_offset + i;
- while (npages--)
- *(tcep++) = cpu_to_be64(0);
+ *(pnv_tce(tbl, idx)) = cpu_to_be64(0);
+ }
+}
- if (tbl->it_type & TCE_PCI_SWINV_FREE)
- pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
+unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
+{
+ return *(pnv_tce(tbl, index - tbl->it_offset));
}
-static void pnv_tce_free_vm(struct iommu_table *tbl, long index, long npages)
+struct iommu_table *pnv_pci_table_alloc(int nid)
{
- pnv_tce_free(tbl, index, npages, false);
+ struct iommu_table *tbl;
+
+ tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid);
+ INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+
+ return tbl;
}
-static unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
+long pnv_pci_link_table_and_group(int node, int num,
+ struct iommu_table *tbl,
+ struct iommu_table_group *table_group)
{
- return ((u64 *)tbl->it_base)[index - tbl->it_offset];
+ struct iommu_table_group_link *tgl = NULL;
+
+ if (WARN_ON(!tbl || !table_group))
+ return -EINVAL;
+
+ tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL,
+ node);
+ if (!tgl)
+ return -ENOMEM;
+
+ tgl->table_group = table_group;
+ list_add_rcu(&tgl->next, &tbl->it_group_list);
+
+ table_group->tables[num] = tbl;
+
+ return 0;
}
-static int pnv_tce_build_rm(struct iommu_table *tbl, long index, long npages,
- unsigned long uaddr,
- enum dma_data_direction direction,
- struct dma_attrs *attrs)
+static void pnv_iommu_table_group_link_free(struct rcu_head *head)
{
- return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs, true);
+ struct iommu_table_group_link *tgl = container_of(head,
+ struct iommu_table_group_link, rcu);
+
+ kfree(tgl);
}
-static void pnv_tce_free_rm(struct iommu_table *tbl, long index, long npages)
+void pnv_pci_unlink_table_and_group(struct iommu_table *tbl,
+ struct iommu_table_group *table_group)
{
- pnv_tce_free(tbl, index, npages, true);
+ long i;
+ bool found;
+ struct iommu_table_group_link *tgl;
+
+ if (!tbl || !table_group)
+ return;
+
+ /* Remove link to a group from table's list of attached groups */
+ found = false;
+ list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+ if (tgl->table_group == table_group) {
+ list_del_rcu(&tgl->next);
+ call_rcu(&tgl->rcu, pnv_iommu_table_group_link_free);
+ found = true;
+ break;
+ }
+ }
+ if (WARN_ON(!found))
+ return;
+
+ /* Clean a pointer to iommu_table in iommu_table_group::tables[] */
+ found = false;
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ if (table_group->tables[i] == tbl) {
+ table_group->tables[i] = NULL;
+ found = true;
+ break;
+ }
+ }
+ WARN_ON(!found);
}
void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
@@ -662,7 +734,7 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
tbl->it_type = TCE_PCI;
}
-static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
+void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
{
struct pci_controller *hose = pci_bus_to_host(pdev->bus);
struct pnv_phb *phb = hose->private_data;
@@ -689,16 +761,6 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
phb->dma_dev_setup(phb, pdev);
}
-int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
-{
- struct pci_controller *hose = pci_bus_to_host(pdev->bus);
- struct pnv_phb *phb = hose->private_data;
-
- if (phb && phb->dma_set_mask)
- return phb->dma_set_mask(phb, pdev, dma_mask);
- return __dma_set_mask(&pdev->dev, dma_mask);
-}
-
u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
{
struct pci_controller *hose = pci_bus_to_host(pdev->bus);
@@ -714,12 +776,9 @@ void pnv_pci_shutdown(void)
{
struct pci_controller *hose;
- list_for_each_entry(hose, &hose_list, list_node) {
- struct pnv_phb *phb = hose->private_data;
-
- if (phb && phb->shutdown)
- phb->shutdown(phb);
- }
+ list_for_each_entry(hose, &hose_list, list_node)
+ if (hose->controller_ops.shutdown)
+ hose->controller_ops.shutdown(hose);
}
/* Fixup wrong class code in p7ioc and p8 root complex */
@@ -762,22 +821,7 @@ void __init pnv_pci_init(void)
pci_devs_phb_init();
/* Configure IOMMU DMA hooks */
- ppc_md.tce_build = pnv_tce_build_vm;
- ppc_md.tce_free = pnv_tce_free_vm;
- ppc_md.tce_build_rm = pnv_tce_build_rm;
- ppc_md.tce_free_rm = pnv_tce_free_rm;
- ppc_md.tce_get = pnv_tce_get;
set_pci_dma_ops(&dma_iommu_ops);
-
- /* Configure MSIs */
-#ifdef CONFIG_PCI_MSI
- ppc_md.setup_msi_irqs = pnv_setup_msi_irqs;
- ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
-#endif
}
machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init);
-
-struct pci_controller_ops pnv_pci_controller_ops = {
- .dma_dev_setup = pnv_pci_dma_dev_setup,
-};
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 070ee888fc95..8ef2d28aded0 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -57,8 +57,7 @@ struct pnv_ioda_pe {
/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
int tce32_seg;
int tce32_segcount;
- struct iommu_table *tce32_table;
- phys_addr_t tce_inval_reg_phys;
+ struct iommu_table_group table_group;
/* 64-bit TCE bypass region */
bool tce_bypass_enabled;
@@ -106,13 +105,10 @@ struct pnv_phb {
unsigned int hwirq, unsigned int virq,
unsigned int is_64, struct msi_msg *msg);
void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
- int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
- u64 dma_mask);
u64 (*dma_get_required_mask)(struct pnv_phb *phb,
struct pci_dev *pdev);
void (*fixup_phb)(struct pci_controller *hose);
u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
- void (*shutdown)(struct pnv_phb *phb);
int (*init_m64)(struct pnv_phb *phb);
void (*reserve_m64_pe)(struct pnv_phb *phb);
int (*pick_m64_pe)(struct pnv_phb *phb, struct pci_bus *bus, int all);
@@ -123,6 +119,7 @@ struct pnv_phb {
union {
struct {
struct iommu_table iommu_table;
+ struct iommu_table_group table_group;
} p5ioc2;
struct {
@@ -186,6 +183,12 @@ struct pnv_phb {
* boot for resource allocation purposes
*/
struct list_head pe_dma_list;
+
+ /* TCE cache invalidate registers (physical and
+ * remapped)
+ */
+ phys_addr_t tce_inval_reg_phys;
+ __be64 __iomem *tce_inval_reg;
} ioda;
};
@@ -200,6 +203,13 @@ struct pnv_phb {
};
extern struct pci_ops pnv_pci_ops;
+extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
+ unsigned long uaddr, enum dma_data_direction direction,
+ struct dma_attrs *attrs);
+extern void pnv_tce_free(struct iommu_table *tbl, long index, long npages);
+extern int pnv_tce_xchg(struct iommu_table *tbl, long index,
+ unsigned long *hpa, enum dma_data_direction *direction);
+extern unsigned long pnv_tce_get(struct iommu_table *tbl, long index);
void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
unsigned char *log_buff);
@@ -207,6 +217,13 @@ int pnv_pci_cfg_read(struct pci_dn *pdn,
int where, int size, u32 *val);
int pnv_pci_cfg_write(struct pci_dn *pdn,
int where, int size, u32 val);
+extern struct iommu_table *pnv_pci_table_alloc(int nid);
+
+extern long pnv_pci_link_table_and_group(int node, int num,
+ struct iommu_table *tbl,
+ struct iommu_table_group *table_group);
+extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl,
+ struct iommu_table_group *table_group);
extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
void *tce_mem, u64 tce_size,
u64 dma_offset, unsigned page_shift);
@@ -218,4 +235,8 @@ extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
+extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
+extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
+extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
+
#endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 826d2c9bea56..9269e30e4ca0 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -12,29 +12,24 @@ struct pci_dev;
#ifdef CONFIG_PCI
extern void pnv_pci_init(void);
extern void pnv_pci_shutdown(void);
-extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
extern u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev);
#else
static inline void pnv_pci_init(void) { }
static inline void pnv_pci_shutdown(void) { }
-static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
-{
- return -ENODEV;
-}
-
static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
{
return 0;
}
#endif
-extern struct pci_controller_ops pnv_pci_controller_ops;
-
extern u32 pnv_get_supported_cpuidle_states(void);
extern void pnv_lpc_init(void);
+extern void opal_handle_events(uint64_t events);
+extern void opal_event_shutdown(void);
+
bool cpu_core_split_required(void);
#endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 16fdcb23f4c3..53737e019ae3 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -35,12 +35,8 @@
#include <asm/opal.h>
#include <asm/kexec.h>
#include <asm/smp.h>
-#include <asm/cputhreads.h>
-#include <asm/cpuidle.h>
-#include <asm/code-patching.h>
#include "powernv.h"
-#include "subcore.h"
static void __init pnv_setup_arch(void)
{
@@ -111,7 +107,7 @@ static void pnv_prepare_going_down(void)
* Disable all notifiers from OPAL, we can't
* service interrupts anymore anyway
*/
- opal_notifier_disable();
+ opal_event_shutdown();
/* Soft disable interrupts */
local_irq_disable();
@@ -169,13 +165,6 @@ static void pnv_progress(char *s, unsigned short hex)
{
}
-static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
-{
- if (dev_is_pci(dev))
- return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask);
- return __dma_set_mask(dev, dma_mask);
-}
-
static u64 pnv_dma_get_required_mask(struct device *dev)
{
if (dev_is_pci(dev))
@@ -277,173 +266,6 @@ static void __init pnv_setup_machdep_opal(void)
ppc_md.handle_hmi_exception = opal_handle_hmi_exception;
}
-static u32 supported_cpuidle_states;
-
-int pnv_save_sprs_for_winkle(void)
-{
- int cpu;
- int rc;
-
- /*
- * hid0, hid1, hid4, hid5, hmeer and lpcr values are symmetric accross
- * all cpus at boot. Get these reg values of current cpu and use the
- * same accross all cpus.
- */
- uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
- uint64_t hid0_val = mfspr(SPRN_HID0);
- uint64_t hid1_val = mfspr(SPRN_HID1);
- uint64_t hid4_val = mfspr(SPRN_HID4);
- uint64_t hid5_val = mfspr(SPRN_HID5);
- uint64_t hmeer_val = mfspr(SPRN_HMEER);
-
- for_each_possible_cpu(cpu) {
- uint64_t pir = get_hard_smp_processor_id(cpu);
- uint64_t hsprg0_val = (uint64_t)&paca[cpu];
-
- /*
- * HSPRG0 is used to store the cpu's pointer to paca. Hence last
- * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0
- * with 63rd bit set, so that when a thread wakes up at 0x100 we
- * can use this bit to distinguish between fastsleep and
- * deep winkle.
- */
- hsprg0_val |= 1;
-
- rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
- if (rc != 0)
- return rc;
-
- rc = opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
- if (rc != 0)
- return rc;
-
- /* HIDs are per core registers */
- if (cpu_thread_in_core(cpu) == 0) {
-
- rc = opal_slw_set_reg(pir, SPRN_HMEER, hmeer_val);
- if (rc != 0)
- return rc;
-
- rc = opal_slw_set_reg(pir, SPRN_HID0, hid0_val);
- if (rc != 0)
- return rc;
-
- rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val);
- if (rc != 0)
- return rc;
-
- rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val);
- if (rc != 0)
- return rc;
-
- rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val);
- if (rc != 0)
- return rc;
- }
- }
-
- return 0;
-}
-
-static void pnv_alloc_idle_core_states(void)
-{
- int i, j;
- int nr_cores = cpu_nr_cores();
- u32 *core_idle_state;
-
- /*
- * core_idle_state - First 8 bits track the idle state of each thread
- * of the core. The 8th bit is the lock bit. Initially all thread bits
- * are set. They are cleared when the thread enters deep idle state
- * like sleep and winkle. Initially the lock bit is cleared.
- * The lock bit has 2 purposes
- * a. While the first thread is restoring core state, it prevents
- * other threads in the core from switching to process context.
- * b. While the last thread in the core is saving the core state, it
- * prevents a different thread from waking up.
- */
- for (i = 0; i < nr_cores; i++) {
- int first_cpu = i * threads_per_core;
- int node = cpu_to_node(first_cpu);
-
- core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
- *core_idle_state = PNV_CORE_IDLE_THREAD_BITS;
-
- for (j = 0; j < threads_per_core; j++) {
- int cpu = first_cpu + j;
-
- paca[cpu].core_idle_state_ptr = core_idle_state;
- paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
- paca[cpu].thread_mask = 1 << j;
- }
- }
-
- update_subcore_sibling_mask();
-
- if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED)
- pnv_save_sprs_for_winkle();
-}
-
-u32 pnv_get_supported_cpuidle_states(void)
-{
- return supported_cpuidle_states;
-}
-EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
-
-static int __init pnv_init_idle_states(void)
-{
- struct device_node *power_mgt;
- int dt_idle_states;
- u32 *flags;
- int i;
-
- supported_cpuidle_states = 0;
-
- if (cpuidle_disable != IDLE_NO_OVERRIDE)
- goto out;
-
- if (!firmware_has_feature(FW_FEATURE_OPALv3))
- goto out;
-
- power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
- if (!power_mgt) {
- pr_warn("opal: PowerMgmt Node not found\n");
- goto out;
- }
- dt_idle_states = of_property_count_u32_elems(power_mgt,
- "ibm,cpu-idle-state-flags");
- if (dt_idle_states < 0) {
- pr_warn("cpuidle-powernv: no idle states found in the DT\n");
- goto out;
- }
-
- flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
- if (of_property_read_u32_array(power_mgt,
- "ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
- pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
- goto out_free;
- }
-
- for (i = 0; i < dt_idle_states; i++)
- supported_cpuidle_states |= flags[i];
-
- if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
- patch_instruction(
- (unsigned int *)pnv_fastsleep_workaround_at_entry,
- PPC_INST_NOP);
- patch_instruction(
- (unsigned int *)pnv_fastsleep_workaround_at_exit,
- PPC_INST_NOP);
- }
- pnv_alloc_idle_core_states();
-out_free:
- kfree(flags);
-out:
- return 0;
-}
-
-subsys_initcall(pnv_init_idle_states);
-
static int __init pnv_probe(void)
{
unsigned long root = of_get_flat_dt_root();
@@ -492,7 +314,6 @@ define_machine(powernv) {
.machine_shutdown = pnv_shutdown,
.power_save = power7_idle,
.calibrate_decr = generic_calibrate_decr,
- .dma_set_mask = pnv_dma_set_mask,
.dma_get_required_mask = pnv_dma_get_required_mask,
#ifdef CONFIG_KEXEC
.kexec_cpu_down = pnv_kexec_cpu_down,
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 019d34aaf054..47d9cebe7159 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -421,11 +421,10 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
return -ENODEV;
dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent);
+ of_node_put(parent);
if (!dn)
return -EINVAL;
- of_node_put(parent);
-
rc = dlpar_attach_node(dn);
if (rc) {
dlpar_release_drc(drc_index);
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 2039397cc75d..1ba55d0bb449 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -519,7 +519,7 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option)
/**
* pseries_eeh_wait_state - Wait for PE state
* @pe: EEH PE
- * @max_wait: maximal period in microsecond
+ * @max_wait: maximal period in millisecond
*
* Wait for the state of associated PE. It might take some time
* to retrieve the PE's state.
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 61d5a17f45c0..10510dea16b3 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -36,6 +36,8 @@
#include <linux/crash_dump.h>
#include <linux/memory.h>
#include <linux/of.h>
+#include <linux/iommu.h>
+#include <linux/rculist.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/rtas.h>
@@ -51,6 +53,73 @@
#include "pseries.h"
+static struct iommu_table_group *iommu_pseries_alloc_group(int node)
+{
+ struct iommu_table_group *table_group = NULL;
+ struct iommu_table *tbl = NULL;
+ struct iommu_table_group_link *tgl = NULL;
+
+ table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL,
+ node);
+ if (!table_group)
+ goto fail_exit;
+
+ tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, node);
+ if (!tbl)
+ goto fail_exit;
+
+ tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL,
+ node);
+ if (!tgl)
+ goto fail_exit;
+
+ INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+ tgl->table_group = table_group;
+ list_add_rcu(&tgl->next, &tbl->it_group_list);
+
+ table_group->tables[0] = tbl;
+
+ return table_group;
+
+fail_exit:
+ kfree(tgl);
+ kfree(table_group);
+ kfree(tbl);
+
+ return NULL;
+}
+
+static void iommu_pseries_free_group(struct iommu_table_group *table_group,
+ const char *node_name)
+{
+ struct iommu_table *tbl;
+#ifdef CONFIG_IOMMU_API
+ struct iommu_table_group_link *tgl;
+#endif
+
+ if (!table_group)
+ return;
+
+ tbl = table_group->tables[0];
+#ifdef CONFIG_IOMMU_API
+ tgl = list_first_entry_or_null(&tbl->it_group_list,
+ struct iommu_table_group_link, next);
+
+ WARN_ON_ONCE(!tgl);
+ if (tgl) {
+ list_del_rcu(&tgl->next);
+ kfree(tgl);
+ }
+ if (table_group->group) {
+ iommu_group_put(table_group->group);
+ BUG_ON(table_group->group);
+ }
+#endif
+ iommu_free_table(tbl, node_name);
+
+ kfree(table_group);
+}
+
static void tce_invalidate_pSeries_sw(struct iommu_table *tbl,
__be64 *startp, __be64 *endp)
{
@@ -193,7 +262,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
int ret = 0;
unsigned long flags;
- if (npages == 1) {
+ if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) {
return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
direction, attrs);
}
@@ -285,6 +354,9 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n
{
u64 rc;
+ if (!firmware_has_feature(FW_FEATURE_MULTITCE))
+ return tce_free_pSeriesLP(tbl, tcenum, npages);
+
rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
if (rc && printk_ratelimit()) {
@@ -460,7 +532,6 @@ static int tce_setrange_multi_pSeriesLP_walk(unsigned long start_pfn,
return tce_setrange_multi_pSeriesLP(start_pfn, num_pfn, arg);
}
-
#ifdef CONFIG_PCI
static void iommu_table_setparms(struct pci_controller *phb,
struct device_node *dn,
@@ -546,6 +617,12 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
tbl->it_size = size >> tbl->it_page_shift;
}
+struct iommu_table_ops iommu_table_pseries_ops = {
+ .set = tce_build_pSeries,
+ .clear = tce_free_pSeries,
+ .get = tce_get_pseries
+};
+
static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
{
struct device_node *dn;
@@ -610,12 +687,13 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
pci->phb->dma_window_size = 0x8000000ul;
pci->phb->dma_window_base_cur = 0x8000000ul;
- tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
- pci->phb->node);
+ pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
+ tbl = pci->table_group->tables[0];
iommu_table_setparms(pci->phb, dn, tbl);
- pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
- iommu_register_group(tbl, pci_domain_nr(bus), 0);
+ tbl->it_ops = &iommu_table_pseries_ops;
+ iommu_init_table(tbl, pci->phb->node);
+ iommu_register_group(pci->table_group, pci_domain_nr(bus), 0);
/* Divide the rest (1.75GB) among the children */
pci->phb->dma_window_size = 0x80000000ul;
@@ -625,6 +703,11 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
pr_debug("ISA/IDE, window size is 0x%llx\n", pci->phb->dma_window_size);
}
+struct iommu_table_ops iommu_table_lpar_multi_ops = {
+ .set = tce_buildmulti_pSeriesLP,
+ .clear = tce_freemulti_pSeriesLP,
+ .get = tce_get_pSeriesLP
+};
static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
{
@@ -653,15 +736,17 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
ppci = PCI_DN(pdn);
pr_debug(" parent is %s, iommu_table: 0x%p\n",
- pdn->full_name, ppci->iommu_table);
+ pdn->full_name, ppci->table_group);
- if (!ppci->iommu_table) {
- tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
- ppci->phb->node);
+ if (!ppci->table_group) {
+ ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
+ tbl = ppci->table_group->tables[0];
iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
- ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
- iommu_register_group(tbl, pci_domain_nr(bus), 0);
- pr_debug(" created table: %p\n", ppci->iommu_table);
+ tbl->it_ops = &iommu_table_lpar_multi_ops;
+ iommu_init_table(tbl, ppci->phb->node);
+ iommu_register_group(ppci->table_group,
+ pci_domain_nr(bus), 0);
+ pr_debug(" created table: %p\n", ppci->table_group);
}
}
@@ -683,13 +768,15 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
struct pci_controller *phb = PCI_DN(dn)->phb;
pr_debug(" --> first child, no bridge. Allocating iommu table.\n");
- tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
- phb->node);
+ PCI_DN(dn)->table_group = iommu_pseries_alloc_group(phb->node);
+ tbl = PCI_DN(dn)->table_group->tables[0];
iommu_table_setparms(phb, dn, tbl);
- PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
- iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
- set_iommu_table_base_and_group(&dev->dev,
- PCI_DN(dn)->iommu_table);
+ tbl->it_ops = &iommu_table_pseries_ops;
+ iommu_init_table(tbl, phb->node);
+ iommu_register_group(PCI_DN(dn)->table_group,
+ pci_domain_nr(phb->bus), 0);
+ set_iommu_table_base(&dev->dev, tbl);
+ iommu_add_device(&dev->dev);
return;
}
@@ -697,13 +784,14 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
* an already allocated iommu table is found and use that.
*/
- while (dn && PCI_DN(dn) && PCI_DN(dn)->iommu_table == NULL)
+ while (dn && PCI_DN(dn) && PCI_DN(dn)->table_group == NULL)
dn = dn->parent;
- if (dn && PCI_DN(dn))
- set_iommu_table_base_and_group(&dev->dev,
- PCI_DN(dn)->iommu_table);
- else
+ if (dn && PCI_DN(dn)) {
+ set_iommu_table_base(&dev->dev,
+ PCI_DN(dn)->table_group->tables[0]);
+ iommu_add_device(&dev->dev);
+ } else
printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
pci_name(dev));
}
@@ -1088,7 +1176,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
dn = pci_device_to_OF_node(dev);
pr_debug(" node is %s\n", dn->full_name);
- for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
+ for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
pdn = pdn->parent) {
dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
if (dma_window)
@@ -1104,18 +1192,21 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
pr_debug(" parent is %s\n", pdn->full_name);
pci = PCI_DN(pdn);
- if (!pci->iommu_table) {
- tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
- pci->phb->node);
+ if (!pci->table_group) {
+ pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
+ tbl = pci->table_group->tables[0];
iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
- pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
- iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0);
- pr_debug(" created table: %p\n", pci->iommu_table);
+ tbl->it_ops = &iommu_table_lpar_multi_ops;
+ iommu_init_table(tbl, pci->phb->node);
+ iommu_register_group(pci->table_group,
+ pci_domain_nr(pci->phb->bus), 0);
+ pr_debug(" created table: %p\n", pci->table_group);
} else {
- pr_debug(" found DMA window, table: %p\n", pci->iommu_table);
+ pr_debug(" found DMA window, table: %p\n", pci->table_group);
}
- set_iommu_table_base_and_group(&dev->dev, pci->iommu_table);
+ set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
+ iommu_add_device(&dev->dev);
}
static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
@@ -1145,7 +1236,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
* search upwards in the tree until we either hit a dma-window
* property, OR find a parent with a table already allocated.
*/
- for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
+ for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
pdn = pdn->parent) {
dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
if (dma_window)
@@ -1189,7 +1280,7 @@ static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
dn = pci_device_to_OF_node(pdev);
/* search upwards for ibm,dma-window */
- for (; dn && PCI_DN(dn) && !PCI_DN(dn)->iommu_table;
+ for (; dn && PCI_DN(dn) && !PCI_DN(dn)->table_group;
dn = dn->parent)
if (of_get_property(dn, "ibm,dma-window", NULL))
break;
@@ -1269,8 +1360,9 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
* the device node.
*/
remove_ddw(np, false);
- if (pci && pci->iommu_table)
- iommu_free_table(pci->iommu_table, np->full_name);
+ if (pci && pci->table_group)
+ iommu_pseries_free_group(pci->table_group,
+ np->full_name);
spin_lock(&direct_window_list_lock);
list_for_each_entry(window, &direct_window_list, list) {
@@ -1300,22 +1392,11 @@ void iommu_init_early_pSeries(void)
return;
if (firmware_has_feature(FW_FEATURE_LPAR)) {
- if (firmware_has_feature(FW_FEATURE_MULTITCE)) {
- ppc_md.tce_build = tce_buildmulti_pSeriesLP;
- ppc_md.tce_free = tce_freemulti_pSeriesLP;
- } else {
- ppc_md.tce_build = tce_build_pSeriesLP;
- ppc_md.tce_free = tce_free_pSeriesLP;
- }
- ppc_md.tce_get = tce_get_pSeriesLP;
pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
} else {
- ppc_md.tce_build = tce_build_pSeries;
- ppc_md.tce_free = tce_free_pSeries;
- ppc_md.tce_get = tce_get_pseries;
pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries;
pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries;
}
@@ -1333,8 +1414,6 @@ static int __init disable_multitce(char *str)
firmware_has_feature(FW_FEATURE_LPAR) &&
firmware_has_feature(FW_FEATURE_MULTITCE)) {
printk(KERN_INFO "Disabling MULTITCE firmware feature\n");
- ppc_md.tce_build = tce_build_pSeriesLP;
- ppc_md.tce_free = tce_free_pSeriesLP;
powerpc_firmware_features &= ~FW_FEATURE_MULTITCE;
}
return 1;
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index c8d24f9a6948..c22bb647cce6 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -18,6 +18,8 @@
#include <asm/ppc-pci.h>
#include <asm/machdep.h>
+#include "pseries.h"
+
static int query_token, change_token;
#define RTAS_QUERY_FN 0
@@ -505,6 +507,8 @@ static void rtas_msi_pci_irq_fixup(struct pci_dev *pdev)
static int rtas_msi_init(void)
{
+ struct pci_controller *phb;
+
query_token = rtas_token("ibm,query-interrupt-source-number");
change_token = rtas_token("ibm,change-msi");
@@ -516,9 +520,15 @@ static int rtas_msi_init(void)
pr_debug("rtas_msi: Registering RTAS MSI callbacks.\n");
- WARN_ON(ppc_md.setup_msi_irqs);
- ppc_md.setup_msi_irqs = rtas_setup_msi_irqs;
- ppc_md.teardown_msi_irqs = rtas_teardown_msi_irqs;
+ WARN_ON(pseries_pci_controller_ops.setup_msi_irqs);
+ pseries_pci_controller_ops.setup_msi_irqs = rtas_setup_msi_irqs;
+ pseries_pci_controller_ops.teardown_msi_irqs = rtas_teardown_msi_irqs;
+
+ list_for_each_entry(phb, &hose_list, list_node) {
+ WARN_ON(phb->controller_ops.setup_msi_irqs);
+ phb->controller_ops.setup_msi_irqs = rtas_setup_msi_irqs;
+ phb->controller_ops.teardown_msi_irqs = rtas_teardown_msi_irqs;
+ }
WARN_ON(ppc_md.pci_irq_fixup);
ppc_md.pci_irq_fixup = rtas_msi_pci_irq_fixup;
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index f7cb2a1b01fa..5b492a6438ff 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -2,7 +2,7 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-mpic-msi-obj-$(CONFIG_PCI_MSI) += mpic_msi.o mpic_u3msi.o mpic_pasemi_msi.o
+mpic-msi-obj-$(CONFIG_PCI_MSI) += mpic_msi.o mpic_u3msi.o
obj-$(CONFIG_MPIC) += mpic.o $(mpic-msi-obj-y)
obj-$(CONFIG_MPIC_TIMER) += mpic_timer.o
obj-$(CONFIG_FSL_MPIC_TIMER_WAKEUP) += fsl_mpic_timer_wakeup.o
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index d00a5663e312..90bcdfeedf48 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -286,6 +286,12 @@ static int __init dart_init(struct device_node *dart_node)
return 0;
}
+static struct iommu_table_ops iommu_dart_ops = {
+ .set = dart_build,
+ .clear = dart_free,
+ .flush = dart_flush,
+};
+
static void iommu_table_dart_setup(void)
{
iommu_table_dart.it_busno = 0;
@@ -298,6 +304,7 @@ static void iommu_table_dart_setup(void)
iommu_table_dart.it_base = (unsigned long)dart_vbase;
iommu_table_dart.it_index = 0;
iommu_table_dart.it_blocksize = 1;
+ iommu_table_dart.it_ops = &iommu_dart_ops;
iommu_init_table(&iommu_table_dart, -1);
/* Reserve the last page of the DART to avoid possible prefetch
@@ -386,11 +393,6 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
if (dart_init(dn) != 0)
goto bail;
- /* Setup low level TCE operations for the core IOMMU code */
- ppc_md.tce_build = dart_build;
- ppc_md.tce_free = dart_free;
- ppc_md.tce_flush = dart_flush;
-
/* Setup bypass if supported */
if (dart_is_u4)
ppc_md.dma_set_mask = dart_dma_set_mask;
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index f086c6f22dc9..5236e5427c38 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -405,6 +405,7 @@ static int fsl_of_msi_probe(struct platform_device *dev)
const struct fsl_msi_feature *features;
int len;
u32 offset;
+ struct pci_controller *phb;
match = of_match_device(fsl_of_msi_ids, &dev->dev);
if (!match)
@@ -541,14 +542,20 @@ static int fsl_of_msi_probe(struct platform_device *dev)
list_add_tail(&msi->list, &msi_head);
- /* The multiple setting ppc_md.setup_msi_irqs will not harm things */
- if (!ppc_md.setup_msi_irqs) {
- ppc_md.setup_msi_irqs = fsl_setup_msi_irqs;
- ppc_md.teardown_msi_irqs = fsl_teardown_msi_irqs;
- } else if (ppc_md.setup_msi_irqs != fsl_setup_msi_irqs) {
- dev_err(&dev->dev, "Different MSI driver already installed!\n");
- err = -ENODEV;
- goto error_out;
+ /*
+ * Apply the MSI ops to all the controllers.
+ * It doesn't hurt to reassign the same ops,
+ * but bail out if we find another MSI driver.
+ */
+ list_for_each_entry(phb, &hose_list, list_node) {
+ if (!phb->controller_ops.setup_msi_irqs) {
+ phb->controller_ops.setup_msi_irqs = fsl_setup_msi_irqs;
+ phb->controller_ops.teardown_msi_irqs = fsl_teardown_msi_irqs;
+ } else if (phb->controller_ops.setup_msi_irqs != fsl_setup_msi_irqs) {
+ dev_err(&dev->dev, "Different MSI driver already installed!\n");
+ err = -ENODEV;
+ goto error_out;
+ }
}
return 0;
error_out:
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index 45598da0b321..31c33475c7b7 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -204,7 +204,7 @@ static int i8259_host_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops i8259_host_ops = {
+static const struct irq_domain_ops i8259_host_ops = {
.match = i8259_host_match,
.map = i8259_host_map,
.xlate = i8259_host_xlate,
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index b28733727ed3..d78f1364b639 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -691,7 +691,7 @@ static int ipic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops ipic_host_ops = {
+static const struct irq_domain_ops ipic_host_ops = {
.match = ipic_host_match,
.map = ipic_host_map,
.xlate = irq_domain_xlate_onetwocell,
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index c4828c0be5bd..d93a78be4346 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -120,7 +120,7 @@ static int mpc8xx_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
}
-static struct irq_domain_ops mpc8xx_pic_host_ops = {
+static const struct irq_domain_ops mpc8xx_pic_host_ops = {
.map = mpc8xx_pic_host_map,
.xlate = mpc8xx_pic_host_xlate,
};
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index b2b8447a227a..c8e73332eaad 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1195,7 +1195,7 @@ static void mpic_cascade(unsigned int irq, struct irq_desc *desc)
chip->irq_eoi(&desc->irq_data);
}
-static struct irq_domain_ops mpic_host_ops = {
+static const struct irq_domain_ops mpic_host_ops = {
.match = mpic_host_match,
.map = mpic_host_map,
.xlate = mpic_host_xlate,
diff --git a/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h
index 24bf07a63924..32971a41853b 100644
--- a/arch/powerpc/sysdev/mpic.h
+++ b/arch/powerpc/sysdev/mpic.h
@@ -15,7 +15,6 @@
extern void mpic_msi_reserve_hwirq(struct mpic *mpic, irq_hw_number_t hwirq);
extern int mpic_msi_init_allocator(struct mpic *mpic);
extern int mpic_u3msi_init(struct mpic *mpic);
-extern int mpic_pasemi_msi_init(struct mpic *mpic);
#else
static inline void mpic_msi_reserve_hwirq(struct mpic *mpic,
irq_hw_number_t hwirq)
@@ -27,11 +26,12 @@ static inline int mpic_u3msi_init(struct mpic *mpic)
{
return -1;
}
+#endif
-static inline int mpic_pasemi_msi_init(struct mpic *mpic)
-{
- return -1;
-}
+#if defined(CONFIG_PCI_MSI) && defined(CONFIG_PPC_PASEMI)
+int mpic_pasemi_msi_init(struct mpic *mpic);
+#else
+static inline int mpic_pasemi_msi_init(struct mpic *mpic) { return -1; }
#endif
extern int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type);
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index b2cef1809389..fc46ef3b816e 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -181,6 +181,7 @@ static int u3msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
int mpic_u3msi_init(struct mpic *mpic)
{
int rc;
+ struct pci_controller *phb;
rc = mpic_msi_init_allocator(mpic);
if (rc) {
@@ -193,9 +194,11 @@ int mpic_u3msi_init(struct mpic *mpic)
BUG_ON(msi_mpic);
msi_mpic = mpic;
- WARN_ON(ppc_md.setup_msi_irqs);
- ppc_md.setup_msi_irqs = u3msi_setup_msi_irqs;
- ppc_md.teardown_msi_irqs = u3msi_teardown_msi_irqs;
+ list_for_each_entry(phb, &hose_list, list_node) {
+ WARN_ON(phb->controller_ops.setup_msi_irqs);
+ phb->controller_ops.setup_msi_irqs = u3msi_setup_msi_irqs;
+ phb->controller_ops.teardown_msi_irqs = u3msi_teardown_msi_irqs;
+ }
return 0;
}
diff --git a/arch/powerpc/sysdev/mv64x60_pic.c b/arch/powerpc/sysdev/mv64x60_pic.c
index 8848e99a83f2..0f842dd16bcd 100644
--- a/arch/powerpc/sysdev/mv64x60_pic.c
+++ b/arch/powerpc/sysdev/mv64x60_pic.c
@@ -223,7 +223,7 @@ static int mv64x60_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops mv64x60_host_ops = {
+static const struct irq_domain_ops mv64x60_host_ops = {
.map = mv64x60_host_map,
};
diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
index f366d2d4c079..2bc33674ebfc 100644
--- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
@@ -128,6 +128,7 @@ static int hsta_msi_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct resource *mem;
int irq, ret, irq_count;
+ struct pci_controller *phb;
mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (IS_ERR(mem)) {
@@ -171,8 +172,10 @@ static int hsta_msi_probe(struct platform_device *pdev)
}
}
- ppc_md.setup_msi_irqs = hsta_setup_msi_irqs;
- ppc_md.teardown_msi_irqs = hsta_teardown_msi_irqs;
+ list_for_each_entry(phb, &hose_list, list_node) {
+ phb->controller_ops.setup_msi_irqs = hsta_setup_msi_irqs;
+ phb->controller_ops.teardown_msi_irqs = hsta_teardown_msi_irqs;
+ }
return 0;
out2:
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 6e2e6aa378bb..6eb21f2ea585 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -218,6 +218,7 @@ static int ppc4xx_msi_probe(struct platform_device *dev)
struct ppc4xx_msi *msi;
struct resource res;
int err = 0;
+ struct pci_controller *phb;
dev_dbg(&dev->dev, "PCIE-MSI: Setting up MSI support...\n");
@@ -250,8 +251,10 @@ static int ppc4xx_msi_probe(struct platform_device *dev)
}
ppc4xx_msi = *msi;
- ppc_md.setup_msi_irqs = ppc4xx_setup_msi_irqs;
- ppc_md.teardown_msi_irqs = ppc4xx_teardown_msi_irqs;
+ list_for_each_entry(phb, &hose_list, list_node) {
+ phb->controller_ops.setup_msi_irqs = ppc4xx_setup_msi_irqs;
+ phb->controller_ops.teardown_msi_irqs = ppc4xx_teardown_msi_irqs;
+ }
return err;
error_out:
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index 543765e1ef14..6512cd8caa51 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -271,7 +271,7 @@ static int qe_ic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops qe_ic_host_ops = {
+static const struct irq_domain_ops qe_ic_host_ops = {
.match = qe_ic_host_match,
.map = qe_ic_host_map,
.xlate = irq_domain_xlate_onetwocell,
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 188012c58f7f..57b54476e747 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -397,7 +397,7 @@ static int pci_irq_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops pci_irq_domain_ops = {
+static const struct irq_domain_ops pci_irq_domain_ops = {
.map = pci_irq_host_map,
.xlate = pci_irq_host_xlate,
};
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 7c37157d4c24..d77345338671 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -189,7 +189,7 @@ static int uic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops uic_host_ops = {
+static const struct irq_domain_ops uic_host_ops = {
.map = uic_host_map,
.xlate = irq_domain_xlate_twocell,
};
@@ -198,7 +198,7 @@ void uic_irq_cascade(unsigned int virq, struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
struct irq_data *idata = irq_desc_get_irq_data(desc);
- struct uic *uic = irq_get_handler_data(virq);
+ struct uic *uic = irq_desc_get_handler_data(desc);
u32 msr;
int src;
int subvirq;
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 2fc4cf1b7557..eae32654bdf2 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -147,12 +147,16 @@ static void icp_native_cause_ipi(int cpu, unsigned long data)
{
kvmppc_set_host_ipi(cpu, 1);
#ifdef CONFIG_PPC_DOORBELL
- if (cpu_has_feature(CPU_FTR_DBELL) &&
- (cpumask_test_cpu(cpu, cpu_sibling_mask(smp_processor_id()))))
- doorbell_cause_ipi(cpu, data);
- else
+ if (cpu_has_feature(CPU_FTR_DBELL)) {
+ if (cpumask_test_cpu(cpu, cpu_sibling_mask(get_cpu()))) {
+ doorbell_cause_ipi(cpu, data);
+ put_cpu();
+ return;
+ }
+ put_cpu();
+ }
#endif
- icp_native_set_qirr(cpu, IPI_PRIORITY);
+ icp_native_set_qirr(cpu, IPI_PRIORITY);
}
/*
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 878a54036a25..08c248eb491b 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -227,7 +227,7 @@ void xics_migrate_irqs_away(void)
/* Locate interrupt server */
server = -1;
- ics = irq_get_chip_data(virq);
+ ics = irq_desc_get_chip_data(desc);
if (ics)
server = ics->get_server(ics, irq);
if (server < 0) {
@@ -360,7 +360,7 @@ static int xics_host_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops xics_host_ops = {
+static const struct irq_domain_ops xics_host_ops = {
.match = xics_host_match,
.map = xics_host_map,
.xlate = xics_host_xlate,
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index 56f0524e47a6..43b8b275bc5c 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -179,7 +179,7 @@ static int xilinx_intc_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops xilinx_intc_ops = {
+static const struct irq_domain_ops xilinx_intc_ops = {
.map = xilinx_intc_map,
.xlate = xilinx_intc_xlate,
};
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index 7940dc90e80b..b258110da952 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -16,11 +16,12 @@
#define GHASH_DIGEST_SIZE 16
struct ghash_ctx {
- u8 icv[16];
- u8 key[16];
+ u8 key[GHASH_BLOCK_SIZE];
};
struct ghash_desc_ctx {
+ u8 icv[GHASH_BLOCK_SIZE];
+ u8 key[GHASH_BLOCK_SIZE];
u8 buffer[GHASH_BLOCK_SIZE];
u32 bytes;
};
@@ -28,8 +29,10 @@ struct ghash_desc_ctx {
static int ghash_init(struct shash_desc *desc)
{
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+ struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
memset(dctx, 0, sizeof(*dctx));
+ memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE);
return 0;
}
@@ -45,7 +48,6 @@ static int ghash_setkey(struct crypto_shash *tfm,
}
memcpy(ctx->key, key, GHASH_BLOCK_SIZE);
- memset(ctx->icv, 0, GHASH_BLOCK_SIZE);
return 0;
}
@@ -54,7 +56,6 @@ static int ghash_update(struct shash_desc *desc,
const u8 *src, unsigned int srclen)
{
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
- struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
unsigned int n;
u8 *buf = dctx->buffer;
int ret;
@@ -70,7 +71,7 @@ static int ghash_update(struct shash_desc *desc,
src += n;
if (!dctx->bytes) {
- ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf,
+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf,
GHASH_BLOCK_SIZE);
if (ret != GHASH_BLOCK_SIZE)
return -EIO;
@@ -79,7 +80,7 @@ static int ghash_update(struct shash_desc *desc,
n = srclen & ~(GHASH_BLOCK_SIZE - 1);
if (n) {
- ret = crypt_s390_kimd(KIMD_GHASH, ctx, src, n);
+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, src, n);
if (ret != n)
return -EIO;
src += n;
@@ -94,7 +95,7 @@ static int ghash_update(struct shash_desc *desc,
return 0;
}
-static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+static int ghash_flush(struct ghash_desc_ctx *dctx)
{
u8 *buf = dctx->buffer;
int ret;
@@ -104,24 +105,24 @@ static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
memset(pos, 0, dctx->bytes);
- ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, GHASH_BLOCK_SIZE);
+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE);
if (ret != GHASH_BLOCK_SIZE)
return -EIO;
+
+ dctx->bytes = 0;
}
- dctx->bytes = 0;
return 0;
}
static int ghash_final(struct shash_desc *desc, u8 *dst)
{
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
- struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
int ret;
- ret = ghash_flush(ctx, dctx);
+ ret = ghash_flush(dctx);
if (!ret)
- memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE);
+ memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE);
return ret;
}
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 1f374b39a4ec..9d5192c94963 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -125,7 +125,7 @@ static int generate_entropy(u8 *ebuf, size_t nbytes)
/* fill page with urandom bytes */
get_random_bytes(pg, PAGE_SIZE);
/* exor page with stckf values */
- for (n = 0; n < sizeof(PAGE_SIZE/sizeof(u64)); n++) {
+ for (n = 0; n < PAGE_SIZE / sizeof(u64); n++) {
u64 *p = ((u64 *)pg) + n;
*p ^= get_tod_clock_fast();
}
diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c
index f043c3c7e73c..dd42a26d049d 100644
--- a/arch/s390/hypfs/hypfs_sprp.c
+++ b/arch/s390/hypfs/hypfs_sprp.c
@@ -128,14 +128,14 @@ static struct hypfs_dbfs_file hypfs_sprp_file = {
int hypfs_sprp_init(void)
{
- if (!sclp_has_sprp())
+ if (!sclp.has_sprp)
return 0;
return hypfs_dbfs_create_file(&hypfs_sprp_file);
}
void hypfs_sprp_exit(void)
{
- if (!sclp_has_sprp())
+ if (!sclp.has_sprp)
return;
hypfs_dbfs_remove_file(&hypfs_sprp_file);
}
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 8d724718ec21..e6f8615a11eb 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
-#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
#define smp_store_release(p, v) \
do { \
diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h
index 4eadec466b8c..411464f4c97a 100644
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -32,8 +32,6 @@
__old; \
})
-#define __HAVE_ARCH_CMPXCHG
-
#define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn) \
({ \
register __typeof__(*(p1)) __old1 asm("2") = (o1); \
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 30fd5c84680e..cb5fdf3a78fc 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -29,6 +29,7 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
#define ioremap_nocache(addr, size) ioremap(addr, size)
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
{
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index d01fc588b5c3..3024acbe1f9d 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -80,6 +80,7 @@ struct sca_block {
#define CPUSTAT_MCDS 0x00000100
#define CPUSTAT_SM 0x00000080
#define CPUSTAT_IBS 0x00000040
+#define CPUSTAT_GED2 0x00000010
#define CPUSTAT_G 0x00000008
#define CPUSTAT_GED 0x00000004
#define CPUSTAT_J 0x00000002
@@ -95,7 +96,8 @@ struct kvm_s390_sie_block {
#define PROG_IN_SIE (1<<0)
__u32 prog0c; /* 0x000c */
__u8 reserved10[16]; /* 0x0010 */
-#define PROG_BLOCK_SIE 0x00000001
+#define PROG_BLOCK_SIE (1<<0)
+#define PROG_REQUEST (1<<1)
atomic_t prog20; /* 0x0020 */
__u8 reserved24[4]; /* 0x0024 */
__u64 cputm; /* 0x0028 */
@@ -634,7 +636,7 @@ static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_free_memslot(struct kvm *kvm,
struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot) {}
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index fc642399b489..0bb2da79adf3 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -494,7 +494,7 @@ static inline int pmd_large(pmd_t pmd)
return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
}
-static inline int pmd_pfn(pmd_t pmd)
+static inline unsigned long pmd_pfn(pmd_t pmd)
{
unsigned long origin_mask;
@@ -1565,9 +1565,9 @@ static inline int has_transparent_hugepage(void)
/*
* 64 bit swap entry format:
* A page-table entry has some bits we have to treat in a special way.
- * Bits 52 and bit 55 have to be zero, otherwise an specification
+ * Bits 52 and bit 55 have to be zero, otherwise a specification
* exception will occur instead of a page translation exception. The
- * specifiation exception has the bad habit not to store necessary
+ * specification exception has the bad habit not to store necessary
* information in the lowcore.
* Bits 54 and 63 are used to indicate the page type.
* A swap pte is indicated by bit pattern (pte & 0x201) == 0x200
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index f1096bab5199..c891f41b2753 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -46,33 +46,39 @@ struct sclp_cpu_info {
struct sclp_cpu_entry cpu[MAX_CPU_ADDRESS + 1];
};
+struct sclp_info {
+ unsigned char has_linemode : 1;
+ unsigned char has_vt220 : 1;
+ unsigned char has_siif : 1;
+ unsigned char has_sigpif : 1;
+ unsigned char has_cpu_type : 1;
+ unsigned char has_sprp : 1;
+ unsigned int ibc;
+ unsigned int mtid;
+ unsigned int mtid_cp;
+ unsigned int mtid_prev;
+ unsigned long long rzm;
+ unsigned long long rnmax;
+ unsigned long long hamax;
+ unsigned int max_cpu;
+ unsigned long hsa_size;
+ unsigned long long facilities;
+};
+extern struct sclp_info sclp;
+
int sclp_get_cpu_info(struct sclp_cpu_info *info);
int sclp_cpu_configure(u8 cpu);
int sclp_cpu_deconfigure(u8 cpu);
-unsigned long long sclp_get_rnmax(void);
-unsigned long long sclp_get_rzm(void);
-unsigned int sclp_get_max_cpu(void);
-unsigned int sclp_get_mtid(u8 cpu_type);
-unsigned int sclp_get_mtid_max(void);
-unsigned int sclp_get_mtid_prev(void);
int sclp_sdias_blk_count(void);
int sclp_sdias_copy(void *dest, int blk_num, int nr_blks);
int sclp_chp_configure(struct chp_id chpid);
int sclp_chp_deconfigure(struct chp_id chpid);
int sclp_chp_read_info(struct sclp_chp_info *info);
void sclp_get_ipl_info(struct sclp_ipl_info *info);
-bool __init sclp_has_linemode(void);
-bool __init sclp_has_vt220(void);
-bool sclp_has_sprp(void);
int sclp_pci_configure(u32 fid);
int sclp_pci_deconfigure(u32 fid);
int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
-unsigned long sclp_get_hsa_size(void);
void sclp_early_detect(void);
-int sclp_has_siif(void);
-int sclp_has_sigpif(void);
-unsigned int sclp_get_ibc(void);
-
long _sclp_print_early(const char *);
#endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 98eb2a579223..dcb6312a0b91 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -10,6 +10,7 @@
#define _ASM_S390_TIMEX_H
#include <asm/lowcore.h>
+#include <linux/time64.h>
/* The value of the TOD clock for 1.1.1970. */
#define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -108,10 +109,10 @@ int get_sync_clock(unsigned long long *clock);
void init_cpu_timer(void);
unsigned long long monotonic_clock(void);
-void tod_to_timeval(__u64, struct timespec *);
+void tod_to_timeval(__u64 todval, struct timespec64 *xt);
static inline
-void stck_to_timespec(unsigned long long stck, struct timespec *ts)
+void stck_to_timespec64(unsigned long long stck, struct timespec64 *ts)
{
tod_to_timeval(stck - TOD_UNIX_EPOCH, ts);
}
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index b1453a2ae1ca..4990f6c66288 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -22,7 +22,8 @@ DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology);
#define topology_physical_package_id(cpu) (per_cpu(cpu_topology, cpu).socket_id)
#define topology_thread_id(cpu) (per_cpu(cpu_topology, cpu).thread_id)
-#define topology_thread_cpumask(cpu) (&per_cpu(cpu_topology, cpu).thread_mask)
+#define topology_sibling_cpumask(cpu) \
+ (&per_cpu(cpu_topology, cpu).thread_mask)
#define topology_core_id(cpu) (per_cpu(cpu_topology, cpu).core_id)
#define topology_core_cpumask(cpu) (&per_cpu(cpu_topology, cpu).core_mask)
#define topology_book_id(cpu) (per_cpu(cpu_topology, cpu).book_id)
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index d64a7a62164f..9dd4cc47ddc7 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -98,7 +98,8 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x)
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -118,7 +119,8 @@ unsigned long __must_check __copy_from_user(void *to, const void __user *from,
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -264,7 +266,8 @@ int __get_user_bad(void) __attribute__((noreturn));
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space.
*
@@ -290,7 +293,8 @@ __compiletime_warning("copy_from_user() buffer size is not provably correct")
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space.
*
@@ -348,7 +352,8 @@ static inline unsigned long strnlen_user(const char __user *src, unsigned long n
* strlen_user: - Get the size of a string in user space.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 9f73c8059022..d9f0dcfcae5e 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -122,7 +122,7 @@ static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize,
{
int rc;
- if (src < sclp_get_hsa_size()) {
+ if (src < sclp.hsa_size) {
rc = memcpy_hsa(buf, src, csize, userbuf);
} else {
if (userbuf)
@@ -215,7 +215,7 @@ static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
unsigned long pfn,
unsigned long size, pgprot_t prot)
{
- unsigned long hsa_end = sclp_get_hsa_size();
+ unsigned long hsa_end = sclp.hsa_size;
unsigned long size_hsa;
if (pfn < hsa_end >> PAGE_SHIFT) {
@@ -258,7 +258,7 @@ int copy_from_oldmem(void *dest, void *src, size_t count)
return rc;
}
} else {
- unsigned long hsa_end = sclp_get_hsa_size();
+ unsigned long hsa_end = sclp.hsa_size;
if ((unsigned long) src < hsa_end) {
copied = min(count, hsa_end - (unsigned long) src);
rc = memcpy_hsa(dest, (unsigned long) src, copied, 0);
@@ -609,7 +609,7 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
if (elfcorehdr_addr != ELFCORE_ADDR_MAX)
return 0;
/* If we cannot get HSA size for zfcpdump return error */
- if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp_get_hsa_size())
+ if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp.hsa_size)
return -ENODEV;
/* For kdump, exclude previous crashkernel memory */
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index c1f21aca76e7..6fca0e46464e 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -1457,23 +1457,24 @@ int
debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
int area, debug_entry_t * entry, char *out_buf)
{
- struct timespec time_spec;
+ struct timespec64 time_spec;
char *except_str;
unsigned long caller;
int rc = 0;
unsigned int level;
level = entry->id.fields.level;
- stck_to_timespec(entry->id.stck, &time_spec);
+ stck_to_timespec64(entry->id.stck, &time_spec);
if (entry->id.fields.exception)
except_str = "*";
else
except_str = "-";
caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN;
- rc += sprintf(out_buf, "%02i %011lu:%06lu %1u %1s %02i %p ",
- area, time_spec.tv_sec, time_spec.tv_nsec / 1000, level,
- except_str, entry->id.fields.cpuid, (void *) caller);
+ rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p ",
+ area, (long long)time_spec.tv_sec,
+ time_spec.tv_nsec / 1000, level, except_str,
+ entry->id.fields.cpuid, (void *)caller);
return rc;
}
EXPORT_SYMBOL(debug_dflt_header_fn);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 99b44acbfcc7..3238893c9d4f 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -1005,7 +1005,7 @@ ENTRY(sie64a)
.Lsie_gmap:
lg %r14,__SF_EMPTY(%r15) # get control block pointer
oi __SIE_PROG0C+3(%r14),1 # we are going into SIE now
- tm __SIE_PROG20+3(%r14),1 # last exit...
+ tm __SIE_PROG20+3(%r14),3 # last exit...
jnz .Lsie_done
LPP __SF_EMPTY(%r15) # set guest id
sie 0(%r14)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 7262fe438c99..af4f41d52cde 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -128,9 +128,9 @@ __setup("condev=", condev_setup);
static void __init set_preferred_console(void)
{
if (MACHINE_IS_KVM) {
- if (sclp_has_vt220())
+ if (sclp.has_vt220)
add_preferred_console("ttyS", 1, NULL);
- else if (sclp_has_linemode())
+ else if (sclp.has_linemode)
add_preferred_console("ttyS", 0, NULL);
else
add_preferred_console("hvc", 0, NULL);
@@ -510,8 +510,8 @@ static void reserve_memory_end(void)
{
#ifdef CONFIG_CRASH_DUMP
if (ipl_info.type == IPL_TYPE_FCP_DUMP &&
- !OLDMEM_BASE && sclp_get_hsa_size()) {
- memory_end = sclp_get_hsa_size();
+ !OLDMEM_BASE && sclp.hsa_size) {
+ memory_end = sclp.hsa_size;
memory_end &= PAGE_MASK;
memory_end_set = 1;
}
@@ -576,7 +576,7 @@ static void __init reserve_crashkernel(void)
crash_base = low;
} else {
/* Find suitable area in free memory */
- low = max_t(unsigned long, crash_size, sclp_get_hsa_size());
+ low = max_t(unsigned long, crash_size, sclp.hsa_size);
high = crash_base ? crash_base + crash_size : ULONG_MAX;
if (crash_base && crash_base < low) {
@@ -640,19 +640,24 @@ static void __init check_initrd(void)
}
/*
- * Reserve all kernel text
+ * Reserve memory used for lowcore/command line/kernel image.
*/
static void __init reserve_kernel(void)
{
- unsigned long start_pfn;
- start_pfn = PFN_UP(__pa(&_end));
+ unsigned long start_pfn = PFN_UP(__pa(&_end));
+#ifdef CONFIG_DMA_API_DEBUG
/*
- * Reserve memory used for lowcore/command line/kernel image.
+ * DMA_API_DEBUG code stumbles over addresses from the
+ * range [_ehead, _stext]. Mark the memory as reserved
+ * so it is not used for CONFIG_DMA_API_DEBUG=y.
*/
+ memblock_reserve(0, PFN_PHYS(start_pfn));
+#else
memblock_reserve(0, (unsigned long)_ehead);
memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
- (unsigned long)_stext);
+#endif
}
static void __init reserve_elfcorehdr(void)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index efd2c1968000..0d9d59d4710e 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -601,7 +601,7 @@ static void __init smp_store_cpu_states(struct sclp_cpu_info *info)
/* No previous system present, normal boot. */
return;
/* Set multi-threading state to the previous system. */
- pcpu_set_smt(sclp_get_mtid_prev());
+ pcpu_set_smt(sclp.mtid_prev);
/* Collect CPU states. */
cpu = 0;
for (i = 0; i < info->configured; i++) {
@@ -740,7 +740,7 @@ static void __init smp_detect_cpus(void)
#endif
/* Set multi-threading state for the current system */
- mtid = sclp_get_mtid(boot_cpu_type);
+ mtid = boot_cpu_type ? sclp.mtid : sclp.mtid_cp;
mtid = (mtid < smp_max_threads) ? mtid : smp_max_threads - 1;
pcpu_set_smt(mtid);
@@ -880,12 +880,13 @@ void __noreturn cpu_die(void)
void __init smp_fill_possible_mask(void)
{
- unsigned int possible, sclp, cpu;
+ unsigned int possible, sclp_max, cpu;
- sclp = min(smp_max_threads, sclp_get_mtid_max() + 1);
- sclp = sclp_get_max_cpu()*sclp ?: nr_cpu_ids;
+ sclp_max = max(sclp.mtid, sclp.mtid_cp) + 1;
+ sclp_max = min(smp_max_threads, sclp_max);
+ sclp_max = sclp.max_cpu * sclp_max ?: nr_cpu_ids;
possible = setup_possible_cpus ?: nr_cpu_ids;
- possible = min(possible, sclp);
+ possible = min(possible, sclp_max);
for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
set_cpu_possible(cpu, true);
}
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index d3236c9e226b..39e2f41b6cf0 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -9,10 +9,10 @@
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/mm.h>
+#include <linux/pci.h>
#include <asm/ctl_reg.h>
#include <asm/ipl.h>
#include <asm/cio.h>
-#include <asm/pci.h>
#include <asm/sections.h>
#include "entry.h"
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 170ddd2018b3..9e733d965e08 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -76,7 +76,7 @@ unsigned long long monotonic_clock(void)
}
EXPORT_SYMBOL(monotonic_clock);
-void tod_to_timeval(__u64 todval, struct timespec *xt)
+void tod_to_timeval(__u64 todval, struct timespec64 *xt)
{
unsigned long long sec;
@@ -181,12 +181,12 @@ static void timing_alert_interrupt(struct ext_code ext_code,
static void etr_reset(void);
static void stp_reset(void);
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
{
tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts);
}
-void read_boot_clock(struct timespec *ts)
+void read_boot_clock64(struct timespec64 *ts)
{
tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts);
}
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 9e3779e3e496..7365e8a46032 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -241,21 +241,6 @@ static int handle_prog(struct kvm_vcpu *vcpu)
return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
}
-static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
-{
- int rc, rc2;
-
- vcpu->stat.exit_instr_and_program++;
- rc = handle_instruction(vcpu);
- rc2 = handle_prog(vcpu);
-
- if (rc == -EOPNOTSUPP)
- vcpu->arch.sie_block->icptcode = 0x04;
- if (rc)
- return rc;
- return rc2;
-}
-
/**
* handle_external_interrupt - used for external interruption interceptions
*
@@ -355,7 +340,6 @@ static const intercept_handler_t intercept_funcs[] = {
[0x00 >> 2] = handle_noop,
[0x04 >> 2] = handle_instruction,
[0x08 >> 2] = handle_prog,
- [0x0C >> 2] = handle_instruction_and_prog,
[0x10 >> 2] = handle_noop,
[0x14 >> 2] = handle_external_interrupt,
[0x18 >> 2] = handle_noop,
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9de47265ef73..c98d89708e99 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -134,6 +134,8 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
active_mask = pending_local_irqs(vcpu);
active_mask |= pending_floating_irqs(vcpu);
+ if (!active_mask)
+ return 0;
if (psw_extint_disabled(vcpu))
active_mask &= ~IRQ_PEND_EXT_MASK;
@@ -799,7 +801,7 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
- if (!sclp_has_sigpif())
+ if (!sclp.has_sigpif)
return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
return (sigp_ctrl & SIGP_CTRL_C) &&
@@ -941,12 +943,9 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
if (cpu_timer_irq_pending(vcpu))
set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
- do {
- irqs = deliverable_irqs(vcpu);
+ while ((irqs = deliverable_irqs(vcpu)) && !rc) {
/* bits are in the order of interrupt priority */
irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT);
- if (irq_type == IRQ_PEND_COUNT)
- break;
if (is_ioirq(irq_type)) {
rc = __deliver_io(vcpu, irq_type);
} else {
@@ -958,9 +957,7 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
}
rc = func(vcpu);
}
- if (rc)
- break;
- } while (!rc);
+ }
set_intercept_indicators(vcpu);
@@ -1058,10 +1055,10 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
return -EINVAL;
- if (sclp_has_sigpif())
+ if (sclp.has_sigpif)
return __inject_extcall_sigpif(vcpu, src_id);
- if (!test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
+ if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
return -EBUSY;
*extcall = irq->u.extcall;
atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
@@ -1340,12 +1337,54 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
return 0;
}
-static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
+/*
+ * Find a destination VCPU for a floating irq and kick it.
+ */
+static void __floating_irq_kick(struct kvm *kvm, u64 type)
{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
struct kvm_s390_local_interrupt *li;
+ struct kvm_vcpu *dst_vcpu;
+ int sigcpu, online_vcpus, nr_tries = 0;
+
+ online_vcpus = atomic_read(&kvm->online_vcpus);
+ if (!online_vcpus)
+ return;
+
+ /* find idle VCPUs first, then round robin */
+ sigcpu = find_first_bit(fi->idle_mask, online_vcpus);
+ if (sigcpu == online_vcpus) {
+ do {
+ sigcpu = fi->next_rr_cpu;
+ fi->next_rr_cpu = (fi->next_rr_cpu + 1) % online_vcpus;
+ /* avoid endless loops if all vcpus are stopped */
+ if (nr_tries++ >= online_vcpus)
+ return;
+ } while (is_vcpu_stopped(kvm_get_vcpu(kvm, sigcpu)));
+ }
+ dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
+
+ /* make the VCPU drop out of the SIE, or wake it up if sleeping */
+ li = &dst_vcpu->arch.local_int;
+ spin_lock(&li->lock);
+ switch (type) {
+ case KVM_S390_MCHK:
+ atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+ break;
+ case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+ atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
+ break;
+ default:
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ break;
+ }
+ spin_unlock(&li->lock);
+ kvm_s390_vcpu_wakeup(dst_vcpu);
+}
+
+static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
+{
struct kvm_s390_float_interrupt *fi;
- struct kvm_vcpu *dst_vcpu = NULL;
- int sigcpu;
u64 type = READ_ONCE(inti->type);
int rc;
@@ -1373,32 +1412,8 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
if (rc)
return rc;
- sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
- if (sigcpu == KVM_MAX_VCPUS) {
- do {
- sigcpu = fi->next_rr_cpu++;
- if (sigcpu == KVM_MAX_VCPUS)
- sigcpu = fi->next_rr_cpu = 0;
- } while (kvm_get_vcpu(kvm, sigcpu) == NULL);
- }
- dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
- li = &dst_vcpu->arch.local_int;
- spin_lock(&li->lock);
- switch (type) {
- case KVM_S390_MCHK:
- atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
- break;
- case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
- break;
- default:
- atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
- break;
- }
- spin_unlock(&li->lock);
- kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
+ __floating_irq_kick(kvm, type);
return 0;
-
}
int kvm_s390_inject_vm(struct kvm *kvm,
@@ -1606,6 +1621,9 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm)
int i;
spin_lock(&fi->lock);
+ fi->pending_irqs = 0;
+ memset(&fi->srv_signal, 0, sizeof(fi->srv_signal));
+ memset(&fi->mchk, 0, sizeof(fi->mchk));
for (i = 0; i < FIRQ_LIST_COUNT; i++)
clear_irq_list(&fi->lists[i]);
for (i = 0; i < FIRQ_MAX_COUNT; i++)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8cd8e7b288c5..2078f92d15ac 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -36,6 +36,10 @@
#include "kvm-s390.h"
#include "gaccess.h"
+#define KMSG_COMPONENT "kvm-s390"
+#undef pr_fmt
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
#define CREATE_TRACE_POINTS
#include "trace.h"
#include "trace-s390.h"
@@ -110,7 +114,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
/* upper facilities limit for kvm */
unsigned long kvm_s390_fac_list_mask[] = {
0xffe6fffbfcfdfc40UL,
- 0x005c800000000000UL,
+ 0x005e800000000000UL,
};
unsigned long kvm_s390_fac_list_mask_size(void)
@@ -236,6 +240,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
{
int r;
unsigned long n;
+ struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int is_dirty = 0;
@@ -245,7 +250,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
if (log->slot >= KVM_USER_MEM_SLOTS)
goto out;
- memslot = id_to_memslot(kvm->memslots, log->slot);
+ slots = kvm_memslots(kvm);
+ memslot = id_to_memslot(slots, log->slot);
r = -ENOENT;
if (!memslot->dirty_bitmap)
goto out;
@@ -454,10 +460,10 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
mutex_lock(&kvm->lock);
kvm->arch.epoch = gtod - host_tod;
- kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) {
+ kvm_s390_vcpu_block_all(kvm);
+ kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm)
cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch;
- exit_sie(cur_vcpu);
- }
+ kvm_s390_vcpu_unblock_all(kvm);
mutex_unlock(&kvm->lock);
return 0;
}
@@ -604,7 +610,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
goto out;
}
get_cpu_id((struct cpuid *) &mach->cpuid);
- mach->ibc = sclp_get_ibc();
+ mach->ibc = sclp.ibc;
memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
@@ -1068,7 +1074,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
S390_ARCH_FAC_LIST_SIZE_BYTE);
kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
- kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff;
+ kvm->arch.model.ibc = sclp.ibc & 0x0fff;
if (kvm_s390_crypto_init(kvm) < 0)
goto out_err;
@@ -1311,8 +1317,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
CPUSTAT_SM |
- CPUSTAT_STOPPED |
- CPUSTAT_GED);
+ CPUSTAT_STOPPED);
+
+ if (test_kvm_facility(vcpu->kvm, 78))
+ atomic_set_mask(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
+ else if (test_kvm_facility(vcpu->kvm, 8))
+ atomic_set_mask(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
+
kvm_s390_vcpu_setup_model(vcpu);
vcpu->arch.sie_block->ecb = 6;
@@ -1321,9 +1332,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->ecb2 = 8;
vcpu->arch.sie_block->eca = 0xC1002000U;
- if (sclp_has_siif())
+ if (sclp.has_siif)
vcpu->arch.sie_block->eca |= 1;
- if (sclp_has_sigpif())
+ if (sclp.has_sigpif)
vcpu->arch.sie_block->eca |= 0x10000000U;
if (test_kvm_facility(vcpu->kvm, 129)) {
vcpu->arch.sie_block->eca |= 0x00020000;
@@ -1409,16 +1420,28 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
return kvm_s390_vcpu_has_irq(vcpu, 0);
}
-void s390_vcpu_block(struct kvm_vcpu *vcpu)
+void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
{
atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
+ exit_sie(vcpu);
}
-void s390_vcpu_unblock(struct kvm_vcpu *vcpu)
+void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu)
{
atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
}
+static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu)
+{
+ atomic_set_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+ exit_sie(vcpu);
+}
+
+static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
+{
+ atomic_clear_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+}
+
/*
* Kick a guest cpu out of SIE and wait until SIE is not running.
* If the CPU is not running (e.g. waiting as idle) the function will
@@ -1430,11 +1453,11 @@ void exit_sie(struct kvm_vcpu *vcpu)
cpu_relax();
}
-/* Kick a guest cpu out of SIE and prevent SIE-reentry */
-void exit_sie_sync(struct kvm_vcpu *vcpu)
+/* Kick a guest cpu out of SIE to process a request synchronously */
+void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu)
{
- s390_vcpu_block(vcpu);
- exit_sie(vcpu);
+ kvm_make_request(req, vcpu);
+ kvm_s390_vcpu_request(vcpu);
}
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
@@ -1447,8 +1470,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
/* match against both prefix pages */
if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
- kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
- exit_sie_sync(vcpu);
+ kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu);
}
}
}
@@ -1720,8 +1742,10 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
+ if (!vcpu->requests)
+ return 0;
retry:
- s390_vcpu_unblock(vcpu);
+ kvm_s390_vcpu_request_handled(vcpu);
/*
* We use MMU_RELOAD just to re-arm the ipte notifier for the
* guest prefix page. gmap_ipte_notify will wait on the ptl lock.
@@ -1993,12 +2017,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
* As PF_VCPU will be used in fault handler, between
* guest_enter and guest_exit should be no uaccess.
*/
- preempt_disable();
- kvm_guest_enter();
- preempt_enable();
+ local_irq_disable();
+ __kvm_guest_enter();
+ local_irq_enable();
exit_reason = sie64a(vcpu->arch.sie_block,
vcpu->run->s.regs.gprs);
- kvm_guest_exit();
+ local_irq_disable();
+ __kvm_guest_exit();
+ local_irq_enable();
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
rc = vcpu_post_run(vcpu, exit_reason);
@@ -2068,7 +2094,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
kvm_s390_vcpu_start(vcpu);
} else if (is_vcpu_stopped(vcpu)) {
- pr_err_ratelimited("kvm-s390: can't run stopped vcpu %d\n",
+ pr_err_ratelimited("can't run stopped vcpu %d\n",
vcpu->vcpu_id);
return -EINVAL;
}
@@ -2206,8 +2232,7 @@ int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
- kvm_make_request(KVM_REQ_DISABLE_IBS, vcpu);
- exit_sie_sync(vcpu);
+ kvm_s390_sync_request(KVM_REQ_DISABLE_IBS, vcpu);
}
static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
@@ -2223,8 +2248,7 @@ static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu);
- kvm_make_request(KVM_REQ_ENABLE_IBS, vcpu);
- exit_sie_sync(vcpu);
+ kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
}
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
@@ -2563,7 +2587,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
/* Section: memory related */
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
/* A few sanity checks. We can have memory slots which have to be
@@ -2581,8 +2605,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
int rc;
@@ -2601,7 +2626,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
mem->guest_phys_addr, mem->memory_size);
if (rc)
- printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
+ pr_warn("failed to commit memory region\n");
return;
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index ca108b90ae56..c5704786e473 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -211,10 +211,10 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr);
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
-void s390_vcpu_block(struct kvm_vcpu *vcpu);
-void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu);
void exit_sie(struct kvm_vcpu *vcpu);
-void exit_sie_sync(struct kvm_vcpu *vcpu);
+void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu);
int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
/* is cmma enabled */
@@ -228,6 +228,25 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
struct kvm_s390_pgm_info *pgm_info);
+static inline void kvm_s390_vcpu_block_all(struct kvm *kvm)
+{
+ int i;
+ struct kvm_vcpu *vcpu;
+
+ WARN_ON(!mutex_is_locked(&kvm->lock));
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_s390_vcpu_block(vcpu);
+}
+
+static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm)
+{
+ int i;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_s390_vcpu_unblock(vcpu);
+}
+
/**
* kvm_s390_inject_prog_cond - conditionally inject a program check
* @vcpu: virtual cpu
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d22d8ee1ff9d..ad4242245771 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -698,10 +698,14 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
case 0x00001000:
end = (start + (1UL << 20)) & ~((1UL << 20) - 1);
break;
- /* We dont support EDAT2
case 0x00002000:
+ /* only support 2G frame size if EDAT2 is available and we are
+ not in 24-bit addressing mode */
+ if (!test_kvm_facility(vcpu->kvm, 78) ||
+ psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_24BIT)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
end = (start + (1UL << 31)) & ~((1UL << 31) - 1);
- break;*/
+ break;
default:
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 76515bcea2f1..4c8f5d7f9c23 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -399,7 +399,7 @@ static inline int do_exception(struct pt_regs *regs, int access)
* user context.
*/
fault = VM_FAULT_BADCONTEXT;
- if (unlikely(!user_space_fault(regs) || in_atomic() || !mm))
+ if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm))
goto out;
address = trans_exc_code & __FAIL_ADDR_MASK;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 80875c43a4a4..76e873748b56 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -213,7 +213,7 @@ unsigned long memory_block_size_bytes(void)
* Make sure the memory block size is always greater
* or equal than the memory increment size.
*/
- return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp_get_rzm());
+ return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp.rzm);
}
#ifdef CONFIG_MEMORY_HOTREMOVE
diff --git a/arch/s390/mm/mem_detect.c b/arch/s390/mm/mem_detect.c
index 0f3604395805..e00f0d5d296d 100644
--- a/arch/s390/mm/mem_detect.c
+++ b/arch/s390/mm/mem_detect.c
@@ -31,8 +31,8 @@ void __init detect_memory_memblock(void)
unsigned long addr, size;
int type;
- rzm = sclp_get_rzm();
- rnmax = sclp_get_rnmax();
+ rzm = sclp.rzm;
+ rnmax = sclp.rnmax;
memsize = rzm * rnmax;
if (!rzm)
rzm = 1ULL << 17;
diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index ba8593a515ba..f6498eec9ee1 100644
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -28,6 +28,9 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
* | old backchain | |
* +---------------+ |
* | r15 - r6 | |
+ * +---------------+ |
+ * | 4 byte align | |
+ * | tail_call_cnt | |
* BFP -> +===============+ |
* | | |
* | BPF stack | |
@@ -46,12 +49,17 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
* R15 -> +---------------+ + low
*
* We get 160 bytes stack space from calling function, but only use
- * 11 * 8 byte (old backchain + r15 - r6) for storing registers.
+ * 12 * 8 byte for old backchain, r15..r6, and tail_call_cnt.
*/
-#define STK_OFF (MAX_BPF_STACK + 8 + 4 + 4 + (160 - 11 * 8))
+#define STK_SPACE (MAX_BPF_STACK + 8 + 4 + 4 + 160)
+#define STK_160_UNUSED (160 - 12 * 8)
+#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_R6 (160 - 11 * 8) /* Offset of r6 on stack */
+#define STK_OFF_TCCNT (160 - 12 * 8) /* Offset of tail_call_cnt on stack */
+
/* Offset to skip condition code check */
#define OFF_OK 4
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 7690dc8e1ab5..d3766dd67e23 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -21,6 +21,7 @@
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/init.h>
+#include <linux/bpf.h>
#include <asm/cacheflush.h>
#include <asm/dis.h>
#include "bpf_jit.h"
@@ -40,6 +41,8 @@ struct bpf_jit {
int base_ip; /* Base address for literal pool */
int ret0_ip; /* Address of return 0 */
int exit_ip; /* Address of exit */
+ int tail_call_start; /* Tail call start offset */
+ int labels[1]; /* Labels for local jumps */
};
#define BPF_SIZE_MAX 4096 /* Max size for program */
@@ -49,6 +52,7 @@ struct bpf_jit {
#define SEEN_RET0 4 /* ret0_ip points to a valid return 0 */
#define SEEN_LITERAL 8 /* code uses literals */
#define SEEN_FUNC 16 /* calls C functions */
+#define SEEN_TAIL_CALL 32 /* code uses tail calls */
#define SEEN_STACK (SEEN_FUNC | SEEN_MEM | SEEN_SKB)
/*
@@ -60,6 +64,7 @@ struct bpf_jit {
#define REG_L (__MAX_BPF_REG+3) /* Literal pool register */
#define REG_15 (__MAX_BPF_REG+4) /* Register 15 */
#define REG_0 REG_W0 /* Register 0 */
+#define REG_1 REG_W1 /* Register 1 */
#define REG_2 BPF_REG_1 /* Register 2 */
#define REG_14 BPF_REG_0 /* Register 14 */
@@ -223,6 +228,24 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
REG_SET_SEEN(b3); \
})
+#define EMIT6_PCREL_LABEL(op1, op2, b1, b2, label, mask) \
+({ \
+ int rel = (jit->labels[label] - jit->prg) >> 1; \
+ _EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff), \
+ op2 | mask << 12); \
+ REG_SET_SEEN(b1); \
+ REG_SET_SEEN(b2); \
+})
+
+#define EMIT6_PCREL_IMM_LABEL(op1, op2, b1, imm, label, mask) \
+({ \
+ int rel = (jit->labels[label] - jit->prg) >> 1; \
+ _EMIT6(op1 | (reg_high(b1) | mask) << 16 | \
+ (rel & 0xffff), op2 | (imm & 0xff) << 8); \
+ REG_SET_SEEN(b1); \
+ BUILD_BUG_ON(((unsigned long) imm) > 0xff); \
+})
+
#define EMIT6_PCREL(op1, op2, b1, b2, i, off, mask) \
({ \
/* Branch instruction needs 6 bytes */ \
@@ -286,7 +309,7 @@ static void jit_fill_hole(void *area, unsigned int size)
*/
static void save_regs(struct bpf_jit *jit, u32 rs, u32 re)
{
- u32 off = 72 + (rs - 6) * 8;
+ u32 off = STK_OFF_R6 + (rs - 6) * 8;
if (rs == re)
/* stg %rs,off(%r15) */
@@ -301,7 +324,7 @@ static void save_regs(struct bpf_jit *jit, u32 rs, u32 re)
*/
static void restore_regs(struct bpf_jit *jit, u32 rs, u32 re)
{
- u32 off = 72 + (rs - 6) * 8;
+ u32 off = STK_OFF_R6 + (rs - 6) * 8;
if (jit->seen & SEEN_STACK)
off += STK_OFF;
@@ -374,6 +397,16 @@ static void save_restore_regs(struct bpf_jit *jit, int op)
*/
static void bpf_jit_prologue(struct bpf_jit *jit)
{
+ if (jit->seen & SEEN_TAIL_CALL) {
+ /* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */
+ _EMIT6(0xd703f000 | STK_OFF_TCCNT, 0xf000 | STK_OFF_TCCNT);
+ } else {
+ /* j tail_call_start: NOP if no tail calls are used */
+ EMIT4_PCREL(0xa7f40000, 6);
+ _EMIT2(0);
+ }
+ /* Tail calls have to skip above initialization */
+ jit->tail_call_start = jit->prg;
/* Save registers */
save_restore_regs(jit, REGS_SAVE);
/* Setup literal pool */
@@ -384,13 +417,16 @@ static void bpf_jit_prologue(struct bpf_jit *jit)
}
/* Setup stack and backchain */
if (jit->seen & SEEN_STACK) {
- /* lgr %bfp,%r15 (BPF frame pointer) */
- EMIT4(0xb9040000, BPF_REG_FP, REG_15);
+ if (jit->seen & SEEN_FUNC)
+ /* lgr %w1,%r15 (backchain) */
+ EMIT4(0xb9040000, REG_W1, REG_15);
+ /* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */
+ EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED);
/* aghi %r15,-STK_OFF */
EMIT4_IMM(0xa70b0000, REG_15, -STK_OFF);
if (jit->seen & SEEN_FUNC)
- /* stg %bfp,152(%r15) (backchain) */
- EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_FP, REG_0,
+ /* stg %w1,152(%r15) (backchain) */
+ EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
REG_15, 152);
}
/*
@@ -443,8 +479,11 @@ static void bpf_jit_epilogue(struct bpf_jit *jit)
/*
* Compile one eBPF instruction into s390x code
+ *
+ * NOTE: Use noinline because for gcov (-fprofile-arcs) gcc allocates a lot of
+ * stack space for the large switch statement.
*/
-static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
+static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
{
struct bpf_insn *insn = &fp->insnsi[i];
int jmp_off, last, insn_count = 1;
@@ -588,8 +627,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
EMIT4(0xb9160000, dst_reg, rc_reg);
break;
}
- case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / (u32) src */
- case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % (u32) src */
+ case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */
+ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % src */
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
@@ -602,10 +641,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
EMIT4_IMM(0xa7090000, REG_W0, 0);
/* lgr %w1,%dst */
EMIT4(0xb9040000, REG_W1, dst_reg);
- /* llgfr %dst,%src (u32 cast) */
- EMIT4(0xb9160000, dst_reg, src_reg);
/* dlgr %w0,%dst */
- EMIT4(0xb9870000, REG_W0, dst_reg);
+ EMIT4(0xb9870000, REG_W0, src_reg);
/* lgr %dst,%rc */
EMIT4(0xb9040000, dst_reg, rc_reg);
break;
@@ -632,8 +669,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
EMIT4(0xb9160000, dst_reg, rc_reg);
break;
}
- case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / (u32) imm */
- case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % (u32) imm */
+ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */
+ case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % imm */
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
@@ -649,7 +686,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
EMIT4(0xb9040000, REG_W1, dst_reg);
/* dlg %w0,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
- EMIT_CONST_U64((u32) imm));
+ EMIT_CONST_U64(imm));
/* lgr %dst,%rc */
EMIT4(0xb9040000, dst_reg, rc_reg);
break;
@@ -947,6 +984,75 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
EMIT4(0xb9040000, BPF_REG_0, REG_2);
break;
}
+ case BPF_JMP | BPF_CALL | BPF_X:
+ /*
+ * Implicit input:
+ * B1: pointer to ctx
+ * B2: pointer to bpf_array
+ * B3: index in bpf_array
+ */
+ jit->seen |= SEEN_TAIL_CALL;
+
+ /*
+ * if (index >= array->map.max_entries)
+ * goto out;
+ */
+
+ /* llgf %w1,map.max_entries(%b2) */
+ EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2,
+ offsetof(struct bpf_array, map.max_entries));
+ /* clgrj %b3,%w1,0xa,label0: if %b3 >= %w1 goto out */
+ EMIT6_PCREL_LABEL(0xec000000, 0x0065, BPF_REG_3,
+ REG_W1, 0, 0xa);
+
+ /*
+ * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT)
+ * goto out;
+ */
+
+ if (jit->seen & SEEN_STACK)
+ off = STK_OFF_TCCNT + STK_OFF;
+ else
+ off = STK_OFF_TCCNT;
+ /* lhi %w0,1 */
+ EMIT4_IMM(0xa7080000, REG_W0, 1);
+ /* laal %w1,%w0,off(%r15) */
+ EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off);
+ /* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */
+ EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1,
+ MAX_TAIL_CALL_CNT, 0, 0x2);
+
+ /*
+ * prog = array->prog[index];
+ * if (prog == NULL)
+ * goto out;
+ */
+
+ /* sllg %r1,%b3,3: %r1 = index * 8 */
+ EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3);
+ /* lg %r1,prog(%b2,%r1) */
+ EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2,
+ REG_1, offsetof(struct bpf_array, prog));
+ /* clgij %r1,0,0x8,label0 */
+ EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007d, REG_1, 0, 0, 0x8);
+
+ /*
+ * Restore registers before calling function
+ */
+ save_restore_regs(jit, REGS_RESTORE);
+
+ /*
+ * goto *(prog->bpf_func + tail_call_start);
+ */
+
+ /* lg %r1,bpf_func(%r1) */
+ EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, REG_1, REG_0,
+ offsetof(struct bpf_prog, bpf_func));
+ /* bc 0xf,tail_call_start(%r1) */
+ _EMIT4(0x47f01000 + jit->tail_call_start);
+ /* out: */
+ jit->labels[0] = jit->prg;
+ break;
case BPF_JMP | BPF_EXIT: /* return b0 */
last = (i == fp->len - 1) ? 1 : 0;
if (last && !(jit->seen & SEEN_RET0))
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 460fdb21cf61..ed2394dd14e9 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -75,7 +75,13 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
zpci_err_hex(ccdf, sizeof(*ccdf));
switch (ccdf->pec) {
- case 0x0301: /* Standby -> Configured */
+ case 0x0301: /* Reserved|Standby -> Configured */
+ if (!zdev) {
+ ret = clp_add_pci_device(ccdf->fid, ccdf->fh, 0);
+ if (ret)
+ break;
+ zdev = get_zdev_by_fid(ccdf->fid);
+ }
if (!zdev || zdev->state != ZPCI_FN_STATE_STANDBY)
break;
zdev->state = ZPCI_FN_STATE_CONFIGURED;
diff --git a/arch/score/include/asm/cmpxchg.h b/arch/score/include/asm/cmpxchg.h
index f384839c3ee5..cc3f6420b71c 100644
--- a/arch/score/include/asm/cmpxchg.h
+++ b/arch/score/include/asm/cmpxchg.h
@@ -42,8 +42,6 @@ static inline unsigned long __cmpxchg(volatile unsigned long *m,
(unsigned long)(o), \
(unsigned long)(n)))
-#define __HAVE_ARCH_CMPXCHG 1
-
#include <asm-generic/cmpxchg-local.h>
#endif /* _ASM_SCORE_CMPXCHG_H */
diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h
index ab66ddde777b..20a3591225cc 100644
--- a/arch/score/include/asm/uaccess.h
+++ b/arch/score/include/asm/uaccess.h
@@ -36,7 +36,8 @@
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
@@ -61,7 +62,8 @@
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -79,7 +81,8 @@
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -98,7 +101,8 @@
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -119,7 +123,8 @@
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
diff --git a/arch/score/lib/string.S b/arch/score/lib/string.S
index 00b7d3a2fc60..16efa3ad037f 100644
--- a/arch/score/lib/string.S
+++ b/arch/score/lib/string.S
@@ -175,10 +175,10 @@ ENTRY(__clear_user)
br r3
.section .fixup, "ax"
+99:
br r3
.previous
.section __ex_table, "a"
.align 2
-99:
.word 0b, 99b
.previous
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 6860beb2a280..37a6c2e0e969 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -34,6 +34,7 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
+#include <linux/uaccess.h>
/*
* This routine handles page faults. It determines the address,
@@ -73,7 +74,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (pagefault_disabled() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
diff --git a/arch/sh/drivers/pci/ops-sh5.c b/arch/sh/drivers/pci/ops-sh5.c
index 4ce95a001b80..45361946460f 100644
--- a/arch/sh/drivers/pci/ops-sh5.c
+++ b/arch/sh/drivers/pci/ops-sh5.c
@@ -18,7 +18,6 @@
#include <linux/delay.h>
#include <linux/types.h>
#include <linux/irq.h>
-#include <asm/pci.h>
#include <asm/io.h>
#include "pci-sh5.h"
diff --git a/arch/sh/drivers/pci/pci-sh5.c b/arch/sh/drivers/pci/pci-sh5.c
index 16c1e721bf54..8229114c6a58 100644
--- a/arch/sh/drivers/pci/pci-sh5.c
+++ b/arch/sh/drivers/pci/pci-sh5.c
@@ -20,7 +20,6 @@
#include <linux/types.h>
#include <linux/irq.h>
#include <cpu/irq.h>
-#include <asm/pci.h>
#include <asm/io.h>
#include "pci-sh5.h"
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index 43715308b068..bf91037db4e0 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -32,7 +32,7 @@
#define ctrl_barrier() __asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
#endif
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
#include <asm-generic/barrier.h>
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
index f6bd1406b897..85c97b188d71 100644
--- a/arch/sh/include/asm/cmpxchg.h
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ extern void __xchg_called_with_bad_pointer(void);
* if something tries to do an invalid cmpxchg(). */
extern void __cmpxchg_called_with_bad_pointer(void);
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
unsigned long new, int size)
{
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index 5b4511552998..e343dbd02e41 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -86,24 +86,6 @@ extern void pcibios_set_master(struct pci_dev *dev);
* direct memory write.
*/
#define PCI_DISABLE_MWI
-
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- unsigned long cacheline_size;
- u8 byte;
-
- pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-
- if (byte == 0)
- cacheline_size = L1_CACHE_BYTES;
- else
- cacheline_size = byte << 2;
-
- *strat = PCI_DMA_BURST_MULTIPLE;
- *strategy_parameter = cacheline_size;
-}
#endif
/* Board-specific fixup routines. */
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7734.c b/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
index 1fdf1ee672de..7f54bf2f453d 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
@@ -246,8 +246,7 @@ int __init arch_clk_init(void)
for (i = 0; i < ARRAY_SIZE(main_clks); i++)
ret |= clk_register(main_clks[i]);
- for (i = 0; i < ARRAY_SIZE(lookups); i++)
- clkdev_add(&lookups[i]);
+ clkdev_add_table(lookups, ARRAY_SIZE(lookups));
if (!ret)
ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
index 9a28fdb36387..e40ec2c97ad1 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
@@ -141,8 +141,8 @@ int __init arch_clk_init(void)
for (i = 0; i < ARRAY_SIZE(clks); i++)
ret |= clk_register(clks[i]);
- for (i = 0; i < ARRAY_SIZE(lookups); i++)
- clkdev_add(&lookups[i]);
+
+ clkdev_add_table(lookups, ARRAY_SIZE(lookups));
if (!ret)
ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
index 17d0ea55a5a2..8eb6e62340c9 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
@@ -164,8 +164,8 @@ int __init arch_clk_init(void)
for (i = 0; i < ARRAY_SIZE(clks); i++)
ret |= clk_register(clks[i]);
- for (i = 0; i < ARRAY_SIZE(lookups); i++)
- clkdev_add(&lookups[i]);
+
+ clkdev_add_table(lookups, ARRAY_SIZE(lookups));
if (!ret)
ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
index bec2a83f1ba5..5e50e7ebeff0 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
@@ -179,8 +179,8 @@ int __init arch_clk_init(void)
for (i = 0; i < ARRAY_SIZE(clks); i++)
ret |= clk_register(clks[i]);
- for (i = 0; i < ARRAY_SIZE(lookups); i++)
- clkdev_add(&lookups[i]);
+
+ clkdev_add_table(lookups, ARRAY_SIZE(lookups));
if (!ret)
ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-shx3.c b/arch/sh/kernel/cpu/sh4a/clock-shx3.c
index 9a49a44f6f94..605221d1448a 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-shx3.c
@@ -138,8 +138,8 @@ int __init arch_clk_init(void)
for (i = 0; i < ARRAY_SIZE(clks); i++)
ret |= clk_register(clks[i]);
- for (i = 0; i < ARRAY_SIZE(lookups); i++)
- clkdev_add(&lookups[i]);
+
+ clkdev_add_table(lookups, ARRAY_SIZE(lookups));
if (!ret)
ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index a58fec9b55e0..79d8276377d1 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -17,6 +17,7 @@
#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <linux/kdebug.h>
+#include <linux/uaccess.h>
#include <asm/io_trapped.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
@@ -438,9 +439,9 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
/*
* If we're in an interrupt, have no user context or are running
- * in an atomic region then we must not take the fault:
+ * with pagefaults disabled then we must not take the fault:
*/
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(faulthandler_disabled() || !mm)) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index b688731d7ede..c9d2b922734b 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -33,10 +33,10 @@ static int md5_sparc64_init(struct shash_desc *desc)
{
struct md5_state *mctx = shash_desc_ctx(desc);
- mctx->hash[0] = cpu_to_le32(0x67452301);
- mctx->hash[1] = cpu_to_le32(0xefcdab89);
- mctx->hash[2] = cpu_to_le32(0x98badcfe);
- mctx->hash[3] = cpu_to_le32(0x10325476);
+ mctx->hash[0] = cpu_to_le32(MD5_H0);
+ mctx->hash[1] = cpu_to_le32(MD5_H1);
+ mctx->hash[2] = cpu_to_le32(MD5_H2);
+ mctx->hash[3] = cpu_to_le32(MD5_H3);
mctx->byte_count = 0;
return 0;
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 76648941fea7..809941e33e12 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -40,8 +40,8 @@ do { __asm__ __volatile__("ba,pt %%xcc, 1f\n\t" \
#define dma_rmb() rmb()
#define dma_wmb() wmb()
-#define set_mb(__var, __value) \
- do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+#define smp_store_mb(__var, __value) \
+ do { WRITE_ONCE(__var, __value); membar_safe("#StoreLoad"); } while(0)
#ifdef CONFIG_SMP
#define smp_mb() mb()
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index d38b52dca216..83ffb83c5397 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -34,7 +34,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int
*
* Cribbed from <asm-parisc/atomic.h>
*/
-#define __HAVE_ARCH_CMPXCHG 1
/* bug catcher for when unsupported size is used - won't link */
void __cmpxchg_called_with_bad_pointer(void);
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 0e1ed6cfbf68..faa2f61058c2 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -65,8 +65,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
#include <asm-generic/cmpxchg-local.h>
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long
__cmpxchg_u32(volatile int *m, int old, int new)
{
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index a6e424d185d0..a6cfdabb6054 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -24,7 +24,8 @@ typedef struct {
unsigned int icache_line_size;
unsigned int ecache_size;
unsigned int ecache_line_size;
- int core_id;
+ unsigned short sock_id;
+ unsigned short core_id;
int proc_id;
} cpuinfo_sparc;
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index 407ac14295f4..57f26c398dc9 100644
--- a/arch/sparc/include/asm/io_32.h
+++ b/arch/sparc/include/asm/io_32.h
@@ -129,6 +129,7 @@ static inline void sbus_memcpy_toio(volatile void __iomem *dst,
void __iomem *ioremap(unsigned long offset, unsigned long size);
#define ioremap_nocache(X,Y) ioremap((X),(Y))
#define ioremap_wc(X,Y) ioremap((X),(Y))
+#define ioremap_wt(X,Y) ioremap((X),(Y))
void iounmap(volatile void __iomem *addr);
/* Create a virtual mapping cookie for an IO port range */
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 50d4840d9aeb..c32fa3f752c8 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -402,6 +402,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
#define ioremap_nocache(X,Y) ioremap((X),(Y))
#define ioremap_wc(X,Y) ioremap((X),(Y))
+#define ioremap_wt(X,Y) ioremap((X),(Y))
static inline void iounmap(volatile void __iomem *addr)
{
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index 53e9b4987db0..b7c092df3134 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -22,16 +22,6 @@
struct pci_dev;
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- *strat = PCI_DMA_BURST_INFINITY;
- *strategy_parameter = ~0UL;
-}
-#endif
-
#endif /* __KERNEL__ */
#ifndef CONFIG_LEON_PCI
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index bd00a6226169..022d16008a00 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -31,25 +31,6 @@
#define PCI64_REQUIRED_MASK (~(u64)0)
#define PCI64_ADDR_BASE 0xfffc000000000000UL
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- unsigned long cacheline_size;
- u8 byte;
-
- pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
- if (byte == 0)
- cacheline_size = 1024;
- else
- cacheline_size = (int) byte * 4;
-
- *strat = PCI_DMA_BURST_BOUNDARY;
- *strategy_parameter = cacheline_size;
-}
-#endif
-
/* Return the index of the PCI controller for device PDEV. */
int pci_domain_nr(struct pci_bus *bus);
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index dc165ebdf05a..2a52c91d2c8a 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -308,12 +308,26 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
" sllx %1, 32, %1\n"
" or %0, %1, %0\n"
" .previous\n"
+ " .section .sun_m7_2insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " sethi %%uhi(%4), %1\n"
+ " sethi %%hi(%4), %0\n"
+ " .word 662b\n"
+ " or %1, %%ulo(%4), %1\n"
+ " or %0, %%lo(%4), %0\n"
+ " .word 663b\n"
+ " sllx %1, 32, %1\n"
+ " or %0, %1, %0\n"
+ " .previous\n"
: "=r" (mask), "=r" (tmp)
: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
_PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
_PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
"i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
_PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
+ _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V),
+ "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
+ _PAGE_CP_4V | _PAGE_E_4V |
_PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));
return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
@@ -342,9 +356,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
" andn %0, %4, %0\n"
" or %0, %5, %0\n"
" .previous\n"
+ " .section .sun_m7_2insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " andn %0, %6, %0\n"
+ " or %0, %5, %0\n"
+ " .previous\n"
: "=r" (val)
: "0" (val), "i" (_PAGE_CP_4U | _PAGE_CV_4U), "i" (_PAGE_E_4U),
- "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V));
+ "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V),
+ "i" (_PAGE_CP_4V));
return __pgprot(val);
}
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index ed8f071132e4..01d17046225a 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -40,11 +40,12 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
#ifdef CONFIG_SMP
#define topology_physical_package_id(cpu) (cpu_data(cpu).proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).core_id)
-#define topology_core_cpumask(cpu) (&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu) (&cpu_core_sib_map[cpu])
+#define topology_sibling_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
#endif /* CONFIG_SMP */
extern cpumask_t cpu_core_map[NR_CPUS];
+extern cpumask_t cpu_core_sib_map[NR_CPUS];
static inline const struct cpumask *cpu_coregroup_mask(int cpu)
{
return &cpu_core_map[cpu];
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 6fd4436d32f0..ec9c04de3664 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -79,6 +79,8 @@ struct sun4v_2insn_patch_entry {
};
extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
__sun4v_2insn_patch_end;
+extern struct sun4v_2insn_patch_entry __sun_m7_2insn_patch,
+ __sun_m7_2insn_patch_end;
#endif /* !(__ASSEMBLY__) */
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 07cc49e541f4..0f679421b468 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -69,6 +69,8 @@ void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
struct sun4v_1insn_patch_entry *);
void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
struct sun4v_2insn_patch_entry *);
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+ struct sun4v_2insn_patch_entry *);
extern unsigned int dcache_parity_tl1_occurred;
extern unsigned int icache_parity_tl1_occurred;
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index 94e392bdee7d..814fb1729b12 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -723,7 +723,6 @@ static int grpci2_of_probe(struct platform_device *ofdev)
err = -ENOMEM;
goto err1;
}
- memset(grpci2priv, 0, sizeof(*grpci2priv));
priv->regs = regs;
priv->irq = ofdev->archdata.irqs[0]; /* BASE IRQ */
priv->irq_mode = (capability & STS_IRQMODE) >> STS_IRQMODE_BIT;
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 26c80e18d7b1..6f80936e0eea 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -614,45 +614,68 @@ static void fill_in_one_cache(cpuinfo_sparc *c, struct mdesc_handle *hp, u64 mp)
}
}
-static void mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
+static void find_back_node_value(struct mdesc_handle *hp, u64 node,
+ char *srch_val,
+ void (*func)(struct mdesc_handle *, u64, int),
+ u64 val, int depth)
{
- u64 a;
-
- mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) {
- u64 t = mdesc_arc_target(hp, a);
- const char *name;
- const u64 *id;
+ u64 arc;
- name = mdesc_node_name(hp, t);
- if (!strcmp(name, "cpu")) {
- id = mdesc_get_property(hp, t, "id", NULL);
- if (*id < NR_CPUS)
- cpu_data(*id).core_id = core_id;
- } else {
- u64 j;
+ /* Since we have an estimate of recursion depth, do a sanity check. */
+ if (depth == 0)
+ return;
- mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_BACK) {
- u64 n = mdesc_arc_target(hp, j);
- const char *n_name;
+ mdesc_for_each_arc(arc, hp, node, MDESC_ARC_TYPE_BACK) {
+ u64 n = mdesc_arc_target(hp, arc);
+ const char *name = mdesc_node_name(hp, n);
- n_name = mdesc_node_name(hp, n);
- if (strcmp(n_name, "cpu"))
- continue;
+ if (!strcmp(srch_val, name))
+ (*func)(hp, n, val);
- id = mdesc_get_property(hp, n, "id", NULL);
- if (*id < NR_CPUS)
- cpu_data(*id).core_id = core_id;
- }
- }
+ find_back_node_value(hp, n, srch_val, func, val, depth-1);
}
}
+static void __mark_core_id(struct mdesc_handle *hp, u64 node,
+ int core_id)
+{
+ const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+ if (*id < num_possible_cpus())
+ cpu_data(*id).core_id = core_id;
+}
+
+static void __mark_sock_id(struct mdesc_handle *hp, u64 node,
+ int sock_id)
+{
+ const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+ if (*id < num_possible_cpus())
+ cpu_data(*id).sock_id = sock_id;
+}
+
+static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
+ int core_id)
+{
+ find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10);
+}
+
+static void mark_sock_ids(struct mdesc_handle *hp, u64 mp,
+ int sock_id)
+{
+ find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10);
+}
+
static void set_core_ids(struct mdesc_handle *hp)
{
int idx;
u64 mp;
idx = 1;
+
+ /* Identify unique cores by looking for cpus backpointed to by
+ * level 1 instruction caches.
+ */
mdesc_for_each_node_by_name(hp, mp, "cache") {
const u64 *level;
const char *type;
@@ -667,11 +690,72 @@ static void set_core_ids(struct mdesc_handle *hp)
continue;
mark_core_ids(hp, mp, idx);
+ idx++;
+ }
+}
+
+static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
+{
+ u64 mp;
+ int idx = 1;
+ int fnd = 0;
+
+ /* Identify unique sockets by looking for cpus backpointed to by
+ * shared level n caches.
+ */
+ mdesc_for_each_node_by_name(hp, mp, "cache") {
+ const u64 *cur_lvl;
+
+ cur_lvl = mdesc_get_property(hp, mp, "level", NULL);
+ if (*cur_lvl != level)
+ continue;
+
+ mark_sock_ids(hp, mp, idx);
+ idx++;
+ fnd = 1;
+ }
+ return fnd;
+}
+
+static void set_sock_ids_by_socket(struct mdesc_handle *hp, u64 mp)
+{
+ int idx = 1;
+ mdesc_for_each_node_by_name(hp, mp, "socket") {
+ u64 a;
+
+ mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) {
+ u64 t = mdesc_arc_target(hp, a);
+ const char *name;
+ const u64 *id;
+
+ name = mdesc_node_name(hp, t);
+ if (strcmp(name, "cpu"))
+ continue;
+
+ id = mdesc_get_property(hp, t, "id", NULL);
+ if (*id < num_possible_cpus())
+ cpu_data(*id).sock_id = idx;
+ }
idx++;
}
}
+static void set_sock_ids(struct mdesc_handle *hp)
+{
+ u64 mp;
+
+ /* If machine description exposes sockets data use it.
+ * Otherwise fallback to use shared L3 or L2 caches.
+ */
+ mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets");
+ if (mp != MDESC_NODE_NULL)
+ return set_sock_ids_by_socket(hp, mp);
+
+ if (!set_sock_ids_by_cache(hp, 3))
+ set_sock_ids_by_cache(hp, 2);
+}
+
static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
{
u64 a;
@@ -707,7 +791,6 @@ static void __set_proc_ids(struct mdesc_handle *hp, const char *exec_unit_name)
continue;
mark_proc_ids(hp, mp, idx);
-
idx++;
}
}
@@ -900,6 +983,7 @@ void mdesc_fill_in_cpu_data(cpumask_t *mask)
set_core_ids(hp);
set_proc_ids(hp);
+ set_sock_ids(hp);
mdesc_release(hp);
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 6f7251fd2eab..c928bc64b4ba 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1002,6 +1002,38 @@ static int __init pcibios_init(void)
subsys_initcall(pcibios_init);
#ifdef CONFIG_SYSFS
+
+#define SLOT_NAME_SIZE 11 /* Max decimal digits + null in u32 */
+
+static void pcie_bus_slot_names(struct pci_bus *pbus)
+{
+ struct pci_dev *pdev;
+ struct pci_bus *bus;
+
+ list_for_each_entry(pdev, &pbus->devices, bus_list) {
+ char name[SLOT_NAME_SIZE];
+ struct pci_slot *pci_slot;
+ const u32 *slot_num;
+ int len;
+
+ slot_num = of_get_property(pdev->dev.of_node,
+ "physical-slot#", &len);
+
+ if (slot_num == NULL || len != 4)
+ continue;
+
+ snprintf(name, sizeof(name), "%u", slot_num[0]);
+ pci_slot = pci_create_slot(pbus, slot_num[0], name, NULL);
+
+ if (IS_ERR(pci_slot))
+ pr_err("PCI: pci_create_slot returned %ld.\n",
+ PTR_ERR(pci_slot));
+ }
+
+ list_for_each_entry(bus, &pbus->children, node)
+ pcie_bus_slot_names(bus);
+}
+
static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus)
{
const struct pci_slot_names {
@@ -1053,18 +1085,29 @@ static int __init of_pci_slot_init(void)
while ((pbus = pci_find_next_bus(pbus)) != NULL) {
struct device_node *node;
+ struct pci_dev *pdev;
+
+ pdev = list_first_entry(&pbus->devices, struct pci_dev,
+ bus_list);
- if (pbus->self) {
- /* PCI->PCI bridge */
- node = pbus->self->dev.of_node;
+ if (pdev && pci_is_pcie(pdev)) {
+ pcie_bus_slot_names(pbus);
} else {
- struct pci_pbm_info *pbm = pbus->sysdata;
- /* Host PCI controller */
- node = pbm->op->dev.of_node;
- }
+ if (pbus->self) {
+
+ /* PCI->PCI bridge */
+ node = pbus->self->dev.of_node;
+
+ } else {
+ struct pci_pbm_info *pbm = pbus->sysdata;
- pci_bus_slot_names(node, pbus);
+ /* Host PCI controller */
+ node = pbm->op->dev.of_node;
+ }
+
+ pci_bus_slot_names(node, pbus);
+ }
}
return 0;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c38d19fc27ba..f7b261749383 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -255,6 +255,24 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
}
}
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+ struct sun4v_2insn_patch_entry *end)
+{
+ while (start < end) {
+ unsigned long addr = start->addr;
+
+ *(unsigned int *) (addr + 0) = start->insns[0];
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 0));
+
+ *(unsigned int *) (addr + 4) = start->insns[1];
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 4));
+
+ start++;
+ }
+}
+
static void __init sun4v_patch(void)
{
extern void sun4v_hvapi_init(void);
@@ -267,6 +285,9 @@ static void __init sun4v_patch(void)
sun4v_patch_2insn_range(&__sun4v_2insn_patch,
&__sun4v_2insn_patch_end);
+ if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7)
+ sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
+ &__sun_m7_2insn_patch_end);
sun4v_hvapi_init();
}
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 61139d9924ca..19cd08d18672 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -60,8 +60,12 @@ DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = {
+ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL(cpu_core_sib_map);
static cpumask_t smp_commenced_mask;
@@ -1243,6 +1247,15 @@ void smp_fill_in_sib_core_maps(void)
}
}
+ for_each_present_cpu(i) {
+ unsigned int j;
+
+ for_each_present_cpu(j) {
+ if (cpu_data(i).sock_id == cpu_data(j).sock_id)
+ cpumask_set_cpu(j, &cpu_core_sib_map[i]);
+ }
+ }
+
for_each_present_cpu(i) {
unsigned int j;
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 09243057cb0b..f1a2f688b28a 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -138,6 +138,11 @@ SECTIONS
*(.pause_3insn_patch)
__pause_3insn_patch_end = .;
}
+ .sun_m7_2insn_patch : {
+ __sun_m7_2insn_patch = .;
+ *(.sun_m7_2insn_patch)
+ __sun_m7_2insn_patch_end = .;
+ }
PERCPU_SECTION(SMP_CACHE_BYTES)
. = ALIGN(PAGE_SIZE);
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 70d817154fe8..c399e7b3b035 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -21,6 +21,7 @@
#include <linux/perf_event.h>
#include <linux/interrupt.h>
#include <linux/kdebug.h>
+#include <linux/uaccess.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -29,7 +30,6 @@
#include <asm/setup.h>
#include <asm/smp.h>
#include <asm/traps.h>
-#include <asm/uaccess.h>
#include "mm_32.h"
@@ -196,7 +196,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (pagefault_disabled() || !mm)
goto no_context;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 479823249429..e9268ea1a68d 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -22,12 +22,12 @@
#include <linux/kdebug.h>
#include <linux/percpu.h>
#include <linux/context_tracking.h>
+#include <linux/uaccess.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/openprom.h>
#include <asm/oplib.h>
-#include <asm/uaccess.h>
#include <asm/asi.h>
#include <asm/lsu.h>
#include <asm/sections.h>
@@ -330,7 +330,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto intr_or_no_mm;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c
index 449f864f0cef..a454ec5ff07a 100644
--- a/arch/sparc/mm/highmem.c
+++ b/arch/sparc/mm/highmem.c
@@ -53,7 +53,7 @@ void *kmap_atomic(struct page *page)
unsigned long vaddr;
long idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
@@ -91,6 +91,7 @@ void __kunmap_atomic(void *kvaddr)
if (vaddr < FIXADDR_START) { // FIXME
pagefault_enable();
+ preempt_enable();
return;
}
@@ -126,5 +127,6 @@ void __kunmap_atomic(void *kvaddr)
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 4ca0d6ba5ec8..c5d08b89a96c 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -54,6 +54,7 @@
#include "init_64.h"
unsigned long kern_linear_pte_xor[4] __read_mostly;
+static unsigned long page_cache4v_flag;
/* A bitmap, two bits for every 256MB of physical memory. These two
* bits determine what page size we use for kernel linear
@@ -1909,11 +1910,24 @@ static void __init sun4u_linear_pte_xor_finalize(void)
static void __init sun4v_linear_pte_xor_finalize(void)
{
+ unsigned long pagecv_flag;
+
+ /* Bit 9 of TTE is no longer CV bit on M7 processor and it instead
+ * enables MCD error. Do not set bit 9 on M7 processor.
+ */
+ switch (sun4v_chip_type) {
+ case SUN4V_CHIP_SPARC_M7:
+ pagecv_flag = 0x00;
+ break;
+ default:
+ pagecv_flag = _PAGE_CV_4V;
+ break;
+ }
#ifndef CONFIG_DEBUG_PAGEALLOC
if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) {
kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[1] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[1] = kern_linear_pte_xor[0];
@@ -1922,7 +1936,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) {
kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[2] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[2] = kern_linear_pte_xor[1];
@@ -1931,7 +1945,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) {
kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[3] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[3] = kern_linear_pte_xor[2];
@@ -1958,6 +1972,13 @@ static phys_addr_t __init available_memory(void)
return available;
}
+#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U)
+#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V)
+#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
+#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
+#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
+#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
+
/* We need to exclude reserved regions. This exclusion will include
* vmlinux and initrd. To be more precise the initrd size could be used to
* compute a new lower limit because it is freed later during initialization.
@@ -2034,6 +2055,25 @@ void __init paging_init(void)
memset(swapper_4m_tsb, 0x40, sizeof(swapper_4m_tsb));
#endif
+ /* TTE.cv bit on sparc v9 occupies the same position as TTE.mcde
+ * bit on M7 processor. This is a conflicting usage of the same
+ * bit. Enabling TTE.cv on M7 would turn on Memory Corruption
+ * Detection error on all pages and this will lead to problems
+ * later. Kernel does not run with MCD enabled and hence rest
+ * of the required steps to fully configure memory corruption
+ * detection are not taken. We need to ensure TTE.mcde is not
+ * set on M7 processor. Compute the value of cacheability
+ * flag for use later taking this into consideration.
+ */
+ switch (sun4v_chip_type) {
+ case SUN4V_CHIP_SPARC_M7:
+ page_cache4v_flag = _PAGE_CP_4V;
+ break;
+ default:
+ page_cache4v_flag = _PAGE_CACHE_4V;
+ break;
+ }
+
if (tlb_type == hypervisor)
sun4v_pgprot_init();
else
@@ -2274,13 +2314,6 @@ void free_initrd_mem(unsigned long start, unsigned long end)
}
#endif
-#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U)
-#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V)
-#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
-#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
-#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
-#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
-
pgprot_t PAGE_KERNEL __read_mostly;
EXPORT_SYMBOL(PAGE_KERNEL);
@@ -2312,8 +2345,7 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
_PAGE_P_4U | _PAGE_W_4U);
if (tlb_type == hypervisor)
pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
- _PAGE_CP_4V | _PAGE_CV_4V |
- _PAGE_P_4V | _PAGE_W_4V);
+ page_cache4v_flag | _PAGE_P_4V | _PAGE_W_4V);
pte_base |= _PAGE_PMD_HUGE;
@@ -2450,14 +2482,14 @@ static void __init sun4v_pgprot_init(void)
int i;
PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4V | _PAGE_VALID |
- _PAGE_CACHE_4V | _PAGE_P_4V |
+ page_cache4v_flag | _PAGE_P_4V |
__ACCESS_BITS_4V | __DIRTY_BITS_4V |
_PAGE_EXEC_4V);
PAGE_KERNEL_LOCKED = PAGE_KERNEL;
_PAGE_IE = _PAGE_IE_4V;
_PAGE_E = _PAGE_E_4V;
- _PAGE_CACHE = _PAGE_CACHE_4V;
+ _PAGE_CACHE = page_cache4v_flag;
#ifdef CONFIG_DEBUG_PAGEALLOC
kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET;
@@ -2465,8 +2497,8 @@ static void __init sun4v_pgprot_init(void)
kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^
PAGE_OFFSET;
#endif
- kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V |
- _PAGE_P_4V | _PAGE_W_4V);
+ kern_linear_pte_xor[0] |= (page_cache4v_flag | _PAGE_P_4V |
+ _PAGE_W_4V);
for (i = 1; i < 4; i++)
kern_linear_pte_xor[i] = kern_linear_pte_xor[0];
@@ -2479,12 +2511,12 @@ static void __init sun4v_pgprot_init(void)
_PAGE_SZ4MB_4V | _PAGE_SZ512K_4V |
_PAGE_SZ64K_4V | _PAGE_SZ8K_4V);
- page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | _PAGE_CACHE_4V;
- page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | page_cache4v_flag;
+ page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_WRITE_4V | _PAGE_EXEC_4V);
- page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_EXEC_4V);
- page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_EXEC_4V);
page_exec_bit = _PAGE_EXEC_4V;
@@ -2542,7 +2574,7 @@ static unsigned long kern_large_tte(unsigned long paddr)
_PAGE_EXEC_4U | _PAGE_L_4U | _PAGE_W_4U);
if (tlb_type == hypervisor)
val = (_PAGE_VALID | _PAGE_SZ4MB_4V |
- _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V |
+ page_cache4v_flag | _PAGE_P_4V |
_PAGE_EXEC_4V | _PAGE_W_4V);
return val | paddr;
@@ -2706,7 +2738,7 @@ void hugetlb_setup(struct pt_regs *regs)
struct mm_struct *mm = current->mm;
struct tsb_config *tp;
- if (in_atomic() || !mm) {
+ if (faulthandler_disabled() || !mm) {
const struct exception_table_entry *entry;
entry = search_exception_tables(regs->tpc);
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index a07e31b50d3f..59cf0b911898 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -28,6 +28,7 @@ config TILE
select HAVE_DEBUG_STACKOVERFLOW
select ARCH_WANT_FRAME_POINTERS
select HAVE_CONTEXT_TRACKING
+ select EDAC_SUPPORT
# FIXME: investigate whether we need/want these options.
# select HAVE_IOREMAP_PROT
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index 7b11c5fadd42..0496970cef82 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -105,9 +105,6 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-/* Define this to indicate that cmpxchg is an efficient operation. */
-#define __HAVE_ARCH_CMPXCHG
-
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_TILE_ATOMIC_64_H */
diff --git a/arch/tile/include/asm/edac.h b/arch/tile/include/asm/edac.h
deleted file mode 100644
index 87fc83eeaffd..000000000000
--- a/arch/tile/include/asm/edac.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright 2011 Tilera Corporation. All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation, version 2.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for
- * more details.
- */
-
-#ifndef _ASM_TILE_EDAC_H
-#define _ASM_TILE_EDAC_H
-
-/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-
-static inline void atomic_scrub(void *va, u32 size)
-{
- /*
- * These is nothing to be done here because CE is
- * corrected by the mshim.
- */
- return;
-}
-
-#endif /* _ASM_TILE_EDAC_H */
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index 6ef4ecab1df2..dc61de15c1f9 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -54,7 +54,7 @@ extern void iounmap(volatile void __iomem *addr);
#define ioremap_nocache(physaddr, size) ioremap(physaddr, size)
#define ioremap_wc(physaddr, size) ioremap(physaddr, size)
-#define ioremap_writethrough(physaddr, size) ioremap(physaddr, size)
+#define ioremap_wt(physaddr, size) ioremap(physaddr, size)
#define ioremap_fullcache(physaddr, size) ioremap(physaddr, size)
#define mmiowb()
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index 938311844233..76b0d0ebb244 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -55,7 +55,7 @@ static inline const struct cpumask *cpumask_of_node(int node)
#define topology_physical_package_id(cpu) ((void)(cpu), 0)
#define topology_core_id(cpu) (cpu)
#define topology_core_cpumask(cpu) ((void)(cpu), cpu_online_mask)
-#define topology_thread_cpumask(cpu) cpumask_of(cpu)
+#define topology_sibling_cpumask(cpu) cpumask_of(cpu)
#endif
#endif /* _ASM_TILE_TOPOLOGY_H */
diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h
index f41cb53cf645..a33276bf5ca1 100644
--- a/arch/tile/include/asm/uaccess.h
+++ b/arch/tile/include/asm/uaccess.h
@@ -78,7 +78,8 @@ int __range_ok(unsigned long addr, unsigned long size);
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
@@ -192,7 +193,8 @@ extern int __get_user_bad(void)
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -274,7 +276,8 @@ extern int __put_user_bad(void)
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -330,7 +333,8 @@ extern int __put_user_bad(void)
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -366,7 +370,8 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -437,7 +442,8 @@ static inline unsigned long __must_check copy_from_user(void *to,
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to user space. Caller must check
* the specified blocks with access_ok() before calling this function.
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index e83cc999da02..3f4f58d34a92 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -354,9 +354,9 @@ static int handle_page_fault(struct pt_regs *regs,
/*
* If we're in an interrupt, have no user context or are running in an
- * atomic region then we must not take the fault.
+ * region with pagefaults disabled then we must not take the fault.
*/
- if (in_atomic() || !mm) {
+ if (pagefault_disabled() || !mm) {
vma = NULL; /* happy compiler */
goto bad_area_nosemaphore;
}
diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c
index 6aa2f2625447..fcd545014e79 100644
--- a/arch/tile/mm/highmem.c
+++ b/arch/tile/mm/highmem.c
@@ -201,7 +201,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
int idx, type;
pte_t *pte;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
/* Avoid icache flushes by disallowing atomic executable mappings. */
@@ -259,6 +259,7 @@ void __kunmap_atomic(void *kvaddr)
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 8e4daf44e980..47ff9b7f3e5d 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -7,6 +7,7 @@
#include <linux/sched.h>
#include <linux/hardirq.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
#include <asm/current.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -35,10 +36,10 @@ int handle_page_fault(unsigned long address, unsigned long ip,
*code_out = SEGV_MAPERR;
/*
- * If the fault was during atomic operation, don't take the fault, just
+ * If the fault was with pagefaults disabled, don't take the fault, just
* fail.
*/
- if (in_atomic())
+ if (faulthandler_disabled())
goto out_nosemaphore;
if (is_user)
diff --git a/arch/unicore32/include/asm/pci.h b/arch/unicore32/include/asm/pci.h
index 654407e98619..38b3f3785c3c 100644
--- a/arch/unicore32/include/asm/pci.h
+++ b/arch/unicore32/include/asm/pci.h
@@ -18,16 +18,6 @@
#include <asm-generic/pci.h>
#include <mach/hardware.h> /* for PCIBIOS_MIN_* */
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- *strat = PCI_DMA_BURST_INFINITY;
- *strategy_parameter = ~0UL;
-}
-#endif
-
#define HAVE_PCI_MMAP
extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
enum pci_mmap_state mmap_state, int write_combine);
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 0dc922dba915..afccef5529cc 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -218,7 +218,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 3942f74c92d7..1538562cc720 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -1,3 +1,6 @@
+
+obj-y += entry/
+
obj-$(CONFIG_KVM) += kvm/
# Xen paravirtualization support
@@ -11,7 +14,7 @@ obj-y += kernel/
obj-y += mm/
obj-y += crypto/
-obj-y += vdso/
+
obj-$(CONFIG_IA32_EMULATION) += ia32/
obj-y += platform/
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 226d5696e1d1..8e0b76ad8350 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -9,140 +9,143 @@ config 64BIT
config X86_32
def_bool y
depends on !64BIT
- select CLKSRC_I8253
- select HAVE_UID16
config X86_64
def_bool y
depends on 64BIT
- select X86_DEV_DMA_OPS
- select ARCH_USE_CMPXCHG_LOCKREF
- select HAVE_LIVEPATCH
### Arch settings
config X86
def_bool y
- select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
- select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
+ select ACPI_LEGACY_TABLES_LOOKUP if ACPI
+ select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
+ select ANON_INODES
+ select ARCH_CLOCKSOURCE_DATA
+ select ARCH_DISCARD_MEMBLOCK
+ select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+ select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_SG_CHAIN
+ select ARCH_HAVE_NMI_SAFE_CMPXCHG
+ select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
- select HAVE_AOUT if X86_32
- select HAVE_UNSTABLE_SCHED_CLOCK
- select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
- select ARCH_SUPPORTS_INT128 if X86_64
- select HAVE_IDE
- select HAVE_OPROFILE
- select HAVE_PCSPKR_PLATFORM
- select HAVE_PERF_EVENTS
- select HAVE_IOREMAP_PROT
- select HAVE_KPROBES
- select HAVE_MEMBLOCK
- select HAVE_MEMBLOCK_NODE_MAP
- select ARCH_DISCARD_MEMBLOCK
- select ARCH_WANT_OPTIONAL_GPIOLIB
+ select ARCH_SUPPORTS_ATOMIC_RMW
+ select ARCH_SUPPORTS_INT128 if X86_64
+ select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
+ select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_CMPXCHG_LOCKREF if X86_64
+ select ARCH_USE_QUEUED_RWLOCKS
+ select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_WANT_FRAME_POINTERS
- select HAVE_DMA_ATTRS
- select HAVE_DMA_CONTIGUOUS
- select HAVE_KRETPROBES
+ select ARCH_WANT_IPC_PARSE_VERSION if X86_32
+ select ARCH_WANT_OPTIONAL_GPIOLIB
+ select BUILDTIME_EXTABLE_SORT
+ select CLKEVT_I8253
+ select CLKSRC_I8253 if X86_32
+ select CLOCKSOURCE_VALIDATE_LAST_CYCLE
+ select CLOCKSOURCE_WATCHDOG
+ select CLONE_BACKWARDS if X86_32
+ select COMPAT_OLD_SIGACTION if IA32_EMULATION
+ select DCACHE_WORD_ACCESS
+ select EDAC_ATOMIC_SCRUB
+ select EDAC_SUPPORT
+ select GENERIC_CLOCKEVENTS
+ select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
+ select GENERIC_CLOCKEVENTS_MIN_ADJUST
+ select GENERIC_CMOS_UPDATE
+ select GENERIC_CPU_AUTOPROBE
select GENERIC_EARLY_IOREMAP
- select HAVE_OPTPROBES
- select HAVE_KPROBES_ON_FTRACE
- select HAVE_FTRACE_MCOUNT_RECORD
- select HAVE_FENTRY if X86_64
+ select GENERIC_FIND_FIRST_BIT
+ select GENERIC_IOMAP
+ select GENERIC_IRQ_PROBE
+ select GENERIC_IRQ_SHOW
+ select GENERIC_PENDING_IRQ if SMP
+ select GENERIC_SMP_IDLE_THREAD
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
+ select GENERIC_TIME_VSYSCALL
+ select HAVE_ACPI_APEI if ACPI
+ select HAVE_ACPI_APEI_NMI if ACPI
+ select HAVE_ALIGNED_STRUCT_PAGE if SLUB
+ select HAVE_AOUT if X86_32
+ select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
+ select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+ select HAVE_ARCH_KGDB
+ select HAVE_ARCH_KMEMCHECK
+ select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_SOFT_DIRTY if X86_64
+ select HAVE_ARCH_TRACEHOOK
+ select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_BPF_JIT if X86_64
+ select HAVE_CC_STACKPROTECTOR
+ select HAVE_CMPXCHG_DOUBLE
+ select HAVE_CMPXCHG_LOCAL
+ select HAVE_CONTEXT_TRACKING if X86_64
select HAVE_C_RECORDMCOUNT
+ select HAVE_DEBUG_KMEMLEAK
+ select HAVE_DEBUG_STACKOVERFLOW
+ select HAVE_DMA_API_DEBUG
+ select HAVE_DMA_ATTRS
+ select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
- select HAVE_FUNCTION_TRACER
- select HAVE_FUNCTION_GRAPH_TRACER
- select HAVE_FUNCTION_GRAPH_FP_TEST
- select HAVE_SYSCALL_TRACEPOINTS
- select SYSCTL_EXCEPTION_TRACE
- select HAVE_KVM
- select HAVE_ARCH_KGDB
- select HAVE_ARCH_TRACEHOOK
- select HAVE_GENERIC_DMA_COHERENT if X86_32
select HAVE_EFFICIENT_UNALIGNED_ACCESS
- select USER_STACKTRACE_SUPPORT
- select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_DMA_API_DEBUG
- select HAVE_KERNEL_GZIP
+ select HAVE_FENTRY if X86_64
+ select HAVE_FTRACE_MCOUNT_RECORD
+ select HAVE_FUNCTION_GRAPH_FP_TEST
+ select HAVE_FUNCTION_GRAPH_TRACER
+ select HAVE_FUNCTION_TRACER
+ select HAVE_GENERIC_DMA_COHERENT if X86_32
+ select HAVE_HW_BREAKPOINT
+ select HAVE_IDE
+ select HAVE_IOREMAP_PROT
+ select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
+ select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_KERNEL_BZIP2
+ select HAVE_KERNEL_GZIP
+ select HAVE_KERNEL_LZ4
select HAVE_KERNEL_LZMA
- select HAVE_KERNEL_XZ
select HAVE_KERNEL_LZO
- select HAVE_KERNEL_LZ4
- select HAVE_HW_BREAKPOINT
+ select HAVE_KERNEL_XZ
+ select HAVE_KPROBES
+ select HAVE_KPROBES_ON_FTRACE
+ select HAVE_KRETPROBES
+ select HAVE_KVM
+ select HAVE_LIVEPATCH if X86_64
+ select HAVE_MEMBLOCK
+ select HAVE_MEMBLOCK_NODE_MAP
select HAVE_MIXED_BREAKPOINTS_REGS
- select PERF_EVENTS
+ select HAVE_OPROFILE
+ select HAVE_OPTPROBES
+ select HAVE_PCSPKR_PLATFORM
+ select HAVE_PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
- select HAVE_DEBUG_KMEMLEAK
- select ANON_INODES
- select HAVE_ALIGNED_STRUCT_PAGE if SLUB
- select HAVE_CMPXCHG_LOCAL
- select HAVE_CMPXCHG_DOUBLE
- select HAVE_ARCH_KMEMCHECK
- select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+ select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_SYSCALL_TRACEPOINTS
+ select HAVE_UID16 if X86_32
+ select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_USER_RETURN_NOTIFIER
- select ARCH_HAS_ELF_RANDOMIZE
- select HAVE_ARCH_JUMP_LABEL
- select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select SPARSE_IRQ
- select GENERIC_FIND_FIRST_BIT
- select GENERIC_IRQ_PROBE
- select GENERIC_PENDING_IRQ if SMP
- select GENERIC_IRQ_SHOW
- select GENERIC_CLOCKEVENTS_MIN_ADJUST
select IRQ_FORCED_THREADING
- select HAVE_BPF_JIT if X86_64
- select HAVE_ARCH_TRANSPARENT_HUGEPAGE
- select HAVE_ARCH_HUGE_VMAP if X86_64 || (X86_32 && X86_PAE)
- select ARCH_HAS_SG_CHAIN
- select CLKEVT_I8253
- select ARCH_HAVE_NMI_SAFE_CMPXCHG
- select GENERIC_IOMAP
- select DCACHE_WORD_ACCESS
- select GENERIC_SMP_IDLE_THREAD
- select ARCH_WANT_IPC_PARSE_VERSION if X86_32
- select HAVE_ARCH_SECCOMP_FILTER
- select BUILDTIME_EXTABLE_SORT
- select GENERIC_CMOS_UPDATE
- select HAVE_ARCH_SOFT_DIRTY if X86_64
- select CLOCKSOURCE_WATCHDOG
- select GENERIC_CLOCKEVENTS
- select ARCH_CLOCKSOURCE_DATA
- select CLOCKSOURCE_VALIDATE_LAST_CYCLE
- select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
- select GENERIC_TIME_VSYSCALL
- select GENERIC_STRNCPY_FROM_USER
- select GENERIC_STRNLEN_USER
- select HAVE_CONTEXT_TRACKING if X86_64
- select HAVE_IRQ_TIME_ACCOUNTING
- select VIRT_TO_BUS
- select MODULES_USE_ELF_REL if X86_32
- select MODULES_USE_ELF_RELA if X86_64
- select CLONE_BACKWARDS if X86_32
- select ARCH_USE_BUILTIN_BSWAP
- select ARCH_USE_QUEUE_RWLOCK
- select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
- select OLD_SIGACTION if X86_32
- select COMPAT_OLD_SIGACTION if IA32_EMULATION
+ select MODULES_USE_ELF_RELA if X86_64
+ select MODULES_USE_ELF_REL if X86_32
+ select OLD_SIGACTION if X86_32
+ select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
+ select PERF_EVENTS
select RTC_LIB
- select HAVE_DEBUG_STACKOVERFLOW
- select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
- select HAVE_CC_STACKPROTECTOR
- select GENERIC_CPU_AUTOPROBE
- select HAVE_ARCH_AUDITSYSCALL
- select ARCH_SUPPORTS_ATOMIC_RMW
- select HAVE_ACPI_APEI if ACPI
- select HAVE_ACPI_APEI_NMI if ACPI
- select ACPI_LEGACY_TABLES_LOOKUP if ACPI
- select X86_FEATURE_NAMES if PROC_FS
+ select SPARSE_IRQ
select SRCU
+ select SYSCTL_EXCEPTION_TRACE
+ select USER_STACKTRACE_SUPPORT
+ select VIRT_TO_BUS
+ select X86_DEV_DMA_OPS if X86_64
+ select X86_FEATURE_NAMES if PROC_FS
config INSTRUCTION_DECODER
def_bool y
@@ -260,10 +263,6 @@ config X86_64_SMP
def_bool y
depends on X86_64 && SMP
-config X86_HT
- def_bool y
- depends on SMP
-
config X86_32_LAZY_GS
def_bool y
depends on X86_32 && !CC_STACKPROTECTOR
@@ -341,7 +340,7 @@ config X86_FEATURE_NAMES
config X86_X2APIC
bool "Support x2apic"
- depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP
+ depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
---help---
This enables x2apic support on CPUs that have this feature.
@@ -441,6 +440,7 @@ config X86_UV
depends on X86_EXTENDED_PLATFORM
depends on NUMA
depends on X86_X2APIC
+ depends on PCI
---help---
This option is needed in order to support SGI Ultraviolet systems.
If you don't have one of these, you should say N here.
@@ -466,7 +466,6 @@ config X86_INTEL_CE
select X86_REBOOTFIXUPS
select OF
select OF_EARLY_FLATTREE
- select IRQ_DOMAIN
---help---
Select for the Intel CE media processor (CE4100) SOC.
This option compiles in support for the CE4100 SOC for settop
@@ -666,7 +665,7 @@ config PARAVIRT_DEBUG
config PARAVIRT_SPINLOCKS
bool "Paravirtualization layer for spinlocks"
depends on PARAVIRT && SMP
- select UNINLINE_SPIN_UNLOCK
+ select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS
---help---
Paravirtualized spinlocks allow a pvops backend to replace the
spinlock implementation with something virtualization-friendly
@@ -851,11 +850,12 @@ config NR_CPUS
default "1" if !SMP
default "8192" if MAXSMP
default "32" if SMP && X86_BIGSMP
- default "8" if SMP
+ default "8" if SMP && X86_32
+ default "64" if SMP
---help---
This allows you to specify the maximum number of CPUs which this
kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum
- supported value is 4096, otherwise the maximum value is 512. The
+ supported value is 8192, otherwise the maximum value is 512. The
minimum value which makes sense is 2.
This is purely to save memory - each supported CPU adds
@@ -863,7 +863,7 @@ config NR_CPUS
config SCHED_SMT
bool "SMT (Hyperthreading) scheduler support"
- depends on X86_HT
+ depends on SMP
---help---
SMT scheduler support improves the CPU scheduler's decision making
when dealing with Intel Pentium 4 chips with HyperThreading at a
@@ -873,7 +873,7 @@ config SCHED_SMT
config SCHED_MC
def_bool y
prompt "Multi-core scheduler support"
- depends on X86_HT
+ depends on SMP
---help---
Multi-core scheduler support improves the CPU scheduler's decision
making when dealing with multi-core CPU chips at a cost of slightly
@@ -914,12 +914,12 @@ config X86_UP_IOAPIC
config X86_LOCAL_APIC
def_bool y
depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
- select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+ select IRQ_DOMAIN_HIERARCHY
+ select PCI_MSI_IRQ_DOMAIN if PCI_MSI
config X86_IO_APIC
def_bool y
depends on X86_LOCAL_APIC || X86_UP_IOAPIC
- select IRQ_DOMAIN
config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
bool "Reroute for broken boot IRQs"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 72484a645f05..a15893d17c55 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -332,4 +332,27 @@ config X86_DEBUG_STATIC_CPU_HAS
If unsure, say N.
+config X86_DEBUG_FPU
+ bool "Debug the x86 FPU code"
+ depends on DEBUG_KERNEL
+ default y
+ ---help---
+ If this option is enabled then there will be extra sanity
+ checks and (boot time) debug printouts added to the kernel.
+ This debugging adds some small amount of runtime overhead
+ to the kernel.
+
+ If unsure, say N.
+
+config PUNIT_ATOM_DEBUG
+ tristate "ATOM Punit debug driver"
+ select DEBUG_FS
+ select IOSF_MBI
+ ---help---
+ This is a debug driver, which gets the power states
+ of all Punit North Complex devices. The power states of
+ each device is exposed as part of the debugfs interface.
+ The current power state can be read from
+ /sys/kernel/debug/punit_atom/dev_power_state
+
endmenu
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2fda005bb334..118e6debc483 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -77,6 +77,12 @@ else
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
+ # Align jump targets to 1 byte, not the default 16 bytes:
+ KBUILD_CFLAGS += -falign-jumps=1
+
+ # Pack loops tightly as well:
+ KBUILD_CFLAGS += -falign-loops=1
+
# Don't autogenerate traditional x87 instructions
KBUILD_CFLAGS += $(call cc-option,-mno-80387)
KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
@@ -84,6 +90,9 @@ else
# Use -mpreferred-stack-boundary=3 if supported.
KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
+ # Use -mskip-rax-setup if supported.
+ KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
+
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
@@ -140,12 +149,6 @@ endif
sp-$(CONFIG_X86_32) := esp
sp-$(CONFIG_X86_64) := rsp
-# do binutils support CFI?
-cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
-# is .cfi_signal_frame supported too?
-cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
-cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
-
# does binutils support specific instructions?
asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
@@ -153,8 +156,8 @@ asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_AFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_CFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
LDFLAGS := -m elf_$(UTS_MACHINE)
@@ -178,7 +181,7 @@ archscripts: scripts_basic
# Syscall table generation
archheaders:
- $(Q)$(MAKE) $(build)=arch/x86/syscalls all
+ $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
archprepare:
ifeq ($(CONFIG_KEXEC_FILE),y)
@@ -241,7 +244,7 @@ install:
PHONY += vdso_install
vdso_install:
- $(Q)$(MAKE) $(build)=arch/x86/vdso $@
+ $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@
archclean:
$(Q)rm -rf $(objtree)/arch/i386
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 89dd0d78013a..805d25ca5f1d 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -2,15 +2,14 @@
#define BOOT_COMPRESSED_MISC_H
/*
- * we have to be careful, because no indirections are allowed here, and
- * paravirt_ops is a kind of one. As it will only run in baremetal anyway,
- * we just keep it from happening
+ * Special hack: we have to be careful, because no indirections are allowed here,
+ * and paravirt_ops is a kind of one. As it will only run in baremetal anyway,
+ * we just keep it from happening. (This list needs to be extended when new
+ * paravirt and debugging variants are added.)
*/
#undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_SPINLOCKS
#undef CONFIG_KASAN
-#ifdef CONFIG_X86_32
-#define _ASM_X86_DESC_H 1
-#endif
#include <linux/linkage.h>
#include <linux/screen_info.h>
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 112cefacf2af..2bfc8a7c88c1 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -32,7 +32,7 @@
#include <crypto/lrw.h>
#include <crypto/xts.h>
#include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/aes.h>
#include <crypto/ablk_helper.h>
#include <crypto/scatterwalk.h>
@@ -44,15 +44,19 @@
#endif
+#define AESNI_ALIGN 16
+#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE - 1))
+#define RFC4106_HASH_SUBKEY_SIZE 16
+
/* This data is stored at the end of the crypto_tfm struct.
* It's a type of per "session" data storage location.
* This needs to be 16 byte aligned.
*/
struct aesni_rfc4106_gcm_ctx {
- u8 hash_subkey[16];
- struct crypto_aes_ctx aes_key_expanded;
+ u8 hash_subkey[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+ struct crypto_aes_ctx aes_key_expanded
+ __attribute__ ((__aligned__(AESNI_ALIGN)));
u8 nonce[4];
- struct cryptd_aead *cryptd_tfm;
};
struct aesni_gcm_set_hash_subkey_result {
@@ -66,10 +70,6 @@ struct aesni_hash_subkey_req_data {
struct scatterlist sg;
};
-#define AESNI_ALIGN (16)
-#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE-1))
-#define RFC4106_HASH_SUBKEY_SIZE 16
-
struct aesni_lrw_ctx {
struct lrw_table_ctx lrw_table;
u8 raw_aes_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1];
@@ -283,10 +283,11 @@ static void (*aesni_gcm_dec_tfm)(void *ctx, u8 *out,
static inline struct
aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
{
- return
- (struct aesni_rfc4106_gcm_ctx *)
- PTR_ALIGN((u8 *)
- crypto_tfm_ctx(crypto_aead_tfm(tfm)), AESNI_ALIGN);
+ unsigned long align = AESNI_ALIGN;
+
+ if (align <= crypto_tfm_ctx_alignment())
+ align = 1;
+ return PTR_ALIGN(crypto_aead_ctx(tfm), align);
}
#endif
@@ -790,36 +791,30 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
#endif
#ifdef CONFIG_X86_64
-static int rfc4106_init(struct crypto_tfm *tfm)
+static int rfc4106_init(struct crypto_aead *aead)
{
struct cryptd_aead *cryptd_tfm;
- struct aesni_rfc4106_gcm_ctx *ctx = (struct aesni_rfc4106_gcm_ctx *)
- PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN);
- struct crypto_aead *cryptd_child;
- struct aesni_rfc4106_gcm_ctx *child_ctx;
+ struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni",
CRYPTO_ALG_INTERNAL,
CRYPTO_ALG_INTERNAL);
if (IS_ERR(cryptd_tfm))
return PTR_ERR(cryptd_tfm);
- cryptd_child = cryptd_aead_child(cryptd_tfm);
- child_ctx = aesni_rfc4106_gcm_ctx_get(cryptd_child);
- memcpy(child_ctx, ctx, sizeof(*ctx));
- ctx->cryptd_tfm = cryptd_tfm;
- tfm->crt_aead.reqsize = sizeof(struct aead_request)
- + crypto_aead_reqsize(&cryptd_tfm->base);
+ *ctx = cryptd_tfm;
+ crypto_aead_set_reqsize(
+ aead,
+ sizeof(struct aead_request) +
+ crypto_aead_reqsize(&cryptd_tfm->base));
return 0;
}
-static void rfc4106_exit(struct crypto_tfm *tfm)
+static void rfc4106_exit(struct crypto_aead *aead)
{
- struct aesni_rfc4106_gcm_ctx *ctx =
- (struct aesni_rfc4106_gcm_ctx *)
- PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN);
- if (!IS_ERR(ctx->cryptd_tfm))
- cryptd_free_aead(ctx->cryptd_tfm);
- return;
+ struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+ cryptd_free_aead(*ctx);
}
static void
@@ -845,8 +840,6 @@ rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
if (IS_ERR(ctr_tfm))
return PTR_ERR(ctr_tfm);
- crypto_ablkcipher_clear_flags(ctr_tfm, ~0);
-
ret = crypto_ablkcipher_setkey(ctr_tfm, key, key_len);
if (ret)
goto out_free_ablkcipher;
@@ -895,73 +888,29 @@ out_free_ablkcipher:
static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
unsigned int key_len)
{
- int ret = 0;
- struct crypto_tfm *tfm = crypto_aead_tfm(aead);
struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead);
- u8 *new_key_align, *new_key_mem = NULL;
if (key_len < 4) {
- crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+ crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
return -EINVAL;
}
/*Account for 4 byte nonce at the end.*/
key_len -= 4;
- if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 &&
- key_len != AES_KEYSIZE_256) {
- crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
- return -EINVAL;
- }
memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce));
- /*This must be on a 16 byte boundary!*/
- if ((unsigned long)(&(ctx->aes_key_expanded.key_enc[0])) % AESNI_ALIGN)
- return -EINVAL;
-
- if ((unsigned long)key % AESNI_ALIGN) {
- /*key is not aligned: use an auxuliar aligned pointer*/
- new_key_mem = kmalloc(key_len+AESNI_ALIGN, GFP_KERNEL);
- if (!new_key_mem)
- return -ENOMEM;
-
- new_key_align = PTR_ALIGN(new_key_mem, AESNI_ALIGN);
- memcpy(new_key_align, key, key_len);
- key = new_key_align;
- }
- if (!irq_fpu_usable())
- ret = crypto_aes_expand_key(&(ctx->aes_key_expanded),
- key, key_len);
- else {
- kernel_fpu_begin();
- ret = aesni_set_key(&(ctx->aes_key_expanded), key, key_len);
- kernel_fpu_end();
- }
- /*This must be on a 16 byte boundary!*/
- if ((unsigned long)(&(ctx->hash_subkey[0])) % AESNI_ALIGN) {
- ret = -EINVAL;
- goto exit;
- }
- ret = rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
-exit:
- kfree(new_key_mem);
- return ret;
+ return aes_set_key_common(crypto_aead_tfm(aead),
+ &ctx->aes_key_expanded, key, key_len) ?:
+ rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
}
static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
unsigned int key_len)
{
- struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent);
- struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm);
- struct aesni_rfc4106_gcm_ctx *c_ctx = aesni_rfc4106_gcm_ctx_get(child);
- struct cryptd_aead *cryptd_tfm = ctx->cryptd_tfm;
- int ret;
+ struct cryptd_aead **ctx = crypto_aead_ctx(parent);
+ struct cryptd_aead *cryptd_tfm = *ctx;
- ret = crypto_aead_setkey(child, key, key_len);
- if (!ret) {
- memcpy(ctx, c_ctx, sizeof(*ctx));
- ctx->cryptd_tfm = cryptd_tfm;
- }
- return ret;
+ return crypto_aead_setkey(&cryptd_tfm->base, key, key_len);
}
static int common_rfc4106_set_authsize(struct crypto_aead *aead,
@@ -975,7 +924,7 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
default:
return -EINVAL;
}
- crypto_aead_crt(aead)->authsize = authsize;
+
return 0;
}
@@ -984,30 +933,23 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
static int rfc4106_set_authsize(struct crypto_aead *parent,
unsigned int authsize)
{
- struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent);
- struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm);
- int ret;
+ struct cryptd_aead **ctx = crypto_aead_ctx(parent);
+ struct cryptd_aead *cryptd_tfm = *ctx;
- ret = crypto_aead_setauthsize(child, authsize);
- if (!ret)
- crypto_aead_crt(parent)->authsize = authsize;
- return ret;
+ return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
}
-static int __driver_rfc4106_encrypt(struct aead_request *req)
+static int helper_rfc4106_encrypt(struct aead_request *req)
{
u8 one_entry_in_sg = 0;
u8 *src, *dst, *assoc;
__be32 counter = cpu_to_be32(1);
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
- u32 key_len = ctx->aes_key_expanded.key_length;
void *aes_ctx = &(ctx->aes_key_expanded);
unsigned long auth_tag_len = crypto_aead_authsize(tfm);
- u8 iv_tab[16+AESNI_ALIGN];
- u8* iv = (u8 *) PTR_ALIGN((u8 *)iv_tab, AESNI_ALIGN);
+ u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
struct scatter_walk src_sg_walk;
- struct scatter_walk assoc_sg_walk;
struct scatter_walk dst_sg_walk;
unsigned int i;
@@ -1016,12 +958,6 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
/* to 8 or 12 bytes */
if (unlikely(req->assoclen != 8 && req->assoclen != 12))
return -EINVAL;
- if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16))
- return -EINVAL;
- if (unlikely(key_len != AES_KEYSIZE_128 &&
- key_len != AES_KEYSIZE_192 &&
- key_len != AES_KEYSIZE_256))
- return -EINVAL;
/* IV below built */
for (i = 0; i < 4; i++)
@@ -1030,55 +966,57 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
*(iv+4+i) = req->iv[i];
*((__be32 *)(iv+12)) = counter;
- if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) {
+ if (sg_is_last(req->src) &&
+ req->src->offset + req->src->length <= PAGE_SIZE &&
+ sg_is_last(req->dst) &&
+ req->dst->offset + req->dst->length <= PAGE_SIZE) {
one_entry_in_sg = 1;
scatterwalk_start(&src_sg_walk, req->src);
- scatterwalk_start(&assoc_sg_walk, req->assoc);
- src = scatterwalk_map(&src_sg_walk);
- assoc = scatterwalk_map(&assoc_sg_walk);
+ assoc = scatterwalk_map(&src_sg_walk);
+ src = assoc + req->assoclen;
dst = src;
if (unlikely(req->src != req->dst)) {
scatterwalk_start(&dst_sg_walk, req->dst);
- dst = scatterwalk_map(&dst_sg_walk);
+ dst = scatterwalk_map(&dst_sg_walk) + req->assoclen;
}
-
} else {
/* Allocate memory for src, dst, assoc */
- src = kmalloc(req->cryptlen + auth_tag_len + req->assoclen,
+ assoc = kmalloc(req->cryptlen + auth_tag_len + req->assoclen,
GFP_ATOMIC);
- if (unlikely(!src))
+ if (unlikely(!assoc))
return -ENOMEM;
- assoc = (src + req->cryptlen + auth_tag_len);
- scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
- scatterwalk_map_and_copy(assoc, req->assoc, 0,
- req->assoclen, 0);
+ scatterwalk_map_and_copy(assoc, req->src, 0,
+ req->assoclen + req->cryptlen, 0);
+ src = assoc + req->assoclen;
dst = src;
}
+ kernel_fpu_begin();
aesni_gcm_enc_tfm(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv,
ctx->hash_subkey, assoc, (unsigned long)req->assoclen, dst
+ ((unsigned long)req->cryptlen), auth_tag_len);
+ kernel_fpu_end();
/* The authTag (aka the Integrity Check Value) needs to be written
* back to the packet. */
if (one_entry_in_sg) {
if (unlikely(req->src != req->dst)) {
- scatterwalk_unmap(dst);
- scatterwalk_done(&dst_sg_walk, 0, 0);
+ scatterwalk_unmap(dst - req->assoclen);
+ scatterwalk_advance(&dst_sg_walk, req->dst->length);
+ scatterwalk_done(&dst_sg_walk, 1, 0);
}
- scatterwalk_unmap(src);
scatterwalk_unmap(assoc);
- scatterwalk_done(&src_sg_walk, 0, 0);
- scatterwalk_done(&assoc_sg_walk, 0, 0);
+ scatterwalk_advance(&src_sg_walk, req->src->length);
+ scatterwalk_done(&src_sg_walk, req->src == req->dst, 0);
} else {
- scatterwalk_map_and_copy(dst, req->dst, 0,
- req->cryptlen + auth_tag_len, 1);
- kfree(src);
+ scatterwalk_map_and_copy(dst, req->dst, req->assoclen,
+ req->cryptlen + auth_tag_len, 1);
+ kfree(assoc);
}
return 0;
}
-static int __driver_rfc4106_decrypt(struct aead_request *req)
+static int helper_rfc4106_decrypt(struct aead_request *req)
{
u8 one_entry_in_sg = 0;
u8 *src, *dst, *assoc;
@@ -1087,26 +1025,16 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
int retval = 0;
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
- u32 key_len = ctx->aes_key_expanded.key_length;
void *aes_ctx = &(ctx->aes_key_expanded);
unsigned long auth_tag_len = crypto_aead_authsize(tfm);
- u8 iv_and_authTag[32+AESNI_ALIGN];
- u8 *iv = (u8 *) PTR_ALIGN((u8 *)iv_and_authTag, AESNI_ALIGN);
- u8 *authTag = iv + 16;
+ u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+ u8 authTag[16];
struct scatter_walk src_sg_walk;
- struct scatter_walk assoc_sg_walk;
struct scatter_walk dst_sg_walk;
unsigned int i;
- if (unlikely((req->cryptlen < auth_tag_len) ||
- (req->assoclen != 8 && req->assoclen != 12)))
+ if (unlikely(req->assoclen != 8 && req->assoclen != 12))
return -EINVAL;
- if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16))
- return -EINVAL;
- if (unlikely(key_len != AES_KEYSIZE_128 &&
- key_len != AES_KEYSIZE_192 &&
- key_len != AES_KEYSIZE_256))
- return -EINVAL;
/* Assuming we are supporting rfc4106 64-bit extended */
/* sequence numbers We need to have the AAD length */
@@ -1120,33 +1048,36 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
*(iv+4+i) = req->iv[i];
*((__be32 *)(iv+12)) = counter;
- if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) {
+ if (sg_is_last(req->src) &&
+ req->src->offset + req->src->length <= PAGE_SIZE &&
+ sg_is_last(req->dst) &&
+ req->dst->offset + req->dst->length <= PAGE_SIZE) {
one_entry_in_sg = 1;
scatterwalk_start(&src_sg_walk, req->src);
- scatterwalk_start(&assoc_sg_walk, req->assoc);
- src = scatterwalk_map(&src_sg_walk);
- assoc = scatterwalk_map(&assoc_sg_walk);
+ assoc = scatterwalk_map(&src_sg_walk);
+ src = assoc + req->assoclen;
dst = src;
if (unlikely(req->src != req->dst)) {
scatterwalk_start(&dst_sg_walk, req->dst);
- dst = scatterwalk_map(&dst_sg_walk);
+ dst = scatterwalk_map(&dst_sg_walk) + req->assoclen;
}
} else {
/* Allocate memory for src, dst, assoc */
- src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
- if (!src)
+ assoc = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
+ if (!assoc)
return -ENOMEM;
- assoc = (src + req->cryptlen);
- scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
- scatterwalk_map_and_copy(assoc, req->assoc, 0,
- req->assoclen, 0);
+ scatterwalk_map_and_copy(assoc, req->src, 0,
+ req->assoclen + req->cryptlen, 0);
+ src = assoc + req->assoclen;
dst = src;
}
+ kernel_fpu_begin();
aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv,
ctx->hash_subkey, assoc, (unsigned long)req->assoclen,
authTag, auth_tag_len);
+ kernel_fpu_end();
/* Compare generated tag with passed in tag. */
retval = crypto_memneq(src + tempCipherLen, authTag, auth_tag_len) ?
@@ -1154,90 +1085,59 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
if (one_entry_in_sg) {
if (unlikely(req->src != req->dst)) {
- scatterwalk_unmap(dst);
- scatterwalk_done(&dst_sg_walk, 0, 0);
+ scatterwalk_unmap(dst - req->assoclen);
+ scatterwalk_advance(&dst_sg_walk, req->dst->length);
+ scatterwalk_done(&dst_sg_walk, 1, 0);
}
- scatterwalk_unmap(src);
scatterwalk_unmap(assoc);
- scatterwalk_done(&src_sg_walk, 0, 0);
- scatterwalk_done(&assoc_sg_walk, 0, 0);
+ scatterwalk_advance(&src_sg_walk, req->src->length);
+ scatterwalk_done(&src_sg_walk, req->src == req->dst, 0);
} else {
- scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
- kfree(src);
+ scatterwalk_map_and_copy(dst, req->dst, req->assoclen,
+ tempCipherLen, 1);
+ kfree(assoc);
}
return retval;
}
static int rfc4106_encrypt(struct aead_request *req)
{
- int ret;
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
- struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+ struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
+ struct cryptd_aead *cryptd_tfm = *ctx;
+ struct aead_request *subreq = aead_request_ctx(req);
- if (!irq_fpu_usable()) {
- struct aead_request *cryptd_req =
- (struct aead_request *) aead_request_ctx(req);
+ aead_request_set_tfm(subreq, irq_fpu_usable() ?
+ cryptd_aead_child(cryptd_tfm) :
+ &cryptd_tfm->base);
- memcpy(cryptd_req, req, sizeof(*req));
- aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
- ret = crypto_aead_encrypt(cryptd_req);
- } else {
- kernel_fpu_begin();
- ret = __driver_rfc4106_encrypt(req);
- kernel_fpu_end();
- }
- return ret;
+ aead_request_set_callback(subreq, req->base.flags,
+ req->base.complete, req->base.data);
+ aead_request_set_crypt(subreq, req->src, req->dst,
+ req->cryptlen, req->iv);
+ aead_request_set_ad(subreq, req->assoclen);
+
+ return crypto_aead_encrypt(subreq);
}
static int rfc4106_decrypt(struct aead_request *req)
{
- int ret;
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
- struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+ struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
+ struct cryptd_aead *cryptd_tfm = *ctx;
+ struct aead_request *subreq = aead_request_ctx(req);
- if (!irq_fpu_usable()) {
- struct aead_request *cryptd_req =
- (struct aead_request *) aead_request_ctx(req);
+ aead_request_set_tfm(subreq, irq_fpu_usable() ?
+ cryptd_aead_child(cryptd_tfm) :
+ &cryptd_tfm->base);
- memcpy(cryptd_req, req, sizeof(*req));
- aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
- ret = crypto_aead_decrypt(cryptd_req);
- } else {
- kernel_fpu_begin();
- ret = __driver_rfc4106_decrypt(req);
- kernel_fpu_end();
- }
- return ret;
-}
-
-static int helper_rfc4106_encrypt(struct aead_request *req)
-{
- int ret;
-
- if (unlikely(!irq_fpu_usable())) {
- WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context");
- ret = -EINVAL;
- } else {
- kernel_fpu_begin();
- ret = __driver_rfc4106_encrypt(req);
- kernel_fpu_end();
- }
- return ret;
-}
-
-static int helper_rfc4106_decrypt(struct aead_request *req)
-{
- int ret;
+ aead_request_set_callback(subreq, req->base.flags,
+ req->base.complete, req->base.data);
+ aead_request_set_crypt(subreq, req->src, req->dst,
+ req->cryptlen, req->iv);
+ aead_request_set_ad(subreq, req->assoclen);
- if (unlikely(!irq_fpu_usable())) {
- WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context");
- ret = -EINVAL;
- } else {
- kernel_fpu_begin();
- ret = __driver_rfc4106_decrypt(req);
- kernel_fpu_end();
- }
- return ret;
+ return crypto_aead_decrypt(subreq);
}
#endif
@@ -1410,51 +1310,6 @@ static struct crypto_alg aesni_algs[] = { {
.geniv = "chainiv",
},
},
-}, {
- .cra_name = "__gcm-aes-aesni",
- .cra_driver_name = "__driver-gcm-aes-aesni",
- .cra_priority = 0,
- .cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_INTERNAL,
- .cra_blocksize = 1,
- .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx) +
- AESNI_ALIGN,
- .cra_alignmask = 0,
- .cra_type = &crypto_aead_type,
- .cra_module = THIS_MODULE,
- .cra_u = {
- .aead = {
- .setkey = common_rfc4106_set_key,
- .setauthsize = common_rfc4106_set_authsize,
- .encrypt = helper_rfc4106_encrypt,
- .decrypt = helper_rfc4106_decrypt,
- .ivsize = 8,
- .maxauthsize = 16,
- },
- },
-}, {
- .cra_name = "rfc4106(gcm(aes))",
- .cra_driver_name = "rfc4106-gcm-aesni",
- .cra_priority = 400,
- .cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
- .cra_blocksize = 1,
- .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx) +
- AESNI_ALIGN,
- .cra_alignmask = 0,
- .cra_type = &crypto_nivaead_type,
- .cra_module = THIS_MODULE,
- .cra_init = rfc4106_init,
- .cra_exit = rfc4106_exit,
- .cra_u = {
- .aead = {
- .setkey = rfc4106_set_key,
- .setauthsize = rfc4106_set_authsize,
- .encrypt = rfc4106_encrypt,
- .decrypt = rfc4106_decrypt,
- .geniv = "seqiv",
- .ivsize = 8,
- .maxauthsize = 16,
- },
- },
#endif
#if IS_ENABLED(CONFIG_CRYPTO_PCBC)
}, {
@@ -1569,6 +1424,46 @@ static struct crypto_alg aesni_algs[] = { {
},
} };
+#ifdef CONFIG_X86_64
+static struct aead_alg aesni_aead_algs[] = { {
+ .setkey = common_rfc4106_set_key,
+ .setauthsize = common_rfc4106_set_authsize,
+ .encrypt = helper_rfc4106_encrypt,
+ .decrypt = helper_rfc4106_decrypt,
+ .ivsize = 8,
+ .maxauthsize = 16,
+ .base = {
+ .cra_name = "__gcm-aes-aesni",
+ .cra_driver_name = "__driver-gcm-aes-aesni",
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx),
+ .cra_alignmask = AESNI_ALIGN - 1,
+ .cra_module = THIS_MODULE,
+ },
+}, {
+ .init = rfc4106_init,
+ .exit = rfc4106_exit,
+ .setkey = rfc4106_set_key,
+ .setauthsize = rfc4106_set_authsize,
+ .encrypt = rfc4106_encrypt,
+ .decrypt = rfc4106_decrypt,
+ .ivsize = 8,
+ .maxauthsize = 16,
+ .base = {
+ .cra_name = "rfc4106(gcm(aes))",
+ .cra_driver_name = "rfc4106-gcm-aesni",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_ASYNC,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct cryptd_aead *),
+ .cra_module = THIS_MODULE,
+ },
+} };
+#else
+static struct aead_alg aesni_aead_algs[0];
+#endif
+
static const struct x86_cpu_id aesni_cpu_id[] = {
X86_FEATURE_MATCH(X86_FEATURE_AES),
@@ -1616,11 +1511,27 @@ static int __init aesni_init(void)
if (err)
return err;
- return crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+ err = crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+ if (err)
+ goto fpu_exit;
+
+ err = crypto_register_aeads(aesni_aead_algs,
+ ARRAY_SIZE(aesni_aead_algs));
+ if (err)
+ goto unregister_algs;
+
+ return err;
+
+unregister_algs:
+ crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+fpu_exit:
+ crypto_fpu_exit();
+ return err;
}
static void __exit aesni_exit(void)
{
+ crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs));
crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
crypto_fpu_exit();
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index baf0ac21ace5..4c65c70e628b 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -19,8 +19,7 @@
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/camellia.h>
#include <asm/crypto/glue_helper.h>
@@ -561,16 +560,15 @@ static struct crypto_alg cmll_algs[10] = { {
static int __init camellia_aesni_init(void)
{
- u64 xcr0;
+ const char *feature_name;
if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
pr_info("AVX2 or AES-NI instructions are not detected.\n");
return -ENODEV;
}
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX2 detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 78818a1e73e3..80a0e4389c9a 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -19,8 +19,7 @@
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/camellia.h>
#include <asm/crypto/glue_helper.h>
@@ -553,16 +552,10 @@ static struct crypto_alg cmll_algs[10] = { {
static int __init camellia_aesni_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
- pr_info("AVX or AES-NI instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 236c80974457..be00aa48b2b5 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -31,8 +31,7 @@
#include <crypto/cast5.h>
#include <crypto/cryptd.h>
#include <crypto/ctr.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/glue_helper.h>
#define CAST5_PARALLEL_BLOCKS 16
@@ -468,16 +467,10 @@ static struct crypto_alg cast5_algs[6] = { {
static int __init cast5_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_osxsave) {
- pr_info("AVX instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index f448810ca4ac..5dbba7224221 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -36,8 +36,7 @@
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/glue_helper.h>
#define CAST6_PARALLEL_BLOCKS 8
@@ -590,16 +589,10 @@ static struct crypto_alg cast6_algs[10] = { {
static int __init cast6_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_osxsave) {
- pr_info("AVX instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 1937fc1d8763..07d2c6c86a54 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -35,7 +35,7 @@
#include <asm/cpufeature.h>
#include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#define CHKSUM_BLOCK_SIZE 1
#define CHKSUM_DIGEST_SIZE 4
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 28640c3d6af7..81a595d75cf5 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -32,8 +32,7 @@
#include <asm/cpufeature.h>
#include <asm/cpu_device_id.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#define CHKSUM_BLOCK_SIZE 1
#define CHKSUM_DIGEST_SIZE 4
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index b6c67bf30fdf..a3fcfc97a311 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -29,7 +29,7 @@
#include <linux/init.h>
#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/cpufeature.h>
#include <asm/cpu_device_id.h>
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index f368ba261739..e7d679e2a018 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -18,7 +18,7 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
struct crypto_fpu_ctx {
struct crypto_blkcipher *child;
@@ -156,7 +156,7 @@ int __init crypto_fpu_init(void)
return crypto_register_template(&crypto_fpu_tmpl);
}
-void __exit crypto_fpu_exit(void)
+void crypto_fpu_exit(void)
{
crypto_unregister_template(&crypto_fpu_tmpl);
}
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 2079baf06bdd..64d7cf1b50e1 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -19,7 +19,7 @@
#include <crypto/cryptd.h>
#include <crypto/gf128mul.h>
#include <crypto/internal/hash.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/cpu_device_id.h>
#define GHASH_BLOCK_SIZE 16
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 2f63dc89e7a9..7d838dc4d888 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -20,8 +20,7 @@
#include <crypto/lrw.h>
#include <crypto/xts.h>
#include <crypto/serpent.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/serpent-avx.h>
#include <asm/crypto/glue_helper.h>
@@ -537,16 +536,14 @@ static struct crypto_alg srp_algs[10] = { {
static int __init init(void)
{
- u64 xcr0;
+ const char *feature_name;
if (!cpu_has_avx2 || !cpu_has_osxsave) {
pr_info("AVX2 instructions are not detected.\n");
return -ENODEV;
}
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index c8d478af8456..da7dafc9b16d 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -36,8 +36,7 @@
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/serpent-avx.h>
#include <asm/crypto/glue_helper.h>
@@ -596,16 +595,10 @@ static struct crypto_alg serpent_algs[10] = { {
static int __init serpent_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_osxsave) {
- printk(KERN_INFO "AVX instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- printk(KERN_INFO "AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index e510b1c5d690..a841e9765bd6 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -65,11 +65,8 @@
#include <crypto/mcryptd.h>
#include <crypto/crypto_wq.h>
#include <asm/byteorder.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
#include <linux/hardirq.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/api.h>
#include "sha_mb_ctx.h"
#define FLUSH_INTERVAL 1000 /* in usec */
@@ -885,7 +882,8 @@ static int __init sha1_mb_mod_init(void)
INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
cpu_state->cpu = cpu;
cpu_state->alg_state = &sha1_mb_alg_state;
- cpu_state->mgr = (struct sha1_ctx_mgr *) kzalloc(sizeof(struct sha1_ctx_mgr), GFP_KERNEL);
+ cpu_state->mgr = kzalloc(sizeof(struct sha1_ctx_mgr),
+ GFP_KERNEL);
if (!cpu_state->mgr)
goto err2;
sha1_ctx_mgr_init(cpu_state->mgr);
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 33d1b9dc14cc..7c48e8b20848 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -29,9 +29,7 @@
#include <linux/types.h>
#include <crypto/sha.h>
#include <crypto/sha1_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
@@ -123,15 +121,9 @@ static struct shash_alg alg = {
#ifdef CONFIG_AS_AVX
static bool __init avx_usable(void)
{
- u64 xcr0;
-
- if (!cpu_has_avx || !cpu_has_osxsave)
- return false;
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
-
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+ if (cpu_has_avx)
+ pr_info("AVX detected but unusable.\n");
return false;
}
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index ccc338881ee8..f8097fc0d1d1 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -37,9 +37,7 @@
#include <linux/types.h>
#include <crypto/sha.h>
#include <crypto/sha256_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <linux/string.h>
asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data,
@@ -132,15 +130,9 @@ static struct shash_alg algs[] = { {
#ifdef CONFIG_AS_AVX
static bool __init avx_usable(void)
{
- u64 xcr0;
-
- if (!cpu_has_avx || !cpu_has_osxsave)
- return false;
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
-
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+ if (cpu_has_avx)
+ pr_info("AVX detected but unusable.\n");
return false;
}
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index d9fa4c1e063f..2edad7b81870 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -35,9 +35,7 @@
#include <linux/types.h>
#include <crypto/sha.h>
#include <crypto/sha512_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <linux/string.h>
@@ -131,15 +129,9 @@ static struct shash_alg algs[] = { {
#ifdef CONFIG_AS_AVX
static bool __init avx_usable(void)
{
- u64 xcr0;
-
- if (!cpu_has_avx || !cpu_has_osxsave)
- return false;
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
-
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+ if (cpu_has_avx)
+ pr_info("AVX detected but unusable.\n");
return false;
}
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index b5e2d5651851..c2bd0ce718ee 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -36,9 +36,7 @@
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/twofish.h>
#include <asm/crypto/glue_helper.h>
#include <crypto/scatterwalk.h>
@@ -558,16 +556,10 @@ static struct crypto_alg twofish_algs[10] = { {
static int __init twofish_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_osxsave) {
- printk(KERN_INFO "AVX instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- printk(KERN_INFO "AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
new file mode 100644
index 000000000000..7a144971db79
--- /dev/null
+++ b/arch/x86/entry/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the x86 low level entry code
+#
+obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+
+obj-y += vdso/
+obj-y += vsyscall/
+
+obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o
+
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/entry/calling.h
index 1c8b50edb2db..f4e6308c4200 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/entry/calling.h
@@ -46,8 +46,6 @@ For 32-bit we have the following conventions - kernel is built with
*/
-#include <asm/dwarf2.h>
-
#ifdef CONFIG_X86_64
/*
@@ -91,28 +89,27 @@ For 32-bit we have the following conventions - kernel is built with
#define SIZEOF_PTREGS 21*8
.macro ALLOC_PT_GPREGS_ON_STACK addskip=0
- subq $15*8+\addskip, %rsp
- CFI_ADJUST_CFA_OFFSET 15*8+\addskip
+ addq $-(15*8+\addskip), %rsp
.endm
.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
.if \r11
- movq_cfi r11, 6*8+\offset
+ movq %r11, 6*8+\offset(%rsp)
.endif
.if \r8910
- movq_cfi r10, 7*8+\offset
- movq_cfi r9, 8*8+\offset
- movq_cfi r8, 9*8+\offset
+ movq %r10, 7*8+\offset(%rsp)
+ movq %r9, 8*8+\offset(%rsp)
+ movq %r8, 9*8+\offset(%rsp)
.endif
.if \rax
- movq_cfi rax, 10*8+\offset
+ movq %rax, 10*8+\offset(%rsp)
.endif
.if \rcx
- movq_cfi rcx, 11*8+\offset
+ movq %rcx, 11*8+\offset(%rsp)
.endif
- movq_cfi rdx, 12*8+\offset
- movq_cfi rsi, 13*8+\offset
- movq_cfi rdi, 14*8+\offset
+ movq %rdx, 12*8+\offset(%rsp)
+ movq %rsi, 13*8+\offset(%rsp)
+ movq %rdi, 14*8+\offset(%rsp)
.endm
.macro SAVE_C_REGS offset=0
SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
@@ -131,24 +128,24 @@ For 32-bit we have the following conventions - kernel is built with
.endm
.macro SAVE_EXTRA_REGS offset=0
- movq_cfi r15, 0*8+\offset
- movq_cfi r14, 1*8+\offset
- movq_cfi r13, 2*8+\offset
- movq_cfi r12, 3*8+\offset
- movq_cfi rbp, 4*8+\offset
- movq_cfi rbx, 5*8+\offset
+ movq %r15, 0*8+\offset(%rsp)
+ movq %r14, 1*8+\offset(%rsp)
+ movq %r13, 2*8+\offset(%rsp)
+ movq %r12, 3*8+\offset(%rsp)
+ movq %rbp, 4*8+\offset(%rsp)
+ movq %rbx, 5*8+\offset(%rsp)
.endm
.macro SAVE_EXTRA_REGS_RBP offset=0
- movq_cfi rbp, 4*8+\offset
+ movq %rbp, 4*8+\offset(%rsp)
.endm
.macro RESTORE_EXTRA_REGS offset=0
- movq_cfi_restore 0*8+\offset, r15
- movq_cfi_restore 1*8+\offset, r14
- movq_cfi_restore 2*8+\offset, r13
- movq_cfi_restore 3*8+\offset, r12
- movq_cfi_restore 4*8+\offset, rbp
- movq_cfi_restore 5*8+\offset, rbx
+ movq 0*8+\offset(%rsp), %r15
+ movq 1*8+\offset(%rsp), %r14
+ movq 2*8+\offset(%rsp), %r13
+ movq 3*8+\offset(%rsp), %r12
+ movq 4*8+\offset(%rsp), %rbp
+ movq 5*8+\offset(%rsp), %rbx
.endm
.macro ZERO_EXTRA_REGS
@@ -162,24 +159,24 @@ For 32-bit we have the following conventions - kernel is built with
.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
.if \rstor_r11
- movq_cfi_restore 6*8, r11
+ movq 6*8(%rsp), %r11
.endif
.if \rstor_r8910
- movq_cfi_restore 7*8, r10
- movq_cfi_restore 8*8, r9
- movq_cfi_restore 9*8, r8
+ movq 7*8(%rsp), %r10
+ movq 8*8(%rsp), %r9
+ movq 9*8(%rsp), %r8
.endif
.if \rstor_rax
- movq_cfi_restore 10*8, rax
+ movq 10*8(%rsp), %rax
.endif
.if \rstor_rcx
- movq_cfi_restore 11*8, rcx
+ movq 11*8(%rsp), %rcx
.endif
.if \rstor_rdx
- movq_cfi_restore 12*8, rdx
+ movq 12*8(%rsp), %rdx
.endif
- movq_cfi_restore 13*8, rsi
- movq_cfi_restore 14*8, rdi
+ movq 13*8(%rsp), %rsi
+ movq 14*8(%rsp), %rdi
.endm
.macro RESTORE_C_REGS
RESTORE_C_REGS_HELPER 1,1,1,1,1
@@ -204,8 +201,7 @@ For 32-bit we have the following conventions - kernel is built with
.endm
.macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
- addq $15*8+\addskip, %rsp
- CFI_ADJUST_CFA_OFFSET -(15*8+\addskip)
+ subq $-(15*8+\addskip), %rsp
.endm
.macro icebp
@@ -224,23 +220,23 @@ For 32-bit we have the following conventions - kernel is built with
*/
.macro SAVE_ALL
- pushl_cfi_reg eax
- pushl_cfi_reg ebp
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg edx
- pushl_cfi_reg ecx
- pushl_cfi_reg ebx
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
.endm
.macro RESTORE_ALL
- popl_cfi_reg ebx
- popl_cfi_reg ecx
- popl_cfi_reg edx
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi_reg ebp
- popl_cfi_reg eax
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
.endm
#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
new file mode 100644
index 000000000000..21dc60a60b5f
--- /dev/null
+++ b/arch/x86/entry/entry_32.S
@@ -0,0 +1,1248 @@
+/*
+ * Copyright (C) 1991,1992 Linus Torvalds
+ *
+ * entry_32.S contains the system-call and low-level fault and trap handling routines.
+ *
+ * Stack layout in 'syscall_exit':
+ * ptrace needs to have all registers on the stack.
+ * If the order here is changed, it needs to be
+ * updated in fork.c:copy_process(), signal.c:do_signal(),
+ * ptrace.c and ptrace.h
+ *
+ * 0(%esp) - %ebx
+ * 4(%esp) - %ecx
+ * 8(%esp) - %edx
+ * C(%esp) - %esi
+ * 10(%esp) - %edi
+ * 14(%esp) - %ebp
+ * 18(%esp) - %eax
+ * 1C(%esp) - %ds
+ * 20(%esp) - %es
+ * 24(%esp) - %fs
+ * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
+ * 2C(%esp) - orig_eax
+ * 30(%esp) - %eip
+ * 34(%esp) - %cs
+ * 38(%esp) - %eflags
+ * 3C(%esp) - %oldesp
+ * 40(%esp) - %oldss
+ */
+
+#include <linux/linkage.h>
+#include <linux/err.h>
+#include <asm/thread_info.h>
+#include <asm/irqflags.h>
+#include <asm/errno.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+#include <asm/ftrace.h>
+#include <asm/irq_vectors.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE 0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysenter_audit syscall_trace_entry
+# define sysexit_audit syscall_exit_work
+#endif
+
+ .section .entry.text, "ax"
+
+/*
+ * We use macros for low-level operations which need to be overridden
+ * for paravirtualization. The following will never clobber any registers:
+ * INTERRUPT_RETURN (aka. "iret")
+ * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
+ * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
+ *
+ * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
+ * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
+ * Allowing a register to be clobbered can shrink the paravirt replacement
+ * enough to patch inline, increasing performance.
+ */
+
+#ifdef CONFIG_PREEMPT
+# define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
+#else
+# define preempt_stop(clobbers)
+# define resume_kernel restore_all
+#endif
+
+.macro TRACE_IRQS_IRET
+#ifdef CONFIG_TRACE_IRQFLAGS
+ testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off?
+ jz 1f
+ TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+/*
+ * User gs save/restore
+ *
+ * %gs is used for userland TLS and kernel only uses it for stack
+ * canary which is required to be at %gs:20 by gcc. Read the comment
+ * at the top of stackprotector.h for more info.
+ *
+ * Local labels 98 and 99 are used.
+ */
+#ifdef CONFIG_X86_32_LAZY_GS
+
+ /* unfortunately push/pop can't be no-op */
+.macro PUSH_GS
+ pushl $0
+.endm
+.macro POP_GS pop=0
+ addl $(4 + \pop), %esp
+.endm
+.macro POP_GS_EX
+.endm
+
+ /* all the rest are no-op */
+.macro PTGS_TO_GS
+.endm
+.macro PTGS_TO_GS_EX
+.endm
+.macro GS_TO_REG reg
+.endm
+.macro REG_TO_PTGS reg
+.endm
+.macro SET_KERNEL_GS reg
+.endm
+
+#else /* CONFIG_X86_32_LAZY_GS */
+
+.macro PUSH_GS
+ pushl %gs
+.endm
+
+.macro POP_GS pop=0
+98: popl %gs
+ .if \pop <> 0
+ add $\pop, %esp
+ .endif
+.endm
+.macro POP_GS_EX
+.pushsection .fixup, "ax"
+99: movl $0, (%esp)
+ jmp 98b
+.popsection
+ _ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro PTGS_TO_GS
+98: mov PT_GS(%esp), %gs
+.endm
+.macro PTGS_TO_GS_EX
+.pushsection .fixup, "ax"
+99: movl $0, PT_GS(%esp)
+ jmp 98b
+.popsection
+ _ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro GS_TO_REG reg
+ movl %gs, \reg
+.endm
+.macro REG_TO_PTGS reg
+ movl \reg, PT_GS(%esp)
+.endm
+.macro SET_KERNEL_GS reg
+ movl $(__KERNEL_STACK_CANARY), \reg
+ movl \reg, %gs
+.endm
+
+#endif /* CONFIG_X86_32_LAZY_GS */
+
+.macro SAVE_ALL
+ cld
+ PUSH_GS
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ movl $(__USER_DS), %edx
+ movl %edx, %ds
+ movl %edx, %es
+ movl $(__KERNEL_PERCPU), %edx
+ movl %edx, %fs
+ SET_KERNEL_GS %edx
+.endm
+
+.macro RESTORE_INT_REGS
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+.endm
+
+.macro RESTORE_REGS pop=0
+ RESTORE_INT_REGS
+1: popl %ds
+2: popl %es
+3: popl %fs
+ POP_GS \pop
+.pushsection .fixup, "ax"
+4: movl $0, (%esp)
+ jmp 1b
+5: movl $0, (%esp)
+ jmp 2b
+6: movl $0, (%esp)
+ jmp 3b
+.popsection
+ _ASM_EXTABLE(1b, 4b)
+ _ASM_EXTABLE(2b, 5b)
+ _ASM_EXTABLE(3b, 6b)
+ POP_GS_EX
+.endm
+
+ENTRY(ret_from_fork)
+ pushl %eax
+ call schedule_tail
+ GET_THREAD_INFO(%ebp)
+ popl %eax
+ pushl $0x0202 # Reset kernel eflags
+ popfl
+ jmp syscall_exit
+END(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+ pushl %eax
+ call schedule_tail
+ GET_THREAD_INFO(%ebp)
+ popl %eax
+ pushl $0x0202 # Reset kernel eflags
+ popfl
+ movl PT_EBP(%esp), %eax
+ call *PT_EBX(%esp)
+ movl $0, PT_EAX(%esp)
+ jmp syscall_exit
+ENDPROC(ret_from_kernel_thread)
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+ # userspace resumption stub bypassing syscall exit tracing
+ ALIGN
+ret_from_exception:
+ preempt_stop(CLBR_ANY)
+ret_from_intr:
+ GET_THREAD_INFO(%ebp)
+#ifdef CONFIG_VM86
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
+#else
+ /*
+ * We can be coming here from child spawned by kernel_thread().
+ */
+ movl PT_CS(%esp), %eax
+ andl $SEGMENT_RPL_MASK, %eax
+#endif
+ cmpl $USER_RPL, %eax
+ jb resume_kernel # not returning to v8086 or userspace
+
+ENTRY(resume_userspace)
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ andl $_TIF_WORK_MASK, %ecx # is there any work to be done on
+ # int/exception return?
+ jne work_pending
+ jmp restore_all
+END(ret_from_exception)
+
+#ifdef CONFIG_PREEMPT
+ENTRY(resume_kernel)
+ DISABLE_INTERRUPTS(CLBR_ANY)
+need_resched:
+ cmpl $0, PER_CPU_VAR(__preempt_count)
+ jnz restore_all
+ testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
+ jz restore_all
+ call preempt_schedule_irq
+ jmp need_resched
+END(resume_kernel)
+#endif
+
+/*
+ * SYSENTER_RETURN points to after the SYSENTER instruction
+ * in the vsyscall page. See vsyscall-sysentry.S, which defines
+ * the symbol.
+ */
+
+ # SYSENTER call handler stub
+ENTRY(entry_SYSENTER_32)
+ movl TSS_sysenter_sp0(%esp), %esp
+sysenter_past_esp:
+ /*
+ * Interrupts are disabled here, but we can't trace it until
+ * enough kernel state to call TRACE_IRQS_OFF can be called - but
+ * we immediately enable interrupts at that point anyway.
+ */
+ pushl $__USER_DS
+ pushl %ebp
+ pushfl
+ orl $X86_EFLAGS_IF, (%esp)
+ pushl $__USER_CS
+ /*
+ * Push current_thread_info()->sysenter_return to the stack.
+ * A tiny bit of offset fixup is necessary: TI_sysenter_return
+ * is relative to thread_info, which is at the bottom of the
+ * kernel stack page. 4*4 means the 4 words pushed above;
+ * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
+ * and THREAD_SIZE takes us to the bottom.
+ */
+ pushl ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
+
+ pushl %eax
+ SAVE_ALL
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+/*
+ * Load the potential sixth argument from user stack.
+ * Careful about security.
+ */
+ cmpl $__PAGE_OFFSET-3, %ebp
+ jae syscall_fault
+ ASM_STAC
+1: movl (%ebp), %ebp
+ ASM_CLAC
+ movl %ebp, PT_EBP(%esp)
+ _ASM_EXTABLE(1b, syscall_fault)
+
+ GET_THREAD_INFO(%ebp)
+
+ testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+ jnz sysenter_audit
+sysenter_do_call:
+ cmpl $(NR_syscalls), %eax
+ jae sysenter_badsys
+ call *sys_call_table(, %eax, 4)
+sysenter_after_call:
+ movl %eax, PT_EAX(%esp)
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $_TIF_ALLWORK_MASK, %ecx
+ jnz sysexit_audit
+sysenter_exit:
+/* if something modifies registers it must also disable sysexit */
+ movl PT_EIP(%esp), %edx
+ movl PT_OLDESP(%esp), %ecx
+ xorl %ebp, %ebp
+ TRACE_IRQS_ON
+1: mov PT_FS(%esp), %fs
+ PTGS_TO_GS
+ ENABLE_INTERRUPTS_SYSEXIT
+
+#ifdef CONFIG_AUDITSYSCALL
+sysenter_audit:
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), TI_flags(%ebp)
+ jnz syscall_trace_entry
+ /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
+ movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */
+ /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
+ pushl PT_ESI(%esp) /* a3: 5th arg */
+ pushl PT_EDX+4(%esp) /* a2: 4th arg */
+ call __audit_syscall_entry
+ popl %ecx /* get that remapped edx off the stack */
+ popl %ecx /* get that remapped esi off the stack */
+ movl PT_EAX(%esp), %eax /* reload syscall number */
+ jmp sysenter_do_call
+
+sysexit_audit:
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+ jnz syscall_exit_work
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_ANY)
+ movl %eax, %edx /* second arg, syscall return value */
+ cmpl $-MAX_ERRNO, %eax /* is it an error ? */
+ setbe %al /* 1 if so, 0 if not */
+ movzbl %al, %eax /* zero-extend that */
+ call __audit_syscall_exit
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+ jnz syscall_exit_work
+ movl PT_EAX(%esp), %eax /* reload syscall return value */
+ jmp sysenter_exit
+#endif
+
+.pushsection .fixup, "ax"
+2: movl $0, PT_FS(%esp)
+ jmp 1b
+.popsection
+ _ASM_EXTABLE(1b, 2b)
+ PTGS_TO_GS_EX
+ENDPROC(entry_SYSENTER_32)
+
+ # system call handler stub
+ENTRY(entry_INT80_32)
+ ASM_CLAC
+ pushl %eax # save orig_eax
+ SAVE_ALL
+ GET_THREAD_INFO(%ebp)
+ # system call tracing in operation / emulation
+ testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+ jnz syscall_trace_entry
+ cmpl $(NR_syscalls), %eax
+ jae syscall_badsys
+syscall_call:
+ call *sys_call_table(, %eax, 4)
+syscall_after_call:
+ movl %eax, PT_EAX(%esp) # store the return value
+syscall_exit:
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $_TIF_ALLWORK_MASK, %ecx # current->work
+ jnz syscall_exit_work
+
+restore_all:
+ TRACE_IRQS_IRET
+restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
+ /*
+ * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+ * are returning to the kernel.
+ * See comments in process.c:copy_thread() for details.
+ */
+ movb PT_OLDSS(%esp), %ah
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+ cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
+ je ldt_ss # returning to user-space with LDT SS
+#endif
+restore_nocheck:
+ RESTORE_REGS 4 # skip orig_eax/error_code
+irq_return:
+ INTERRUPT_RETURN
+.section .fixup, "ax"
+ENTRY(iret_exc )
+ pushl $0 # no error code
+ pushl $do_iret_error
+ jmp error_code
+.previous
+ _ASM_EXTABLE(irq_return, iret_exc)
+
+#ifdef CONFIG_X86_ESPFIX32
+ldt_ss:
+#ifdef CONFIG_PARAVIRT
+ /*
+ * The kernel can't run on a non-flat stack if paravirt mode
+ * is active. Rather than try to fixup the high bits of
+ * ESP, bypass this code entirely. This may break DOSemu
+ * and/or Wine support in a paravirt VM, although the option
+ * is still available to implement the setting of the high
+ * 16-bits in the INTERRUPT_RETURN paravirt-op.
+ */
+ cmpl $0, pv_info+PARAVIRT_enabled
+ jne restore_nocheck
+#endif
+
+/*
+ * Setup and switch to ESPFIX stack
+ *
+ * We're returning to userspace with a 16 bit stack. The CPU will not
+ * restore the high word of ESP for us on executing iret... This is an
+ * "official" bug of all the x86-compatible CPUs, which we can work
+ * around to make dosemu and wine happy. We do this by preloading the
+ * high word of ESP with the high word of the userspace ESP while
+ * compensating for the offset by changing to the ESPFIX segment with
+ * a base address that matches for the difference.
+ */
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+ mov %esp, %edx /* load kernel esp */
+ mov PT_OLDESP(%esp), %eax /* load userspace esp */
+ mov %dx, %ax /* eax: new kernel esp */
+ sub %eax, %edx /* offset (low word is 0) */
+ shr $16, %edx
+ mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
+ mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
+ pushl $__ESPFIX_SS
+ pushl %eax /* new kernel esp */
+ /*
+ * Disable interrupts, but do not irqtrace this section: we
+ * will soon execute iret and the tracer was already set to
+ * the irqstate after the IRET:
+ */
+ DISABLE_INTERRUPTS(CLBR_EAX)
+ lss (%esp), %esp /* switch to espfix segment */
+ jmp restore_nocheck
+#endif
+ENDPROC(entry_INT80_32)
+
+ # perform work that needs to be done immediately before resumption
+ ALIGN
+work_pending:
+ testb $_TIF_NEED_RESCHED, %cl
+ jz work_notifysig
+work_resched:
+ call schedule
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ andl $_TIF_WORK_MASK, %ecx # is there any work to be done other
+ # than syscall tracing?
+ jz restore_all
+ testb $_TIF_NEED_RESCHED, %cl
+ jnz work_resched
+
+work_notifysig: # deal with pending signals and
+ # notify-resume requests
+#ifdef CONFIG_VM86
+ testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
+ movl %esp, %eax
+ jnz work_notifysig_v86 # returning to kernel-space or
+ # vm86-space
+1:
+#else
+ movl %esp, %eax
+#endif
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ movb PT_CS(%esp), %bl
+ andb $SEGMENT_RPL_MASK, %bl
+ cmpb $USER_RPL, %bl
+ jb resume_kernel
+ xorl %edx, %edx
+ call do_notify_resume
+ jmp resume_userspace
+
+#ifdef CONFIG_VM86
+ ALIGN
+work_notifysig_v86:
+ pushl %ecx # save ti_flags for do_notify_resume
+ call save_v86_state # %eax contains pt_regs pointer
+ popl %ecx
+ movl %eax, %esp
+ jmp 1b
+#endif
+END(work_pending)
+
+ # perform syscall exit tracing
+ ALIGN
+syscall_trace_entry:
+ movl $-ENOSYS, PT_EAX(%esp)
+ movl %esp, %eax
+ call syscall_trace_enter
+ /* What it returned is what we'll actually use. */
+ cmpl $(NR_syscalls), %eax
+ jnae syscall_call
+ jmp syscall_exit
+END(syscall_trace_entry)
+
+ # perform syscall exit tracing
+ ALIGN
+syscall_exit_work:
+ testl $_TIF_WORK_SYSCALL_EXIT, %ecx
+ jz work_pending
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call
+ # schedule() instead
+ movl %esp, %eax
+ call syscall_trace_leave
+ jmp resume_userspace
+END(syscall_exit_work)
+
+syscall_fault:
+ ASM_CLAC
+ GET_THREAD_INFO(%ebp)
+ movl $-EFAULT, PT_EAX(%esp)
+ jmp resume_userspace
+END(syscall_fault)
+
+syscall_badsys:
+ movl $-ENOSYS, %eax
+ jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+ movl $-ENOSYS, %eax
+ jmp sysenter_after_call
+END(sysenter_badsys)
+
+.macro FIXUP_ESPFIX_STACK
+/*
+ * Switch back for ESPFIX stack to the normal zerobased stack
+ *
+ * We can't call C functions using the ESPFIX stack. This code reads
+ * the high word of the segment base from the GDT and swiches to the
+ * normal stack and adjusts ESP with the matching offset.
+ */
+#ifdef CONFIG_X86_ESPFIX32
+ /* fixup the stack */
+ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
+ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+ shl $16, %eax
+ addl %esp, %eax /* the adjusted stack pointer */
+ pushl $__KERNEL_DS
+ pushl %eax
+ lss (%esp), %esp /* switch to the normal stack segment */
+#endif
+.endm
+.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
+ movl %ss, %eax
+ /* see if on espfix stack */
+ cmpw $__ESPFIX_SS, %ax
+ jne 27f
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ /* switch to normal stack */
+ FIXUP_ESPFIX_STACK
+27:
+#endif
+.endm
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+ .align 8
+ENTRY(irq_entries_start)
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ pushl $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_interrupt
+ .align 8
+ .endr
+END(irq_entries_start)
+
+/*
+ * the CPU automatically disables interrupts when executing an IRQ vector,
+ * so IRQ-flags tracing has to follow that:
+ */
+ .p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+ ASM_CLAC
+ addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ movl %esp, %eax
+ call do_IRQ
+ jmp ret_from_intr
+ENDPROC(common_interrupt)
+
+#define BUILD_INTERRUPT3(name, nr, fn) \
+ENTRY(name) \
+ ASM_CLAC; \
+ pushl $~(nr); \
+ SAVE_ALL; \
+ TRACE_IRQS_OFF \
+ movl %esp, %eax; \
+ call fn; \
+ jmp ret_from_intr; \
+ENDPROC(name)
+
+
+#ifdef CONFIG_TRACING
+# define TRACE_BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
+#else
+# define TRACE_BUILD_INTERRUPT(name, nr)
+#endif
+
+#define BUILD_INTERRUPT(name, nr) \
+ BUILD_INTERRUPT3(name, nr, smp_##name); \
+ TRACE_BUILD_INTERRUPT(name, nr)
+
+/* The include is where all of the SMP etc. interrupts come from */
+#include <asm/entry_arch.h>
+
+ENTRY(coprocessor_error)
+ ASM_CLAC
+ pushl $0
+ pushl $do_coprocessor_error
+ jmp error_code
+END(coprocessor_error)
+
+ENTRY(simd_coprocessor_error)
+ ASM_CLAC
+ pushl $0
+#ifdef CONFIG_X86_INVD_BUG
+ /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
+ ALTERNATIVE "pushl $do_general_protection", \
+ "pushl $do_simd_coprocessor_error", \
+ X86_FEATURE_XMM
+#else
+ pushl $do_simd_coprocessor_error
+#endif
+ jmp error_code
+END(simd_coprocessor_error)
+
+ENTRY(device_not_available)
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+ pushl $do_device_not_available
+ jmp error_code
+END(device_not_available)
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
+ iret
+ _ASM_EXTABLE(native_iret, iret_exc)
+END(native_iret)
+
+ENTRY(native_irq_enable_sysexit)
+ sti
+ sysexit
+END(native_irq_enable_sysexit)
+#endif
+
+ENTRY(overflow)
+ ASM_CLAC
+ pushl $0
+ pushl $do_overflow
+ jmp error_code
+END(overflow)
+
+ENTRY(bounds)
+ ASM_CLAC
+ pushl $0
+ pushl $do_bounds
+ jmp error_code
+END(bounds)
+
+ENTRY(invalid_op)
+ ASM_CLAC
+ pushl $0
+ pushl $do_invalid_op
+ jmp error_code
+END(invalid_op)
+
+ENTRY(coprocessor_segment_overrun)
+ ASM_CLAC
+ pushl $0
+ pushl $do_coprocessor_segment_overrun
+ jmp error_code
+END(coprocessor_segment_overrun)
+
+ENTRY(invalid_TSS)
+ ASM_CLAC
+ pushl $do_invalid_TSS
+ jmp error_code
+END(invalid_TSS)
+
+ENTRY(segment_not_present)
+ ASM_CLAC
+ pushl $do_segment_not_present
+ jmp error_code
+END(segment_not_present)
+
+ENTRY(stack_segment)
+ ASM_CLAC
+ pushl $do_stack_segment
+ jmp error_code
+END(stack_segment)
+
+ENTRY(alignment_check)
+ ASM_CLAC
+ pushl $do_alignment_check
+ jmp error_code
+END(alignment_check)
+
+ENTRY(divide_error)
+ ASM_CLAC
+ pushl $0 # no error code
+ pushl $do_divide_error
+ jmp error_code
+END(divide_error)
+
+#ifdef CONFIG_X86_MCE
+ENTRY(machine_check)
+ ASM_CLAC
+ pushl $0
+ pushl machine_check_vector
+ jmp error_code
+END(machine_check)
+#endif
+
+ENTRY(spurious_interrupt_bug)
+ ASM_CLAC
+ pushl $0
+ pushl $do_spurious_interrupt_bug
+ jmp error_code
+END(spurious_interrupt_bug)
+
+#ifdef CONFIG_XEN
+/*
+ * Xen doesn't set %esp to be precisely what the normal SYSENTER
+ * entry point expects, so fix it up before using the normal path.
+ */
+ENTRY(xen_sysenter_target)
+ addl $5*4, %esp /* remove xen-provided frame */
+ jmp sysenter_past_esp
+
+ENTRY(xen_hypervisor_callback)
+ pushl $-1 /* orig_ax = -1 => not a system call */
+ SAVE_ALL
+ TRACE_IRQS_OFF
+
+ /*
+ * Check to see if we got the event in the critical
+ * region in xen_iret_direct, after we've reenabled
+ * events and checked for pending events. This simulates
+ * iret instruction's behaviour where it delivers a
+ * pending interrupt when enabling interrupts:
+ */
+ movl PT_EIP(%esp), %eax
+ cmpl $xen_iret_start_crit, %eax
+ jb 1f
+ cmpl $xen_iret_end_crit, %eax
+ jae 1f
+
+ jmp xen_iret_crit_fixup
+
+ENTRY(xen_do_upcall)
+1: mov %esp, %eax
+ call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
+ jmp ret_from_intr
+ENDPROC(xen_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ * 1. Fault while reloading DS, ES, FS or GS
+ * 2. Fault while executing IRET
+ * Category 1 we fix up by reattempting the load, and zeroing the segment
+ * register if the load fails.
+ * Category 2 we fix up by jumping to do_iret_error. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by maintaining a status value in EAX.
+ */
+ENTRY(xen_failsafe_callback)
+ pushl %eax
+ movl $1, %eax
+1: mov 4(%esp), %ds
+2: mov 8(%esp), %es
+3: mov 12(%esp), %fs
+4: mov 16(%esp), %gs
+ /* EAX == 0 => Category 1 (Bad segment)
+ EAX != 0 => Category 2 (Bad IRET) */
+ testl %eax, %eax
+ popl %eax
+ lea 16(%esp), %esp
+ jz 5f
+ jmp iret_exc
+5: pushl $-1 /* orig_ax = -1 => not a system call */
+ SAVE_ALL
+ jmp ret_from_exception
+
+.section .fixup, "ax"
+6: xorl %eax, %eax
+ movl %eax, 4(%esp)
+ jmp 1b
+7: xorl %eax, %eax
+ movl %eax, 8(%esp)
+ jmp 2b
+8: xorl %eax, %eax
+ movl %eax, 12(%esp)
+ jmp 3b
+9: xorl %eax, %eax
+ movl %eax, 16(%esp)
+ jmp 4b
+.previous
+ _ASM_EXTABLE(1b, 6b)
+ _ASM_EXTABLE(2b, 7b)
+ _ASM_EXTABLE(3b, 8b)
+ _ASM_EXTABLE(4b, 9b)
+ENDPROC(xen_failsafe_callback)
+
+BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+ xen_evtchn_do_upcall)
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+ hyperv_vector_handler)
+
+#endif /* CONFIG_HYPERV */
+
+#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+ ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ pushl $0 /* Pass NULL as regs pointer */
+ movl 4*4(%esp), %eax
+ movl 0x4(%ebp), %edx
+ movl function_trace_op, %ecx
+ subl $MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+ call ftrace_stub
+
+ addl $4, %esp /* skip NULL pointer */
+ popl %edx
+ popl %ecx
+ popl %eax
+ftrace_ret:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ jmp ftrace_stub
+#endif
+
+.globl ftrace_stub
+ftrace_stub:
+ ret
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+ pushf /* push flags before compare (in cs location) */
+
+ /*
+ * i386 does not save SS and ESP when coming from kernel.
+ * Instead, to get sp, &regs->sp is used (see ptrace.h).
+ * Unfortunately, that means eflags must be at the same location
+ * as the current return ip is. We move the return ip into the
+ * ip location, and move flags into the return ip location.
+ */
+ pushl 4(%esp) /* save return ip into ip slot */
+
+ pushl $0 /* Load 0 into orig_ax */
+ pushl %gs
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+
+ movl 13*4(%esp), %eax /* Get the saved flags */
+ movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
+ /* clobbering return ip */
+ movl $__KERNEL_CS, 13*4(%esp)
+
+ movl 12*4(%esp), %eax /* Load ip (1st parameter) */
+ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
+ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
+ movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+ pushl %esp /* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ addl $4, %esp /* Skip pt_regs */
+ movl 14*4(%esp), %eax /* Move flags back into cs */
+ movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
+ movl 12*4(%esp), %eax /* Get return ip from regs->ip */
+ movl %eax, 14*4(%esp) /* Put return ip back for ret */
+
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+ popl %ds
+ popl %es
+ popl %fs
+ popl %gs
+ addl $8, %esp /* Skip orig_ax and ip */
+ popf /* Pop flags at end (no addl to corrupt flags) */
+ jmp ftrace_ret
+
+ popf
+ jmp ftrace_stub
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(mcount)
+ cmpl $__PAGE_OFFSET, %esp
+ jb ftrace_stub /* Paging not enabled yet? */
+
+ cmpl $ftrace_stub, ftrace_trace_function
+ jnz trace
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ cmpl $ftrace_stub, ftrace_graph_return
+ jnz ftrace_graph_caller
+
+ cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
+ jnz ftrace_graph_caller
+#endif
+.globl ftrace_stub
+ftrace_stub:
+ ret
+
+ /* taken from glibc */
+trace:
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ movl 0xc(%esp), %eax
+ movl 0x4(%ebp), %edx
+ subl $MCOUNT_INSN_SIZE, %eax
+
+ call *ftrace_trace_function
+
+ popl %edx
+ popl %ecx
+ popl %eax
+ jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ movl 0xc(%esp), %eax
+ lea 0x4(%ebp), %edx
+ movl (%ebp), %ecx
+ subl $MCOUNT_INSN_SIZE, %eax
+ call prepare_ftrace_return
+ popl %edx
+ popl %ecx
+ popl %eax
+ ret
+END(ftrace_graph_caller)
+
+.globl return_to_handler
+return_to_handler:
+ pushl %eax
+ pushl %edx
+ movl %ebp, %eax
+ call ftrace_return_to_handler
+ movl %eax, %ecx
+ popl %edx
+ popl %eax
+ jmp *%ecx
+#endif
+
+#ifdef CONFIG_TRACING
+ENTRY(trace_page_fault)
+ ASM_CLAC
+ pushl $trace_do_page_fault
+ jmp error_code
+END(trace_page_fault)
+#endif
+
+ENTRY(page_fault)
+ ASM_CLAC
+ pushl $do_page_fault
+ ALIGN
+error_code:
+ /* the function address is in %gs's slot on the stack */
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ cld
+ movl $(__KERNEL_PERCPU), %ecx
+ movl %ecx, %fs
+ UNWIND_ESPFIX_STACK
+ GS_TO_REG %ecx
+ movl PT_GS(%esp), %edi # get the function address
+ movl PT_ORIG_EAX(%esp), %edx # get the error code
+ movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
+ REG_TO_PTGS %ecx
+ SET_KERNEL_GS %ecx
+ movl $(__USER_DS), %ecx
+ movl %ecx, %ds
+ movl %ecx, %es
+ TRACE_IRQS_OFF
+ movl %esp, %eax # pt_regs pointer
+ call *%edi
+ jmp ret_from_exception
+END(page_fault)
+
+/*
+ * Debug traps and NMI can happen at the one SYSENTER instruction
+ * that sets up the real kernel stack. Check here, since we can't
+ * allow the wrong stack to be used.
+ *
+ * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
+ * already pushed 3 words if it hits on the sysenter instruction:
+ * eflags, cs and eip.
+ *
+ * We just load the right stack, and push the three (known) values
+ * by hand onto the new stack - while updating the return eip past
+ * the instruction that would have done it for sysenter.
+ */
+.macro FIX_STACK offset ok label
+ cmpw $__KERNEL_CS, 4(%esp)
+ jne \ok
+\label:
+ movl TSS_sysenter_sp0 + \offset(%esp), %esp
+ pushfl
+ pushl $__KERNEL_CS
+ pushl $sysenter_past_esp
+.endm
+
+ENTRY(debug)
+ ASM_CLAC
+ cmpl $entry_SYSENTER_32, (%esp)
+ jne debug_stack_correct
+ FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
+debug_stack_correct:
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ xorl %edx, %edx # error code 0
+ movl %esp, %eax # pt_regs pointer
+ call do_debug
+ jmp ret_from_exception
+END(debug)
+
+/*
+ * NMI is doubly nasty. It can happen _while_ we're handling
+ * a debug fault, and the debug fault hasn't yet been able to
+ * clear up the stack. So we first check whether we got an
+ * NMI on the sysenter entry path, but after that we need to
+ * check whether we got an NMI on the debug path where the debug
+ * fault happened on the sysenter path.
+ */
+ENTRY(nmi)
+ ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
+ pushl %eax
+ movl %ss, %eax
+ cmpw $__ESPFIX_SS, %ax
+ popl %eax
+ je nmi_espfix_stack
+#endif
+ cmpl $entry_SYSENTER_32, (%esp)
+ je nmi_stack_fixup
+ pushl %eax
+ movl %esp, %eax
+ /*
+ * Do not access memory above the end of our stack page,
+ * it might not exist.
+ */
+ andl $(THREAD_SIZE-1), %eax
+ cmpl $(THREAD_SIZE-20), %eax
+ popl %eax
+ jae nmi_stack_correct
+ cmpl $entry_SYSENTER_32, 12(%esp)
+ je nmi_debug_stack_check
+nmi_stack_correct:
+ pushl %eax
+ SAVE_ALL
+ xorl %edx, %edx # zero error code
+ movl %esp, %eax # pt_regs pointer
+ call do_nmi
+ jmp restore_all_notrace
+
+nmi_stack_fixup:
+ FIX_STACK 12, nmi_stack_correct, 1
+ jmp nmi_stack_correct
+
+nmi_debug_stack_check:
+ cmpw $__KERNEL_CS, 16(%esp)
+ jne nmi_stack_correct
+ cmpl $debug, (%esp)
+ jb nmi_stack_correct
+ cmpl $debug_esp_fix_insn, (%esp)
+ ja nmi_stack_correct
+ FIX_STACK 24, nmi_stack_correct, 1
+ jmp nmi_stack_correct
+
+#ifdef CONFIG_X86_ESPFIX32
+nmi_espfix_stack:
+ /*
+ * create the pointer to lss back
+ */
+ pushl %ss
+ pushl %esp
+ addl $4, (%esp)
+ /* copy the iret frame of 12 bytes */
+ .rept 3
+ pushl 16(%esp)
+ .endr
+ pushl %eax
+ SAVE_ALL
+ FIXUP_ESPFIX_STACK # %eax == %esp
+ xorl %edx, %edx # zero error code
+ call do_nmi
+ RESTORE_REGS
+ lss 12+4(%esp), %esp # back to espfix stack
+ jmp irq_return
+#endif
+END(nmi)
+
+ENTRY(int3)
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ xorl %edx, %edx # zero error code
+ movl %esp, %eax # pt_regs pointer
+ call do_int3
+ jmp ret_from_exception
+END(int3)
+
+ENTRY(general_protection)
+ pushl $do_general_protection
+ jmp error_code
+END(general_protection)
+
+#ifdef CONFIG_KVM_GUEST
+ENTRY(async_page_fault)
+ ASM_CLAC
+ pushl $do_async_page_fault
+ jmp error_code
+END(async_page_fault)
+#endif
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/entry/entry_64.S
index 02c2eff7478d..3bb2c4302df1 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -4,34 +4,25 @@
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
* Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
- */
-
-/*
+ *
* entry.S contains the system-call and fault low-level handling routines.
*
* Some of this is documented in Documentation/x86/entry_64.txt
*
- * NOTE: This code handles signal-recognition, which happens every time
- * after an interrupt and after each system call.
- *
* A note on terminology:
- * - iret frame: Architecture defined interrupt frame from SS to RIP
- * at the top of the kernel process stack.
+ * - iret frame: Architecture defined interrupt frame from SS to RIP
+ * at the top of the kernel process stack.
*
* Some macro usage:
- * - CFI macros are used to generate dwarf2 unwind information for better
- * backtraces. They don't change any code.
- * - ENTRY/END Define functions in the symbol table.
- * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging.
- * - idtentry - Define exception entry points.
+ * - ENTRY/END: Define functions in the symbol table.
+ * - TRACE_IRQ_*: Trace hardirq state for lock debugging.
+ * - idtentry: Define exception entry points.
*/
-
#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/cache.h>
#include <asm/errno.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
+#include "calling.h"
#include <asm/asm-offsets.h>
#include <asm/msr.h>
#include <asm/unistd.h>
@@ -49,13 +40,12 @@
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
-#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_64BIT 0x80000000
-#define __AUDIT_ARCH_LE 0x40000000
-
- .code64
- .section .entry.text, "ax"
+#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_64BIT 0x80000000
+#define __AUDIT_ARCH_LE 0x40000000
+.code64
+.section .entry.text, "ax"
#ifdef CONFIG_PARAVIRT
ENTRY(native_usergs_sysret64)
@@ -64,11 +54,10 @@ ENTRY(native_usergs_sysret64)
ENDPROC(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
-
.macro TRACE_IRQS_IRETQ
#ifdef CONFIG_TRACE_IRQFLAGS
- bt $9,EFLAGS(%rsp) /* interrupts off? */
- jnc 1f
+ bt $9, EFLAGS(%rsp) /* interrupts off? */
+ jnc 1f
TRACE_IRQS_ON
1:
#endif
@@ -88,89 +77,34 @@ ENDPROC(native_usergs_sysret64)
#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
.macro TRACE_IRQS_OFF_DEBUG
- call debug_stack_set_zero
+ call debug_stack_set_zero
TRACE_IRQS_OFF
- call debug_stack_reset
+ call debug_stack_reset
.endm
.macro TRACE_IRQS_ON_DEBUG
- call debug_stack_set_zero
+ call debug_stack_set_zero
TRACE_IRQS_ON
- call debug_stack_reset
+ call debug_stack_reset
.endm
.macro TRACE_IRQS_IRETQ_DEBUG
- bt $9,EFLAGS(%rsp) /* interrupts off? */
- jnc 1f
+ bt $9, EFLAGS(%rsp) /* interrupts off? */
+ jnc 1f
TRACE_IRQS_ON_DEBUG
1:
.endm
#else
-# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF
-# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON
-# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ
+# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ
#endif
/*
- * empty frame
- */
- .macro EMPTY_FRAME start=1 offset=0
- .if \start
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,8+\offset
- .else
- CFI_DEF_CFA_OFFSET 8+\offset
- .endif
- .endm
-
-/*
- * initial frame state for interrupts (and exceptions without error code)
- */
- .macro INTR_FRAME start=1 offset=0
- EMPTY_FRAME \start, 5*8+\offset
- /*CFI_REL_OFFSET ss, 4*8+\offset*/
- CFI_REL_OFFSET rsp, 3*8+\offset
- /*CFI_REL_OFFSET rflags, 2*8+\offset*/
- /*CFI_REL_OFFSET cs, 1*8+\offset*/
- CFI_REL_OFFSET rip, 0*8+\offset
- .endm
-
-/*
- * initial frame state for exceptions with error code (and interrupts
- * with vector already pushed)
- */
- .macro XCPT_FRAME start=1 offset=0
- INTR_FRAME \start, 1*8+\offset
- .endm
-
-/*
- * frame that enables passing a complete pt_regs to a C function.
- */
- .macro DEFAULT_FRAME start=1 offset=0
- XCPT_FRAME \start, ORIG_RAX+\offset
- CFI_REL_OFFSET rdi, RDI+\offset
- CFI_REL_OFFSET rsi, RSI+\offset
- CFI_REL_OFFSET rdx, RDX+\offset
- CFI_REL_OFFSET rcx, RCX+\offset
- CFI_REL_OFFSET rax, RAX+\offset
- CFI_REL_OFFSET r8, R8+\offset
- CFI_REL_OFFSET r9, R9+\offset
- CFI_REL_OFFSET r10, R10+\offset
- CFI_REL_OFFSET r11, R11+\offset
- CFI_REL_OFFSET rbx, RBX+\offset
- CFI_REL_OFFSET rbp, RBP+\offset
- CFI_REL_OFFSET r12, R12+\offset
- CFI_REL_OFFSET r13, R13+\offset
- CFI_REL_OFFSET r14, R14+\offset
- CFI_REL_OFFSET r15, R15+\offset
- .endm
-
-/*
- * 64bit SYSCALL instruction entry. Up to 6 arguments in registers.
+ * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
*
- * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
* then loads new ss, cs, and rip from previously programmed MSRs.
* rflags gets masked by a value from another MSR (so CLD and CLAC
* are not needed). SYSCALL does not save anything on the stack
@@ -186,7 +120,7 @@ ENDPROC(native_usergs_sysret64)
* r10 arg3 (needs to be moved to rcx to conform to C ABI)
* r8 arg4
* r9 arg5
- * (note: r12-r15,rbp,rbx are callee-preserved in C ABI)
+ * (note: r12-r15, rbp, rbx are callee-preserved in C ABI)
*
* Only called from user space.
*
@@ -195,13 +129,7 @@ ENDPROC(native_usergs_sysret64)
* with them due to bugs in both AMD and Intel CPUs.
*/
-ENTRY(system_call)
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rip,rcx
- /*CFI_REGISTER rflags,r11*/
-
+ENTRY(entry_SYSCALL_64)
/*
* Interrupts are off on entry.
* We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
@@ -213,14 +141,14 @@ ENTRY(system_call)
* after the swapgs, so that it can do the swapgs
* for the guest and jump here on syscall.
*/
-GLOBAL(system_call_after_swapgs)
+GLOBAL(entry_SYSCALL_64_after_swapgs)
- movq %rsp,PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack),%rsp
+ movq %rsp, PER_CPU_VAR(rsp_scratch)
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
/* Construct struct pt_regs on stack */
- pushq_cfi $__USER_DS /* pt_regs->ss */
- pushq_cfi PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
+ pushq $__USER_DS /* pt_regs->ss */
+ pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
/*
* Re-enable interrupts.
* We use 'rsp_scratch' as a scratch space, hence irq-off block above
@@ -229,36 +157,34 @@ GLOBAL(system_call_after_swapgs)
* with using rsp_scratch:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %r11 /* pt_regs->flags */
- pushq_cfi $__USER_CS /* pt_regs->cs */
- pushq_cfi %rcx /* pt_regs->ip */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi $-ENOSYS /* pt_regs->ax */
- pushq_cfi_reg r8 /* pt_regs->r8 */
- pushq_cfi_reg r9 /* pt_regs->r9 */
- pushq_cfi_reg r10 /* pt_regs->r10 */
- pushq_cfi_reg r11 /* pt_regs->r11 */
- sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 6*8
-
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz tracesys
-system_call_fastpath:
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ pushq %r8 /* pt_regs->r8 */
+ pushq %r9 /* pt_regs->r9 */
+ pushq %r10 /* pt_regs->r10 */
+ pushq %r11 /* pt_regs->r11 */
+ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz tracesys
+entry_SYSCALL_64_fastpath:
#if __SYSCALL_MASK == ~0
- cmpq $__NR_syscall_max,%rax
+ cmpq $__NR_syscall_max, %rax
#else
- andl $__SYSCALL_MASK,%eax
- cmpl $__NR_syscall_max,%eax
+ andl $__SYSCALL_MASK, %eax
+ cmpl $__NR_syscall_max, %eax
#endif
- ja 1f /* return -ENOSYS (already in pt_regs->ax) */
- movq %r10,%rcx
- call *sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
+ ja 1f /* return -ENOSYS (already in pt_regs->ax) */
+ movq %r10, %rcx
+ call *sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
1:
/*
* Syscall return path ending with SYSRET (fast path).
@@ -279,19 +205,15 @@ system_call_fastpath:
* flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
* very bad.
*/
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */
-
- CFI_REMEMBER_STATE
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */
RESTORE_C_REGS_EXCEPT_RCX_R11
- movq RIP(%rsp),%rcx
- CFI_REGISTER rip,rcx
- movq EFLAGS(%rsp),%r11
- /*CFI_REGISTER rflags,r11*/
- movq RSP(%rsp),%rsp
+ movq RIP(%rsp), %rcx
+ movq EFLAGS(%rsp), %r11
+ movq RSP(%rsp), %rsp
/*
- * 64bit SYSRET restores rip from rcx,
+ * 64-bit SYSRET restores rip from rcx,
* rflags from r11 (but RF and VM bits are forced to 0),
* cs and ss are loaded from MSRs.
* Restoration of rflags re-enables interrupts.
@@ -307,25 +229,23 @@ system_call_fastpath:
*/
USERGS_SYSRET64
- CFI_RESTORE_STATE
-
/* Do syscall entry tracing */
tracesys:
- movq %rsp, %rdi
- movl $AUDIT_ARCH_X86_64, %esi
- call syscall_trace_enter_phase1
- test %rax, %rax
- jnz tracesys_phase2 /* if needed, run the slow path */
- RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */
- movq ORIG_RAX(%rsp), %rax
- jmp system_call_fastpath /* and return to the fast path */
+ movq %rsp, %rdi
+ movl $AUDIT_ARCH_X86_64, %esi
+ call syscall_trace_enter_phase1
+ test %rax, %rax
+ jnz tracesys_phase2 /* if needed, run the slow path */
+ RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */
+ movq ORIG_RAX(%rsp), %rax
+ jmp entry_SYSCALL_64_fastpath /* and return to the fast path */
tracesys_phase2:
SAVE_EXTRA_REGS
- movq %rsp, %rdi
- movl $AUDIT_ARCH_X86_64, %esi
- movq %rax,%rdx
- call syscall_trace_enter_phase2
+ movq %rsp, %rdi
+ movl $AUDIT_ARCH_X86_64, %esi
+ movq %rax, %rdx
+ call syscall_trace_enter_phase2
/*
* Reload registers from stack in case ptrace changed them.
@@ -335,15 +255,15 @@ tracesys_phase2:
RESTORE_C_REGS_EXCEPT_RAX
RESTORE_EXTRA_REGS
#if __SYSCALL_MASK == ~0
- cmpq $__NR_syscall_max,%rax
+ cmpq $__NR_syscall_max, %rax
#else
- andl $__SYSCALL_MASK,%eax
- cmpl $__NR_syscall_max,%eax
+ andl $__SYSCALL_MASK, %eax
+ cmpl $__NR_syscall_max, %eax
#endif
- ja 1f /* return -ENOSYS (already in pt_regs->ax) */
- movq %r10,%rcx /* fixup for C */
- call *sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
+ ja 1f /* return -ENOSYS (already in pt_regs->ax) */
+ movq %r10, %rcx /* fixup for C */
+ call *sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
1:
/* Use IRET because user could have changed pt_regs->foo */
@@ -355,31 +275,33 @@ GLOBAL(int_ret_from_sys_call)
DISABLE_INTERRUPTS(CLBR_NONE)
int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
TRACE_IRQS_OFF
- movl $_TIF_ALLWORK_MASK,%edi
+ movl $_TIF_ALLWORK_MASK, %edi
/* edi: mask to check */
GLOBAL(int_with_check)
LOCKDEP_SYS_EXIT_IRQ
GET_THREAD_INFO(%rcx)
- movl TI_flags(%rcx),%edx
- andl %edi,%edx
- jnz int_careful
- andl $~TS_COMPAT,TI_status(%rcx)
+ movl TI_flags(%rcx), %edx
+ andl %edi, %edx
+ jnz int_careful
+ andl $~TS_COMPAT, TI_status(%rcx)
jmp syscall_return
- /* Either reschedule or signal or syscall exit tracking needed. */
- /* First do a reschedule test. */
- /* edx: work, edi: workmask */
+ /*
+ * Either reschedule or signal or syscall exit tracking needed.
+ * First do a reschedule test.
+ * edx: work, edi: workmask
+ */
int_careful:
- bt $TIF_NEED_RESCHED,%edx
- jnc int_very_careful
+ bt $TIF_NEED_RESCHED, %edx
+ jnc int_very_careful
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %rdi
+ pushq %rdi
SCHEDULE_USER
- popq_cfi %rdi
+ popq %rdi
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- jmp int_with_check
+ jmp int_with_check
/* handle signals and tracing -- both require a full pt_regs */
int_very_careful:
@@ -387,27 +309,27 @@ int_very_careful:
ENABLE_INTERRUPTS(CLBR_NONE)
SAVE_EXTRA_REGS
/* Check for syscall exit trace */
- testl $_TIF_WORK_SYSCALL_EXIT,%edx
- jz int_signal
- pushq_cfi %rdi
- leaq 8(%rsp),%rdi # &ptregs -> arg1
- call syscall_trace_leave
- popq_cfi %rdi
- andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
- jmp int_restore_rest
+ testl $_TIF_WORK_SYSCALL_EXIT, %edx
+ jz int_signal
+ pushq %rdi
+ leaq 8(%rsp), %rdi /* &ptregs -> arg1 */
+ call syscall_trace_leave
+ popq %rdi
+ andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU), %edi
+ jmp int_restore_rest
int_signal:
- testl $_TIF_DO_NOTIFY_MASK,%edx
- jz 1f
- movq %rsp,%rdi # &ptregs -> arg1
- xorl %esi,%esi # oldset -> arg2
- call do_notify_resume
-1: movl $_TIF_WORK_MASK,%edi
+ testl $_TIF_DO_NOTIFY_MASK, %edx
+ jz 1f
+ movq %rsp, %rdi /* &ptregs -> arg1 */
+ xorl %esi, %esi /* oldset -> arg2 */
+ call do_notify_resume
+1: movl $_TIF_WORK_MASK, %edi
int_restore_rest:
RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- jmp int_with_check
+ jmp int_with_check
syscall_return:
/* The IRETQ could re-enable interrupts: */
@@ -418,34 +340,37 @@ syscall_return:
* Try to use SYSRET instead of IRET if we're returning to
* a completely clean 64-bit userspace context.
*/
- movq RCX(%rsp),%rcx
- cmpq %rcx,RIP(%rsp) /* RCX == RIP */
- jne opportunistic_sysret_failed
+ movq RCX(%rsp), %rcx
+ movq RIP(%rsp), %r11
+ cmpq %rcx, %r11 /* RCX == RIP */
+ jne opportunistic_sysret_failed
/*
* On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
* in kernel space. This essentially lets the user take over
- * the kernel, since userspace controls RSP. It's not worth
- * testing for canonicalness exactly -- this check detects any
- * of the 17 high bits set, which is true for non-canonical
- * or kernel addresses. (This will pessimize vsyscall=native.
- * Big deal.)
+ * the kernel, since userspace controls RSP.
*
- * If virtual addresses ever become wider, this will need
+ * If width of "canonical tail" ever becomes variable, this will need
* to be updated to remain correct on both old and new CPUs.
*/
.ifne __VIRTUAL_MASK_SHIFT - 47
.error "virtual address width changed -- SYSRET checks need update"
.endif
- shr $__VIRTUAL_MASK_SHIFT, %rcx
- jnz opportunistic_sysret_failed
- cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */
- jne opportunistic_sysret_failed
+ /* Change top 16 bits to be the sign-extension of 47th bit */
+ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+ sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
- movq R11(%rsp),%r11
- cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */
- jne opportunistic_sysret_failed
+ /* If this changed %rcx, it was not canonical */
+ cmpq %rcx, %r11
+ jne opportunistic_sysret_failed
+
+ cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ movq R11(%rsp), %r11
+ cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */
+ jne opportunistic_sysret_failed
/*
* SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
@@ -454,47 +379,41 @@ syscall_return:
* with register state that satisfies the opportunistic SYSRET
* conditions. For example, single-stepping this user code:
*
- * movq $stuck_here,%rcx
+ * movq $stuck_here, %rcx
* pushfq
* popq %r11
* stuck_here:
*
* would never get past 'stuck_here'.
*/
- testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
- jnz opportunistic_sysret_failed
+ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
+ jnz opportunistic_sysret_failed
/* nothing to check for RSP */
- cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */
- jne opportunistic_sysret_failed
+ cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
+ jne opportunistic_sysret_failed
/*
- * We win! This label is here just for ease of understanding
- * perf profiles. Nothing jumps here.
+ * We win! This label is here just for ease of understanding
+ * perf profiles. Nothing jumps here.
*/
syscall_return_via_sysret:
- CFI_REMEMBER_STATE
- /* r11 is already restored (see code above) */
- RESTORE_C_REGS_EXCEPT_R11
- movq RSP(%rsp),%rsp
+ /* rcx and r11 are already restored (see code above) */
+ RESTORE_C_REGS_EXCEPT_RCX_R11
+ movq RSP(%rsp), %rsp
USERGS_SYSRET64
- CFI_RESTORE_STATE
opportunistic_sysret_failed:
SWAPGS
jmp restore_c_regs_and_iret
- CFI_ENDPROC
-END(system_call)
+END(entry_SYSCALL_64)
.macro FORK_LIKE func
ENTRY(stub_\func)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8 /* offset 8: return address */
SAVE_EXTRA_REGS 8
- jmp sys_\func
- CFI_ENDPROC
+ jmp sys_\func
END(stub_\func)
.endm
@@ -503,8 +422,6 @@ END(stub_\func)
FORK_LIKE vfork
ENTRY(stub_execve)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
call sys_execve
return_from_execve:
testl %eax, %eax
@@ -514,11 +431,9 @@ return_from_execve:
1:
/* must use IRET code path (pt_regs->cs may have changed) */
addq $8, %rsp
- CFI_ADJUST_CFA_OFFSET -8
ZERO_EXTRA_REGS
- movq %rax,RAX(%rsp)
+ movq %rax, RAX(%rsp)
jmp int_ret_from_sys_call
- CFI_ENDPROC
END(stub_execve)
/*
* Remaining execve stubs are only 7 bytes long.
@@ -526,47 +441,25 @@ END(stub_execve)
*/
.align 8
GLOBAL(stub_execveat)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
call sys_execveat
jmp return_from_execve
- CFI_ENDPROC
END(stub_execveat)
-#ifdef CONFIG_X86_X32_ABI
+#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
.align 8
GLOBAL(stub_x32_execve)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call compat_sys_execve
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_x32_execve)
- .align 8
-GLOBAL(stub_x32_execveat)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call compat_sys_execveat
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_x32_execveat)
-#endif
-
-#ifdef CONFIG_IA32_EMULATION
- .align 8
GLOBAL(stub32_execve)
- CFI_STARTPROC
call compat_sys_execve
jmp return_from_execve
- CFI_ENDPROC
END(stub32_execve)
+END(stub_x32_execve)
.align 8
+GLOBAL(stub_x32_execveat)
GLOBAL(stub32_execveat)
- CFI_STARTPROC
call compat_sys_execveat
jmp return_from_execve
- CFI_ENDPROC
END(stub32_execveat)
+END(stub_x32_execveat)
#endif
/*
@@ -574,8 +467,6 @@ END(stub32_execveat)
* This cannot be done with SYSRET, so use the IRET return path instead.
*/
ENTRY(stub_rt_sigreturn)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
/*
* SAVE_EXTRA_REGS result is not normally needed:
* sigreturn overwrites all pt_regs->GPREGS.
@@ -584,24 +475,19 @@ ENTRY(stub_rt_sigreturn)
* we SAVE_EXTRA_REGS here.
*/
SAVE_EXTRA_REGS 8
- call sys_rt_sigreturn
+ call sys_rt_sigreturn
return_from_stub:
addq $8, %rsp
- CFI_ADJUST_CFA_OFFSET -8
RESTORE_EXTRA_REGS
- movq %rax,RAX(%rsp)
- jmp int_ret_from_sys_call
- CFI_ENDPROC
+ movq %rax, RAX(%rsp)
+ jmp int_ret_from_sys_call
END(stub_rt_sigreturn)
#ifdef CONFIG_X86_X32_ABI
ENTRY(stub_x32_rt_sigreturn)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
SAVE_EXTRA_REGS 8
- call sys32_x32_rt_sigreturn
- jmp return_from_stub
- CFI_ENDPROC
+ call sys32_x32_rt_sigreturn
+ jmp return_from_stub
END(stub_x32_rt_sigreturn)
#endif
@@ -611,36 +497,36 @@ END(stub_x32_rt_sigreturn)
* rdi: prev task we switched from
*/
ENTRY(ret_from_fork)
- DEFAULT_FRAME
- LOCK ; btr $TIF_FORK,TI_flags(%r8)
+ LOCK ; btr $TIF_FORK, TI_flags(%r8)
- pushq_cfi $0x0002
- popfq_cfi # reset kernel eflags
+ pushq $0x0002
+ popfq /* reset kernel eflags */
- call schedule_tail # rdi: 'prev' task parameter
+ call schedule_tail /* rdi: 'prev' task parameter */
RESTORE_EXTRA_REGS
- testl $3,CS(%rsp) # from kernel_thread?
+ testb $3, CS(%rsp) /* from kernel_thread? */
/*
* By the time we get here, we have no idea whether our pt_regs,
* ti flags, and ti status came from the 64-bit SYSCALL fast path,
- * the slow path, or one of the ia32entry paths.
+ * the slow path, or one of the 32-bit compat paths.
* Use IRET code path to return, since it can safely handle
* all of the above.
*/
jnz int_ret_from_sys_call
- /* We came from kernel_thread */
- /* nb: we depend on RESTORE_EXTRA_REGS above */
- movq %rbp, %rdi
- call *%rbx
- movl $0, RAX(%rsp)
+ /*
+ * We came from kernel_thread
+ * nb: we depend on RESTORE_EXTRA_REGS above
+ */
+ movq %rbp, %rdi
+ call *%rbx
+ movl $0, RAX(%rsp)
RESTORE_EXTRA_REGS
- jmp int_ret_from_sys_call
- CFI_ENDPROC
+ jmp int_ret_from_sys_call
END(ret_from_fork)
/*
@@ -649,16 +535,13 @@ END(ret_from_fork)
*/
.align 8
ENTRY(irq_entries_start)
- INTR_FRAME
vector=FIRST_EXTERNAL_VECTOR
.rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
- pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */
+ pushq $(~vector+0x80) /* Note: always in signed byte range */
vector=vector+1
jmp common_interrupt
- CFI_ADJUST_CFA_OFFSET -8
.align 8
.endr
- CFI_ENDPROC
END(irq_entries_start)
/*
@@ -684,10 +567,10 @@ END(irq_entries_start)
/* this goes to 0(%rsp) for unwinder, not for saving the value: */
SAVE_EXTRA_REGS_RBP -RBP
- leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */
+ leaq -RBP(%rsp), %rdi /* arg1 for \func (pointer to pt_regs) */
- testl $3, CS-RBP(%rsp)
- je 1f
+ testb $3, CS-RBP(%rsp)
+ jz 1f
SWAPGS
1:
/*
@@ -697,24 +580,14 @@ END(irq_entries_start)
* a little cheaper to use a separate counter in the PDA (short of
* moving irq_enter into assembly, which would be too much work)
*/
- movq %rsp, %rsi
- incl PER_CPU_VAR(irq_count)
- cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
- CFI_DEF_CFA_REGISTER rsi
- pushq %rsi
- /*
- * For debugger:
- * "CFA (Current Frame Address) is the value on stack + offset"
- */
- CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
- 0x77 /* DW_OP_breg7 (rsp) */, 0, \
- 0x06 /* DW_OP_deref */, \
- 0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \
- 0x22 /* DW_OP_plus */
+ movq %rsp, %rsi
+ incl PER_CPU_VAR(irq_count)
+ cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp
+ pushq %rsi
/* We entered an interrupt context - irqs are off: */
TRACE_IRQS_OFF
- call \func
+ call \func
.endm
/*
@@ -723,42 +596,36 @@ END(irq_entries_start)
*/
.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
- XCPT_FRAME
ASM_CLAC
- addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
+ addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
interrupt do_IRQ
/* 0(%rsp): old RSP */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- decl PER_CPU_VAR(irq_count)
+ decl PER_CPU_VAR(irq_count)
/* Restore saved previous stack */
- popq %rsi
- CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */
+ popq %rsi
/* return code expects complete pt_regs - adjust rsp accordingly: */
- leaq -RBP(%rsi),%rsp
- CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET RBP
+ leaq -RBP(%rsi), %rsp
- testl $3,CS(%rsp)
- je retint_kernel
+ testb $3, CS(%rsp)
+ jz retint_kernel
/* Interrupt came from user space */
-
+retint_user:
GET_THREAD_INFO(%rcx)
- /*
- * %rcx: thread info. Interrupts off.
- */
+
+ /* %rcx: thread info. Interrupts are off. */
retint_with_reschedule:
- movl $_TIF_WORK_MASK,%edi
+ movl $_TIF_WORK_MASK, %edi
retint_check:
LOCKDEP_SYS_EXIT_IRQ
- movl TI_flags(%rcx),%edx
- andl %edi,%edx
- CFI_REMEMBER_STATE
- jnz retint_careful
+ movl TI_flags(%rcx), %edx
+ andl %edi, %edx
+ jnz retint_careful
-retint_swapgs: /* return to user-space */
+retint_swapgs: /* return to user-space */
/*
* The iretq could re-enable interrupts:
*/
@@ -773,9 +640,9 @@ retint_kernel:
#ifdef CONFIG_PREEMPT
/* Interrupts are off */
/* Check if we need preemption */
- bt $9,EFLAGS(%rsp) /* interrupts were off? */
+ bt $9, EFLAGS(%rsp) /* were interrupts off? */
jnc 1f
-0: cmpl $0,PER_CPU_VAR(__preempt_count)
+0: cmpl $0, PER_CPU_VAR(__preempt_count)
jnz 1f
call preempt_schedule_irq
jmp 0b
@@ -793,8 +660,6 @@ retint_kernel:
restore_c_regs_and_iret:
RESTORE_C_REGS
REMOVE_PT_GPREGS_FROM_STACK 8
-
-irq_return:
INTERRUPT_RETURN
ENTRY(native_iret)
@@ -803,8 +668,8 @@ ENTRY(native_iret)
* 64-bit mode SS:RSP on the exception stack is always valid.
*/
#ifdef CONFIG_X86_ESPFIX64
- testb $4,(SS-RIP)(%rsp)
- jnz native_irq_return_ldt
+ testb $4, (SS-RIP)(%rsp)
+ jnz native_irq_return_ldt
#endif
.global native_irq_return_iret
@@ -819,62 +684,60 @@ native_irq_return_iret:
#ifdef CONFIG_X86_ESPFIX64
native_irq_return_ldt:
- pushq_cfi %rax
- pushq_cfi %rdi
+ pushq %rax
+ pushq %rdi
SWAPGS
- movq PER_CPU_VAR(espfix_waddr),%rdi
- movq %rax,(0*8)(%rdi) /* RAX */
- movq (2*8)(%rsp),%rax /* RIP */
- movq %rax,(1*8)(%rdi)
- movq (3*8)(%rsp),%rax /* CS */
- movq %rax,(2*8)(%rdi)
- movq (4*8)(%rsp),%rax /* RFLAGS */
- movq %rax,(3*8)(%rdi)
- movq (6*8)(%rsp),%rax /* SS */
- movq %rax,(5*8)(%rdi)
- movq (5*8)(%rsp),%rax /* RSP */
- movq %rax,(4*8)(%rdi)
- andl $0xffff0000,%eax
- popq_cfi %rdi
- orq PER_CPU_VAR(espfix_stack),%rax
+ movq PER_CPU_VAR(espfix_waddr), %rdi
+ movq %rax, (0*8)(%rdi) /* RAX */
+ movq (2*8)(%rsp), %rax /* RIP */
+ movq %rax, (1*8)(%rdi)
+ movq (3*8)(%rsp), %rax /* CS */
+ movq %rax, (2*8)(%rdi)
+ movq (4*8)(%rsp), %rax /* RFLAGS */
+ movq %rax, (3*8)(%rdi)
+ movq (6*8)(%rsp), %rax /* SS */
+ movq %rax, (5*8)(%rdi)
+ movq (5*8)(%rsp), %rax /* RSP */
+ movq %rax, (4*8)(%rdi)
+ andl $0xffff0000, %eax
+ popq %rdi
+ orq PER_CPU_VAR(espfix_stack), %rax
SWAPGS
- movq %rax,%rsp
- popq_cfi %rax
- jmp native_irq_return_iret
+ movq %rax, %rsp
+ popq %rax
+ jmp native_irq_return_iret
#endif
/* edi: workmask, edx: work */
retint_careful:
- CFI_RESTORE_STATE
- bt $TIF_NEED_RESCHED,%edx
- jnc retint_signal
+ bt $TIF_NEED_RESCHED, %edx
+ jnc retint_signal
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %rdi
+ pushq %rdi
SCHEDULE_USER
- popq_cfi %rdi
+ popq %rdi
GET_THREAD_INFO(%rcx)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- jmp retint_check
+ jmp retint_check
retint_signal:
- testl $_TIF_DO_NOTIFY_MASK,%edx
- jz retint_swapgs
+ testl $_TIF_DO_NOTIFY_MASK, %edx
+ jz retint_swapgs
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
SAVE_EXTRA_REGS
- movq $-1,ORIG_RAX(%rsp)
- xorl %esi,%esi # oldset
- movq %rsp,%rdi # &pt_regs
- call do_notify_resume
+ movq $-1, ORIG_RAX(%rsp)
+ xorl %esi, %esi /* oldset */
+ movq %rsp, %rdi /* &pt_regs */
+ call do_notify_resume
RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
- jmp retint_with_reschedule
+ jmp retint_with_reschedule
- CFI_ENDPROC
END(common_interrupt)
/*
@@ -882,13 +745,11 @@ END(common_interrupt)
*/
.macro apicinterrupt3 num sym do_sym
ENTRY(\sym)
- INTR_FRAME
ASM_CLAC
- pushq_cfi $~(\num)
+ pushq $~(\num)
.Lcommon_\sym:
interrupt \do_sym
- jmp ret_from_intr
- CFI_ENDPROC
+ jmp ret_from_intr
END(\sym)
.endm
@@ -910,53 +771,45 @@ trace_apicinterrupt \num \sym
.endm
#ifdef CONFIG_SMP
-apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \
- irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
-apicinterrupt3 REBOOT_VECTOR \
- reboot_interrupt smp_reboot_interrupt
+apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
+apicinterrupt3 REBOOT_VECTOR reboot_interrupt smp_reboot_interrupt
#endif
#ifdef CONFIG_X86_UV
-apicinterrupt3 UV_BAU_MESSAGE \
- uv_bau_message_intr1 uv_bau_message_interrupt
+apicinterrupt3 UV_BAU_MESSAGE uv_bau_message_intr1 uv_bau_message_interrupt
#endif
-apicinterrupt LOCAL_TIMER_VECTOR \
- apic_timer_interrupt smp_apic_timer_interrupt
-apicinterrupt X86_PLATFORM_IPI_VECTOR \
- x86_platform_ipi smp_x86_platform_ipi
+
+apicinterrupt LOCAL_TIMER_VECTOR apic_timer_interrupt smp_apic_timer_interrupt
+apicinterrupt X86_PLATFORM_IPI_VECTOR x86_platform_ipi smp_x86_platform_ipi
#ifdef CONFIG_HAVE_KVM
-apicinterrupt3 POSTED_INTR_VECTOR \
- kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_VECTOR kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
-apicinterrupt THRESHOLD_APIC_VECTOR \
- threshold_interrupt smp_threshold_interrupt
+apicinterrupt THRESHOLD_APIC_VECTOR threshold_interrupt smp_threshold_interrupt
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+apicinterrupt DEFERRED_ERROR_VECTOR deferred_error_interrupt smp_deferred_error_interrupt
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
-apicinterrupt THERMAL_APIC_VECTOR \
- thermal_interrupt smp_thermal_interrupt
+apicinterrupt THERMAL_APIC_VECTOR thermal_interrupt smp_thermal_interrupt
#endif
#ifdef CONFIG_SMP
-apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
- call_function_single_interrupt smp_call_function_single_interrupt
-apicinterrupt CALL_FUNCTION_VECTOR \
- call_function_interrupt smp_call_function_interrupt
-apicinterrupt RESCHEDULE_VECTOR \
- reschedule_interrupt smp_reschedule_interrupt
+apicinterrupt CALL_FUNCTION_SINGLE_VECTOR call_function_single_interrupt smp_call_function_single_interrupt
+apicinterrupt CALL_FUNCTION_VECTOR call_function_interrupt smp_call_function_interrupt
+apicinterrupt RESCHEDULE_VECTOR reschedule_interrupt smp_reschedule_interrupt
#endif
-apicinterrupt ERROR_APIC_VECTOR \
- error_interrupt smp_error_interrupt
-apicinterrupt SPURIOUS_APIC_VECTOR \
- spurious_interrupt smp_spurious_interrupt
+apicinterrupt ERROR_APIC_VECTOR error_interrupt smp_error_interrupt
+apicinterrupt SPURIOUS_APIC_VECTOR spurious_interrupt smp_spurious_interrupt
#ifdef CONFIG_IRQ_WORK
-apicinterrupt IRQ_WORK_VECTOR \
- irq_work_interrupt smp_irq_work_interrupt
+apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt
#endif
/*
@@ -971,100 +824,87 @@ ENTRY(\sym)
.error "using shift_ist requires paranoid=1"
.endif
- .if \has_error_code
- XCPT_FRAME
- .else
- INTR_FRAME
- .endif
-
ASM_CLAC
PARAVIRT_ADJUST_EXCEPTION_FRAME
.ifeq \has_error_code
- pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
+ pushq $-1 /* ORIG_RAX: no syscall to restart */
.endif
ALLOC_PT_GPREGS_ON_STACK
.if \paranoid
.if \paranoid == 1
- CFI_REMEMBER_STATE
- testl $3, CS(%rsp) /* If coming from userspace, switch */
- jnz 1f /* stacks. */
+ testb $3, CS(%rsp) /* If coming from userspace, switch stacks */
+ jnz 1f
.endif
- call paranoid_entry
+ call paranoid_entry
.else
- call error_entry
+ call error_entry
.endif
/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
- DEFAULT_FRAME 0
-
.if \paranoid
.if \shift_ist != -1
- TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */
+ TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */
.else
TRACE_IRQS_OFF
.endif
.endif
- movq %rsp,%rdi /* pt_regs pointer */
+ movq %rsp, %rdi /* pt_regs pointer */
.if \has_error_code
- movq ORIG_RAX(%rsp),%rsi /* get error code */
- movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
+ movq ORIG_RAX(%rsp), %rsi /* get error code */
+ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
.else
- xorl %esi,%esi /* no error code */
+ xorl %esi, %esi /* no error code */
.endif
.if \shift_ist != -1
- subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+ subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
.endif
- call \do_sym
+ call \do_sym
.if \shift_ist != -1
- addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+ addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
.endif
/* these procedures expect "no swapgs" flag in ebx */
.if \paranoid
- jmp paranoid_exit
+ jmp paranoid_exit
.else
- jmp error_exit
+ jmp error_exit
.endif
.if \paranoid == 1
- CFI_RESTORE_STATE
/*
* Paranoid entry from userspace. Switch stacks and treat it
* as a normal entry. This means that paranoid handlers
* run in real process context if user_mode(regs).
*/
1:
- call error_entry
+ call error_entry
- DEFAULT_FRAME 0
- movq %rsp,%rdi /* pt_regs pointer */
- call sync_regs
- movq %rax,%rsp /* switch stack */
+ movq %rsp, %rdi /* pt_regs pointer */
+ call sync_regs
+ movq %rax, %rsp /* switch stack */
- movq %rsp,%rdi /* pt_regs pointer */
+ movq %rsp, %rdi /* pt_regs pointer */
.if \has_error_code
- movq ORIG_RAX(%rsp),%rsi /* get error code */
- movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
+ movq ORIG_RAX(%rsp), %rsi /* get error code */
+ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
.else
- xorl %esi,%esi /* no error code */
+ xorl %esi, %esi /* no error code */
.endif
- call \do_sym
+ call \do_sym
- jmp error_exit /* %ebx: no swapgs flag */
+ jmp error_exit /* %ebx: no swapgs flag */
.endif
-
- CFI_ENDPROC
END(\sym)
.endm
@@ -1079,65 +919,58 @@ idtentry \sym \do_sym has_error_code=\has_error_code
.endm
#endif
-idtentry divide_error do_divide_error has_error_code=0
-idtentry overflow do_overflow has_error_code=0
-idtentry bounds do_bounds has_error_code=0
-idtentry invalid_op do_invalid_op has_error_code=0
-idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault do_double_fault has_error_code=1 paranoid=2
-idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
-idtentry invalid_TSS do_invalid_TSS has_error_code=1
-idtentry segment_not_present do_segment_not_present has_error_code=1
-idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
-idtentry coprocessor_error do_coprocessor_error has_error_code=0
-idtentry alignment_check do_alignment_check has_error_code=1
-idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
-
-
- /* Reload gs selector with exception handling */
- /* edi: new selector */
+idtentry divide_error do_divide_error has_error_code=0
+idtentry overflow do_overflow has_error_code=0
+idtentry bounds do_bounds has_error_code=0
+idtentry invalid_op do_invalid_op has_error_code=0
+idtentry device_not_available do_device_not_available has_error_code=0
+idtentry double_fault do_double_fault has_error_code=1 paranoid=2
+idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
+idtentry invalid_TSS do_invalid_TSS has_error_code=1
+idtentry segment_not_present do_segment_not_present has_error_code=1
+idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
+idtentry coprocessor_error do_coprocessor_error has_error_code=0
+idtentry alignment_check do_alignment_check has_error_code=1
+idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
+
+
+ /*
+ * Reload gs selector with exception handling
+ * edi: new selector
+ */
ENTRY(native_load_gs_index)
- CFI_STARTPROC
- pushfq_cfi
+ pushfq
DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
SWAPGS
gs_change:
- movl %edi,%gs
-2: mfence /* workaround */
+ movl %edi, %gs
+2: mfence /* workaround */
SWAPGS
- popfq_cfi
+ popfq
ret
- CFI_ENDPROC
END(native_load_gs_index)
- _ASM_EXTABLE(gs_change,bad_gs)
- .section .fixup,"ax"
+ _ASM_EXTABLE(gs_change, bad_gs)
+ .section .fixup, "ax"
/* running with kernelgs */
bad_gs:
- SWAPGS /* switch back to user gs */
- xorl %eax,%eax
- movl %eax,%gs
- jmp 2b
+ SWAPGS /* switch back to user gs */
+ xorl %eax, %eax
+ movl %eax, %gs
+ jmp 2b
.previous
/* Call softirq on interrupt stack. Interrupts are off. */
ENTRY(do_softirq_own_stack)
- CFI_STARTPROC
- pushq_cfi %rbp
- CFI_REL_OFFSET rbp,0
- mov %rsp,%rbp
- CFI_DEF_CFA_REGISTER rbp
- incl PER_CPU_VAR(irq_count)
- cmove PER_CPU_VAR(irq_stack_ptr),%rsp
- push %rbp # backlink for old unwinder
- call __do_softirq
+ pushq %rbp
+ mov %rsp, %rbp
+ incl PER_CPU_VAR(irq_count)
+ cmove PER_CPU_VAR(irq_stack_ptr), %rsp
+ push %rbp /* frame pointer backlink */
+ call __do_softirq
leaveq
- CFI_RESTORE rbp
- CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET -8
- decl PER_CPU_VAR(irq_count)
+ decl PER_CPU_VAR(irq_count)
ret
- CFI_ENDPROC
END(do_softirq_own_stack)
#ifdef CONFIG_XEN
@@ -1156,29 +989,24 @@ idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
* existing activation in its critical region -- if so, we pop the current
* activation and restart the handler using the previous one.
*/
-ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs)
- CFI_STARTPROC
+ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */
+
/*
* Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
* see the correct pointer to the pt_regs
*/
- movq %rdi, %rsp # we don't return, adjust the stack frame
- CFI_ENDPROC
- DEFAULT_FRAME
-11: incl PER_CPU_VAR(irq_count)
- movq %rsp,%rbp
- CFI_DEF_CFA_REGISTER rbp
- cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
- pushq %rbp # backlink for old unwinder
- call xen_evtchn_do_upcall
- popq %rsp
- CFI_DEF_CFA_REGISTER rsp
- decl PER_CPU_VAR(irq_count)
+ movq %rdi, %rsp /* we don't return, adjust the stack frame */
+11: incl PER_CPU_VAR(irq_count)
+ movq %rsp, %rbp
+ cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp
+ pushq %rbp /* frame pointer backlink */
+ call xen_evtchn_do_upcall
+ popq %rsp
+ decl PER_CPU_VAR(irq_count)
#ifndef CONFIG_PREEMPT
- call xen_maybe_preempt_hcall
+ call xen_maybe_preempt_hcall
#endif
- jmp error_exit
- CFI_ENDPROC
+ jmp error_exit
END(xen_do_hypervisor_callback)
/*
@@ -1195,51 +1023,35 @@ END(xen_do_hypervisor_callback)
* with its current contents: any discrepancy means we in category 1.
*/
ENTRY(xen_failsafe_callback)
- INTR_FRAME 1 (6*8)
- /*CFI_REL_OFFSET gs,GS*/
- /*CFI_REL_OFFSET fs,FS*/
- /*CFI_REL_OFFSET es,ES*/
- /*CFI_REL_OFFSET ds,DS*/
- CFI_REL_OFFSET r11,8
- CFI_REL_OFFSET rcx,0
- movw %ds,%cx
- cmpw %cx,0x10(%rsp)
- CFI_REMEMBER_STATE
- jne 1f
- movw %es,%cx
- cmpw %cx,0x18(%rsp)
- jne 1f
- movw %fs,%cx
- cmpw %cx,0x20(%rsp)
- jne 1f
- movw %gs,%cx
- cmpw %cx,0x28(%rsp)
- jne 1f
+ movl %ds, %ecx
+ cmpw %cx, 0x10(%rsp)
+ jne 1f
+ movl %es, %ecx
+ cmpw %cx, 0x18(%rsp)
+ jne 1f
+ movl %fs, %ecx
+ cmpw %cx, 0x20(%rsp)
+ jne 1f
+ movl %gs, %ecx
+ cmpw %cx, 0x28(%rsp)
+ jne 1f
/* All segments match their saved values => Category 2 (Bad IRET). */
- movq (%rsp),%rcx
- CFI_RESTORE rcx
- movq 8(%rsp),%r11
- CFI_RESTORE r11
- addq $0x30,%rsp
- CFI_ADJUST_CFA_OFFSET -0x30
- pushq_cfi $0 /* RIP */
- pushq_cfi %r11
- pushq_cfi %rcx
- jmp general_protection
- CFI_RESTORE_STATE
+ movq (%rsp), %rcx
+ movq 8(%rsp), %r11
+ addq $0x30, %rsp
+ pushq $0 /* RIP */
+ pushq %r11
+ pushq %rcx
+ jmp general_protection
1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
- movq (%rsp),%rcx
- CFI_RESTORE rcx
- movq 8(%rsp),%r11
- CFI_RESTORE r11
- addq $0x30,%rsp
- CFI_ADJUST_CFA_OFFSET -0x30
- pushq_cfi $-1 /* orig_ax = -1 => not a system call */
+ movq (%rsp), %rcx
+ movq 8(%rsp), %r11
+ addq $0x30, %rsp
+ pushq $-1 /* orig_ax = -1 => not a system call */
ALLOC_PT_GPREGS_ON_STACK
SAVE_C_REGS
SAVE_EXTRA_REGS
- jmp error_exit
- CFI_ENDPROC
+ jmp error_exit
END(xen_failsafe_callback)
apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
@@ -1252,21 +1064,25 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
hyperv_callback_vector hyperv_vector_handler
#endif /* CONFIG_HYPERV */
-idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry stack_segment do_stack_segment has_error_code=1
+idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry stack_segment do_stack_segment has_error_code=1
+
#ifdef CONFIG_XEN
-idtentry xen_debug do_debug has_error_code=0
-idtentry xen_int3 do_int3 has_error_code=0
-idtentry xen_stack_segment do_stack_segment has_error_code=1
+idtentry xen_debug do_debug has_error_code=0
+idtentry xen_int3 do_int3 has_error_code=0
+idtentry xen_stack_segment do_stack_segment has_error_code=1
#endif
-idtentry general_protection do_general_protection has_error_code=1
-trace_idtentry page_fault do_page_fault has_error_code=1
+
+idtentry general_protection do_general_protection has_error_code=1
+trace_idtentry page_fault do_page_fault has_error_code=1
+
#ifdef CONFIG_KVM_GUEST
-idtentry async_page_fault do_async_page_fault has_error_code=1
+idtentry async_page_fault do_async_page_fault has_error_code=1
#endif
+
#ifdef CONFIG_X86_MCE
-idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
+idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
#endif
/*
@@ -1275,19 +1091,17 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(
* Return: ebx=0: need swapgs on exit, ebx=1: otherwise
*/
ENTRY(paranoid_entry)
- XCPT_FRAME 1 15*8
cld
SAVE_C_REGS 8
SAVE_EXTRA_REGS 8
- movl $1,%ebx
- movl $MSR_GS_BASE,%ecx
+ movl $1, %ebx
+ movl $MSR_GS_BASE, %ecx
rdmsr
- testl %edx,%edx
- js 1f /* negative -> in kernel */
+ testl %edx, %edx
+ js 1f /* negative -> in kernel */
SWAPGS
- xorl %ebx,%ebx
+ xorl %ebx, %ebx
1: ret
- CFI_ENDPROC
END(paranoid_entry)
/*
@@ -1299,17 +1113,17 @@ END(paranoid_entry)
* in syscall entry), so checking for preemption here would
* be complicated. Fortunately, we there's no good reason
* to try to handle preemption here.
+ *
+ * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
*/
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
ENTRY(paranoid_exit)
- DEFAULT_FRAME
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF_DEBUG
- testl %ebx,%ebx /* swapgs needed? */
- jnz paranoid_exit_no_swapgs
+ testl %ebx, %ebx /* swapgs needed? */
+ jnz paranoid_exit_no_swapgs
TRACE_IRQS_IRETQ
SWAPGS_UNSAFE_STACK
- jmp paranoid_exit_restore
+ jmp paranoid_exit_restore
paranoid_exit_no_swapgs:
TRACE_IRQS_IRETQ_DEBUG
paranoid_exit_restore:
@@ -1317,24 +1131,24 @@ paranoid_exit_restore:
RESTORE_C_REGS
REMOVE_PT_GPREGS_FROM_STACK 8
INTERRUPT_RETURN
- CFI_ENDPROC
END(paranoid_exit)
/*
* Save all registers in pt_regs, and switch gs if needed.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ * Return: EBX=0: came from user mode; EBX=1: otherwise
*/
ENTRY(error_entry)
- XCPT_FRAME 1 15*8
cld
SAVE_C_REGS 8
SAVE_EXTRA_REGS 8
- xorl %ebx,%ebx
- testl $3,CS+8(%rsp)
- je error_kernelspace
-error_swapgs:
+ xorl %ebx, %ebx
+ testb $3, CS+8(%rsp)
+ jz error_kernelspace
+
+ /* We entered from user mode */
SWAPGS
-error_sti:
+
+error_entry_done:
TRACE_IRQS_OFF
ret
@@ -1345,56 +1159,66 @@ error_sti:
* for these here too.
*/
error_kernelspace:
- CFI_REL_OFFSET rcx, RCX+8
- incl %ebx
- leaq native_irq_return_iret(%rip),%rcx
- cmpq %rcx,RIP+8(%rsp)
- je error_bad_iret
- movl %ecx,%eax /* zero extend */
- cmpq %rax,RIP+8(%rsp)
- je bstep_iret
- cmpq $gs_change,RIP+8(%rsp)
- je error_swapgs
- jmp error_sti
+ incl %ebx
+ leaq native_irq_return_iret(%rip), %rcx
+ cmpq %rcx, RIP+8(%rsp)
+ je error_bad_iret
+ movl %ecx, %eax /* zero extend */
+ cmpq %rax, RIP+8(%rsp)
+ je bstep_iret
+ cmpq $gs_change, RIP+8(%rsp)
+ jne error_entry_done
+
+ /*
+ * hack: gs_change can fail with user gsbase. If this happens, fix up
+ * gsbase and proceed. We'll fix up the exception and land in
+ * gs_change's error handler with kernel gsbase.
+ */
+ SWAPGS
+ jmp error_entry_done
bstep_iret:
/* Fix truncated RIP */
- movq %rcx,RIP+8(%rsp)
+ movq %rcx, RIP+8(%rsp)
/* fall through */
error_bad_iret:
+ /*
+ * We came from an IRET to user mode, so we have user gsbase.
+ * Switch to kernel gsbase:
+ */
SWAPGS
- mov %rsp,%rdi
- call fixup_bad_iret
- mov %rax,%rsp
- decl %ebx /* Return to usergs */
- jmp error_sti
- CFI_ENDPROC
+
+ /*
+ * Pretend that the exception came from user mode: set up pt_regs
+ * as if we faulted immediately after IRET and clear EBX so that
+ * error_exit knows that we will be returning to user mode.
+ */
+ mov %rsp, %rdi
+ call fixup_bad_iret
+ mov %rax, %rsp
+ decl %ebx
+ jmp error_entry_done
END(error_entry)
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
+/*
+ * On entry, EBS is a "return to kernel mode" flag:
+ * 1: already in kernel mode, don't need SWAPGS
+ * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
+ */
ENTRY(error_exit)
- DEFAULT_FRAME
- movl %ebx,%eax
+ movl %ebx, %eax
RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- GET_THREAD_INFO(%rcx)
- testl %eax,%eax
- jne retint_kernel
- LOCKDEP_SYS_EXIT_IRQ
- movl TI_flags(%rcx),%edx
- movl $_TIF_WORK_MASK,%edi
- andl %edi,%edx
- jnz retint_careful
- jmp retint_swapgs
- CFI_ENDPROC
+ testl %eax, %eax
+ jnz retint_kernel
+ jmp retint_user
END(error_exit)
/* Runs on exception stack */
ENTRY(nmi)
- INTR_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
/*
* We allow breakpoints in NMIs. If a breakpoint occurs, then
@@ -1429,22 +1253,21 @@ ENTRY(nmi)
*/
/* Use %rdx as our temp variable throughout */
- pushq_cfi %rdx
- CFI_REL_OFFSET rdx, 0
+ pushq %rdx
/*
* If %cs was not the kernel segment, then the NMI triggered in user
* space, which means it is definitely not nested.
*/
- cmpl $__KERNEL_CS, 16(%rsp)
- jne first_nmi
+ cmpl $__KERNEL_CS, 16(%rsp)
+ jne first_nmi
/*
* Check the special variable on the stack to see if NMIs are
* executing.
*/
- cmpl $1, -8(%rsp)
- je nested_nmi
+ cmpl $1, -8(%rsp)
+ je nested_nmi
/*
* Now test if the previous stack was an NMI stack.
@@ -1458,51 +1281,46 @@ ENTRY(nmi)
cmpq %rdx, 4*8(%rsp)
/* If the stack pointer is above the NMI stack, this is a normal NMI */
ja first_nmi
+
subq $EXCEPTION_STKSZ, %rdx
cmpq %rdx, 4*8(%rsp)
/* If it is below the NMI stack, it is a normal NMI */
jb first_nmi
/* Ah, it is within the NMI stack, treat it as nested */
- CFI_REMEMBER_STATE
-
nested_nmi:
/*
* Do nothing if we interrupted the fixup in repeat_nmi.
* It's about to repeat the NMI handler, so we are fine
* with ignoring this one.
*/
- movq $repeat_nmi, %rdx
- cmpq 8(%rsp), %rdx
- ja 1f
- movq $end_repeat_nmi, %rdx
- cmpq 8(%rsp), %rdx
- ja nested_nmi_out
+ movq $repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja 1f
+ movq $end_repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja nested_nmi_out
1:
/* Set up the interrupted NMIs stack to jump to repeat_nmi */
- leaq -1*8(%rsp), %rdx
- movq %rdx, %rsp
- CFI_ADJUST_CFA_OFFSET 1*8
- leaq -10*8(%rsp), %rdx
- pushq_cfi $__KERNEL_DS
- pushq_cfi %rdx
- pushfq_cfi
- pushq_cfi $__KERNEL_CS
- pushq_cfi $repeat_nmi
+ leaq -1*8(%rsp), %rdx
+ movq %rdx, %rsp
+ leaq -10*8(%rsp), %rdx
+ pushq $__KERNEL_DS
+ pushq %rdx
+ pushfq
+ pushq $__KERNEL_CS
+ pushq $repeat_nmi
/* Put stack back */
- addq $(6*8), %rsp
- CFI_ADJUST_CFA_OFFSET -6*8
+ addq $(6*8), %rsp
nested_nmi_out:
- popq_cfi %rdx
- CFI_RESTORE rdx
+ popq %rdx
/* No need to check faults here */
INTERRUPT_RETURN
- CFI_RESTORE_STATE
first_nmi:
/*
* Because nested NMIs will use the pushed location that we
@@ -1540,23 +1358,18 @@ first_nmi:
* is also used by nested NMIs and can not be trusted on exit.
*/
/* Do not pop rdx, nested NMIs will corrupt that part of the stack */
- movq (%rsp), %rdx
- CFI_RESTORE rdx
+ movq (%rsp), %rdx
/* Set the NMI executing variable on the stack. */
- pushq_cfi $1
+ pushq $1
- /*
- * Leave room for the "copied" frame
- */
- subq $(5*8), %rsp
- CFI_ADJUST_CFA_OFFSET 5*8
+ /* Leave room for the "copied" frame */
+ subq $(5*8), %rsp
/* Copy the stack frame to the Saved frame */
.rept 5
- pushq_cfi 11*8(%rsp)
+ pushq 11*8(%rsp)
.endr
- CFI_DEF_CFA_OFFSET 5*8
/* Everything up to here is safe from nested NMIs */
@@ -1575,16 +1388,14 @@ repeat_nmi:
* is benign for the non-repeat case, where 1 was pushed just above
* to this very stack slot).
*/
- movq $1, 10*8(%rsp)
+ movq $1, 10*8(%rsp)
/* Make another copy, this one may be modified by nested NMIs */
- addq $(10*8), %rsp
- CFI_ADJUST_CFA_OFFSET -10*8
+ addq $(10*8), %rsp
.rept 5
- pushq_cfi -6*8(%rsp)
+ pushq -6*8(%rsp)
.endr
- subq $(5*8), %rsp
- CFI_DEF_CFA_OFFSET 5*8
+ subq $(5*8), %rsp
end_repeat_nmi:
/*
@@ -1592,7 +1403,7 @@ end_repeat_nmi:
* NMI if the first NMI took an exception and reset our iret stack
* so that we repeat another NMI.
*/
- pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
+ pushq $-1 /* ORIG_RAX: no syscall to restart */
ALLOC_PT_GPREGS_ON_STACK
/*
@@ -1602,8 +1413,7 @@ end_repeat_nmi:
* setting NEED_RESCHED or anything that normal interrupts and
* exceptions might do.
*/
- call paranoid_entry
- DEFAULT_FRAME 0
+ call paranoid_entry
/*
* Save off the CR2 register. If we take a page fault in the NMI then
@@ -1614,22 +1424,21 @@ end_repeat_nmi:
* origin fault. Save it off and restore it if it changes.
* Use the r12 callee-saved register.
*/
- movq %cr2, %r12
+ movq %cr2, %r12
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
- movq %rsp,%rdi
- movq $-1,%rsi
- call do_nmi
+ movq %rsp, %rdi
+ movq $-1, %rsi
+ call do_nmi
/* Did the NMI take a page fault? Restore cr2 if it did */
- movq %cr2, %rcx
- cmpq %rcx, %r12
- je 1f
- movq %r12, %cr2
+ movq %cr2, %rcx
+ cmpq %rcx, %r12
+ je 1f
+ movq %r12, %cr2
1:
-
- testl %ebx,%ebx /* swapgs needed? */
- jnz nmi_restore
+ testl %ebx, %ebx /* swapgs needed? */
+ jnz nmi_restore
nmi_swapgs:
SWAPGS_UNSAFE_STACK
nmi_restore:
@@ -1639,15 +1448,11 @@ nmi_restore:
REMOVE_PT_GPREGS_FROM_STACK 6*8
/* Clear the NMI executing stack variable */
- movq $0, 5*8(%rsp)
- jmp irq_return
- CFI_ENDPROC
+ movq $0, 5*8(%rsp)
+ INTERRUPT_RETURN
END(nmi)
ENTRY(ignore_sysret)
- CFI_STARTPROC
- mov $-ENOSYS,%eax
+ mov $-ENOSYS, %eax
sysret
- CFI_ENDPROC
END(ignore_sysret)
-
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
new file mode 100644
index 000000000000..bb187a6a877c
--- /dev/null
+++ b/arch/x86/entry/entry_64_compat.S
@@ -0,0 +1,556 @@
+/*
+ * Compatibility mode system call entry point for x86-64.
+ *
+ * Copyright 2000-2002 Andi Kleen, SuSE Labs.
+ */
+#include "calling.h"
+#include <asm/asm-offsets.h>
+#include <asm/current.h>
+#include <asm/errno.h>
+#include <asm/ia32_unistd.h>
+#include <asm/thread_info.h>
+#include <asm/segment.h>
+#include <asm/irqflags.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <linux/linkage.h>
+#include <linux/err.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE 0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysexit_audit ia32_ret_from_sys_call
+# define sysretl_audit ia32_ret_from_sys_call
+#endif
+
+ .section .entry.text, "ax"
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret32)
+ swapgs
+ sysretl
+ENDPROC(native_usergs_sysret32)
+#endif
+
+/*
+ * 32-bit SYSENTER instruction entry.
+ *
+ * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
+ * IF and VM in rflags are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old rip (!!!) and rflags.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp user stack
+ * 0(%ebp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSENTER_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ SWAPGS_UNSAFE_STACK
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %ebp, %ebp
+ movl %eax, %eax
+
+ movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER32_DS /* pt_regs->ss */
+ pushq %rbp /* pt_regs->sp */
+ pushfq /* pt_regs->flags */
+ pushq $__USER32_CS /* pt_regs->cs */
+ pushq %r10 /* pt_regs->ip = thread_info->sysenter_return */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ cld
+ sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+ /*
+ * no need to do an access_ok check here because rbp has been
+ * 32-bit zero extended
+ */
+ ASM_STAC
+1: movl (%rbp), %ebp
+ _ASM_EXTABLE(1b, ia32_badarg)
+ ASM_CLAC
+
+ /*
+ * Sysenter doesn't filter flags, so we need to clear NT
+ * ourselves. To save a few cycles, we can check whether
+ * NT was set instead of doing an unconditional popfq.
+ */
+ testl $X86_EFLAGS_NT, EFLAGS(%rsp)
+ jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysenter_tracesys
+
+sysenter_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+sysenter_dispatch:
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysexit_audit
+sysexit_from_sys_call:
+ /*
+ * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
+ * NMI between STI and SYSEXIT has poorly specified behavior,
+ * and and NMI followed by an IRQ with usergs is fatal. So
+ * we just pretend we're using SYSEXIT but we really use
+ * SYSRETL instead.
+ *
+ * This code path is still called 'sysexit' because it pairs
+ * with 'sysenter' and it uses the SYSENTER calling convention.
+ */
+ andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ movl RIP(%rsp), %ecx /* User %eip */
+ RESTORE_RSI_RDI
+ xorl %edx, %edx /* Do not leak kernel information */
+ xorq %r8, %r8
+ xorq %r9, %r9
+ xorq %r10, %r10
+ movl EFLAGS(%rsp), %r11d /* User eflags */
+ TRACE_IRQS_ON
+
+ /*
+ * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT,
+ * since it avoids a dicey window with interrupts enabled.
+ */
+ movl RSP(%rsp), %esp
+
+ /*
+ * USERGS_SYSRET32 does:
+ * gsbase = user's gs base
+ * eip = ecx
+ * rflags = r11
+ * cs = __USER32_CS
+ * ss = __USER_DS
+ *
+ * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
+ *
+ * pop %ebp
+ * pop %edx
+ * pop %ecx
+ *
+ * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
+ * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's
+ * address (already known to user code), and R12-R15 are
+ * callee-saved and therefore don't contain any interesting
+ * kernel data.
+ */
+ USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+ .macro auditsys_entry_common
+ /*
+ * At this point, registers hold syscall args in the 32-bit syscall ABI:
+ * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
+ *
+ * We want to pass them to __audit_syscall_entry(), which is a 64-bit
+ * C function with 5 parameters, so shuffle them to match what
+ * the function expects: RDI,RSI,RDX,RCX,R8.
+ */
+ movl %esi, %r8d /* arg5 (R8 ) <= 4th syscall arg (ESI) */
+ xchg %ecx, %edx /* arg4 (RCX) <= 3rd syscall arg (EDX) */
+ /* arg3 (RDX) <= 2nd syscall arg (ECX) */
+ movl %ebx, %esi /* arg2 (RSI) <= 1st syscall arg (EBX) */
+ movl %eax, %edi /* arg1 (RDI) <= syscall number (EAX) */
+ call __audit_syscall_entry
+
+ /*
+ * We are going to jump back to the syscall dispatch code.
+ * Prepare syscall args as required by the 64-bit C ABI.
+ * Registers clobbered by __audit_syscall_entry() are
+ * loaded from pt_regs on stack:
+ */
+ movl ORIG_RAX(%rsp), %eax /* syscall number */
+ movl %ebx, %edi /* arg1 */
+ movl RCX(%rsp), %esi /* arg2 */
+ movl RDX(%rsp), %edx /* arg3 */
+ movl RSI(%rsp), %ecx /* arg4 */
+ movl RDI(%rsp), %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ .endm
+
+ .macro auditsys_exit exit
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz ia32_ret_from_sys_call
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ movl %eax, %esi /* second arg, syscall return value */
+ cmpl $-MAX_ERRNO, %eax /* is it an error ? */
+ jbe 1f
+ movslq %eax, %rsi /* if error sign extend to 64 bits */
+1: setbe %al /* 1 if error, 0 if not */
+ movzbl %al, %edi /* zero-extend that into %edi */
+ call __audit_syscall_exit
+ movq RAX(%rsp), %rax /* reload syscall return value */
+ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz \exit
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ jmp int_with_check
+ .endm
+
+sysenter_auditsys:
+ auditsys_entry_common
+ jmp sysenter_dispatch
+
+sysexit_audit:
+ auditsys_exit sysexit_from_sys_call
+#endif
+
+sysenter_fix_flags:
+ pushq $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+ popfq
+ jmp sysenter_flags_fixed
+
+sysenter_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz sysenter_auditsys
+#endif
+ SAVE_EXTRA_REGS
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+
+ /* Reload arg registers from stack. (see sysenter_tracesys) */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+
+ RESTORE_EXTRA_REGS
+ jmp sysenter_do_call
+ENDPROC(entry_SYSENTER_compat)
+
+/*
+ * 32-bit SYSCALL instruction entry.
+ *
+ * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Note: rflags saving+masking-with-MSR happens only in Long mode
+ * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
+ * Don't get confused: rflags saving+masking depends on Long Mode Active bit
+ * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
+ * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
+ *
+ * Arguments:
+ * eax system call number
+ * ecx return address
+ * ebx arg1
+ * ebp arg2 (note: not saved in the stack frame, should not be touched)
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * esp user stack
+ * 0(%esp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSCALL_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ SWAPGS_UNSAFE_STACK
+ movl %esp, %r8d
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %eax, %eax
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER32_DS /* pt_regs->ss */
+ pushq %r8 /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER32_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rbp /* pt_regs->cx */
+ movl %ebp, %ecx
+ pushq $-ENOSYS /* pt_regs->ax */
+ sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+ /*
+ * No need to do an access_ok check here because r8 has been
+ * 32-bit zero extended:
+ */
+ ASM_STAC
+1: movl (%r8), %ebp
+ _ASM_EXTABLE(1b, ia32_badarg)
+ ASM_CLAC
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz cstar_tracesys
+
+cstar_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+
+cstar_dispatch:
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ movl RCX(%rsp), %ebp
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysretl_audit
+
+sysretl_from_sys_call:
+ andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ RESTORE_RSI_RDI_RDX
+ movl RIP(%rsp), %ecx
+ movl EFLAGS(%rsp), %r11d
+ xorq %r10, %r10
+ xorq %r9, %r9
+ xorq %r8, %r8
+ TRACE_IRQS_ON
+ movl RSP(%rsp), %esp
+ /*
+ * 64-bit->32-bit SYSRET restores eip from ecx,
+ * eflags from r11 (but RF and VM bits are forced to 0),
+ * cs and ss are loaded from MSRs.
+ * (Note: 32-bit->32-bit SYSRET is different: since r11
+ * does not exist, it merely sets eflags.IF=1).
+ *
+ * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+ * descriptor is not reinitialized. This means that we must
+ * avoid SYSRET with SS == NULL, which could happen if we schedule,
+ * exit the kernel, and re-enter using an interrupt vector. (All
+ * interrupt entries on x86_64 set SS to NULL.) We prevent that
+ * from happening by reloading SS in __switch_to.
+ */
+ USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+cstar_auditsys:
+ auditsys_entry_common
+ jmp cstar_dispatch
+
+sysretl_audit:
+ auditsys_exit sysretl_from_sys_call
+#endif
+
+cstar_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz cstar_auditsys
+#endif
+ SAVE_EXTRA_REGS
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+
+ /* Reload arg registers from stack. (see sysenter_tracesys) */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+
+ RESTORE_EXTRA_REGS
+ jmp cstar_do_call
+END(entry_SYSCALL_compat)
+
+ia32_badarg:
+ ASM_CLAC
+ movq $-EFAULT, RAX(%rsp)
+ia32_ret_from_sys_call:
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ jmp int_ret_from_sys_call
+
+/*
+ * Emulated IA32 system calls via int 0x80.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp arg6 (note: not saved in the stack frame, should not be touched)
+ *
+ * Notes:
+ * Uses the same stack frame as the x86-64 version.
+ * All registers except eax must be saved (but ptrace may violate that).
+ * Arguments are zero extended. For system calls that want sign extension and
+ * take long arguments a wrapper is needed. Most calls can just be called
+ * directly.
+ * Assumes it is only called from user space and entered with interrupts off.
+ */
+
+ENTRY(entry_INT80_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
+ SWAPGS
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %eax, %eax
+
+ /* Construct struct pt_regs on stack (iret frame is already on stack) */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ pushq $0 /* pt_regs->r8 */
+ pushq $0 /* pt_regs->r9 */
+ pushq $0 /* pt_regs->r10 */
+ pushq $0 /* pt_regs->r11 */
+ cld
+ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz ia32_tracesys
+
+ia32_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ jmp int_ret_from_sys_call
+
+ia32_tracesys:
+ SAVE_EXTRA_REGS
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+ /*
+ * Reload arg registers from stack in case ptrace changed them.
+ * Don't reload %eax because syscall_trace_enter() returned
+ * the %rax value we should see. But do truncate it to 32 bits.
+ * If it's -1 to make us punt the syscall, then (u32)-1 is still
+ * an appropriately invalid value.
+ */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+ RESTORE_EXTRA_REGS
+ jmp ia32_do_call
+END(entry_INT80_compat)
+
+ .macro PTREGSCALL label, func
+ ALIGN
+GLOBAL(\label)
+ leaq \func(%rip), %rax
+ jmp ia32_ptregs_common
+ .endm
+
+ PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
+ PTREGSCALL stub32_sigreturn, sys32_sigreturn
+ PTREGSCALL stub32_fork, sys_fork
+ PTREGSCALL stub32_vfork, sys_vfork
+
+ ALIGN
+GLOBAL(stub32_clone)
+ leaq sys_clone(%rip), %rax
+ /*
+ * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
+ * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
+ *
+ * The native 64-bit kernel's sys_clone() implements the latter,
+ * so we need to swap arguments here before calling it:
+ */
+ xchg %r8, %rcx
+ jmp ia32_ptregs_common
+
+ ALIGN
+ia32_ptregs_common:
+ SAVE_EXTRA_REGS 8
+ call *%rax
+ RESTORE_EXTRA_REGS 8
+ ret
+END(ia32_ptregs_common)
diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/entry/syscall_32.c
index 3777189c4a19..8ea34f94e973 100644
--- a/arch/x86/kernel/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -10,7 +10,7 @@
#else
#define SYM(sym, compat) sym
#define ia32_sys_call_table sys_call_table
-#define __NR_ia32_syscall_max __NR_syscall_max
+#define __NR_syscall_compat_max __NR_syscall_max
#endif
#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
@@ -23,11 +23,11 @@ typedef asmlinkage void (*sys_call_ptr_t)(void);
extern asmlinkage void sys_ni_syscall(void);
-__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
+__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
*/
- [0 ... __NR_ia32_syscall_max] = &sys_ni_syscall,
+ [0 ... __NR_syscall_compat_max] = &sys_ni_syscall,
#include <asm/syscalls_32.h>
};
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/entry/syscall_64.c
index 4ac730b37f0b..4ac730b37f0b 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile
index a55abb9f6c5e..57aa59fd140c 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/entry/syscalls/Makefile
@@ -1,5 +1,5 @@
-out := $(obj)/../include/generated/asm
-uapi := $(obj)/../include/generated/uapi/asm
+out := $(obj)/../../include/generated/asm
+uapi := $(obj)/../../include/generated/uapi/asm
# Create output directory if not already present
_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ef8187f9d28d..ef8187f9d28d 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9ef32d5f1b19..9ef32d5f1b19 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
diff --git a/arch/x86/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh
index 31fd5f1f38f7..31fd5f1f38f7 100644
--- a/arch/x86/syscalls/syscallhdr.sh
+++ b/arch/x86/entry/syscalls/syscallhdr.sh
diff --git a/arch/x86/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh
index 0e7f8ec071e7..0e7f8ec071e7 100644
--- a/arch/x86/syscalls/syscalltbl.sh
+++ b/arch/x86/entry/syscalls/syscalltbl.sh
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/entry/thunk_32.S
index 5eb715087b80..e5a17114a8c4 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -6,16 +6,14 @@
*/
#include <linux/linkage.h>
#include <asm/asm.h>
- #include <asm/dwarf2.h>
/* put return address in eax (arg1) */
.macro THUNK name, func, put_ret_addr_in_eax=0
.globl \name
\name:
- CFI_STARTPROC
- pushl_cfi_reg eax
- pushl_cfi_reg ecx
- pushl_cfi_reg edx
+ pushl %eax
+ pushl %ecx
+ pushl %edx
.if \put_ret_addr_in_eax
/* Place EIP in the arg1 */
@@ -23,11 +21,10 @@
.endif
call \func
- popl_cfi_reg edx
- popl_cfi_reg ecx
- popl_cfi_reg eax
+ popl %edx
+ popl %ecx
+ popl %eax
ret
- CFI_ENDPROC
_ASM_NOKPROBE(\name)
.endm
@@ -38,8 +35,6 @@
#ifdef CONFIG_PREEMPT
THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
- THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
+ THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
#endif
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/entry/thunk_64.S
index f89ba4e93025..efb2b932b748 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -6,35 +6,32 @@
* Subject to the GNU public license, v.2. No warranty of any kind.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
+#include "calling.h"
#include <asm/asm.h>
/* rdi: arg1 ... normal C conventions. rax is saved/restored. */
.macro THUNK name, func, put_ret_addr_in_rdi=0
.globl \name
\name:
- CFI_STARTPROC
/* this one pushes 9 elems, the next one would be %rIP */
- pushq_cfi_reg rdi
- pushq_cfi_reg rsi
- pushq_cfi_reg rdx
- pushq_cfi_reg rcx
- pushq_cfi_reg rax
- pushq_cfi_reg r8
- pushq_cfi_reg r9
- pushq_cfi_reg r10
- pushq_cfi_reg r11
+ pushq %rdi
+ pushq %rsi
+ pushq %rdx
+ pushq %rcx
+ pushq %rax
+ pushq %r8
+ pushq %r9
+ pushq %r10
+ pushq %r11
.if \put_ret_addr_in_rdi
/* 9*8(%rsp) is return addr on stack */
- movq_cfi_restore 9*8, rdi
+ movq 9*8(%rsp), %rdi
.endif
call \func
jmp restore
- CFI_ENDPROC
_ASM_NOKPROBE(\name)
.endm
@@ -49,27 +46,22 @@
#ifdef CONFIG_PREEMPT
THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
- THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
+ THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
#endif
#if defined(CONFIG_TRACE_IRQFLAGS) \
|| defined(CONFIG_DEBUG_LOCK_ALLOC) \
|| defined(CONFIG_PREEMPT)
- CFI_STARTPROC
- CFI_ADJUST_CFA_OFFSET 9*8
restore:
- popq_cfi_reg r11
- popq_cfi_reg r10
- popq_cfi_reg r9
- popq_cfi_reg r8
- popq_cfi_reg rax
- popq_cfi_reg rcx
- popq_cfi_reg rdx
- popq_cfi_reg rsi
- popq_cfi_reg rdi
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+ popq %rdi
ret
- CFI_ENDPROC
_ASM_NOKPROBE(restore)
#endif
diff --git a/arch/x86/vdso/.gitignore b/arch/x86/entry/vdso/.gitignore
index aae8ffdd5880..aae8ffdd5880 100644
--- a/arch/x86/vdso/.gitignore
+++ b/arch/x86/entry/vdso/.gitignore
diff --git a/arch/x86/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index e97032069f88..e97032069f88 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
diff --git a/arch/x86/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh
index 7ee90a9b549d..7ee90a9b549d 100755
--- a/arch/x86/vdso/checkundef.sh
+++ b/arch/x86/entry/vdso/checkundef.sh
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 9793322751e0..9793322751e0 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index de2c921025f5..de2c921025f5 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
diff --git a/arch/x86/vdso/vdso-note.S b/arch/x86/entry/vdso/vdso-note.S
index 79a071e4357e..79a071e4357e 100644
--- a/arch/x86/vdso/vdso-note.S
+++ b/arch/x86/entry/vdso/vdso-note.S
diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S
index 6807932643c2..6807932643c2 100644
--- a/arch/x86/vdso/vdso.lds.S
+++ b/arch/x86/entry/vdso/vdso.lds.S
diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 8627db24a7f6..8627db24a7f6 100644
--- a/arch/x86/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 0224987556ce..0224987556ce 100644
--- a/arch/x86/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index e904c270573b..e904c270573b 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
diff --git a/arch/x86/vdso/vdso32/.gitignore b/arch/x86/entry/vdso/vdso32/.gitignore
index e45fba9d0ced..e45fba9d0ced 100644
--- a/arch/x86/vdso/vdso32/.gitignore
+++ b/arch/x86/entry/vdso/vdso32/.gitignore
diff --git a/arch/x86/vdso/vdso32/int80.S b/arch/x86/entry/vdso/vdso32/int80.S
index b15b7c01aedb..b15b7c01aedb 100644
--- a/arch/x86/vdso/vdso32/int80.S
+++ b/arch/x86/entry/vdso/vdso32/int80.S
diff --git a/arch/x86/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S
index c83f25734696..c83f25734696 100644
--- a/arch/x86/vdso/vdso32/note.S
+++ b/arch/x86/entry/vdso/vdso32/note.S
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S
index d7ec4e251c0a..d7ec4e251c0a 100644
--- a/arch/x86/vdso/vdso32/sigreturn.S
+++ b/arch/x86/entry/vdso/vdso32/sigreturn.S
diff --git a/arch/x86/vdso/vdso32/syscall.S b/arch/x86/entry/vdso/vdso32/syscall.S
index 6b286bb5251c..6b286bb5251c 100644
--- a/arch/x86/vdso/vdso32/syscall.S
+++ b/arch/x86/entry/vdso/vdso32/syscall.S
diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/entry/vdso/vdso32/sysenter.S
index e354bceee0e0..e354bceee0e0 100644
--- a/arch/x86/vdso/vdso32/sysenter.S
+++ b/arch/x86/entry/vdso/vdso32/sysenter.S
diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
index 175cc72c0f68..175cc72c0f68 100644
--- a/arch/x86/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
diff --git a/arch/x86/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
index 541468e25265..541468e25265 100644
--- a/arch/x86/vdso/vdso32/vdso-fakesections.c
+++ b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
index 31056cf294bf..31056cf294bf 100644
--- a/arch/x86/vdso/vdso32/vdso32.lds.S
+++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S
index 697c11ece90c..697c11ece90c 100644
--- a/arch/x86/vdso/vdsox32.lds.S
+++ b/arch/x86/entry/vdso/vdsox32.lds.S
diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/entry/vdso/vgetcpu.c
index 8ec3d1f4ce9a..8ec3d1f4ce9a 100644
--- a/arch/x86/vdso/vgetcpu.c
+++ b/arch/x86/entry/vdso/vgetcpu.c
diff --git a/arch/x86/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 1c9f750c3859..1c9f750c3859 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile
new file mode 100644
index 000000000000..a9f4856f622a
--- /dev/null
+++ b/arch/x86/entry/vsyscall/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the x86 low level vsyscall code
+#
+obj-y := vsyscall_gtod.o
+
+obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
+
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 2dcc6ff6fdcc..2dcc6ff6fdcc 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
index c9596a9af159..c9596a9af159 100644
--- a/arch/x86/kernel/vsyscall_emu_64.S
+++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
index 51e330416995..51e330416995 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
diff --git a/arch/x86/kernel/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h
index a8b2edec54fe..9dd7359a38a8 100644
--- a/arch/x86/kernel/vsyscall_trace.h
+++ b/arch/x86/entry/vsyscall/vsyscall_trace.h
@@ -24,6 +24,6 @@ TRACE_EVENT(emulate_vsyscall,
#endif
#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../arch/x86/kernel
+#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/
#define TRACE_INCLUDE_FILE vsyscall_trace
#include <trace/define_trace.h>
diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile
index bb635c641869..cd4339bae066 100644
--- a/arch/x86/ia32/Makefile
+++ b/arch/x86/ia32/Makefile
@@ -2,7 +2,7 @@
# Makefile for the ia32 kernel emulation subsystem.
#
-obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o
+obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_signal.o
obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index c81d35e6c7f1..ae3a29ae875b 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -21,8 +21,8 @@
#include <linux/binfmts.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
#include <asm/ptrace.h>
#include <asm/ia32_unistd.h>
#include <asm/user32.h>
@@ -198,7 +198,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
buf = compat_ptr(tmp);
} get_user_catch(err);
- err |= restore_xstate_sig(buf, 1);
+ err |= fpu__restore_sig(buf, 1);
force_iret();
@@ -308,6 +308,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
size_t frame_size,
void __user **fpstate)
{
+ struct fpu *fpu = &current->thread.fpu;
unsigned long sp;
/* Default to using normal stack */
@@ -322,12 +323,12 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
ksig->ka.sa.sa_restorer)
sp = (unsigned long) ksig->ka.sa.sa_restorer;
- if (used_math()) {
+ if (fpu->fpstate_active) {
unsigned long fx_aligned, math_size;
- sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size);
+ sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
*fpstate = (struct _fpstate_ia32 __user *) sp;
- if (save_xstate_sig(*fpstate, (void __user *)fx_aligned,
+ if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
math_size) < 0)
return (void __user *) -1L;
}
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
deleted file mode 100644
index 72bf2680f819..000000000000
--- a/arch/x86/ia32/ia32entry.S
+++ /dev/null
@@ -1,611 +0,0 @@
-/*
- * Compatibility mode system call entry point for x86-64.
- *
- * Copyright 2000-2002 Andi Kleen, SuSE Labs.
- */
-
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm-offsets.h>
-#include <asm/current.h>
-#include <asm/errno.h>
-#include <asm/ia32_unistd.h>
-#include <asm/thread_info.h>
-#include <asm/segment.h>
-#include <asm/irqflags.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-#include <linux/linkage.h>
-#include <linux/err.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE 0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysexit_audit ia32_ret_from_sys_call
-#define sysretl_audit ia32_ret_from_sys_call
-#endif
-
- .section .entry.text, "ax"
-
- /* clobbers %rax */
- .macro CLEAR_RREGS _r9=rax
- xorl %eax,%eax
- movq %rax,R11(%rsp)
- movq %rax,R10(%rsp)
- movq %\_r9,R9(%rsp)
- movq %rax,R8(%rsp)
- .endm
-
- /*
- * Reload arg registers from stack in case ptrace changed them.
- * We don't reload %eax because syscall_trace_enter() returned
- * the %rax value we should see. Instead, we just truncate that
- * value to 32 bits again as we did on entry from user mode.
- * If it's a new value set by user_regset during entry tracing,
- * this matches the normal truncation of the user-mode value.
- * If it's -1 to make us punt the syscall, then (u32)-1 is still
- * an appropriately invalid value.
- */
- .macro LOAD_ARGS32 _r9=0
- .if \_r9
- movl R9(%rsp),%r9d
- .endif
- movl RCX(%rsp),%ecx
- movl RDX(%rsp),%edx
- movl RSI(%rsp),%esi
- movl RDI(%rsp),%edi
- movl %eax,%eax /* zero extension */
- .endm
-
- .macro CFI_STARTPROC32 simple
- CFI_STARTPROC \simple
- CFI_UNDEFINED r8
- CFI_UNDEFINED r9
- CFI_UNDEFINED r10
- CFI_UNDEFINED r11
- CFI_UNDEFINED r12
- CFI_UNDEFINED r13
- CFI_UNDEFINED r14
- CFI_UNDEFINED r15
- .endm
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret32)
- swapgs
- sysretl
-ENDPROC(native_usergs_sysret32)
-
-ENTRY(native_irq_enable_sysexit)
- swapgs
- sti
- sysexit
-ENDPROC(native_irq_enable_sysexit)
-#endif
-
-/*
- * 32bit SYSENTER instruction entry.
- *
- * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
- * IF and VM in rflags are cleared (IOW: interrupts are off).
- * SYSENTER does not save anything on the stack,
- * and does not save old rip (!!!) and rflags.
- *
- * Arguments:
- * eax system call number
- * ebx arg1
- * ecx arg2
- * edx arg3
- * esi arg4
- * edi arg5
- * ebp user stack
- * 0(%ebp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_sysenter_target)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rsp,rbp
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- SWAPGS_UNSAFE_STACK
- movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %ebp, %ebp
- movl %eax, %eax
-
- movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
- CFI_REGISTER rip,r10
-
- /* Construct struct pt_regs on stack */
- pushq_cfi $__USER32_DS /* pt_regs->ss */
- pushq_cfi %rbp /* pt_regs->sp */
- CFI_REL_OFFSET rsp,0
- pushfq_cfi /* pt_regs->flags */
- pushq_cfi $__USER32_CS /* pt_regs->cs */
- pushq_cfi %r10 /* pt_regs->ip = thread_info->sysenter_return */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi_reg rax /* pt_regs->ax */
- cld
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- /*
- * no need to do an access_ok check here because rbp has been
- * 32bit zero extended
- */
- ASM_STAC
-1: movl (%rbp),%ebp
- _ASM_EXTABLE(1b,ia32_badarg)
- ASM_CLAC
-
- /*
- * Sysenter doesn't filter flags, so we need to clear NT
- * ourselves. To save a few cycles, we can check whether
- * NT was set instead of doing an unconditional popfq.
- */
- testl $X86_EFLAGS_NT,EFLAGS(%rsp)
- jnz sysenter_fix_flags
-sysenter_flags_fixed:
-
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- CFI_REMEMBER_STATE
- jnz sysenter_tracesys
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
-sysenter_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- movl %ebp,%r9d /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
-sysenter_dispatch:
- call *ia32_sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysexit_audit
-sysexit_from_sys_call:
- /*
- * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
- * NMI between STI and SYSEXIT has poorly specified behavior,
- * and and NMI followed by an IRQ with usergs is fatal. So
- * we just pretend we're using SYSEXIT but we really use
- * SYSRETL instead.
- *
- * This code path is still called 'sysexit' because it pairs
- * with 'sysenter' and it uses the SYSENTER calling convention.
- */
- andl $~TS_COMPAT,ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- movl RIP(%rsp),%ecx /* User %eip */
- CFI_REGISTER rip,rcx
- RESTORE_RSI_RDI
- xorl %edx,%edx /* avoid info leaks */
- xorq %r8,%r8
- xorq %r9,%r9
- xorq %r10,%r10
- movl EFLAGS(%rsp),%r11d /* User eflags */
- /*CFI_RESTORE rflags*/
- TRACE_IRQS_ON
-
- /*
- * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT,
- * since it avoids a dicey window with interrupts enabled.
- */
- movl RSP(%rsp),%esp
-
- /*
- * USERGS_SYSRET32 does:
- * gsbase = user's gs base
- * eip = ecx
- * rflags = r11
- * cs = __USER32_CS
- * ss = __USER_DS
- *
- * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
- *
- * pop %ebp
- * pop %edx
- * pop %ecx
- *
- * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
- * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's
- * address (already known to user code), and R12-R15 are
- * callee-saved and therefore don't contain any interesting
- * kernel data.
- */
- USERGS_SYSRET32
-
- CFI_RESTORE_STATE
-
-#ifdef CONFIG_AUDITSYSCALL
- .macro auditsys_entry_common
- movl %esi,%r8d /* 5th arg: 4th syscall arg */
- movl %ecx,%r9d /*swap with edx*/
- movl %edx,%ecx /* 4th arg: 3rd syscall arg */
- movl %r9d,%edx /* 3rd arg: 2nd syscall arg */
- movl %ebx,%esi /* 2nd arg: 1st syscall arg */
- movl %eax,%edi /* 1st arg: syscall number */
- call __audit_syscall_entry
- movl RAX(%rsp),%eax /* reload syscall number */
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
- movl %ebx,%edi /* reload 1st syscall arg */
- movl RCX(%rsp),%esi /* reload 2nd syscall arg */
- movl RDX(%rsp),%edx /* reload 3rd syscall arg */
- movl RSI(%rsp),%ecx /* reload 4th syscall arg */
- movl RDI(%rsp),%r8d /* reload 5th syscall arg */
- .endm
-
- .macro auditsys_exit exit
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz ia32_ret_from_sys_call
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- movl %eax,%esi /* second arg, syscall return value */
- cmpl $-MAX_ERRNO,%eax /* is it an error ? */
- jbe 1f
- movslq %eax, %rsi /* if error sign extend to 64 bits */
-1: setbe %al /* 1 if error, 0 if not */
- movzbl %al,%edi /* zero-extend that into %edi */
- call __audit_syscall_exit
- movq RAX(%rsp),%rax /* reload syscall return value */
- movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz \exit
- CLEAR_RREGS
- jmp int_with_check
- .endm
-
-sysenter_auditsys:
- auditsys_entry_common
- movl %ebp,%r9d /* reload 6th syscall arg */
- jmp sysenter_dispatch
-
-sysexit_audit:
- auditsys_exit sysexit_from_sys_call
-#endif
-
-sysenter_fix_flags:
- pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
- popfq_cfi
- jmp sysenter_flags_fixed
-
-sysenter_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz sysenter_auditsys
-#endif
- SAVE_EXTRA_REGS
- CLEAR_RREGS
- movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
- jmp sysenter_do_call
- CFI_ENDPROC
-ENDPROC(ia32_sysenter_target)
-
-/*
- * 32bit SYSCALL instruction entry.
- *
- * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
- * then loads new ss, cs, and rip from previously programmed MSRs.
- * rflags gets masked by a value from another MSR (so CLD and CLAC
- * are not needed). SYSCALL does not save anything on the stack
- * and does not change rsp.
- *
- * Note: rflags saving+masking-with-MSR happens only in Long mode
- * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it).
- * Don't get confused: rflags saving+masking depends on Long Mode Active bit
- * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
- * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
- *
- * Arguments:
- * eax system call number
- * ecx return address
- * ebx arg1
- * ebp arg2 (note: not saved in the stack frame, should not be touched)
- * edx arg3
- * esi arg4
- * edi arg5
- * esp user stack
- * 0(%esp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_cstar_target)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rip,rcx
- /*CFI_REGISTER rflags,r11*/
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- SWAPGS_UNSAFE_STACK
- movl %esp,%r8d
- CFI_REGISTER rsp,r8
- movq PER_CPU_VAR(kernel_stack),%rsp
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %eax,%eax
-
- /* Construct struct pt_regs on stack */
- pushq_cfi $__USER32_DS /* pt_regs->ss */
- pushq_cfi %r8 /* pt_regs->sp */
- CFI_REL_OFFSET rsp,0
- pushq_cfi %r11 /* pt_regs->flags */
- pushq_cfi $__USER32_CS /* pt_regs->cs */
- pushq_cfi %rcx /* pt_regs->ip */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rbp /* pt_regs->cx */
- movl %ebp,%ecx
- pushq_cfi_reg rax /* pt_regs->ax */
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- /*
- * no need to do an access_ok check here because r8 has been
- * 32bit zero extended
- */
- ASM_STAC
-1: movl (%r8),%r9d
- _ASM_EXTABLE(1b,ia32_badarg)
- ASM_CLAC
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- CFI_REMEMBER_STATE
- jnz cstar_tracesys
- cmpq $IA32_NR_syscalls-1,%rax
- ja ia32_badsys
-cstar_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- /* r9 already loaded */ /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
-cstar_dispatch:
- call *ia32_sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysretl_audit
-sysretl_from_sys_call:
- andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- RESTORE_RSI_RDI_RDX
- movl RIP(%rsp),%ecx
- CFI_REGISTER rip,rcx
- movl EFLAGS(%rsp),%r11d
- /*CFI_REGISTER rflags,r11*/
- xorq %r10,%r10
- xorq %r9,%r9
- xorq %r8,%r8
- TRACE_IRQS_ON
- movl RSP(%rsp),%esp
- CFI_RESTORE rsp
- /*
- * 64bit->32bit SYSRET restores eip from ecx,
- * eflags from r11 (but RF and VM bits are forced to 0),
- * cs and ss are loaded from MSRs.
- * (Note: 32bit->32bit SYSRET is different: since r11
- * does not exist, it merely sets eflags.IF=1).
- *
- * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
- * descriptor is not reinitialized. This means that we must
- * avoid SYSRET with SS == NULL, which could happen if we schedule,
- * exit the kernel, and re-enter using an interrupt vector. (All
- * interrupt entries on x86_64 set SS to NULL.) We prevent that
- * from happening by reloading SS in __switch_to.
- */
- USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-cstar_auditsys:
- CFI_RESTORE_STATE
- movl %r9d,R9(%rsp) /* register to be clobbered by call */
- auditsys_entry_common
- movl R9(%rsp),%r9d /* reload 6th syscall arg */
- jmp cstar_dispatch
-
-sysretl_audit:
- auditsys_exit sysretl_from_sys_call
-#endif
-
-cstar_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz cstar_auditsys
-#endif
- xchgl %r9d,%ebp
- SAVE_EXTRA_REGS
- CLEAR_RREGS r9
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- xchgl %ebp,%r9d
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
- jmp cstar_do_call
-END(ia32_cstar_target)
-
-ia32_badarg:
- ASM_CLAC
- movq $-EFAULT,%rax
- jmp ia32_sysret
- CFI_ENDPROC
-
-/*
- * Emulated IA32 system calls via int 0x80.
- *
- * Arguments:
- * eax system call number
- * ebx arg1
- * ecx arg2
- * edx arg3
- * esi arg4
- * edi arg5
- * ebp arg6 (note: not saved in the stack frame, should not be touched)
- *
- * Notes:
- * Uses the same stack frame as the x86-64 version.
- * All registers except eax must be saved (but ptrace may violate that).
- * Arguments are zero extended. For system calls that want sign extension and
- * take long arguments a wrapper is needed. Most calls can just be called
- * directly.
- * Assumes it is only called from user space and entered with interrupts off.
- */
-
-ENTRY(ia32_syscall)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,5*8
- /*CFI_REL_OFFSET ss,4*8 */
- CFI_REL_OFFSET rsp,3*8
- /*CFI_REL_OFFSET rflags,2*8 */
- /*CFI_REL_OFFSET cs,1*8 */
- CFI_REL_OFFSET rip,0*8
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- PARAVIRT_ADJUST_EXCEPTION_FRAME
- SWAPGS
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %eax,%eax
-
- /* Construct struct pt_regs on stack (iret frame is already on stack) */
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi_reg rax /* pt_regs->ax */
- cld
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz ia32_tracesys
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
-ia32_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- movl %ebp,%r9d /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
- call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
-ia32_sysret:
- movq %rax,RAX(%rsp)
-ia32_ret_from_sys_call:
- CLEAR_RREGS
- jmp int_ret_from_sys_call
-
-ia32_tracesys:
- SAVE_EXTRA_REGS
- CLEAR_RREGS
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
- jmp ia32_do_call
-END(ia32_syscall)
-
-ia32_badsys:
- movq $0,ORIG_RAX(%rsp)
- movq $-ENOSYS,%rax
- jmp ia32_sysret
-
- CFI_ENDPROC
-
- .macro PTREGSCALL label, func
- ALIGN
-GLOBAL(\label)
- leaq \func(%rip),%rax
- jmp ia32_ptregs_common
- .endm
-
- CFI_STARTPROC32
-
- PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
- PTREGSCALL stub32_sigreturn, sys32_sigreturn
- PTREGSCALL stub32_fork, sys_fork
- PTREGSCALL stub32_vfork, sys_vfork
-
- ALIGN
-GLOBAL(stub32_clone)
- leaq sys_clone(%rip),%rax
- mov %r8, %rcx
- jmp ia32_ptregs_common
-
- ALIGN
-ia32_ptregs_common:
- CFI_ENDPROC
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,SIZEOF_PTREGS
- CFI_REL_OFFSET rax,RAX
- CFI_REL_OFFSET rcx,RCX
- CFI_REL_OFFSET rdx,RDX
- CFI_REL_OFFSET rsi,RSI
- CFI_REL_OFFSET rdi,RDI
- CFI_REL_OFFSET rip,RIP
-/* CFI_REL_OFFSET cs,CS*/
-/* CFI_REL_OFFSET rflags,EFLAGS*/
- CFI_REL_OFFSET rsp,RSP
-/* CFI_REL_OFFSET ss,SS*/
- SAVE_EXTRA_REGS 8
- call *%rax
- RESTORE_EXTRA_REGS 8
- ret
- CFI_ENDPROC
-END(ia32_ptregs_common)
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index bdf02eeee765..e7636bac7372 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -18,6 +18,12 @@
.endm
#endif
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
.long \orig - .
.long \alt - .
@@ -27,6 +33,12 @@
.byte \pad_len
.endm
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
.macro ALTERNATIVE oldinstr, newinstr, feature
140:
\oldinstr
@@ -55,6 +67,12 @@
*/
#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
140:
\oldinstr
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index ba32af062f61..7bfc85bbb8ff 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -52,6 +52,12 @@ struct alt_instr {
u8 padlen; /* length of build-time padding */
} __packed;
+/*
+ * Debug flag that can be tested to see whether alternative
+ * instructions were patched in already:
+ */
+extern int alternatives_patched;
+
extern void alternative_instructions(void);
extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index aaac3b2fb746..1a5da2e63aee 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -98,11 +98,22 @@ static inline u16 amd_get_node_id(struct pci_dev *pdev)
return 0;
}
+static inline bool amd_gart_present(void)
+{
+ /* GART present only on Fam15h, upto model 0fh */
+ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+ (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
+ return true;
+
+ return false;
+}
+
#else
#define amd_nb_num(x) 0
#define amd_nb_has_feature(x) false
#define node_to_amd_nb(x) NULL
+#define amd_gart_present(x) false
#endif
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 976b86a325e5..c8393634ca0c 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -644,6 +644,12 @@ static inline void entering_ack_irq(void)
entering_irq();
}
+static inline void ipi_entering_ack_irq(void)
+{
+ ack_APIC_irq();
+ irq_enter();
+}
+
static inline void exiting_irq(void)
{
irq_exit();
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 7730c1c5c83a..189679aba703 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -63,6 +63,31 @@
_ASM_ALIGN ; \
_ASM_PTR (entry); \
.popsection
+
+.macro ALIGN_DESTINATION
+ /* check for bad alignment of destination */
+ movl %edi,%ecx
+ andl $7,%ecx
+ jz 102f /* already aligned */
+ subl $8,%ecx
+ negl %ecx
+ subl %ecx,%edx
+100: movb (%rsi),%al
+101: movb %al,(%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz 100b
+102:
+ .section .fixup,"ax"
+103: addl %ecx,%edx /* ecx is zerorest also */
+ jmp copy_user_handle_tail
+ .previous
+
+ _ASM_EXTABLE(100b,103b)
+ _ASM_EXTABLE(101b,103b)
+ .endm
+
#else
# define _ASM_EXTABLE(from,to) \
" .pushsection \"__ex_table\",\"a\"\n" \
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 5e5cd123fdfb..e9168955c42f 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -22,7 +22,7 @@
*
* Atomically reads the value of @v.
*/
-static inline int atomic_read(const atomic_t *v)
+static __always_inline int atomic_read(const atomic_t *v)
{
return ACCESS_ONCE((v)->counter);
}
@@ -34,7 +34,7 @@ static inline int atomic_read(const atomic_t *v)
*
* Atomically sets the value of @v to @i.
*/
-static inline void atomic_set(atomic_t *v, int i)
+static __always_inline void atomic_set(atomic_t *v, int i)
{
v->counter = i;
}
@@ -46,7 +46,7 @@ static inline void atomic_set(atomic_t *v, int i)
*
* Atomically adds @i to @v.
*/
-static inline void atomic_add(int i, atomic_t *v)
+static __always_inline void atomic_add(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "addl %1,%0"
: "+m" (v->counter)
@@ -60,7 +60,7 @@ static inline void atomic_add(int i, atomic_t *v)
*
* Atomically subtracts @i from @v.
*/
-static inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void atomic_sub(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "subl %1,%0"
: "+m" (v->counter)
@@ -76,7 +76,7 @@ static inline void atomic_sub(int i, atomic_t *v)
* true if the result is zero, or false for all
* other cases.
*/
-static inline int atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
}
@@ -87,7 +87,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v)
*
* Atomically increments @v by 1.
*/
-static inline void atomic_inc(atomic_t *v)
+static __always_inline void atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
: "+m" (v->counter));
@@ -99,7 +99,7 @@ static inline void atomic_inc(atomic_t *v)
*
* Atomically decrements @v by 1.
*/
-static inline void atomic_dec(atomic_t *v)
+static __always_inline void atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
: "+m" (v->counter));
@@ -113,7 +113,7 @@ static inline void atomic_dec(atomic_t *v)
* returns true if the result is 0, or false for all other
* cases.
*/
-static inline int atomic_dec_and_test(atomic_t *v)
+static __always_inline int atomic_dec_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
}
@@ -126,7 +126,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
* and returns true if the result is zero, or false for all
* other cases.
*/
-static inline int atomic_inc_and_test(atomic_t *v)
+static __always_inline int atomic_inc_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
}
@@ -140,7 +140,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
-static inline int atomic_add_negative(int i, atomic_t *v)
+static __always_inline int atomic_add_negative(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
}
@@ -152,7 +152,7 @@ static inline int atomic_add_negative(int i, atomic_t *v)
*
* Atomically adds @i to @v and returns @i + @v
*/
-static inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int atomic_add_return(int i, atomic_t *v)
{
return i + xadd(&v->counter, i);
}
@@ -164,7 +164,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
*
* Atomically subtracts @i from @v and returns @v - @i
*/
-static inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int atomic_sub_return(int i, atomic_t *v)
{
return atomic_add_return(-i, v);
}
@@ -172,7 +172,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
#define atomic_inc_return(v) (atomic_add_return(1, v))
#define atomic_dec_return(v) (atomic_sub_return(1, v))
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
{
return cmpxchg(&v->counter, old, new);
}
@@ -191,7 +191,7 @@ static inline int atomic_xchg(atomic_t *v, int new)
* Atomically adds @a to @v, so long as @v was not already @u.
* Returns the old value of @v.
*/
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
{
int c, old;
c = atomic_read(v);
@@ -213,7 +213,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
* Atomically adds 1 to @v
* Returns the new value of @u
*/
-static inline short int atomic_inc_short(short int *v)
+static __always_inline short int atomic_inc_short(short int *v)
{
asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
return *v;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index f8d273e18516..b965f9e03f2a 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long i)
*
* Atomically adds @i to @v.
*/
-static inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void atomic64_add(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "addq %1,%0"
: "=m" (v->counter)
@@ -81,7 +81,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v)
*
* Atomically increments @v by 1.
*/
-static inline void atomic64_inc(atomic64_t *v)
+static __always_inline void atomic64_inc(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "incq %0"
: "=m" (v->counter)
@@ -94,7 +94,7 @@ static inline void atomic64_inc(atomic64_t *v)
*
* Atomically decrements @v by 1.
*/
-static inline void atomic64_dec(atomic64_t *v)
+static __always_inline void atomic64_dec(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "decq %0"
: "=m" (v->counter)
@@ -148,7 +148,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v)
*
* Atomically adds @i to @v and returns @i + @v
*/
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long atomic64_add_return(long i, atomic64_t *v)
{
return i + xadd(&v->counter, i);
}
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 959e45b81fe2..e51a8f803f55 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -35,12 +35,12 @@
#define smp_mb() mb()
#define smp_rmb() dma_rmb()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* !SMP */
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
#endif /* SMP */
#define read_barrier_depends() do { } while (0)
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 47c8e32f621a..b6f7457d12e4 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -8,7 +8,7 @@
/*
* The set_memory_* API can be used to change various attributes of a virtual
* address range. The attributes include:
- * Cachability : UnCached, WriteCombining, WriteBack
+ * Cachability : UnCached, WriteCombining, WriteThrough, WriteBack
* Executability : eXeutable, NoteXecutable
* Read/Write : ReadOnly, ReadWrite
* Presence : NotPresent
@@ -35,9 +35,11 @@
int _set_memory_uc(unsigned long addr, int numpages);
int _set_memory_wc(unsigned long addr, int numpages);
+int _set_memory_wt(unsigned long addr, int numpages);
int _set_memory_wb(unsigned long addr, int numpages);
int set_memory_uc(unsigned long addr, int numpages);
int set_memory_wc(unsigned long addr, int numpages);
+int set_memory_wt(unsigned long addr, int numpages);
int set_memory_wb(unsigned long addr, int numpages);
int set_memory_x(unsigned long addr, int numpages);
int set_memory_nx(unsigned long addr, int numpages);
@@ -48,10 +50,12 @@ int set_memory_4k(unsigned long addr, int numpages);
int set_memory_array_uc(unsigned long *addr, int addrinarray);
int set_memory_array_wc(unsigned long *addr, int addrinarray);
+int set_memory_array_wt(unsigned long *addr, int addrinarray);
int set_memory_array_wb(unsigned long *addr, int addrinarray);
int set_pages_array_uc(struct page **pages, int addrinarray);
int set_pages_array_wc(struct page **pages, int addrinarray);
+int set_pages_array_wt(struct page **pages, int addrinarray);
int set_pages_array_wb(struct page **pages, int addrinarray);
/*
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 99c105d78b7e..ad19841eddfe 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -4,8 +4,6 @@
#include <linux/compiler.h>
#include <asm/alternative.h> /* Provides LOCK_PREFIX */
-#define __HAVE_ARCH_CMPXCHG 1
-
/*
* Non-existant functions to indicate usage errors at link time
* (or compile-time if the compiler implements __compiletime_error().
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
index 1eef55596e82..03bb1065c335 100644
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -7,7 +7,7 @@
#include <linux/kernel.h>
#include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <crypto/b128ops.h>
typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 808dae63eeea..1f5b7287d1ad 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -127,50 +127,14 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
#define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL)
-static inline void *
+void *
dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, struct dma_attrs *attrs)
-{
- struct dma_map_ops *ops = get_dma_ops(dev);
- void *memory;
-
- gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
- if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
- return memory;
-
- if (!dev)
- dev = &x86_dma_fallback_dev;
-
- if (!is_device_dma_capable(dev))
- return NULL;
-
- if (!ops->alloc)
- return NULL;
-
- memory = ops->alloc(dev, size, dma_handle,
- dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
- debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
-
- return memory;
-}
+ gfp_t gfp, struct dma_attrs *attrs);
#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-static inline void dma_free_attrs(struct device *dev, size_t size,
- void *vaddr, dma_addr_t bus,
- struct dma_attrs *attrs)
-{
- struct dma_map_ops *ops = get_dma_ops(dev);
-
- WARN_ON(irqs_disabled()); /* for portability */
-
- if (dma_release_from_coherent(dev, get_order(size), vaddr))
- return;
-
- debug_dma_free_coherent(dev, size, vaddr, bus);
- if (ops->free)
- ops->free(dev, size, vaddr, bus, attrs);
-}
+void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t bus,
+ struct dma_attrs *attrs);
#endif
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
deleted file mode 100644
index de1cdaf4d743..000000000000
--- a/arch/x86/include/asm/dwarf2.h
+++ /dev/null
@@ -1,170 +0,0 @@
-#ifndef _ASM_X86_DWARF2_H
-#define _ASM_X86_DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
- * Macros for dwarf2 CFI unwind table entries.
- * See "as.info" for details on these pseudo ops. Unfortunately
- * they are only supported in very new binutils, so define them
- * away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-#define CFI_ESCAPE .cfi_escape
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
- /*
- * Emit CFI data in .debug_frame sections, not .eh_frame sections.
- * The latter we currently just discard since we don't do DWARF
- * unwinding at runtime. So only the offline DWARF information is
- * useful to anyone. Note we should not use this directive if this
- * file is used in the vDSO assembly, or if vmlinux.lds.S gets
- * changed so it doesn't discard .eh_frame.
- */
- .cfi_sections .debug_frame
-#endif
-
-#else
-
-/*
- * Due to the structure of pre-exisiting code, don't use assembler line
- * comment character # to ignore the arguments. Instead, use a dummy macro.
- */
-.macro cfi_ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC cfi_ignore
-#define CFI_ENDPROC cfi_ignore
-#define CFI_DEF_CFA cfi_ignore
-#define CFI_DEF_CFA_REGISTER cfi_ignore
-#define CFI_DEF_CFA_OFFSET cfi_ignore
-#define CFI_ADJUST_CFA_OFFSET cfi_ignore
-#define CFI_OFFSET cfi_ignore
-#define CFI_REL_OFFSET cfi_ignore
-#define CFI_REGISTER cfi_ignore
-#define CFI_RESTORE cfi_ignore
-#define CFI_REMEMBER_STATE cfi_ignore
-#define CFI_RESTORE_STATE cfi_ignore
-#define CFI_UNDEFINED cfi_ignore
-#define CFI_ESCAPE cfi_ignore
-#define CFI_SIGNAL_FRAME cfi_ignore
-
-#endif
-
-/*
- * An attempt to make CFI annotations more or less
- * correct and shorter. It is implied that you know
- * what you're doing if you use them.
- */
-#ifdef __ASSEMBLY__
-#ifdef CONFIG_X86_64
- .macro pushq_cfi reg
- pushq \reg
- CFI_ADJUST_CFA_OFFSET 8
- .endm
-
- .macro pushq_cfi_reg reg
- pushq %\reg
- CFI_ADJUST_CFA_OFFSET 8
- CFI_REL_OFFSET \reg, 0
- .endm
-
- .macro popq_cfi reg
- popq \reg
- CFI_ADJUST_CFA_OFFSET -8
- .endm
-
- .macro popq_cfi_reg reg
- popq %\reg
- CFI_ADJUST_CFA_OFFSET -8
- CFI_RESTORE \reg
- .endm
-
- .macro pushfq_cfi
- pushfq
- CFI_ADJUST_CFA_OFFSET 8
- .endm
-
- .macro popfq_cfi
- popfq
- CFI_ADJUST_CFA_OFFSET -8
- .endm
-
- .macro movq_cfi reg offset=0
- movq %\reg, \offset(%rsp)
- CFI_REL_OFFSET \reg, \offset
- .endm
-
- .macro movq_cfi_restore offset reg
- movq \offset(%rsp), %\reg
- CFI_RESTORE \reg
- .endm
-#else /*!CONFIG_X86_64*/
- .macro pushl_cfi reg
- pushl \reg
- CFI_ADJUST_CFA_OFFSET 4
- .endm
-
- .macro pushl_cfi_reg reg
- pushl %\reg
- CFI_ADJUST_CFA_OFFSET 4
- CFI_REL_OFFSET \reg, 0
- .endm
-
- .macro popl_cfi reg
- popl \reg
- CFI_ADJUST_CFA_OFFSET -4
- .endm
-
- .macro popl_cfi_reg reg
- popl %\reg
- CFI_ADJUST_CFA_OFFSET -4
- CFI_RESTORE \reg
- .endm
-
- .macro pushfl_cfi
- pushfl
- CFI_ADJUST_CFA_OFFSET 4
- .endm
-
- .macro popfl_cfi
- popfl
- CFI_ADJUST_CFA_OFFSET -4
- .endm
-
- .macro movl_cfi reg offset=0
- movl %\reg, \offset(%esp)
- CFI_REL_OFFSET \reg, \offset
- .endm
-
- .macro movl_cfi_restore offset reg
- movl \offset(%esp), %\reg
- CFI_RESTORE \reg
- .endm
-#endif /*!CONFIG_X86_64*/
-#endif /*__ASSEMBLY__*/
-
-#endif /* _ASM_X86_DWARF2_H */
diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h
index e9b57ecc70c5..cf8fdf83b231 100644
--- a/arch/x86/include/asm/edac.h
+++ b/arch/x86/include/asm/edac.h
@@ -3,7 +3,7 @@
/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-static inline void atomic_scrub(void *va, u32 size)
+static inline void edac_atomic_scrub(void *va, u32 size)
{
u32 i, *virt_addr = va;
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3738b138b843..155162ea0e00 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -1,7 +1,7 @@
#ifndef _ASM_X86_EFI_H
#define _ASM_X86_EFI_H
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/pgtable.h>
/*
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index dc5fa661465f..df002992d8fd 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -23,6 +23,8 @@ BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
#ifdef CONFIG_HAVE_KVM
BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
smp_kvm_posted_intr_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
+ smp_kvm_posted_intr_wakeup_ipi)
#endif
/*
@@ -50,4 +52,7 @@ BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
#endif
+#ifdef CONFIG_X86_MCE_AMD
+BUILD_INTERRUPT(deferred_error_interrupt, DEFERRED_ERROR_VECTOR)
+#endif
#endif
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
deleted file mode 100644
index da5e96756570..000000000000
--- a/arch/x86/include/asm/fpu-internal.h
+++ /dev/null
@@ -1,626 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _FPU_INTERNAL_H
-#define _FPU_INTERNAL_H
-
-#include <linux/kernel_stat.h>
-#include <linux/regset.h>
-#include <linux/compat.h>
-#include <linux/slab.h>
-#include <asm/asm.h>
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/uaccess.h>
-#include <asm/xsave.h>
-#include <asm/smap.h>
-
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-struct ksignal;
-int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
- compat_sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct ksignal *ksig,
- compat_sigset_t *set, struct pt_regs *regs);
-#else
-# define user_i387_ia32_struct user_i387_struct
-# define user32_fxsr_struct user_fxsr_struct
-# define ia32_setup_frame __setup_frame
-# define ia32_setup_rt_frame __setup_rt_frame
-#endif
-
-extern unsigned int mxcsr_feature_mask;
-extern void fpu_init(void);
-extern void eager_fpu_init(void);
-
-DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
-
-extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
- struct task_struct *tsk);
-extern void convert_to_fxsr(struct task_struct *tsk,
- const struct user_i387_ia32_struct *env);
-
-extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
- xstateregs_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
- xstateregs_set;
-
-/*
- * xstateregs_active == fpregs_active. Please refer to the comment
- * at the definition of fpregs_active.
- */
-#define xstateregs_active fpregs_active
-
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-/*
- * Must be run with preemption disabled: this clears the fpu_owner_task,
- * on this CPU.
- *
- * This will disable any lazy FPU state restore of the current FPU state,
- * but if the current thread owns the FPU, it will still be saved by.
- */
-static inline void __cpu_disable_lazy_restore(unsigned int cpu)
-{
- per_cpu(fpu_owner_task, cpu) = NULL;
-}
-
-/*
- * Used to indicate that the FPU state in memory is newer than the FPU
- * state in registers, and the FPU state should be reloaded next time the
- * task is run. Only safe on the current task, or non-running tasks.
- */
-static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk)
-{
- tsk->thread.fpu.last_cpu = ~0;
-}
-
-static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
-{
- return new == this_cpu_read_stable(fpu_owner_task) &&
- cpu == new->thread.fpu.last_cpu;
-}
-
-static inline int is_ia32_compat_frame(void)
-{
- return config_enabled(CONFIG_IA32_EMULATION) &&
- test_thread_flag(TIF_IA32);
-}
-
-static inline int is_ia32_frame(void)
-{
- return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
-}
-
-static inline int is_x32_frame(void)
-{
- return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
-}
-
-#define X87_FSW_ES (1 << 7) /* Exception Summary */
-
-static __always_inline __pure bool use_eager_fpu(void)
-{
- return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
-}
-
-static __always_inline __pure bool use_xsaveopt(void)
-{
- return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
-}
-
-static __always_inline __pure bool use_xsave(void)
-{
- return static_cpu_has_safe(X86_FEATURE_XSAVE);
-}
-
-static __always_inline __pure bool use_fxsr(void)
-{
- return static_cpu_has_safe(X86_FEATURE_FXSR);
-}
-
-static inline void fx_finit(struct i387_fxsave_struct *fx)
-{
- fx->cwd = 0x37f;
- fx->mxcsr = MXCSR_DEFAULT;
-}
-
-extern void __sanitize_i387_state(struct task_struct *);
-
-static inline void sanitize_i387_state(struct task_struct *tsk)
-{
- if (!use_xsaveopt())
- return;
- __sanitize_i387_state(tsk);
-}
-
-#define user_insn(insn, output, input...) \
-({ \
- int err; \
- asm volatile(ASM_STAC "\n" \
- "1:" #insn "\n\t" \
- "2: " ASM_CLAC "\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err), output \
- : "0"(0), input); \
- err; \
-})
-
-#define check_insn(insn, output, input...) \
-({ \
- int err; \
- asm volatile("1:" #insn "\n\t" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err), output \
- : "0"(0), input); \
- err; \
-})
-
-static inline int fsave_user(struct i387_fsave_struct __user *fx)
-{
- return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
-}
-
-static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
-{
- if (config_enabled(CONFIG_X86_32))
- return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
- else if (config_enabled(CONFIG_AS_FXSAVEQ))
- return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
-
- /* See comment in fpu_fxsave() below. */
- return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
-}
-
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
- if (config_enabled(CONFIG_X86_32))
- return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
- else if (config_enabled(CONFIG_AS_FXSAVEQ))
- return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
- /* See comment in fpu_fxsave() below. */
- return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
- "m" (*fx));
-}
-
-static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
-{
- if (config_enabled(CONFIG_X86_32))
- return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
- else if (config_enabled(CONFIG_AS_FXSAVEQ))
- return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
- /* See comment in fpu_fxsave() below. */
- return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
- "m" (*fx));
-}
-
-static inline int frstor_checking(struct i387_fsave_struct *fx)
-{
- return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int frstor_user(struct i387_fsave_struct __user *fx)
-{
- return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
- if (config_enabled(CONFIG_X86_32))
- asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
- else if (config_enabled(CONFIG_AS_FXSAVEQ))
- asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave));
- else {
- /* Using "rex64; fxsave %0" is broken because, if the memory
- * operand uses any extended registers for addressing, a second
- * REX prefix will be generated (to the assembler, rex64
- * followed by semicolon is a separate instruction), and hence
- * the 64-bitness is lost.
- *
- * Using "fxsaveq %0" would be the ideal choice, but is only
- * supported starting with gas 2.16.
- *
- * Using, as a workaround, the properly prefixed form below
- * isn't accepted by any binutils version so far released,
- * complaining that the same type of prefix is used twice if
- * an extended register is needed for addressing (fix submitted
- * to mainline 2005-11-21).
- *
- * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
- *
- * This, however, we can work around by forcing the compiler to
- * select an addressing mode that doesn't require extended
- * registers.
- */
- asm volatile( "rex64/fxsave (%[fx])"
- : "=m" (fpu->state->fxsave)
- : [fx] "R" (&fpu->state->fxsave));
- }
-}
-
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact.
- */
-static inline int fpu_save_init(struct fpu *fpu)
-{
- if (use_xsave()) {
- fpu_xsave(fpu);
-
- /*
- * xsave header may indicate the init state of the FP.
- */
- if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
- return 1;
- } else if (use_fxsr()) {
- fpu_fxsave(fpu);
- } else {
- asm volatile("fnsave %[fx]; fwait"
- : [fx] "=m" (fpu->state->fsave));
- return 0;
- }
-
- /*
- * If exceptions are pending, we need to clear them so
- * that we don't randomly get exceptions later.
- *
- * FIXME! Is this perhaps only true for the old-style
- * irq13 case? Maybe we could leave the x87 state
- * intact otherwise?
- */
- if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
- asm volatile("fnclex");
- return 0;
- }
- return 1;
-}
-
-static inline int __save_init_fpu(struct task_struct *tsk)
-{
- return fpu_save_init(&tsk->thread.fpu);
-}
-
-static inline int fpu_restore_checking(struct fpu *fpu)
-{
- if (use_xsave())
- return fpu_xrstor_checking(&fpu->state->xsave);
- else if (use_fxsr())
- return fxrstor_checking(&fpu->state->fxsave);
- else
- return frstor_checking(&fpu->state->fsave);
-}
-
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
- /*
- * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
- * pending. Clear the x87 state here by setting it to fixed values.
- * "m" is a random variable that should be in L1.
- */
- if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
- asm volatile(
- "fnclex\n\t"
- "emms\n\t"
- "fildl %P[addr]" /* set F?P to defined value */
- : : [addr] "m" (tsk->thread.fpu.has_fpu));
- }
-
- return fpu_restore_checking(&tsk->thread.fpu);
-}
-
-/*
- * Software FPU state helpers. Careful: these need to
- * be preemption protection *and* they need to be
- * properly paired with the CR0.TS changes!
- */
-static inline int __thread_has_fpu(struct task_struct *tsk)
-{
- return tsk->thread.fpu.has_fpu;
-}
-
-/* Must be paired with an 'stts' after! */
-static inline void __thread_clear_has_fpu(struct task_struct *tsk)
-{
- tsk->thread.fpu.has_fpu = 0;
- this_cpu_write(fpu_owner_task, NULL);
-}
-
-/* Must be paired with a 'clts' before! */
-static inline void __thread_set_has_fpu(struct task_struct *tsk)
-{
- tsk->thread.fpu.has_fpu = 1;
- this_cpu_write(fpu_owner_task, tsk);
-}
-
-/*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
- * These generally need preemption protection to work,
- * do try to avoid using these on their own.
- */
-static inline void __thread_fpu_end(struct task_struct *tsk)
-{
- __thread_clear_has_fpu(tsk);
- if (!use_eager_fpu())
- stts();
-}
-
-static inline void __thread_fpu_begin(struct task_struct *tsk)
-{
- if (!use_eager_fpu())
- clts();
- __thread_set_has_fpu(tsk);
-}
-
-static inline void drop_fpu(struct task_struct *tsk)
-{
- /*
- * Forget coprocessor state..
- */
- preempt_disable();
- tsk->thread.fpu_counter = 0;
-
- if (__thread_has_fpu(tsk)) {
- /* Ignore delayed exceptions from user space */
- asm volatile("1: fwait\n"
- "2:\n"
- _ASM_EXTABLE(1b, 2b));
- __thread_fpu_end(tsk);
- }
-
- clear_stopped_child_used_math(tsk);
- preempt_enable();
-}
-
-static inline void restore_init_xstate(void)
-{
- if (use_xsave())
- xrstor_state(init_xstate_buf, -1);
- else
- fxrstor_checking(&init_xstate_buf->i387);
-}
-
-/*
- * Reset the FPU state in the eager case and drop it in the lazy case (later use
- * will reinit it).
- */
-static inline void fpu_reset_state(struct task_struct *tsk)
-{
- if (!use_eager_fpu())
- drop_fpu(tsk);
- else
- restore_init_xstate();
-}
-
-/*
- * FPU state switching for scheduling.
- *
- * This is a two-stage process:
- *
- * - switch_fpu_prepare() saves the old state and
- * sets the new state of the CR0.TS bit. This is
- * done within the context of the old process.
- *
- * - switch_fpu_finish() restores the new state as
- * necessary.
- */
-typedef struct { int preload; } fpu_switch_t;
-
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
-{
- fpu_switch_t fpu;
-
- /*
- * If the task has used the math, pre-load the FPU on xsave processors
- * or if the past 5 consecutive context-switches used math.
- */
- fpu.preload = tsk_used_math(new) &&
- (use_eager_fpu() || new->thread.fpu_counter > 5);
-
- if (__thread_has_fpu(old)) {
- if (!__save_init_fpu(old))
- task_disable_lazy_fpu_restore(old);
- else
- old->thread.fpu.last_cpu = cpu;
-
- /* But leave fpu_owner_task! */
- old->thread.fpu.has_fpu = 0;
-
- /* Don't change CR0.TS if we just switch! */
- if (fpu.preload) {
- new->thread.fpu_counter++;
- __thread_set_has_fpu(new);
- prefetch(new->thread.fpu.state);
- } else if (!use_eager_fpu())
- stts();
- } else {
- old->thread.fpu_counter = 0;
- task_disable_lazy_fpu_restore(old);
- if (fpu.preload) {
- new->thread.fpu_counter++;
- if (fpu_lazy_restore(new, cpu))
- fpu.preload = 0;
- else
- prefetch(new->thread.fpu.state);
- __thread_fpu_begin(new);
- }
- }
- return fpu;
-}
-
-/*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
- */
-static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
-{
- if (fpu.preload) {
- if (unlikely(restore_fpu_checking(new)))
- fpu_reset_state(new);
- }
-}
-
-/*
- * Signal frame handlers...
- */
-extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
-extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
-
-static inline int xstate_sigframe_size(void)
-{
- return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
-}
-
-static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
-{
- void __user *buf_fx = buf;
- int size = xstate_sigframe_size();
-
- if (ia32_frame && use_fxsr()) {
- buf_fx = buf + sizeof(struct i387_fsave_struct);
- size += sizeof(struct i387_fsave_struct);
- }
-
- return __restore_xstate_sig(buf, buf_fx, size);
-}
-
-/*
- * Needs to be preemption-safe.
- *
- * NOTE! user_fpu_begin() must be used only immediately before restoring
- * the save state. It does not do any saving/restoring on its own. In
- * lazy FPU mode, it is just an optimization to avoid a #NM exception,
- * the task can lose the FPU right after preempt_enable().
- */
-static inline void user_fpu_begin(void)
-{
- preempt_disable();
- if (!user_has_fpu())
- __thread_fpu_begin(current);
- preempt_enable();
-}
-
-static inline void __save_fpu(struct task_struct *tsk)
-{
- if (use_xsave()) {
- if (unlikely(system_state == SYSTEM_BOOTING))
- xsave_state_booting(&tsk->thread.fpu.state->xsave, -1);
- else
- xsave_state(&tsk->thread.fpu.state->xsave, -1);
- } else
- fpu_fxsave(&tsk->thread.fpu);
-}
-
-/*
- * i387 state interaction
- */
-static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
-{
- if (cpu_has_fxsr) {
- return tsk->thread.fpu.state->fxsave.cwd;
- } else {
- return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
- }
-}
-
-static inline unsigned short get_fpu_swd(struct task_struct *tsk)
-{
- if (cpu_has_fxsr) {
- return tsk->thread.fpu.state->fxsave.swd;
- } else {
- return (unsigned short)tsk->thread.fpu.state->fsave.swd;
- }
-}
-
-static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
-{
- if (cpu_has_xmm) {
- return tsk->thread.fpu.state->fxsave.mxcsr;
- } else {
- return MXCSR_DEFAULT;
- }
-}
-
-static bool fpu_allocated(struct fpu *fpu)
-{
- return fpu->state != NULL;
-}
-
-static inline int fpu_alloc(struct fpu *fpu)
-{
- if (fpu_allocated(fpu))
- return 0;
- fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
- if (!fpu->state)
- return -ENOMEM;
- WARN_ON((unsigned long)fpu->state & 15);
- return 0;
-}
-
-static inline void fpu_free(struct fpu *fpu)
-{
- if (fpu->state) {
- kmem_cache_free(task_xstate_cachep, fpu->state);
- fpu->state = NULL;
- }
-}
-
-static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
-{
- if (use_eager_fpu()) {
- memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
- __save_fpu(dst);
- } else {
- struct fpu *dfpu = &dst->thread.fpu;
- struct fpu *sfpu = &src->thread.fpu;
-
- unlazy_fpu(src);
- memcpy(dfpu->state, sfpu->state, xstate_size);
- }
-}
-
-static inline unsigned long
-alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
- unsigned long *size)
-{
- unsigned long frame_size = xstate_sigframe_size();
-
- *buf_fx = sp = round_down(sp - frame_size, 64);
- if (ia32_frame && use_fxsr()) {
- frame_size += sizeof(struct i387_fsave_struct);
- sp -= sizeof(struct i387_fsave_struct);
- }
-
- *size = frame_size;
- return sp;
-}
-
-#endif
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
new file mode 100644
index 000000000000..1429a7c736db
--- /dev/null
+++ b/arch/x86/include/asm/fpu/api.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_API_H
+#define _ASM_X86_FPU_API_H
+
+/*
+ * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
+ * and they don't touch the preempt state on their own.
+ * If you enable preemption after __kernel_fpu_begin(), preempt notifier
+ * should call the __kernel_fpu_end() to prevent the kernel/user FPU
+ * state from getting corrupted. KVM for example uses this model.
+ *
+ * All other cases use kernel_fpu_begin/end() which disable preemption
+ * during kernel FPU usage.
+ */
+extern void __kernel_fpu_begin(void);
+extern void __kernel_fpu_end(void);
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
+extern bool irq_fpu_usable(void);
+
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context as well. To prevent these kernel instructions
+ * in interrupt context interacting wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+extern int irq_ts_save(void);
+extern void irq_ts_restore(int TS_state);
+
+/*
+ * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
+ *
+ * If 'feature_name' is set then put a human-readable description of
+ * the feature there as well - this can be used to print error (or success)
+ * messages.
+ */
+extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
+
+#endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
new file mode 100644
index 000000000000..3c3550c3a4a3
--- /dev/null
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -0,0 +1,694 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_INTERNAL_H
+#define _ASM_X86_FPU_INTERNAL_H
+
+#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/user.h>
+#include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
+
+/*
+ * High level FPU state handling functions:
+ */
+extern void fpu__activate_curr(struct fpu *fpu);
+extern void fpu__activate_fpstate_read(struct fpu *fpu);
+extern void fpu__activate_fpstate_write(struct fpu *fpu);
+extern void fpu__save(struct fpu *fpu);
+extern void fpu__restore(struct fpu *fpu);
+extern int fpu__restore_sig(void __user *buf, int ia32_frame);
+extern void fpu__drop(struct fpu *fpu);
+extern int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
+extern void fpu__clear(struct fpu *fpu);
+extern int fpu__exception_code(struct fpu *fpu, int trap_nr);
+extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
+
+/*
+ * Boot time FPU initialization functions:
+ */
+extern void fpu__init_cpu(void);
+extern void fpu__init_system_xstate(void);
+extern void fpu__init_cpu_xstate(void);
+extern void fpu__init_system(struct cpuinfo_x86 *c);
+extern void fpu__init_check_bugs(void);
+extern void fpu__resume_cpu(void);
+
+/*
+ * Debugging facility:
+ */
+#ifdef CONFIG_X86_DEBUG_FPU
+# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
+#else
+# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+#endif
+
+/*
+ * FPU related CPU feature flag helper routines:
+ */
+static __always_inline __pure bool use_eager_fpu(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
+}
+
+static __always_inline __pure bool use_xsaveopt(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_FXSR);
+}
+
+/*
+ * fpstate handling functions:
+ */
+
+extern union fpregs_state init_fpstate;
+
+extern void fpstate_init(union fpregs_state *state);
+#ifdef CONFIG_MATH_EMULATION
+extern void fpstate_init_soft(struct swregs_state *soft);
+#else
+static inline void fpstate_init_soft(struct swregs_state *soft) {}
+#endif
+static inline void fpstate_init_fxstate(struct fxregs_state *fx)
+{
+ fx->cwd = 0x37f;
+ fx->mxcsr = MXCSR_DEFAULT;
+}
+extern void fpstate_sanitize_xstate(struct fpu *fpu);
+
+#define user_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile(ASM_STAC "\n" \
+ "1:" #insn "\n\t" \
+ "2: " ASM_CLAC "\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+#define check_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+static inline int copy_fregs_to_user(struct fregs_state __user *fx)
+{
+ return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
+{
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+ /* See comment in copy_fxregs_to_kernel() below. */
+ return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
+}
+
+static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
+{
+ int err;
+
+ if (config_enabled(CONFIG_X86_32)) {
+ err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ } else {
+ if (config_enabled(CONFIG_AS_FXSAVEQ)) {
+ err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+ } else {
+ /* See comment in copy_fxregs_to_kernel() below. */
+ err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+ }
+ }
+ /* Copying from a kernel buffer to FPU registers should never fail: */
+ WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
+{
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+ /* See comment in copy_fxregs_to_kernel() below. */
+ return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+ "m" (*fx));
+}
+
+static inline void copy_kernel_to_fregs(struct fregs_state *fx)
+{
+ int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+ WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fregs(struct fregs_state __user *fx)
+{
+ return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void copy_fxregs_to_kernel(struct fpu *fpu)
+{
+ if (config_enabled(CONFIG_X86_32))
+ asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
+ else {
+ /* Using "rex64; fxsave %0" is broken because, if the memory
+ * operand uses any extended registers for addressing, a second
+ * REX prefix will be generated (to the assembler, rex64
+ * followed by semicolon is a separate instruction), and hence
+ * the 64-bitness is lost.
+ *
+ * Using "fxsaveq %0" would be the ideal choice, but is only
+ * supported starting with gas 2.16.
+ *
+ * Using, as a workaround, the properly prefixed form below
+ * isn't accepted by any binutils version so far released,
+ * complaining that the same type of prefix is used twice if
+ * an extended register is needed for addressing (fix submitted
+ * to mainline 2005-11-21).
+ *
+ * asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave));
+ *
+ * This, however, we can work around by forcing the compiler to
+ * select an addressing mode that doesn't require extended
+ * registers.
+ */
+ asm volatile( "rex64/fxsave (%[fx])"
+ : "=m" (fpu->state.fxsave)
+ : [fx] "R" (&fpu->state.fxsave));
+ }
+}
+
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+/* xstate instruction fault handler: */
+#define xstate_fault(__err) \
+ \
+ ".section .fixup,\"ax\"\n" \
+ \
+ "3: movl $-2,%[_err]\n" \
+ " jmp 2b\n" \
+ \
+ ".previous\n" \
+ \
+ _ASM_EXTABLE(1b, 3b) \
+ : [_err] "=r" (__err)
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
+{
+ u64 mask = -1;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ WARN_ON(system_state != SYSTEM_BOOTING);
+
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ asm volatile("1:"XSAVES"\n\t"
+ "2:\n\t"
+ xstate_fault(err)
+ : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory");
+ else
+ asm volatile("1:"XSAVE"\n\t"
+ "2:\n\t"
+ xstate_fault(err)
+ : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory");
+
+ /* We should never fault when copying to a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
+{
+ u64 mask = -1;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ WARN_ON(system_state != SYSTEM_BOOTING);
+
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ asm volatile("1:"XRSTORS"\n\t"
+ "2:\n\t"
+ xstate_fault(err)
+ : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory");
+ else
+ asm volatile("1:"XRSTOR"\n\t"
+ "2:\n\t"
+ xstate_fault(err)
+ : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory");
+
+ /* We should never fault when copying from a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * Save processor xstate to xsave area.
+ */
+static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
+{
+ u64 mask = -1;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ WARN_ON(!alternatives_patched);
+
+ /*
+ * If xsaves is enabled, xsaves replaces xsaveopt because
+ * it supports compact format and supervisor states in addition to
+ * modified optimization in xsaveopt.
+ *
+ * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
+ * because xsaveopt supports modified optimization which is not
+ * supported by xsave.
+ *
+ * If none of xsaves and xsaveopt is enabled, use xsave.
+ */
+ alternative_input_2(
+ "1:"XSAVE,
+ XSAVEOPT,
+ X86_FEATURE_XSAVEOPT,
+ XSAVES,
+ X86_FEATURE_XSAVES,
+ [xstate] "D" (xstate), "a" (lmask), "d" (hmask) :
+ "memory");
+ asm volatile("2:\n\t"
+ xstate_fault(err)
+ : "0" (err)
+ : "memory");
+
+ /* We should never fault when copying to a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * Restore processor xstate from xsave area.
+ */
+static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
+{
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ /*
+ * Use xrstors to restore context if it is enabled. xrstors supports
+ * compacted format of xsave area which is not supported by xrstor.
+ */
+ alternative_input(
+ "1: " XRSTOR,
+ XRSTORS,
+ X86_FEATURE_XSAVES,
+ "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask)
+ : "memory");
+
+ asm volatile("2:\n"
+ xstate_fault(err)
+ : "0" (err)
+ : "memory");
+
+ /* We should never fault when copying from a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for
+ * backward compatibility for old applications which don't understand
+ * compacted format of xsave area.
+ */
+static inline int copy_xregs_to_user(struct xregs_state __user *buf)
+{
+ int err;
+
+ /*
+ * Clear the xsave header first, so that reserved fields are
+ * initialized to zero.
+ */
+ err = __clear_user(&buf->header, sizeof(buf->header));
+ if (unlikely(err))
+ return -EFAULT;
+
+ __asm__ __volatile__(ASM_STAC "\n"
+ "1:"XSAVE"\n"
+ "2: " ASM_CLAC "\n"
+ xstate_fault(err)
+ : "D" (buf), "a" (-1), "d" (-1), "0" (err)
+ : "memory");
+ return err;
+}
+
+/*
+ * Restore xstate from user space xsave area.
+ */
+static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
+{
+ struct xregs_state *xstate = ((__force struct xregs_state *)buf);
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ __asm__ __volatile__(ASM_STAC "\n"
+ "1:"XRSTOR"\n"
+ "2: " ASM_CLAC "\n"
+ xstate_fault(err)
+ : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory"); /* memory required? */
+ return err;
+}
+
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+ if (likely(use_xsave())) {
+ copy_xregs_to_kernel(&fpu->state.xsave);
+ return 1;
+ }
+
+ if (likely(use_fxsr())) {
+ copy_fxregs_to_kernel(fpu);
+ return 1;
+ }
+
+ /*
+ * Legacy FPU register saving, FNSAVE always clears FPU registers,
+ * so we have to mark them inactive:
+ */
+ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+ return 0;
+}
+
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+ if (use_xsave()) {
+ copy_kernel_to_xregs(&fpstate->xsave, -1);
+ } else {
+ if (use_fxsr())
+ copy_kernel_to_fxregs(&fpstate->fxsave);
+ else
+ copy_kernel_to_fregs(&fpstate->fsave);
+ }
+}
+
+static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+ /*
+ * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
+ * pending. Clear the x87 state here by setting it to fixed values.
+ * "m" is a random variable that should be in L1.
+ */
+ if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
+ asm volatile(
+ "fnclex\n\t"
+ "emms\n\t"
+ "fildl %P[addr]" /* set F?P to defined value */
+ : : [addr] "m" (fpstate));
+ }
+
+ __copy_kernel_to_fpregs(fpstate);
+}
+
+extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+
+/*
+ * FPU context switch related helper methods:
+ */
+
+DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/*
+ * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx,
+ * on this CPU.
+ *
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
+ */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+ per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
+}
+
+static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
+{
+ return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+}
+
+
+/*
+ * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
+ * idiom, which is then paired with the sw-flag (fpregs_active) later on:
+ */
+
+static inline void __fpregs_activate_hw(void)
+{
+ if (!use_eager_fpu())
+ clts();
+}
+
+static inline void __fpregs_deactivate_hw(void)
+{
+ if (!use_eager_fpu())
+ stts();
+}
+
+/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
+static inline void __fpregs_deactivate(struct fpu *fpu)
+{
+ WARN_ON_FPU(!fpu->fpregs_active);
+
+ fpu->fpregs_active = 0;
+ this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+}
+
+/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
+static inline void __fpregs_activate(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu->fpregs_active);
+
+ fpu->fpregs_active = 1;
+ this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+}
+
+/*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ */
+static inline int fpregs_active(void)
+{
+ return current->thread.fpu.fpregs_active;
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void fpregs_activate(struct fpu *fpu)
+{
+ __fpregs_activate_hw();
+ __fpregs_activate(fpu);
+}
+
+static inline void fpregs_deactivate(struct fpu *fpu)
+{
+ __fpregs_deactivate(fpu);
+ __fpregs_deactivate_hw();
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ * - switch_fpu_prepare() saves the old state and
+ * sets the new state of the CR0.TS bit. This is
+ * done within the context of the old process.
+ *
+ * - switch_fpu_finish() restores the new state as
+ * necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+static inline fpu_switch_t
+switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
+{
+ fpu_switch_t fpu;
+
+ /*
+ * If the task has used the math, pre-load the FPU on xsave processors
+ * or if the past 5 consecutive context-switches used math.
+ */
+ fpu.preload = new_fpu->fpstate_active &&
+ (use_eager_fpu() || new_fpu->counter > 5);
+
+ if (old_fpu->fpregs_active) {
+ if (!copy_fpregs_to_fpstate(old_fpu))
+ old_fpu->last_cpu = -1;
+ else
+ old_fpu->last_cpu = cpu;
+
+ /* But leave fpu_fpregs_owner_ctx! */
+ old_fpu->fpregs_active = 0;
+
+ /* Don't change CR0.TS if we just switch! */
+ if (fpu.preload) {
+ new_fpu->counter++;
+ __fpregs_activate(new_fpu);
+ prefetch(&new_fpu->state);
+ } else {
+ __fpregs_deactivate_hw();
+ }
+ } else {
+ old_fpu->counter = 0;
+ old_fpu->last_cpu = -1;
+ if (fpu.preload) {
+ new_fpu->counter++;
+ if (fpu_want_lazy_restore(new_fpu, cpu))
+ fpu.preload = 0;
+ else
+ prefetch(&new_fpu->state);
+ fpregs_activate(new_fpu);
+ }
+ }
+ return fpu;
+}
+
+/*
+ * Misc helper functions:
+ */
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch)
+{
+ if (fpu_switch.preload)
+ copy_kernel_to_fpregs(&new_fpu->state);
+}
+
+/*
+ * Needs to be preemption-safe.
+ *
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * the save state. It does not do any saving/restoring on its own. In
+ * lazy FPU mode, it is just an optimization to avoid a #NM exception,
+ * the task can lose the FPU right after preempt_enable().
+ */
+static inline void user_fpu_begin(void)
+{
+ struct fpu *fpu = &current->thread.fpu;
+
+ preempt_disable();
+ if (!fpregs_active())
+ fpregs_activate(fpu);
+ preempt_enable();
+}
+
+/*
+ * MXCSR and XCR definitions:
+ */
+
+extern unsigned int mxcsr_feature_mask;
+
+#define XCR_XFEATURE_ENABLED_MASK 0x00000000
+
+static inline u64 xgetbv(u32 index)
+{
+ u32 eax, edx;
+
+ asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
+ : "=a" (eax), "=d" (edx)
+ : "c" (index));
+ return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+ u32 eax = value;
+ u32 edx = value >> 32;
+
+ asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
+ : : "a" (eax), "d" (edx), "c" (index));
+}
+
+#endif /* _ASM_X86_FPU_INTERNAL_H */
diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h
new file mode 100644
index 000000000000..39d3107ac6c7
--- /dev/null
+++ b/arch/x86/include/asm/fpu/regset.h
@@ -0,0 +1,21 @@
+/*
+ * FPU regset handling methods:
+ */
+#ifndef _ASM_X86_FPU_REGSET_H
+#define _ASM_X86_FPU_REGSET_H
+
+#include <linux/regset.h>
+
+extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+ xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+ xstateregs_set;
+
+/*
+ * xstateregs_active == regset_fpregs_active. Please refer to the comment
+ * at the definition of regset_fpregs_active.
+ */
+#define xstateregs_active regset_fpregs_active
+
+#endif /* _ASM_X86_FPU_REGSET_H */
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
new file mode 100644
index 000000000000..7358e9d61f1e
--- /dev/null
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -0,0 +1,33 @@
+/*
+ * x86 FPU signal frame handling methods:
+ */
+#ifndef _ASM_X86_FPU_SIGNAL_H
+#define _ASM_X86_FPU_SIGNAL_H
+
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+struct ksignal;
+int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
+ compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct ksignal *ksig,
+ compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct user_i387_struct
+# define user32_fxsr_struct user_fxsr_struct
+# define ia32_setup_frame __setup_frame
+# define ia32_setup_rt_frame __setup_rt_frame
+#endif
+
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+ struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env);
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+ unsigned long *buf_fx, unsigned long *size);
+
+extern void fpu__init_prepare_fx_sw_frame(void);
+
+#endif /* _ASM_X86_FPU_SIGNAL_H */
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
new file mode 100644
index 000000000000..0637826292de
--- /dev/null
+++ b/arch/x86/include/asm/fpu/types.h
@@ -0,0 +1,293 @@
+/*
+ * FPU data structures:
+ */
+#ifndef _ASM_X86_FPU_H
+#define _ASM_X86_FPU_H
+
+/*
+ * The legacy x87 FPU state format, as saved by FSAVE and
+ * restored by the FRSTOR instructions:
+ */
+struct fregs_state {
+ u32 cwd; /* FPU Control Word */
+ u32 swd; /* FPU Status Word */
+ u32 twd; /* FPU Tag Word */
+ u32 fip; /* FPU IP Offset */
+ u32 fcs; /* FPU IP Selector */
+ u32 foo; /* FPU Operand Pointer Offset */
+ u32 fos; /* FPU Operand Pointer Selector */
+
+ /* 8*10 bytes for each FP-reg = 80 bytes: */
+ u32 st_space[20];
+
+ /* Software status information [not touched by FSAVE]: */
+ u32 status;
+};
+
+/*
+ * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and
+ * restored by the FXRSTOR instructions. It's similar to the FSAVE
+ * format, but differs in some areas, plus has extensions at
+ * the end for the XMM registers.
+ */
+struct fxregs_state {
+ u16 cwd; /* Control Word */
+ u16 swd; /* Status Word */
+ u16 twd; /* Tag Word */
+ u16 fop; /* Last Instruction Opcode */
+ union {
+ struct {
+ u64 rip; /* Instruction Pointer */
+ u64 rdp; /* Data Pointer */
+ };
+ struct {
+ u32 fip; /* FPU IP Offset */
+ u32 fcs; /* FPU IP Selector */
+ u32 foo; /* FPU Operand Offset */
+ u32 fos; /* FPU Operand Selector */
+ };
+ };
+ u32 mxcsr; /* MXCSR Register State */
+ u32 mxcsr_mask; /* MXCSR Mask */
+
+ /* 8*16 bytes for each FP-reg = 128 bytes: */
+ u32 st_space[32];
+
+ /* 16*16 bytes for each XMM-reg = 256 bytes: */
+ u32 xmm_space[64];
+
+ u32 padding[12];
+
+ union {
+ u32 padding1[12];
+ u32 sw_reserved[12];
+ };
+
+} __attribute__((aligned(16)));
+
+/* Default value for fxregs_state.mxcsr: */
+#define MXCSR_DEFAULT 0x1f80
+
+/*
+ * Software based FPU emulation state. This is arbitrary really,
+ * it matches the x87 format to make it easier to understand:
+ */
+struct swregs_state {
+ u32 cwd;
+ u32 swd;
+ u32 twd;
+ u32 fip;
+ u32 fcs;
+ u32 foo;
+ u32 fos;
+ /* 8*10 bytes for each FP-reg = 80 bytes: */
+ u32 st_space[20];
+ u8 ftop;
+ u8 changed;
+ u8 lookahead;
+ u8 no_update;
+ u8 rm;
+ u8 alimit;
+ struct math_emu_info *info;
+ u32 entry_eip;
+};
+
+/*
+ * List of XSAVE features Linux knows about:
+ */
+enum xfeature_bit {
+ XSTATE_BIT_FP,
+ XSTATE_BIT_SSE,
+ XSTATE_BIT_YMM,
+ XSTATE_BIT_BNDREGS,
+ XSTATE_BIT_BNDCSR,
+ XSTATE_BIT_OPMASK,
+ XSTATE_BIT_ZMM_Hi256,
+ XSTATE_BIT_Hi16_ZMM,
+
+ XFEATURES_NR_MAX,
+};
+
+#define XSTATE_FP (1 << XSTATE_BIT_FP)
+#define XSTATE_SSE (1 << XSTATE_BIT_SSE)
+#define XSTATE_YMM (1 << XSTATE_BIT_YMM)
+#define XSTATE_BNDREGS (1 << XSTATE_BIT_BNDREGS)
+#define XSTATE_BNDCSR (1 << XSTATE_BIT_BNDCSR)
+#define XSTATE_OPMASK (1 << XSTATE_BIT_OPMASK)
+#define XSTATE_ZMM_Hi256 (1 << XSTATE_BIT_ZMM_Hi256)
+#define XSTATE_Hi16_ZMM (1 << XSTATE_BIT_Hi16_ZMM)
+
+#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE)
+#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/*
+ * There are 16x 256-bit AVX registers named YMM0-YMM15.
+ * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15)
+ * and are stored in 'struct fxregs_state::xmm_space[]'.
+ *
+ * The high 128 bits are stored here:
+ * 16x 128 bits == 256 bytes.
+ */
+struct ymmh_struct {
+ u8 ymmh_space[256];
+};
+
+/* We don't support LWP yet: */
+struct lwp_struct {
+ u8 reserved[128];
+};
+
+/* Intel MPX support: */
+struct bndreg {
+ u64 lower_bound;
+ u64 upper_bound;
+} __packed;
+
+struct bndcsr {
+ u64 bndcfgu;
+ u64 bndstatus;
+} __packed;
+
+struct mpx_struct {
+ struct bndreg bndreg[4];
+ struct bndcsr bndcsr;
+};
+
+struct xstate_header {
+ u64 xfeatures;
+ u64 xcomp_bv;
+ u64 reserved[6];
+} __attribute__((packed));
+
+/* New processor state extensions should be added here: */
+#define XSTATE_RESERVE (sizeof(struct ymmh_struct) + \
+ sizeof(struct lwp_struct) + \
+ sizeof(struct mpx_struct) )
+/*
+ * This is our most modern FPU state format, as saved by the XSAVE
+ * and restored by the XRSTOR instructions.
+ *
+ * It consists of a legacy fxregs portion, an xstate header and
+ * subsequent fixed size areas as defined by the xstate header.
+ * Not all CPUs support all the extensions.
+ */
+struct xregs_state {
+ struct fxregs_state i387;
+ struct xstate_header header;
+ u8 __reserved[XSTATE_RESERVE];
+} __attribute__ ((packed, aligned (64)));
+
+/*
+ * This is a union of all the possible FPU state formats
+ * put together, so that we can pick the right one runtime.
+ *
+ * The size of the structure is determined by the largest
+ * member - which is the xsave area:
+ */
+union fpregs_state {
+ struct fregs_state fsave;
+ struct fxregs_state fxsave;
+ struct swregs_state soft;
+ struct xregs_state xsave;
+};
+
+/*
+ * Highest level per task FPU state data structure that
+ * contains the FPU register state plus various FPU
+ * state fields:
+ */
+struct fpu {
+ /*
+ * @state:
+ *
+ * In-memory copy of all FPU registers that we save/restore
+ * over context switches. If the task is using the FPU then
+ * the registers in the FPU are more recent than this state
+ * copy. If the task context-switches away then they get
+ * saved here and represent the FPU state.
+ *
+ * After context switches there may be a (short) time period
+ * during which the in-FPU hardware registers are unchanged
+ * and still perfectly match this state, if the tasks
+ * scheduled afterwards are not using the FPU.
+ *
+ * This is the 'lazy restore' window of optimization, which
+ * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
+ *
+ * We detect whether a subsequent task uses the FPU via setting
+ * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
+ *
+ * During this window, if the task gets scheduled again, we
+ * might be able to skip having to do a restore from this
+ * memory buffer to the hardware registers - at the cost of
+ * incurring the overhead of #NM fault traps.
+ *
+ * Note that on modern CPUs that support the XSAVEOPT (or other
+ * optimized XSAVE instructions), we don't use #NM traps anymore,
+ * as the hardware can track whether FPU registers need saving
+ * or not. On such CPUs we activate the non-lazy ('eagerfpu')
+ * logic, which unconditionally saves/restores all FPU state
+ * across context switches. (if FPU state exists.)
+ */
+ union fpregs_state state;
+
+ /*
+ * @last_cpu:
+ *
+ * Records the last CPU on which this context was loaded into
+ * FPU registers. (In the lazy-restore case we might be
+ * able to reuse FPU registers across multiple context switches
+ * this way, if no intermediate task used the FPU.)
+ *
+ * A value of -1 is used to indicate that the FPU state in context
+ * memory is newer than the FPU state in registers, and that the
+ * FPU state should be reloaded next time the task is run.
+ */
+ unsigned int last_cpu;
+
+ /*
+ * @fpstate_active:
+ *
+ * This flag indicates whether this context is active: if the task
+ * is not running then we can restore from this context, if the task
+ * is running then we should save into this context.
+ */
+ unsigned char fpstate_active;
+
+ /*
+ * @fpregs_active:
+ *
+ * This flag determines whether a given context is actively
+ * loaded into the FPU's registers and that those registers
+ * represent the task's current FPU state.
+ *
+ * Note the interaction with fpstate_active:
+ *
+ * # task does not use the FPU:
+ * fpstate_active == 0
+ *
+ * # task uses the FPU and regs are active:
+ * fpstate_active == 1 && fpregs_active == 1
+ *
+ * # the regs are inactive but still match fpstate:
+ * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
+ *
+ * The third state is what we use for the lazy restore optimization
+ * on lazy-switching CPUs.
+ */
+ unsigned char fpregs_active;
+
+ /*
+ * @counter:
+ *
+ * This counter contains the number of consecutive context switches
+ * during which the FPU stays used. If this is over a threshold, the
+ * lazy FPU restore logic becomes eager, to save the trap overhead.
+ * This is an unsigned char so that after 256 iterations the counter
+ * wraps and the context switch behavior turns lazy again; this is to
+ * deal with bursty apps that only use the FPU for a short time:
+ */
+ unsigned char counter;
+};
+
+#endif /* _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
new file mode 100644
index 000000000000..4656b25bb9a7
--- /dev/null
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -0,0 +1,46 @@
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+
+/* Bit 63 of XCR0 is reserved for future expansion */
+#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63)))
+
+#define XSTATE_CPUID 0x0000000d
+
+#define FXSAVE_SIZE 512
+
+#define XSAVE_HDR_SIZE 64
+#define XSAVE_HDR_OFFSET FXSAVE_SIZE
+
+#define XSAVE_YMM_SIZE 256
+#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
+
+/* Supported features which support lazy state saving */
+#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
+ | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/* Supported features which require eager state saving */
+#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR)
+
+/* All currently supported features */
+#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX "0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern unsigned int xstate_size;
+extern u64 xfeatures_mask;
+extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+
+extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
+
+void *get_xsave_addr(struct xregs_state *xsave, int xstate);
+const void *get_xsave_field_ptr(int xstate_field);
+
+#endif
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 3b629f47eb65..793179cf8e21 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -1,20 +1,17 @@
#ifdef __ASSEMBLY__
#include <asm/asm.h>
-#include <asm/dwarf2.h>
/* The annotation hides the frame from the unwinder and makes it look
like a ordinary ebp save/restore. This avoids some special cases for
frame pointer later */
#ifdef CONFIG_FRAME_POINTER
.macro FRAME
- __ASM_SIZE(push,_cfi) %__ASM_REG(bp)
- CFI_REL_OFFSET __ASM_REG(bp), 0
+ __ASM_SIZE(push,) %__ASM_REG(bp)
__ASM_SIZE(mov) %__ASM_REG(sp), %__ASM_REG(bp)
.endm
.macro ENDFRAME
- __ASM_SIZE(pop,_cfi) %__ASM_REG(bp)
- CFI_RESTORE __ASM_REG(bp)
+ __ASM_SIZE(pop,) %__ASM_REG(bp)
.endm
#else
.macro FRAME
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 0f5fb6b6567e..7178043b0e1d 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -14,6 +14,7 @@ typedef struct {
#endif
#ifdef CONFIG_HAVE_KVM
unsigned int kvm_posted_intr_ipis;
+ unsigned int kvm_posted_intr_wakeup_ipis;
#endif
unsigned int x86_platform_ipis; /* arch dependent */
unsigned int apic_perf_irqs;
@@ -33,6 +34,9 @@ typedef struct {
#ifdef CONFIG_X86_MCE_THRESHOLD
unsigned int irq_threshold_count;
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ unsigned int irq_deferred_error_count;
+#endif
#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
unsigned int irq_hv_callback_count;
#endif
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 36f7125945e3..5fa9fb0f8809 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,20 +74,16 @@ extern unsigned int hpet_readl(unsigned int a);
extern void force_hpet_resume(void);
struct irq_data;
+struct hpet_dev;
+struct irq_domain;
+
extern void hpet_msi_unmask(struct irq_data *data);
extern void hpet_msi_mask(struct irq_data *data);
-struct hpet_dev;
extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
-
-#ifdef CONFIG_PCI_MSI
-extern int default_setup_hpet_msi(unsigned int irq, unsigned int id);
-#else
-static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id)
-{
- return -EINVAL;
-}
-#endif
+extern struct irq_domain *hpet_create_irq_domain(int hpet_id);
+extern int hpet_assign_irq(struct irq_domain *domain,
+ struct hpet_dev *dev, int dev_num);
#ifdef CONFIG_HPET_EMULATE_RTC
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index e9571ddabc4f..6615032e19c8 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,6 +29,7 @@
extern asmlinkage void apic_timer_interrupt(void);
extern asmlinkage void x86_platform_ipi(void);
extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
extern asmlinkage void error_interrupt(void);
extern asmlinkage void irq_work_interrupt(void);
@@ -36,43 +37,10 @@ extern asmlinkage void spurious_interrupt(void);
extern asmlinkage void thermal_interrupt(void);
extern asmlinkage void reschedule_interrupt(void);
-extern asmlinkage void invalidate_interrupt(void);
-extern asmlinkage void invalidate_interrupt0(void);
-extern asmlinkage void invalidate_interrupt1(void);
-extern asmlinkage void invalidate_interrupt2(void);
-extern asmlinkage void invalidate_interrupt3(void);
-extern asmlinkage void invalidate_interrupt4(void);
-extern asmlinkage void invalidate_interrupt5(void);
-extern asmlinkage void invalidate_interrupt6(void);
-extern asmlinkage void invalidate_interrupt7(void);
-extern asmlinkage void invalidate_interrupt8(void);
-extern asmlinkage void invalidate_interrupt9(void);
-extern asmlinkage void invalidate_interrupt10(void);
-extern asmlinkage void invalidate_interrupt11(void);
-extern asmlinkage void invalidate_interrupt12(void);
-extern asmlinkage void invalidate_interrupt13(void);
-extern asmlinkage void invalidate_interrupt14(void);
-extern asmlinkage void invalidate_interrupt15(void);
-extern asmlinkage void invalidate_interrupt16(void);
-extern asmlinkage void invalidate_interrupt17(void);
-extern asmlinkage void invalidate_interrupt18(void);
-extern asmlinkage void invalidate_interrupt19(void);
-extern asmlinkage void invalidate_interrupt20(void);
-extern asmlinkage void invalidate_interrupt21(void);
-extern asmlinkage void invalidate_interrupt22(void);
-extern asmlinkage void invalidate_interrupt23(void);
-extern asmlinkage void invalidate_interrupt24(void);
-extern asmlinkage void invalidate_interrupt25(void);
-extern asmlinkage void invalidate_interrupt26(void);
-extern asmlinkage void invalidate_interrupt27(void);
-extern asmlinkage void invalidate_interrupt28(void);
-extern asmlinkage void invalidate_interrupt29(void);
-extern asmlinkage void invalidate_interrupt30(void);
-extern asmlinkage void invalidate_interrupt31(void);
-
extern asmlinkage void irq_move_cleanup_interrupt(void);
extern asmlinkage void reboot_interrupt(void);
extern asmlinkage void threshold_interrupt(void);
+extern asmlinkage void deferred_error_interrupt(void);
extern asmlinkage void call_function_interrupt(void);
extern asmlinkage void call_function_single_interrupt(void);
@@ -87,60 +55,93 @@ extern void trace_spurious_interrupt(void);
extern void trace_thermal_interrupt(void);
extern void trace_reschedule_interrupt(void);
extern void trace_threshold_interrupt(void);
+extern void trace_deferred_error_interrupt(void);
extern void trace_call_function_interrupt(void);
extern void trace_call_function_single_interrupt(void);
#define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt
#define trace_reboot_interrupt reboot_interrupt
#define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
+#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
#endif /* CONFIG_TRACING */
-#ifdef CONFIG_IRQ_REMAP
-/* Intel specific interrupt remapping information */
-struct irq_2_iommu {
- struct intel_iommu *iommu;
- u16 irte_index;
- u16 sub_handle;
- u8 irte_mask;
-};
-
-/* AMD specific interrupt remapping information */
-struct irq_2_irte {
- u16 devid; /* Device ID for IRTE table */
- u16 index; /* Index into IRTE table*/
-};
-#endif /* CONFIG_IRQ_REMAP */
-
#ifdef CONFIG_X86_LOCAL_APIC
struct irq_data;
+struct pci_dev;
+struct msi_desc;
+
+enum irq_alloc_type {
+ X86_IRQ_ALLOC_TYPE_IOAPIC = 1,
+ X86_IRQ_ALLOC_TYPE_HPET,
+ X86_IRQ_ALLOC_TYPE_MSI,
+ X86_IRQ_ALLOC_TYPE_MSIX,
+ X86_IRQ_ALLOC_TYPE_DMAR,
+ X86_IRQ_ALLOC_TYPE_UV,
+};
-struct irq_cfg {
- cpumask_var_t domain;
- cpumask_var_t old_domain;
- u8 vector;
- u8 move_in_progress : 1;
-#ifdef CONFIG_IRQ_REMAP
- u8 remapped : 1;
+struct irq_alloc_info {
+ enum irq_alloc_type type;
+ u32 flags;
+ const struct cpumask *mask; /* CPU mask for vector allocation */
union {
- struct irq_2_iommu irq_2_iommu;
- struct irq_2_irte irq_2_irte;
- };
+ int unused;
+#ifdef CONFIG_HPET_TIMER
+ struct {
+ int hpet_id;
+ int hpet_index;
+ void *hpet_data;
+ };
#endif
- union {
-#ifdef CONFIG_X86_IO_APIC
+#ifdef CONFIG_PCI_MSI
struct {
- struct list_head irq_2_pin;
+ struct pci_dev *msi_dev;
+ irq_hw_number_t msi_hwirq;
+ };
+#endif
+#ifdef CONFIG_X86_IO_APIC
+ struct {
+ int ioapic_id;
+ int ioapic_pin;
+ int ioapic_node;
+ u32 ioapic_trigger : 1;
+ u32 ioapic_polarity : 1;
+ u32 ioapic_valid : 1;
+ struct IO_APIC_route_entry *ioapic_entry;
+ };
+#endif
+#ifdef CONFIG_DMAR_TABLE
+ struct {
+ int dmar_id;
+ void *dmar_data;
+ };
+#endif
+#ifdef CONFIG_HT_IRQ
+ struct {
+ int ht_pos;
+ int ht_idx;
+ struct pci_dev *ht_dev;
+ void *ht_update;
+ };
+#endif
+#ifdef CONFIG_X86_UV
+ struct {
+ int uv_limit;
+ int uv_blade;
+ unsigned long uv_offset;
+ char *uv_name;
};
#endif
};
};
+struct irq_cfg {
+ unsigned int dest_apicid;
+ u8 vector;
+};
+
extern struct irq_cfg *irq_cfg(unsigned int irq);
extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
-extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
extern void lock_vector_lock(void);
extern void unlock_vector_lock(void);
-extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
-extern void clear_irq_vector(int irq, struct irq_cfg *cfg);
extern void setup_vector_irq(int cpu);
#ifdef CONFIG_SMP
extern void send_cleanup_vector(struct irq_cfg *);
@@ -150,10 +151,7 @@ static inline void send_cleanup_vector(struct irq_cfg *c) { }
static inline void irq_complete_move(struct irq_cfg *c) { }
#endif
-extern int apic_retrigger_irq(struct irq_data *data);
extern void apic_ack_edge(struct irq_data *data);
-extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- unsigned int *dest_id);
#else /* CONFIG_X86_LOCAL_APIC */
static inline void lock_vector_lock(void) {}
static inline void unlock_vector_lock(void) {}
@@ -163,8 +161,7 @@ static inline void unlock_vector_lock(void) {}
extern atomic_t irq_err_count;
extern atomic_t irq_mis_count;
-/* EISA */
-extern void eisa_set_level_irq(unsigned int irq);
+extern void elcr_set_level_irq(unsigned int irq);
/* SMP */
extern __visible void smp_apic_timer_interrupt(struct pt_regs *);
@@ -178,7 +175,6 @@ extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
extern __visible void smp_reschedule_interrupt(struct pt_regs *);
extern __visible void smp_call_function_interrupt(struct pt_regs *);
extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
-extern __visible void smp_invalidate_interrupt(struct pt_regs *);
#endif
extern char irq_entries_start[];
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
deleted file mode 100644
index 6eb6fcb83f63..000000000000
--- a/arch/x86/include/asm/i387.h
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _ASM_X86_I387_H
-#define _ASM_X86_I387_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/hardirq.h>
-
-struct pt_regs;
-struct user_i387_struct;
-
-extern int init_fpu(struct task_struct *child);
-extern void fpu_finit(struct fpu *fpu);
-extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
-extern void math_state_restore(void);
-
-extern bool irq_fpu_usable(void);
-
-/*
- * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
- * and they don't touch the preempt state on their own.
- * If you enable preemption after __kernel_fpu_begin(), preempt notifier
- * should call the __kernel_fpu_end() to prevent the kernel/user FPU
- * state from getting corrupted. KVM for example uses this model.
- *
- * All other cases use kernel_fpu_begin/end() which disable preemption
- * during kernel FPU usage.
- */
-extern void __kernel_fpu_begin(void);
-extern void __kernel_fpu_end(void);
-
-static inline void kernel_fpu_begin(void)
-{
- preempt_disable();
- WARN_ON_ONCE(!irq_fpu_usable());
- __kernel_fpu_begin();
-}
-
-static inline void kernel_fpu_end(void)
-{
- __kernel_fpu_end();
- preempt_enable();
-}
-
-/* Must be called with preempt disabled */
-extern void kernel_fpu_disable(void);
-extern void kernel_fpu_enable(void);
-
-/*
- * Some instructions like VIA's padlock instructions generate a spurious
- * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context as well. To prevent these kernel instructions
- * in interrupt context interacting wrongly with other user/kernel fpu usage, we
- * should use them only in the context of irq_ts_save/restore()
- */
-static inline int irq_ts_save(void)
-{
- /*
- * If in process context and not atomic, we can take a spurious DNA fault.
- * Otherwise, doing clts() in process context requires disabling preemption
- * or some heavy lifting like kernel_fpu_begin()
- */
- if (!in_atomic())
- return 0;
-
- if (read_cr0() & X86_CR0_TS) {
- clts();
- return 1;
- }
-
- return 0;
-}
-
-static inline void irq_ts_restore(int TS_state)
-{
- if (TS_state)
- stts();
-}
-
-/*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int user_has_fpu(void)
-{
- return current->thread.fpu.has_fpu;
-}
-
-extern void unlazy_fpu(struct task_struct *tsk);
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_I387_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34a5b93704d3..83ec9b1d77cc 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -35,11 +35,13 @@
*/
#define ARCH_HAS_IOREMAP_WC
+#define ARCH_HAS_IOREMAP_WT
#include <linux/string.h>
#include <linux/compiler.h>
#include <asm/page.h>
#include <asm/early_ioremap.h>
+#include <asm/pgtable_types.h>
#define build_mmio_read(name, size, type, reg, barrier) \
static inline type name(const volatile void __iomem *addr) \
@@ -177,6 +179,7 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
* look at pci_iomap().
*/
extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
unsigned long prot_val);
@@ -197,8 +200,6 @@ extern void set_iounmap_nonlazy(void);
#include <asm-generic/iomap.h>
-#include <linux/vmalloc.h>
-
/*
* Convert a virtual cached pointer to an uncached pointer
*/
@@ -320,6 +321,7 @@ extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
enum page_cache_mode pcm);
extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
extern bool is_early_ioremap_ptep(pte_t *ptep);
@@ -338,6 +340,9 @@ extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
#define IO_SPACE_LIMIT 0xffff
#ifdef CONFIG_MTRR
+extern int __must_check arch_phys_wc_index(int handle);
+#define arch_phys_wc_index arch_phys_wc_index
+
extern int __must_check arch_phys_wc_add(unsigned long base,
unsigned long size);
extern void arch_phys_wc_del(int handle);
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 2f91685fe1cd..6cbf2cfb3f8a 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -95,9 +95,22 @@ struct IR_IO_APIC_route_entry {
index : 15;
} __attribute__ ((packed));
-#define IOAPIC_AUTO -1
-#define IOAPIC_EDGE 0
-#define IOAPIC_LEVEL 1
+struct irq_alloc_info;
+struct ioapic_domain_cfg;
+
+#define IOAPIC_AUTO -1
+#define IOAPIC_EDGE 0
+#define IOAPIC_LEVEL 1
+
+#define IOAPIC_MASKED 1
+#define IOAPIC_UNMASKED 0
+
+#define IOAPIC_POL_HIGH 0
+#define IOAPIC_POL_LOW 1
+
+#define IOAPIC_DEST_MODE_PHYSICAL 0
+#define IOAPIC_DEST_MODE_LOGICAL 1
+
#define IOAPIC_MAP_ALLOC 0x1
#define IOAPIC_MAP_CHECK 0x2
@@ -110,9 +123,6 @@ extern int nr_ioapics;
extern int mpc_ioapic_id(int ioapic);
extern unsigned int mpc_ioapic_addr(int ioapic);
-extern struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic);
-
-#define MP_MAX_IOAPIC_PIN 127
/* # of MP IRQ source entries */
extern int mp_irq_entries;
@@ -120,9 +130,6 @@ extern int mp_irq_entries;
/* MP IRQ source entries */
extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
-/* Older SiS APIC requires we rewrite the index register */
-extern int sis_apic_bug;
-
/* 1 if "noapic" boot option passed */
extern int skip_ioapic_setup;
@@ -132,6 +139,8 @@ extern int noioapicquirk;
/* -1 if "noapic" boot option passed */
extern int noioapicreroute;
+extern u32 gsi_top;
+
extern unsigned long io_apic_irqs;
#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs))
@@ -147,13 +156,6 @@ struct irq_cfg;
extern void ioapic_insert_resources(void);
extern int arch_early_ioapic_init(void);
-extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
- unsigned int, int,
- struct io_apic_irq_attr *);
-extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg);
-
-extern void native_eoi_ioapic_pin(int apic, int pin, int vector);
-
extern int save_ioapic_entries(void);
extern void mask_ioapic_entries(void);
extern int restore_ioapic_entries(void);
@@ -161,82 +163,32 @@ extern int restore_ioapic_entries(void);
extern void setup_ioapic_ids_from_mpc(void);
extern void setup_ioapic_ids_from_mpc_nocheck(void);
-struct io_apic_irq_attr {
- int ioapic;
- int ioapic_pin;
- int trigger;
- int polarity;
-};
-
-enum ioapic_domain_type {
- IOAPIC_DOMAIN_INVALID,
- IOAPIC_DOMAIN_LEGACY,
- IOAPIC_DOMAIN_STRICT,
- IOAPIC_DOMAIN_DYNAMIC,
-};
-
-struct device_node;
-struct irq_domain;
-struct irq_domain_ops;
-
-struct ioapic_domain_cfg {
- enum ioapic_domain_type type;
- const struct irq_domain_ops *ops;
- struct device_node *dev;
-};
-
-struct mp_ioapic_gsi{
- u32 gsi_base;
- u32 gsi_end;
-};
-extern u32 gsi_top;
-
extern int mp_find_ioapic(u32 gsi);
extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
-extern u32 mp_pin_to_gsi(int ioapic, int pin);
-extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
+extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+ struct irq_alloc_info *info);
extern void mp_unmap_irq(int irq);
extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
struct ioapic_domain_cfg *cfg);
extern int mp_unregister_ioapic(u32 gsi_base);
extern int mp_ioapic_registered(u32 gsi_base);
-extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
- irq_hw_number_t hwirq);
-extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
-extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node);
-extern void __init pre_init_apic_IRQ0(void);
+
+extern void ioapic_set_alloc_attr(struct irq_alloc_info *info,
+ int node, int trigger, int polarity);
extern void mp_save_irq(struct mpc_intsrc *m);
extern void disable_ioapic_support(void);
-extern void __init native_io_apic_init_mappings(void);
+extern void __init io_apic_init_mappings(void);
extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg);
-extern void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int val);
-extern void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
extern void native_disable_io_apic(void);
-extern void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern void intel_ir_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern int native_ioapic_set_affinity(struct irq_data *,
- const struct cpumask *,
- bool);
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
{
return x86_io_apic_ops.read(apic, reg);
}
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
-{
- x86_io_apic_ops.write(apic, reg, value);
-}
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
- x86_io_apic_ops.modify(apic, reg, value);
-}
-
-extern void io_apic_eoi(unsigned int apic, unsigned int vector);
-
extern void setup_IO_APIC(void);
extern void enable_IO_APIC(void);
extern void disable_IO_APIC(void);
@@ -253,8 +205,12 @@ static inline int arch_early_ioapic_init(void) { return 0; }
static inline void print_IO_APICs(void) {}
#define gsi_top (NR_IRQS_LEGACY)
static inline int mp_find_ioapic(u32 gsi) { return 0; }
-static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; }
-static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; }
+static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+ struct irq_alloc_info *info)
+{
+ return gsi;
+}
+
static inline void mp_unmap_irq(int irq) { }
static inline int save_ioapic_entries(void)
@@ -268,17 +224,11 @@ static inline int restore_ioapic_entries(void)
return -ENOMEM;
}
-static inline void mp_save_irq(struct mpc_intsrc *m) { };
+static inline void mp_save_irq(struct mpc_intsrc *m) { }
static inline void disable_ioapic_support(void) { }
-#define native_io_apic_init_mappings NULL
+static inline void io_apic_init_mappings(void) { }
#define native_io_apic_read NULL
-#define native_io_apic_write NULL
-#define native_io_apic_modify NULL
#define native_disable_io_apic NULL
-#define native_io_apic_print_entries NULL
-#define native_ioapic_set_affinity NULL
-#define native_setup_ioapic_entry NULL
-#define native_eoi_ioapic_pin NULL
static inline void setup_IO_APIC(void) { }
static inline void enable_IO_APIC(void) { }
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index a80cbb88ea91..8008d06581c7 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -30,6 +30,10 @@ extern void fixup_irqs(void);
extern void irq_force_complete_move(int);
#endif
+#ifdef CONFIG_HAVE_KVM
+extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
+#endif
+
extern void (*x86_platform_ipi_callback)(void);
extern void native_init_IRQ(void);
extern bool handle_irq(unsigned irq, struct pt_regs *regs);
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 6224d316c405..046c7fb1ca43 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -22,84 +22,72 @@
#ifndef __X86_IRQ_REMAPPING_H
#define __X86_IRQ_REMAPPING_H
+#include <asm/irqdomain.h>
+#include <asm/hw_irq.h>
#include <asm/io_apic.h>
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_chip;
struct msi_msg;
-struct pci_dev;
-struct irq_cfg;
+struct irq_alloc_info;
+
+enum irq_remap_cap {
+ IRQ_POSTING_CAP = 0,
+};
#ifdef CONFIG_IRQ_REMAP
+extern bool irq_remapping_cap(enum irq_remap_cap cap);
extern void set_irq_remapping_broken(void);
extern int irq_remapping_prepare(void);
extern int irq_remapping_enable(void);
extern void irq_remapping_disable(void);
extern int irq_remapping_reenable(int);
extern int irq_remap_enable_fault_handling(void);
-extern int setup_ioapic_remapped_entry(int irq,
- struct IO_APIC_route_entry *entry,
- unsigned int destination,
- int vector,
- struct io_apic_irq_attr *attr);
-extern void free_remapped_irq(int irq);
-extern void compose_remapped_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id);
-extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id);
extern void panic_if_irq_remap(const char *msg);
-extern bool setup_remapped_irq(int irq,
- struct irq_cfg *cfg,
- struct irq_chip *chip);
-void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+extern struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info);
+extern struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info);
+
+/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */
+extern struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent);
+
+/* Get parent irqdomain for interrupt remapping irqdomain */
+static inline struct irq_domain *arch_get_ir_parent_domain(void)
+{
+ return x86_vector_domain;
+}
+
+struct vcpu_data {
+ u64 pi_desc_addr; /* Physical address of PI Descriptor */
+ u32 vector; /* Guest vector of the interrupt */
+};
#else /* CONFIG_IRQ_REMAP */
+static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
static inline void set_irq_remapping_broken(void) { }
static inline int irq_remapping_prepare(void) { return -ENODEV; }
static inline int irq_remapping_enable(void) { return -ENODEV; }
static inline void irq_remapping_disable(void) { }
static inline int irq_remapping_reenable(int eim) { return -ENODEV; }
static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; }
-static inline int setup_ioapic_remapped_entry(int irq,
- struct IO_APIC_route_entry *entry,
- unsigned int destination,
- int vector,
- struct io_apic_irq_attr *attr)
-{
- return -ENODEV;
-}
-static inline void free_remapped_irq(int irq) { }
-static inline void compose_remapped_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
-{
-}
-static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
- return -ENODEV;
-}
static inline void panic_if_irq_remap(const char *msg)
{
}
-static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
{
+ return NULL;
}
-static inline bool setup_remapped_irq(int irq,
- struct irq_cfg *cfg,
- struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
{
- return false;
+ return NULL;
}
-#endif /* CONFIG_IRQ_REMAP */
-
-#define dmar_alloc_hwirq() irq_alloc_hwirq(-1)
-#define dmar_free_hwirq irq_free_hwirq
+#endif /* CONFIG_IRQ_REMAP */
#endif /* __X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 666c89ec4bd7..4c2d2eb2060a 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -47,31 +47,12 @@
#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR
#define IA32_SYSCALL_VECTOR 0x80
-#ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR 0x80
-#endif
/*
* Vectors 0x30-0x3f are used for ISA interrupts.
* round up to the next 16-vector boundary
*/
-#define IRQ0_VECTOR ((FIRST_EXTERNAL_VECTOR + 16) & ~15)
-
-#define IRQ1_VECTOR (IRQ0_VECTOR + 1)
-#define IRQ2_VECTOR (IRQ0_VECTOR + 2)
-#define IRQ3_VECTOR (IRQ0_VECTOR + 3)
-#define IRQ4_VECTOR (IRQ0_VECTOR + 4)
-#define IRQ5_VECTOR (IRQ0_VECTOR + 5)
-#define IRQ6_VECTOR (IRQ0_VECTOR + 6)
-#define IRQ7_VECTOR (IRQ0_VECTOR + 7)
-#define IRQ8_VECTOR (IRQ0_VECTOR + 8)
-#define IRQ9_VECTOR (IRQ0_VECTOR + 9)
-#define IRQ10_VECTOR (IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR (IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR (IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR (IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR (IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR (IRQ0_VECTOR + 15)
+#define ISA_IRQ_VECTOR(irq) (((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq)
/*
* Special IRQ vectors used by the SMP architecture, 0xf0-0xff
@@ -102,21 +83,23 @@
*/
#define X86_PLATFORM_IPI_VECTOR 0xf7
-/* Vector for KVM to deliver posted interrupt IPI */
-#ifdef CONFIG_HAVE_KVM
-#define POSTED_INTR_VECTOR 0xf2
-#endif
-
+#define POSTED_INTR_WAKEUP_VECTOR 0xf1
/*
* IRQ work vector:
*/
#define IRQ_WORK_VECTOR 0xf6
#define UV_BAU_MESSAGE 0xf5
+#define DEFERRED_ERROR_VECTOR 0xf4
/* Vector on which hypervisor callbacks will be delivered */
#define HYPERVISOR_CALLBACK_VECTOR 0xf3
+/* Vector for KVM to deliver posted interrupt IPI */
+#ifdef CONFIG_HAVE_KVM
+#define POSTED_INTR_VECTOR 0xf2
+#endif
+
/*
* Local APIC timer IRQ vector is on a different priority level,
* to work around the 'lost local interrupt if more than 2 IRQ
@@ -155,18 +138,22 @@ static inline int invalid_vm86_irq(int irq)
* static arrays.
*/
-#define NR_IRQS_LEGACY 16
+#define NR_IRQS_LEGACY 16
-#define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS )
+#define CPU_VECTOR_LIMIT (64 * NR_CPUS)
+#define IO_APIC_VECTOR_LIMIT (32 * MAX_IO_APICS)
-#ifdef CONFIG_X86_IO_APIC
-# define CPU_VECTOR_LIMIT (64 * NR_CPUS)
-# define NR_IRQS \
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI)
+#define NR_IRQS \
(CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \
(NR_VECTORS + CPU_VECTOR_LIMIT) : \
(NR_VECTORS + IO_APIC_VECTOR_LIMIT))
-#else /* !CONFIG_X86_IO_APIC: */
-# define NR_IRQS NR_IRQS_LEGACY
+#elif defined(CONFIG_X86_IO_APIC)
+#define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#elif defined(CONFIG_PCI_MSI)
+#define NR_IRQS (NR_VECTORS + CPU_VECTOR_LIMIT)
+#else
+#define NR_IRQS NR_IRQS_LEGACY
#endif
#endif /* _ASM_X86_IRQ_VECTORS_H */
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
new file mode 100644
index 000000000000..d26075b52885
--- /dev/null
+++ b/arch/x86/include/asm/irqdomain.h
@@ -0,0 +1,63 @@
+#ifndef _ASM_IRQDOMAIN_H
+#define _ASM_IRQDOMAIN_H
+
+#include <linux/irqdomain.h>
+#include <asm/hw_irq.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+enum {
+ /* Allocate contiguous CPU vectors */
+ X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1,
+};
+
+extern struct irq_domain *x86_vector_domain;
+
+extern void init_irq_alloc_info(struct irq_alloc_info *info,
+ const struct cpumask *mask);
+extern void copy_irq_alloc_info(struct irq_alloc_info *dst,
+ struct irq_alloc_info *src);
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#ifdef CONFIG_X86_IO_APIC
+struct device_node;
+struct irq_data;
+
+enum ioapic_domain_type {
+ IOAPIC_DOMAIN_INVALID,
+ IOAPIC_DOMAIN_LEGACY,
+ IOAPIC_DOMAIN_STRICT,
+ IOAPIC_DOMAIN_DYNAMIC,
+};
+
+struct ioapic_domain_cfg {
+ enum ioapic_domain_type type;
+ const struct irq_domain_ops *ops;
+ struct device_node *dev;
+};
+
+extern const struct irq_domain_ops mp_ioapic_irqdomain_ops;
+
+extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg);
+extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs);
+extern void mp_irqdomain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data);
+extern void mp_irqdomain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data);
+extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
+#endif /* CONFIG_X86_IO_APIC */
+
+#ifdef CONFIG_PCI_MSI
+extern void arch_init_msi_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_msi_domain(struct irq_domain *domain) { }
+#endif
+
+#ifdef CONFIG_HT_IRQ
+extern void arch_init_htirq_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_htirq_domain(struct irq_domain *domain) { }
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 57a9d94fe160..e16466ec473c 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -193,6 +193,8 @@ struct x86_emulate_ops {
int (*cpl)(struct x86_emulate_ctxt *ctxt);
int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
+ u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt);
+ void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase);
int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
@@ -262,6 +264,11 @@ enum x86emul_mode {
X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */
};
+/* These match some of the HF_* flags defined in kvm_host.h */
+#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
+#define X86EMUL_SMM_MASK (1 << 6)
+#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7)
+
struct x86_emulate_ctxt {
const struct x86_emulate_ops *ops;
@@ -273,8 +280,8 @@ struct x86_emulate_ctxt {
/* interruptibility state, as a result of execution of STI or MOV SS */
int interruptibility;
+ int emul_flags;
- bool guest_mode; /* guest running a nested guest */
bool perm_ok; /* do not check permissions if true */
bool ud; /* inject an #UD if host doesn't support insn */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dea2e7e962e3..c7fa57b529d2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -184,29 +184,28 @@ struct kvm_mmu_memory_cache {
void *objects[KVM_NR_MEM_OBJS];
};
-/*
- * kvm_mmu_page_role, below, is defined as:
- *
- * bits 0:3 - total guest paging levels (2-4, or zero for real mode)
- * bits 4:7 - page table level for this shadow (1-4)
- * bits 8:9 - page table quadrant for 2-level guests
- * bit 16 - direct mapping of virtual to physical mapping at gfn
- * used for real mode and two-dimensional paging
- * bits 17:19 - common access permissions for all ptes in this shadow page
- */
union kvm_mmu_page_role {
unsigned word;
struct {
unsigned level:4;
unsigned cr4_pae:1;
unsigned quadrant:2;
- unsigned pad_for_nice_hex_output:6;
unsigned direct:1;
unsigned access:3;
unsigned invalid:1;
unsigned nxe:1;
unsigned cr0_wp:1;
unsigned smep_andnot_wp:1;
+ unsigned smap_andnot_wp:1;
+ unsigned :8;
+
+ /*
+ * This is left at the top of the word so that
+ * kvm_memslots_for_spte_role can extract it with a
+ * simple shift. While there is room, give it a whole
+ * byte so it is also faster to load it from memory.
+ */
+ unsigned smm:8;
};
};
@@ -337,12 +336,28 @@ struct kvm_pmu {
u64 reprogram_pmi;
};
+struct kvm_pmu_ops;
+
enum {
KVM_DEBUGREG_BP_ENABLED = 1,
KVM_DEBUGREG_WONT_EXIT = 2,
KVM_DEBUGREG_RELOAD = 4,
};
+struct kvm_mtrr_range {
+ u64 base;
+ u64 mask;
+ struct list_head node;
+};
+
+struct kvm_mtrr {
+ struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR];
+ mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION];
+ u64 deftype;
+
+ struct list_head head;
+};
+
struct kvm_vcpu_arch {
/*
* rip and regs accesses must go through
@@ -367,6 +382,7 @@ struct kvm_vcpu_arch {
int32_t apic_arb_prio;
int mp_state;
u64 ia32_misc_enable_msr;
+ u64 smbase;
bool tpr_access_reporting;
u64 ia32_xss;
@@ -400,6 +416,7 @@ struct kvm_vcpu_arch {
struct kvm_mmu_memory_cache mmu_page_header_cache;
struct fpu guest_fpu;
+ bool eager_fpu;
u64 xcr0;
u64 guest_supported_xcr0;
u32 guest_xstate_size;
@@ -469,8 +486,9 @@ struct kvm_vcpu_arch {
atomic_t nmi_queued; /* unprocessed asynchronous NMIs */
unsigned nmi_pending; /* NMI queued after currently running handler */
bool nmi_injected; /* Trying to inject an NMI this entry */
+ bool smi_pending; /* SMI queued after currently running handler */
- struct mtrr_state_type mtrr_state;
+ struct kvm_mtrr mtrr_state;
u64 pat;
unsigned switch_db_regs;
@@ -635,6 +653,8 @@ struct kvm_arch {
#endif
bool boot_vcpu_runs_old_kvmclock;
+
+ u64 disabled_quirks;
};
struct kvm_vm_stat {
@@ -687,12 +707,13 @@ struct msr_data {
struct kvm_lapic_irq {
u32 vector;
- u32 delivery_mode;
- u32 dest_mode;
- u32 level;
- u32 trig_mode;
+ u16 delivery_mode;
+ u16 dest_mode;
+ bool level;
+ u16 trig_mode;
u32 shorthand;
u32 dest_id;
+ bool msi_redir_hint;
};
struct kvm_x86_ops {
@@ -704,19 +725,20 @@ struct kvm_x86_ops {
int (*hardware_setup)(void); /* __init */
void (*hardware_unsetup)(void); /* __exit */
bool (*cpu_has_accelerated_tpr)(void);
+ bool (*cpu_has_high_real_mode_segbase)(void);
void (*cpuid_update)(struct kvm_vcpu *vcpu);
/* Create, but do not attach this VCPU */
struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
void (*vcpu_free)(struct kvm_vcpu *vcpu);
- void (*vcpu_reset)(struct kvm_vcpu *vcpu);
+ void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu);
- int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
+ int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
void (*get_segment)(struct kvm_vcpu *vcpu,
@@ -743,6 +765,7 @@ struct kvm_x86_ops {
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+ void (*fpu_activate)(struct kvm_vcpu *vcpu);
void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
void (*tlb_flush)(struct kvm_vcpu *vcpu);
@@ -833,6 +856,8 @@ struct kvm_x86_ops {
void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t offset, unsigned long mask);
+ /* pmu operations of sub-arch */
+ const struct kvm_pmu_ops *pmu_ops;
};
struct kvm_arch_async_pf {
@@ -868,7 +893,7 @@ void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
struct kvm_memory_slot *memslot);
void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
- struct kvm_memory_slot *memslot);
+ const struct kvm_memory_slot *memslot);
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
struct kvm_memory_slot *memslot);
void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
@@ -879,7 +904,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn_offset, unsigned long mask);
void kvm_mmu_zap_all(struct kvm *kvm);
-void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm);
+void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots);
unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
@@ -887,7 +912,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
const void *val, int bytes);
-u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
struct kvm_irq_mask_notifier {
void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
@@ -935,7 +959,7 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu,
void kvm_enable_efer_bits(u64);
bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
-int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
+int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
struct x86_emulate_ctxt;
@@ -964,7 +988,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);
-int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
@@ -999,8 +1023,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
-int fx_init(struct kvm_vcpu *vcpu);
-
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
const u8 *new, int bytes);
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
@@ -1109,6 +1131,14 @@ enum {
#define HF_NMI_MASK (1 << 3)
#define HF_IRET_MASK (1 << 4)
#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
+#define HF_SMM_MASK (1 << 6)
+#define HF_SMM_INSIDE_NMI_MASK (1 << 7)
+
+#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#define KVM_ADDRESS_SPACE_NUM 2
+
+#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
+#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
/*
* Hardware virtualization extension instructions may fault if a
@@ -1143,7 +1173,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
-void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
unsigned long address);
@@ -1167,16 +1197,9 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
int kvm_is_in_guest(void);
-void kvm_pmu_init(struct kvm_vcpu *vcpu);
-void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
-void kvm_pmu_reset(struct kvm_vcpu *vcpu);
-void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu);
-bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr);
-int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
-int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
-int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc);
-int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
-void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
-void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
+int __x86_set_memory_region(struct kvm *kvm,
+ const struct kvm_userspace_memory_region *mem);
+int x86_set_memory_region(struct kvm *kvm,
+ const struct kvm_userspace_memory_region *mem);
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 2d29197bd2fb..19c099afa861 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -21,6 +21,7 @@
#ifndef _ASM_X86_LIVEPATCH_H
#define _ASM_X86_LIVEPATCH_H
+#include <asm/setup.h>
#include <linux/module.h>
#include <linux/ftrace.h>
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 1f5a86d518db..982dfc3679ad 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -17,11 +17,16 @@
#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */
#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */
+#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */
/* MCG_STATUS register defines */
#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */
#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */
#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */
+#define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */
+
+/* MCG_EXT_CTL register defines */
+#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */
/* MCi_STATUS register defines */
#define MCI_STATUS_VAL (1ULL<<63) /* valid error */
@@ -104,6 +109,7 @@ struct mce_log {
struct mca_config {
bool dont_log_ce;
bool cmci_disabled;
+ bool lmce_disabled;
bool ignore_ce;
bool disabled;
bool ser;
@@ -117,8 +123,19 @@ struct mca_config {
};
struct mce_vendor_flags {
- __u64 overflow_recov : 1, /* cpuid_ebx(80000007) */
- __reserved_0 : 63;
+ /*
+ * overflow recovery cpuid bit indicates that overflow
+ * conditions are not fatal
+ */
+ __u64 overflow_recov : 1,
+
+ /*
+ * SUCCOR stands for S/W UnCorrectable error COntainment
+ * and Recovery. It indicates support for data poisoning
+ * in HW and deferred error interrupts.
+ */
+ succor : 1,
+ __reserved_0 : 62;
};
extern struct mce_vendor_flags mce_flags;
@@ -168,12 +185,16 @@ void cmci_clear(void);
void cmci_reenable(void);
void cmci_rediscover(void);
void cmci_recheck(void);
+void lmce_clear(void);
+void lmce_enable(void);
#else
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
static inline void cmci_clear(void) {}
static inline void cmci_reenable(void) {}
static inline void cmci_rediscover(void) {}
static inline void cmci_recheck(void) {}
+static inline void lmce_clear(void) {}
+static inline void lmce_enable(void) {}
#endif
#ifdef CONFIG_X86_MCE_AMD
@@ -223,6 +244,9 @@ void do_machine_check(struct pt_regs *, long);
extern void (*mce_threshold_vector)(void);
extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
+/* Deferred error interrupt handler */
+extern void (*deferred_error_int_vector)(void);
+
/*
* Thermal handler
*/
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 2fb20d6f7e23..9e6278c7140e 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -1,6 +1,8 @@
#ifndef _ASM_X86_MICROCODE_H
#define _ASM_X86_MICROCODE_H
+#include <linux/earlycpio.h>
+
#define native_rdmsr(msr, val1, val2) \
do { \
u64 __val = native_read_msr((msr)); \
@@ -152,6 +154,7 @@ extern void __init load_ucode_bsp(void);
extern void load_ucode_ap(void);
extern int __init save_microcode_in_initrd(void);
void reload_early_microcode(void);
+extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
#else
static inline void __init load_ucode_bsp(void) {}
static inline void load_ucode_ap(void) {}
@@ -160,6 +163,9 @@ static inline int __init save_microcode_in_initrd(void)
return 0;
}
static inline void reload_early_microcode(void) {}
+static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+ return false;
+}
#endif
-
#endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index af935397e053..ac6d328977a6 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -65,12 +65,12 @@ extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, s
extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
#ifdef CONFIG_MICROCODE_AMD_EARLY
-extern void __init load_ucode_amd_bsp(void);
+extern void __init load_ucode_amd_bsp(unsigned int family);
extern void load_ucode_amd_ap(void);
extern int __init save_microcode_in_initrd_amd(void);
void reload_ucode_amd(void);
#else
-static inline void __init load_ucode_amd_bsp(void) {}
+static inline void __init load_ucode_amd_bsp(unsigned int family) {}
static inline void load_ucode_amd_ap(void) {}
static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; }
void reload_ucode_amd(void) {}
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 2b9209c46ca9..7991c606125d 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -51,20 +51,11 @@ struct extended_sigtable {
(((struct microcode_intel *)mc)->hdr.datasize ? \
((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE)
-#define sigmatch(s1, s2, p1, p2) \
- (((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0))))
-
#define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
-extern int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc);
+extern int has_newer_microcode(void *mc, unsigned int csig, int cpf, int rev);
extern int microcode_sanity_check(void *mc, int print_err);
-extern int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc);
-
-static inline int
-revision_is_newer(struct microcode_header_intel *mc_header, int rev)
-{
- return (mc_header->rev <= rev) ? 0 : 1;
-}
+extern int find_matching_signature(void *mc, unsigned int csig, int cpf);
#ifdef CONFIG_MICROCODE_INTEL_EARLY
extern void __init load_ucode_intel_bsp(void);
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 883f6b933fa4..5e8daee7c5c9 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -142,6 +142,19 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
paravirt_arch_exit_mmap(mm);
}
+#ifdef CONFIG_X86_64
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+ return !config_enabled(CONFIG_IA32_EMULATION) ||
+ !(mm->context.ia32_compat == TIF_IA32);
+}
+#else
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+ return false;
+}
+#endif
+
static inline void arch_bprm_mm_init(struct mm_struct *mm,
struct vm_area_struct *vma)
{
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index a952a13d59a7..7a35495275a9 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -13,55 +13,50 @@
#define MPX_BNDCFG_ENABLE_FLAG 0x1
#define MPX_BD_ENTRY_VALID_FLAG 0x1
-#ifdef CONFIG_X86_64
-
-/* upper 28 bits [47:20] of the virtual address in 64-bit used to
- * index into bounds directory (BD).
- */
-#define MPX_BD_ENTRY_OFFSET 28
-#define MPX_BD_ENTRY_SHIFT 3
-/* bits [19:3] of the virtual address in 64-bit used to index into
- * bounds table (BT).
+/*
+ * The upper 28 bits [47:20] of the virtual address in 64-bit
+ * are used to index into bounds directory (BD).
+ *
+ * The directory is 2G (2^31) in size, and with 8-byte entries
+ * it has 2^28 entries.
*/
-#define MPX_BT_ENTRY_OFFSET 17
-#define MPX_BT_ENTRY_SHIFT 5
-#define MPX_IGN_BITS 3
-#define MPX_BD_ENTRY_TAIL 3
+#define MPX_BD_SIZE_BYTES_64 (1UL<<31)
+#define MPX_BD_ENTRY_BYTES_64 8
+#define MPX_BD_NR_ENTRIES_64 (MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64)
-#else
-
-#define MPX_BD_ENTRY_OFFSET 20
-#define MPX_BD_ENTRY_SHIFT 2
-#define MPX_BT_ENTRY_OFFSET 10
-#define MPX_BT_ENTRY_SHIFT 4
-#define MPX_IGN_BITS 2
-#define MPX_BD_ENTRY_TAIL 2
+/*
+ * The 32-bit directory is 4MB (2^22) in size, and with 4-byte
+ * entries it has 2^20 entries.
+ */
+#define MPX_BD_SIZE_BYTES_32 (1UL<<22)
+#define MPX_BD_ENTRY_BYTES_32 4
+#define MPX_BD_NR_ENTRIES_32 (MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32)
-#endif
+/*
+ * A 64-bit table is 4MB total in size, and an entry is
+ * 4 64-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_64 (1UL<<22)
+#define MPX_BT_ENTRY_BYTES_64 32
+#define MPX_BT_NR_ENTRIES_64 (MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64)
-#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
-#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
+/*
+ * A 32-bit table is 16kB total in size, and an entry is
+ * 4 32-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_32 (1UL<<14)
+#define MPX_BT_ENTRY_BYTES_32 16
+#define MPX_BT_NR_ENTRIES_32 (MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32)
#define MPX_BNDSTA_TAIL 2
#define MPX_BNDCFG_TAIL 12
#define MPX_BNDSTA_ADDR_MASK (~((1UL<<MPX_BNDSTA_TAIL)-1))
#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
-#define MPX_BT_ADDR_MASK (~((1UL<<MPX_BD_ENTRY_TAIL)-1))
-
-#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
#define MPX_BNDSTA_ERROR_CODE 0x3
-#define MPX_BD_ENTRY_MASK ((1<<MPX_BD_ENTRY_OFFSET)-1)
-#define MPX_BT_ENTRY_MASK ((1<<MPX_BT_ENTRY_OFFSET)-1)
-#define MPX_GET_BD_ENTRY_OFFSET(addr) ((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
- MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
-#define MPX_GET_BT_ENTRY_OFFSET(addr) ((((addr)>>MPX_IGN_BITS) & \
- MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
-
#ifdef CONFIG_X86_INTEL_MPX
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf);
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs);
+int mpx_handle_bd_fault(void);
static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
{
return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
@@ -77,12 +72,11 @@ static inline void mpx_mm_init(struct mm_struct *mm)
void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long start, unsigned long end);
#else
-static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf)
+static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
{
return NULL;
}
-static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+static inline int mpx_handle_bd_fault(void)
{
return -EINVAL;
}
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
new file mode 100644
index 000000000000..93724cc62177
--- /dev/null
+++ b/arch/x86/include/asm/msi.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_MSI_H
+#define _ASM_X86_MSI_H
+#include <asm/hw_irq.h>
+
+typedef struct irq_alloc_info msi_alloc_info_t;
+
+#endif /* _ASM_X86_MSI_H */
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index c469490db4a8..9ebc3d009373 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,7 @@
#define MSR_IA32_MCG_CAP 0x00000179
#define MSR_IA32_MCG_STATUS 0x0000017a
#define MSR_IA32_MCG_CTL 0x0000017b
+#define MSR_IA32_MCG_EXT_CTL 0x000004d0
#define MSR_OFFCORE_RSP_0 0x000001a6
#define MSR_OFFCORE_RSP_1 0x000001a7
@@ -140,6 +141,7 @@
#define MSR_CORE_C3_RESIDENCY 0x000003fc
#define MSR_CORE_C6_RESIDENCY 0x000003fd
#define MSR_CORE_C7_RESIDENCY 0x000003fe
+#define MSR_KNL_CORE_C6_RESIDENCY 0x000003ff
#define MSR_PKG_C2_RESIDENCY 0x0000060d
#define MSR_PKG_C8_RESIDENCY 0x00000630
#define MSR_PKG_C9_RESIDENCY 0x00000631
@@ -379,6 +381,7 @@
#define FEATURE_CONTROL_LOCKED (1<<0)
#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1)
#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2)
+#define FEATURE_CONTROL_LMCE (1<<20)
#define MSR_IA32_APICBASE 0x0000001b
#define MSR_IA32_APICBASE_BSP (1<<8)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index de36f22eb0b9..e6a707eb5081 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -1,13 +1,14 @@
#ifndef _ASM_X86_MSR_H
#define _ASM_X86_MSR_H
-#include <uapi/asm/msr.h>
+#include "msr-index.h"
#ifndef __ASSEMBLY__
#include <asm/asm.h>
#include <asm/errno.h>
#include <asm/cpumask.h>
+#include <uapi/asm/msr.h>
struct msr {
union {
@@ -205,8 +206,13 @@ do { \
#endif /* !CONFIG_PARAVIRT */
-#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \
- (u32)((val) >> 32))
+/*
+ * 64-bit version of wrmsr_safe():
+ */
+static inline int wrmsrl_safe(u32 msr, u64 val)
+{
+ return wrmsr_safe(msr, (u32)val, (u32)(val >> 32));
+}
#define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high))
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index f768f6298419..b94f6f64e23d 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -31,7 +31,7 @@
* arch_phys_wc_add and arch_phys_wc_del.
*/
# ifdef CONFIG_MTRR
-extern u8 mtrr_type_lookup(u64 addr, u64 end);
+extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform);
extern void mtrr_save_fixed_ranges(void *);
extern void mtrr_save_state(void);
extern int mtrr_add(unsigned long base, unsigned long size,
@@ -48,14 +48,13 @@ extern void mtrr_aps_init(void);
extern void mtrr_bp_restore(void);
extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
extern int amd_special_default_mtrr(void);
-extern int phys_wc_to_mtrr_index(int handle);
# else
-static inline u8 mtrr_type_lookup(u64 addr, u64 end)
+static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform)
{
/*
* Return no-MTRRs:
*/
- return 0xff;
+ return MTRR_TYPE_INVALID;
}
#define mtrr_save_fixed_ranges(arg) do {} while (0)
#define mtrr_save_state() do {} while (0)
@@ -84,10 +83,6 @@ 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 int phys_wc_to_mtrr_index(int handle)
-{
- return -1;
-}
#define mtrr_ap_init() do {} while (0)
#define mtrr_bp_init() do {} while (0)
@@ -127,4 +122,8 @@ struct mtrr_gentry32 {
_IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry32)
#endif /* CONFIG_COMPAT */
+/* Bit fields for enabled in struct mtrr_state_type */
+#define MTRR_STATE_MTRR_FIXED_ENABLED 0x01
+#define MTRR_STATE_MTRR_ENABLED 0x02
+
#endif /* _ASM_X86_MTRR_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8957810ad7d1..d143bfad45d7 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,6 +712,31 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
+ u32 val)
+{
+ PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val);
+}
+
+static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
+{
+ PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock);
+}
+
+static __always_inline void pv_wait(u8 *ptr, u8 val)
+{
+ PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+}
+
+static __always_inline void pv_kick(int cpu)
+{
+ PVOP_VCALL1(pv_lock_ops.kick, cpu);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
__ticket_t ticket)
{
@@ -724,7 +749,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
}
-#endif
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+#endif /* SMP && PARAVIRT_SPINLOCKS */
#ifdef CONFIG_X86_32
#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index f7b0b5c112f2..a6b8f9fadb06 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -160,13 +160,14 @@ struct pv_cpu_ops {
u64 (*read_pmc)(int counter);
unsigned long long (*read_tscp)(unsigned int *aux);
+#ifdef CONFIG_X86_32
/*
* Atomically enable interrupts and return to userspace. This
- * is only ever used to return to 32-bit processes; in a
- * 64-bit kernel, it's used for 32-on-64 compat processes, but
- * never native 64-bit processes. (Jump, not call.)
+ * is only used in 32-bit kernels. 64-bit kernels use
+ * usergs_sysret32 instead.
*/
void (*irq_enable_sysexit)(void);
+#endif
/*
* Switch to usermode gs and return to 64-bit usermode using
@@ -333,9 +334,19 @@ struct arch_spinlock;
typedef u16 __ticket_t;
#endif
+struct qspinlock;
+
struct pv_lock_ops {
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
+ struct paravirt_callee_save queued_spin_unlock;
+
+ void (*wait)(u8 *ptr, u8 val);
+ void (*kick)(int cpu);
+#else /* !CONFIG_QUEUED_SPINLOCKS */
struct paravirt_callee_save lock_spinning;
void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
};
/* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 91bc4ba95f91..ca6c228d5e62 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -4,14 +4,9 @@
#include <linux/types.h>
#include <asm/pgtable_types.h>
-#ifdef CONFIG_X86_PAT
-extern int pat_enabled;
-#else
-static const int pat_enabled;
-#endif
-
+bool pat_enabled(void);
extern void pat_init(void);
-void pat_init_cache_modes(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/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 4e370a5d8117..b962e0fe5658 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -80,13 +80,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
#ifdef CONFIG_PCI
extern void early_quirks(void);
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
- enum pci_dma_burst_strategy *strat,
- unsigned long *strategy_parameter)
-{
- *strat = PCI_DMA_BURST_INFINITY;
- *strategy_parameter = ~0UL;
-}
#else
static inline void early_quirks(void) { }
#endif
@@ -96,15 +89,10 @@ extern void pci_iommu_alloc(void);
#ifdef CONFIG_PCI_MSI
/* implemented in arch/x86/kernel/apic/io_apic. */
struct msi_desc;
-void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq,
- unsigned int dest, struct msi_msg *msg, u8 hpet_id);
int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
void native_teardown_msi_irq(unsigned int irq);
void native_restore_msi_irqs(struct pci_dev *dev);
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- unsigned int irq_base, unsigned int irq_offset);
#else
-#define native_compose_msi_msg NULL
#define native_setup_msi_irqs NULL
#define native_teardown_msi_irq NULL
#endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index fe57e7a98839..2562e303405b 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -398,11 +398,17 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
* requested memtype:
* - request is uncached, return cannot be write-back
* - request is write-combine, return cannot be write-back
+ * - request is write-through, return cannot be write-back
+ * - request is write-through, return cannot be write-combine
*/
if ((pcm == _PAGE_CACHE_MODE_UC_MINUS &&
new_pcm == _PAGE_CACHE_MODE_WB) ||
(pcm == _PAGE_CACHE_MODE_WC &&
- new_pcm == _PAGE_CACHE_MODE_WB)) {
+ new_pcm == _PAGE_CACHE_MODE_WB) ||
+ (pcm == _PAGE_CACHE_MODE_WT &&
+ new_pcm == _PAGE_CACHE_MODE_WB) ||
+ (pcm == _PAGE_CACHE_MODE_WT &&
+ new_pcm == _PAGE_CACHE_MODE_WC)) {
return 0;
}
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 78f0c8cbe316..13f310bfc09a 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -367,6 +367,9 @@ extern int nx_enabled;
#define pgprot_writecombine pgprot_writecombine
extern pgprot_t pgprot_writecombine(pgprot_t prot);
+#define pgprot_writethrough pgprot_writethrough
+extern pgprot_t pgprot_writethrough(pgprot_t prot);
+
/* Indicate that x86 has its own track and untrack pfn vma functions */
#define __HAVE_PFNMAP_TRACKING
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 8f3271842533..dca71714f860 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -99,11 +99,9 @@ static __always_inline bool should_resched(void)
extern asmlinkage void ___preempt_schedule(void);
# define __preempt_schedule() asm ("call ___preempt_schedule")
extern asmlinkage void preempt_schedule(void);
-# ifdef CONFIG_CONTEXT_TRACKING
- extern asmlinkage void ___preempt_schedule_context(void);
-# define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
- extern asmlinkage void preempt_schedule_context(void);
-# endif
+ extern asmlinkage void ___preempt_schedule_notrace(void);
+# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace")
+ extern asmlinkage void preempt_schedule_notrace(void);
#endif
#endif /* __ASM_PREEMPT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 23ba6765b718..43e6519df0d5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -21,6 +21,7 @@ struct mm_struct;
#include <asm/desc_defs.h>
#include <asm/nops.h>
#include <asm/special_insns.h>
+#include <asm/fpu/types.h>
#include <linux/personality.h>
#include <linux/cpumask.h>
@@ -52,11 +53,16 @@ static inline void *current_text_addr(void)
return pc;
}
+/*
+ * These alignment constraints are for performance in the vSMP case,
+ * but in the task_struct case we must also meet hardware imposed
+ * alignment requirements of the FPU state:
+ */
#ifdef CONFIG_X86_VSMP
# define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT)
# define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT)
#else
-# define ARCH_MIN_TASKALIGN 16
+# define ARCH_MIN_TASKALIGN __alignof__(union fpregs_state)
# define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif
@@ -166,7 +172,6 @@ extern const struct seq_operations cpuinfo_op;
#define cache_line_size() (boot_cpu_data.x86_cache_alignment)
extern void cpu_detect(struct cpuinfo_x86 *c);
-extern void fpu_detect(struct cpuinfo_x86 *c);
extern void early_cpu_init(void);
extern void identify_boot_cpu(void);
@@ -313,128 +318,6 @@ struct orig_ist {
unsigned long ist[7];
};
-#define MXCSR_DEFAULT 0x1f80
-
-struct i387_fsave_struct {
- u32 cwd; /* FPU Control Word */
- u32 swd; /* FPU Status Word */
- u32 twd; /* FPU Tag Word */
- u32 fip; /* FPU IP Offset */
- u32 fcs; /* FPU IP Selector */
- u32 foo; /* FPU Operand Pointer Offset */
- u32 fos; /* FPU Operand Pointer Selector */
-
- /* 8*10 bytes for each FP-reg = 80 bytes: */
- u32 st_space[20];
-
- /* Software status information [not touched by FSAVE ]: */
- u32 status;
-};
-
-struct i387_fxsave_struct {
- u16 cwd; /* Control Word */
- u16 swd; /* Status Word */
- u16 twd; /* Tag Word */
- u16 fop; /* Last Instruction Opcode */
- union {
- struct {
- u64 rip; /* Instruction Pointer */
- u64 rdp; /* Data Pointer */
- };
- struct {
- u32 fip; /* FPU IP Offset */
- u32 fcs; /* FPU IP Selector */
- u32 foo; /* FPU Operand Offset */
- u32 fos; /* FPU Operand Selector */
- };
- };
- u32 mxcsr; /* MXCSR Register State */
- u32 mxcsr_mask; /* MXCSR Mask */
-
- /* 8*16 bytes for each FP-reg = 128 bytes: */
- u32 st_space[32];
-
- /* 16*16 bytes for each XMM-reg = 256 bytes: */
- u32 xmm_space[64];
-
- u32 padding[12];
-
- union {
- u32 padding1[12];
- u32 sw_reserved[12];
- };
-
-} __attribute__((aligned(16)));
-
-struct i387_soft_struct {
- u32 cwd;
- u32 swd;
- u32 twd;
- u32 fip;
- u32 fcs;
- u32 foo;
- u32 fos;
- /* 8*10 bytes for each FP-reg = 80 bytes: */
- u32 st_space[20];
- u8 ftop;
- u8 changed;
- u8 lookahead;
- u8 no_update;
- u8 rm;
- u8 alimit;
- struct math_emu_info *info;
- u32 entry_eip;
-};
-
-struct ymmh_struct {
- /* 16 * 16 bytes for each YMMH-reg = 256 bytes */
- u32 ymmh_space[64];
-};
-
-/* We don't support LWP yet: */
-struct lwp_struct {
- u8 reserved[128];
-};
-
-struct bndreg {
- u64 lower_bound;
- u64 upper_bound;
-} __packed;
-
-struct bndcsr {
- u64 bndcfgu;
- u64 bndstatus;
-} __packed;
-
-struct xsave_hdr_struct {
- u64 xstate_bv;
- u64 xcomp_bv;
- u64 reserved[6];
-} __attribute__((packed));
-
-struct xsave_struct {
- struct i387_fxsave_struct i387;
- struct xsave_hdr_struct xsave_hdr;
- struct ymmh_struct ymmh;
- struct lwp_struct lwp;
- struct bndreg bndreg[4];
- struct bndcsr bndcsr;
- /* new processor state extensions will go here */
-} __attribute__ ((packed, aligned (64)));
-
-union thread_xstate {
- struct i387_fsave_struct fsave;
- struct i387_fxsave_struct fxsave;
- struct i387_soft_struct soft;
- struct xsave_struct xsave;
-};
-
-struct fpu {
- unsigned int last_cpu;
- unsigned int has_fpu;
- union thread_xstate *state;
-};
-
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(struct orig_ist, orig_ist);
@@ -483,8 +366,6 @@ DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
#endif /* X86_64 */
extern unsigned int xstate_size;
-extern void free_thread_xstate(struct task_struct *);
-extern struct kmem_cache *task_xstate_cachep;
struct perf_event;
@@ -508,6 +389,10 @@ struct thread_struct {
unsigned long fs;
#endif
unsigned long gs;
+
+ /* Floating point and extended processor state */
+ struct fpu fpu;
+
/* Save middle states of ptrace breakpoints */
struct perf_event *ptrace_bps[HBP_NUM];
/* Debug status used for traps, single steps, etc... */
@@ -518,8 +403,6 @@ struct thread_struct {
unsigned long cr2;
unsigned long trap_nr;
unsigned long error_code;
- /* floating point and extended processor state */
- struct fpu fpu;
#ifdef CONFIG_X86_32
/* Virtual 86 mode info */
struct vm86_struct __user *vm86_info;
@@ -535,15 +418,6 @@ struct thread_struct {
unsigned long iopl;
/* Max allowed port in the bitmap, in bytes: */
unsigned io_bitmap_max;
- /*
- * fpu_counter contains the number of consecutive context switches
- * that the FPU is used. If this is over a threshold, the lazy fpu
- * saving becomes unlazy to save the trap. This is an unsigned char
- * so that after 256 times the counter wraps and the behavior turns
- * lazy again; this to deal with bursty apps that only use FPU for
- * a short time
- */
- unsigned char fpu_counter;
};
/*
@@ -928,24 +802,25 @@ extern int get_tsc_mode(unsigned long adr);
extern int set_tsc_mode(unsigned int val);
/* Register/unregister a process' MPX related resource */
-#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk))
-#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk))
+#define MPX_ENABLE_MANAGEMENT() mpx_enable_management()
+#define MPX_DISABLE_MANAGEMENT() mpx_disable_management()
#ifdef CONFIG_X86_INTEL_MPX
-extern int mpx_enable_management(struct task_struct *tsk);
-extern int mpx_disable_management(struct task_struct *tsk);
+extern int mpx_enable_management(void);
+extern int mpx_disable_management(void);
#else
-static inline int mpx_enable_management(struct task_struct *tsk)
+static inline int mpx_enable_management(void)
{
return -EINVAL;
}
-static inline int mpx_disable_management(struct task_struct *tsk)
+static inline int mpx_disable_management(void)
{
return -EINVAL;
}
#endif /* CONFIG_X86_INTEL_MPX */
extern u16 amd_get_nb_id(int cpu);
+extern u32 amd_get_nodes_per_socket(void);
static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
{
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index a90f8972dad5..a4a77286cb1d 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -5,12 +5,14 @@
/* misc architecture specific prototypes */
-void system_call(void);
void syscall_init(void);
-void ia32_syscall(void);
-void ia32_cstar_target(void);
-void ia32_sysenter_target(void);
+void entry_SYSCALL_64(void);
+void entry_SYSCALL_compat(void);
+void entry_INT80_32(void);
+void entry_INT80_compat(void);
+void entry_SYSENTER_32(void);
+void entry_SYSENTER_compat(void);
void x86_configure_nx(void);
void x86_report_nx(void);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 19507ffa5d28..5fabf1362942 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -107,7 +107,7 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
static inline int user_mode(struct pt_regs *regs)
{
#ifdef CONFIG_X86_32
- return (regs->cs & SEGMENT_RPL_MASK) == USER_RPL;
+ return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL;
#else
return !!(regs->cs & 3);
#endif
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 6167fd798188..655e07a48f6c 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -41,5 +41,6 @@ struct pvclock_wall_clock {
#define PVCLOCK_TSC_STABLE_BIT (1 << 0)
#define PVCLOCK_GUEST_STOPPED (1 << 1)
+#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index d6b078e9fa28..628954ceede1 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -86,7 +86,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
offset = pvclock_get_nsec_offset(src);
ret = src->system_time + offset;
ret_flags = src->flags;
- rdtsc_barrier();
*cycles = ret;
*flags = ret_flags;
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
new file mode 100644
index 000000000000..9d51fae1cba3
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock.h
@@ -0,0 +1,57 @@
+#ifndef _ASM_X86_QSPINLOCK_H
+#define _ASM_X86_QSPINLOCK_H
+
+#include <asm/cpufeature.h>
+#include <asm-generic/qspinlock_types.h>
+#include <asm/paravirt.h>
+
+#define queued_spin_unlock queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * A smp_store_release() on the least-significant byte.
+ */
+static inline void native_queued_spin_unlock(struct qspinlock *lock)
+{
+ smp_store_release((u8 *)lock, 0);
+}
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+
+static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+ pv_queued_spin_lock_slowpath(lock, val);
+}
+
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ pv_queued_spin_unlock(lock);
+}
+#else
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ native_queued_spin_unlock(lock);
+}
+#endif
+
+#define virt_queued_spin_lock virt_queued_spin_lock
+
+static inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+ if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+ return false;
+
+ while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0)
+ cpu_relax();
+
+ return true;
+}
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_X86_QSPINLOCK_H */
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
new file mode 100644
index 000000000000..b002e711ba88
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_QSPINLOCK_PARAVIRT_H
+#define __ASM_QSPINLOCK_PARAVIRT_H
+
+PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
+
+#endif
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 5a9856eb12ba..7d5a1929d76b 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -231,11 +231,21 @@
#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8)
#ifdef __KERNEL__
+
+/*
+ * early_idt_handler_array is an array of entry points referenced in the
+ * early IDT. For simplicity, it's a real array with one entry point
+ * every nine bytes. That leaves room for an optional 'push $0' if the
+ * vector has no error code (two bytes), a 'push $vector_number' (two
+ * bytes), and a jump to the common entry code (up to five bytes).
+ */
+#define EARLY_IDT_HANDLER_SIZE 9
+
#ifndef __ASSEMBLY__
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
+extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
#ifdef CONFIG_TRACING
-# define trace_early_idt_handlers early_idt_handlers
+# define trace_early_idt_handler_array early_idt_handler_array
#endif
/*
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index f69e06b283fb..11af24e09c8a 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -60,17 +60,24 @@ static inline void x86_ce4100_early_setup(void) { }
#ifndef _SETUP
#include <asm/espfix.h>
+#include <linux/kernel.h>
/*
* This is set up by the setup-routine at boot-time
*/
extern struct boot_params boot_params;
+extern char _text[];
static inline bool kaslr_enabled(void)
{
return !!(boot_params.hdr.loadflags & KASLR_FLAG);
}
+static inline unsigned long kaslr_offset(void)
+{
+ return (unsigned long)&_text - __START_KERNEL;
+}
+
/*
* Do NOT EVER look at the BIOS memory size location.
* It does not work on many machines.
diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h
index ee80b92f0096..6c8a7ed13365 100644
--- a/arch/x86/include/asm/simd.h
+++ b/arch/x86/include/asm/simd.h
@@ -1,5 +1,5 @@
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
/*
* may_use_simd - whether it is allowable at this time to issue SIMD
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 17a8dced12da..222a6a3ca2b5 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -37,16 +37,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
-static inline struct cpumask *cpu_sibling_mask(int cpu)
-{
- return per_cpu(cpu_sibling_map, cpu);
-}
-
-static inline struct cpumask *cpu_core_mask(int cpu)
-{
- return per_cpu(cpu_core_map, cpu);
-}
-
static inline struct cpumask *cpu_llc_shared_mask(int cpu)
{
return per_cpu(cpu_llc_shared_map, cpu);
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index aeb4666e0c0a..2270e41b32fd 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -215,6 +215,44 @@ static inline void clwb(volatile void *__p)
: [pax] "a" (p));
}
+/**
+ * pcommit_sfence() - persistent commit and fence
+ *
+ * The PCOMMIT instruction ensures that data that has been flushed from the
+ * processor's cache hierarchy with CLWB, CLFLUSHOPT or CLFLUSH is accepted to
+ * memory and is durable on the DIMM. The primary use case for this is
+ * persistent memory.
+ *
+ * This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH and PCOMMIT
+ * with appropriate fencing.
+ *
+ * Example:
+ * void flush_and_commit_buffer(void *vaddr, unsigned int size)
+ * {
+ * unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+ * void *vend = vaddr + size;
+ * void *p;
+ *
+ * for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+ * p < vend; p += boot_cpu_data.x86_clflush_size)
+ * clwb(p);
+ *
+ * // SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes
+ * // MFENCE via mb() also works
+ * wmb();
+ *
+ * // PCOMMIT and the required SFENCE for ordering
+ * pcommit_sfence();
+ * }
+ *
+ * After this function completes the data pointed to by 'vaddr' has been
+ * accepted to memory and will be durable if the 'vaddr' points to persistent
+ * memory.
+ *
+ * PCOMMIT must always be ordered by an MFENCE or SFENCE, so to help simplify
+ * things we include both the PCOMMIT and the required SFENCE in the
+ * alternatives generated by pcommit_sfence().
+ */
static inline void pcommit_sfence(void)
{
alternative(ASM_NOP7,
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 64b611782ef0..be0a05913b91 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -42,6 +42,10 @@
extern struct static_key paravirt_ticketlocks_enabled;
static __always_inline bool static_key_false(struct static_key *key);
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm/qspinlock.h>
+#else
+
#ifdef CONFIG_PARAVIRT_SPINLOCKS
static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
@@ -196,6 +200,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
cpu_relax();
}
}
+#endif /* CONFIG_QUEUED_SPINLOCKS */
/*
* Read-write spinlocks, allowing multiple readers
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 5f9d7572d82b..65c3e37f879a 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -23,6 +23,9 @@ typedef u32 __ticketpair_t;
#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm-generic/qspinlock_types.h>
+#else
typedef struct arch_spinlock {
union {
__ticketpair_t head_tail;
@@ -33,6 +36,7 @@ typedef struct arch_spinlock {
} arch_spinlock_t;
#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
#include <asm-generic/qrwlock_types.h>
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 6a998598f172..c2e00bb2a136 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -39,7 +39,9 @@
#include <asm/processor.h>
#include <asm/percpu.h>
#include <asm/desc.h>
+
#include <linux/random.h>
+#include <linux/sched.h>
/*
* 24 byte read-only segment initializer for stack canary. Linker
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 552d6c90a6d4..d1793f06854d 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -7,7 +7,7 @@
#define _ASM_X86_SUSPEND_32_H
#include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
/* image of the saved processor state */
struct saved_context {
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index bc6232834bab..7ebf0ebe4e68 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -7,7 +7,7 @@
#define _ASM_X86_SUSPEND_64_H
#include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
/*
* Image of the saved processor state, used by the low level ACPI suspend to
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index b4bdec3e9523..225ee545e1a0 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -177,8 +177,6 @@ struct thread_info {
*/
#ifndef __ASSEMBLY__
-DECLARE_PER_CPU(unsigned long, kernel_stack);
-
static inline struct thread_info *current_thread_info(void)
{
return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE);
@@ -197,9 +195,13 @@ static inline unsigned long current_stack_pointer(void)
#else /* !__ASSEMBLY__ */
+#ifdef CONFIG_X86_64
+# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+#endif
+
/* Load thread_info address into "reg" */
#define GET_THREAD_INFO(reg) \
- _ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
+ _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
_ASM_SUB $(THREAD_SIZE),reg ;
/*
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 0e8f04f2c26f..0fb46482dfde 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -26,7 +26,7 @@
#define _ASM_X86_TOPOLOGY_H
#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
# define ENABLE_TOPO_DEFINES
# endif
#else
@@ -124,7 +124,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
#ifdef ENABLE_TOPO_DEFINES
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
#endif
static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 4cab890007a7..38a09a13a9bc 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -101,6 +101,12 @@ DEFINE_IRQ_VECTOR_EVENT(call_function_single);
DEFINE_IRQ_VECTOR_EVENT(threshold_apic);
/*
+ * deferred_error_apic - called when entering/exiting a deferred apic interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic);
+
+/*
* thermal_apic - called when entering/exiting a thermal apic interrupt
* vector handler
*/
diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h
new file mode 100644
index 000000000000..173dd3ba108c
--- /dev/null
+++ b/arch/x86/include/asm/trace/mpx.h
@@ -0,0 +1,132 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mpx
+
+#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MPX_H
+
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_X86_INTEL_MPX
+
+TRACE_EVENT(mpx_bounds_register_exception,
+
+ TP_PROTO(void *addr_referenced,
+ const struct bndreg *bndreg),
+ TP_ARGS(addr_referenced, bndreg),
+
+ TP_STRUCT__entry(
+ __field(void *, addr_referenced)
+ __field(u64, lower_bound)
+ __field(u64, upper_bound)
+ ),
+
+ TP_fast_assign(
+ __entry->addr_referenced = addr_referenced;
+ __entry->lower_bound = bndreg->lower_bound;
+ __entry->upper_bound = bndreg->upper_bound;
+ ),
+ /*
+ * Note that we are printing out the '~' of the upper
+ * bounds register here. It is actually stored in its
+ * one's complement form so that its 'init' state
+ * corresponds to all 0's. But, that looks like
+ * gibberish when printed out, so print out the 1's
+ * complement instead of the actual value here. Note
+ * though that you still need to specify filters for the
+ * actual value, not the displayed one.
+ */
+ TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx",
+ __entry->addr_referenced,
+ __entry->lower_bound,
+ ~__entry->upper_bound
+ )
+);
+
+TRACE_EVENT(bounds_exception_mpx,
+
+ TP_PROTO(const struct bndcsr *bndcsr),
+ TP_ARGS(bndcsr),
+
+ TP_STRUCT__entry(
+ __field(u64, bndcfgu)
+ __field(u64, bndstatus)
+ ),
+
+ TP_fast_assign(
+ /* need to get rid of the 'const' on bndcsr */
+ __entry->bndcfgu = (u64)bndcsr->bndcfgu;
+ __entry->bndstatus = (u64)bndcsr->bndstatus;
+ ),
+
+ TP_printk("bndcfgu:0x%llx bndstatus:0x%llx",
+ __entry->bndcfgu,
+ __entry->bndstatus)
+);
+
+DECLARE_EVENT_CLASS(mpx_range_trace,
+
+ TP_PROTO(unsigned long start,
+ unsigned long end),
+ TP_ARGS(start, end),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, start)
+ __field(unsigned long, end)
+ ),
+
+ TP_fast_assign(
+ __entry->start = start;
+ __entry->end = end;
+ ),
+
+ TP_printk("[0x%p:0x%p]",
+ (void *)__entry->start,
+ (void *)__entry->end
+ )
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap,
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end)
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_search,
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end)
+);
+
+TRACE_EVENT(mpx_new_bounds_table,
+
+ TP_PROTO(unsigned long table_vaddr),
+ TP_ARGS(table_vaddr),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, table_vaddr)
+ ),
+
+ TP_fast_assign(
+ __entry->table_vaddr = table_vaddr;
+ ),
+
+ TP_printk("table vaddr:%p", (void *)__entry->table_vaddr)
+);
+
+#else
+
+/*
+ * This gets used outside of MPX-specific code, so we need a stub.
+ */
+static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr)
+{
+}
+
+#endif /* CONFIG_X86_INTEL_MPX */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE mpx
+#endif /* _TRACE_MPX_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 4e49d7dff78e..c5380bea2a36 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -108,7 +108,8 @@ extern int panic_on_unrecovered_nmi;
void math_emulate(struct math_emu_info *);
#ifndef CONFIG_X86_32
asmlinkage void smp_thermal_interrupt(void);
-asmlinkage void mce_threshold_interrupt(void);
+asmlinkage void smp_threshold_interrupt(void);
+asmlinkage void smp_deferred_error_interrupt(void);
#endif
extern enum ctx_state ist_enter(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index ace9dec050b1..a8df874f3e88 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -74,7 +74,8 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
@@ -145,7 +146,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -240,7 +242,8 @@ extern void __put_user_8(void);
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
@@ -455,7 +458,8 @@ struct __large_struct { unsigned long buf[100]; };
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
@@ -479,7 +483,8 @@ struct __large_struct { unsigned long buf[100]; };
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 3c03a5de64d3..f5dcb5204dcd 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -59,6 +59,10 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
__put_user_size(*(u32 *)from, (u32 __user *)to,
4, ret, 4);
return ret;
+ case 8:
+ __put_user_size(*(u64 *)from, (u64 __user *)to,
+ 8, ret, 8);
+ return ret;
}
}
return __copy_to_user_ll(to, from, n);
@@ -70,7 +74,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
@@ -117,7 +122,8 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h
index ccab4af1646d..59a54e869f15 100644
--- a/arch/x86/include/asm/user.h
+++ b/arch/x86/include/asm/user.h
@@ -14,8 +14,8 @@ struct user_ymmh_regs {
__u32 ymmh_space[64];
};
-struct user_xsave_hdr {
- __u64 xstate_bv;
+struct user_xstate_header {
+ __u64 xfeatures;
__u64 reserved1[2];
__u64 reserved2[5];
};
@@ -41,11 +41,11 @@ struct user_xsave_hdr {
* particular process/thread.
*
* Also when the user modifies certain state FP/SSE/etc through the
- * ptrace interface, they must ensure that the xsave_hdr.xstate_bv
+ * ptrace interface, they must ensure that the header.xfeatures
* bytes[512..519] of the memory layout are updated correspondingly.
* i.e., for example when FP state is modified to a non-init state,
- * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to
- * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc.
+ * header.xfeatures's bit 0 must be set to '1', when SSE is modified to
+ * non-init state, header.xfeatures's bit 1 must to be set to '1', etc.
*/
#define USER_XSTATE_FX_SW_WORDS 6
#define USER_XSTATE_XCR0_WORD 0
@@ -55,7 +55,7 @@ struct user_xstateregs {
__u64 fpx_space[58];
__u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS];
} i387;
- struct user_xsave_hdr xsave_hdr;
+ struct user_xstate_header header;
struct user_ymmh_regs ymmh;
/* further processor state extensions go here */
};
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index f58a9c7a3c86..48d34d28f5a6 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -171,38 +171,17 @@ struct x86_platform_ops {
};
struct pci_dev;
-struct msi_msg;
struct x86_msi_ops {
int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
- void (*compose_msi_msg)(struct pci_dev *dev, unsigned int irq,
- unsigned int dest, struct msi_msg *msg,
- u8 hpet_id);
void (*teardown_msi_irq)(unsigned int irq);
void (*teardown_msi_irqs)(struct pci_dev *dev);
void (*restore_msi_irqs)(struct pci_dev *dev);
- int (*setup_hpet_msi)(unsigned int irq, unsigned int id);
};
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_data;
-struct cpumask;
-
struct x86_io_apic_ops {
- void (*init) (void);
unsigned int (*read) (unsigned int apic, unsigned int reg);
- void (*write) (unsigned int apic, unsigned int reg, unsigned int value);
- void (*modify) (unsigned int apic, unsigned int reg, unsigned int value);
void (*disable)(void);
- void (*print_entries)(unsigned int apic, unsigned int nr_entries);
- int (*set_affinity)(struct irq_data *data,
- const struct cpumask *mask,
- bool force);
- int (*setup_entry)(int irq, struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr);
- void (*eoi_ioapic_pin)(int apic, int pin, int vector);
};
extern struct x86_init_ops x86_init;
diff --git a/arch/x86/include/asm/xcr.h b/arch/x86/include/asm/xcr.h
deleted file mode 100644
index f2cba4e79a23..000000000000
--- a/arch/x86/include/asm/xcr.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- * Copyright 2008 rPath, Inc. - All Rights Reserved
- *
- * This file is part of the Linux kernel, and is made available under
- * the terms of the GNU General Public License version 2 or (at your
- * option) any later version; incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * asm-x86/xcr.h
- *
- * Definitions for the eXtended Control Register instructions
- */
-
-#ifndef _ASM_X86_XCR_H
-#define _ASM_X86_XCR_H
-
-#define XCR_XFEATURE_ENABLED_MASK 0x00000000
-
-#ifdef __KERNEL__
-# ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-
-static inline u64 xgetbv(u32 index)
-{
- u32 eax, edx;
-
- asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
- : "=a" (eax), "=d" (edx)
- : "c" (index));
- return eax + ((u64)edx << 32);
-}
-
-static inline void xsetbv(u32 index, u64 value)
-{
- u32 eax = value;
- u32 edx = value >> 32;
-
- asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
- : : "a" (eax), "d" (edx), "c" (index));
-}
-
-# endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_XCR_H */
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
index d8829751b3f8..1f5c5161ead6 100644
--- a/arch/x86/include/asm/xor.h
+++ b/arch/x86/include/asm/xor.h
@@ -36,7 +36,7 @@
* no advantages to be gotten from x86-64 here anyways.
*/
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#ifdef CONFIG_X86_32
/* reduce register pressure */
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index ce05722e3c68..5a08bc8bff33 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -26,7 +26,7 @@
#define XO3(x, y) " pxor 8*("#x")(%4), %%mm"#y" ;\n"
#define XO4(x, y) " pxor 8*("#x")(%5), %%mm"#y" ;\n"
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
static void
xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 492b29802f57..7c0a517ec751 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -18,7 +18,7 @@
#ifdef CONFIG_AS_AVX
#include <linux/compiler.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#define BLOCK4(i) \
BLOCK(32 * i, 0) \
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
deleted file mode 100644
index c9a6d68b8d62..000000000000
--- a/arch/x86/include/asm/xsave.h
+++ /dev/null
@@ -1,257 +0,0 @@
-#ifndef __ASM_X86_XSAVE_H
-#define __ASM_X86_XSAVE_H
-
-#include <linux/types.h>
-#include <asm/processor.h>
-
-#define XSTATE_CPUID 0x0000000d
-
-#define XSTATE_FP 0x1
-#define XSTATE_SSE 0x2
-#define XSTATE_YMM 0x4
-#define XSTATE_BNDREGS 0x8
-#define XSTATE_BNDCSR 0x10
-#define XSTATE_OPMASK 0x20
-#define XSTATE_ZMM_Hi256 0x40
-#define XSTATE_Hi16_ZMM 0x80
-
-#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE)
-#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-/* Bit 63 of XCR0 is reserved for future expansion */
-#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63)))
-
-#define FXSAVE_SIZE 512
-
-#define XSAVE_HDR_SIZE 64
-#define XSAVE_HDR_OFFSET FXSAVE_SIZE
-
-#define XSAVE_YMM_SIZE 256
-#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
-
-/* Supported features which support lazy state saving */
-#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
- | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-
-/* Supported features which require eager state saving */
-#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR)
-
-/* All currently supported features */
-#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER)
-
-#ifdef CONFIG_X86_64
-#define REX_PREFIX "0x48, "
-#else
-#define REX_PREFIX
-#endif
-
-extern unsigned int xstate_size;
-extern u64 pcntxt_mask;
-extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
-extern struct xsave_struct *init_xstate_buf;
-
-extern void xsave_init(void);
-extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
-extern int init_fpu(struct task_struct *child);
-
-/* These macros all use (%edi)/(%rdi) as the single memory argument. */
-#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
-#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
-#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
-#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
-#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
-
-#define xstate_fault ".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err)
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err = 0;
-
- WARN_ON(system_state != SYSTEM_BOOTING);
-
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- asm volatile("1:"XSAVES"\n\t"
- "2:\n\t"
- xstate_fault
- : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
- else
- asm volatile("1:"XSAVE"\n\t"
- "2:\n\t"
- xstate_fault
- : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
- return err;
-}
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err = 0;
-
- WARN_ON(system_state != SYSTEM_BOOTING);
-
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- asm volatile("1:"XRSTORS"\n\t"
- "2:\n\t"
- xstate_fault
- : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
- else
- asm volatile("1:"XRSTOR"\n\t"
- "2:\n\t"
- xstate_fault
- : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
- return err;
-}
-
-/*
- * Save processor xstate to xsave area.
- */
-static inline int xsave_state(struct xsave_struct *fx, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err = 0;
-
- /*
- * If xsaves is enabled, xsaves replaces xsaveopt because
- * it supports compact format and supervisor states in addition to
- * modified optimization in xsaveopt.
- *
- * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
- * because xsaveopt supports modified optimization which is not
- * supported by xsave.
- *
- * If none of xsaves and xsaveopt is enabled, use xsave.
- */
- alternative_input_2(
- "1:"XSAVE,
- XSAVEOPT,
- X86_FEATURE_XSAVEOPT,
- XSAVES,
- X86_FEATURE_XSAVES,
- [fx] "D" (fx), "a" (lmask), "d" (hmask) :
- "memory");
- asm volatile("2:\n\t"
- xstate_fault
- : "0" (0)
- : "memory");
-
- return err;
-}
-
-/*
- * Restore processor xstate from xsave area.
- */
-static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
-{
- int err = 0;
- u32 lmask = mask;
- u32 hmask = mask >> 32;
-
- /*
- * Use xrstors to restore context if it is enabled. xrstors supports
- * compacted format of xsave area which is not supported by xrstor.
- */
- alternative_input(
- "1: " XRSTOR,
- XRSTORS,
- X86_FEATURE_XSAVES,
- "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
-
- asm volatile("2:\n"
- xstate_fault
- : "0" (0)
- : "memory");
-
- return err;
-}
-
-/*
- * Save xstate context for old process during context switch.
- */
-static inline void fpu_xsave(struct fpu *fpu)
-{
- xsave_state(&fpu->state->xsave, -1);
-}
-
-/*
- * Restore xstate context for new process during context switch.
- */
-static inline int fpu_xrstor_checking(struct xsave_struct *fx)
-{
- return xrstor_state(fx, -1);
-}
-
-/*
- * Save xstate to user space xsave area.
- *
- * We don't use modified optimization because xrstor/xrstors might track
- * a different application.
- *
- * We don't use compacted format xsave area for
- * backward compatibility for old applications which don't understand
- * compacted format of xsave area.
- */
-static inline int xsave_user(struct xsave_struct __user *buf)
-{
- int err;
-
- /*
- * Clear the xsave header first, so that reserved fields are
- * initialized to zero.
- */
- err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
- if (unlikely(err))
- return -EFAULT;
-
- __asm__ __volatile__(ASM_STAC "\n"
- "1:"XSAVE"\n"
- "2: " ASM_CLAC "\n"
- xstate_fault
- : "D" (buf), "a" (-1), "d" (-1), "0" (0)
- : "memory");
- return err;
-}
-
-/*
- * Restore xstate from user space xsave area.
- */
-static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
-{
- int err = 0;
- struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
- u32 lmask = mask;
- u32 hmask = mask >> 32;
-
- __asm__ __volatile__(ASM_STAC "\n"
- "1:"XRSTOR"\n"
- "2: " ASM_CLAC "\n"
- xstate_fault
- : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
- : "memory"); /* memory required? */
- return err;
-}
-
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate);
-void setup_xstate_comp(void);
-
-#endif
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index d7dcef58aefa..a4ae82eb82aa 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -106,6 +106,8 @@ struct kvm_ioapic_state {
#define KVM_IRQCHIP_IOAPIC 2
#define KVM_NR_IRQCHIPS 3
+#define KVM_RUN_X86_SMM (1 << 0)
+
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
@@ -281,6 +283,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001
#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
+#define KVM_VCPUEVENT_VALID_SMM 0x00000008
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -309,7 +312,13 @@ struct kvm_vcpu_events {
} nmi;
__u32 sipi_vector;
__u32 flags;
- __u32 reserved[10];
+ struct {
+ __u8 smm;
+ __u8 pending;
+ __u8 smm_inside_nmi;
+ __u8 latched_init;
+ } smi;
+ __u32 reserved[9];
};
/* for KVM_GET/SET_DEBUGREGS */
@@ -345,4 +354,7 @@ struct kvm_xcrs {
struct kvm_sync_regs {
};
+#define KVM_QUIRK_LINT0_REENABLED (1 << 0)
+#define KVM_QUIRK_CD_NW_CLEARED (1 << 1)
+
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h
index 155e51048fa4..c41f4fe25483 100644
--- a/arch/x86/include/uapi/asm/msr.h
+++ b/arch/x86/include/uapi/asm/msr.h
@@ -1,8 +1,6 @@
#ifndef _UAPI_ASM_X86_MSR_H
#define _UAPI_ASM_X86_MSR_H
-#include <asm/msr-index.h>
-
#ifndef __ASSEMBLY__
#include <linux/types.h>
diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h
index d0acb658c8f4..7528dcf59691 100644
--- a/arch/x86/include/uapi/asm/mtrr.h
+++ b/arch/x86/include/uapi/asm/mtrr.h
@@ -103,7 +103,7 @@ struct mtrr_state_type {
#define MTRRIOC_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
#define MTRRIOC_KILL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry)
-/* These are the region types */
+/* MTRR memory types, which are defined in SDM */
#define MTRR_TYPE_UNCACHABLE 0
#define MTRR_TYPE_WRCOMB 1
/*#define MTRR_TYPE_ 2*/
@@ -113,5 +113,11 @@ struct mtrr_state_type {
#define MTRR_TYPE_WRBACK 6
#define MTRR_NUM_TYPES 7
+/*
+ * Invalid MTRR memory type. mtrr_type_lookup() returns this value when
+ * MTRRs are disabled. Note, this value is allocated from the reserved
+ * values (0x7-0xff) of the MTRR memory types.
+ */
+#define MTRR_TYPE_INVALID 0xff
#endif /* _UAPI_ASM_X86_MTRR_H */
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 16dc4e8a2cd3..0e8a973de9ee 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -25,7 +25,7 @@ struct _fpx_sw_bytes {
__u32 extended_size; /* total size of the layout referred by
* fpstate pointer in the sigcontext.
*/
- __u64 xstate_bv;
+ __u64 xfeatures;
/* feature bit mask (including fp/sse/extended
* state) that is present in the memory
* layout.
@@ -209,8 +209,8 @@ struct sigcontext {
#endif /* !__i386__ */
-struct _xsave_hdr {
- __u64 xstate_bv;
+struct _header {
+ __u64 xfeatures;
__u64 reserved1[2];
__u64 reserved2[5];
};
@@ -228,7 +228,7 @@ struct _ymmh_state {
*/
struct _xstate {
struct _fpstate fpstate;
- struct _xsave_hdr xstate_hdr;
+ struct _header xstate_hdr;
struct _ymmh_state ymmh;
/* new processor state extensions go here */
};
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9bcd0b56ca17..0f15af41bd80 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -22,7 +22,7 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n
CFLAGS_irq.o := -I$(src)/../include/asm/trace
-obj-y := process_$(BITS).o signal.o entry_$(BITS).o
+obj-y := process_$(BITS).o signal.o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o
obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o
@@ -31,9 +31,6 @@ obj-y += probe_roms.o
obj-$(CONFIG_X86_32) += i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += mcount_64.o
-obj-y += syscall_$(BITS).o vsyscall_gtod.o
-obj-$(CONFIG_IA32_EMULATION) += syscall_32.o
-obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
@@ -44,7 +41,7 @@ obj-y += pci-iommu_table.o
obj-y += resource.o
obj-y += process.o
-obj-y += i387.o xsave.o
+obj-y += fpu/
obj-y += ptrace.o
obj-$(CONFIG_X86_32) += tls.o
obj-$(CONFIG_IA32_EMULATION) += tls.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dbe76a14c3c9..e49ee24da85e 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -31,12 +31,12 @@
#include <linux/module.h>
#include <linux/dmi.h>
#include <linux/irq.h>
-#include <linux/irqdomain.h>
#include <linux/slab.h>
#include <linux/bootmem.h>
#include <linux/ioport.h>
#include <linux/pci.h>
+#include <asm/irqdomain.h>
#include <asm/pci_x86.h>
#include <asm/pgtable.h>
#include <asm/io_apic.h>
@@ -400,57 +400,13 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
return 0;
}
-static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
- int polarity)
-{
- int irq, node;
-
- if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
- return gsi;
-
- trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
- polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
- node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
- if (mp_set_gsi_attr(gsi, trigger, polarity, node)) {
- pr_warn("Failed to set pin attr for GSI%d\n", gsi);
- return -1;
- }
-
- irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC);
- if (irq < 0)
- return irq;
-
- /* Don't set up the ACPI SCI because it's already set up */
- if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi)
- mp_config_acpi_gsi(dev, gsi, trigger, polarity);
-
- return irq;
-}
-
-static void mp_unregister_gsi(u32 gsi)
-{
- int irq;
-
- if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
- return;
-
- irq = mp_map_gsi_to_irq(gsi, 0);
- if (irq > 0)
- mp_unmap_irq(irq);
-}
-
-static struct irq_domain_ops acpi_irqdomain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
-};
-
static int __init
acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
{
struct acpi_madt_io_apic *ioapic = NULL;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_DYNAMIC,
- .ops = &acpi_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
ioapic = (struct acpi_madt_io_apic *)header;
@@ -652,7 +608,7 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi,
* Make sure all (legacy) PCI IRQs are set as level-triggered.
*/
if (trigger == ACPI_LEVEL_SENSITIVE)
- eisa_set_level_irq(gsi);
+ elcr_set_level_irq(gsi);
#endif
return gsi;
@@ -663,10 +619,21 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
int trigger, int polarity)
{
int irq = gsi;
-
#ifdef CONFIG_X86_IO_APIC
+ int node;
+ struct irq_alloc_info info;
+
+ node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
+ trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
+ polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
+ ioapic_set_alloc_attr(&info, node, trigger, polarity);
+
mutex_lock(&acpi_ioapic_lock);
- irq = mp_register_gsi(dev, gsi, trigger, polarity);
+ irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
+ /* Don't set up the ACPI SCI because it's already set up */
+ if (irq >= 0 && enable_update_mptable &&
+ acpi_gbl_FADT.sci_interrupt != gsi)
+ mp_config_acpi_gsi(dev, gsi, trigger, polarity);
mutex_unlock(&acpi_ioapic_lock);
#endif
@@ -676,8 +643,12 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
static void acpi_unregister_gsi_ioapic(u32 gsi)
{
#ifdef CONFIG_X86_IO_APIC
+ int irq;
+
mutex_lock(&acpi_ioapic_lock);
- mp_unregister_gsi(gsi);
+ irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+ if (irq > 0)
+ mp_unmap_irq(irq);
mutex_unlock(&acpi_ioapic_lock);
#endif
}
@@ -786,7 +757,7 @@ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
u64 addr;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_DYNAMIC,
- .ops = &acpi_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr);
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 665c6b7d2ea9..0c26b1b44e51 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -12,11 +12,13 @@ ENTRY(wakeup_pmode_return)
wakeup_pmode_return:
movw $__KERNEL_DS, %ax
movw %ax, %ss
- movw %ax, %ds
- movw %ax, %es
movw %ax, %fs
movw %ax, %gs
+ movw $__USER_DS, %ax
+ movw %ax, %ds
+ movw %ax, %es
+
# reload the gdt, as we need the full 32 bit address
lidt saved_idt
lldt saved_ldt
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index ae693b51ed8e..8c35df468104 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -62,7 +62,7 @@ ENTRY(do_suspend_lowlevel)
pushfq
popq pt_regs_flags(%rax)
- movq $resume_point, saved_rip(%rip)
+ movq $.Lresume_point, saved_rip(%rip)
movq %rsp, saved_rsp
movq %rbp, saved_rbp
@@ -75,10 +75,10 @@ ENTRY(do_suspend_lowlevel)
xorl %eax, %eax
call x86_acpi_enter_sleep_state
/* in case something went wrong, restore the machine status and go on */
- jmp resume_point
+ jmp .Lresume_point
.align 4
-resume_point:
+.Lresume_point:
/* We don't restore %rax, it must be 0 anyway */
movq $saved_context, %rax
movq saved_context_cr4(%rax), %rbx
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index aef653193160..c42827eb86cf 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -21,6 +21,10 @@
#include <asm/io.h>
#include <asm/fixmap.h>
+int __read_mostly alternatives_patched;
+
+EXPORT_SYMBOL_GPL(alternatives_patched);
+
#define MAX_PATCH_LEN (255-1)
static int __initdata_or_module debug_alternative;
@@ -227,6 +231,15 @@ void __init arch_init_ideal_nops(void)
#endif
}
break;
+
+ case X86_VENDOR_AMD:
+ if (boot_cpu_data.x86 > 0xf) {
+ ideal_nops = p6_nops;
+ return;
+ }
+
+ /* fall through */
+
default:
#ifdef CONFIG_X86_64
ideal_nops = k8_nops;
@@ -627,6 +640,7 @@ void __init alternative_instructions(void)
apply_paravirt(__parainstructions, __parainstructions_end);
restart_nmi();
+ alternatives_patched = 1;
}
/**
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 5caed1dd7ccf..29fa475ec518 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -89,9 +89,7 @@ int amd_cache_northbridges(void)
next_northbridge(link, amd_nb_link_ids);
}
- /* GART present only on Fam15h upto model 0fh */
- if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
- (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
+ if (amd_gart_present())
amd_northbridges.flags |= AMD_NB_GART;
/*
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 6a7c23ff21d3..ede92c3364d3 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -171,10 +171,6 @@ static int __init apbt_clockevent_register(void)
static void apbt_setup_irq(struct apbt_dev *adev)
{
- /* timer0 irq has been setup early */
- if (adev->irq == 0)
- return;
-
irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
}
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 76164e173a24..6e85f713641d 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -262,6 +262,9 @@ void __init early_gart_iommu_check(void)
u64 aper_base = 0, last_aper_base = 0;
int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0;
+ if (!amd_gart_present())
+ return;
+
if (!early_pci_allowed())
return;
@@ -355,6 +358,9 @@ int __init gart_iommu_hole_init(void)
int fix, slot, valid_agp = 0;
int i, node;
+ if (!amd_gart_present())
+ return -ENODEV;
+
if (gart_iommu_aperture_disabled || !fix_aperture ||
!early_pci_allowed())
return -ENODEV;
@@ -452,7 +458,7 @@ out:
force_iommu ||
valid_agp ||
fallback_aper_force) {
- pr_info("Your BIOS doesn't leave a aperture memory hole\n");
+ pr_info("Your BIOS doesn't leave an aperture memory hole\n");
pr_info("Please enable the IOMMU option in the BIOS setup\n");
pr_info("This costs you %dMB of RAM\n",
32 << fallback_aper_order);
diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c
index 816f36e979ad..ae50d3454d78 100644
--- a/arch/x86/kernel/apic/htirq.c
+++ b/arch/x86/kernel/apic/htirq.c
@@ -3,6 +3,8 @@
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Add support of hierarchical irqdomain
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -14,78 +16,112 @@
#include <linux/device.h>
#include <linux/pci.h>
#include <linux/htirq.h>
+#include <asm/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/hypertransport.h>
+static struct irq_domain *htirq_domain;
+
/*
* Hypertransport interrupt support
*/
-static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
-{
- struct ht_irq_msg msg;
-
- fetch_ht_irq_msg(irq, &msg);
-
- msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
- msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
-
- msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
- msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
-
- write_ht_irq_msg(irq, &msg);
-}
-
static int
ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest;
+ struct irq_data *parent = data->parent_data;
int ret;
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- target_ht_irq(data->irq, dest, cfg->vector);
- return IRQ_SET_MASK_OK_NOCOPY;
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret >= 0) {
+ struct ht_irq_msg msg;
+ struct irq_cfg *cfg = irqd_cfg(data);
+
+ fetch_ht_irq_msg(data->irq, &msg);
+ msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK |
+ HT_IRQ_LOW_DEST_ID_MASK);
+ msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) |
+ HT_IRQ_LOW_DEST_ID(cfg->dest_apicid);
+ msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+ msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
+ write_ht_irq_msg(data->irq, &msg);
+ }
+
+ return ret;
}
static struct irq_chip ht_irq_chip = {
.name = "PCI-HT",
.irq_mask = mask_ht_irq,
.irq_unmask = unmask_ht_irq,
- .irq_ack = apic_ack_edge,
+ .irq_ack = irq_chip_ack_parent,
.irq_set_affinity = ht_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
+static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- struct irq_cfg *cfg;
- struct ht_irq_msg msg;
- unsigned dest;
- int err;
+ struct ht_irq_cfg *ht_cfg;
+ struct irq_alloc_info *info = arg;
+ struct pci_dev *dev;
+ irq_hw_number_t hwirq;
+ int ret;
- if (disable_apic)
- return -ENXIO;
+ if (nr_irqs > 1 || !info)
+ return -EINVAL;
- cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, apic->target_cpus());
- if (err)
- return err;
+ dev = info->ht_dev;
+ hwirq = (info->ht_idx & 0xFF) |
+ PCI_DEVID(dev->bus->number, dev->devfn) << 8 |
+ (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24;
+ if (irq_find_mapping(domain, hwirq) > 0)
+ return -EEXIST;
- err = apic->cpu_mask_to_apicid_and(cfg->domain,
- apic->target_cpus(), &dest);
- if (err)
- return err;
+ ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL);
+ if (!ht_cfg)
+ return -ENOMEM;
- msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+ if (ret < 0) {
+ kfree(ht_cfg);
+ return ret;
+ }
+
+ /* Initialize msg to a value that will never match the first write. */
+ ht_cfg->msg.address_lo = 0xffffffff;
+ ht_cfg->msg.address_hi = 0xffffffff;
+ ht_cfg->dev = info->ht_dev;
+ ht_cfg->update = info->ht_update;
+ ht_cfg->pos = info->ht_pos;
+ ht_cfg->idx = 0x10 + (info->ht_idx * 2);
+ irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg,
+ handle_edge_irq, ht_cfg, "edge");
+
+ return 0;
+}
+
+static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
+{
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+ BUG_ON(nr_irqs != 1);
+ kfree(irq_data->chip_data);
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
+}
+static void htirq_domain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct ht_irq_msg msg;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
+
+ msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
msg.address_lo =
HT_IRQ_LOW_BASE |
- HT_IRQ_LOW_DEST_ID(dest) |
+ HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
HT_IRQ_LOW_VECTOR(cfg->vector) |
((apic->irq_dest_mode == 0) ?
HT_IRQ_LOW_DM_PHYSICAL :
@@ -95,13 +131,56 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
HT_IRQ_LOW_MT_FIXED :
HT_IRQ_LOW_MT_ARBITRATED) |
HT_IRQ_LOW_IRQ_MASKED;
+ write_ht_irq_msg(irq_data->irq, &msg);
+}
- write_ht_irq_msg(irq, &msg);
+static void htirq_domain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct ht_irq_msg msg;
- irq_set_chip_and_handler_name(irq, &ht_irq_chip,
- handle_edge_irq, "edge");
+ memset(&msg, 0, sizeof(msg));
+ write_ht_irq_msg(irq_data->irq, &msg);
+}
- dev_dbg(&dev->dev, "irq %d for HT\n", irq);
+static const struct irq_domain_ops htirq_domain_ops = {
+ .alloc = htirq_domain_alloc,
+ .free = htirq_domain_free,
+ .activate = htirq_domain_activate,
+ .deactivate = htirq_domain_deactivate,
+};
- return 0;
+void arch_init_htirq_domain(struct irq_domain *parent)
+{
+ if (disable_apic)
+ return;
+
+ htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL);
+ if (!htirq_domain)
+ pr_warn("failed to initialize irqdomain for HTIRQ.\n");
+ else
+ htirq_domain->parent = parent;
+}
+
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+ ht_irq_update_t *update)
+{
+ struct irq_alloc_info info;
+
+ if (!htirq_domain)
+ return -ENOSYS;
+
+ init_irq_alloc_info(&info, NULL);
+ info.ht_idx = idx;
+ info.ht_pos = pos;
+ info.ht_dev = dev;
+ info.ht_update = update;
+
+ return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev),
+ &info);
+}
+
+void arch_teardown_ht_irq(unsigned int irq)
+{
+ irq_domain_free_irqs(irq, 1);
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f4dc2462a1ac..845dc0df2002 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -18,6 +18,16 @@
* and Rolf G. Tews
* for testing these extensively
* Paul Diefenbaugh : Added full ACPI support
+ *
+ * Historical information which is worth to be preserved:
+ *
+ * - SiS APIC rmw bug:
+ *
+ * We used to have a workaround for a bug in SiS chips which
+ * required to rewrite the index register for a read-modify-write
+ * operation as the chip lost the index information which was
+ * setup for the read already. We cache the data now, so that
+ * workaround has been removed.
*/
#include <linux/mm.h>
@@ -31,13 +41,13 @@
#include <linux/acpi.h>
#include <linux/module.h>
#include <linux/syscore_ops.h>
-#include <linux/irqdomain.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/jiffies.h> /* time_after() */
#include <linux/slab.h>
#include <linux/bootmem.h>
+#include <asm/irqdomain.h>
#include <asm/idle.h>
#include <asm/io.h>
#include <asm/smp.h>
@@ -63,27 +73,31 @@
#define for_each_ioapic_pin(idx, pin) \
for_each_ioapic((idx)) \
for_each_pin((idx), (pin))
-
#define for_each_irq_pin(entry, head) \
list_for_each_entry(entry, &head, list)
-/*
- * Is the SiS APIC rmw bug present ?
- * -1 = don't know, 0 = no, 1 = yes
- */
-int sis_apic_bug = -1;
-
static DEFINE_RAW_SPINLOCK(ioapic_lock);
static DEFINE_MUTEX(ioapic_mutex);
static unsigned int ioapic_dynirq_base;
static int ioapic_initialized;
-struct mp_pin_info {
+struct irq_pin_list {
+ struct list_head list;
+ int apic, pin;
+};
+
+struct mp_chip_data {
+ struct list_head irq_2_pin;
+ struct IO_APIC_route_entry entry;
int trigger;
int polarity;
- int node;
- int set;
u32 count;
+ bool isa_irq;
+};
+
+struct mp_ioapic_gsi {
+ u32 gsi_base;
+ u32 gsi_end;
};
static struct ioapic {
@@ -101,7 +115,6 @@ static struct ioapic {
struct mp_ioapic_gsi gsi_config;
struct ioapic_domain_cfg irqdomain_cfg;
struct irq_domain *irqdomain;
- struct mp_pin_info *pin_info;
struct resource *iomem_res;
} ioapics[MAX_IO_APICS];
@@ -117,7 +130,7 @@ unsigned int mpc_ioapic_addr(int ioapic_idx)
return ioapics[ioapic_idx].mp_config.apicaddr;
}
-struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
+static inline struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
{
return &ioapics[ioapic_idx].gsi_config;
}
@@ -129,11 +142,16 @@ static inline int mp_ioapic_pin_count(int ioapic)
return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
}
-u32 mp_pin_to_gsi(int ioapic, int pin)
+static inline u32 mp_pin_to_gsi(int ioapic, int pin)
{
return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin;
}
+static inline bool mp_is_legacy_irq(int irq)
+{
+ return irq >= 0 && irq < nr_legacy_irqs();
+}
+
/*
* Initialize all legacy IRQs and all pins on the first IOAPIC
* if we have legacy interrupt controller. Kernel boot option "pirq="
@@ -144,12 +162,7 @@ static inline int mp_init_irq_at_boot(int ioapic, int irq)
if (!nr_legacy_irqs())
return 0;
- return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs());
-}
-
-static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin)
-{
- return ioapics[ioapic_idx].pin_info + pin;
+ return ioapic == 0 || mp_is_legacy_irq(irq);
}
static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic)
@@ -216,16 +229,6 @@ void mp_save_irq(struct mpc_intsrc *m)
panic("Max # of irq sources exceeded!!\n");
}
-struct irq_pin_list {
- struct list_head list;
- int apic, pin;
-};
-
-static struct irq_pin_list *alloc_irq_pin_list(int node)
-{
- return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
-}
-
static void alloc_ioapic_saved_registers(int idx)
{
size_t size;
@@ -247,8 +250,7 @@ static void free_ioapic_saved_registers(int idx)
int __init arch_early_ioapic_init(void)
{
- struct irq_cfg *cfg;
- int i, node = cpu_to_node(0);
+ int i;
if (!nr_legacy_irqs())
io_apic_irqs = ~0UL;
@@ -256,16 +258,6 @@ int __init arch_early_ioapic_init(void)
for_each_ioapic(i)
alloc_ioapic_saved_registers(i);
- /*
- * For legacy IRQ's, start with assigning irq0 to irq15 to
- * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
- */
- for (i = 0; i < nr_legacy_irqs(); i++) {
- cfg = alloc_irq_and_cfg_at(i, node);
- cfg->vector = IRQ0_VECTOR + i;
- cpumask_setall(cfg->domain);
- }
-
return 0;
}
@@ -283,7 +275,7 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
+ (mpc_ioapic_addr(idx) & ~PAGE_MASK);
}
-void io_apic_eoi(unsigned int apic, unsigned int vector)
+static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(vector, &io_apic->eoi);
@@ -296,7 +288,8 @@ unsigned int native_io_apic_read(unsigned int apic, unsigned int reg)
return readl(&io_apic->data);
}
-void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void io_apic_write(unsigned int apic, unsigned int reg,
+ unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
@@ -304,21 +297,6 @@ void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int valu
writel(value, &io_apic->data);
}
-/*
- * Re-write a value: to be used for read-modify-write
- * cycles where the read already set up the index register.
- *
- * Older SiS APIC requires we rewrite the index register
- */
-void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
- struct io_apic __iomem *io_apic = io_apic_base(apic);
-
- if (sis_apic_bug)
- writel(reg, &io_apic->index);
- writel(value, &io_apic->data);
-}
-
union entry_union {
struct { u32 w1, w2; };
struct IO_APIC_route_entry entry;
@@ -378,7 +356,7 @@ static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
static void ioapic_mask_entry(int apic, int pin)
{
unsigned long flags;
- union entry_union eu = { .entry.mask = 1 };
+ union entry_union eu = { .entry.mask = IOAPIC_MASKED };
raw_spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic, 0x10 + 2*pin, eu.w1);
@@ -391,16 +369,17 @@ static void ioapic_mask_entry(int apic, int pin)
* shared ISA-space IRQs, so we have to support them. We are super
* fast in the common case, and fast for shared ISA-space IRQs.
*/
-static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct mp_chip_data *data,
+ int node, int apic, int pin)
{
struct irq_pin_list *entry;
/* don't allow duplicates */
- for_each_irq_pin(entry, cfg->irq_2_pin)
+ for_each_irq_pin(entry, data->irq_2_pin)
if (entry->apic == apic && entry->pin == pin)
return 0;
- entry = alloc_irq_pin_list(node);
+ entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node);
if (!entry) {
pr_err("can not alloc irq_pin_list (%d,%d,%d)\n",
node, apic, pin);
@@ -408,16 +387,16 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi
}
entry->apic = apic;
entry->pin = pin;
+ list_add_tail(&entry->list, &data->irq_2_pin);
- list_add_tail(&entry->list, &cfg->irq_2_pin);
return 0;
}
-static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
+static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin)
{
struct irq_pin_list *tmp, *entry;
- list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list)
+ list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list)
if (entry->apic == apic && entry->pin == pin) {
list_del(&entry->list);
kfree(entry);
@@ -425,22 +404,23 @@ static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
}
}
-static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static void add_pin_to_irq_node(struct mp_chip_data *data,
+ int node, int apic, int pin)
{
- if (__add_pin_to_irq_node(cfg, node, apic, pin))
+ if (__add_pin_to_irq_node(data, node, apic, pin))
panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
}
/*
* Reroute an IRQ to a different pin.
*/
-static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
+static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node,
int oldapic, int oldpin,
int newapic, int newpin)
{
struct irq_pin_list *entry;
- for_each_irq_pin(entry, cfg->irq_2_pin) {
+ for_each_irq_pin(entry, data->irq_2_pin) {
if (entry->apic == oldapic && entry->pin == oldpin) {
entry->apic = newapic;
entry->pin = newpin;
@@ -450,32 +430,26 @@ static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
}
/* old apic/pin didn't exist, so just add new ones */
- add_pin_to_irq_node(cfg, node, newapic, newpin);
-}
-
-static void __io_apic_modify_irq(struct irq_pin_list *entry,
- int mask_and, int mask_or,
- void (*final)(struct irq_pin_list *entry))
-{
- unsigned int reg, pin;
-
- pin = entry->pin;
- reg = io_apic_read(entry->apic, 0x10 + pin * 2);
- reg &= mask_and;
- reg |= mask_or;
- io_apic_modify(entry->apic, 0x10 + pin * 2, reg);
- if (final)
- final(entry);
+ add_pin_to_irq_node(data, node, newapic, newpin);
}
-static void io_apic_modify_irq(struct irq_cfg *cfg,
+static void io_apic_modify_irq(struct mp_chip_data *data,
int mask_and, int mask_or,
void (*final)(struct irq_pin_list *entry))
{
+ union entry_union eu;
struct irq_pin_list *entry;
- for_each_irq_pin(entry, cfg->irq_2_pin)
- __io_apic_modify_irq(entry, mask_and, mask_or, final);
+ eu.entry = data->entry;
+ eu.w1 &= mask_and;
+ eu.w1 |= mask_or;
+ data->entry = eu.entry;
+
+ for_each_irq_pin(entry, data->irq_2_pin) {
+ io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1);
+ if (final)
+ final(entry);
+ }
}
static void io_apic_sync(struct irq_pin_list *entry)
@@ -490,39 +464,31 @@ static void io_apic_sync(struct irq_pin_list *entry)
readl(&io_apic->data);
}
-static void mask_ioapic(struct irq_cfg *cfg)
+static void mask_ioapic_irq(struct irq_data *irq_data)
{
+ struct mp_chip_data *data = irq_data->chip_data;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+ io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void mask_ioapic_irq(struct irq_data *data)
+static void __unmask_ioapic(struct mp_chip_data *data)
{
- mask_ioapic(irqd_cfg(data));
+ io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL);
}
-static void __unmask_ioapic(struct irq_cfg *cfg)
-{
- io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
-static void unmask_ioapic(struct irq_cfg *cfg)
+static void unmask_ioapic_irq(struct irq_data *irq_data)
{
+ struct mp_chip_data *data = irq_data->chip_data;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- __unmask_ioapic(cfg);
+ __unmask_ioapic(data);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void unmask_ioapic_irq(struct irq_data *data)
-{
- unmask_ioapic(irqd_cfg(data));
-}
-
/*
* IO-APIC versions below 0x20 don't support EOI register.
* For the record, here is the information about various versions:
@@ -539,7 +505,7 @@ static void unmask_ioapic_irq(struct irq_data *data)
* Otherwise, we simulate the EOI message manually by changing the trigger
* mode to edge and then back to level, with RTE being masked during this.
*/
-void native_eoi_ioapic_pin(int apic, int pin, int vector)
+static void __eoi_ioapic_pin(int apic, int pin, int vector)
{
if (mpc_ioapic_ver(apic) >= 0x20) {
io_apic_eoi(apic, vector);
@@ -551,7 +517,7 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector)
/*
* Mask the entry and change the trigger mode to edge.
*/
- entry1.mask = 1;
+ entry1.mask = IOAPIC_MASKED;
entry1.trigger = IOAPIC_EDGE;
__ioapic_write_entry(apic, pin, entry1);
@@ -563,15 +529,14 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector)
}
}
-void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+void eoi_ioapic_pin(int vector, struct mp_chip_data *data)
{
- struct irq_pin_list *entry;
unsigned long flags;
+ struct irq_pin_list *entry;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- for_each_irq_pin(entry, cfg->irq_2_pin)
- x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin,
- cfg->vector);
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __eoi_ioapic_pin(entry->apic, entry->pin, vector);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
@@ -588,8 +553,8 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
* Make sure the entry is masked and re-read the contents to check
* if it is a level triggered pin and if the remote-IRR is set.
*/
- if (!entry.mask) {
- entry.mask = 1;
+ if (entry.mask == IOAPIC_UNMASKED) {
+ entry.mask = IOAPIC_MASKED;
ioapic_write_entry(apic, pin, entry);
entry = ioapic_read_entry(apic, pin);
}
@@ -602,13 +567,12 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
* doesn't clear the remote-IRR if the trigger mode is not
* set to level.
*/
- if (!entry.trigger) {
+ if (entry.trigger == IOAPIC_EDGE) {
entry.trigger = IOAPIC_LEVEL;
ioapic_write_entry(apic, pin, entry);
}
-
raw_spin_lock_irqsave(&ioapic_lock, flags);
- x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector);
+ __eoi_ioapic_pin(apic, pin, entry.vector);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
@@ -706,8 +670,8 @@ void mask_ioapic_entries(void)
struct IO_APIC_route_entry entry;
entry = ioapics[apic].saved_registers[pin];
- if (!entry.mask) {
- entry.mask = 1;
+ if (entry.mask == IOAPIC_UNMASKED) {
+ entry.mask = IOAPIC_MASKED;
ioapic_write_entry(apic, pin, entry);
}
}
@@ -809,11 +773,11 @@ static int EISA_ELCR(unsigned int irq)
#endif
-/* ISA interrupts are always polarity zero edge triggered,
+/* ISA interrupts are always active high edge triggered,
* when listed as conforming in the MP table. */
-#define default_ISA_trigger(idx) (0)
-#define default_ISA_polarity(idx) (0)
+#define default_ISA_trigger(idx) (IOAPIC_EDGE)
+#define default_ISA_polarity(idx) (IOAPIC_POL_HIGH)
/* EISA interrupts are always polarity zero and can be edge or level
* trigger depending on the ELCR value. If an interrupt is listed as
@@ -823,53 +787,55 @@ static int EISA_ELCR(unsigned int irq)
#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq))
#define default_EISA_polarity(idx) default_ISA_polarity(idx)
-/* PCI interrupts are always polarity one level triggered,
+/* PCI interrupts are always active low level triggered,
* when listed as conforming in the MP table. */
-#define default_PCI_trigger(idx) (1)
-#define default_PCI_polarity(idx) (1)
+#define default_PCI_trigger(idx) (IOAPIC_LEVEL)
+#define default_PCI_polarity(idx) (IOAPIC_POL_LOW)
static int irq_polarity(int idx)
{
int bus = mp_irqs[idx].srcbus;
- int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].irqflag & 3)
- {
- case 0: /* conforms, ie. bus-type dependent polarity */
- if (test_bit(bus, mp_bus_not_pci))
- polarity = default_ISA_polarity(idx);
- else
- polarity = default_PCI_polarity(idx);
- break;
- case 1: /* high active */
- {
- polarity = 0;
- break;
- }
- case 2: /* reserved */
- {
- pr_warn("broken BIOS!!\n");
- polarity = 1;
- break;
- }
- case 3: /* low active */
- {
- polarity = 1;
- break;
- }
- default: /* invalid */
- {
- pr_warn("broken BIOS!!\n");
- polarity = 1;
- break;
- }
+ switch (mp_irqs[idx].irqflag & 0x03) {
+ case 0:
+ /* conforms to spec, ie. bus-type dependent polarity */
+ if (test_bit(bus, mp_bus_not_pci))
+ return default_ISA_polarity(idx);
+ else
+ return default_PCI_polarity(idx);
+ case 1:
+ return IOAPIC_POL_HIGH;
+ case 2:
+ pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
+ case 3:
+ default: /* Pointless default required due to do gcc stupidity */
+ return IOAPIC_POL_LOW;
+ }
+}
+
+#ifdef CONFIG_EISA
+static int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+ switch (mp_bus_id_to_type[bus]) {
+ case MP_BUS_PCI:
+ case MP_BUS_ISA:
+ return trigger;
+ case MP_BUS_EISA:
+ return default_EISA_trigger(idx);
}
- return polarity;
+ pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus);
+ return IOAPIC_LEVEL;
}
+#else
+static inline int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+ return trigger;
+}
+#endif
static int irq_trigger(int idx)
{
@@ -879,153 +845,227 @@ static int irq_trigger(int idx)
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].irqflag>>2) & 3)
- {
- case 0: /* conforms, ie. bus-type dependent */
- if (test_bit(bus, mp_bus_not_pci))
- trigger = default_ISA_trigger(idx);
- else
- trigger = default_PCI_trigger(idx);
-#ifdef CONFIG_EISA
- switch (mp_bus_id_to_type[bus]) {
- case MP_BUS_ISA: /* ISA pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_EISA: /* EISA pin */
- {
- trigger = default_EISA_trigger(idx);
- break;
- }
- case MP_BUS_PCI: /* PCI pin */
- {
- /* set before the switch */
- break;
- }
- default:
- {
- pr_warn("broken BIOS!!\n");
- trigger = 1;
- break;
- }
- }
+ switch ((mp_irqs[idx].irqflag >> 2) & 0x03) {
+ case 0:
+ /* conforms to spec, ie. bus-type dependent trigger mode */
+ if (test_bit(bus, mp_bus_not_pci))
+ trigger = default_ISA_trigger(idx);
+ else
+ trigger = default_PCI_trigger(idx);
+ /* Take EISA into account */
+ return eisa_irq_trigger(idx, bus, trigger);
+ case 1:
+ return IOAPIC_EDGE;
+ case 2:
+ pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
+ case 3:
+ default: /* Pointless default required due to do gcc stupidity */
+ return IOAPIC_LEVEL;
+ }
+}
+
+void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node,
+ int trigger, int polarity)
+{
+ init_irq_alloc_info(info, NULL);
+ info->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ info->ioapic_node = node;
+ info->ioapic_trigger = trigger;
+ info->ioapic_polarity = polarity;
+ info->ioapic_valid = 1;
+}
+
+#ifndef CONFIG_ACPI
+int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity);
#endif
- break;
- case 1: /* edge */
- {
- trigger = 0;
- break;
- }
- case 2: /* reserved */
- {
- pr_warn("broken BIOS!!\n");
- trigger = 1;
- break;
- }
- case 3: /* level */
- {
- trigger = 1;
- break;
- }
- default: /* invalid */
- {
- pr_warn("broken BIOS!!\n");
- trigger = 0;
- break;
+
+static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst,
+ struct irq_alloc_info *src,
+ u32 gsi, int ioapic_idx, int pin)
+{
+ int trigger, polarity;
+
+ copy_irq_alloc_info(dst, src);
+ dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ dst->ioapic_id = mpc_ioapic_id(ioapic_idx);
+ dst->ioapic_pin = pin;
+ dst->ioapic_valid = 1;
+ if (src && src->ioapic_valid) {
+ dst->ioapic_node = src->ioapic_node;
+ dst->ioapic_trigger = src->ioapic_trigger;
+ dst->ioapic_polarity = src->ioapic_polarity;
+ } else {
+ dst->ioapic_node = NUMA_NO_NODE;
+ if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) {
+ dst->ioapic_trigger = trigger;
+ dst->ioapic_polarity = polarity;
+ } else {
+ /*
+ * PCI interrupts are always active low level
+ * triggered.
+ */
+ dst->ioapic_trigger = IOAPIC_LEVEL;
+ dst->ioapic_polarity = IOAPIC_POL_LOW;
}
}
- return trigger;
}
-static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin)
+static int ioapic_alloc_attr_node(struct irq_alloc_info *info)
+{
+ return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE;
+}
+
+static void mp_register_handler(unsigned int irq, unsigned long trigger)
+{
+ irq_flow_handler_t hdl;
+ bool fasteoi;
+
+ if (trigger) {
+ irq_set_status_flags(irq, IRQ_LEVEL);
+ fasteoi = true;
+ } else {
+ irq_clear_status_flags(irq, IRQ_LEVEL);
+ fasteoi = false;
+ }
+
+ hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
+ __irq_set_handler(irq, hdl, 0, fasteoi ? "fasteoi" : "edge");
+}
+
+static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
{
+ struct mp_chip_data *data = irq_get_chip_data(irq);
+
+ /*
+ * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger
+ * and polarity attirbutes. So allow the first user to reprogram the
+ * pin with real trigger and polarity attributes.
+ */
+ if (irq < nr_legacy_irqs() && data->count == 1) {
+ if (info->ioapic_trigger != data->trigger)
+ mp_register_handler(irq, data->trigger);
+ data->entry.trigger = data->trigger = info->ioapic_trigger;
+ data->entry.polarity = data->polarity = info->ioapic_polarity;
+ }
+
+ return data->trigger == info->ioapic_trigger &&
+ data->polarity == info->ioapic_polarity;
+}
+
+static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi,
+ struct irq_alloc_info *info)
+{
+ bool legacy = false;
int irq = -1;
- int ioapic = (int)(long)domain->host_data;
int type = ioapics[ioapic].irqdomain_cfg.type;
switch (type) {
case IOAPIC_DOMAIN_LEGACY:
/*
- * Dynamically allocate IRQ number for non-ISA IRQs in the first 16
- * GSIs on some weird platforms.
+ * Dynamically allocate IRQ number for non-ISA IRQs in the first
+ * 16 GSIs on some weird platforms.
*/
- if (gsi < nr_legacy_irqs())
- irq = irq_create_mapping(domain, pin);
- else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
+ if (!ioapic_initialized || gsi >= nr_legacy_irqs())
irq = gsi;
+ legacy = mp_is_legacy_irq(irq);
break;
case IOAPIC_DOMAIN_STRICT:
- if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
- irq = gsi;
+ irq = gsi;
break;
case IOAPIC_DOMAIN_DYNAMIC:
- irq = irq_create_mapping(domain, pin);
break;
default:
WARN(1, "ioapic: unknown irqdomain type %d\n", type);
- break;
+ return -1;
+ }
+
+ return __irq_domain_alloc_irqs(domain, irq, 1,
+ ioapic_alloc_attr_node(info),
+ info, legacy);
+}
+
+/*
+ * Need special handling for ISA IRQs because there may be multiple IOAPIC pins
+ * sharing the same ISA IRQ number and irqdomain only supports 1:1 mapping
+ * between IOAPIC pin and IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are
+ * used for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
+ * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are available, and
+ * some BIOSes may use MP Interrupt Source records to override IRQ numbers for
+ * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be
+ * multiple pins sharing the same legacy IRQ number when ACPI is disabled.
+ */
+static int alloc_isa_irq_from_domain(struct irq_domain *domain,
+ int irq, int ioapic, int pin,
+ struct irq_alloc_info *info)
+{
+ struct mp_chip_data *data;
+ struct irq_data *irq_data = irq_get_irq_data(irq);
+ int node = ioapic_alloc_attr_node(info);
+
+ /*
+ * Legacy ISA IRQ has already been allocated, just add pin to
+ * the pin list assoicated with this IRQ and program the IOAPIC
+ * entry. The IOAPIC entry
+ */
+ if (irq_data && irq_data->parent_data) {
+ if (!mp_check_pin_attr(irq, info))
+ return -EBUSY;
+ if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic,
+ info->ioapic_pin))
+ return -ENOMEM;
+ } else {
+ irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true);
+ if (irq >= 0) {
+ irq_data = irq_domain_get_irq_data(domain, irq);
+ data = irq_data->chip_data;
+ data->isa_irq = true;
+ }
}
- return irq > 0 ? irq : -1;
+ return irq;
}
static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
- unsigned int flags)
+ unsigned int flags, struct irq_alloc_info *info)
{
int irq;
+ bool legacy = false;
+ struct irq_alloc_info tmp;
+ struct mp_chip_data *data;
struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
- struct mp_pin_info *info = mp_pin_info(ioapic, pin);
if (!domain)
- return -1;
+ return -ENOSYS;
- mutex_lock(&ioapic_mutex);
-
- /*
- * Don't use irqdomain to manage ISA IRQs because there may be
- * multiple IOAPIC pins sharing the same ISA IRQ number and
- * irqdomain only supports 1:1 mapping between IOAPIC pin and
- * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used
- * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
- * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are
- * available, and some BIOSes may use MP Interrupt Source records
- * to override IRQ numbers for PIRQs instead of reprogramming
- * the interrupt routing logic. Thus there may be multiple pins
- * sharing the same legacy IRQ number when ACPI is disabled.
- */
if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
irq = mp_irqs[idx].srcbusirq;
- if (flags & IOAPIC_MAP_ALLOC) {
- if (info->count == 0 &&
- mp_irqdomain_map(domain, irq, pin) != 0)
- irq = -1;
+ legacy = mp_is_legacy_irq(irq);
+ }
- /* special handling for timer IRQ0 */
+ mutex_lock(&ioapic_mutex);
+ if (!(flags & IOAPIC_MAP_ALLOC)) {
+ if (!legacy) {
+ irq = irq_find_mapping(domain, pin);
if (irq == 0)
- info->count++;
+ irq = -ENOENT;
}
} else {
- irq = irq_find_mapping(domain, pin);
- if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC))
- irq = alloc_irq_from_domain(domain, gsi, pin);
- }
-
- if (flags & IOAPIC_MAP_ALLOC) {
- /* special handling for legacy IRQs */
- if (irq < nr_legacy_irqs() && info->count == 1 &&
- mp_irqdomain_map(domain, irq, pin) != 0)
- irq = -1;
-
- if (irq > 0)
- info->count++;
- else if (info->count == 0)
- info->set = 0;
+ ioapic_copy_alloc_attr(&tmp, info, gsi, ioapic, pin);
+ if (legacy)
+ irq = alloc_isa_irq_from_domain(domain, irq,
+ ioapic, pin, &tmp);
+ else if ((irq = irq_find_mapping(domain, pin)) == 0)
+ irq = alloc_irq_from_domain(domain, ioapic, gsi, &tmp);
+ else if (!mp_check_pin_attr(irq, &tmp))
+ irq = -EBUSY;
+ if (irq >= 0) {
+ data = irq_get_chip_data(irq);
+ data->count++;
+ }
}
-
mutex_unlock(&ioapic_mutex);
- return irq > 0 ? irq : -1;
+ return irq;
}
static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
@@ -1058,10 +1098,10 @@ static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
}
#endif
- return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+ return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, NULL);
}
-int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
+int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info)
{
int ioapic, pin, idx;
@@ -1074,31 +1114,24 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
if ((flags & IOAPIC_MAP_CHECK) && idx < 0)
return -1;
- return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+ return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info);
}
void mp_unmap_irq(int irq)
{
- struct irq_data *data = irq_get_irq_data(irq);
- struct mp_pin_info *info;
- int ioapic, pin;
+ struct irq_data *irq_data = irq_get_irq_data(irq);
+ struct mp_chip_data *data;
- if (!data || !data->domain)
+ if (!irq_data || !irq_data->domain)
return;
- ioapic = (int)(long)data->domain->host_data;
- pin = (int)data->hwirq;
- info = mp_pin_info(ioapic, pin);
+ data = irq_data->chip_data;
+ if (!data || data->isa_irq)
+ return;
mutex_lock(&ioapic_mutex);
- if (--info->count == 0) {
- info->set = 0;
- if (irq < nr_legacy_irqs() &&
- ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY)
- mp_irqdomain_unmap(data->domain, irq);
- else
- irq_dispose_mapping(irq);
- }
+ if (--data->count == 0)
+ irq_domain_free_irqs(irq, 1);
mutex_unlock(&ioapic_mutex);
}
@@ -1165,7 +1198,7 @@ out:
}
EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-static struct irq_chip ioapic_chip;
+static struct irq_chip ioapic_chip, ioapic_ir_chip;
#ifdef CONFIG_X86_32
static inline int IO_APIC_irq_trigger(int irq)
@@ -1189,96 +1222,6 @@ static inline int IO_APIC_irq_trigger(int irq)
}
#endif
-static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
- unsigned long trigger)
-{
- struct irq_chip *chip = &ioapic_chip;
- irq_flow_handler_t hdl;
- bool fasteoi;
-
- if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
- trigger == IOAPIC_LEVEL) {
- irq_set_status_flags(irq, IRQ_LEVEL);
- fasteoi = true;
- } else {
- irq_clear_status_flags(irq, IRQ_LEVEL);
- fasteoi = false;
- }
-
- if (setup_remapped_irq(irq, cfg, chip))
- fasteoi = trigger != 0;
-
- hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
- irq_set_chip_and_handler_name(irq, chip, hdl,
- fasteoi ? "fasteoi" : "edge");
-}
-
-int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
-{
- memset(entry, 0, sizeof(*entry));
-
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->dest = destination;
- entry->vector = vector;
- entry->mask = 0; /* enable IRQ */
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
-
- /*
- * Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
-
- return 0;
-}
-
-static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
- struct io_apic_irq_attr *attr)
-{
- struct IO_APIC_route_entry entry;
- unsigned int dest;
-
- if (!IO_APIC_IRQ(irq))
- return;
-
- if (assign_irq_vector(irq, cfg, apic->target_cpus()))
- return;
-
- if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(),
- &dest)) {
- pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n",
- mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
- clear_irq_vector(irq, cfg);
-
- return;
- }
-
- apic_printk(APIC_VERBOSE,KERN_DEBUG
- "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
- "IRQ %d Mode:%i Active:%i Dest:%d)\n",
- attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin,
- cfg->vector, irq, attr->trigger, attr->polarity, dest);
-
- if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) {
- pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n",
- mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
- clear_irq_vector(irq, cfg);
-
- return;
- }
-
- ioapic_register_intr(irq, cfg, attr->trigger);
- if (irq < nr_legacy_irqs())
- legacy_pic->mask(irq);
-
- ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry);
-}
-
static void __init setup_IO_APIC_irqs(void)
{
unsigned int ioapic, pin;
@@ -1298,106 +1241,41 @@ static void __init setup_IO_APIC_irqs(void)
}
}
-/*
- * Set up the timer pin, possibly with the 8259A-master behind.
- */
-static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
- unsigned int pin, int vector)
-{
- struct IO_APIC_route_entry entry;
- unsigned int dest;
-
- memset(&entry, 0, sizeof(entry));
-
- /*
- * We use logical delivery to get the timer IRQ
- * to the first CPU.
- */
- if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(),
- apic->target_cpus(), &dest)))
- dest = BAD_APICID;
-
- entry.dest_mode = apic->irq_dest_mode;
- entry.mask = 0; /* don't mask IRQ for edge */
- entry.dest = dest;
- entry.delivery_mode = apic->irq_delivery_mode;
- entry.polarity = 0;
- entry.trigger = 0;
- entry.vector = vector;
-
- /*
- * The timer IRQ doesn't have to know that behind the
- * scene we may have a 8259A-master in AEOI mode ...
- */
- irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
- "edge");
-
- /*
- * Add it to the IO-APIC irq-routing table:
- */
- ioapic_write_entry(ioapic_idx, pin, entry);
-}
-
-void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
+void ioapic_zap_locks(void)
{
- int i;
-
- pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n");
-
- for (i = 0; i <= nr_entries; i++) {
- struct IO_APIC_route_entry entry;
-
- entry = ioapic_read_entry(apic, i);
-
- pr_debug(" %02x %02X ", i, entry.dest);
- pr_cont("%1d %1d %1d %1d %1d "
- "%1d %1d %02X\n",
- entry.mask,
- entry.trigger,
- entry.irr,
- entry.polarity,
- entry.delivery_status,
- entry.dest_mode,
- entry.delivery_mode,
- entry.vector);
- }
+ raw_spin_lock_init(&ioapic_lock);
}
-void intel_ir_io_apic_print_entries(unsigned int apic,
- unsigned int nr_entries)
+static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
{
int i;
+ char buf[256];
+ struct IO_APIC_route_entry entry;
+ struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry;
- pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n");
-
+ printk(KERN_DEBUG "IOAPIC %d:\n", apic);
for (i = 0; i <= nr_entries; i++) {
- struct IR_IO_APIC_route_entry *ir_entry;
- struct IO_APIC_route_entry entry;
-
entry = ioapic_read_entry(apic, i);
-
- ir_entry = (struct IR_IO_APIC_route_entry *)&entry;
-
- pr_debug(" %02x %04X ", i, ir_entry->index);
- pr_cont("%1d %1d %1d %1d %1d "
- "%1d %1d %X %02X\n",
- ir_entry->format,
- ir_entry->mask,
- ir_entry->trigger,
- ir_entry->irr,
- ir_entry->polarity,
- ir_entry->delivery_status,
- ir_entry->index2,
- ir_entry->zero,
- ir_entry->vector);
+ snprintf(buf, sizeof(buf),
+ " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)",
+ i,
+ entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ",
+ entry.trigger == IOAPIC_LEVEL ? "level" : "edge ",
+ entry.polarity == IOAPIC_POL_LOW ? "low " : "high",
+ entry.vector, entry.irr, entry.delivery_status);
+ if (ir_entry->format)
+ printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n",
+ buf, (ir_entry->index << 15) | ir_entry->index,
+ ir_entry->zero);
+ else
+ printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n",
+ buf,
+ entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ?
+ "logical " : "physical",
+ entry.dest, entry.delivery_mode);
}
}
-void ioapic_zap_locks(void)
-{
- raw_spin_lock_init(&ioapic_lock);
-}
-
static void __init print_IO_APIC(int ioapic_idx)
{
union IO_APIC_reg_00 reg_00;
@@ -1451,16 +1329,13 @@ static void __init print_IO_APIC(int ioapic_idx)
}
printk(KERN_DEBUG ".... IRQ redirection table:\n");
-
- x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries);
+ io_apic_print_entries(ioapic_idx, reg_01.bits.entries);
}
void __init print_IO_APICs(void)
{
int ioapic_idx;
- struct irq_cfg *cfg;
unsigned int irq;
- struct irq_chip *chip;
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for_each_ioapic(ioapic_idx)
@@ -1480,18 +1355,20 @@ void __init print_IO_APICs(void)
printk(KERN_DEBUG "IRQ to pin mappings:\n");
for_each_active_irq(irq) {
struct irq_pin_list *entry;
+ struct irq_chip *chip;
+ struct mp_chip_data *data;
chip = irq_get_chip(irq);
- if (chip != &ioapic_chip)
+ if (chip != &ioapic_chip && chip != &ioapic_ir_chip)
continue;
-
- cfg = irq_cfg(irq);
- if (!cfg)
+ data = irq_get_chip_data(irq);
+ if (!data)
continue;
- if (list_empty(&cfg->irq_2_pin))
+ if (list_empty(&data->irq_2_pin))
continue;
+
printk(KERN_DEBUG "IRQ%d ", irq);
- for_each_irq_pin(entry, cfg->irq_2_pin)
+ for_each_irq_pin(entry, data->irq_2_pin)
pr_cont("-> %d:%d", entry->apic, entry->pin);
pr_cont("\n");
}
@@ -1564,15 +1441,12 @@ void native_disable_io_apic(void)
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
- entry.mask = 0; /* Enabled */
- entry.trigger = 0; /* Edge */
- entry.irr = 0;
- entry.polarity = 0; /* High */
- entry.delivery_status = 0;
- entry.dest_mode = 0; /* Physical */
- entry.delivery_mode = dest_ExtINT; /* ExtInt */
- entry.vector = 0;
- entry.dest = read_apic_id();
+ entry.mask = IOAPIC_UNMASKED;
+ entry.trigger = IOAPIC_EDGE;
+ entry.polarity = IOAPIC_POL_HIGH;
+ entry.dest_mode = IOAPIC_DEST_MODE_PHYSICAL;
+ entry.delivery_mode = dest_ExtINT;
+ entry.dest = read_apic_id();
/*
* Add it to the IO-APIC irq-routing table:
@@ -1582,7 +1456,6 @@ void native_disable_io_apic(void)
if (cpu_has_apic || apic_from_smp_config())
disconnect_bsp_APIC(ioapic_i8259.pin != -1);
-
}
/*
@@ -1792,7 +1665,6 @@ static int __init timer_irq_works(void)
* This is not complete - we should be able to fake
* an edge even if it isn't on the 8259A...
*/
-
static unsigned int startup_ioapic_irq(struct irq_data *data)
{
int was_pending = 0, irq = data->irq;
@@ -1804,74 +1676,22 @@ static unsigned int startup_ioapic_irq(struct irq_data *data)
if (legacy_pic->irq_pending(irq))
was_pending = 1;
}
- __unmask_ioapic(irqd_cfg(data));
+ __unmask_ioapic(data->chip_data);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return was_pending;
}
-/*
- * Level and edge triggered IO-APIC interrupts need different handling,
- * so we use two separate IRQ descriptors. Edge triggered IRQs can be
- * handled with the level-triggered descriptor, but that one has slightly
- * more overhead. Level-triggered interrupts cannot be handled with the
- * edge-triggered handler, without risking IRQ storms and other ugly
- * races.
- */
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
- int apic, pin;
- struct irq_pin_list *entry;
- u8 vector = cfg->vector;
-
- for_each_irq_pin(entry, cfg->irq_2_pin) {
- unsigned int reg;
-
- apic = entry->apic;
- pin = entry->pin;
-
- io_apic_write(apic, 0x11 + pin*2, dest);
- reg = io_apic_read(apic, 0x10 + pin*2);
- reg &= ~IO_APIC_REDIR_VECTOR_MASK;
- reg |= vector;
- io_apic_modify(apic, 0x10 + pin*2, reg);
- }
-}
-
-int native_ioapic_set_affinity(struct irq_data *data,
- const struct cpumask *mask,
- bool force)
-{
- unsigned int dest, irq = data->irq;
- unsigned long flags;
- int ret;
-
- if (!config_enabled(CONFIG_SMP))
- return -EPERM;
-
- raw_spin_lock_irqsave(&ioapic_lock, flags);
- ret = apic_set_affinity(data, mask, &dest);
- if (!ret) {
- /* Only the high 8 bits are valid. */
- dest = SET_APIC_LOGICAL_ID(dest);
- __target_IO_APIC_irq(irq, dest, irqd_cfg(data));
- ret = IRQ_SET_MASK_OK_NOCOPY;
- }
- raw_spin_unlock_irqrestore(&ioapic_lock, flags);
- return ret;
-}
-
atomic_t irq_mis_count;
#ifdef CONFIG_GENERIC_PENDING_IRQ
-static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
+static bool io_apic_level_ack_pending(struct mp_chip_data *data)
{
struct irq_pin_list *entry;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- for_each_irq_pin(entry, cfg->irq_2_pin) {
+ for_each_irq_pin(entry, data->irq_2_pin) {
unsigned int reg;
int pin;
@@ -1888,18 +1708,17 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
return false;
}
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
{
/* If we are moving the irq we need to mask it */
if (unlikely(irqd_is_setaffinity_pending(data))) {
- mask_ioapic(cfg);
+ mask_ioapic_irq(data);
return true;
}
return false;
}
-static inline void ioapic_irqd_unmask(struct irq_data *data,
- struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
{
if (unlikely(masked)) {
/* Only migrate the irq if the ack has been received.
@@ -1928,31 +1747,30 @@ static inline void ioapic_irqd_unmask(struct irq_data *data,
* accurate and is causing problems then it is a hardware bug
* and you can go talk to the chipset vendor about it.
*/
- if (!io_apic_level_ack_pending(cfg))
+ if (!io_apic_level_ack_pending(data->chip_data))
irq_move_masked_irq(data);
- unmask_ioapic(cfg);
+ unmask_ioapic_irq(data);
}
}
#else
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
{
return false;
}
-static inline void ioapic_irqd_unmask(struct irq_data *data,
- struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
{
}
#endif
-static void ack_ioapic_level(struct irq_data *data)
+static void ioapic_ack_level(struct irq_data *irq_data)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- int i, irq = data->irq;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
unsigned long v;
bool masked;
+ int i;
irq_complete_move(cfg);
- masked = ioapic_irqd_mask(data, cfg);
+ masked = ioapic_irqd_mask(irq_data);
/*
* It appears there is an erratum which affects at least version 0x11
@@ -2004,11 +1822,49 @@ static void ack_ioapic_level(struct irq_data *data)
*/
if (!(v & (1 << (i & 0x1f)))) {
atomic_inc(&irq_mis_count);
+ eoi_ioapic_pin(cfg->vector, irq_data->chip_data);
+ }
+
+ ioapic_irqd_unmask(irq_data, masked);
+}
+
+static void ioapic_ir_ack_level(struct irq_data *irq_data)
+{
+ struct mp_chip_data *data = irq_data->chip_data;
+
+ /*
+ * Intr-remapping uses pin number as the virtual vector
+ * in the RTE. Actual vector is programmed in
+ * intr-remapping table entry. Hence for the io-apic
+ * EOI we use the pin number.
+ */
+ ack_APIC_irq();
+ eoi_ioapic_pin(data->entry.vector, data);
+}
- eoi_ioapic_irq(irq, cfg);
+static int ioapic_set_affinity(struct irq_data *irq_data,
+ const struct cpumask *mask, bool force)
+{
+ struct irq_data *parent = irq_data->parent_data;
+ struct mp_chip_data *data = irq_data->chip_data;
+ struct irq_pin_list *entry;
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ int ret;
+
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
+ cfg = irqd_cfg(irq_data);
+ data->entry.dest = cfg->dest_apicid;
+ data->entry.vector = cfg->vector;
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __ioapic_write_entry(entry->apic, entry->pin,
+ data->entry);
}
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
- ioapic_irqd_unmask(data, cfg, masked);
+ return ret;
}
static struct irq_chip ioapic_chip __read_mostly = {
@@ -2016,10 +1872,20 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_startup = startup_ioapic_irq,
.irq_mask = mask_ioapic_irq,
.irq_unmask = unmask_ioapic_irq,
- .irq_ack = apic_ack_edge,
- .irq_eoi = ack_ioapic_level,
- .irq_set_affinity = native_ioapic_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_eoi = ioapic_ack_level,
+ .irq_set_affinity = ioapic_set_affinity,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+static struct irq_chip ioapic_ir_chip __read_mostly = {
+ .name = "IR-IO-APIC",
+ .irq_startup = startup_ioapic_irq,
+ .irq_mask = mask_ioapic_irq,
+ .irq_unmask = unmask_ioapic_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_eoi = ioapic_ir_ack_level,
+ .irq_set_affinity = ioapic_set_affinity,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
@@ -2113,12 +1979,12 @@ static inline void __init unlock_ExtINT_logic(void)
memset(&entry1, 0, sizeof(entry1));
- entry1.dest_mode = 0; /* physical delivery */
- entry1.mask = 0; /* unmask IRQ now */
+ entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL;
+ entry1.mask = IOAPIC_UNMASKED;
entry1.dest = hard_smp_processor_id();
entry1.delivery_mode = dest_ExtINT;
entry1.polarity = entry0.polarity;
- entry1.trigger = 0;
+ entry1.trigger = IOAPIC_EDGE;
entry1.vector = 0;
ioapic_write_entry(apic, pin, entry1);
@@ -2152,6 +2018,25 @@ static int __init disable_timer_pin_setup(char *arg)
}
early_param("disable_timer_pin_1", disable_timer_pin_setup);
+static int mp_alloc_timer_irq(int ioapic, int pin)
+{
+ int irq = -1;
+ struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
+
+ if (domain) {
+ struct irq_alloc_info info;
+
+ ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0);
+ info.ioapic_id = mpc_ioapic_id(ioapic);
+ info.ioapic_pin = pin;
+ mutex_lock(&ioapic_mutex);
+ irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info);
+ mutex_unlock(&ioapic_mutex);
+ }
+
+ return irq;
+}
+
/*
* This code may look a bit paranoid, but it's supposed to cooperate with
* a wide range of boards and BIOS bugs. Fortunately only the timer IRQ
@@ -2162,7 +2047,9 @@ early_param("disable_timer_pin_1", disable_timer_pin_setup);
*/
static inline void __init check_timer(void)
{
- struct irq_cfg *cfg = irq_cfg(0);
+ struct irq_data *irq_data = irq_get_irq_data(0);
+ struct mp_chip_data *data = irq_data->chip_data;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
int node = cpu_to_node(0);
int apic1, pin1, apic2, pin2;
unsigned long flags;
@@ -2174,7 +2061,6 @@ static inline void __init check_timer(void)
* get/set the timer IRQ vector:
*/
legacy_pic->mask(0);
- assign_irq_vector(0, cfg, apic->target_cpus());
/*
* As IRQ0 is to be enabled in the 8259A, the virtual
@@ -2215,23 +2101,21 @@ static inline void __init check_timer(void)
}
if (pin1 != -1) {
- /*
- * Ok, does IRQ0 through the IOAPIC work?
- */
+ /* Ok, does IRQ0 through the IOAPIC work? */
if (no_pin1) {
- add_pin_to_irq_node(cfg, node, apic1, pin1);
- setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+ mp_alloc_timer_irq(apic1, pin1);
} else {
- /* for edge trigger, setup_ioapic_irq already
- * leave it unmasked.
+ /*
+ * for edge trigger, it's already unmasked,
* so only need to unmask if it is level-trigger
* do we really have level trigger timer?
*/
int idx;
idx = find_irq_entry(apic1, pin1, mp_INT);
if (idx != -1 && irq_trigger(idx))
- unmask_ioapic(cfg);
+ unmask_ioapic_irq(irq_get_chip_data(0));
}
+ irq_domain_activate_irq(irq_data);
if (timer_irq_works()) {
if (disable_timer_pin_1 > 0)
clear_IO_APIC_pin(0, pin1);
@@ -2251,8 +2135,8 @@ static inline void __init check_timer(void)
/*
* legacy devices should be connected to IO APIC #0
*/
- replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
- setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+ irq_domain_activate_irq(irq_data);
legacy_pic->unmask(0);
if (timer_irq_works()) {
apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
@@ -2329,36 +2213,35 @@ out:
static int mp_irqdomain_create(int ioapic)
{
- size_t size;
+ struct irq_alloc_info info;
+ struct irq_domain *parent;
int hwirqs = mp_ioapic_pin_count(ioapic);
struct ioapic *ip = &ioapics[ioapic];
struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg;
struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic);
- size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic);
- ip->pin_info = kzalloc(size, GFP_KERNEL);
- if (!ip->pin_info)
- return -ENOMEM;
-
if (cfg->type == IOAPIC_DOMAIN_INVALID)
return 0;
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ info.ioapic_id = mpc_ioapic_id(ioapic);
+ parent = irq_remapping_get_ir_irq_domain(&info);
+ if (!parent)
+ parent = x86_vector_domain;
+
ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops,
(void *)(long)ioapic);
- if(!ip->irqdomain) {
- kfree(ip->pin_info);
- ip->pin_info = NULL;
+ if (!ip->irqdomain)
return -ENOMEM;
- }
+
+ ip->irqdomain->parent = parent;
if (cfg->type == IOAPIC_DOMAIN_LEGACY ||
cfg->type == IOAPIC_DOMAIN_STRICT)
ioapic_dynirq_base = max(ioapic_dynirq_base,
gsi_cfg->gsi_end + 1);
- if (gsi_cfg->gsi_base == 0)
- irq_set_default_host(ip->irqdomain);
-
return 0;
}
@@ -2368,8 +2251,6 @@ static void ioapic_destroy_irqdomain(int idx)
irq_domain_remove(ioapics[idx].irqdomain);
ioapics[idx].irqdomain = NULL;
}
- kfree(ioapics[idx].pin_info);
- ioapics[idx].pin_info = NULL;
}
void __init setup_IO_APIC(void)
@@ -2399,20 +2280,6 @@ void __init setup_IO_APIC(void)
ioapic_initialized = 1;
}
-/*
- * Called after all the initialization is done. If we didn't find any
- * APIC bugs then we can allow the modify fast path
- */
-
-static int __init io_apic_bug_finalize(void)
-{
- if (sis_apic_bug == -1)
- sis_apic_bug = 0;
- return 0;
-}
-
-late_initcall(io_apic_bug_finalize);
-
static void resume_ioapic_id(int ioapic_idx)
{
unsigned long flags;
@@ -2451,20 +2318,6 @@ static int __init ioapic_init_ops(void)
device_initcall(ioapic_init_ops);
-static int
-io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
-{
- struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
- int ret;
-
- if (!cfg)
- return -EINVAL;
- ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin);
- if (!ret)
- setup_ioapic_irq(irq, cfg, attr);
- return ret;
-}
-
static int io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
@@ -2692,7 +2545,7 @@ void __init setup_ioapic_dest(void)
else
mask = apic->target_cpus();
- x86_io_apic_ops.set_affinity(idata, mask, false);
+ irq_set_affinity(irq, mask);
}
}
@@ -2737,7 +2590,7 @@ static struct resource * __init ioapic_setup_resources(void)
return res;
}
-void __init native_io_apic_init_mappings(void)
+void __init io_apic_init_mappings(void)
{
unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
struct resource *ioapic_res;
@@ -2962,7 +2815,6 @@ int mp_unregister_ioapic(u32 gsi_base)
{
int ioapic, pin;
int found = 0;
- struct mp_pin_info *pin_info;
for_each_ioapic(ioapic)
if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) {
@@ -2975,11 +2827,17 @@ int mp_unregister_ioapic(u32 gsi_base)
}
for_each_pin(ioapic, pin) {
- pin_info = mp_pin_info(ioapic, pin);
- if (pin_info->count) {
- pr_warn("pin%d on IOAPIC%d is still in use.\n",
- pin, ioapic);
- return -EBUSY;
+ u32 gsi = mp_pin_to_gsi(ioapic, pin);
+ int irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+ struct mp_chip_data *data;
+
+ if (irq >= 0) {
+ data = irq_get_chip_data(irq);
+ if (data && data->count) {
+ pr_warn("pin%d on IOAPIC%d is still in use.\n",
+ pin, ioapic);
+ return -EBUSY;
+ }
}
}
@@ -3006,108 +2864,141 @@ int mp_ioapic_registered(u32 gsi_base)
return 0;
}
-static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
- int ioapic, int ioapic_pin,
- int trigger, int polarity)
+static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data,
+ struct irq_alloc_info *info)
{
- irq_attr->ioapic = ioapic;
- irq_attr->ioapic_pin = ioapic_pin;
- irq_attr->trigger = trigger;
- irq_attr->polarity = polarity;
+ if (info && info->ioapic_valid) {
+ data->trigger = info->ioapic_trigger;
+ data->polarity = info->ioapic_polarity;
+ } else if (acpi_get_override_irq(gsi, &data->trigger,
+ &data->polarity) < 0) {
+ /* PCI interrupts are always active low level triggered. */
+ data->trigger = IOAPIC_LEVEL;
+ data->polarity = IOAPIC_POL_LOW;
+ }
}
-int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
- irq_hw_number_t hwirq)
+static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data,
+ struct IO_APIC_route_entry *entry)
{
- int ioapic = (int)(long)domain->host_data;
- struct mp_pin_info *info = mp_pin_info(ioapic, hwirq);
- struct io_apic_irq_attr attr;
+ memset(entry, 0, sizeof(*entry));
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->dest = cfg->dest_apicid;
+ entry->vector = cfg->vector;
+ entry->trigger = data->trigger;
+ entry->polarity = data->polarity;
+ /*
+ * Mask level triggered irqs. Edge triggered irqs are masked
+ * by the irq core code in case they fire.
+ */
+ if (data->trigger == IOAPIC_LEVEL)
+ entry->mask = IOAPIC_MASKED;
+ else
+ entry->mask = IOAPIC_UNMASKED;
+}
- /* Get default attribute if not set by caller yet */
- if (!info->set) {
- u32 gsi = mp_pin_to_gsi(ioapic, hwirq);
+int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ int ret, ioapic, pin;
+ struct irq_cfg *cfg;
+ struct irq_data *irq_data;
+ struct mp_chip_data *data;
+ struct irq_alloc_info *info = arg;
- if (acpi_get_override_irq(gsi, &info->trigger,
- &info->polarity) < 0) {
- /*
- * PCI interrupts are always polarity one level
- * triggered.
- */
- info->trigger = 1;
- info->polarity = 1;
- }
- info->node = NUMA_NO_NODE;
+ if (!info || nr_irqs > 1)
+ return -EINVAL;
+ irq_data = irq_domain_get_irq_data(domain, virq);
+ if (!irq_data)
+ return -EINVAL;
- /*
- * setup_IO_APIC_irqs() programs all legacy IRQs with default
- * trigger and polarity attributes. Don't set the flag for that
- * case so the first legacy IRQ user could reprogram the pin
- * with real trigger and polarity attributes.
- */
- if (virq >= nr_legacy_irqs() || info->count)
- info->set = 1;
- }
- set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger,
- info->polarity);
+ ioapic = mp_irqdomain_ioapic_idx(domain);
+ pin = info->ioapic_pin;
+ if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0)
+ return -EEXIST;
- return io_apic_setup_irq_pin(virq, info->node, &attr);
-}
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
-void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq)
-{
- struct irq_data *data = irq_get_irq_data(virq);
- struct irq_cfg *cfg = irq_cfg(virq);
- int ioapic = (int)(long)domain->host_data;
- int pin = (int)data->hwirq;
+ info->ioapic_entry = &data->entry;
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+ if (ret < 0) {
+ kfree(data);
+ return ret;
+ }
+
+ INIT_LIST_HEAD(&data->irq_2_pin);
+ irq_data->hwirq = info->ioapic_pin;
+ irq_data->chip = (domain->parent == x86_vector_domain) ?
+ &ioapic_chip : &ioapic_ir_chip;
+ irq_data->chip_data = data;
+ mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info);
+
+ cfg = irqd_cfg(irq_data);
+ add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin);
+ if (info->ioapic_entry)
+ mp_setup_entry(cfg, data, info->ioapic_entry);
+ mp_register_handler(virq, data->trigger);
+ if (virq < nr_legacy_irqs())
+ legacy_pic->mask(virq);
+
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n",
+ ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector,
+ virq, data->trigger, data->polarity, cfg->dest_apicid);
- ioapic_mask_entry(ioapic, pin);
- __remove_pin_from_irq(cfg, ioapic, pin);
- WARN_ON(!list_empty(&cfg->irq_2_pin));
- arch_teardown_hwirq(virq);
+ return 0;
}
-int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
+void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
{
- int ret = 0;
- int ioapic, pin;
- struct mp_pin_info *info;
+ struct irq_data *irq_data;
+ struct mp_chip_data *data;
- ioapic = mp_find_ioapic(gsi);
- if (ioapic < 0)
- return -ENODEV;
-
- pin = mp_find_ioapic_pin(ioapic, gsi);
- info = mp_pin_info(ioapic, pin);
- trigger = trigger ? 1 : 0;
- polarity = polarity ? 1 : 0;
-
- mutex_lock(&ioapic_mutex);
- if (!info->set) {
- info->trigger = trigger;
- info->polarity = polarity;
- info->node = node;
- info->set = 1;
- } else if (info->trigger != trigger || info->polarity != polarity) {
- ret = -EBUSY;
+ BUG_ON(nr_irqs != 1);
+ irq_data = irq_domain_get_irq_data(domain, virq);
+ if (irq_data && irq_data->chip_data) {
+ data = irq_data->chip_data;
+ __remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain),
+ (int)irq_data->hwirq);
+ WARN_ON(!list_empty(&data->irq_2_pin));
+ kfree(irq_data->chip_data);
}
- mutex_unlock(&ioapic_mutex);
-
- return ret;
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
}
-/* Enable IOAPIC early just for system timer */
-void __init pre_init_apic_IRQ0(void)
+void mp_irqdomain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
- struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
+ unsigned long flags;
+ struct irq_pin_list *entry;
+ struct mp_chip_data *data = irq_data->chip_data;
- printk(KERN_INFO "Early APIC setup for system timer0\n");
-#ifndef CONFIG_SMP
- physid_set_mask_of_physid(boot_cpu_physical_apicid,
- &phys_cpu_present_map);
-#endif
- setup_local_APIC();
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __ioapic_write_entry(entry->apic, entry->pin, data->entry);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+}
- io_apic_setup_irq_pin(0, 0, &attr);
- irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
- "edge");
+void mp_irqdomain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ /* It won't be called for IRQ with multiple IOAPIC pins associated */
+ ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain),
+ (int)irq_data->hwirq);
+}
+
+int mp_irqdomain_ioapic_idx(struct irq_domain *domain)
+{
+ return (int)(long)domain->host_data;
}
+
+const struct irq_domain_ops mp_ioapic_irqdomain_ops = {
+ .alloc = mp_irqdomain_alloc,
+ .free = mp_irqdomain_free,
+ .activate = mp_irqdomain_activate,
+ .deactivate = mp_irqdomain_deactivate,
+};
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index d6ba2d660dc5..1a9d735e09c6 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -3,6 +3,8 @@
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Convert to hierarchical irqdomain
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -14,22 +16,23 @@
#include <linux/dmar.h>
#include <linux/hpet.h>
#include <linux/msi.h>
+#include <asm/irqdomain.h>
#include <asm/msidef.h>
#include <asm/hpet.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/irq_remapping.h>
-void native_compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
+static struct irq_domain *msi_default_domain;
+
+static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
{
- struct irq_cfg *cfg = irq_cfg(irq);
+ struct irq_cfg *cfg = irqd_cfg(data);
msg->address_hi = MSI_ADDR_BASE_HI;
if (x2apic_enabled())
- msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
+ msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid);
msg->address_lo =
MSI_ADDR_BASE_LO |
@@ -39,7 +42,7 @@ void native_compose_msi_msg(struct pci_dev *pdev,
((apic->irq_delivery_mode != dest_LowestPrio) ?
MSI_ADDR_REDIRECTION_CPU :
MSI_ADDR_REDIRECTION_LOWPRI) |
- MSI_ADDR_DEST_ID(dest);
+ MSI_ADDR_DEST_ID(cfg->dest_apicid);
msg->data =
MSI_DATA_TRIGGER_EDGE |
@@ -50,180 +53,201 @@ void native_compose_msi_msg(struct pci_dev *pdev,
MSI_DATA_VECTOR(cfg->vector);
}
-static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
- struct msi_msg *msg, u8 hpet_id)
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip pci_msi_controller = {
+ .name = "PCI-MSI",
+ .irq_unmask = pci_msi_unmask_irq,
+ .irq_mask = pci_msi_mask_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
- struct irq_cfg *cfg;
- int err;
- unsigned dest;
+ struct irq_domain *domain;
+ struct irq_alloc_info info;
- if (disable_apic)
- return -ENXIO;
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_MSI;
+ info.msi_dev = dev;
- cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, apic->target_cpus());
- if (err)
- return err;
+ domain = irq_remapping_get_irq_domain(&info);
+ if (domain == NULL)
+ domain = msi_default_domain;
+ if (domain == NULL)
+ return -ENOSYS;
- err = apic->cpu_mask_to_apicid_and(cfg->domain,
- apic->target_cpus(), &dest);
- if (err)
- return err;
+ return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
+}
- x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
+void native_teardown_msi_irq(unsigned int irq)
+{
+ irq_domain_free_irqs(irq, 1);
+}
- return 0;
+static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
+{
+ return arg->msi_hwirq;
}
-static int
-msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
+static int pci_msi_prepare(struct irq_domain *domain, struct device *dev,
+ int nvec, msi_alloc_info_t *arg)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- struct msi_msg msg;
- unsigned int dest;
- int ret;
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct msi_desc *desc = first_pci_msi_entry(pdev);
+
+ init_irq_alloc_info(arg, NULL);
+ arg->msi_dev = pdev;
+ if (desc->msi_attrib.is_msix) {
+ arg->type = X86_IRQ_ALLOC_TYPE_MSIX;
+ } else {
+ arg->type = X86_IRQ_ALLOC_TYPE_MSI;
+ arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+ }
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
+ return 0;
+}
- __get_cached_msi_msg(data->msi_desc, &msg);
+static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+ arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
+}
+
+static struct msi_domain_ops pci_msi_domain_ops = {
+ .get_hwirq = pci_msi_get_hwirq,
+ .msi_prepare = pci_msi_prepare,
+ .set_desc = pci_msi_set_desc,
+};
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+static struct msi_domain_info pci_msi_domain_info = {
+ .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_PCI_MSIX,
+ .ops = &pci_msi_domain_ops,
+ .chip = &pci_msi_controller,
+ .handler = handle_edge_irq,
+ .handler_name = "edge",
+};
- __pci_write_msi_msg(data->msi_desc, &msg);
+void arch_init_msi_domain(struct irq_domain *parent)
+{
+ if (disable_apic)
+ return;
- return IRQ_SET_MASK_OK_NOCOPY;
+ msi_default_domain = pci_msi_create_irq_domain(NULL,
+ &pci_msi_domain_info, parent);
+ if (!msi_default_domain)
+ pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
}
-/*
- * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI or MSI-X Capability Structure.
- */
-static struct irq_chip msi_chip = {
- .name = "PCI-MSI",
+#ifdef CONFIG_IRQ_REMAP
+static struct irq_chip pci_msi_ir_controller = {
+ .name = "IR-PCI-MSI",
.irq_unmask = pci_msi_unmask_irq,
.irq_mask = pci_msi_mask_irq,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- unsigned int irq_base, unsigned int irq_offset)
-{
- struct irq_chip *chip = &msi_chip;
- struct msi_msg msg;
- unsigned int irq = irq_base + irq_offset;
- int ret;
-
- ret = msi_compose_msg(dev, irq, &msg, -1);
- if (ret < 0)
- return ret;
-
- irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
-
- /*
- * MSI-X message is written per-IRQ, the offset is always 0.
- * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
- */
- if (!irq_offset)
- pci_write_msi_msg(irq, &msg);
+static struct msi_domain_info pci_msi_ir_domain_info = {
+ .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+ .ops = &pci_msi_domain_ops,
+ .chip = &pci_msi_ir_controller,
+ .handler = handle_edge_irq,
+ .handler_name = "edge",
+};
- setup_remapped_irq(irq, irq_cfg(irq), chip);
+struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent)
+{
+ return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent);
+}
+#endif
- irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
+#ifdef CONFIG_DMAR_TABLE
+static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
+{
+ dmar_msi_write(data->irq, msg);
+}
- dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq);
+static struct irq_chip dmar_msi_controller = {
+ .name = "DMAR-MSI",
+ .irq_unmask = dmar_msi_unmask,
+ .irq_mask = dmar_msi_mask,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_set_affinity = msi_domain_set_affinity,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
+ .irq_write_msi_msg = dmar_msi_write_msg,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
- return 0;
+static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
+{
+ return arg->dmar_id;
}
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+static int dmar_msi_init(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq,
+ irq_hw_number_t hwirq, msi_alloc_info_t *arg)
{
- struct msi_desc *msidesc;
- unsigned int irq;
- int node, ret;
+ irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL,
+ handle_edge_irq, arg->dmar_data, "edge");
- /* Multiple MSI vectors only supported with interrupt remapping */
- if (type == PCI_CAP_ID_MSI && nvec > 1)
- return 1;
+ return 0;
+}
- node = dev_to_node(&dev->dev);
+static struct msi_domain_ops dmar_msi_domain_ops = {
+ .get_hwirq = dmar_msi_get_hwirq,
+ .msi_init = dmar_msi_init,
+};
- list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = irq_alloc_hwirq(node);
- if (!irq)
- return -ENOSPC;
+static struct msi_domain_info dmar_msi_domain_info = {
+ .ops = &dmar_msi_domain_ops,
+ .chip = &dmar_msi_controller,
+};
- ret = setup_msi_irq(dev, msidesc, irq, 0);
- if (ret < 0) {
- irq_free_hwirq(irq);
- return ret;
- }
+static struct irq_domain *dmar_get_irq_domain(void)
+{
+ static struct irq_domain *dmar_domain;
+ static DEFINE_MUTEX(dmar_lock);
- }
- return 0;
-}
+ mutex_lock(&dmar_lock);
+ if (dmar_domain == NULL)
+ dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info,
+ x86_vector_domain);
+ mutex_unlock(&dmar_lock);
-void native_teardown_msi_irq(unsigned int irq)
-{
- irq_free_hwirq(irq);
+ return dmar_domain;
}
-#ifdef CONFIG_DMAR_TABLE
-static int
-dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
+int dmar_alloc_hwirq(int id, int node, void *arg)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest, irq = data->irq;
- struct msi_msg msg;
- int ret;
-
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
+ struct irq_domain *domain = dmar_get_irq_domain();
+ struct irq_alloc_info info;
- dmar_msi_read(irq, &msg);
+ if (!domain)
+ return -1;
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
- msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_DMAR;
+ info.dmar_id = id;
+ info.dmar_data = arg;
- dmar_msi_write(irq, &msg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
+ return irq_domain_alloc_irqs(domain, 1, node, &info);
}
-static struct irq_chip dmar_msi_type = {
- .name = "DMAR_MSI",
- .irq_unmask = dmar_msi_unmask,
- .irq_mask = dmar_msi_mask,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = dmar_msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
- .flags = IRQCHIP_SKIP_SET_WAKE,
-};
-
-int arch_setup_dmar_msi(unsigned int irq)
+void dmar_free_hwirq(int irq)
{
- int ret;
- struct msi_msg msg;
-
- ret = msi_compose_msg(NULL, irq, &msg, -1);
- if (ret < 0)
- return ret;
- dmar_msi_write(irq, &msg);
- irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
- return 0;
+ irq_domain_free_irqs(irq, 1);
}
#endif
@@ -231,56 +255,103 @@ int arch_setup_dmar_msi(unsigned int irq)
* MSI message composition
*/
#ifdef CONFIG_HPET_TIMER
+static inline int hpet_dev_id(struct irq_domain *domain)
+{
+ struct msi_domain_info *info = msi_get_domain_info(domain);
+
+ return (int)(long)info->data;
+}
-static int hpet_msi_set_affinity(struct irq_data *data,
- const struct cpumask *mask, bool force)
+static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- struct msi_msg msg;
- unsigned int dest;
- int ret;
+ hpet_msi_write(data->handler_data, msg);
+}
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
+static struct irq_chip hpet_msi_controller = {
+ .name = "HPET-MSI",
+ .irq_unmask = hpet_msi_unmask,
+ .irq_mask = hpet_msi_mask,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_set_affinity = msi_domain_set_affinity,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
+ .irq_write_msi_msg = hpet_msi_write_msg,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
- hpet_msi_read(data->handler_data, &msg);
+static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
+{
+ return arg->hpet_index;
+}
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+static int hpet_msi_init(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq,
+ irq_hw_number_t hwirq, msi_alloc_info_t *arg)
+{
+ irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+ irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL,
+ handle_edge_irq, arg->hpet_data, "edge");
- hpet_msi_write(data->handler_data, &msg);
+ return 0;
+}
- return IRQ_SET_MASK_OK_NOCOPY;
+static void hpet_msi_free(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq)
+{
+ irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
}
-static struct irq_chip hpet_msi_type = {
- .name = "HPET_MSI",
- .irq_unmask = hpet_msi_unmask,
- .irq_mask = hpet_msi_mask,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = hpet_msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+static struct msi_domain_ops hpet_msi_domain_ops = {
+ .get_hwirq = hpet_msi_get_hwirq,
+ .msi_init = hpet_msi_init,
+ .msi_free = hpet_msi_free,
+};
+
+static struct msi_domain_info hpet_msi_domain_info = {
+ .ops = &hpet_msi_domain_ops,
+ .chip = &hpet_msi_controller,
};
-int default_setup_hpet_msi(unsigned int irq, unsigned int id)
+struct irq_domain *hpet_create_irq_domain(int hpet_id)
{
- struct irq_chip *chip = &hpet_msi_type;
- struct msi_msg msg;
- int ret;
+ struct irq_domain *parent;
+ struct irq_alloc_info info;
+ struct msi_domain_info *domain_info;
+
+ if (x86_vector_domain == NULL)
+ return NULL;
+
+ domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL);
+ if (!domain_info)
+ return NULL;
+
+ *domain_info = hpet_msi_domain_info;
+ domain_info->data = (void *)(long)hpet_id;
+
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_HPET;
+ info.hpet_id = hpet_id;
+ parent = irq_remapping_get_ir_irq_domain(&info);
+ if (parent == NULL)
+ parent = x86_vector_domain;
+ else
+ hpet_msi_controller.name = "IR-HPET-MSI";
+
+ return msi_create_irq_domain(NULL, domain_info, parent);
+}
- ret = msi_compose_msg(NULL, irq, &msg, id);
- if (ret < 0)
- return ret;
+int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev,
+ int dev_num)
+{
+ struct irq_alloc_info info;
- hpet_msi_write(irq_get_handler_data(irq), &msg);
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- setup_remapped_irq(irq, irq_cfg(irq), chip);
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_HPET;
+ info.hpet_data = dev;
+ info.hpet_id = hpet_dev_id(domain);
+ info.hpet_index = dev_num;
- irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
- return 0;
+ return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info);
}
#endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 6cedd7914581..28eba2d38b15 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -3,6 +3,8 @@
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Enable support of hierarchical irqdomains
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -11,15 +13,28 @@
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compiler.h>
-#include <linux/irqdomain.h>
#include <linux/slab.h>
+#include <asm/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/i8259.h>
#include <asm/desc.h>
#include <asm/irq_remapping.h>
+struct apic_chip_data {
+ struct irq_cfg cfg;
+ cpumask_var_t domain;
+ cpumask_var_t old_domain;
+ u8 move_in_progress : 1;
+};
+
+struct irq_domain *x86_vector_domain;
static DEFINE_RAW_SPINLOCK(vector_lock);
+static cpumask_var_t vector_cpumask;
+static struct irq_chip lapic_controller;
+#ifdef CONFIG_X86_IO_APIC
+static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
+#endif
void lock_vector_lock(void)
{
@@ -34,71 +49,59 @@ void unlock_vector_lock(void)
raw_spin_unlock(&vector_lock);
}
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data)
{
- return irq_get_chip_data(irq);
+ if (!irq_data)
+ return NULL;
+
+ while (irq_data->parent_data)
+ irq_data = irq_data->parent_data;
+
+ return irq_data->chip_data;
}
struct irq_cfg *irqd_cfg(struct irq_data *irq_data)
{
- return irq_data->chip_data;
+ struct apic_chip_data *data = apic_chip_data(irq_data);
+
+ return data ? &data->cfg : NULL;
}
-static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+struct irq_cfg *irq_cfg(unsigned int irq)
{
- struct irq_cfg *cfg;
+ return irqd_cfg(irq_get_irq_data(irq));
+}
- cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
- if (!cfg)
+static struct apic_chip_data *alloc_apic_chip_data(int node)
+{
+ struct apic_chip_data *data;
+
+ data = kzalloc_node(sizeof(*data), GFP_KERNEL, node);
+ if (!data)
return NULL;
- if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
- goto out_cfg;
- if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+ if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node))
+ goto out_data;
+ if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node))
goto out_domain;
-#ifdef CONFIG_X86_IO_APIC
- INIT_LIST_HEAD(&cfg->irq_2_pin);
-#endif
- return cfg;
+ return data;
out_domain:
- free_cpumask_var(cfg->domain);
-out_cfg:
- kfree(cfg);
+ free_cpumask_var(data->domain);
+out_data:
+ kfree(data);
return NULL;
}
-struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
+static void free_apic_chip_data(struct apic_chip_data *data)
{
- int res = irq_alloc_desc_at(at, node);
- struct irq_cfg *cfg;
-
- if (res < 0) {
- if (res != -EEXIST)
- return NULL;
- cfg = irq_cfg(at);
- if (cfg)
- return cfg;
+ if (data) {
+ free_cpumask_var(data->domain);
+ free_cpumask_var(data->old_domain);
+ kfree(data);
}
-
- cfg = alloc_irq_cfg(at, node);
- if (cfg)
- irq_set_chip_data(at, cfg);
- else
- irq_free_desc(at);
- return cfg;
-}
-
-static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
-{
- if (!cfg)
- return;
- irq_set_chip_data(at, NULL);
- free_cpumask_var(cfg->domain);
- free_cpumask_var(cfg->old_domain);
- kfree(cfg);
}
-static int
-__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int __assign_irq_vector(int irq, struct apic_chip_data *d,
+ const struct cpumask *mask)
{
/*
* NOTE! The local APIC isn't very good at handling
@@ -114,36 +117,33 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
static int current_offset = VECTOR_OFFSET_START % 16;
int cpu, err;
- cpumask_var_t tmp_mask;
- if (cfg->move_in_progress)
+ if (d->move_in_progress)
return -EBUSY;
- if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
- return -ENOMEM;
-
/* Only try and allocate irqs on cpus that are present */
err = -ENOSPC;
- cpumask_clear(cfg->old_domain);
+ cpumask_clear(d->old_domain);
cpu = cpumask_first_and(mask, cpu_online_mask);
while (cpu < nr_cpu_ids) {
int new_cpu, vector, offset;
- apic->vector_allocation_domain(cpu, tmp_mask, mask);
+ apic->vector_allocation_domain(cpu, vector_cpumask, mask);
- if (cpumask_subset(tmp_mask, cfg->domain)) {
+ if (cpumask_subset(vector_cpumask, d->domain)) {
err = 0;
- if (cpumask_equal(tmp_mask, cfg->domain))
+ if (cpumask_equal(vector_cpumask, d->domain))
break;
/*
* New cpumask using the vector is a proper subset of
* the current in use mask. So cleanup the vector
* allocation for the members that are not used anymore.
*/
- cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
- cfg->move_in_progress =
- cpumask_intersects(cfg->old_domain, cpu_online_mask);
- cpumask_and(cfg->domain, cfg->domain, tmp_mask);
+ cpumask_andnot(d->old_domain, d->domain,
+ vector_cpumask);
+ d->move_in_progress =
+ cpumask_intersects(d->old_domain, cpu_online_mask);
+ cpumask_and(d->domain, d->domain, vector_cpumask);
break;
}
@@ -157,16 +157,18 @@ next:
}
if (unlikely(current_vector == vector)) {
- cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
- cpumask_andnot(tmp_mask, mask, cfg->old_domain);
- cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
+ cpumask_or(d->old_domain, d->old_domain,
+ vector_cpumask);
+ cpumask_andnot(vector_cpumask, mask, d->old_domain);
+ cpu = cpumask_first_and(vector_cpumask,
+ cpu_online_mask);
continue;
}
if (test_bit(vector, used_vectors))
goto next;
- for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
+ for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
if (per_cpu(vector_irq, new_cpu)[vector] >
VECTOR_UNDEFINED)
goto next;
@@ -174,55 +176,73 @@ next:
/* Found one! */
current_vector = vector;
current_offset = offset;
- if (cfg->vector) {
- cpumask_copy(cfg->old_domain, cfg->domain);
- cfg->move_in_progress =
- cpumask_intersects(cfg->old_domain, cpu_online_mask);
+ if (d->cfg.vector) {
+ cpumask_copy(d->old_domain, d->domain);
+ d->move_in_progress =
+ cpumask_intersects(d->old_domain, cpu_online_mask);
}
- for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+ for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
per_cpu(vector_irq, new_cpu)[vector] = irq;
- cfg->vector = vector;
- cpumask_copy(cfg->domain, tmp_mask);
+ d->cfg.vector = vector;
+ cpumask_copy(d->domain, vector_cpumask);
err = 0;
break;
}
- free_cpumask_var(tmp_mask);
+
+ if (!err) {
+ /* cache destination APIC IDs into cfg->dest_apicid */
+ err = apic->cpu_mask_to_apicid_and(mask, d->domain,
+ &d->cfg.dest_apicid);
+ }
return err;
}
-int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int assign_irq_vector(int irq, struct apic_chip_data *data,
+ const struct cpumask *mask)
{
int err;
unsigned long flags;
raw_spin_lock_irqsave(&vector_lock, flags);
- err = __assign_irq_vector(irq, cfg, mask);
+ err = __assign_irq_vector(irq, data, mask);
raw_spin_unlock_irqrestore(&vector_lock, flags);
return err;
}
-void clear_irq_vector(int irq, struct irq_cfg *cfg)
+static int assign_irq_vector_policy(int irq, int node,
+ struct apic_chip_data *data,
+ struct irq_alloc_info *info)
+{
+ if (info && info->mask)
+ return assign_irq_vector(irq, data, info->mask);
+ if (node != NUMA_NO_NODE &&
+ assign_irq_vector(irq, data, cpumask_of_node(node)) == 0)
+ return 0;
+ return assign_irq_vector(irq, data, apic->target_cpus());
+}
+
+static void clear_irq_vector(int irq, struct apic_chip_data *data)
{
int cpu, vector;
unsigned long flags;
raw_spin_lock_irqsave(&vector_lock, flags);
- BUG_ON(!cfg->vector);
+ BUG_ON(!data->cfg.vector);
- vector = cfg->vector;
- for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ vector = data->cfg.vector;
+ for_each_cpu_and(cpu, data->domain, cpu_online_mask)
per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
- cfg->vector = 0;
- cpumask_clear(cfg->domain);
+ data->cfg.vector = 0;
+ cpumask_clear(data->domain);
- if (likely(!cfg->move_in_progress)) {
+ if (likely(!data->move_in_progress)) {
raw_spin_unlock_irqrestore(&vector_lock, flags);
return;
}
- for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
if (per_cpu(vector_irq, cpu)[vector] != irq)
@@ -231,10 +251,95 @@ void clear_irq_vector(int irq, struct irq_cfg *cfg)
break;
}
}
- cfg->move_in_progress = 0;
+ data->move_in_progress = 0;
raw_spin_unlock_irqrestore(&vector_lock, flags);
}
+void init_irq_alloc_info(struct irq_alloc_info *info,
+ const struct cpumask *mask)
+{
+ memset(info, 0, sizeof(*info));
+ info->mask = mask;
+}
+
+void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
+{
+ if (src)
+ *dst = *src;
+ else
+ memset(dst, 0, sizeof(*dst));
+}
+
+static void x86_vector_free_irqs(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs)
+{
+ struct irq_data *irq_data;
+ int i;
+
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
+ if (irq_data && irq_data->chip_data) {
+ clear_irq_vector(virq + i, irq_data->chip_data);
+ free_apic_chip_data(irq_data->chip_data);
+#ifdef CONFIG_X86_IO_APIC
+ if (virq + i < nr_legacy_irqs())
+ legacy_irq_data[virq + i] = NULL;
+#endif
+ irq_domain_reset_irq_data(irq_data);
+ }
+ }
+}
+
+static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ struct irq_alloc_info *info = arg;
+ struct apic_chip_data *data;
+ struct irq_data *irq_data;
+ int i, err;
+
+ if (disable_apic)
+ return -ENXIO;
+
+ /* Currently vector allocator can't guarantee contiguous allocations */
+ if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1)
+ return -ENOSYS;
+
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ BUG_ON(!irq_data);
+#ifdef CONFIG_X86_IO_APIC
+ if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i])
+ data = legacy_irq_data[virq + i];
+ else
+#endif
+ data = alloc_apic_chip_data(irq_data->node);
+ if (!data) {
+ err = -ENOMEM;
+ goto error;
+ }
+
+ irq_data->chip = &lapic_controller;
+ irq_data->chip_data = data;
+ irq_data->hwirq = virq + i;
+ err = assign_irq_vector_policy(virq, irq_data->node, data,
+ info);
+ if (err)
+ goto error;
+ }
+
+ return 0;
+
+error:
+ x86_vector_free_irqs(domain, virq, i + 1);
+ return err;
+}
+
+static const struct irq_domain_ops x86_vector_domain_ops = {
+ .alloc = x86_vector_alloc_irqs,
+ .free = x86_vector_free_irqs,
+};
+
int __init arch_probe_nr_irqs(void)
{
int nr;
@@ -258,8 +363,43 @@ int __init arch_probe_nr_irqs(void)
return nr_legacy_irqs();
}
+#ifdef CONFIG_X86_IO_APIC
+static void init_legacy_irqs(void)
+{
+ int i, node = cpu_to_node(0);
+ struct apic_chip_data *data;
+
+ /*
+ * For legacy IRQ's, start with assigning irq0 to irq15 to
+ * ISA_IRQ_VECTOR(i) for all cpu's.
+ */
+ for (i = 0; i < nr_legacy_irqs(); i++) {
+ data = legacy_irq_data[i] = alloc_apic_chip_data(node);
+ BUG_ON(!data);
+
+ data->cfg.vector = ISA_IRQ_VECTOR(i);
+ cpumask_setall(data->domain);
+ irq_set_chip_data(i, data);
+ }
+}
+#else
+static void init_legacy_irqs(void) { }
+#endif
+
int __init arch_early_irq_init(void)
{
+ init_legacy_irqs();
+
+ x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops,
+ NULL);
+ BUG_ON(x86_vector_domain == NULL);
+ irq_set_default_host(x86_vector_domain);
+
+ arch_init_msi_domain(x86_vector_domain);
+ arch_init_htirq_domain(x86_vector_domain);
+
+ BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+
return arch_early_ioapic_init();
}
@@ -267,7 +407,7 @@ static void __setup_vector_irq(int cpu)
{
/* Initialize vector_irq on a new cpu */
int irq, vector;
- struct irq_cfg *cfg;
+ struct apic_chip_data *data;
/*
* vector_lock will make sure that we don't run into irq vector
@@ -277,13 +417,13 @@ static void __setup_vector_irq(int cpu)
raw_spin_lock(&vector_lock);
/* Mark the inuse vectors */
for_each_active_irq(irq) {
- cfg = irq_cfg(irq);
- if (!cfg)
+ data = apic_chip_data(irq_get_irq_data(irq));
+ if (!data)
continue;
- if (!cpumask_test_cpu(cpu, cfg->domain))
+ if (!cpumask_test_cpu(cpu, data->domain))
continue;
- vector = cfg->vector;
+ vector = data->cfg.vector;
per_cpu(vector_irq, cpu)[vector] = irq;
}
/* Mark the free vectors */
@@ -292,8 +432,8 @@ static void __setup_vector_irq(int cpu)
if (irq <= VECTOR_UNDEFINED)
continue;
- cfg = irq_cfg(irq);
- if (!cpumask_test_cpu(cpu, cfg->domain))
+ data = apic_chip_data(irq_get_irq_data(irq));
+ if (!cpumask_test_cpu(cpu, data->domain))
per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
}
raw_spin_unlock(&vector_lock);
@@ -314,20 +454,20 @@ void setup_vector_irq(int cpu)
* legacy vector to irq mapping:
*/
for (irq = 0; irq < nr_legacy_irqs(); irq++)
- per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+ per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq;
__setup_vector_irq(cpu);
}
-int apic_retrigger_irq(struct irq_data *data)
+static int apic_retrigger_irq(struct irq_data *irq_data)
{
- struct irq_cfg *cfg = irqd_cfg(data);
+ struct apic_chip_data *data = apic_chip_data(irq_data);
unsigned long flags;
int cpu;
raw_spin_lock_irqsave(&vector_lock, flags);
- cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
- apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
+ cpu = cpumask_first_and(data->domain, cpu_online_mask);
+ apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector);
raw_spin_unlock_irqrestore(&vector_lock, flags);
return 1;
@@ -340,73 +480,76 @@ void apic_ack_edge(struct irq_data *data)
ack_APIC_irq();
}
-/*
- * Either sets data->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves data->affinity untouched.
- */
-int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- unsigned int *dest_id)
+static int apic_set_affinity(struct irq_data *irq_data,
+ const struct cpumask *dest, bool force)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int irq = data->irq;
- int err;
+ struct apic_chip_data *data = irq_data->chip_data;
+ int err, irq = irq_data->irq;
if (!config_enabled(CONFIG_SMP))
return -EPERM;
- if (!cpumask_intersects(mask, cpu_online_mask))
+ if (!cpumask_intersects(dest, cpu_online_mask))
return -EINVAL;
- err = assign_irq_vector(irq, cfg, mask);
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
+ err = assign_irq_vector(irq, data, dest);
if (err) {
- if (assign_irq_vector(irq, cfg, data->affinity))
+ struct irq_data *top = irq_get_irq_data(irq);
+
+ if (assign_irq_vector(irq, data, top->affinity))
pr_err("Failed to recover vector for irq %d\n", irq);
return err;
}
- cpumask_copy(data->affinity, mask);
-
- return 0;
+ return IRQ_SET_MASK_OK;
}
+static struct irq_chip lapic_controller = {
+ .irq_ack = apic_ack_edge,
+ .irq_set_affinity = apic_set_affinity,
+ .irq_retrigger = apic_retrigger_irq,
+};
+
#ifdef CONFIG_SMP
-void send_cleanup_vector(struct irq_cfg *cfg)
+static void __send_cleanup_vector(struct apic_chip_data *data)
{
cpumask_var_t cleanup_mask;
if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
unsigned int i;
- for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ for_each_cpu_and(i, data->old_domain, cpu_online_mask)
apic->send_IPI_mask(cpumask_of(i),
IRQ_MOVE_CLEANUP_VECTOR);
} else {
- cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+ cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
free_cpumask_var(cleanup_mask);
}
- cfg->move_in_progress = 0;
+ data->move_in_progress = 0;
+}
+
+void send_cleanup_vector(struct irq_cfg *cfg)
+{
+ struct apic_chip_data *data;
+
+ data = container_of(cfg, struct apic_chip_data, cfg);
+ if (data->move_in_progress)
+ __send_cleanup_vector(data);
}
asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
{
unsigned vector, me;
- ack_APIC_irq();
- irq_enter();
- exit_idle();
+ entering_ack_irq();
me = smp_processor_id();
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
int irq;
unsigned int irr;
struct irq_desc *desc;
- struct irq_cfg *cfg;
+ struct apic_chip_data *data;
irq = __this_cpu_read(vector_irq[vector]);
@@ -417,8 +560,8 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
if (!desc)
continue;
- cfg = irq_cfg(irq);
- if (!cfg)
+ data = apic_chip_data(&desc->irq_data);
+ if (!data)
continue;
raw_spin_lock(&desc->lock);
@@ -427,10 +570,11 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
* Check if the irq migration is in progress. If so, we
* haven't received the cleanup request yet for this irq.
*/
- if (cfg->move_in_progress)
+ if (data->move_in_progress)
goto unlock;
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+ if (vector == data->cfg.vector &&
+ cpumask_test_cpu(me, data->domain))
goto unlock;
irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
@@ -450,20 +594,21 @@ unlock:
raw_spin_unlock(&desc->lock);
}
- irq_exit();
+ exiting_irq();
}
static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
{
unsigned me;
+ struct apic_chip_data *data;
- if (likely(!cfg->move_in_progress))
+ data = container_of(cfg, struct apic_chip_data, cfg);
+ if (likely(!data->move_in_progress))
return;
me = smp_processor_id();
-
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
- send_cleanup_vector(cfg);
+ if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain))
+ __send_cleanup_vector(data);
}
void irq_complete_move(struct irq_cfg *cfg)
@@ -475,46 +620,11 @@ void irq_force_complete_move(int irq)
{
struct irq_cfg *cfg = irq_cfg(irq);
- if (!cfg)
- return;
-
- __irq_complete_move(cfg, cfg->vector);
+ if (cfg)
+ __irq_complete_move(cfg, cfg->vector);
}
#endif
-/*
- * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
- */
-int arch_setup_hwirq(unsigned int irq, int node)
-{
- struct irq_cfg *cfg;
- unsigned long flags;
- int ret;
-
- cfg = alloc_irq_cfg(irq, node);
- if (!cfg)
- return -ENOMEM;
-
- raw_spin_lock_irqsave(&vector_lock, flags);
- ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
- raw_spin_unlock_irqrestore(&vector_lock, flags);
-
- if (!ret)
- irq_set_chip_data(irq, cfg);
- else
- free_irq_cfg(irq, cfg);
- return ret;
-}
-
-void arch_teardown_hwirq(unsigned int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- free_remapped_irq(irq);
- clear_irq_vector(irq, cfg);
- free_irq_cfg(irq, cfg);
-}
-
static void __init print_APIC_field(int base)
{
int i;
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 6fae733e9194..3ffd925655e0 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -21,11 +21,13 @@ early_param("x2apic_phys", set_x2apic_phys_mode);
static bool x2apic_fadt_phys(void)
{
+#ifdef CONFIG_ACPI
if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
printk(KERN_DEBUG "System requires x2apic physical mode\n");
return true;
}
+#endif
return false;
}
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 9f6b9341950f..8e3d22a1af94 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -41,6 +41,25 @@ void common(void) {
OFFSET(pbe_orig_address, pbe, orig_address);
OFFSET(pbe_next, pbe, next);
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+ BLANK();
+ OFFSET(IA32_SIGCONTEXT_ax, sigcontext_ia32, ax);
+ OFFSET(IA32_SIGCONTEXT_bx, sigcontext_ia32, bx);
+ OFFSET(IA32_SIGCONTEXT_cx, sigcontext_ia32, cx);
+ OFFSET(IA32_SIGCONTEXT_dx, sigcontext_ia32, dx);
+ OFFSET(IA32_SIGCONTEXT_si, sigcontext_ia32, si);
+ OFFSET(IA32_SIGCONTEXT_di, sigcontext_ia32, di);
+ OFFSET(IA32_SIGCONTEXT_bp, sigcontext_ia32, bp);
+ OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp);
+ OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip);
+
+ BLANK();
+ OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+
+ BLANK();
+ OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
+#endif
+
#ifdef CONFIG_PARAVIRT
BLANK();
OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
@@ -49,7 +68,9 @@ void common(void) {
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+#ifdef CONFIG_X86_32
OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+#endif
OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
#endif
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 47703aed74cf..6ce39025f467 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -17,17 +17,6 @@ void foo(void);
void foo(void)
{
- OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax);
- OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx);
- OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx);
- OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx);
- OFFSET(IA32_SIGCONTEXT_si, sigcontext, si);
- OFFSET(IA32_SIGCONTEXT_di, sigcontext, di);
- OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp);
- OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp);
- OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip);
- BLANK();
-
OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
@@ -37,10 +26,6 @@ void foo(void)
OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
BLANK();
- OFFSET(TI_sysenter_return, thread_info, sysenter_return);
- OFFSET(TI_cpu, thread_info, cpu);
- BLANK();
-
OFFSET(PT_EBX, pt_regs, bx);
OFFSET(PT_ECX, pt_regs, cx);
OFFSET(PT_EDX, pt_regs, dx);
@@ -60,9 +45,6 @@ void foo(void)
OFFSET(PT_OLDSS, pt_regs, ss);
BLANK();
- OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
- BLANK();
-
OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
BLANK();
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 5ce6f2da8763..d8f42f902a0f 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -29,27 +29,6 @@ int main(void)
BLANK();
#endif
-#ifdef CONFIG_IA32_EMULATION
- OFFSET(TI_sysenter_return, thread_info, sysenter_return);
- BLANK();
-
-#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry)
- ENTRY(ax);
- ENTRY(bx);
- ENTRY(cx);
- ENTRY(dx);
- ENTRY(si);
- ENTRY(di);
- ENTRY(bp);
- ENTRY(sp);
- ENTRY(ip);
- BLANK();
-#undef ENTRY
-
- OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
- BLANK();
-#endif
-
#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
ENTRY(bx);
ENTRY(cx);
@@ -87,7 +66,7 @@ int main(void)
DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
DEFINE(NR_syscalls, sizeof(syscalls_64));
- DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1);
+ DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1);
DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
return 0;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e4cf63301ff4..dd3a4baffe50 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -19,6 +19,13 @@
#include "cpu.h"
+/*
+ * nodes_per_socket: Stores the number of nodes per socket.
+ * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
+ * Node Identifiers[10:8]
+ */
+static u32 nodes_per_socket = 1;
+
static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
{
u32 gprs[8] = { 0 };
@@ -288,10 +295,10 @@ static int nearby_node(int apicid)
* Assumption: Number of cores in each internal node is the same.
* (2) AMD processors supporting compute units
*/
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
static void amd_get_topology(struct cpuinfo_x86 *c)
{
- u32 nodes, cores_per_cu = 1;
+ u32 cores_per_cu = 1;
u8 node_id;
int cpu = smp_processor_id();
@@ -300,7 +307,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
u32 eax, ebx, ecx, edx;
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- nodes = ((ecx >> 8) & 7) + 1;
+ nodes_per_socket = ((ecx >> 8) & 7) + 1;
node_id = ecx & 7;
/* get compute unit information */
@@ -311,18 +318,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
u64 value;
rdmsrl(MSR_FAM10H_NODE_ID, value);
- nodes = ((value >> 3) & 7) + 1;
+ nodes_per_socket = ((value >> 3) & 7) + 1;
node_id = value & 7;
} else
return;
/* fixup multi-node processor information */
- if (nodes > 1) {
+ if (nodes_per_socket > 1) {
u32 cores_per_node;
u32 cus_per_node;
set_cpu_cap(c, X86_FEATURE_AMD_DCM);
- cores_per_node = c->x86_max_cores / nodes;
+ cores_per_node = c->x86_max_cores / nodes_per_socket;
cus_per_node = cores_per_node / cores_per_cu;
/* store NodeID, use llc_shared_map to store sibling info */
@@ -341,7 +348,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
*/
static void amd_detect_cmp(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
@@ -366,6 +373,12 @@ u16 amd_get_nb_id(int cpu)
}
EXPORT_SYMBOL_GPL(amd_get_nb_id);
+u32 amd_get_nodes_per_socket(void)
+{
+ return nodes_per_socket;
+}
+EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket);
+
static void srat_detect_node(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_NUMA
@@ -420,7 +433,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
static void early_init_amd_mc(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned bits, ecx;
/* Multi core CPU? */
@@ -520,8 +533,16 @@ static void early_init_amd(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_K6_MTRR);
#endif
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
- /* check CPU config space for extended APIC ID */
- if (cpu_has_apic && c->x86 >= 0xf) {
+ /*
+ * ApicID can always be treated as an 8-bit value for AMD APIC versions
+ * >= 0x10, but even old K8s came out of reset with version 0x10. So, we
+ * can safely set X86_FEATURE_EXTD_APICID unconditionally for families
+ * after 16h.
+ */
+ if (cpu_has_apic && c->x86 > 0x16) {
+ set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+ } else if (cpu_has_apic && c->x86 >= 0xf) {
+ /* check CPU config space for extended APIC ID */
unsigned int val;
val = read_pci_config(0, 24, 0, 0x68);
if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 03445346ee0a..bd17db15a2c1 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,57 +12,11 @@
#include <asm/bugs.h>
#include <asm/processor.h>
#include <asm/processor-flags.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
#include <asm/msr.h>
#include <asm/paravirt.h>
#include <asm/alternative.h>
-static double __initdata x = 4195835.0;
-static double __initdata y = 3145727.0;
-
-/*
- * This used to check for exceptions..
- * However, it turns out that to support that,
- * the XMM trap handlers basically had to
- * be buggy. So let's have a correct XMM trap
- * handler, and forget about printing out
- * some status at boot.
- *
- * We should really only care about bugs here
- * anyway. Not features.
- */
-static void __init check_fpu(void)
-{
- s32 fdiv_bug;
-
- kernel_fpu_begin();
-
- /*
- * trap_init() enabled FXSR and company _before_ testing for FP
- * problems here.
- *
- * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
- */
- __asm__("fninit\n\t"
- "fldl %1\n\t"
- "fdivl %2\n\t"
- "fmull %2\n\t"
- "fldl %1\n\t"
- "fsubp %%st,%%st(1)\n\t"
- "fistpl %0\n\t"
- "fwait\n\t"
- "fninit"
- : "=m" (*&fdiv_bug)
- : "m" (*&x), "m" (*&y));
-
- kernel_fpu_end();
-
- if (fdiv_bug) {
- set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
- pr_warn("Hmm, FPU with FDIV bug\n");
- }
-}
-
void __init check_bugs(void)
{
identify_boot_cpu();
@@ -85,10 +39,5 @@ void __init check_bugs(void)
'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
alternative_instructions();
- /*
- * kernel_fpu_begin/end() in check_fpu() relies on the patched
- * alternative instructions.
- */
- if (cpu_has_fpu)
- check_fpu();
+ fpu__init_check_bugs();
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a62cf04dac8a..9fc5e3d9d9c8 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -5,6 +5,7 @@
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/string.h>
+#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/sched.h>
#include <linux/init.h>
@@ -31,8 +32,7 @@
#include <asm/setup.h>
#include <asm/apic.h>
#include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/mtrr.h>
#include <linux/numa.h>
#include <asm/asm.h>
@@ -145,32 +145,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
-static int __init x86_xsave_setup(char *s)
+static int __init x86_mpx_setup(char *s)
{
+ /* require an exact match without trailing characters */
if (strlen(s))
return 0;
- setup_clear_cpu_cap(X86_FEATURE_XSAVE);
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
- setup_clear_cpu_cap(X86_FEATURE_XSAVES);
- setup_clear_cpu_cap(X86_FEATURE_AVX);
- setup_clear_cpu_cap(X86_FEATURE_AVX2);
- return 1;
-}
-__setup("noxsave", x86_xsave_setup);
-static int __init x86_xsaveopt_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
- return 1;
-}
-__setup("noxsaveopt", x86_xsaveopt_setup);
+ /* do not emit a message if the feature is not present */
+ if (!boot_cpu_has(X86_FEATURE_MPX))
+ return 1;
-static int __init x86_xsaves_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+ setup_clear_cpu_cap(X86_FEATURE_MPX);
+ pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
return 1;
}
-__setup("noxsaves", x86_xsaves_setup);
+__setup("nompx", x86_mpx_setup);
#ifdef CONFIG_X86_32
static int cachesize_override = -1;
@@ -183,14 +172,6 @@ static int __init cachesize_setup(char *str)
}
__setup("cachesize=", cachesize_setup);
-static int __init x86_fxsr_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_FXSR);
- setup_clear_cpu_cap(X86_FEATURE_XMM);
- return 1;
-}
-__setup("nofxsr", x86_fxsr_setup);
-
static int __init x86_sep_setup(char *s)
{
setup_clear_cpu_cap(X86_FEATURE_SEP);
@@ -419,7 +400,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
static void get_model_name(struct cpuinfo_x86 *c)
{
unsigned int *v;
- char *p, *q;
+ char *p, *q, *s;
if (c->extended_cpuid_level < 0x80000004)
return;
@@ -430,19 +411,21 @@ static void get_model_name(struct cpuinfo_x86 *c)
cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
c->x86_model_id[48] = 0;
- /*
- * Intel chips right-justify this string for some dumb reason;
- * undo that brain damage:
- */
- p = q = &c->x86_model_id[0];
+ /* Trim whitespace */
+ p = q = s = &c->x86_model_id[0];
+
while (*p == ' ')
p++;
- if (p != q) {
- while (*p)
- *q++ = *p++;
- while (q <= &c->x86_model_id[48])
- *q++ = '\0'; /* Zero-pad the rest */
+
+ while (*p) {
+ /* Note the last non-whitespace index */
+ if (!isspace(*p))
+ s = q;
+
+ *q++ = *p++;
}
+
+ *(s + 1) = '\0';
}
void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
@@ -508,7 +491,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
void detect_ht(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
u32 eax, ebx, ecx, edx;
int index_msb, core_bits;
static bool printed;
@@ -759,7 +742,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
cpu_detect(c);
get_cpu_vendor(c);
get_cpu_cap(c);
- fpu_detect(c);
+ fpu__init_system(c);
if (this_cpu->c_early_init)
this_cpu->c_early_init(c);
@@ -844,7 +827,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
if (c->cpuid_level >= 0x00000001) {
c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
# else
c->apicid = c->initial_apicid;
@@ -1026,7 +1009,7 @@ void enable_sep_cpu(void)
(unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
0);
- wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);
+ wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
out:
put_cpu();
@@ -1122,7 +1105,7 @@ void print_cpu_info(struct cpuinfo_x86 *c)
printk(KERN_CONT "%s ", vendor);
if (c->x86_model_id[0])
- printk(KERN_CONT "%s", strim(c->x86_model_id));
+ printk(KERN_CONT "%s", c->x86_model_id);
else
printk(KERN_CONT "%d86", c->x86);
@@ -1155,10 +1138,6 @@ static __init int setup_disablecpuid(char *arg)
}
__setup("clearcpuid=", setup_disablecpuid);
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
- (unsigned long)&init_thread_union + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
#ifdef CONFIG_X86_64
struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1183,8 +1162,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
EXPORT_PER_CPU_SYMBOL(__preempt_count);
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
-
/*
* Special IST stacks which the CPU switches to when it calls
* an IST-marked descriptor entry. Up to 7 stacks (hardware
@@ -1208,10 +1185,10 @@ void syscall_init(void)
* set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
*/
wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32);
- wrmsrl(MSR_LSTAR, system_call);
+ wrmsrl(MSR_LSTAR, entry_SYSCALL_64);
#ifdef CONFIG_IA32_EMULATION
- wrmsrl(MSR_CSTAR, ia32_cstar_target);
+ wrmsrl(MSR_CSTAR, entry_SYSCALL_compat);
/*
* This only works on Intel CPUs.
* On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
@@ -1220,7 +1197,7 @@ void syscall_init(void)
*/
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
#else
wrmsrl(MSR_CSTAR, ignore_sysret);
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
@@ -1275,7 +1252,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
EXPORT_PER_CPU_SYMBOL(current_task);
DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
EXPORT_PER_CPU_SYMBOL(__preempt_count);
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
/*
* On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
@@ -1439,7 +1415,7 @@ void cpu_init(void)
clear_all_debug_regs();
dbg_restore_debug_regs();
- fpu_init();
+ fpu__init_cpu();
if (is_uv_system())
uv_cpu_init();
@@ -1495,7 +1471,7 @@ void cpu_init(void)
clear_all_debug_regs();
dbg_restore_debug_regs();
- fpu_init();
+ fpu__init_cpu();
}
#endif
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index edcb0e28c336..be4febc58b94 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -654,7 +654,7 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned int cpu = c->cpu_index;
#endif
@@ -773,19 +773,19 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
if (new_l2) {
l2 = new_l2;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
per_cpu(cpu_llc_id, cpu) = l2_id;
#endif
}
if (new_l3) {
l3 = new_l3;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
per_cpu(cpu_llc_id, cpu) = l3_id;
#endif
}
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
/*
* If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
* turns means that the only possibility is SMT (as indicated in
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e535533d5ab8..df919ff103c3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -53,9 +53,12 @@
static DEFINE_MUTEX(mce_chrdev_read_mutex);
#define rcu_dereference_check_mce(p) \
- rcu_dereference_index_check((p), \
- rcu_read_lock_sched_held() || \
- lockdep_is_held(&mce_chrdev_read_mutex))
+({ \
+ rcu_lockdep_assert(rcu_read_lock_sched_held() || \
+ lockdep_is_held(&mce_chrdev_read_mutex), \
+ "suspicious rcu_dereference_check_mce() usage"); \
+ smp_load_acquire(&(p)); \
+})
#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
@@ -708,6 +711,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
struct pt_regs *regs)
{
int i, ret = 0;
+ char *tmp;
for (i = 0; i < mca_cfg.banks; i++) {
m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
@@ -716,9 +720,11 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
if (quirk_no_way_out)
quirk_no_way_out(i, m, regs);
}
- if (mce_severity(m, mca_cfg.tolerant, msg, true) >=
- MCE_PANIC_SEVERITY)
+
+ if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+ *msg = tmp;
ret = 1;
+ }
}
return ret;
}
@@ -1047,6 +1053,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
char *msg = "Unknown";
u64 recover_paddr = ~0ull;
int flags = MF_ACTION_REQUIRED;
+ int lmce = 0;
prev_state = ist_enter(regs);
@@ -1074,11 +1081,20 @@ void do_machine_check(struct pt_regs *regs, long error_code)
kill_it = 1;
/*
- * Go through all the banks in exclusion of the other CPUs.
- * This way we don't report duplicated events on shared banks
- * because the first one to see it will clear it.
+ * Check if this MCE is signaled to only this logical processor
*/
- order = mce_start(&no_way_out);
+ if (m.mcgstatus & MCG_STATUS_LMCES)
+ lmce = 1;
+ else {
+ /*
+ * Go through all the banks in exclusion of the other CPUs.
+ * This way we don't report duplicated events on shared banks
+ * because the first one to see it will clear it.
+ * If this is a Local MCE, then no need to perform rendezvous.
+ */
+ order = mce_start(&no_way_out);
+ }
+
for (i = 0; i < cfg->banks; i++) {
__clear_bit(i, toclear);
if (!test_bit(i, valid_banks))
@@ -1155,8 +1171,18 @@ void do_machine_check(struct pt_regs *regs, long error_code)
* Do most of the synchronization with other CPUs.
* When there's any problem use only local no_way_out state.
*/
- if (mce_end(order) < 0)
- no_way_out = worst >= MCE_PANIC_SEVERITY;
+ if (!lmce) {
+ if (mce_end(order) < 0)
+ no_way_out = worst >= MCE_PANIC_SEVERITY;
+ } else {
+ /*
+ * Local MCE skipped calling mce_reign()
+ * If we found a fatal error, we need to panic here.
+ */
+ if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
+ mce_panic("Machine check from unknown source",
+ NULL, NULL);
+ }
/*
* At insane "tolerant" levels we take no action. Otherwise
@@ -1637,10 +1663,16 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
mce_intel_feature_init(c);
mce_adjust_timer = cmci_intel_adjust_timer;
break;
- case X86_VENDOR_AMD:
+
+ case X86_VENDOR_AMD: {
+ u32 ebx = cpuid_ebx(0x80000007);
+
mce_amd_feature_init(c);
- mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1;
+ mce_flags.overflow_recov = !!(ebx & BIT(0));
+ mce_flags.succor = !!(ebx & BIT(1));
break;
+ }
+
default:
break;
}
@@ -1884,7 +1916,7 @@ out:
static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &mce_chrdev_wait, wait);
- if (rcu_access_index(mcelog.next))
+ if (READ_ONCE(mcelog.next))
return POLLIN | POLLRDNORM;
if (!mce_apei_read_done && apei_check_mce())
return POLLIN | POLLRDNORM;
@@ -1929,8 +1961,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
}
EXPORT_SYMBOL_GPL(register_mce_write_callback);
-ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
- size_t usize, loff_t *off)
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+ size_t usize, loff_t *off)
{
if (mce_write)
return mce_write(filp, ubuf, usize, off);
@@ -1976,6 +2008,7 @@ void mce_disable_bank(int bank)
/*
* mce=off Disables machine check
* mce=no_cmci Disables CMCI
+ * mce=no_lmce Disables LMCE
* mce=dont_log_ce Clears corrected events silently, no log created for CEs.
* mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
* mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
@@ -1999,6 +2032,8 @@ static int __init mcheck_enable(char *str)
cfg->disabled = true;
else if (!strcmp(str, "no_cmci"))
cfg->cmci_disabled = true;
+ else if (!strcmp(str, "no_lmce"))
+ cfg->lmce_disabled = true;
else if (!strcmp(str, "dont_log_ce"))
cfg->dont_log_ce = true;
else if (!strcmp(str, "ignore_ce"))
@@ -2008,11 +2043,8 @@ static int __init mcheck_enable(char *str)
else if (!strcmp(str, "bios_cmci_threshold"))
cfg->bios_cmci_threshold = true;
else if (isdigit(str[0])) {
- get_option(&str, &(cfg->tolerant));
- if (*str == ',') {
- ++str;
+ if (get_option(&str, &cfg->tolerant) == 2)
get_option(&str, &(cfg->monarch_timeout));
- }
} else {
pr_info("mce argument %s ignored. Please use /sys\n", str);
return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 55ad9b37cae8..e99b15077e94 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1,19 +1,13 @@
/*
- * (c) 2005-2012 Advanced Micro Devices, Inc.
+ * (c) 2005-2015 Advanced Micro Devices, Inc.
* Your use of this code is subject to the terms and conditions of the
* GNU general public license version 2. See "COPYING" or
* http://www.gnu.org/licenses/gpl.html
*
* Written by Jacob Shin - AMD, Inc.
- *
* Maintained by: Borislav Petkov <bp@alien8.de>
*
- * April 2006
- * - added support for AMD Family 0x10 processors
- * May 2012
- * - major scrubbing
- *
- * All MC4_MISCi registers are shared between multi-cores
+ * All MC4_MISCi registers are shared between cores on a node.
*/
#include <linux/interrupt.h>
#include <linux/notifier.h>
@@ -32,6 +26,7 @@
#include <asm/idle.h>
#include <asm/mce.h>
#include <asm/msr.h>
+#include <asm/trace/irq_vectors.h>
#define NR_BLOCKS 9
#define THRESHOLD_MAX 0xFFF
@@ -47,6 +42,13 @@
#define MASK_BLKPTR_LO 0xFF000000
#define MCG_XBLK_ADDR 0xC0000400
+/* Deferred error settings */
+#define MSR_CU_DEF_ERR 0xC0000410
+#define MASK_DEF_LVTOFF 0x000000F0
+#define MASK_DEF_INT_TYPE 0x00000006
+#define DEF_LVT_OFF 0x2
+#define DEF_INT_TYPE_APIC 0x2
+
static const char * const th_names[] = {
"load_store",
"insn_fetch",
@@ -60,6 +62,13 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */
static void amd_threshold_interrupt(void);
+static void amd_deferred_error_interrupt(void);
+
+static void default_deferred_error_interrupt(void)
+{
+ pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR);
+}
+void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
/*
* CPU Initialization
@@ -196,7 +205,7 @@ static void mce_threshold_block_init(struct threshold_block *b, int offset)
threshold_restart_bank(&tr);
};
-static int setup_APIC_mce(int reserved, int new)
+static int setup_APIC_mce_threshold(int reserved, int new)
{
if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
APIC_EILVT_MSG_FIX, 0))
@@ -205,6 +214,39 @@ static int setup_APIC_mce(int reserved, int new)
return reserved;
}
+static int setup_APIC_deferred_error(int reserved, int new)
+{
+ if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
+ APIC_EILVT_MSG_FIX, 0))
+ return new;
+
+ return reserved;
+}
+
+static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
+{
+ u32 low = 0, high = 0;
+ int def_offset = -1, def_new;
+
+ if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
+ return;
+
+ def_new = (low & MASK_DEF_LVTOFF) >> 4;
+ if (!(low & MASK_DEF_LVTOFF)) {
+ pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
+ def_new = DEF_LVT_OFF;
+ low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
+ }
+
+ def_offset = setup_APIC_deferred_error(def_offset, def_new);
+ if ((def_offset == def_new) &&
+ (deferred_error_int_vector != amd_deferred_error_interrupt))
+ deferred_error_int_vector = amd_deferred_error_interrupt;
+
+ low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+ wrmsr(MSR_CU_DEF_ERR, low, high);
+}
+
/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
@@ -252,7 +294,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
b.interrupt_enable = 1;
new = (high & MASK_LVTOFF_HI) >> 20;
- offset = setup_APIC_mce(offset, new);
+ offset = setup_APIC_mce_threshold(offset, new);
if ((offset == new) &&
(mce_threshold_vector != amd_threshold_interrupt))
@@ -262,6 +304,73 @@ init:
mce_threshold_block_init(&b, offset);
}
}
+
+ if (mce_flags.succor)
+ deferred_error_interrupt_enable(c);
+}
+
+static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
+{
+ struct mce m;
+ u64 status;
+
+ rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+ if (!(status & MCI_STATUS_VAL))
+ return;
+
+ mce_setup(&m);
+
+ m.status = status;
+ m.bank = bank;
+
+ if (threshold_err)
+ m.misc = misc;
+
+ if (m.status & MCI_STATUS_ADDRV)
+ rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr);
+
+ mce_log(&m);
+ wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+}
+
+static inline void __smp_deferred_error_interrupt(void)
+{
+ inc_irq_stat(irq_deferred_error_count);
+ deferred_error_int_vector();
+}
+
+asmlinkage __visible void smp_deferred_error_interrupt(void)
+{
+ entering_irq();
+ __smp_deferred_error_interrupt();
+ exiting_ack_irq();
+}
+
+asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
+{
+ entering_irq();
+ trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
+ __smp_deferred_error_interrupt();
+ trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
+ exiting_ack_irq();
+}
+
+/* APIC interrupt handler for deferred errors */
+static void amd_deferred_error_interrupt(void)
+{
+ u64 status;
+ unsigned int bank;
+
+ for (bank = 0; bank < mca_cfg.banks; ++bank) {
+ rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+
+ if (!(status & MCI_STATUS_VAL) ||
+ !(status & MCI_STATUS_DEFERRED))
+ continue;
+
+ __log_error(bank, false, 0);
+ break;
+ }
}
/*
@@ -273,12 +382,12 @@ init:
* the interrupt goes off when error_count reaches threshold_limit.
* the handler will simply log mcelog w/ software defined bank number.
*/
+
static void amd_threshold_interrupt(void)
{
u32 low = 0, high = 0, address = 0;
int cpu = smp_processor_id();
unsigned int bank, block;
- struct mce m;
/* assume first bank caused it */
for (bank = 0; bank < mca_cfg.banks; ++bank) {
@@ -321,15 +430,7 @@ static void amd_threshold_interrupt(void)
return;
log:
- mce_setup(&m);
- rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status);
- if (!(m.status & MCI_STATUS_VAL))
- return;
- m.misc = ((u64)high << 32) | low;
- m.bank = bank;
- mce_log(&m);
-
- wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+ __log_error(bank, true, ((u64)high << 32) | low);
}
/*
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index b4a41cf030ed..844f56c5616d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -91,6 +91,36 @@ static int cmci_supported(int *banks)
return !!(cap & MCG_CMCI_P);
}
+static bool lmce_supported(void)
+{
+ u64 tmp;
+
+ if (mca_cfg.lmce_disabled)
+ return false;
+
+ rdmsrl(MSR_IA32_MCG_CAP, tmp);
+
+ /*
+ * LMCE depends on recovery support in the processor. Hence both
+ * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP.
+ */
+ if ((tmp & (MCG_SER_P | MCG_LMCE_P)) !=
+ (MCG_SER_P | MCG_LMCE_P))
+ return false;
+
+ /*
+ * BIOS should indicate support for LMCE by setting bit 20 in
+ * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will
+ * generate a #GP fault.
+ */
+ rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp);
+ if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) ==
+ (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE))
+ return true;
+
+ return false;
+}
+
bool mce_intel_cmci_poll(void)
{
if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
@@ -405,8 +435,22 @@ static void intel_init_cmci(void)
cmci_recheck();
}
+void intel_init_lmce(void)
+{
+ u64 val;
+
+ if (!lmce_supported())
+ return;
+
+ rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+
+ if (!(val & MCG_EXT_CTL_LMCE_EN))
+ wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+}
+
void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
intel_init_thermal(c);
intel_init_cmci();
+ intel_init_lmce();
}
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 737737edbd1e..e8a215a9a345 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -228,7 +228,23 @@ static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch)
}
}
-void __init load_ucode_amd_bsp(void)
+static bool __init load_builtin_amd_microcode(struct cpio_data *cp,
+ unsigned int family)
+{
+#ifdef CONFIG_X86_64
+ char fw_name[36] = "amd-ucode/microcode_amd.bin";
+
+ if (family >= 0x15)
+ snprintf(fw_name, sizeof(fw_name),
+ "amd-ucode/microcode_amd_fam%.2xh.bin", family);
+
+ return get_builtin_firmware(cp, fw_name);
+#else
+ return false;
+#endif
+}
+
+void __init load_ucode_amd_bsp(unsigned int family)
{
struct cpio_data cp;
void **data;
@@ -243,8 +259,10 @@ void __init load_ucode_amd_bsp(void)
#endif
cp = find_ucode_in_initrd();
- if (!cp.data)
- return;
+ if (!cp.data) {
+ if (!load_builtin_amd_microcode(&cp, family))
+ return;
+ }
*data = cp.data;
*size = cp.size;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 36a83617eb21..6236a54a63f4 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -1,74 +1,16 @@
/*
- * Intel CPU Microcode Update Driver for Linux
+ * CPU Microcode Update Driver for Linux
*
- * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- * 2006 Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * 2006 Shaohua Li <shaohua.li@intel.com>
+ * 2013-2015 Borislav Petkov <bp@alien8.de>
*
- * This driver allows to upgrade microcode on Intel processors
- * belonging to IA-32 family - PentiumPro, Pentium II,
- * Pentium III, Xeon, Pentium 4, etc.
+ * This driver allows to upgrade microcode on x86 processors.
*
- * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- * Software Developer's Manual
- * Order Number 253668 or free download from:
- *
- * http://developer.intel.com/Assets/PDF/manual/253668.pdf
- *
- * For more information, go to http://www.urbanmyth.org/microcode
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Initial release.
- * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Added read() support + cleanups.
- * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Added 'device trimming' support. open(O_WRONLY) zeroes
- * and frees the saved copy of applied microcode.
- * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Made to use devfs (/dev/cpu/microcode) + cleanups.
- * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com>
- * Added misc device support (now uses both devfs and misc).
- * Added MICROCODE_IOCFREE ioctl to clear memory.
- * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com>
- * Messages for error cases (non Intel & no suitable microcode).
- * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- * Removed ->release(). Removed exclusive open and status bitmap.
- * Added microcode_rwsem to serialize read()/write()/ioctl().
- * Removed global kernel lock usage.
- * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- * Write 0 to 0x8B msr and then cpuid before reading revision,
- * so that it works even if there were no update done by the
- * BIOS. Otherwise, reading from 0x8B gives junk (which happened
- * to be 0 on my machine which is why it worked even when I
- * disabled update by the BIOS)
- * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- * Tigran Aivazian <tigran@veritas.com>
- * Intel Pentium 4 processor support and bugfixes.
- * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- * Bugfix for HT (Hyper-Threading) enabled processors
- * whereby processor resources are shared by all logical processors
- * in a single CPU package.
- * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- * Tigran Aivazian <tigran@veritas.com>,
- * Serialize updates as required on HT processors due to
- * speculative nature of implementation.
- * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- * Fix the panic when writing zero-length microcode chunk.
- * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- * Jun Nakajima <jun.nakajima@intel.com>
- * Support for the microcode updates in the new format.
- * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- * because we no longer hold a copy of applied microcode
- * in kernel memory.
- * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- * Fix sigmatch() macro to handle old CPUs with pf == 0.
- * Thanks to Stuart Swales for pointing out this bug.
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
index a413a69cbd74..8ebc421d6299 100644
--- a/arch/x86/kernel/cpu/microcode/core_early.c
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -3,6 +3,7 @@
*
* Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
* H Peter Anvin" <hpa@zytor.com>
+ * (C) 2015 Borislav Petkov <bp@alien8.de>
*
* This driver allows to early upgrade microcode on Intel processors
* belonging to IA-32 family - PentiumPro, Pentium II,
@@ -17,6 +18,7 @@
* 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
+#include <linux/firmware.h>
#include <asm/microcode.h>
#include <asm/microcode_intel.h>
#include <asm/microcode_amd.h>
@@ -43,9 +45,29 @@ static bool __init check_loader_disabled_bsp(void)
return *res;
}
+extern struct builtin_fw __start_builtin_fw[];
+extern struct builtin_fw __end_builtin_fw[];
+
+bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+#ifdef CONFIG_FW_LOADER
+ struct builtin_fw *b_fw;
+
+ for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) {
+ if (!strcmp(name, b_fw->name)) {
+ cd->size = b_fw->size;
+ cd->data = b_fw->data;
+ return true;
+ }
+ }
+#endif
+ return false;
+}
+
void __init load_ucode_bsp(void)
{
- int vendor, family;
+ int vendor;
+ unsigned int family;
if (check_loader_disabled_bsp())
return;
@@ -63,7 +85,7 @@ void __init load_ucode_bsp(void)
break;
case X86_VENDOR_AMD:
if (family >= 0x10)
- load_ucode_amd_bsp();
+ load_ucode_amd_bsp(family);
break;
default:
break;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a41beadb3db9..969dc17eb1b4 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -1,74 +1,13 @@
/*
- * Intel CPU Microcode Update Driver for Linux
+ * Intel CPU Microcode Update Driver for Linux
*
- * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- * 2006 Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * 2006 Shaohua Li <shaohua.li@intel.com>
*
- * This driver allows to upgrade microcode on Intel processors
- * belonging to IA-32 family - PentiumPro, Pentium II,
- * Pentium III, Xeon, Pentium 4, etc.
- *
- * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- * Software Developer's Manual
- * Order Number 253668 or free download from:
- *
- * http://developer.intel.com/Assets/PDF/manual/253668.pdf
- *
- * For more information, go to http://www.urbanmyth.org/microcode
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Initial release.
- * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Added read() support + cleanups.
- * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Added 'device trimming' support. open(O_WRONLY) zeroes
- * and frees the saved copy of applied microcode.
- * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Made to use devfs (/dev/cpu/microcode) + cleanups.
- * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com>
- * Added misc device support (now uses both devfs and misc).
- * Added MICROCODE_IOCFREE ioctl to clear memory.
- * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com>
- * Messages for error cases (non Intel & no suitable microcode).
- * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- * Removed ->release(). Removed exclusive open and status bitmap.
- * Added microcode_rwsem to serialize read()/write()/ioctl().
- * Removed global kernel lock usage.
- * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- * Write 0 to 0x8B msr and then cpuid before reading revision,
- * so that it works even if there were no update done by the
- * BIOS. Otherwise, reading from 0x8B gives junk (which happened
- * to be 0 on my machine which is why it worked even when I
- * disabled update by the BIOS)
- * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- * Tigran Aivazian <tigran@veritas.com>
- * Intel Pentium 4 processor support and bugfixes.
- * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- * Bugfix for HT (Hyper-Threading) enabled processors
- * whereby processor resources are shared by all logical processors
- * in a single CPU package.
- * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- * Tigran Aivazian <tigran@veritas.com>,
- * Serialize updates as required on HT processors due to
- * speculative nature of implementation.
- * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- * Fix the panic when writing zero-length microcode chunk.
- * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- * Jun Nakajima <jun.nakajima@intel.com>
- * Support for the microcode updates in the new format.
- * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- * because we no longer hold a copy of applied microcode
- * in kernel memory.
- * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- * Fix sigmatch() macro to handle old CPUs with pf == 0.
- * Thanks to Stuart Swales for pointing out this bug.
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -124,7 +63,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
cpf = cpu_sig.pf;
crev = cpu_sig.rev;
- return get_matching_microcode(csig, cpf, crev, mc_intel);
+ return has_newer_microcode(mc_intel, csig, cpf, crev);
}
static int apply_microcode_intel(int cpu)
@@ -226,7 +165,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
csig = uci->cpu_sig.sig;
cpf = uci->cpu_sig.pf;
- if (get_matching_microcode(csig, cpf, new_rev, mc)) {
+ if (has_newer_microcode(mc, csig, cpf, new_rev)) {
vfree(new_mc);
new_rev = mc_header.rev;
new_mc = mc;
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index 2f49ab4ac0ae..8187b7247d1c 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -59,10 +59,10 @@ load_microcode_early(struct microcode_intel **saved,
ucode_ptr = saved[i];
mc_hdr = (struct microcode_header_intel *)ucode_ptr;
- ret = get_matching_microcode(uci->cpu_sig.sig,
- uci->cpu_sig.pf,
- new_rev,
- ucode_ptr);
+ ret = has_newer_microcode(ucode_ptr,
+ uci->cpu_sig.sig,
+ uci->cpu_sig.pf,
+ new_rev);
if (!ret)
continue;
@@ -246,7 +246,7 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
u8 *ucode_ptr, unsigned int num_saved)
{
struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
- unsigned int sig, pf, new_rev;
+ unsigned int sig, pf;
int found = 0, i;
mc_hdr = (struct microcode_header_intel *)ucode_ptr;
@@ -255,14 +255,13 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i];
sig = mc_saved_hdr->sig;
pf = mc_saved_hdr->pf;
- new_rev = mc_hdr->rev;
- if (!get_matching_sig(sig, pf, new_rev, ucode_ptr))
+ if (!find_matching_signature(ucode_ptr, sig, pf))
continue;
found = 1;
- if (!revision_is_newer(mc_hdr, new_rev))
+ if (mc_hdr->rev <= mc_saved_hdr->rev)
continue;
/*
@@ -522,6 +521,27 @@ out:
EXPORT_SYMBOL_GPL(save_mc_for_early);
#endif
+static bool __init load_builtin_intel_microcode(struct cpio_data *cp)
+{
+#ifdef CONFIG_X86_64
+ unsigned int eax = 0x00000001, ebx, ecx = 0, edx;
+ unsigned int family, model, stepping;
+ char name[30];
+
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+
+ family = __x86_family(eax);
+ model = x86_model(eax);
+ stepping = eax & 0xf;
+
+ sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping);
+
+ return get_builtin_firmware(cp, name);
+#else
+ return false;
+#endif
+}
+
static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
static __init enum ucode_state
scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
@@ -540,8 +560,10 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
cd.size = 0;
cd = find_cpio_data(p, (void *)start, size, &offset);
- if (!cd.data)
- return UCODE_ERROR;
+ if (!cd.data) {
+ if (!load_builtin_intel_microcode(&cd))
+ return UCODE_ERROR;
+ }
return get_matching_model_microcode(0, start, cd.data, cd.size,
mc_saved_data, initrd, uci);
diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c
index cd47a510a3f1..1883d252ff7d 100644
--- a/arch/x86/kernel/cpu/microcode/intel_lib.c
+++ b/arch/x86/kernel/cpu/microcode/intel_lib.c
@@ -31,11 +31,18 @@
#include <asm/processor.h>
#include <asm/msr.h>
-static inline int
-update_match_cpu(unsigned int csig, unsigned int cpf,
- unsigned int sig, unsigned int pf)
+static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
+ unsigned int s2, unsigned int p2)
{
- return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1;
+ if (s1 != s2)
+ return false;
+
+ /* Processor flags are either both 0 ... */
+ if (!p1 && !p2)
+ return true;
+
+ /* ... or they intersect. */
+ return p1 & p2;
}
int microcode_sanity_check(void *mc, int print_err)
@@ -124,27 +131,25 @@ EXPORT_SYMBOL_GPL(microcode_sanity_check);
/*
* Returns 1 if update has been found, 0 otherwise.
*/
-int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
+int find_matching_signature(void *mc, unsigned int csig, int cpf)
{
- struct microcode_header_intel *mc_header = mc;
- struct extended_sigtable *ext_header;
- unsigned long total_size = get_totalsize(mc_header);
- int ext_sigcount, i;
+ struct microcode_header_intel *mc_hdr = mc;
+ struct extended_sigtable *ext_hdr;
struct extended_signature *ext_sig;
+ int i;
- if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf))
+ if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
return 1;
/* Look for ext. headers: */
- if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
+ if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE)
return 0;
- ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
- ext_sigcount = ext_header->count;
- ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+ ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE;
+ ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
- for (i = 0; i < ext_sigcount; i++) {
- if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf))
+ for (i = 0; i < ext_hdr->count; i++) {
+ if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
return 1;
ext_sig++;
}
@@ -154,13 +159,13 @@ int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
/*
* Returns 1 if update has been found, 0 otherwise.
*/
-int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc)
+int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
{
struct microcode_header_intel *mc_hdr = mc;
- if (!revision_is_newer(mc_hdr, rev))
+ if (mc_hdr->rev <= new_rev)
return 0;
- return get_matching_sig(csig, cpf, rev, mc);
+ return find_matching_signature(mc, csig, cpf);
}
-EXPORT_SYMBOL_GPL(get_matching_microcode);
+EXPORT_SYMBOL_GPL(has_newer_microcode);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 939155ffdece..aad4bd84b475 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -39,14 +39,12 @@ void hyperv_vector_handler(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- irq_enter();
- exit_idle();
-
+ entering_irq();
inc_irq_stat(irq_hv_callback_count);
if (vmbus_handler)
vmbus_handler();
- irq_exit();
+ exiting_irq();
set_irq_regs(old_regs);
}
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 5f90b85ff22e..70d7c93f4550 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -98,7 +98,8 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
continue;
base = range_state[i].base_pfn;
if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed &&
- (mtrr_state.enabled & 1)) {
+ (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+ (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
/* Var MTRR contains UC entry below 1M? Skip it: */
printk(BIOS_BUG_MSG, i);
if (base + size <= (1<<(20-PAGE_SHIFT)))
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7d74f7b3c6ba..3b533cf37c74 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -102,59 +102,76 @@ static int check_type_overlap(u8 *prev, u8 *curr)
return 0;
}
-/*
- * Error/Semi-error returns:
- * 0xFF - when MTRR is not enabled
- * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
- * corresponds only to [start:*partial_end].
- * Caller has to lookup again for [*partial_end:end].
+/**
+ * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries
+ *
+ * Return the MTRR fixed memory type of 'start'.
+ *
+ * MTRR fixed entries are divided into the following ways:
+ * 0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges
+ * 0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges
+ * 0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges
+ *
+ * Return Values:
+ * MTRR_TYPE_(type) - Matched memory type
+ * MTRR_TYPE_INVALID - Unmatched
+ */
+static u8 mtrr_type_lookup_fixed(u64 start, u64 end)
+{
+ int idx;
+
+ if (start >= 0x100000)
+ return MTRR_TYPE_INVALID;
+
+ /* 0x0 - 0x7FFFF */
+ if (start < 0x80000) {
+ idx = 0;
+ idx += (start >> 16);
+ return mtrr_state.fixed_ranges[idx];
+ /* 0x80000 - 0xBFFFF */
+ } else if (start < 0xC0000) {
+ idx = 1 * 8;
+ idx += ((start - 0x80000) >> 14);
+ return mtrr_state.fixed_ranges[idx];
+ }
+
+ /* 0xC0000 - 0xFFFFF */
+ idx = 3 * 8;
+ idx += ((start - 0xC0000) >> 12);
+ return mtrr_state.fixed_ranges[idx];
+}
+
+/**
+ * mtrr_type_lookup_variable - look up memory type in MTRR variable entries
+ *
+ * Return Value:
+ * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched)
+ *
+ * Output Arguments:
+ * repeat - Set to 1 when [start:end] spanned across MTRR range and type
+ * returned corresponds only to [start:*partial_end]. Caller has
+ * to lookup again for [*partial_end:end].
+ *
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ * region is fully covered by a single MTRR entry or the default
+ * type.
*/
-static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
+static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
+ int *repeat, u8 *uniform)
{
int i;
u64 base, mask;
u8 prev_match, curr_match;
*repeat = 0;
- if (!mtrr_state_set)
- return 0xFF;
-
- if (!mtrr_state.enabled)
- return 0xFF;
+ *uniform = 1;
- /* Make end inclusive end, instead of exclusive */
+ /* Make end inclusive instead of exclusive */
end--;
- /* Look in fixed ranges. Just return the type as per start */
- if (mtrr_state.have_fixed && (start < 0x100000)) {
- int idx;
-
- if (start < 0x80000) {
- idx = 0;
- idx += (start >> 16);
- return mtrr_state.fixed_ranges[idx];
- } else if (start < 0xC0000) {
- idx = 1 * 8;
- idx += ((start - 0x80000) >> 14);
- return mtrr_state.fixed_ranges[idx];
- } else if (start < 0x1000000) {
- idx = 3 * 8;
- idx += ((start - 0xC0000) >> 12);
- return mtrr_state.fixed_ranges[idx];
- }
- }
-
- /*
- * Look in variable ranges
- * Look of multiple ranges matching this address and pick type
- * as per MTRR precedence
- */
- if (!(mtrr_state.enabled & 2))
- return mtrr_state.def_type;
-
- prev_match = 0xFF;
+ prev_match = MTRR_TYPE_INVALID;
for (i = 0; i < num_var_ranges; ++i) {
- unsigned short start_state, end_state;
+ unsigned short start_state, end_state, inclusive;
if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11)))
continue;
@@ -166,20 +183,29 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
start_state = ((start & mask) == (base & mask));
end_state = ((end & mask) == (base & mask));
+ inclusive = ((start < base) && (end > base));
- if (start_state != end_state) {
+ if ((start_state != end_state) || inclusive) {
/*
* We have start:end spanning across an MTRR.
- * We split the region into
- * either
- * (start:mtrr_end) (mtrr_end:end)
- * or
- * (start:mtrr_start) (mtrr_start:end)
+ * We split the region into either
+ *
+ * - start_state:1
+ * (start:mtrr_end)(mtrr_end:end)
+ * - end_state:1
+ * (start:mtrr_start)(mtrr_start:end)
+ * - inclusive:1
+ * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end)
+ *
* depending on kind of overlap.
- * Return the type for first region and a pointer to
- * the start of second region so that caller will
- * lookup again on the second region.
- * Note: This way we handle multiple overlaps as well.
+ *
+ * Return the type of the first region and a pointer
+ * to the start of next region so that caller will be
+ * advised to lookup again after having adjusted start
+ * and end.
+ *
+ * Note: This way we handle overlaps with multiple
+ * entries and the default type properly.
*/
if (start_state)
*partial_end = base + get_mtrr_size(mask);
@@ -193,59 +219,94 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
end = *partial_end - 1; /* end is inclusive */
*repeat = 1;
+ *uniform = 0;
}
if ((start & mask) != (base & mask))
continue;
curr_match = mtrr_state.var_ranges[i].base_lo & 0xff;
- if (prev_match == 0xFF) {
+ if (prev_match == MTRR_TYPE_INVALID) {
prev_match = curr_match;
continue;
}
+ *uniform = 0;
if (check_type_overlap(&prev_match, &curr_match))
return curr_match;
}
- if (mtrr_tom2) {
- if (start >= (1ULL<<32) && (end < mtrr_tom2))
- return MTRR_TYPE_WRBACK;
- }
-
- if (prev_match != 0xFF)
+ if (prev_match != MTRR_TYPE_INVALID)
return prev_match;
return mtrr_state.def_type;
}
-/*
- * Returns the effective MTRR type for the region
- * Error return:
- * 0xFF - when MTRR is not enabled
+/**
+ * mtrr_type_lookup - look up memory type in MTRR
+ *
+ * Return Values:
+ * MTRR_TYPE_(type) - The effective MTRR type for the region
+ * MTRR_TYPE_INVALID - MTRR is disabled
+ *
+ * Output Argument:
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ * region is fully covered by a single MTRR entry or the default
+ * type.
*/
-u8 mtrr_type_lookup(u64 start, u64 end)
+u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
{
- u8 type, prev_type;
+ u8 type, prev_type, is_uniform = 1, dummy;
int repeat;
u64 partial_end;
- type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+ if (!mtrr_state_set)
+ return MTRR_TYPE_INVALID;
+
+ if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED))
+ return MTRR_TYPE_INVALID;
+
+ /*
+ * Look up the fixed ranges first, which take priority over
+ * the variable ranges.
+ */
+ if ((start < 0x100000) &&
+ (mtrr_state.have_fixed) &&
+ (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
+ is_uniform = 0;
+ type = mtrr_type_lookup_fixed(start, end);
+ goto out;
+ }
+
+ /*
+ * Look up the variable ranges. Look of multiple ranges matching
+ * this address and pick type as per MTRR precedence.
+ */
+ type = mtrr_type_lookup_variable(start, end, &partial_end,
+ &repeat, &is_uniform);
/*
* Common path is with repeat = 0.
* However, we can have cases where [start:end] spans across some
- * MTRR range. Do repeated lookups for that case here.
+ * MTRR ranges and/or the default type. Do repeated lookups for
+ * that case here.
*/
while (repeat) {
prev_type = type;
start = partial_end;
- type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+ is_uniform = 0;
+ type = mtrr_type_lookup_variable(start, end, &partial_end,
+ &repeat, &dummy);
if (check_type_overlap(&prev_type, &type))
- return type;
+ goto out;
}
+ if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2))
+ type = MTRR_TYPE_WRBACK;
+
+out:
+ *uniform = is_uniform;
return type;
}
@@ -347,7 +408,9 @@ static void __init print_mtrr_state(void)
mtrr_attrib_to_str(mtrr_state.def_type));
if (mtrr_state.have_fixed) {
pr_debug("MTRR fixed ranges %sabled:\n",
- mtrr_state.enabled & 1 ? "en" : "dis");
+ ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+ (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ?
+ "en" : "dis");
print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
for (i = 0; i < 2; ++i)
print_fixed(0x80000 + i * 0x20000, 0x04000,
@@ -360,7 +423,7 @@ static void __init print_mtrr_state(void)
print_fixed_last();
}
pr_debug("MTRR variable ranges %sabled:\n",
- mtrr_state.enabled & 2 ? "en" : "dis");
+ mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis");
high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4;
for (i = 0; i < num_var_ranges; ++i) {
@@ -382,7 +445,7 @@ static void __init print_mtrr_state(void)
}
/* Grab all of the MTRR state for this CPU into *state */
-void __init get_mtrr_state(void)
+bool __init get_mtrr_state(void)
{
struct mtrr_var_range *vrs;
unsigned long flags;
@@ -426,6 +489,8 @@ void __init get_mtrr_state(void)
post_set();
local_irq_restore(flags);
+
+ return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
}
/* Some BIOS's are messed up and don't set all MTRRs the same! */
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index ea5f363a1948..e7ed0d8ebacb 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -59,6 +59,12 @@
#define MTRR_TO_PHYS_WC_OFFSET 1000
u32 num_var_ranges;
+static bool __mtrr_enabled;
+
+static bool mtrr_enabled(void)
+{
+ return __mtrr_enabled;
+}
unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
static DEFINE_MUTEX(mtrr_mutex);
@@ -286,7 +292,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
int i, replace, error;
mtrr_type ltype;
- if (!mtrr_if)
+ if (!mtrr_enabled())
return -ENXIO;
error = mtrr_if->validate_add_page(base, size, type);
@@ -435,6 +441,8 @@ static int mtrr_check(unsigned long base, unsigned long size)
int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
bool increment)
{
+ if (!mtrr_enabled())
+ return -ENODEV;
if (mtrr_check(base, size))
return -EINVAL;
return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
@@ -463,8 +471,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
unsigned long lbase, lsize;
int error = -EINVAL;
- if (!mtrr_if)
- return -ENXIO;
+ if (!mtrr_enabled())
+ return -ENODEV;
max = num_var_ranges;
/* No CPU hotplug when we change MTRR entries */
@@ -523,6 +531,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
*/
int mtrr_del(int reg, unsigned long base, unsigned long size)
{
+ if (!mtrr_enabled())
+ return -ENODEV;
if (mtrr_check(base, size))
return -EINVAL;
return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
@@ -538,6 +548,9 @@ EXPORT_SYMBOL(mtrr_del);
* attempts to add a WC MTRR covering size bytes starting at base and
* logs an error if this fails.
*
+ * The called should provide a power of two size on an equivalent
+ * power of two boundary.
+ *
* Drivers must store the return value to pass to mtrr_del_wc_if_needed,
* but drivers should not try to interpret that return value.
*/
@@ -545,7 +558,7 @@ int arch_phys_wc_add(unsigned long base, unsigned long size)
{
int ret;
- if (pat_enabled)
+ if (pat_enabled() || !mtrr_enabled())
return 0; /* Success! (We don't need to do anything.) */
ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true);
@@ -577,7 +590,7 @@ void arch_phys_wc_del(int handle)
EXPORT_SYMBOL(arch_phys_wc_del);
/*
- * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value
+ * arch_phys_wc_index - translates arch_phys_wc_add's return value
* @handle: Return value from arch_phys_wc_add
*
* This will turn the return value from arch_phys_wc_add into an mtrr
@@ -587,14 +600,14 @@ EXPORT_SYMBOL(arch_phys_wc_del);
* in printk line. Alas there is an illegitimate use in some ancient
* drm ioctls.
*/
-int phys_wc_to_mtrr_index(int handle)
+int arch_phys_wc_index(int handle)
{
if (handle < MTRR_TO_PHYS_WC_OFFSET)
return -1;
else
return handle - MTRR_TO_PHYS_WC_OFFSET;
}
-EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index);
+EXPORT_SYMBOL_GPL(arch_phys_wc_index);
/*
* HACK ALERT!
@@ -734,10 +747,12 @@ void __init mtrr_bp_init(void)
}
if (mtrr_if) {
+ __mtrr_enabled = true;
set_num_var_ranges();
init_table();
if (use_intel()) {
- get_mtrr_state();
+ /* BIOS may override */
+ __mtrr_enabled = get_mtrr_state();
if (mtrr_cleanup(phys_addr)) {
changed_by_mtrr_cleanup = 1;
@@ -745,10 +760,16 @@ void __init mtrr_bp_init(void)
}
}
}
+
+ if (!mtrr_enabled())
+ pr_info("MTRR: Disabled\n");
}
void mtrr_ap_init(void)
{
+ if (!mtrr_enabled())
+ return;
+
if (!use_intel() || mtrr_aps_delayed_init)
return;
/*
@@ -774,6 +795,9 @@ void mtrr_save_state(void)
{
int first_cpu;
+ if (!mtrr_enabled())
+ return;
+
get_online_cpus();
first_cpu = cpumask_first(cpu_online_mask);
smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
@@ -782,6 +806,8 @@ void mtrr_save_state(void)
void set_mtrr_aps_delayed_init(void)
{
+ if (!mtrr_enabled())
+ return;
if (!use_intel())
return;
@@ -793,7 +819,7 @@ void set_mtrr_aps_delayed_init(void)
*/
void mtrr_aps_init(void)
{
- if (!use_intel())
+ if (!use_intel() || !mtrr_enabled())
return;
/*
@@ -810,7 +836,7 @@ void mtrr_aps_init(void)
void mtrr_bp_restore(void)
{
- if (!use_intel())
+ if (!use_intel() || !mtrr_enabled())
return;
mtrr_if->set_all();
@@ -818,7 +844,7 @@ void mtrr_bp_restore(void)
static int __init mtrr_init_finialize(void)
{
- if (!mtrr_if)
+ if (!mtrr_enabled())
return 0;
if (use_intel()) {
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index df5e41f31a27..951884dcc433 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -51,7 +51,7 @@ 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);
-void get_mtrr_state(void);
+bool get_mtrr_state(void);
extern void set_mtrr_ops(const struct mtrr_ops *ops);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 87848ebe2bb7..5801a14f7524 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
}
static atomic_t active_events;
+static atomic_t pmc_refcount;
static DEFINE_MUTEX(pmc_reserve_mutex);
#ifdef CONFIG_X86_LOCAL_APIC
@@ -190,6 +191,7 @@ static bool check_hw_exists(void)
u64 val, val_fail, val_new= ~0;
int i, reg, reg_fail, ret = 0;
int bios_fail = 0;
+ int reg_safe = -1;
/*
* Check to see if the BIOS enabled any of the counters, if so
@@ -204,6 +206,8 @@ static bool check_hw_exists(void)
bios_fail = 1;
val_fail = val;
reg_fail = reg;
+ } else {
+ reg_safe = i;
}
}
@@ -222,11 +226,22 @@ static bool check_hw_exists(void)
}
/*
+ * If all the counters are enabled, the below test will always
+ * fail. The tools will also become useless in this scenario.
+ * Just fail and disable the hardware counters.
+ */
+
+ if (reg_safe == -1) {
+ reg = reg_safe;
+ goto msr_fail;
+ }
+
+ /*
* Read the current value, change it and read it back to see if it
* matches, this is needed to detect certain hardware emulators
* (qemu/kvm) that don't trap on the MSR access and always return 0s.
*/
- reg = x86_pmu_event_addr(0);
+ reg = x86_pmu_event_addr(reg_safe);
if (rdmsrl_safe(reg, &val))
goto msr_fail;
val ^= 0xffffUL;
@@ -256,11 +271,8 @@ msr_fail:
static void hw_perf_event_destroy(struct perf_event *event)
{
- if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
- release_pmc_hardware();
- release_ds_buffers();
- mutex_unlock(&pmc_reserve_mutex);
- }
+ x86_release_hardware();
+ atomic_dec(&active_events);
}
void hw_perf_lbr_event_destroy(struct perf_event *event)
@@ -310,6 +322,35 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
return x86_pmu_extra_regs(val, event);
}
+int x86_reserve_hardware(void)
+{
+ int err = 0;
+
+ if (!atomic_inc_not_zero(&pmc_refcount)) {
+ mutex_lock(&pmc_reserve_mutex);
+ if (atomic_read(&pmc_refcount) == 0) {
+ if (!reserve_pmc_hardware())
+ err = -EBUSY;
+ else
+ reserve_ds_buffers();
+ }
+ if (!err)
+ atomic_inc(&pmc_refcount);
+ mutex_unlock(&pmc_reserve_mutex);
+ }
+
+ return err;
+}
+
+void x86_release_hardware(void)
+{
+ if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) {
+ release_pmc_hardware();
+ release_ds_buffers();
+ mutex_unlock(&pmc_reserve_mutex);
+ }
+}
+
/*
* Check if we can create event of a certain type (that no conflicting events
* are present).
@@ -322,21 +363,34 @@ int x86_add_exclusive(unsigned int what)
return 0;
mutex_lock(&pmc_reserve_mutex);
- for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++)
+ for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
goto out;
+ }
atomic_inc(&x86_pmu.lbr_exclusive[what]);
ret = 0;
out:
mutex_unlock(&pmc_reserve_mutex);
+
+ /*
+ * Assuming that all exclusive events will share the PMI handler
+ * (which checks active_events for whether there is work to do),
+ * we can bump active_events counter right here, except for
+ * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init()
+ * path, which already bumps active_events for them.
+ */
+ if (!ret && what != x86_lbr_exclusive_lbr)
+ atomic_inc(&active_events);
+
return ret;
}
void x86_del_exclusive(unsigned int what)
{
atomic_dec(&x86_pmu.lbr_exclusive[what]);
+ atomic_dec(&active_events);
}
int x86_setup_perfctr(struct perf_event *event)
@@ -513,22 +567,11 @@ static int __x86_pmu_event_init(struct perf_event *event)
if (!x86_pmu_initialized())
return -ENODEV;
- err = 0;
- if (!atomic_inc_not_zero(&active_events)) {
- mutex_lock(&pmc_reserve_mutex);
- if (atomic_read(&active_events) == 0) {
- if (!reserve_pmc_hardware())
- err = -EBUSY;
- else
- reserve_ds_buffers();
- }
- if (!err)
- atomic_inc(&active_events);
- mutex_unlock(&pmc_reserve_mutex);
- }
+ err = x86_reserve_hardware();
if (err)
return err;
+ atomic_inc(&active_events);
event->destroy = hw_perf_event_destroy;
event->hw.idx = -1;
@@ -611,6 +654,7 @@ struct sched_state {
int event; /* event index */
int counter; /* counter index */
int unassigned; /* number of events to be assigned left */
+ int nr_gp; /* number of GP counters used */
unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
};
@@ -620,27 +664,29 @@ struct sched_state {
struct perf_sched {
int max_weight;
int max_events;
- struct perf_event **events;
- struct sched_state state;
+ int max_gp;
int saved_states;
+ struct event_constraint **constraints;
+ struct sched_state state;
struct sched_state saved[SCHED_STATES_MAX];
};
/*
* Initialize interator that runs through all events and counters.
*/
-static void perf_sched_init(struct perf_sched *sched, struct perf_event **events,
- int num, int wmin, int wmax)
+static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints,
+ int num, int wmin, int wmax, int gpmax)
{
int idx;
memset(sched, 0, sizeof(*sched));
sched->max_events = num;
sched->max_weight = wmax;
- sched->events = events;
+ sched->max_gp = gpmax;
+ sched->constraints = constraints;
for (idx = 0; idx < num; idx++) {
- if (events[idx]->hw.constraint->weight == wmin)
+ if (constraints[idx]->weight == wmin)
break;
}
@@ -687,7 +733,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
if (sched->state.event >= sched->max_events)
return false;
- c = sched->events[sched->state.event]->hw.constraint;
+ c = sched->constraints[sched->state.event];
/* Prefer fixed purpose counters */
if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
idx = INTEL_PMC_IDX_FIXED;
@@ -696,11 +742,16 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
goto done;
}
}
+
/* Grab the first unused counter starting with idx */
idx = sched->state.counter;
for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
- if (!__test_and_set_bit(idx, sched->state.used))
+ if (!__test_and_set_bit(idx, sched->state.used)) {
+ if (sched->state.nr_gp++ >= sched->max_gp)
+ return false;
+
goto done;
+ }
}
return false;
@@ -745,7 +796,7 @@ static bool perf_sched_next_event(struct perf_sched *sched)
if (sched->state.weight > sched->max_weight)
return false;
}
- c = sched->events[sched->state.event]->hw.constraint;
+ c = sched->constraints[sched->state.event];
} while (c->weight != sched->state.weight);
sched->state.counter = 0; /* start with first counter */
@@ -756,12 +807,12 @@ static bool perf_sched_next_event(struct perf_sched *sched)
/*
* Assign a counter for each event.
*/
-int perf_assign_events(struct perf_event **events, int n,
- int wmin, int wmax, int *assign)
+int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int gpmax, int *assign)
{
struct perf_sched sched;
- perf_sched_init(&sched, events, n, wmin, wmax);
+ perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax);
do {
if (!perf_sched_find_counter(&sched))
@@ -788,9 +839,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
x86_pmu.start_scheduling(cpuc);
for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
- hwc = &cpuc->event_list[i]->hw;
+ cpuc->event_constraint[i] = NULL;
c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
- hwc->constraint = c;
+ cpuc->event_constraint[i] = c;
wmin = min(wmin, c->weight);
wmax = max(wmax, c->weight);
@@ -801,7 +852,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
*/
for (i = 0; i < n; i++) {
hwc = &cpuc->event_list[i]->hw;
- c = hwc->constraint;
+ c = cpuc->event_constraint[i];
/* never assigned */
if (hwc->idx == -1)
@@ -821,9 +872,26 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
}
/* slow path */
- if (i != n)
- unsched = perf_assign_events(cpuc->event_list, n, wmin,
- wmax, assign);
+ if (i != n) {
+ int gpmax = x86_pmu.num_counters;
+
+ /*
+ * Do not allow scheduling of more than half the available
+ * generic counters.
+ *
+ * This helps avoid counter starvation of sibling thread by
+ * ensuring at most half the counters cannot be in exclusive
+ * mode. There is no designated counters for the limits. Any
+ * N/2 counters can be used. This helps with events with
+ * specific counter constraints.
+ */
+ if (is_ht_workaround_enabled() && !cpuc->is_fake &&
+ READ_ONCE(cpuc->excl_cntrs->exclusive_present))
+ gpmax /= 2;
+
+ unsched = perf_assign_events(cpuc->event_constraint, n, wmin,
+ wmax, gpmax, assign);
+ }
/*
* In case of success (unsched = 0), mark events as committed,
@@ -840,12 +908,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
e = cpuc->event_list[i];
e->hw.flags |= PERF_X86_EVENT_COMMITTED;
if (x86_pmu.commit_scheduling)
- x86_pmu.commit_scheduling(cpuc, e, assign[i]);
+ x86_pmu.commit_scheduling(cpuc, i, assign[i]);
}
- }
-
- if (!assign || unsched) {
-
+ } else {
for (i = 0; i < n; i++) {
e = cpuc->event_list[i];
/*
@@ -1058,13 +1123,16 @@ int x86_perf_event_set_period(struct perf_event *event)
per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
- /*
- * The hw event starts counting from this event offset,
- * mark it to be able to extra future deltas:
- */
- local64_set(&hwc->prev_count, (u64)-left);
+ if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) ||
+ local64_read(&hwc->prev_count) != (u64)-left) {
+ /*
+ * The hw event starts counting from this event offset,
+ * mark it to be able to extra future deltas:
+ */
+ local64_set(&hwc->prev_count, (u64)-left);
- wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+ wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+ }
/*
* Due to erratum on certan cpu we need
@@ -1292,8 +1360,10 @@ static void x86_pmu_del(struct perf_event *event, int flags)
x86_pmu.put_event_constraints(cpuc, event);
/* Delete the array entry. */
- while (++i < cpuc->n_events)
+ while (++i < cpuc->n_events) {
cpuc->event_list[i-1] = cpuc->event_list[i];
+ cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
+ }
--cpuc->n_events;
perf_event_update_userpage(event);
@@ -1374,6 +1444,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
u64 finish_clock;
int ret;
+ /*
+ * All PMUs/events that share this PMI handler should make sure to
+ * increment active_events for their events.
+ */
if (!atomic_read(&active_events))
return NMI_DONE;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6ac5cb7a9e14..3e7fd27dfe20 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -74,6 +74,9 @@ struct event_constraint {
#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */
#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */
#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */
struct amd_nb {
@@ -87,6 +90,18 @@ struct amd_nb {
#define MAX_PEBS_EVENTS 8
/*
+ * Flags PEBS can handle without an PMI.
+ *
+ * TID can only be handled by flushing at context switch.
+ *
+ */
+#define PEBS_FREERUNNING_FLAGS \
+ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
+ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
+ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
+ PERF_SAMPLE_TRANSACTION)
+
+/*
* A debug store configuration.
*
* We only support architectures that use 64bit fields.
@@ -132,10 +147,7 @@ enum intel_excl_state_type {
};
struct intel_excl_states {
- enum intel_excl_state_type init_state[X86_PMC_IDX_MAX];
enum intel_excl_state_type state[X86_PMC_IDX_MAX];
- int num_alloc_cntrs;/* #counters allocated */
- int max_alloc_cntrs;/* max #counters allowed */
bool sched_started; /* true if scheduling has started */
};
@@ -144,6 +156,11 @@ struct intel_excl_cntrs {
struct intel_excl_states states[2];
+ union {
+ u16 has_exclusive[2];
+ u32 exclusive_present;
+ };
+
int refcnt; /* per-core: #HT threads */
unsigned core_id; /* per-core: core id */
};
@@ -172,7 +189,11 @@ struct cpu_hw_events {
added in the current transaction */
int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
u64 tags[X86_PMC_IDX_MAX];
+
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+ struct event_constraint *event_constraint[X86_PMC_IDX_MAX];
+
+ int n_excl; /* the number of exclusive events */
unsigned int group_flag;
int is_fake;
@@ -519,12 +540,10 @@ struct x86_pmu {
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
- void (*commit_scheduling)(struct cpu_hw_events *cpuc,
- struct perf_event *event,
- int cntr);
-
void (*start_scheduling)(struct cpu_hw_events *cpuc);
+ void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
+
void (*stop_scheduling)(struct cpu_hw_events *cpuc);
struct event_constraint *event_constraints;
@@ -697,6 +716,10 @@ int x86_add_exclusive(unsigned int what);
void x86_del_exclusive(unsigned int what);
+int x86_reserve_hardware(void);
+
+void x86_release_hardware(void);
+
void hw_perf_lbr_event_destroy(struct perf_event *event);
int x86_setup_perfctr(struct perf_event *event);
@@ -717,8 +740,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
void x86_pmu_enable_all(int added);
-int perf_assign_events(struct perf_event **events, int n,
- int wmin, int wmax, int *assign);
+int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int gpmax, int *assign);
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
void x86_pmu_stop(struct perf_event *event, int flags);
@@ -860,6 +883,8 @@ void intel_pmu_pebs_enable_all(void);
void intel_pmu_pebs_disable_all(void);
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
@@ -929,4 +954,8 @@ static inline struct intel_shared_regs *allocate_shared_regs(int cpu)
return NULL;
}
+static inline int is_ht_workaround_enabled(void)
+{
+ return 0;
+}
#endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3998131d1a68..b9826a981fb2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1903,9 +1903,8 @@ static void
intel_start_scheduling(struct cpu_hw_events *cpuc)
{
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct intel_excl_states *xl, *xlo;
+ struct intel_excl_states *xl;
int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid; /* sibling thread */
/*
* nothing needed if in group validation mode
@@ -1916,35 +1915,52 @@ intel_start_scheduling(struct cpu_hw_events *cpuc)
/*
* no exclusion needed
*/
- if (!excl_cntrs)
+ if (WARN_ON_ONCE(!excl_cntrs))
return;
- xlo = &excl_cntrs->states[o_tid];
xl = &excl_cntrs->states[tid];
xl->sched_started = true;
- xl->num_alloc_cntrs = 0;
/*
* lock shared state until we are done scheduling
* in stop_event_scheduling()
* makes scheduling appear as a transaction
*/
- WARN_ON_ONCE(!irqs_disabled());
raw_spin_lock(&excl_cntrs->lock);
+}
- /*
- * save initial state of sibling thread
- */
- memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state));
+static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+ struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
+ struct event_constraint *c = cpuc->event_constraint[idx];
+ struct intel_excl_states *xl;
+ int tid = cpuc->excl_thread_id;
+
+ if (cpuc->is_fake || !is_ht_workaround_enabled())
+ return;
+
+ if (WARN_ON_ONCE(!excl_cntrs))
+ return;
+
+ if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
+ return;
+
+ xl = &excl_cntrs->states[tid];
+
+ lockdep_assert_held(&excl_cntrs->lock);
+
+ if (c->flags & PERF_X86_EVENT_EXCL)
+ xl->state[cntr] = INTEL_EXCL_EXCLUSIVE;
+ else
+ xl->state[cntr] = INTEL_EXCL_SHARED;
}
static void
intel_stop_scheduling(struct cpu_hw_events *cpuc)
{
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct intel_excl_states *xl, *xlo;
+ struct intel_excl_states *xl;
int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid; /* sibling thread */
/*
* nothing needed if in group validation mode
@@ -1954,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc)
/*
* no exclusion needed
*/
- if (!excl_cntrs)
+ if (WARN_ON_ONCE(!excl_cntrs))
return;
- xlo = &excl_cntrs->states[o_tid];
xl = &excl_cntrs->states[tid];
- /*
- * make new sibling thread state visible
- */
- memcpy(xlo->state, xlo->init_state, sizeof(xlo->state));
-
xl->sched_started = false;
/*
* release shared state lock (acquired in intel_start_scheduling())
@@ -1976,12 +1986,10 @@ static struct event_constraint *
intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
int idx, struct event_constraint *c)
{
- struct event_constraint *cx;
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct intel_excl_states *xl, *xlo;
- int is_excl, i;
+ struct intel_excl_states *xlo;
int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid; /* alternate */
+ int is_excl, i;
/*
* validating a group does not require
@@ -1993,34 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
/*
* no exclusion needed
*/
- if (!excl_cntrs)
+ if (WARN_ON_ONCE(!excl_cntrs))
return c;
- /*
- * event requires exclusive counter access
- * across HT threads
- */
- is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
- /*
- * xl = state of current HT
- * xlo = state of sibling HT
- */
- xl = &excl_cntrs->states[tid];
- xlo = &excl_cntrs->states[o_tid];
-
- /*
- * do not allow scheduling of more than max_alloc_cntrs
- * which is set to half the available generic counters.
- * this helps avoid counter starvation of sibling thread
- * by ensuring at most half the counters cannot be in
- * exclusive mode. There is not designated counters for the
- * limits. Any N/2 counters can be used. This helps with
- * events with specifix counter constraints
- */
- if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs)
- return &emptyconstraint;
-
- cx = c;
/*
* because we modify the constraint, we need
@@ -2031,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
* been cloned (marked dynamic)
*/
if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
-
- /* sanity check */
- if (idx < 0)
- return &emptyconstraint;
+ struct event_constraint *cx;
/*
* grab pre-allocated constraint entry
@@ -2045,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
* initialize dynamic constraint
* with static constraint
*/
- memcpy(cx, c, sizeof(*cx));
+ *cx = *c;
/*
* mark constraint as dynamic, so we
* can free it later on
*/
cx->flags |= PERF_X86_EVENT_DYNAMIC;
+ c = cx;
}
/*
@@ -2062,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
*/
/*
+ * state of sibling HT
+ */
+ xlo = &excl_cntrs->states[tid ^ 1];
+
+ /*
+ * event requires exclusive counter access
+ * across HT threads
+ */
+ is_excl = c->flags & PERF_X86_EVENT_EXCL;
+ if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
+ event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
+ if (!cpuc->n_excl++)
+ WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
+ }
+
+ /*
* Modify static constraint with current dynamic
* state of thread
*
@@ -2069,44 +2065,44 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
* SHARED : sibling counter measuring non-exclusive event
* UNUSED : sibling counter unused
*/
- for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) {
+ for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
/*
* exclusive event in sibling counter
* our corresponding counter cannot be used
* regardless of our event
*/
- if (xl->state[i] == INTEL_EXCL_EXCLUSIVE)
- __clear_bit(i, cx->idxmsk);
+ if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+ __clear_bit(i, c->idxmsk);
/*
* if measuring an exclusive event, sibling
* measuring non-exclusive, then counter cannot
* be used
*/
- if (is_excl && xl->state[i] == INTEL_EXCL_SHARED)
- __clear_bit(i, cx->idxmsk);
+ if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+ __clear_bit(i, c->idxmsk);
}
/*
* recompute actual bit weight for scheduling algorithm
*/
- cx->weight = hweight64(cx->idxmsk64);
+ c->weight = hweight64(c->idxmsk64);
/*
* if we return an empty mask, then switch
* back to static empty constraint to avoid
* the cost of freeing later on
*/
- if (cx->weight == 0)
- cx = &emptyconstraint;
+ if (c->weight == 0)
+ c = &emptyconstraint;
- return cx;
+ return c;
}
static struct event_constraint *
intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
{
- struct event_constraint *c1 = event->hw.constraint;
+ struct event_constraint *c1 = cpuc->event_constraint[idx];
struct event_constraint *c2;
/*
@@ -2132,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
{
struct hw_perf_event *hwc = &event->hw;
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct intel_excl_states *xlo, *xl;
- unsigned long flags = 0; /* keep compiler happy */
int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid;
+ struct intel_excl_states *xl;
/*
* nothing needed if in group validation mode
@@ -2143,31 +2137,35 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
if (cpuc->is_fake)
return;
- WARN_ON_ONCE(!excl_cntrs);
-
- if (!excl_cntrs)
+ if (WARN_ON_ONCE(!excl_cntrs))
return;
- xl = &excl_cntrs->states[tid];
- xlo = &excl_cntrs->states[o_tid];
+ if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
+ hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
+ if (!--cpuc->n_excl)
+ WRITE_ONCE(excl_cntrs->has_exclusive[tid], 0);
+ }
/*
- * put_constraint may be called from x86_schedule_events()
- * which already has the lock held so here make locking
- * conditional
+ * If event was actually assigned, then mark the counter state as
+ * unused now.
*/
- if (!xl->sched_started)
- raw_spin_lock_irqsave(&excl_cntrs->lock, flags);
+ if (hwc->idx >= 0) {
+ xl = &excl_cntrs->states[tid];
- /*
- * if event was actually assigned, then mark the
- * counter state as unused now
- */
- if (hwc->idx >= 0)
- xlo->state[hwc->idx] = INTEL_EXCL_UNUSED;
+ /*
+ * put_constraint may be called from x86_schedule_events()
+ * which already has the lock held so here make locking
+ * conditional.
+ */
+ if (!xl->sched_started)
+ raw_spin_lock(&excl_cntrs->lock);
- if (!xl->sched_started)
- raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags);
+ xl->state[hwc->idx] = INTEL_EXCL_UNUSED;
+
+ if (!xl->sched_started)
+ raw_spin_unlock(&excl_cntrs->lock);
+ }
}
static void
@@ -2188,8 +2186,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
struct perf_event *event)
{
- struct event_constraint *c = event->hw.constraint;
-
intel_put_shared_regs_event_constraints(cpuc, event);
/*
@@ -2197,48 +2193,8 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
* all events are subject to and must call the
* put_excl_constraints() routine
*/
- if (c && cpuc->excl_cntrs)
+ if (cpuc->excl_cntrs)
intel_put_excl_constraints(cpuc, event);
-
- /* cleanup dynamic constraint */
- if (c && (c->flags & PERF_X86_EVENT_DYNAMIC))
- event->hw.constraint = NULL;
-}
-
-static void intel_commit_scheduling(struct cpu_hw_events *cpuc,
- struct perf_event *event, int cntr)
-{
- struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct event_constraint *c = event->hw.constraint;
- struct intel_excl_states *xlo, *xl;
- int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid;
- int is_excl;
-
- if (cpuc->is_fake || !c)
- return;
-
- is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
- if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
- return;
-
- WARN_ON_ONCE(!excl_cntrs);
-
- if (!excl_cntrs)
- return;
-
- xl = &excl_cntrs->states[tid];
- xlo = &excl_cntrs->states[o_tid];
-
- WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock));
-
- if (cntr >= 0) {
- if (is_excl)
- xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE;
- else
- xlo->init_state[cntr] = INTEL_EXCL_SHARED;
- }
}
static void intel_pebs_aliases_core2(struct perf_event *event)
@@ -2304,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event)
if (ret)
return ret;
- if (event->attr.precise_ip && x86_pmu.pebs_aliases)
- x86_pmu.pebs_aliases(event);
+ if (event->attr.precise_ip) {
+ if (!event->attr.freq) {
+ event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
+ if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS))
+ event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+ }
+ if (x86_pmu.pebs_aliases)
+ x86_pmu.pebs_aliases(event);
+ }
if (needs_branch_stack(event)) {
ret = intel_pmu_setup_lbr_filter(event);
@@ -2554,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu)
static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
{
struct intel_excl_cntrs *c;
- int i;
c = kzalloc_node(sizeof(struct intel_excl_cntrs),
GFP_KERNEL, cpu_to_node(cpu));
if (c) {
raw_spin_lock_init(&c->lock);
- for (i = 0; i < X86_PMC_IDX_MAX; i++) {
- c->states[0].state[i] = INTEL_EXCL_UNUSED;
- c->states[0].init_state[i] = INTEL_EXCL_UNUSED;
-
- c->states[1].state[i] = INTEL_EXCL_UNUSED;
- c->states[1].init_state[i] = INTEL_EXCL_UNUSED;
- }
c->core_id = -1;
}
return c;
@@ -2621,7 +2576,7 @@ static void intel_pmu_cpu_starting(int cpu)
if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
- for_each_cpu(i, topology_thread_cpumask(cpu)) {
+ for_each_cpu(i, topology_sibling_cpumask(cpu)) {
struct intel_shared_regs *pc;
pc = per_cpu(cpu_hw_events, i).shared_regs;
@@ -2639,9 +2594,7 @@ static void intel_pmu_cpu_starting(int cpu)
cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
- int h = x86_pmu.num_counters >> 1;
-
- for_each_cpu(i, topology_thread_cpumask(cpu)) {
+ for_each_cpu(i, topology_sibling_cpumask(cpu)) {
struct intel_excl_cntrs *c;
c = per_cpu(cpu_hw_events, i).excl_cntrs;
@@ -2654,11 +2607,6 @@ static void intel_pmu_cpu_starting(int cpu)
}
cpuc->excl_cntrs->core_id = core_id;
cpuc->excl_cntrs->refcnt++;
- /*
- * set hard limit to half the number of generic counters
- */
- cpuc->excl_cntrs->states[0].max_alloc_cntrs = h;
- cpuc->excl_cntrs->states[1].max_alloc_cntrs = h;
}
}
@@ -2694,6 +2642,15 @@ static void intel_pmu_cpu_dying(int cpu)
fini_debug_store_on_cpu(cpu);
}
+static void intel_pmu_sched_task(struct perf_event_context *ctx,
+ bool sched_in)
+{
+ if (x86_pmu.pebs_active)
+ intel_pmu_pebs_sched_task(ctx, sched_in);
+ if (x86_pmu.lbr_nr)
+ intel_pmu_lbr_sched_task(ctx, sched_in);
+}
+
PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2783,7 +2740,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
.guest_get_msrs = intel_guest_get_msrs,
- .sched_task = intel_pmu_lbr_sched_task,
+ .sched_task = intel_pmu_sched_task,
};
static __init void intel_clovertown_quirk(void)
@@ -2956,8 +2913,8 @@ static __init void intel_ht_bug(void)
{
x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED;
- x86_pmu.commit_scheduling = intel_commit_scheduling;
x86_pmu.start_scheduling = intel_start_scheduling;
+ x86_pmu.commit_scheduling = intel_commit_scheduling;
x86_pmu.stop_scheduling = intel_stop_scheduling;
}
@@ -3270,6 +3227,8 @@ __init int intel_pmu_init(void)
case 61: /* 14nm Broadwell Core-M */
case 86: /* 14nm Broadwell Xeon D */
+ case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+ case 79: /* 14nm Broadwell Server */
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -3339,13 +3298,13 @@ __init int intel_pmu_init(void)
* counter, so do not extend mask to generic counters
*/
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if (c->cmask != FIXED_EVENT_FLAGS
- || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
- continue;
+ if (c->cmask == FIXED_EVENT_FLAGS
+ && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+ c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
}
-
- c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
- c->weight += x86_pmu.num_counters;
+ c->idxmsk64 &=
+ ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+ c->weight = hweight64(c->idxmsk64);
}
}
@@ -3403,7 +3362,7 @@ static __init int fixup_ht_bug(void)
if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED))
return 0;
- w = cpumask_weight(topology_thread_cpumask(cpu));
+ w = cpumask_weight(topology_sibling_cpumask(cpu));
if (w > 1) {
pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n");
return 0;
@@ -3413,8 +3372,8 @@ static __init int fixup_ht_bug(void)
x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
- x86_pmu.commit_scheduling = NULL;
x86_pmu.start_scheduling = NULL;
+ x86_pmu.commit_scheduling = NULL;
x86_pmu.stop_scheduling = NULL;
watchdog_nmi_enable_all();
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index ac1f0c55f379..7795f3f8b1d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -483,17 +483,26 @@ static int bts_event_add(struct perf_event *event, int mode)
static void bts_event_destroy(struct perf_event *event)
{
+ x86_release_hardware();
x86_del_exclusive(x86_lbr_exclusive_bts);
}
static int bts_event_init(struct perf_event *event)
{
+ int ret;
+
if (event->attr.type != bts_pmu.type)
return -ENOENT;
if (x86_add_exclusive(x86_lbr_exclusive_bts))
return -EBUSY;
+ ret = x86_reserve_hardware();
+ if (ret) {
+ x86_del_exclusive(x86_lbr_exclusive_bts);
+ return ret;
+ }
+
event->destroy = bts_event_destroy;
return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index e4d1b8b738fa..188076161c1b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -13,16 +13,35 @@
#define MSR_IA32_QM_CTR 0x0c8e
#define MSR_IA32_QM_EVTSEL 0x0c8d
-static unsigned int cqm_max_rmid = -1;
+static u32 cqm_max_rmid = -1;
static unsigned int cqm_l3_scale; /* supposedly cacheline size */
-struct intel_cqm_state {
- raw_spinlock_t lock;
- int rmid;
- int cnt;
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid: The cached Resource Monitoring ID
+ * @closid: The cached Class Of Service ID
+ * @rmid_usecnt: The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+ u32 rmid;
+ u32 closid;
+ int rmid_usecnt;
};
-static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
+/*
+ * The cached intel_pqr_state is strictly per CPU and can never be
+ * updated from a remote CPU. Both functions which modify the state
+ * (intel_cqm_event_start and intel_cqm_event_stop) are called with
+ * interrupts disabled, which is sufficient for the protection.
+ */
+static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
/*
* Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
@@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask;
* near-zero occupancy value, i.e. no cachelines are tagged with this
* RMID, once __intel_cqm_rmid_rotate() returns.
*/
-static unsigned int intel_cqm_rotation_rmid;
+static u32 intel_cqm_rotation_rmid;
#define INVALID_RMID (-1)
@@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid;
* Likewise, an rmid value of -1 is used to indicate "no rmid currently
* assigned" and is used as part of the rotation code.
*/
-static inline bool __rmid_valid(unsigned int rmid)
+static inline bool __rmid_valid(u32 rmid)
{
if (!rmid || rmid == INVALID_RMID)
return false;
@@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid)
return true;
}
-static u64 __rmid_read(unsigned int rmid)
+static u64 __rmid_read(u32 rmid)
{
u64 val;
@@ -102,7 +121,7 @@ enum rmid_recycle_state {
};
struct cqm_rmid_entry {
- unsigned int rmid;
+ u32 rmid;
enum rmid_recycle_state state;
struct list_head list;
unsigned long queue_time;
@@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru);
*/
static struct cqm_rmid_entry **cqm_rmid_ptrs;
-static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
+static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid)
{
struct cqm_rmid_entry *entry;
@@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
*
* We expect to be called with cache_mutex held.
*/
-static int __get_rmid(void)
+static u32 __get_rmid(void)
{
struct cqm_rmid_entry *entry;
@@ -177,7 +196,7 @@ static int __get_rmid(void)
return entry->rmid;
}
-static void __put_rmid(unsigned int rmid)
+static void __put_rmid(u32 rmid)
{
struct cqm_rmid_entry *entry;
@@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b)
}
struct rmid_read {
- unsigned int rmid;
+ u32 rmid;
atomic64_t value;
};
@@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info);
/*
* Exchange the RMID of a group of events.
*/
-static unsigned int
-intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid)
+static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
{
struct perf_event *event;
- unsigned int old_rmid = group->hw.cqm_rmid;
struct list_head *head = &group->hw.cqm_group_entry;
+ u32 old_rmid = group->hw.cqm_rmid;
lockdep_assert_held(&cache_mutex);
@@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg)
* If we have group events waiting for an RMID that don't conflict with
* events already running, assign @rmid.
*/
-static bool intel_cqm_sched_in_event(unsigned int rmid)
+static bool intel_cqm_sched_in_event(u32 rmid)
{
struct perf_event *leader, *event;
@@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available)
static void __intel_cqm_pick_and_rotate(struct perf_event *next)
{
struct perf_event *rotor;
- unsigned int rmid;
+ u32 rmid;
lockdep_assert_held(&cache_mutex);
@@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next)
static void intel_cqm_sched_out_conflicting_events(struct perf_event *event)
{
struct perf_event *group, *g;
- unsigned int rmid;
+ u32 rmid;
lockdep_assert_held(&cache_mutex);
@@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event,
struct perf_event **group)
{
struct perf_event *iter;
- unsigned int rmid;
bool conflict = false;
+ u32 rmid;
list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
rmid = iter->hw.cqm_rmid;
@@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
static void intel_cqm_event_read(struct perf_event *event)
{
unsigned long flags;
- unsigned int rmid;
+ u32 rmid;
u64 val;
/*
@@ -961,55 +979,48 @@ out:
static void intel_cqm_event_start(struct perf_event *event, int mode)
{
- struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
- unsigned int rmid = event->hw.cqm_rmid;
- unsigned long flags;
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+ u32 rmid = event->hw.cqm_rmid;
if (!(event->hw.cqm_state & PERF_HES_STOPPED))
return;
event->hw.cqm_state &= ~PERF_HES_STOPPED;
- raw_spin_lock_irqsave(&state->lock, flags);
-
- if (state->cnt++)
- WARN_ON_ONCE(state->rmid != rmid);
- else
+ if (state->rmid_usecnt++) {
+ if (!WARN_ON_ONCE(state->rmid != rmid))
+ return;
+ } else {
WARN_ON_ONCE(state->rmid);
+ }
state->rmid = rmid;
- wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid);
-
- raw_spin_unlock_irqrestore(&state->lock, flags);
+ wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid);
}
static void intel_cqm_event_stop(struct perf_event *event, int mode)
{
- struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
- unsigned long flags;
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
if (event->hw.cqm_state & PERF_HES_STOPPED)
return;
event->hw.cqm_state |= PERF_HES_STOPPED;
- raw_spin_lock_irqsave(&state->lock, flags);
intel_cqm_event_read(event);
- if (!--state->cnt) {
+ if (!--state->rmid_usecnt) {
state->rmid = 0;
- wrmsrl(MSR_IA32_PQR_ASSOC, 0);
+ wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid);
} else {
WARN_ON_ONCE(!state->rmid);
}
-
- raw_spin_unlock_irqrestore(&state->lock, flags);
}
static int intel_cqm_event_add(struct perf_event *event, int mode)
{
unsigned long flags;
- unsigned int rmid;
+ u32 rmid;
raw_spin_lock_irqsave(&cache_lock, flags);
@@ -1024,11 +1035,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode)
return 0;
}
-static void intel_cqm_event_del(struct perf_event *event, int mode)
-{
- intel_cqm_event_stop(event, mode);
-}
-
static void intel_cqm_event_destroy(struct perf_event *event)
{
struct perf_event *group_other = NULL;
@@ -1057,7 +1063,7 @@ static void intel_cqm_event_destroy(struct perf_event *event)
list_replace(&event->hw.cqm_groups_entry,
&group_other->hw.cqm_groups_entry);
} else {
- unsigned int rmid = event->hw.cqm_rmid;
+ u32 rmid = event->hw.cqm_rmid;
if (__rmid_valid(rmid))
__put_rmid(rmid);
@@ -1221,7 +1227,7 @@ static struct pmu intel_cqm_pmu = {
.task_ctx_nr = perf_sw_context,
.event_init = intel_cqm_event_init,
.add = intel_cqm_event_add,
- .del = intel_cqm_event_del,
+ .del = intel_cqm_event_stop,
.start = intel_cqm_event_start,
.stop = intel_cqm_event_stop,
.read = intel_cqm_event_read,
@@ -1243,12 +1249,12 @@ static inline void cqm_pick_event_reader(int cpu)
static void intel_cqm_cpu_prepare(unsigned int cpu)
{
- struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
+ struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu);
- raw_spin_lock_init(&state->lock);
state->rmid = 0;
- state->cnt = 0;
+ state->closid = 0;
+ state->rmid_usecnt = 0;
WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 813f75d71175..71fc40238843 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -11,7 +11,7 @@
#define BTS_RECORD_SIZE 24
#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE PAGE_SIZE
+#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
#define PEBS_FIXUP_SIZE PAGE_SIZE
/*
@@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
int node = cpu_to_node(cpu);
- int max, thresh = 1; /* always use a single PEBS record */
+ int max;
void *buffer, *ibuffer;
if (!x86_pmu.pebs)
@@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu)
ds->pebs_absolute_maximum = ds->pebs_buffer_base +
max * x86_pmu.pebs_record_size;
- ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
- thresh * x86_pmu.pebs_record_size;
-
return 0;
}
@@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void)
return 1;
}
+static inline void intel_pmu_drain_pebs_buffer(void)
+{
+ struct pt_regs regs;
+
+ x86_pmu.drain_pebs(&regs);
+}
+
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+ if (!sched_in)
+ intel_pmu_drain_pebs_buffer();
+}
+
/*
* PEBS
*/
@@ -684,33 +694,81 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
return &emptyconstraint;
}
+static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+{
+ return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+}
+
void intel_pmu_pebs_enable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
+ struct debug_store *ds = cpuc->ds;
+ bool first_pebs;
+ u64 threshold;
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
+ first_pebs = !pebs_is_enabled(cpuc);
cpuc->pebs_enabled |= 1ULL << hwc->idx;
if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
+
+ /*
+ * When the event is constrained enough we can use a larger
+ * threshold and run the event with less frequent PMI.
+ */
+ if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
+ threshold = ds->pebs_absolute_maximum -
+ x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+
+ if (first_pebs)
+ perf_sched_cb_inc(event->ctx->pmu);
+ } else {
+ threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+
+ /*
+ * If not all events can use larger buffer,
+ * roll back to threshold = 1
+ */
+ if (!first_pebs &&
+ (ds->pebs_interrupt_threshold > threshold))
+ perf_sched_cb_dec(event->ctx->pmu);
+ }
+
+ /* Use auto-reload if possible to save a MSR write in the PMI */
+ if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+ ds->pebs_event_reset[hwc->idx] =
+ (u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+ }
+
+ if (first_pebs || ds->pebs_interrupt_threshold > threshold)
+ ds->pebs_interrupt_threshold = threshold;
}
void intel_pmu_pebs_disable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
+ struct debug_store *ds = cpuc->ds;
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
- if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
- else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST)
+ else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled &= ~(1ULL << 63);
+ if (ds->pebs_interrupt_threshold >
+ ds->pebs_buffer_base + x86_pmu.pebs_record_size) {
+ intel_pmu_drain_pebs_buffer();
+ if (!pebs_is_enabled(cpuc))
+ perf_sched_cb_dec(event->ctx->pmu);
+ }
+
if (cpuc->enabled)
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
@@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
return txn;
}
-static void __intel_pmu_pebs_event(struct perf_event *event,
- struct pt_regs *iregs, void *__pebs)
+static void setup_pebs_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
#define PERF_X86_EVENT_PEBS_HSW_PREC \
(PERF_X86_EVENT_PEBS_ST_HSW | \
@@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
*/
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_hsw *pebs = __pebs;
- struct perf_sample_data data;
- struct pt_regs regs;
u64 sample_type;
int fll, fst, dsrc;
int fl = event->hw.flags;
- if (!intel_pmu_save_and_restart(event))
+ if (pebs == NULL)
return;
sample_type = event->attr.sample_type;
@@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
- perf_sample_data_init(&data, 0, event->hw.last_period);
+ perf_sample_data_init(data, 0, event->hw.last_period);
- data.period = event->hw.last_period;
+ data->period = event->hw.last_period;
/*
* Use latency for weight (only avail with PEBS-LL)
*/
if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
- data.weight = pebs->lat;
+ data->weight = pebs->lat;
/*
* data.data_src encodes the data source
@@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
val = precise_datala_hsw(event, pebs->dse);
else if (fst)
val = precise_store_data(pebs->dse);
- data.data_src.val = val;
+ data->data_src.val = val;
}
/*
@@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
* PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
* A possible PERF_SAMPLE_REGS will have to transfer all regs.
*/
- regs = *iregs;
- regs.flags = pebs->flags;
- set_linear_ip(&regs, pebs->ip);
- regs.bp = pebs->bp;
- regs.sp = pebs->sp;
+ *regs = *iregs;
+ regs->flags = pebs->flags;
+ set_linear_ip(regs, pebs->ip);
+ regs->bp = pebs->bp;
+ regs->sp = pebs->sp;
if (sample_type & PERF_SAMPLE_REGS_INTR) {
- regs.ax = pebs->ax;
- regs.bx = pebs->bx;
- regs.cx = pebs->cx;
- regs.dx = pebs->dx;
- regs.si = pebs->si;
- regs.di = pebs->di;
- regs.bp = pebs->bp;
- regs.sp = pebs->sp;
-
- regs.flags = pebs->flags;
+ regs->ax = pebs->ax;
+ regs->bx = pebs->bx;
+ regs->cx = pebs->cx;
+ regs->dx = pebs->dx;
+ regs->si = pebs->si;
+ regs->di = pebs->di;
+ regs->bp = pebs->bp;
+ regs->sp = pebs->sp;
+
+ regs->flags = pebs->flags;
#ifndef CONFIG_X86_32
- regs.r8 = pebs->r8;
- regs.r9 = pebs->r9;
- regs.r10 = pebs->r10;
- regs.r11 = pebs->r11;
- regs.r12 = pebs->r12;
- regs.r13 = pebs->r13;
- regs.r14 = pebs->r14;
- regs.r15 = pebs->r15;
+ regs->r8 = pebs->r8;
+ regs->r9 = pebs->r9;
+ regs->r10 = pebs->r10;
+ regs->r11 = pebs->r11;
+ regs->r12 = pebs->r12;
+ regs->r13 = pebs->r13;
+ regs->r14 = pebs->r14;
+ regs->r15 = pebs->r15;
#endif
}
if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
- regs.ip = pebs->real_ip;
- regs.flags |= PERF_EFLAGS_EXACT;
- } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
- regs.flags |= PERF_EFLAGS_EXACT;
+ regs->ip = pebs->real_ip;
+ regs->flags |= PERF_EFLAGS_EXACT;
+ } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
+ regs->flags |= PERF_EFLAGS_EXACT;
else
- regs.flags &= ~PERF_EFLAGS_EXACT;
+ regs->flags &= ~PERF_EFLAGS_EXACT;
if ((sample_type & PERF_SAMPLE_ADDR) &&
x86_pmu.intel_cap.pebs_format >= 1)
- data.addr = pebs->dla;
+ data->addr = pebs->dla;
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
- data.weight = intel_hsw_weight(pebs);
+ data->weight = intel_hsw_weight(pebs);
if (sample_type & PERF_SAMPLE_TRANSACTION)
- data.txn = intel_hsw_transaction(pebs);
+ data->txn = intel_hsw_transaction(pebs);
}
if (has_branch_stack(event))
- data.br_stack = &cpuc->lbr_stack;
+ data->br_stack = &cpuc->lbr_stack;
+}
+
+static inline void *
+get_next_pebs_record_by_bit(void *base, void *top, int bit)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ void *at;
+ u64 pebs_status;
+
+ if (base == NULL)
+ return NULL;
+
+ for (at = base; at < top; at += x86_pmu.pebs_record_size) {
+ struct pebs_record_nhm *p = at;
- if (perf_event_overflow(event, &data, &regs))
+ if (test_bit(bit, (unsigned long *)&p->status)) {
+ /* PEBS v3 has accurate status bits */
+ if (x86_pmu.intel_cap.pebs_format >= 3)
+ return at;
+
+ if (p->status == (1 << bit))
+ return at;
+
+ /* clear non-PEBS bit and re-check */
+ pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+ if (pebs_status == (1 << bit))
+ return at;
+ }
+ }
+ return NULL;
+}
+
+static void __intel_pmu_pebs_event(struct perf_event *event,
+ struct pt_regs *iregs,
+ void *base, void *top,
+ int bit, int count)
+{
+ struct perf_sample_data data;
+ struct pt_regs regs;
+ void *at = get_next_pebs_record_by_bit(base, top, bit);
+
+ if (!intel_pmu_save_and_restart(event) &&
+ !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD))
+ return;
+
+ while (count > 1) {
+ setup_pebs_sample_data(event, iregs, at, &data, &regs);
+ perf_event_output(event, &data, &regs);
+ at += x86_pmu.pebs_record_size;
+ at = get_next_pebs_record_by_bit(at, top, bit);
+ count--;
+ }
+
+ setup_pebs_sample_data(event, iregs, at, &data, &regs);
+
+ /*
+ * All but the last records are processed.
+ * The last one is left to be able to call the overflow handler.
+ */
+ if (perf_event_overflow(event, &data, &regs)) {
x86_pmu_stop(event, 0);
+ return;
+ }
+
}
static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
@@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
if (!event->attr.precise_ip)
return;
- n = top - at;
+ n = (top - at) / x86_pmu.pebs_record_size;
if (n <= 0)
return;
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(n > 1, "bad leftover pebs %d\n", n);
- at += n - 1;
-
- __intel_pmu_pebs_event(event, iregs, at);
+ __intel_pmu_pebs_event(event, iregs, at, top, 0, n);
}
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
- struct perf_event *event = NULL;
- void *at, *top;
- u64 status = 0;
- int bit;
+ struct perf_event *event;
+ void *base, *at, *top;
+ short counts[MAX_PEBS_EVENTS] = {};
+ short error[MAX_PEBS_EVENTS] = {};
+ int bit, i;
if (!x86_pmu.pebs_active)
return;
- at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+ base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
ds->pebs_index = ds->pebs_buffer_base;
- if (unlikely(at > top))
+ if (unlikely(base >= top))
return;
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
- "Unexpected number of pebs records %ld\n",
- (long)(top - at) / x86_pmu.pebs_record_size);
-
- for (; at < top; at += x86_pmu.pebs_record_size) {
+ for (at = base; at < top; at += x86_pmu.pebs_record_size) {
struct pebs_record_nhm *p = at;
- for_each_set_bit(bit, (unsigned long *)&p->status,
- x86_pmu.max_pebs_events) {
- event = cpuc->events[bit];
- if (!test_bit(bit, cpuc->active_mask))
- continue;
-
- WARN_ON_ONCE(!event);
+ /* PEBS v3 has accurate status bits */
+ if (x86_pmu.intel_cap.pebs_format >= 3) {
+ for_each_set_bit(bit, (unsigned long *)&p->status,
+ MAX_PEBS_EVENTS)
+ counts[bit]++;
- if (!event->attr.precise_ip)
- continue;
+ continue;
+ }
- if (__test_and_set_bit(bit, (unsigned long *)&status))
+ bit = find_first_bit((unsigned long *)&p->status,
+ x86_pmu.max_pebs_events);
+ if (bit >= x86_pmu.max_pebs_events)
+ continue;
+ if (!test_bit(bit, cpuc->active_mask))
+ continue;
+ /*
+ * The PEBS hardware does not deal well with the situation
+ * when events happen near to each other and multiple bits
+ * are set. But it should happen rarely.
+ *
+ * If these events include one PEBS and multiple non-PEBS
+ * events, it doesn't impact PEBS record. The record will
+ * be handled normally. (slow path)
+ *
+ * If these events include two or more PEBS events, the
+ * records for the events can be collapsed into a single
+ * one, and it's not possible to reconstruct all events
+ * that caused the PEBS record. It's called collision.
+ * If collision happened, the record will be dropped.
+ *
+ */
+ if (p->status != (1 << bit)) {
+ u64 pebs_status;
+
+ /* slow path */
+ pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+ if (pebs_status != (1 << bit)) {
+ for_each_set_bit(i, (unsigned long *)&pebs_status,
+ MAX_PEBS_EVENTS)
+ error[i]++;
continue;
-
- break;
+ }
}
+ counts[bit]++;
+ }
- if (!event || bit >= x86_pmu.max_pebs_events)
+ for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+ if ((counts[bit] == 0) && (error[bit] == 0))
continue;
+ event = cpuc->events[bit];
+ WARN_ON_ONCE(!event);
+ WARN_ON_ONCE(!event->attr.precise_ip);
- __intel_pmu_pebs_event(event, iregs, at);
+ /* log dropped samples number */
+ if (error[bit])
+ perf_log_lost_samples(event, error[bit]);
+
+ if (counts[bit]) {
+ __intel_pmu_pebs_event(event, iregs, base,
+ top, bit, counts[bit]);
+ }
}
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 94e5b506caa6..452a7bd2dedb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -96,6 +96,7 @@ enum {
X86_BR_NO_TX = 1 << 14,/* not in transaction */
X86_BR_ZERO_CALL = 1 << 15,/* zero length call */
X86_BR_CALL_STACK = 1 << 16,/* call stack */
+ X86_BR_IND_JMP = 1 << 17,/* indirect jump */
};
#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -113,6 +114,7 @@ enum {
X86_BR_IRQ |\
X86_BR_ABORT |\
X86_BR_IND_CALL |\
+ X86_BR_IND_JMP |\
X86_BR_ZERO_CALL)
#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
@@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct x86_perf_task_context *task_ctx;
- if (!x86_pmu.lbr_nr)
- return;
-
/*
* If LBR callstack feature is enabled and the stack was saved when
* the task was scheduled out, restore the stack. Otherwise flush
@@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
X86_BR_CALL_STACK;
}
+ if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
+ mask |= X86_BR_IND_JMP;
+
/*
* stash actual user request into reg, it may
* be used by fixup code for some CPU
@@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
break;
case 4:
case 5:
- ret = X86_BR_JMP;
+ ret = X86_BR_IND_JMP;
break;
}
break;
@@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
*/
[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC,
+ [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
};
static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
| LBR_FAR,
[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL,
[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC,
+ [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
};
static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC,
[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL
| LBR_RETURN | LBR_CALL_STACK,
+ [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
};
/* core */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index ffe666c2c6b5..159887c3a89d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -151,7 +151,7 @@ static int __init pt_pmu_hw_init(void)
de_attr->attr.attr.name = pt_caps[i].name;
- sysfs_attr_init(&de_attrs->attr.attr);
+ sysfs_attr_init(&de_attr->attr.attr);
de_attr->attr.attr.mode = S_IRUGO;
de_attr->attr.show = pt_cap_show;
@@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event)
* These all are cpu affine and operate on a local PT
*/
-static bool pt_is_running(void)
-{
- u64 ctl;
-
- rdmsrl(MSR_IA32_RTIT_CTL, ctl);
-
- return !!(ctl & RTIT_CTL_TRACEEN);
-}
-
static void pt_config(struct perf_event *event)
{
u64 reg;
@@ -609,16 +600,19 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg)
* @handle: Current output handle.
*
* Place INT and STOP marks to prevent overwriting old data that the consumer
- * hasn't yet collected.
+ * hasn't yet collected and waking up the consumer after a certain fraction of
+ * the buffer has filled up. Only needed and sensible for non-snapshot counters.
+ *
+ * This obviously relies on buf::head to figure out buffer markers, so it has
+ * to be called after pt_buffer_reset_offsets() and before the hardware tracing
+ * is enabled.
*/
static int pt_buffer_reset_markers(struct pt_buffer *buf,
struct perf_output_handle *handle)
{
- unsigned long idx, npages, end;
-
- if (buf->snapshot)
- return 0;
+ unsigned long head = local64_read(&buf->head);
+ unsigned long idx, npages, wakeup;
/* can't stop in the middle of an output region */
if (buf->output_off + handle->size + 1 <
@@ -634,17 +628,26 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
buf->topa_index[buf->stop_pos]->stop = 0;
buf->topa_index[buf->intr_pos]->intr = 0;
- if (pt_cap_get(PT_CAP_topa_multiple_entries)) {
- npages = (handle->size + 1) >> PAGE_SHIFT;
- end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages;
- /*if (end > handle->wakeup >> PAGE_SHIFT)
- end = handle->wakeup >> PAGE_SHIFT;*/
- idx = end & (buf->nr_pages - 1);
- buf->stop_pos = idx;
- idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1;
- idx &= buf->nr_pages - 1;
- buf->intr_pos = idx;
- }
+ /* how many pages till the STOP marker */
+ npages = handle->size >> PAGE_SHIFT;
+
+ /* if it's on a page boundary, fill up one more page */
+ if (!offset_in_page(head + handle->size + 1))
+ npages++;
+
+ idx = (head >> PAGE_SHIFT) + npages;
+ idx &= buf->nr_pages - 1;
+ buf->stop_pos = idx;
+
+ wakeup = handle->wakeup >> PAGE_SHIFT;
+
+ /* in the worst case, wake up the consumer one page before hard stop */
+ idx = (head >> PAGE_SHIFT) + npages - 1;
+ if (idx > wakeup)
+ idx = wakeup;
+
+ idx &= buf->nr_pages - 1;
+ buf->intr_pos = idx;
buf->topa_index[buf->stop_pos]->stop = 1;
buf->topa_index[buf->intr_pos]->intr = 1;
@@ -664,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
struct topa *cur = buf->first, *prev = buf->last;
struct topa_entry *te_cur = TOPA_ENTRY(cur, 0),
*te_prev = TOPA_ENTRY(prev, prev->last - 1);
- int pg = 0, idx = 0, ntopa = 0;
+ int pg = 0, idx = 0;
while (pg < buf->nr_pages) {
int tidx;
@@ -679,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
/* advance to next topa table */
idx = 0;
cur = list_entry(cur->list.next, struct topa, list);
- ntopa++;
- } else
+ } else {
idx++;
+ }
te_cur = TOPA_ENTRY(cur, idx);
}
@@ -693,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
* @head: Write pointer (aux_head) from AUX buffer.
*
* Find the ToPA table and entry corresponding to given @head and set buffer's
- * "current" pointers accordingly.
+ * "current" pointers accordingly. This is done after we have obtained the
+ * current aux_head position from a successful call to perf_aux_output_begin()
+ * to make sure the hardware is writing to the right place.
+ *
+ * This function modifies buf::{cur,cur_idx,output_off} that will be programmed
+ * into PT msrs when the tracing is enabled and buf::head and buf::data_size,
+ * which are used to determine INT and STOP markers' locations by a subsequent
+ * call to pt_buffer_reset_markers().
*/
static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
{
@@ -891,6 +901,7 @@ void intel_pt_interrupt(void)
}
pt_buffer_reset_offsets(buf, pt->handle.head);
+ /* snapshot counters don't use PMI, so it's safe */
ret = pt_buffer_reset_markers(buf, &pt->handle);
if (ret) {
perf_aux_output_end(&pt->handle, 0, true);
@@ -913,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode)
struct pt *pt = this_cpu_ptr(&pt_ctx);
struct pt_buffer *buf = perf_get_aux(&pt->handle);
- if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) {
+ if (!buf || pt_buffer_is_full(buf, pt)) {
event->hw.state = PERF_HES_STOPPED;
return;
}
@@ -944,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode)
event->hw.state = PERF_HES_STOPPED;
if (mode & PERF_EF_UPDATE) {
- struct pt *pt = this_cpu_ptr(&pt_ctx);
struct pt_buffer *buf = perf_get_aux(&pt->handle);
if (!buf)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 358c54ad20d4..5cbd4e64feb5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -204,9 +204,8 @@ again:
static void rapl_start_hrtimer(struct rapl_pmu *pmu)
{
- __hrtimer_start_range_ns(&pmu->hrtimer,
- pmu->timer_interval, 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&pmu->hrtimer, pmu->timer_interval,
+ HRTIMER_MODE_REL_PINNED);
}
static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c635b8b49e93..21b5e38c921b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -233,9 +233,8 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
{
- __hrtimer_start_range_ns(&box->hrtimer,
- ns_to_ktime(box->hrtimer_duration), 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
+ HRTIMER_MODE_REL_PINNED);
}
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
@@ -365,9 +364,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
- hwc = &box->event_list[i]->hw;
c = uncore_get_event_constraint(box, box->event_list[i]);
- hwc->constraint = c;
+ box->event_constraint[i] = c;
wmin = min(wmin, c->weight);
wmax = max(wmax, c->weight);
}
@@ -375,7 +373,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
/* fastpath, try to reuse previous register */
for (i = 0; i < n; i++) {
hwc = &box->event_list[i]->hw;
- c = hwc->constraint;
+ c = box->event_constraint[i];
/* never assigned */
if (hwc->idx == -1)
@@ -395,8 +393,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
}
/* slow path */
if (i != n)
- ret = perf_assign_events(box->event_list, n,
- wmin, wmax, assign);
+ ret = perf_assign_events(box->event_constraint, n,
+ wmin, wmax, n, assign);
if (!assign || ret) {
for (i = 0; i < n; i++)
@@ -840,6 +838,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
box->phys_id = phys_id;
box->pci_dev = pdev;
box->pmu = pmu;
+ uncore_box_init(box);
pci_set_drvdata(pdev, box);
raw_spin_lock(&uncore_box_lock);
@@ -922,6 +921,9 @@ static int __init uncore_pci_init(void)
case 69: /* Haswell Celeron */
ret = hsw_uncore_pci_init();
break;
+ case 61: /* Broadwell */
+ ret = bdw_uncore_pci_init();
+ break;
default:
return 0;
}
@@ -1003,8 +1005,10 @@ static int uncore_cpu_starting(int cpu)
pmu = &type->pmus[j];
box = *per_cpu_ptr(pmu->box, cpu);
/* called by uncore_cpu_init? */
- if (box && box->phys_id >= 0)
+ if (box && box->phys_id >= 0) {
+ uncore_box_init(box);
continue;
+ }
for_each_online_cpu(k) {
exist = *per_cpu_ptr(pmu->box, k);
@@ -1020,8 +1024,10 @@ static int uncore_cpu_starting(int cpu)
}
}
- if (box)
+ if (box) {
box->phys_id = phys_id;
+ uncore_box_init(box);
+ }
}
}
return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 6c8c1e7e69d8..0f77f0a196e4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -97,6 +97,7 @@ struct intel_uncore_box {
atomic_t refcnt;
struct perf_event *events[UNCORE_PMC_IDX_MAX];
struct perf_event *event_list[UNCORE_PMC_IDX_MAX];
+ struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX];
unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
u64 tags[UNCORE_PMC_IDX_MAX];
struct pci_dev *pci_dev;
@@ -257,14 +258,6 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
return box->pmu->type->num_counters;
}
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
- if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
- if (box->pmu->type->ops->init_box)
- box->pmu->type->ops->init_box(box);
- }
-}
-
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
@@ -273,8 +266,6 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
static inline void uncore_enable_box(struct intel_uncore_box *box)
{
- uncore_box_init(box);
-
if (box->pmu->type->ops->enable_box)
box->pmu->type->ops->enable_box(box);
}
@@ -297,6 +288,14 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
return box->pmu->type->ops->read_counter(box, event);
}
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+ if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+ if (box->pmu->type->ops->init_box)
+ box->pmu->type->ops->init_box(box);
+ }
+}
+
static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
{
return (box->phys_id < 0);
@@ -326,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty;
int snb_uncore_pci_init(void);
int ivb_uncore_pci_init(void);
int hsw_uncore_pci_init(void);
+int bdw_uncore_pci_init(void);
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 4562e9e22c60..b005a78c7012 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -7,6 +7,7 @@
#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -486,6 +487,14 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = {
{ /* end: all zeroes */ },
};
+static const struct pci_device_id bdw_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
@@ -501,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = {
.id_table = hsw_uncore_pci_ids,
};
+static struct pci_driver bdw_uncore_pci_driver = {
+ .name = "bdw_uncore",
+ .id_table = bdw_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
@@ -514,6 +528,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */
IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */
+ IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */
{ /* end marker */ }
};
@@ -561,6 +576,11 @@ int hsw_uncore_pci_init(void)
return imc_uncore_pci_init();
}
+int bdw_uncore_pci_init(void)
+{
+ return imc_uncore_pci_init();
+}
+
/* end of Sandy Bridge uncore support */
/* Nehalem uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 12d9548457e7..6d6e85dd5849 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -164,8 +164,8 @@
((1ULL << (n)) - 1)))
/* Haswell-EP Ubox */
-#define HSWEP_U_MSR_PMON_CTR0 0x705
-#define HSWEP_U_MSR_PMON_CTL0 0x709
+#define HSWEP_U_MSR_PMON_CTR0 0x709
+#define HSWEP_U_MSR_PMON_CTL0 0x705
#define HSWEP_U_MSR_PMON_FILTER 0x707
#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL 0x703
@@ -1914,7 +1914,7 @@ static struct intel_uncore_type hswep_uncore_cbox = {
.name = "cbox",
.num_counters = 4,
.num_boxes = 18,
- .perf_ctr_bits = 44,
+ .perf_ctr_bits = 48,
.event_ctl = HSWEP_C0_MSR_PMON_CTL0,
.perf_ctr = HSWEP_C0_MSR_PMON_CTR0,
.event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index e7d8c7608471..18ca99f2798b 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
{
#ifdef CONFIG_SMP
seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
- seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu)));
+ seq_printf(m, "siblings\t: %d\n",
+ cpumask_weight(topology_core_cpumask(cpu)));
seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
seq_printf(m, "apicid\t\t: %d\n", c->apicid);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c76d3e37c6e1..e068d6683dba 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -22,6 +22,7 @@
#include <linux/elfcore.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
#include <asm/processor.h>
#include <asm/hardirq.h>
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 6367a780cc8c..5ee771859b6f 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -4,7 +4,6 @@
#include <linux/bootmem.h>
#include <linux/export.h>
#include <linux/io.h>
-#include <linux/irqdomain.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/of.h>
@@ -17,6 +16,7 @@
#include <linux/of_pci.h>
#include <linux/initrd.h>
+#include <asm/irqdomain.h>
#include <asm/hpet.h>
#include <asm/apic.h>
#include <asm/pci_x86.h>
@@ -196,38 +196,31 @@ static struct of_ioapic_type of_ioapic_type[] =
},
};
-static int ioapic_xlate(struct irq_domain *domain,
- struct device_node *controller,
- const u32 *intspec, u32 intsize,
- irq_hw_number_t *out_hwirq, u32 *out_type)
+static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
+ struct of_phandle_args *irq_data = (void *)arg;
struct of_ioapic_type *it;
- u32 line, idx, gsi;
+ struct irq_alloc_info tmp;
- if (WARN_ON(intsize < 2))
+ if (WARN_ON(irq_data->args_count < 2))
return -EINVAL;
-
- line = intspec[0];
-
- if (intspec[1] >= ARRAY_SIZE(of_ioapic_type))
+ if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type))
return -EINVAL;
- it = &of_ioapic_type[intspec[1]];
+ it = &of_ioapic_type[irq_data->args[1]];
+ ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity);
+ tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
+ tmp.ioapic_pin = irq_data->args[0];
- idx = (u32)(long)domain->host_data;
- gsi = mp_pin_to_gsi(idx, line);
- if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0)))
- return -EBUSY;
-
- *out_hwirq = line;
- *out_type = it->out_type;
- return 0;
+ return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp);
}
-const struct irq_domain_ops ioapic_irq_domain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
- .xlate = ioapic_xlate,
+static const struct irq_domain_ops ioapic_irq_domain_ops = {
+ .alloc = dt_irqdomain_alloc,
+ .free = mp_irqdomain_free,
+ .activate = mp_irqdomain_activate,
+ .deactivate = mp_irqdomain_deactivate,
};
static void __init dtb_add_ioapic(struct device_node *dn)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index fe9f0b79a18b..5cb9a4d6f623 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -627,8 +627,12 @@ static struct chipset early_qrk[] __initdata = {
{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
QFLAG_APPLY_ONCE, intel_graphics_stolen },
/*
- * HPET on current version of Baytrail platform has accuracy
- * problems, disable it for now:
+ * HPET on the current version of the Baytrail platform has accuracy
+ * problems: it will halt in deep idle state - so we disable it.
+ *
+ * More details can be found in section 18.10.1.3 of the datasheet:
+ *
+ * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/atom-z8000-datasheet-vol-1.pdf
*/
{ PCI_VENDOR_ID_INTEL, 0x0f00,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
deleted file mode 100644
index 1c309763e321..000000000000
--- a/arch/x86/kernel/entry_32.S
+++ /dev/null
@@ -1,1401 +0,0 @@
-/*
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-/*
- * entry.S contains the system-call and fault low-level handling routines.
- * This also contains the timer-interrupt handler, as well as all interrupts
- * and faults that can result in a task-switch.
- *
- * NOTE: This code handles signal-recognition, which happens every time
- * after a timer-interrupt and after each system call.
- *
- * I changed all the .align's to 4 (16 byte alignment), as that's faster
- * on a 486.
- *
- * Stack layout in 'syscall_exit':
- * ptrace needs to have all regs on the stack.
- * if the order here is changed, it needs to be
- * updated in fork.c:copy_process, signal.c:do_signal,
- * ptrace.c and ptrace.h
- *
- * 0(%esp) - %ebx
- * 4(%esp) - %ecx
- * 8(%esp) - %edx
- * C(%esp) - %esi
- * 10(%esp) - %edi
- * 14(%esp) - %ebp
- * 18(%esp) - %eax
- * 1C(%esp) - %ds
- * 20(%esp) - %es
- * 24(%esp) - %fs
- * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
- * 2C(%esp) - orig_eax
- * 30(%esp) - %eip
- * 34(%esp) - %cs
- * 38(%esp) - %eflags
- * 3C(%esp) - %oldesp
- * 40(%esp) - %oldss
- *
- * "current" is in register %ebx during any slow entries.
- */
-
-#include <linux/linkage.h>
-#include <linux/err.h>
-#include <asm/thread_info.h>
-#include <asm/irqflags.h>
-#include <asm/errno.h>
-#include <asm/segment.h>
-#include <asm/smp.h>
-#include <asm/page_types.h>
-#include <asm/percpu.h>
-#include <asm/dwarf2.h>
-#include <asm/processor-flags.h>
-#include <asm/ftrace.h>
-#include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
-#include <asm/alternative-asm.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE 0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysenter_audit syscall_trace_entry
-#define sysexit_audit syscall_exit_work
-#endif
-
- .section .entry.text, "ax"
-
-/*
- * We use macros for low-level operations which need to be overridden
- * for paravirtualization. The following will never clobber any registers:
- * INTERRUPT_RETURN (aka. "iret")
- * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
- * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
- *
- * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
- * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
- * Allowing a register to be clobbered can shrink the paravirt replacement
- * enough to patch inline, increasing performance.
- */
-
-#ifdef CONFIG_PREEMPT
-#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
-#else
-#define preempt_stop(clobbers)
-#define resume_kernel restore_all
-#endif
-
-.macro TRACE_IRQS_IRET
-#ifdef CONFIG_TRACE_IRQFLAGS
- testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off?
- jz 1f
- TRACE_IRQS_ON
-1:
-#endif
-.endm
-
-/*
- * User gs save/restore
- *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc. Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
- */
-#ifdef CONFIG_X86_32_LAZY_GS
-
- /* unfortunately push/pop can't be no-op */
-.macro PUSH_GS
- pushl_cfi $0
-.endm
-.macro POP_GS pop=0
- addl $(4 + \pop), %esp
- CFI_ADJUST_CFA_OFFSET -(4 + \pop)
-.endm
-.macro POP_GS_EX
-.endm
-
- /* all the rest are no-op */
-.macro PTGS_TO_GS
-.endm
-.macro PTGS_TO_GS_EX
-.endm
-.macro GS_TO_REG reg
-.endm
-.macro REG_TO_PTGS reg
-.endm
-.macro SET_KERNEL_GS reg
-.endm
-
-#else /* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
- pushl_cfi %gs
- /*CFI_REL_OFFSET gs, 0*/
-.endm
-
-.macro POP_GS pop=0
-98: popl_cfi %gs
- /*CFI_RESTORE gs*/
- .if \pop <> 0
- add $\pop, %esp
- CFI_ADJUST_CFA_OFFSET -\pop
- .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99: movl $0, (%esp)
- jmp 98b
-.popsection
- _ASM_EXTABLE(98b,99b)
-.endm
-
-.macro PTGS_TO_GS
-98: mov PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99: movl $0, PT_GS(%esp)
- jmp 98b
-.popsection
- _ASM_EXTABLE(98b,99b)
-.endm
-
-.macro GS_TO_REG reg
- movl %gs, \reg
- /*CFI_REGISTER gs, \reg*/
-.endm
-.macro REG_TO_PTGS reg
- movl \reg, PT_GS(%esp)
- /*CFI_REL_OFFSET gs, PT_GS*/
-.endm
-.macro SET_KERNEL_GS reg
- movl $(__KERNEL_STACK_CANARY), \reg
- movl \reg, %gs
-.endm
-
-#endif /* CONFIG_X86_32_LAZY_GS */
-
-.macro SAVE_ALL
- cld
- PUSH_GS
- pushl_cfi %fs
- /*CFI_REL_OFFSET fs, 0;*/
- pushl_cfi %es
- /*CFI_REL_OFFSET es, 0;*/
- pushl_cfi %ds
- /*CFI_REL_OFFSET ds, 0;*/
- pushl_cfi %eax
- CFI_REL_OFFSET eax, 0
- pushl_cfi %ebp
- CFI_REL_OFFSET ebp, 0
- pushl_cfi %edi
- CFI_REL_OFFSET edi, 0
- pushl_cfi %esi
- CFI_REL_OFFSET esi, 0
- pushl_cfi %edx
- CFI_REL_OFFSET edx, 0
- pushl_cfi %ecx
- CFI_REL_OFFSET ecx, 0
- pushl_cfi %ebx
- CFI_REL_OFFSET ebx, 0
- movl $(__USER_DS), %edx
- movl %edx, %ds
- movl %edx, %es
- movl $(__KERNEL_PERCPU), %edx
- movl %edx, %fs
- SET_KERNEL_GS %edx
-.endm
-
-.macro RESTORE_INT_REGS
- popl_cfi %ebx
- CFI_RESTORE ebx
- popl_cfi %ecx
- CFI_RESTORE ecx
- popl_cfi %edx
- CFI_RESTORE edx
- popl_cfi %esi
- CFI_RESTORE esi
- popl_cfi %edi
- CFI_RESTORE edi
- popl_cfi %ebp
- CFI_RESTORE ebp
- popl_cfi %eax
- CFI_RESTORE eax
-.endm
-
-.macro RESTORE_REGS pop=0
- RESTORE_INT_REGS
-1: popl_cfi %ds
- /*CFI_RESTORE ds;*/
-2: popl_cfi %es
- /*CFI_RESTORE es;*/
-3: popl_cfi %fs
- /*CFI_RESTORE fs;*/
- POP_GS \pop
-.pushsection .fixup, "ax"
-4: movl $0, (%esp)
- jmp 1b
-5: movl $0, (%esp)
- jmp 2b
-6: movl $0, (%esp)
- jmp 3b
-.popsection
- _ASM_EXTABLE(1b,4b)
- _ASM_EXTABLE(2b,5b)
- _ASM_EXTABLE(3b,6b)
- POP_GS_EX
-.endm
-
-.macro RING0_INT_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 3*4
- /*CFI_OFFSET cs, -2*4;*/
- CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_EC_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 4*4
- /*CFI_OFFSET cs, -2*4;*/
- CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_PTREGS_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, PT_OLDESP-PT_EBX
- /*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/
- CFI_OFFSET eip, PT_EIP-PT_OLDESP
- /*CFI_OFFSET es, PT_ES-PT_OLDESP;*/
- /*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/
- CFI_OFFSET eax, PT_EAX-PT_OLDESP
- CFI_OFFSET ebp, PT_EBP-PT_OLDESP
- CFI_OFFSET edi, PT_EDI-PT_OLDESP
- CFI_OFFSET esi, PT_ESI-PT_OLDESP
- CFI_OFFSET edx, PT_EDX-PT_OLDESP
- CFI_OFFSET ecx, PT_ECX-PT_OLDESP
- CFI_OFFSET ebx, PT_EBX-PT_OLDESP
-.endm
-
-ENTRY(ret_from_fork)
- CFI_STARTPROC
- pushl_cfi %eax
- call schedule_tail
- GET_THREAD_INFO(%ebp)
- popl_cfi %eax
- pushl_cfi $0x0202 # Reset kernel eflags
- popfl_cfi
- jmp syscall_exit
- CFI_ENDPROC
-END(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
- CFI_STARTPROC
- pushl_cfi %eax
- call schedule_tail
- GET_THREAD_INFO(%ebp)
- popl_cfi %eax
- pushl_cfi $0x0202 # Reset kernel eflags
- popfl_cfi
- movl PT_EBP(%esp),%eax
- call *PT_EBX(%esp)
- movl $0,PT_EAX(%esp)
- jmp syscall_exit
- CFI_ENDPROC
-ENDPROC(ret_from_kernel_thread)
-
-/*
- * Return to user mode is not as complex as all this looks,
- * but we want the default path for a system call return to
- * go as quickly as possible which is why some of this is
- * less clear than it otherwise should be.
- */
-
- # userspace resumption stub bypassing syscall exit tracing
- ALIGN
- RING0_PTREGS_FRAME
-ret_from_exception:
- preempt_stop(CLBR_ANY)
-ret_from_intr:
- GET_THREAD_INFO(%ebp)
-#ifdef CONFIG_VM86
- movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
- movb PT_CS(%esp), %al
- andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
-#else
- /*
- * We can be coming here from child spawned by kernel_thread().
- */
- movl PT_CS(%esp), %eax
- andl $SEGMENT_RPL_MASK, %eax
-#endif
- cmpl $USER_RPL, %eax
- jb resume_kernel # not returning to v8086 or userspace
-
-ENTRY(resume_userspace)
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- andl $_TIF_WORK_MASK, %ecx # is there any work to be done on
- # int/exception return?
- jne work_pending
- jmp restore_all
-END(ret_from_exception)
-
-#ifdef CONFIG_PREEMPT
-ENTRY(resume_kernel)
- DISABLE_INTERRUPTS(CLBR_ANY)
-need_resched:
- cmpl $0,PER_CPU_VAR(__preempt_count)
- jnz restore_all
- testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ?
- jz restore_all
- call preempt_schedule_irq
- jmp need_resched
-END(resume_kernel)
-#endif
- CFI_ENDPROC
-
-/* SYSENTER_RETURN points to after the "sysenter" instruction in
- the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */
-
- # sysenter call handler stub
-ENTRY(ia32_sysenter_target)
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 0
- CFI_REGISTER esp, ebp
- movl TSS_sysenter_sp0(%esp),%esp
-sysenter_past_esp:
- /*
- * Interrupts are disabled here, but we can't trace it until
- * enough kernel state to call TRACE_IRQS_OFF can be called - but
- * we immediately enable interrupts at that point anyway.
- */
- pushl_cfi $__USER_DS
- /*CFI_REL_OFFSET ss, 0*/
- pushl_cfi %ebp
- CFI_REL_OFFSET esp, 0
- pushfl_cfi
- orl $X86_EFLAGS_IF, (%esp)
- pushl_cfi $__USER_CS
- /*CFI_REL_OFFSET cs, 0*/
- /*
- * Push current_thread_info()->sysenter_return to the stack.
- * A tiny bit of offset fixup is necessary: TI_sysenter_return
- * is relative to thread_info, which is at the bottom of the
- * kernel stack page. 4*4 means the 4 words pushed above;
- * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
- * and THREAD_SIZE takes us to the bottom.
- */
- pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
- CFI_REL_OFFSET eip, 0
-
- pushl_cfi %eax
- SAVE_ALL
- ENABLE_INTERRUPTS(CLBR_NONE)
-
-/*
- * Load the potential sixth argument from user stack.
- * Careful about security.
- */
- cmpl $__PAGE_OFFSET-3,%ebp
- jae syscall_fault
- ASM_STAC
-1: movl (%ebp),%ebp
- ASM_CLAC
- movl %ebp,PT_EBP(%esp)
- _ASM_EXTABLE(1b,syscall_fault)
-
- GET_THREAD_INFO(%ebp)
-
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
- jnz sysenter_audit
-sysenter_do_call:
- cmpl $(NR_syscalls), %eax
- jae sysenter_badsys
- call *sys_call_table(,%eax,4)
-sysenter_after_call:
- movl %eax,PT_EAX(%esp)
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $_TIF_ALLWORK_MASK, %ecx
- jnz sysexit_audit
-sysenter_exit:
-/* if something modifies registers it must also disable sysexit */
- movl PT_EIP(%esp), %edx
- movl PT_OLDESP(%esp), %ecx
- xorl %ebp,%ebp
- TRACE_IRQS_ON
-1: mov PT_FS(%esp), %fs
- PTGS_TO_GS
- ENABLE_INTERRUPTS_SYSEXIT
-
-#ifdef CONFIG_AUDITSYSCALL
-sysenter_audit:
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
- jnz syscall_trace_entry
- /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
- movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */
- /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
- pushl_cfi PT_ESI(%esp) /* a3: 5th arg */
- pushl_cfi PT_EDX+4(%esp) /* a2: 4th arg */
- call __audit_syscall_entry
- popl_cfi %ecx /* get that remapped edx off the stack */
- popl_cfi %ecx /* get that remapped esi off the stack */
- movl PT_EAX(%esp),%eax /* reload syscall number */
- jmp sysenter_do_call
-
-sysexit_audit:
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
- jnz syscall_exit_work
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_ANY)
- movl %eax,%edx /* second arg, syscall return value */
- cmpl $-MAX_ERRNO,%eax /* is it an error ? */
- setbe %al /* 1 if so, 0 if not */
- movzbl %al,%eax /* zero-extend that */
- call __audit_syscall_exit
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
- jnz syscall_exit_work
- movl PT_EAX(%esp),%eax /* reload syscall return value */
- jmp sysenter_exit
-#endif
-
- CFI_ENDPROC
-.pushsection .fixup,"ax"
-2: movl $0,PT_FS(%esp)
- jmp 1b
-.popsection
- _ASM_EXTABLE(1b,2b)
- PTGS_TO_GS_EX
-ENDPROC(ia32_sysenter_target)
-
- # system call handler stub
-ENTRY(system_call)
- RING0_INT_FRAME # can't unwind into user space anyway
- ASM_CLAC
- pushl_cfi %eax # save orig_eax
- SAVE_ALL
- GET_THREAD_INFO(%ebp)
- # system call tracing in operation / emulation
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
- jnz syscall_trace_entry
- cmpl $(NR_syscalls), %eax
- jae syscall_badsys
-syscall_call:
- call *sys_call_table(,%eax,4)
-syscall_after_call:
- movl %eax,PT_EAX(%esp) # store the return value
-syscall_exit:
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $_TIF_ALLWORK_MASK, %ecx # current->work
- jnz syscall_exit_work
-
-restore_all:
- TRACE_IRQS_IRET
-restore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
- movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
- # Warning: PT_OLDSS(%esp) contains the wrong/random values if we
- # are returning to the kernel.
- # See comments in process.c:copy_thread() for details.
- movb PT_OLDSS(%esp), %ah
- movb PT_CS(%esp), %al
- andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
- cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
- CFI_REMEMBER_STATE
- je ldt_ss # returning to user-space with LDT SS
-#endif
-restore_nocheck:
- RESTORE_REGS 4 # skip orig_eax/error_code
-irq_return:
- INTERRUPT_RETURN
-.section .fixup,"ax"
-ENTRY(iret_exc)
- pushl $0 # no error code
- pushl $do_iret_error
- jmp error_code
-.previous
- _ASM_EXTABLE(irq_return,iret_exc)
-
-#ifdef CONFIG_X86_ESPFIX32
- CFI_RESTORE_STATE
-ldt_ss:
-#ifdef CONFIG_PARAVIRT
- /*
- * The kernel can't run on a non-flat stack if paravirt mode
- * is active. Rather than try to fixup the high bits of
- * ESP, bypass this code entirely. This may break DOSemu
- * and/or Wine support in a paravirt VM, although the option
- * is still available to implement the setting of the high
- * 16-bits in the INTERRUPT_RETURN paravirt-op.
- */
- cmpl $0, pv_info+PARAVIRT_enabled
- jne restore_nocheck
-#endif
-
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
- mov %esp, %edx /* load kernel esp */
- mov PT_OLDESP(%esp), %eax /* load userspace esp */
- mov %dx, %ax /* eax: new kernel esp */
- sub %eax, %edx /* offset (low word is 0) */
- shr $16, %edx
- mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
- mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
- pushl_cfi $__ESPFIX_SS
- pushl_cfi %eax /* new kernel esp */
- /* Disable interrupts, but do not irqtrace this section: we
- * will soon execute iret and the tracer was already set to
- * the irqstate after the iret */
- DISABLE_INTERRUPTS(CLBR_EAX)
- lss (%esp), %esp /* switch to espfix segment */
- CFI_ADJUST_CFA_OFFSET -8
- jmp restore_nocheck
-#endif
- CFI_ENDPROC
-ENDPROC(system_call)
-
- # perform work that needs to be done immediately before resumption
- ALIGN
- RING0_PTREGS_FRAME # can't unwind into user space anyway
-work_pending:
- testb $_TIF_NEED_RESCHED, %cl
- jz work_notifysig
-work_resched:
- call schedule
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- andl $_TIF_WORK_MASK, %ecx # is there any work to be done other
- # than syscall tracing?
- jz restore_all
- testb $_TIF_NEED_RESCHED, %cl
- jnz work_resched
-
-work_notifysig: # deal with pending signals and
- # notify-resume requests
-#ifdef CONFIG_VM86
- testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
- movl %esp, %eax
- jnz work_notifysig_v86 # returning to kernel-space or
- # vm86-space
-1:
-#else
- movl %esp, %eax
-#endif
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- movb PT_CS(%esp), %bl
- andb $SEGMENT_RPL_MASK, %bl
- cmpb $USER_RPL, %bl
- jb resume_kernel
- xorl %edx, %edx
- call do_notify_resume
- jmp resume_userspace
-
-#ifdef CONFIG_VM86
- ALIGN
-work_notifysig_v86:
- pushl_cfi %ecx # save ti_flags for do_notify_resume
- call save_v86_state # %eax contains pt_regs pointer
- popl_cfi %ecx
- movl %eax, %esp
- jmp 1b
-#endif
-END(work_pending)
-
- # perform syscall exit tracing
- ALIGN
-syscall_trace_entry:
- movl $-ENOSYS,PT_EAX(%esp)
- movl %esp, %eax
- call syscall_trace_enter
- /* What it returned is what we'll actually use. */
- cmpl $(NR_syscalls), %eax
- jnae syscall_call
- jmp syscall_exit
-END(syscall_trace_entry)
-
- # perform syscall exit tracing
- ALIGN
-syscall_exit_work:
- testl $_TIF_WORK_SYSCALL_EXIT, %ecx
- jz work_pending
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call
- # schedule() instead
- movl %esp, %eax
- call syscall_trace_leave
- jmp resume_userspace
-END(syscall_exit_work)
- CFI_ENDPROC
-
- RING0_INT_FRAME # can't unwind into user space anyway
-syscall_fault:
- ASM_CLAC
- GET_THREAD_INFO(%ebp)
- movl $-EFAULT,PT_EAX(%esp)
- jmp resume_userspace
-END(syscall_fault)
-
-syscall_badsys:
- movl $-ENOSYS,%eax
- jmp syscall_after_call
-END(syscall_badsys)
-
-sysenter_badsys:
- movl $-ENOSYS,%eax
- jmp sysenter_after_call
-END(sysenter_badsys)
- CFI_ENDPROC
-
-.macro FIXUP_ESPFIX_STACK
-/*
- * Switch back for ESPFIX stack to the normal zerobased stack
- *
- * We can't call C functions using the ESPFIX stack. This code reads
- * the high word of the segment base from the GDT and swiches to the
- * normal stack and adjusts ESP with the matching offset.
- */
-#ifdef CONFIG_X86_ESPFIX32
- /* fixup the stack */
- mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
- mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
- shl $16, %eax
- addl %esp, %eax /* the adjusted stack pointer */
- pushl_cfi $__KERNEL_DS
- pushl_cfi %eax
- lss (%esp), %esp /* switch to the normal stack segment */
- CFI_ADJUST_CFA_OFFSET -8
-#endif
-.endm
-.macro UNWIND_ESPFIX_STACK
-#ifdef CONFIG_X86_ESPFIX32
- movl %ss, %eax
- /* see if on espfix stack */
- cmpw $__ESPFIX_SS, %ax
- jne 27f
- movl $__KERNEL_DS, %eax
- movl %eax, %ds
- movl %eax, %es
- /* switch to normal stack */
- FIXUP_ESPFIX_STACK
-27:
-#endif
-.endm
-
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
- .align 8
-ENTRY(irq_entries_start)
- RING0_INT_FRAME
- vector=FIRST_EXTERNAL_VECTOR
- .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
- pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */
- vector=vector+1
- jmp common_interrupt
- CFI_ADJUST_CFA_OFFSET -4
- .align 8
- .endr
-END(irq_entries_start)
-
-/*
- * the CPU automatically disables interrupts when executing an IRQ vector,
- * so IRQ-flags tracing has to follow that:
- */
- .p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
- ASM_CLAC
- addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */
- SAVE_ALL
- TRACE_IRQS_OFF
- movl %esp,%eax
- call do_IRQ
- jmp ret_from_intr
-ENDPROC(common_interrupt)
- CFI_ENDPROC
-
-#define BUILD_INTERRUPT3(name, nr, fn) \
-ENTRY(name) \
- RING0_INT_FRAME; \
- ASM_CLAC; \
- pushl_cfi $~(nr); \
- SAVE_ALL; \
- TRACE_IRQS_OFF \
- movl %esp,%eax; \
- call fn; \
- jmp ret_from_intr; \
- CFI_ENDPROC; \
-ENDPROC(name)
-
-
-#ifdef CONFIG_TRACING
-#define TRACE_BUILD_INTERRUPT(name, nr) \
- BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
-#else
-#define TRACE_BUILD_INTERRUPT(name, nr)
-#endif
-
-#define BUILD_INTERRUPT(name, nr) \
- BUILD_INTERRUPT3(name, nr, smp_##name); \
- TRACE_BUILD_INTERRUPT(name, nr)
-
-/* The include is where all of the SMP etc. interrupts come from */
-#include <asm/entry_arch.h>
-
-ENTRY(coprocessor_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_coprocessor_error
- jmp error_code
- CFI_ENDPROC
-END(coprocessor_error)
-
-ENTRY(simd_coprocessor_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
-#ifdef CONFIG_X86_INVD_BUG
- /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
- ALTERNATIVE "pushl_cfi $do_general_protection", \
- "pushl $do_simd_coprocessor_error", \
- X86_FEATURE_XMM
-#else
- pushl_cfi $do_simd_coprocessor_error
-#endif
- jmp error_code
- CFI_ENDPROC
-END(simd_coprocessor_error)
-
-ENTRY(device_not_available)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $-1 # mark this as an int
- pushl_cfi $do_device_not_available
- jmp error_code
- CFI_ENDPROC
-END(device_not_available)
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
- iret
- _ASM_EXTABLE(native_iret, iret_exc)
-END(native_iret)
-
-ENTRY(native_irq_enable_sysexit)
- sti
- sysexit
-END(native_irq_enable_sysexit)
-#endif
-
-ENTRY(overflow)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_overflow
- jmp error_code
- CFI_ENDPROC
-END(overflow)
-
-ENTRY(bounds)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_bounds
- jmp error_code
- CFI_ENDPROC
-END(bounds)
-
-ENTRY(invalid_op)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_invalid_op
- jmp error_code
- CFI_ENDPROC
-END(invalid_op)
-
-ENTRY(coprocessor_segment_overrun)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_coprocessor_segment_overrun
- jmp error_code
- CFI_ENDPROC
-END(coprocessor_segment_overrun)
-
-ENTRY(invalid_TSS)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_invalid_TSS
- jmp error_code
- CFI_ENDPROC
-END(invalid_TSS)
-
-ENTRY(segment_not_present)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_segment_not_present
- jmp error_code
- CFI_ENDPROC
-END(segment_not_present)
-
-ENTRY(stack_segment)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_stack_segment
- jmp error_code
- CFI_ENDPROC
-END(stack_segment)
-
-ENTRY(alignment_check)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_alignment_check
- jmp error_code
- CFI_ENDPROC
-END(alignment_check)
-
-ENTRY(divide_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0 # no error code
- pushl_cfi $do_divide_error
- jmp error_code
- CFI_ENDPROC
-END(divide_error)
-
-#ifdef CONFIG_X86_MCE
-ENTRY(machine_check)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi machine_check_vector
- jmp error_code
- CFI_ENDPROC
-END(machine_check)
-#endif
-
-ENTRY(spurious_interrupt_bug)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_spurious_interrupt_bug
- jmp error_code
- CFI_ENDPROC
-END(spurious_interrupt_bug)
-
-#ifdef CONFIG_XEN
-/* Xen doesn't set %esp to be precisely what the normal sysenter
- entrypoint expects, so fix it up before using the normal path. */
-ENTRY(xen_sysenter_target)
- RING0_INT_FRAME
- addl $5*4, %esp /* remove xen-provided frame */
- CFI_ADJUST_CFA_OFFSET -5*4
- jmp sysenter_past_esp
- CFI_ENDPROC
-
-ENTRY(xen_hypervisor_callback)
- CFI_STARTPROC
- pushl_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
- TRACE_IRQS_OFF
-
- /* Check to see if we got the event in the critical
- region in xen_iret_direct, after we've reenabled
- events and checked for pending events. This simulates
- iret instruction's behaviour where it delivers a
- pending interrupt when enabling interrupts. */
- movl PT_EIP(%esp),%eax
- cmpl $xen_iret_start_crit,%eax
- jb 1f
- cmpl $xen_iret_end_crit,%eax
- jae 1f
-
- jmp xen_iret_crit_fixup
-
-ENTRY(xen_do_upcall)
-1: mov %esp, %eax
- call xen_evtchn_do_upcall
-#ifndef CONFIG_PREEMPT
- call xen_maybe_preempt_hcall
-#endif
- jmp ret_from_intr
- CFI_ENDPROC
-ENDPROC(xen_hypervisor_callback)
-
-# Hypervisor uses this for application faults while it executes.
-# We get here for two reasons:
-# 1. Fault while reloading DS, ES, FS or GS
-# 2. Fault while executing IRET
-# Category 1 we fix up by reattempting the load, and zeroing the segment
-# register if the load fails.
-# Category 2 we fix up by jumping to do_iret_error. We cannot use the
-# normal Linux return path in this case because if we use the IRET hypercall
-# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
-# We distinguish between categories by maintaining a status value in EAX.
-ENTRY(xen_failsafe_callback)
- CFI_STARTPROC
- pushl_cfi %eax
- movl $1,%eax
-1: mov 4(%esp),%ds
-2: mov 8(%esp),%es
-3: mov 12(%esp),%fs
-4: mov 16(%esp),%gs
- /* EAX == 0 => Category 1 (Bad segment)
- EAX != 0 => Category 2 (Bad IRET) */
- testl %eax,%eax
- popl_cfi %eax
- lea 16(%esp),%esp
- CFI_ADJUST_CFA_OFFSET -16
- jz 5f
- jmp iret_exc
-5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
- jmp ret_from_exception
- CFI_ENDPROC
-
-.section .fixup,"ax"
-6: xorl %eax,%eax
- movl %eax,4(%esp)
- jmp 1b
-7: xorl %eax,%eax
- movl %eax,8(%esp)
- jmp 2b
-8: xorl %eax,%eax
- movl %eax,12(%esp)
- jmp 3b
-9: xorl %eax,%eax
- movl %eax,16(%esp)
- jmp 4b
-.previous
- _ASM_EXTABLE(1b,6b)
- _ASM_EXTABLE(2b,7b)
- _ASM_EXTABLE(3b,8b)
- _ASM_EXTABLE(4b,9b)
-ENDPROC(xen_failsafe_callback)
-
-BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
- xen_evtchn_do_upcall)
-
-#endif /* CONFIG_XEN */
-
-#if IS_ENABLED(CONFIG_HYPERV)
-
-BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
- hyperv_vector_handler)
-
-#endif /* CONFIG_HYPERV */
-
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(mcount)
- ret
-END(mcount)
-
-ENTRY(ftrace_caller)
- pushl %eax
- pushl %ecx
- pushl %edx
- pushl $0 /* Pass NULL as regs pointer */
- movl 4*4(%esp), %eax
- movl 0x4(%ebp), %edx
- movl function_trace_op, %ecx
- subl $MCOUNT_INSN_SIZE, %eax
-
-.globl ftrace_call
-ftrace_call:
- call ftrace_stub
-
- addl $4,%esp /* skip NULL pointer */
- popl %edx
- popl %ecx
- popl %eax
-ftrace_ret:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
- jmp ftrace_stub
-#endif
-
-.globl ftrace_stub
-ftrace_stub:
- ret
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
- pushf /* push flags before compare (in cs location) */
-
- /*
- * i386 does not save SS and ESP when coming from kernel.
- * Instead, to get sp, &regs->sp is used (see ptrace.h).
- * Unfortunately, that means eflags must be at the same location
- * as the current return ip is. We move the return ip into the
- * ip location, and move flags into the return ip location.
- */
- pushl 4(%esp) /* save return ip into ip slot */
-
- pushl $0 /* Load 0 into orig_ax */
- pushl %gs
- pushl %fs
- pushl %es
- pushl %ds
- pushl %eax
- pushl %ebp
- pushl %edi
- pushl %esi
- pushl %edx
- pushl %ecx
- pushl %ebx
-
- movl 13*4(%esp), %eax /* Get the saved flags */
- movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
- /* clobbering return ip */
- movl $__KERNEL_CS,13*4(%esp)
-
- movl 12*4(%esp), %eax /* Load ip (1st parameter) */
- subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
- movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
- movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
- pushl %esp /* Save pt_regs as 4th parameter */
-
-GLOBAL(ftrace_regs_call)
- call ftrace_stub
-
- addl $4, %esp /* Skip pt_regs */
- movl 14*4(%esp), %eax /* Move flags back into cs */
- movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
- movl 12*4(%esp), %eax /* Get return ip from regs->ip */
- movl %eax, 14*4(%esp) /* Put return ip back for ret */
-
- popl %ebx
- popl %ecx
- popl %edx
- popl %esi
- popl %edi
- popl %ebp
- popl %eax
- popl %ds
- popl %es
- popl %fs
- popl %gs
- addl $8, %esp /* Skip orig_ax and ip */
- popf /* Pop flags at end (no addl to corrupt flags) */
- jmp ftrace_ret
-
- popf
- jmp ftrace_stub
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(mcount)
- cmpl $__PAGE_OFFSET, %esp
- jb ftrace_stub /* Paging not enabled yet? */
-
- cmpl $ftrace_stub, ftrace_trace_function
- jnz trace
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- cmpl $ftrace_stub, ftrace_graph_return
- jnz ftrace_graph_caller
-
- cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
- jnz ftrace_graph_caller
-#endif
-.globl ftrace_stub
-ftrace_stub:
- ret
-
- /* taken from glibc */
-trace:
- pushl %eax
- pushl %ecx
- pushl %edx
- movl 0xc(%esp), %eax
- movl 0x4(%ebp), %edx
- subl $MCOUNT_INSN_SIZE, %eax
-
- call *ftrace_trace_function
-
- popl %edx
- popl %ecx
- popl %eax
- jmp ftrace_stub
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
- pushl %eax
- pushl %ecx
- pushl %edx
- movl 0xc(%esp), %eax
- lea 0x4(%ebp), %edx
- movl (%ebp), %ecx
- subl $MCOUNT_INSN_SIZE, %eax
- call prepare_ftrace_return
- popl %edx
- popl %ecx
- popl %eax
- ret
-END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
- pushl %eax
- pushl %edx
- movl %ebp, %eax
- call ftrace_return_to_handler
- movl %eax, %ecx
- popl %edx
- popl %eax
- jmp *%ecx
-#endif
-
-#ifdef CONFIG_TRACING
-ENTRY(trace_page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $trace_do_page_fault
- jmp error_code
- CFI_ENDPROC
-END(trace_page_fault)
-#endif
-
-ENTRY(page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_page_fault
- ALIGN
-error_code:
- /* the function address is in %gs's slot on the stack */
- pushl_cfi %fs
- /*CFI_REL_OFFSET fs, 0*/
- pushl_cfi %es
- /*CFI_REL_OFFSET es, 0*/
- pushl_cfi %ds
- /*CFI_REL_OFFSET ds, 0*/
- pushl_cfi_reg eax
- pushl_cfi_reg ebp
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg edx
- pushl_cfi_reg ecx
- pushl_cfi_reg ebx
- cld
- movl $(__KERNEL_PERCPU), %ecx
- movl %ecx, %fs
- UNWIND_ESPFIX_STACK
- GS_TO_REG %ecx
- movl PT_GS(%esp), %edi # get the function address
- movl PT_ORIG_EAX(%esp), %edx # get the error code
- movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
- REG_TO_PTGS %ecx
- SET_KERNEL_GS %ecx
- movl $(__USER_DS), %ecx
- movl %ecx, %ds
- movl %ecx, %es
- TRACE_IRQS_OFF
- movl %esp,%eax # pt_regs pointer
- call *%edi
- jmp ret_from_exception
- CFI_ENDPROC
-END(page_fault)
-
-/*
- * Debug traps and NMI can happen at the one SYSENTER instruction
- * that sets up the real kernel stack. Check here, since we can't
- * allow the wrong stack to be used.
- *
- * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
- * already pushed 3 words if it hits on the sysenter instruction:
- * eflags, cs and eip.
- *
- * We just load the right stack, and push the three (known) values
- * by hand onto the new stack - while updating the return eip past
- * the instruction that would have done it for sysenter.
- */
-.macro FIX_STACK offset ok label
- cmpw $__KERNEL_CS, 4(%esp)
- jne \ok
-\label:
- movl TSS_sysenter_sp0 + \offset(%esp), %esp
- CFI_DEF_CFA esp, 0
- CFI_UNDEFINED eip
- pushfl_cfi
- pushl_cfi $__KERNEL_CS
- pushl_cfi $sysenter_past_esp
- CFI_REL_OFFSET eip, 0
-.endm
-
-ENTRY(debug)
- RING0_INT_FRAME
- ASM_CLAC
- cmpl $ia32_sysenter_target,(%esp)
- jne debug_stack_correct
- FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
-debug_stack_correct:
- pushl_cfi $-1 # mark this as an int
- SAVE_ALL
- TRACE_IRQS_OFF
- xorl %edx,%edx # error code 0
- movl %esp,%eax # pt_regs pointer
- call do_debug
- jmp ret_from_exception
- CFI_ENDPROC
-END(debug)
-
-/*
- * NMI is doubly nasty. It can happen _while_ we're handling
- * a debug fault, and the debug fault hasn't yet been able to
- * clear up the stack. So we first check whether we got an
- * NMI on the sysenter entry path, but after that we need to
- * check whether we got an NMI on the debug path where the debug
- * fault happened on the sysenter path.
- */
-ENTRY(nmi)
- RING0_INT_FRAME
- ASM_CLAC
-#ifdef CONFIG_X86_ESPFIX32
- pushl_cfi %eax
- movl %ss, %eax
- cmpw $__ESPFIX_SS, %ax
- popl_cfi %eax
- je nmi_espfix_stack
-#endif
- cmpl $ia32_sysenter_target,(%esp)
- je nmi_stack_fixup
- pushl_cfi %eax
- movl %esp,%eax
- /* Do not access memory above the end of our stack page,
- * it might not exist.
- */
- andl $(THREAD_SIZE-1),%eax
- cmpl $(THREAD_SIZE-20),%eax
- popl_cfi %eax
- jae nmi_stack_correct
- cmpl $ia32_sysenter_target,12(%esp)
- je nmi_debug_stack_check
-nmi_stack_correct:
- /* We have a RING0_INT_FRAME here */
- pushl_cfi %eax
- SAVE_ALL
- xorl %edx,%edx # zero error code
- movl %esp,%eax # pt_regs pointer
- call do_nmi
- jmp restore_all_notrace
- CFI_ENDPROC
-
-nmi_stack_fixup:
- RING0_INT_FRAME
- FIX_STACK 12, nmi_stack_correct, 1
- jmp nmi_stack_correct
-
-nmi_debug_stack_check:
- /* We have a RING0_INT_FRAME here */
- cmpw $__KERNEL_CS,16(%esp)
- jne nmi_stack_correct
- cmpl $debug,(%esp)
- jb nmi_stack_correct
- cmpl $debug_esp_fix_insn,(%esp)
- ja nmi_stack_correct
- FIX_STACK 24, nmi_stack_correct, 1
- jmp nmi_stack_correct
-
-#ifdef CONFIG_X86_ESPFIX32
-nmi_espfix_stack:
- /* We have a RING0_INT_FRAME here.
- *
- * create the pointer to lss back
- */
- pushl_cfi %ss
- pushl_cfi %esp
- addl $4, (%esp)
- /* copy the iret frame of 12 bytes */
- .rept 3
- pushl_cfi 16(%esp)
- .endr
- pushl_cfi %eax
- SAVE_ALL
- FIXUP_ESPFIX_STACK # %eax == %esp
- xorl %edx,%edx # zero error code
- call do_nmi
- RESTORE_REGS
- lss 12+4(%esp), %esp # back to espfix stack
- CFI_ADJUST_CFA_OFFSET -24
- jmp irq_return
-#endif
- CFI_ENDPROC
-END(nmi)
-
-ENTRY(int3)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $-1 # mark this as an int
- SAVE_ALL
- TRACE_IRQS_OFF
- xorl %edx,%edx # zero error code
- movl %esp,%eax # pt_regs pointer
- call do_int3
- jmp ret_from_exception
- CFI_ENDPROC
-END(int3)
-
-ENTRY(general_protection)
- RING0_EC_FRAME
- pushl_cfi $do_general_protection
- jmp error_code
- CFI_ENDPROC
-END(general_protection)
-
-#ifdef CONFIG_KVM_GUEST
-ENTRY(async_page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_async_page_fault
- jmp error_code
- CFI_ENDPROC
-END(async_page_fault)
-#endif
-
diff --git a/arch/x86/kernel/fpu/Makefile b/arch/x86/kernel/fpu/Makefile
new file mode 100644
index 000000000000..68279efb811a
--- /dev/null
+++ b/arch/x86/kernel/fpu/Makefile
@@ -0,0 +1,5 @@
+#
+# Build rules for the FPU support code:
+#
+
+obj-y += init.o bugs.o core.o regset.o signal.o xstate.o
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
new file mode 100644
index 000000000000..dd9ca9b60ff3
--- /dev/null
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -0,0 +1,71 @@
+/*
+ * x86 FPU bug checks:
+ */
+#include <asm/fpu/internal.h>
+
+/*
+ * Boot time CPU/FPU FDIV bug detection code:
+ */
+
+static double __initdata x = 4195835.0;
+static double __initdata y = 3145727.0;
+
+/*
+ * This used to check for exceptions..
+ * However, it turns out that to support that,
+ * the XMM trap handlers basically had to
+ * be buggy. So let's have a correct XMM trap
+ * handler, and forget about printing out
+ * some status at boot.
+ *
+ * We should really only care about bugs here
+ * anyway. Not features.
+ */
+static void __init check_fpu(void)
+{
+ u32 cr0_saved;
+ s32 fdiv_bug;
+
+ /* We might have CR0::TS set already, clear it: */
+ cr0_saved = read_cr0();
+ write_cr0(cr0_saved & ~X86_CR0_TS);
+
+ kernel_fpu_begin();
+
+ /*
+ * trap_init() enabled FXSR and company _before_ testing for FP
+ * problems here.
+ *
+ * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
+ */
+ __asm__("fninit\n\t"
+ "fldl %1\n\t"
+ "fdivl %2\n\t"
+ "fmull %2\n\t"
+ "fldl %1\n\t"
+ "fsubp %%st,%%st(1)\n\t"
+ "fistpl %0\n\t"
+ "fwait\n\t"
+ "fninit"
+ : "=m" (*&fdiv_bug)
+ : "m" (*&x), "m" (*&y));
+
+ kernel_fpu_end();
+
+ write_cr0(cr0_saved);
+
+ if (fdiv_bug) {
+ set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
+ pr_warn("Hmm, FPU with FDIV bug\n");
+ }
+}
+
+void __init fpu__init_check_bugs(void)
+{
+ /*
+ * kernel_fpu_begin/end() in check_fpu() relies on the patched
+ * alternative instructions.
+ */
+ if (cpu_has_fpu)
+ check_fpu();
+}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
new file mode 100644
index 000000000000..79de954626fd
--- /dev/null
+++ b/arch/x86/kernel/fpu/core.c
@@ -0,0 +1,523 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/regset.h>
+#include <asm/fpu/signal.h>
+#include <asm/traps.h>
+
+#include <linux/hardirq.h>
+
+/*
+ * Represents the initial FPU state. It's mostly (but not completely) zeroes,
+ * depending on the FPU hardware format:
+ */
+union fpregs_state init_fpstate __read_mostly;
+
+/*
+ * Track whether the kernel is using the FPU state
+ * currently.
+ *
+ * This flag is used:
+ *
+ * - by IRQ context code to potentially use the FPU
+ * if it's unused.
+ *
+ * - to debug kernel_fpu_begin()/end() correctness
+ */
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+/*
+ * Track which context is using the FPU on the CPU:
+ */
+DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+static void kernel_fpu_disable(void)
+{
+ WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
+ this_cpu_write(in_kernel_fpu, true);
+}
+
+static void kernel_fpu_enable(void)
+{
+ WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+ this_cpu_write(in_kernel_fpu, false);
+}
+
+static bool kernel_fpu_disabled(void)
+{
+ return this_cpu_read(in_kernel_fpu);
+}
+
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: the thread must not have fpu (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return true; in the likely case
+ * the thread has FPU but we are not going to set/clear TS.
+ */
+static bool interrupted_kernel_fpu_idle(void)
+{
+ if (kernel_fpu_disabled())
+ return false;
+
+ if (use_eager_fpu())
+ return true;
+
+ return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static bool interrupted_user_mode(void)
+{
+ struct pt_regs *regs = get_irq_regs();
+ return regs && user_mode(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+bool irq_fpu_usable(void)
+{
+ return !in_interrupt() ||
+ interrupted_user_mode() ||
+ interrupted_kernel_fpu_idle();
+}
+EXPORT_SYMBOL(irq_fpu_usable);
+
+void __kernel_fpu_begin(void)
+{
+ struct fpu *fpu = &current->thread.fpu;
+
+ WARN_ON_FPU(!irq_fpu_usable());
+
+ kernel_fpu_disable();
+
+ if (fpu->fpregs_active) {
+ copy_fpregs_to_fpstate(fpu);
+ } else {
+ this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+ __fpregs_activate_hw();
+ }
+}
+EXPORT_SYMBOL(__kernel_fpu_begin);
+
+void __kernel_fpu_end(void)
+{
+ struct fpu *fpu = &current->thread.fpu;
+
+ if (fpu->fpregs_active)
+ copy_kernel_to_fpregs(&fpu->state);
+ else
+ __fpregs_deactivate_hw();
+
+ kernel_fpu_enable();
+}
+EXPORT_SYMBOL(__kernel_fpu_end);
+
+void kernel_fpu_begin(void)
+{
+ preempt_disable();
+ __kernel_fpu_begin();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+ __kernel_fpu_end();
+ preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);
+
+/*
+ * CR0::TS save/restore functions:
+ */
+int irq_ts_save(void)
+{
+ /*
+ * If in process context and not atomic, we can take a spurious DNA fault.
+ * Otherwise, doing clts() in process context requires disabling preemption
+ * or some heavy lifting like kernel_fpu_begin()
+ */
+ if (!in_atomic())
+ return 0;
+
+ if (read_cr0() & X86_CR0_TS) {
+ clts();
+ return 1;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(irq_ts_save);
+
+void irq_ts_restore(int TS_state)
+{
+ if (TS_state)
+ stts();
+}
+EXPORT_SYMBOL_GPL(irq_ts_restore);
+
+/*
+ * Save the FPU state (mark it for reload if necessary):
+ *
+ * This only ever gets called for the current task.
+ */
+void fpu__save(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != &current->thread.fpu);
+
+ preempt_disable();
+ if (fpu->fpregs_active) {
+ if (!copy_fpregs_to_fpstate(fpu))
+ fpregs_deactivate(fpu);
+ }
+ preempt_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__save);
+
+/*
+ * Legacy x87 fpstate state init:
+ */
+static inline void fpstate_init_fstate(struct fregs_state *fp)
+{
+ fp->cwd = 0xffff037fu;
+ fp->swd = 0xffff0000u;
+ fp->twd = 0xffffffffu;
+ fp->fos = 0xffff0000u;
+}
+
+void fpstate_init(union fpregs_state *state)
+{
+ if (!cpu_has_fpu) {
+ fpstate_init_soft(&state->soft);
+ return;
+ }
+
+ memset(state, 0, xstate_size);
+
+ if (cpu_has_fxsr)
+ fpstate_init_fxstate(&state->fxsave);
+ else
+ fpstate_init_fstate(&state->fsave);
+}
+EXPORT_SYMBOL_GPL(fpstate_init);
+
+/*
+ * Copy the current task's FPU state to a new task's FPU context.
+ *
+ * In both the 'eager' and the 'lazy' case we save hardware registers
+ * directly to the destination buffer.
+ */
+static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+ WARN_ON_FPU(src_fpu != &current->thread.fpu);
+
+ /*
+ * Don't let 'init optimized' areas of the XSAVE area
+ * leak into the child task:
+ */
+ if (use_eager_fpu())
+ memset(&dst_fpu->state.xsave, 0, xstate_size);
+
+ /*
+ * Save current FPU registers directly into the child
+ * FPU context, without any memory-to-memory copying.
+ *
+ * If the FPU context got destroyed in the process (FNSAVE
+ * done on old CPUs) then copy it back into the source
+ * context and mark the current task for lazy restore.
+ *
+ * We have to do all this with preemption disabled,
+ * mostly because of the FNSAVE case, because in that
+ * case we must not allow preemption in the window
+ * between the FNSAVE and us marking the context lazy.
+ *
+ * It shouldn't be an issue as even FNSAVE is plenty
+ * fast in terms of critical section length.
+ */
+ preempt_disable();
+ if (!copy_fpregs_to_fpstate(dst_fpu)) {
+ memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
+ fpregs_deactivate(src_fpu);
+ }
+ preempt_enable();
+}
+
+int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+ dst_fpu->counter = 0;
+ dst_fpu->fpregs_active = 0;
+ dst_fpu->last_cpu = -1;
+
+ if (src_fpu->fpstate_active)
+ fpu_copy(dst_fpu, src_fpu);
+
+ return 0;
+}
+
+/*
+ * Activate the current task's in-memory FPU context,
+ * if it has not been used before:
+ */
+void fpu__activate_curr(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != &current->thread.fpu);
+
+ if (!fpu->fpstate_active) {
+ fpstate_init(&fpu->state);
+
+ /* Safe to do for the current task: */
+ fpu->fpstate_active = 1;
+ }
+}
+EXPORT_SYMBOL_GPL(fpu__activate_curr);
+
+/*
+ * This function must be called before we read a task's fpstate.
+ *
+ * If the task has not used the FPU before then initialize its
+ * fpstate.
+ *
+ * If the task has used the FPU before then save it.
+ */
+void fpu__activate_fpstate_read(struct fpu *fpu)
+{
+ /*
+ * If fpregs are active (in the current CPU), then
+ * copy them to the fpstate:
+ */
+ if (fpu->fpregs_active) {
+ fpu__save(fpu);
+ } else {
+ if (!fpu->fpstate_active) {
+ fpstate_init(&fpu->state);
+
+ /* Safe to do for current and for stopped child tasks: */
+ fpu->fpstate_active = 1;
+ }
+ }
+}
+
+/*
+ * This function must be called before we write a task's fpstate.
+ *
+ * If the task has used the FPU before then unlazy it.
+ * If the task has not used the FPU before then initialize its fpstate.
+ *
+ * After this function call, after registers in the fpstate are
+ * modified and the child task has woken up, the child task will
+ * restore the modified FPU state from the modified context. If we
+ * didn't clear its lazy status here then the lazy in-registers
+ * state pending on its former CPU could be restored, corrupting
+ * the modifications.
+ */
+void fpu__activate_fpstate_write(struct fpu *fpu)
+{
+ /*
+ * Only stopped child tasks can be used to modify the FPU
+ * state in the fpstate buffer:
+ */
+ WARN_ON_FPU(fpu == &current->thread.fpu);
+
+ if (fpu->fpstate_active) {
+ /* Invalidate any lazy state: */
+ fpu->last_cpu = -1;
+ } else {
+ fpstate_init(&fpu->state);
+
+ /* Safe to do for stopped child tasks: */
+ fpu->fpstate_active = 1;
+ }
+}
+
+/*
+ * 'fpu__restore()' is called to copy FPU registers from
+ * the FPU fpstate to the live hw registers and to activate
+ * access to the hardware registers, so that FPU instructions
+ * can be used afterwards.
+ *
+ * Must be called with kernel preemption disabled (for example
+ * with local interrupts disabled, as it is in the case of
+ * do_device_not_available()).
+ */
+void fpu__restore(struct fpu *fpu)
+{
+ fpu__activate_curr(fpu);
+
+ /* Avoid __kernel_fpu_begin() right after fpregs_activate() */
+ kernel_fpu_disable();
+ fpregs_activate(fpu);
+ copy_kernel_to_fpregs(&fpu->state);
+ fpu->counter++;
+ kernel_fpu_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__restore);
+
+/*
+ * Drops current FPU state: deactivates the fpregs and
+ * the fpstate. NOTE: it still leaves previous contents
+ * in the fpregs in the eager-FPU case.
+ *
+ * This function can be used in cases where we know that
+ * a state-restore is coming: either an explicit one,
+ * or a reschedule.
+ */
+void fpu__drop(struct fpu *fpu)
+{
+ preempt_disable();
+ fpu->counter = 0;
+
+ if (fpu->fpregs_active) {
+ /* Ignore delayed exceptions from user space */
+ asm volatile("1: fwait\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b));
+ fpregs_deactivate(fpu);
+ }
+
+ fpu->fpstate_active = 0;
+
+ preempt_enable();
+}
+
+/*
+ * Clear FPU registers by setting them up from
+ * the init fpstate:
+ */
+static inline void copy_init_fpstate_to_fpregs(void)
+{
+ if (use_xsave())
+ copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+ else
+ copy_kernel_to_fxregs(&init_fpstate.fxsave);
+}
+
+/*
+ * Clear the FPU state back to init state.
+ *
+ * Called by sys_execve(), by the signal handler code and by various
+ * error paths.
+ */
+void fpu__clear(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
+
+ if (!use_eager_fpu()) {
+ /* FPU state will be reallocated lazily at the first use. */
+ fpu__drop(fpu);
+ } else {
+ if (!fpu->fpstate_active) {
+ fpu__activate_curr(fpu);
+ user_fpu_begin();
+ }
+ copy_init_fpstate_to_fpregs();
+ }
+}
+
+/*
+ * x87 math exception handling:
+ */
+
+static inline unsigned short get_fpu_cwd(struct fpu *fpu)
+{
+ if (cpu_has_fxsr) {
+ return fpu->state.fxsave.cwd;
+ } else {
+ return (unsigned short)fpu->state.fsave.cwd;
+ }
+}
+
+static inline unsigned short get_fpu_swd(struct fpu *fpu)
+{
+ if (cpu_has_fxsr) {
+ return fpu->state.fxsave.swd;
+ } else {
+ return (unsigned short)fpu->state.fsave.swd;
+ }
+}
+
+static inline unsigned short get_fpu_mxcsr(struct fpu *fpu)
+{
+ if (cpu_has_xmm) {
+ return fpu->state.fxsave.mxcsr;
+ } else {
+ return MXCSR_DEFAULT;
+ }
+}
+
+int fpu__exception_code(struct fpu *fpu, int trap_nr)
+{
+ int err;
+
+ if (trap_nr == X86_TRAP_MF) {
+ unsigned short cwd, swd;
+ /*
+ * (~cwd & swd) will mask out exceptions that are not set to unmasked
+ * status. 0x3f is the exception bits in these regs, 0x200 is the
+ * C1 reg you need in case of a stack fault, 0x040 is the stack
+ * fault bit. We should only be taking one exception at a time,
+ * so if this combination doesn't produce any single exception,
+ * then we have a bad program that isn't synchronizing its FPU usage
+ * and it will suffer the consequences since we won't be able to
+ * fully reproduce the context of the exception
+ */
+ cwd = get_fpu_cwd(fpu);
+ swd = get_fpu_swd(fpu);
+
+ err = swd & ~cwd;
+ } else {
+ /*
+ * The SIMD FPU exceptions are handled a little differently, as there
+ * is only a single status/control register. Thus, to determine which
+ * unmasked exception was caught we must mask the exception mask bits
+ * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+ */
+ unsigned short mxcsr = get_fpu_mxcsr(fpu);
+ err = ~(mxcsr >> 7) & mxcsr;
+ }
+
+ if (err & 0x001) { /* Invalid op */
+ /*
+ * swd & 0x240 == 0x040: Stack Underflow
+ * swd & 0x240 == 0x240: Stack Overflow
+ * User must clear the SF bit (0x40) if set
+ */
+ return FPE_FLTINV;
+ } else if (err & 0x004) { /* Divide by Zero */
+ return FPE_FLTDIV;
+ } else if (err & 0x008) { /* Overflow */
+ return FPE_FLTOVF;
+ } else if (err & 0x012) { /* Denormal, Underflow */
+ return FPE_FLTUND;
+ } else if (err & 0x020) { /* Precision */
+ return FPE_FLTRES;
+ }
+
+ /*
+ * If we're using IRQ 13, or supposedly even some trap
+ * X86_TRAP_MF implementations, it's possible
+ * we get a spurious trap, which is not an error.
+ */
+ return 0;
+}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
new file mode 100644
index 000000000000..fc878fee6a51
--- /dev/null
+++ b/arch/x86/kernel/fpu/init.c
@@ -0,0 +1,354 @@
+/*
+ * x86 FPU boot time init code:
+ */
+#include <asm/fpu/internal.h>
+#include <asm/tlbflush.h>
+
+/*
+ * Initialize the TS bit in CR0 according to the style of context-switches
+ * we are using:
+ */
+static void fpu__init_cpu_ctx_switch(void)
+{
+ if (!cpu_has_eager_fpu)
+ stts();
+ else
+ clts();
+}
+
+/*
+ * Initialize the registers found in all CPUs, CR0 and CR4:
+ */
+static void fpu__init_cpu_generic(void)
+{
+ unsigned long cr0;
+ unsigned long cr4_mask = 0;
+
+ if (cpu_has_fxsr)
+ cr4_mask |= X86_CR4_OSFXSR;
+ if (cpu_has_xmm)
+ cr4_mask |= X86_CR4_OSXMMEXCPT;
+ if (cr4_mask)
+ cr4_set_bits(cr4_mask);
+
+ cr0 = read_cr0();
+ cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+ if (!cpu_has_fpu)
+ cr0 |= X86_CR0_EM;
+ write_cr0(cr0);
+
+ /* Flush out any pending x87 state: */
+ asm volatile ("fninit");
+}
+
+/*
+ * Enable all supported FPU features. Called when a CPU is brought online:
+ */
+void fpu__init_cpu(void)
+{
+ fpu__init_cpu_generic();
+ fpu__init_cpu_xstate();
+ fpu__init_cpu_ctx_switch();
+}
+
+/*
+ * The earliest FPU detection code.
+ *
+ * Set the X86_FEATURE_FPU CPU-capability bit based on
+ * trying to execute an actual sequence of FPU instructions:
+ */
+static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+{
+ unsigned long cr0;
+ u16 fsw, fcw;
+
+ fsw = fcw = 0xffff;
+
+ cr0 = read_cr0();
+ cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
+ write_cr0(cr0);
+
+ asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+ : "+m" (fsw), "+m" (fcw));
+
+ if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+ set_cpu_cap(c, X86_FEATURE_FPU);
+ else
+ clear_cpu_cap(c, X86_FEATURE_FPU);
+
+#ifndef CONFIG_MATH_EMULATION
+ if (!cpu_has_fpu) {
+ pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
+ for (;;)
+ asm volatile("hlt");
+ }
+#endif
+}
+
+/*
+ * Boot time FPU feature detection code:
+ */
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+
+static void __init fpu__init_system_mxcsr(void)
+{
+ unsigned int mask = 0;
+
+ if (cpu_has_fxsr) {
+ struct fxregs_state fx_tmp __aligned(32) = { };
+
+ asm volatile("fxsave %0" : "+m" (fx_tmp));
+
+ mask = fx_tmp.mxcsr_mask;
+
+ /*
+ * If zero then use the default features mask,
+ * which has all features set, except the
+ * denormals-are-zero feature bit:
+ */
+ if (mask == 0)
+ mask = 0x0000ffbf;
+ }
+ mxcsr_feature_mask &= mask;
+}
+
+/*
+ * Once per bootup FPU initialization sequences that will run on most x86 CPUs:
+ */
+static void __init fpu__init_system_generic(void)
+{
+ /*
+ * Set up the legacy init FPU context. (xstate init might overwrite this
+ * with a more modern format, if the CPU supports it.)
+ */
+ fpstate_init_fxstate(&init_fpstate.fxsave);
+
+ fpu__init_system_mxcsr();
+}
+
+/*
+ * Size of the FPU context state. All tasks in the system use the
+ * same context size, regardless of what portion they use.
+ * This is inherent to the XSAVE architecture which puts all state
+ * components into a single, continuous memory block:
+ */
+unsigned int xstate_size;
+EXPORT_SYMBOL_GPL(xstate_size);
+
+/*
+ * Set up the xstate_size based on the legacy FPU context size.
+ *
+ * We set this up first, and later it will be overwritten by
+ * fpu__init_system_xstate() if the CPU knows about xstates.
+ */
+static void __init fpu__init_system_xstate_size_legacy(void)
+{
+ static int on_boot_cpu = 1;
+
+ WARN_ON_FPU(!on_boot_cpu);
+ on_boot_cpu = 0;
+
+ /*
+ * Note that xstate_size might be overwriten later during
+ * fpu__init_system_xstate().
+ */
+
+ if (!cpu_has_fpu) {
+ /*
+ * Disable xsave as we do not support it if i387
+ * emulation is enabled.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+ xstate_size = sizeof(struct swregs_state);
+ } else {
+ if (cpu_has_fxsr)
+ xstate_size = sizeof(struct fxregs_state);
+ else
+ xstate_size = sizeof(struct fregs_state);
+ }
+ /*
+ * Quirk: we don't yet handle the XSAVES* instructions
+ * correctly, as we don't correctly convert between
+ * standard and compacted format when interfacing
+ * with user-space - so disable it for now.
+ *
+ * The difference is small: with recent CPUs the
+ * compacted format is only marginally smaller than
+ * the standard FPU state format.
+ *
+ * ( This is easy to backport while we are fixing
+ * XSAVES* support. )
+ */
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+}
+
+/*
+ * FPU context switching strategies:
+ *
+ * Against popular belief, we don't do lazy FPU saves, due to the
+ * task migration complications it brings on SMP - we only do
+ * lazy FPU restores.
+ *
+ * 'lazy' is the traditional strategy, which is based on setting
+ * CR0::TS to 1 during context-switch (instead of doing a full
+ * restore of the FPU state), which causes the first FPU instruction
+ * after the context switch (whenever it is executed) to fault - at
+ * which point we lazily restore the FPU state into FPU registers.
+ *
+ * Tasks are of course under no obligation to execute FPU instructions,
+ * so it can easily happen that another context-switch occurs without
+ * a single FPU instruction being executed. If we eventually switch
+ * back to the original task (that still owns the FPU) then we have
+ * not only saved the restores along the way, but we also have the
+ * FPU ready to be used for the original task.
+ *
+ * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * state during every context switch, regardless of whether the task
+ * has used FPU instructions in that time slice or not. This is done
+ * because modern FPU context saving instructions are able to optimize
+ * state saving and restoration in hardware: they can detect both
+ * unused and untouched FPU state and optimize accordingly.
+ *
+ * [ Note that even in 'lazy' mode we might optimize context switches
+ * to use 'eager' restores, if we detect that a task is using the FPU
+ * frequently. See the fpu->counter logic in fpu/internal.h for that. ]
+ */
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+
+static int __init eager_fpu_setup(char *s)
+{
+ if (!strcmp(s, "on"))
+ eagerfpu = ENABLE;
+ else if (!strcmp(s, "off"))
+ eagerfpu = DISABLE;
+ else if (!strcmp(s, "auto"))
+ eagerfpu = AUTO;
+ return 1;
+}
+__setup("eagerfpu=", eager_fpu_setup);
+
+/*
+ * Pick the FPU context switching strategy:
+ */
+static void __init fpu__init_system_ctx_switch(void)
+{
+ static bool on_boot_cpu = 1;
+
+ WARN_ON_FPU(!on_boot_cpu);
+ on_boot_cpu = 0;
+
+ WARN_ON_FPU(current->thread.fpu.fpstate_active);
+ current_thread_info()->status = 0;
+
+ /* Auto enable eagerfpu for xsaveopt */
+ if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+ eagerfpu = ENABLE;
+
+ if (xfeatures_mask & XSTATE_EAGER) {
+ if (eagerfpu == DISABLE) {
+ pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
+ xfeatures_mask & XSTATE_EAGER);
+ xfeatures_mask &= ~XSTATE_EAGER;
+ } else {
+ eagerfpu = ENABLE;
+ }
+ }
+
+ if (eagerfpu == ENABLE)
+ setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+
+ printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy");
+}
+
+/*
+ * Called on the boot CPU once per system bootup, to set up the initial
+ * FPU state that is later cloned into all processes:
+ */
+void __init fpu__init_system(struct cpuinfo_x86 *c)
+{
+ fpu__init_system_early_generic(c);
+
+ /*
+ * The FPU has to be operational for some of the
+ * later FPU init activities:
+ */
+ fpu__init_cpu();
+
+ /*
+ * But don't leave CR0::TS set yet, as some of the FPU setup
+ * methods depend on being able to execute FPU instructions
+ * that will fault on a set TS, such as the FXSAVE in
+ * fpu__init_system_mxcsr().
+ */
+ clts();
+
+ fpu__init_system_generic();
+ fpu__init_system_xstate_size_legacy();
+ fpu__init_system_xstate();
+
+ fpu__init_system_ctx_switch();
+}
+
+/*
+ * Boot parameter to turn off FPU support and fall back to math-emu:
+ */
+static int __init no_387(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_FPU);
+ return 1;
+}
+__setup("no387", no_387);
+
+/*
+ * Disable all xstate CPU features:
+ */
+static int __init x86_noxsave_setup(char *s)
+{
+ if (strlen(s))
+ return 0;
+
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+ setup_clear_cpu_cap(X86_FEATURE_AVX);
+ setup_clear_cpu_cap(X86_FEATURE_AVX2);
+
+ return 1;
+}
+__setup("noxsave", x86_noxsave_setup);
+
+/*
+ * Disable the XSAVEOPT instruction specifically:
+ */
+static int __init x86_noxsaveopt_setup(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+ return 1;
+}
+__setup("noxsaveopt", x86_noxsaveopt_setup);
+
+/*
+ * Disable the XSAVES instruction:
+ */
+static int __init x86_noxsaves_setup(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+
+ return 1;
+}
+__setup("noxsaves", x86_noxsaves_setup);
+
+/*
+ * Disable FX save/restore and SSE support:
+ */
+static int __init x86_nofxsr_setup(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_FXSR);
+ setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
+ setup_clear_cpu_cap(X86_FEATURE_XMM);
+
+ return 1;
+}
+__setup("nofxsr", x86_nofxsr_setup);
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
new file mode 100644
index 000000000000..dc60810c1c74
--- /dev/null
+++ b/arch/x86/kernel/fpu/regset.c
@@ -0,0 +1,356 @@
+/*
+ * FPU register's regset abstraction, for ptrace, core dumps, etc.
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+/*
+ * The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
+ * as the "regset->n" for the xstate regset will be updated based on the feature
+ * capabilites supported by the xsave.
+ */
+int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+ struct fpu *target_fpu = &target->thread.fpu;
+
+ return target_fpu->fpstate_active ? regset->n : 0;
+}
+
+int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+ struct fpu *target_fpu = &target->thread.fpu;
+
+ return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0;
+}
+
+int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+
+ if (!cpu_has_fxsr)
+ return -ENODEV;
+
+ fpu__activate_fpstate_read(fpu);
+ fpstate_sanitize_xstate(fpu);
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &fpu->state.fxsave, 0, -1);
+}
+
+int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ int ret;
+
+ if (!cpu_has_fxsr)
+ return -ENODEV;
+
+ fpu__activate_fpstate_write(fpu);
+ fpstate_sanitize_xstate(fpu);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &fpu->state.fxsave, 0, -1);
+
+ /*
+ * mxcsr reserved bits must be masked to zero for security reasons.
+ */
+ fpu->state.fxsave.mxcsr &= mxcsr_feature_mask;
+
+ /*
+ * update the header bits in the xsave header, indicating the
+ * presence of FP and SSE state.
+ */
+ if (cpu_has_xsave)
+ fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE;
+
+ return ret;
+}
+
+int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct xregs_state *xsave;
+ int ret;
+
+ if (!cpu_has_xsave)
+ return -ENODEV;
+
+ fpu__activate_fpstate_read(fpu);
+
+ xsave = &fpu->state.xsave;
+
+ /*
+ * Copy the 48bytes defined by the software first into the xstate
+ * memory layout in the thread struct, so that we can copy the entire
+ * xstateregs to the user using one user_regset_copyout().
+ */
+ memcpy(&xsave->i387.sw_reserved,
+ xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
+ /*
+ * Copy the xstate memory layout.
+ */
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+ return ret;
+}
+
+int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct xregs_state *xsave;
+ int ret;
+
+ if (!cpu_has_xsave)
+ return -ENODEV;
+
+ fpu__activate_fpstate_write(fpu);
+
+ xsave = &fpu->state.xsave;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+ /*
+ * mxcsr reserved bits must be masked to zero for security reasons.
+ */
+ xsave->i387.mxcsr &= mxcsr_feature_mask;
+ xsave->header.xfeatures &= xfeatures_mask;
+ /*
+ * These bits must be zero.
+ */
+ memset(&xsave->header.reserved, 0, 48);
+
+ return ret;
+}
+
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
+{
+ unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+ /* Transform each pair of bits into 01 (valid) or 00 (empty) */
+ tmp = ~twd;
+ tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+ /* and move the valid bits to the lower byte. */
+ tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+ tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+ tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+
+ return tmp;
+}
+
+#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16)
+#define FP_EXP_TAG_VALID 0
+#define FP_EXP_TAG_ZERO 1
+#define FP_EXP_TAG_SPECIAL 2
+#define FP_EXP_TAG_EMPTY 3
+
+static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave)
+{
+ struct _fpxreg *st;
+ u32 tos = (fxsave->swd >> 11) & 7;
+ u32 twd = (unsigned long) fxsave->twd;
+ u32 tag;
+ u32 ret = 0xffff0000u;
+ int i;
+
+ for (i = 0; i < 8; i++, twd >>= 1) {
+ if (twd & 0x1) {
+ st = FPREG_ADDR(fxsave, (i - tos) & 7);
+
+ switch (st->exponent & 0x7fff) {
+ case 0x7fff:
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ case 0x0000:
+ if (!st->significand[0] &&
+ !st->significand[1] &&
+ !st->significand[2] &&
+ !st->significand[3])
+ tag = FP_EXP_TAG_ZERO;
+ else
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ default:
+ if (st->significand[3] & 0x8000)
+ tag = FP_EXP_TAG_VALID;
+ else
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ }
+ } else {
+ tag = FP_EXP_TAG_EMPTY;
+ }
+ ret |= tag << (2 * i);
+ }
+ return ret;
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+void
+convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
+{
+ struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+ struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
+ struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
+ int i;
+
+ env->cwd = fxsave->cwd | 0xffff0000u;
+ env->swd = fxsave->swd | 0xffff0000u;
+ env->twd = twd_fxsr_to_i387(fxsave);
+
+#ifdef CONFIG_X86_64
+ env->fip = fxsave->rip;
+ env->foo = fxsave->rdp;
+ /*
+ * should be actually ds/cs at fpu exception time, but
+ * that information is not available in 64bit mode.
+ */
+ env->fcs = task_pt_regs(tsk)->cs;
+ if (tsk == current) {
+ savesegment(ds, env->fos);
+ } else {
+ env->fos = tsk->thread.ds;
+ }
+ env->fos |= 0xffff0000;
+#else
+ env->fip = fxsave->fip;
+ env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
+ env->foo = fxsave->foo;
+ env->fos = fxsave->fos;
+#endif
+
+ for (i = 0; i < 8; ++i)
+ memcpy(&to[i], &from[i], sizeof(to[0]));
+}
+
+void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env)
+
+{
+ struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+ struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
+ struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
+ int i;
+
+ fxsave->cwd = env->cwd;
+ fxsave->swd = env->swd;
+ fxsave->twd = twd_i387_to_fxsr(env->twd);
+ fxsave->fop = (u16) ((u32) env->fcs >> 16);
+#ifdef CONFIG_X86_64
+ fxsave->rip = env->fip;
+ fxsave->rdp = env->foo;
+ /* cs and ds ignored */
+#else
+ fxsave->fip = env->fip;
+ fxsave->fcs = (env->fcs & 0xffff);
+ fxsave->foo = env->foo;
+ fxsave->fos = env->fos;
+#endif
+
+ for (i = 0; i < 8; ++i)
+ memcpy(&to[i], &from[i], sizeof(from[0]));
+}
+
+int fpregs_get(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct user_i387_ia32_struct env;
+
+ fpu__activate_fpstate_read(fpu);
+
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
+
+ if (!cpu_has_fxsr)
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &fpu->state.fsave, 0,
+ -1);
+
+ fpstate_sanitize_xstate(fpu);
+
+ if (kbuf && pos == 0 && count == sizeof(env)) {
+ convert_from_fxsr(kbuf, target);
+ return 0;
+ }
+
+ convert_from_fxsr(&env, target);
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+}
+
+int fpregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct user_i387_ia32_struct env;
+ int ret;
+
+ fpu__activate_fpstate_write(fpu);
+ fpstate_sanitize_xstate(fpu);
+
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
+
+ if (!cpu_has_fxsr)
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &fpu->state.fsave, 0,
+ -1);
+
+ if (pos > 0 || count < sizeof(env))
+ convert_from_fxsr(&env, target);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+ if (!ret)
+ convert_to_fxsr(target, &env);
+
+ /*
+ * update the header bit in the xsave header, indicating the
+ * presence of FP.
+ */
+ if (cpu_has_xsave)
+ fpu->state.xsave.header.xfeatures |= XSTATE_FP;
+ return ret;
+}
+
+/*
+ * FPU state for core dumps.
+ * This is only used for a.out dumps now.
+ * It is declared generically using elf_fpregset_t (which is
+ * struct user_i387_struct) but is in fact only used for 32-bit
+ * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
+ */
+int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
+{
+ struct task_struct *tsk = current;
+ struct fpu *fpu = &tsk->thread.fpu;
+ int fpvalid;
+
+ fpvalid = fpu->fpstate_active;
+ if (fpvalid)
+ fpvalid = !fpregs_get(tsk, NULL,
+ 0, sizeof(struct user_i387_ia32_struct),
+ ufpu, NULL);
+
+ return fpvalid;
+}
+EXPORT_SYMBOL(dump_fpu);
+
+#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
new file mode 100644
index 000000000000..50ec9af1bd51
--- /dev/null
+++ b/arch/x86/kernel/fpu/signal.c
@@ -0,0 +1,404 @@
+/*
+ * FPU signal frame handling routines.
+ */
+
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/sigframe.h>
+
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
+
+/*
+ * Check for the presence of extended state information in the
+ * user fpstate pointer in the sigcontext.
+ */
+static inline int check_for_xstate(struct fxregs_state __user *buf,
+ void __user *fpstate,
+ struct _fpx_sw_bytes *fx_sw)
+{
+ int min_xstate_size = sizeof(struct fxregs_state) +
+ sizeof(struct xstate_header);
+ unsigned int magic2;
+
+ if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+ return -1;
+
+ /* Check for the first magic field and other error scenarios. */
+ if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+ fx_sw->xstate_size < min_xstate_size ||
+ fx_sw->xstate_size > xstate_size ||
+ fx_sw->xstate_size > fx_sw->extended_size)
+ return -1;
+
+ /*
+ * Check for the presence of second magic word at the end of memory
+ * layout. This detects the case where the user just copied the legacy
+ * fpstate layout with out copying the extended state information
+ * in the memory layout.
+ */
+ if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+ || magic2 != FP_XSTATE_MAGIC2)
+ return -1;
+
+ return 0;
+}
+
+/*
+ * Signal frame handlers.
+ */
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
+{
+ if (use_fxsr()) {
+ struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+ struct user_i387_ia32_struct env;
+ struct _fpstate_ia32 __user *fp = buf;
+
+ convert_from_fxsr(&env, tsk);
+
+ if (__copy_to_user(buf, &env, sizeof(env)) ||
+ __put_user(xsave->i387.swd, &fp->status) ||
+ __put_user(X86_FXSR_MAGIC, &fp->magic))
+ return -1;
+ } else {
+ struct fregs_state __user *fp = buf;
+ u32 swd;
+ if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
+ return -1;
+ }
+
+ return 0;
+}
+
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
+{
+ struct xregs_state __user *x = buf;
+ struct _fpx_sw_bytes *sw_bytes;
+ u32 xfeatures;
+ int err;
+
+ /* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+ sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+ err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
+
+ if (!use_xsave())
+ return err;
+
+ err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
+
+ /*
+ * Read the xfeatures which we copied (directly from the cpu or
+ * from the state in task struct) to the user buffers.
+ */
+ err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+ /*
+ * For legacy compatible, we always set FP/SSE bits in the bit
+ * vector while saving the state to the user context. This will
+ * enable us capturing any changes(during sigreturn) to
+ * the FP/SSE bits by the legacy applications which don't touch
+ * xfeatures in the xsave header.
+ *
+ * xsave aware apps can change the xfeatures in the xsave
+ * header as well as change any contents in the memory layout.
+ * xrestore as part of sigreturn will capture all the changes.
+ */
+ xfeatures |= XSTATE_FPSSE;
+
+ err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+ return err;
+}
+
+static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
+{
+ int err;
+
+ if (use_xsave())
+ err = copy_xregs_to_user(buf);
+ else if (use_fxsr())
+ err = copy_fxregs_to_user((struct fxregs_state __user *) buf);
+ else
+ err = copy_fregs_to_user((struct fregs_state __user *) buf);
+
+ if (unlikely(err) && __clear_user(buf, xstate_size))
+ err = -EFAULT;
+ return err;
+}
+
+/*
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ * state is copied.
+ * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ * buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ * buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
+ */
+int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+{
+ struct xregs_state *xsave = &current->thread.fpu.state.xsave;
+ struct task_struct *tsk = current;
+ int ia32_fxstate = (buf != buf_fx);
+
+ ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+ config_enabled(CONFIG_IA32_EMULATION));
+
+ if (!access_ok(VERIFY_WRITE, buf, size))
+ return -EACCES;
+
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return fpregs_soft_get(current, NULL, 0,
+ sizeof(struct user_i387_ia32_struct), NULL,
+ (struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+ if (fpregs_active()) {
+ /* Save the live register state to the user directly. */
+ if (copy_fpregs_to_sigframe(buf_fx))
+ return -1;
+ /* Update the thread's fxstate to save the fsave header. */
+ if (ia32_fxstate)
+ copy_fxregs_to_kernel(&tsk->thread.fpu);
+ } else {
+ fpstate_sanitize_xstate(&tsk->thread.fpu);
+ if (__copy_to_user(buf_fx, xsave, xstate_size))
+ return -1;
+ }
+
+ /* Save the fsave header for the 32-bit frames. */
+ if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+ return -1;
+
+ if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+ return -1;
+
+ return 0;
+}
+
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+ struct user_i387_ia32_struct *ia32_env,
+ u64 xfeatures, int fx_only)
+{
+ struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+ struct xstate_header *header = &xsave->header;
+
+ if (use_xsave()) {
+ /* These bits must be zero. */
+ memset(header->reserved, 0, 48);
+
+ /*
+ * Init the state that is not present in the memory
+ * layout and not enabled by the OS.
+ */
+ if (fx_only)
+ header->xfeatures = XSTATE_FPSSE;
+ else
+ header->xfeatures &= (xfeatures_mask & xfeatures);
+ }
+
+ if (use_fxsr()) {
+ /*
+ * mscsr reserved bits must be masked to zero for security
+ * reasons.
+ */
+ xsave->i387.mxcsr &= mxcsr_feature_mask;
+
+ convert_to_fxsr(tsk, ia32_env);
+ }
+}
+
+/*
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
+ */
+static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
+{
+ if (use_xsave()) {
+ if ((unsigned long)buf % 64 || fx_only) {
+ u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE;
+ copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+ return copy_user_to_fxregs(buf);
+ } else {
+ u64 init_bv = xfeatures_mask & ~xbv;
+ if (unlikely(init_bv))
+ copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+ return copy_user_to_xregs(buf, xbv);
+ }
+ } else if (use_fxsr()) {
+ return copy_user_to_fxregs(buf);
+ } else
+ return copy_user_to_fregs(buf);
+}
+
+static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
+{
+ int ia32_fxstate = (buf != buf_fx);
+ struct task_struct *tsk = current;
+ struct fpu *fpu = &tsk->thread.fpu;
+ int state_size = xstate_size;
+ u64 xfeatures = 0;
+ int fx_only = 0;
+
+ ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+ config_enabled(CONFIG_IA32_EMULATION));
+
+ if (!buf) {
+ fpu__clear(fpu);
+ return 0;
+ }
+
+ if (!access_ok(VERIFY_READ, buf, size))
+ return -EACCES;
+
+ fpu__activate_curr(fpu);
+
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return fpregs_soft_set(current, NULL,
+ 0, sizeof(struct user_i387_ia32_struct),
+ NULL, buf) != 0;
+
+ if (use_xsave()) {
+ struct _fpx_sw_bytes fx_sw_user;
+ if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+ /*
+ * Couldn't find the extended state information in the
+ * memory layout. Restore just the FP/SSE and init all
+ * the other extended state.
+ */
+ state_size = sizeof(struct fxregs_state);
+ fx_only = 1;
+ } else {
+ state_size = fx_sw_user.xstate_size;
+ xfeatures = fx_sw_user.xfeatures;
+ }
+ }
+
+ if (ia32_fxstate) {
+ /*
+ * For 32-bit frames with fxstate, copy the user state to the
+ * thread's fpu state, reconstruct fxstate from the fsave
+ * header. Sanitize the copied state etc.
+ */
+ struct fpu *fpu = &tsk->thread.fpu;
+ struct user_i387_ia32_struct env;
+ int err = 0;
+
+ /*
+ * Drop the current fpu which clears fpu->fpstate_active. This ensures
+ * that any context-switch during the copy of the new state,
+ * avoids the intermediate state from getting restored/saved.
+ * Thus avoiding the new restored state from getting corrupted.
+ * We will be ready to restore/save the state only after
+ * fpu->fpstate_active is again set.
+ */
+ fpu__drop(fpu);
+
+ if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) ||
+ __copy_from_user(&env, buf, sizeof(env))) {
+ fpstate_init(&fpu->state);
+ err = -1;
+ } else {
+ sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
+ }
+
+ fpu->fpstate_active = 1;
+ if (use_eager_fpu()) {
+ preempt_disable();
+ fpu__restore(fpu);
+ preempt_enable();
+ }
+
+ return err;
+ } else {
+ /*
+ * For 64-bit frames and 32-bit fsave frames, restore the user
+ * state to the registers directly (with exceptions handled).
+ */
+ user_fpu_begin();
+ if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
+ fpu__clear(fpu);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static inline int xstate_sigframe_size(void)
+{
+ return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+/*
+ * Restore FPU state from a sigframe:
+ */
+int fpu__restore_sig(void __user *buf, int ia32_frame)
+{
+ void __user *buf_fx = buf;
+ int size = xstate_sigframe_size();
+
+ if (ia32_frame && use_fxsr()) {
+ buf_fx = buf + sizeof(struct fregs_state);
+ size += sizeof(struct fregs_state);
+ }
+
+ return __fpu__restore_sig(buf, buf_fx, size);
+}
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+ unsigned long *buf_fx, unsigned long *size)
+{
+ unsigned long frame_size = xstate_sigframe_size();
+
+ *buf_fx = sp = round_down(sp - frame_size, 64);
+ if (ia32_frame && use_fxsr()) {
+ frame_size += sizeof(struct fregs_state);
+ sp -= sizeof(struct fregs_state);
+ }
+
+ *size = frame_size;
+
+ return sp;
+}
+/*
+ * Prepare the SW reserved portion of the fxsave memory layout, indicating
+ * the presence of the extended state information in the memory layout
+ * pointed by the fpstate pointer in the sigcontext.
+ * This will be saved when ever the FP and extended state context is
+ * saved on the user stack during the signal handler delivery to the user.
+ */
+void fpu__init_prepare_fx_sw_frame(void)
+{
+ int fsave_header_size = sizeof(struct fregs_state);
+ int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
+
+ if (config_enabled(CONFIG_X86_32))
+ size += fsave_header_size;
+
+ fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
+ fx_sw_reserved.extended_size = size;
+ fx_sw_reserved.xfeatures = xfeatures_mask;
+ fx_sw_reserved.xstate_size = xstate_size;
+
+ if (config_enabled(CONFIG_IA32_EMULATION)) {
+ fx_sw_reserved_ia32 = fx_sw_reserved;
+ fx_sw_reserved_ia32.extended_size += fsave_header_size;
+ }
+}
+
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
new file mode 100644
index 000000000000..62fc001c7846
--- /dev/null
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -0,0 +1,461 @@
+/*
+ * xsave/xrstor support.
+ *
+ * Author: Suresh Siddha <suresh.b.siddha@intel.com>
+ */
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/api.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/tlbflush.h>
+
+static const char *xfeature_names[] =
+{
+ "x87 floating point registers" ,
+ "SSE registers" ,
+ "AVX registers" ,
+ "MPX bounds registers" ,
+ "MPX CSR" ,
+ "AVX-512 opmask" ,
+ "AVX-512 Hi256" ,
+ "AVX-512 ZMM_Hi256" ,
+ "unknown xstate feature" ,
+};
+
+/*
+ * Mask of xstate features supported by the CPU and the kernel:
+ */
+u64 xfeatures_mask __read_mostly;
+
+static unsigned int xstate_offsets[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_sizes[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
+
+/* The number of supported xfeatures in xfeatures_mask: */
+static unsigned int xfeatures_nr;
+
+/*
+ * Return whether the system supports a given xfeature.
+ *
+ * Also return the name of the (most advanced) feature that the caller requested:
+ */
+int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
+{
+ u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+
+ if (unlikely(feature_name)) {
+ long xfeature_idx, max_idx;
+ u64 xfeatures_print;
+ /*
+ * So we use FLS here to be able to print the most advanced
+ * feature that was requested but is missing. So if a driver
+ * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the
+ * missing AVX feature - this is the most informative message
+ * to users:
+ */
+ if (xfeatures_missing)
+ xfeatures_print = xfeatures_missing;
+ else
+ xfeatures_print = xfeatures_needed;
+
+ xfeature_idx = fls64(xfeatures_print)-1;
+ max_idx = ARRAY_SIZE(xfeature_names)-1;
+ xfeature_idx = min(xfeature_idx, max_idx);
+
+ *feature_name = xfeature_names[xfeature_idx];
+ }
+
+ if (xfeatures_missing)
+ return 0;
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
+
+/*
+ * When executing XSAVEOPT (or other optimized XSAVE instructions), if
+ * a processor implementation detects that an FPU state component is still
+ * (or is again) in its initialized state, it may clear the corresponding
+ * bit in the header.xfeatures field, and can skip the writeout of registers
+ * to the corresponding memory layout.
+ *
+ * This means that when the bit is zero, the state component might still contain
+ * some previous - non-initialized register state.
+ *
+ * Before writing xstate information to user-space we sanitize those components,
+ * to always ensure that the memory layout of a feature will be in the init state
+ * if the corresponding header bit is zero. This is to ensure that user-space doesn't
+ * see some stale state in the memory layout during signal handling, debugging etc.
+ */
+void fpstate_sanitize_xstate(struct fpu *fpu)
+{
+ struct fxregs_state *fx = &fpu->state.fxsave;
+ int feature_bit;
+ u64 xfeatures;
+
+ if (!use_xsaveopt())
+ return;
+
+ xfeatures = fpu->state.xsave.header.xfeatures;
+
+ /*
+ * None of the feature bits are in init state. So nothing else
+ * to do for us, as the memory layout is up to date.
+ */
+ if ((xfeatures & xfeatures_mask) == xfeatures_mask)
+ return;
+
+ /*
+ * FP is in init state
+ */
+ if (!(xfeatures & XSTATE_FP)) {
+ fx->cwd = 0x37f;
+ fx->swd = 0;
+ fx->twd = 0;
+ fx->fop = 0;
+ fx->rip = 0;
+ fx->rdp = 0;
+ memset(&fx->st_space[0], 0, 128);
+ }
+
+ /*
+ * SSE is in init state
+ */
+ if (!(xfeatures & XSTATE_SSE))
+ memset(&fx->xmm_space[0], 0, 256);
+
+ /*
+ * First two features are FPU and SSE, which above we handled
+ * in a special way already:
+ */
+ feature_bit = 0x2;
+ xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+
+ /*
+ * Update all the remaining memory layouts according to their
+ * standard xstate layout, if their header bit is in the init
+ * state:
+ */
+ while (xfeatures) {
+ if (xfeatures & 0x1) {
+ int offset = xstate_offsets[feature_bit];
+ int size = xstate_sizes[feature_bit];
+
+ memcpy((void *)fx + offset,
+ (void *)&init_fpstate.xsave + offset,
+ size);
+ }
+
+ xfeatures >>= 1;
+ feature_bit++;
+ }
+}
+
+/*
+ * Enable the extended processor state save/restore feature.
+ * Called once per CPU onlining.
+ */
+void fpu__init_cpu_xstate(void)
+{
+ if (!cpu_has_xsave || !xfeatures_mask)
+ return;
+
+ cr4_set_bits(X86_CR4_OSXSAVE);
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Record the offsets and sizes of various xstates contained
+ * in the XSAVE state memory layout.
+ *
+ * ( Note that certain features might be non-present, for them
+ * we'll have 0 offset and 0 size. )
+ */
+static void __init setup_xstate_features(void)
+{
+ u32 eax, ebx, ecx, edx, leaf;
+
+ xfeatures_nr = fls64(xfeatures_mask);
+
+ for (leaf = 2; leaf < xfeatures_nr; leaf++) {
+ cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
+
+ xstate_offsets[leaf] = ebx;
+ xstate_sizes[leaf] = eax;
+
+ printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax);
+ }
+}
+
+static void __init print_xstate_feature(u64 xstate_mask)
+{
+ const char *feature_name;
+
+ if (cpu_has_xfeatures(xstate_mask, &feature_name))
+ pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name);
+}
+
+/*
+ * Print out all the supported xstate features:
+ */
+static void __init print_xstate_features(void)
+{
+ print_xstate_feature(XSTATE_FP);
+ print_xstate_feature(XSTATE_SSE);
+ print_xstate_feature(XSTATE_YMM);
+ print_xstate_feature(XSTATE_BNDREGS);
+ print_xstate_feature(XSTATE_BNDCSR);
+ print_xstate_feature(XSTATE_OPMASK);
+ print_xstate_feature(XSTATE_ZMM_Hi256);
+ print_xstate_feature(XSTATE_Hi16_ZMM);
+}
+
+/*
+ * This function sets up offsets and sizes of all extended states in
+ * xsave area. This supports both standard format and compacted format
+ * of the xsave aread.
+ */
+static void __init setup_xstate_comp(void)
+{
+ unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8];
+ int i;
+
+ /*
+ * The FP xstates and SSE xstates are legacy states. They are always
+ * in the fixed offsets in the xsave area in either compacted form
+ * or standard form.
+ */
+ xstate_comp_offsets[0] = 0;
+ xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
+
+ if (!cpu_has_xsaves) {
+ for (i = 2; i < xfeatures_nr; i++) {
+ if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+ xstate_comp_offsets[i] = xstate_offsets[i];
+ xstate_comp_sizes[i] = xstate_sizes[i];
+ }
+ }
+ return;
+ }
+
+ xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+ for (i = 2; i < xfeatures_nr; i++) {
+ if (test_bit(i, (unsigned long *)&xfeatures_mask))
+ xstate_comp_sizes[i] = xstate_sizes[i];
+ else
+ xstate_comp_sizes[i] = 0;
+
+ if (i > 2)
+ xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
+ + xstate_comp_sizes[i-1];
+
+ }
+}
+
+/*
+ * setup the xstate image representing the init state
+ */
+static void __init setup_init_fpu_buf(void)
+{
+ static int on_boot_cpu = 1;
+
+ WARN_ON_FPU(!on_boot_cpu);
+ on_boot_cpu = 0;
+
+ if (!cpu_has_xsave)
+ return;
+
+ setup_xstate_features();
+ print_xstate_features();
+
+ if (cpu_has_xsaves) {
+ init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
+ init_fpstate.xsave.header.xfeatures = xfeatures_mask;
+ }
+
+ /*
+ * Init all the features state with header_bv being 0x0
+ */
+ copy_kernel_to_xregs_booting(&init_fpstate.xsave);
+
+ /*
+ * Dump the init state again. This is to identify the init state
+ * of any feature which is not represented by all zero's.
+ */
+ copy_xregs_to_kernel_booting(&init_fpstate.xsave);
+}
+
+/*
+ * Calculate total size of enabled xstates in XCR0/xfeatures_mask.
+ */
+static void __init init_xstate_size(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ int i;
+
+ if (!cpu_has_xsaves) {
+ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+ xstate_size = ebx;
+ return;
+ }
+
+ xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+ for (i = 2; i < 64; i++) {
+ if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+ cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+ xstate_size += eax;
+ }
+ }
+}
+
+/*
+ * Enable and initialize the xsave feature.
+ * Called once per system bootup.
+ */
+void __init fpu__init_system_xstate(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ static int on_boot_cpu = 1;
+
+ WARN_ON_FPU(!on_boot_cpu);
+ on_boot_cpu = 0;
+
+ if (!cpu_has_xsave) {
+ pr_info("x86/fpu: Legacy x87 FPU detected.\n");
+ return;
+ }
+
+ if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
+ WARN_ON_FPU(1);
+ return;
+ }
+
+ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+ xfeatures_mask = eax + ((u64)edx << 32);
+
+ if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
+ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+ BUG();
+ }
+
+ /* Support only the state known to the OS: */
+ xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+
+ /* Enable xstate instructions to be able to continue with initialization: */
+ fpu__init_cpu_xstate();
+
+ /* Recompute the context size for enabled features: */
+ init_xstate_size();
+
+ update_regset_xstate_info(xstate_size, xfeatures_mask);
+ fpu__init_prepare_fx_sw_frame();
+ setup_init_fpu_buf();
+ setup_xstate_comp();
+
+ pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is 0x%x bytes, using '%s' format.\n",
+ xfeatures_mask,
+ xstate_size,
+ cpu_has_xsaves ? "compacted" : "standard");
+}
+
+/*
+ * Restore minimal FPU state after suspend:
+ */
+void fpu__resume_cpu(void)
+{
+ /*
+ * Restore XCR0 on xsave capable CPUs:
+ */
+ if (cpu_has_xsave)
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Given the xsave area and a state inside, this function returns the
+ * address of the state.
+ *
+ * This is the API that is called to get xstate address in either
+ * standard format or compacted format of xsave area.
+ *
+ * Note that if there is no data for the field in the xsave buffer
+ * this will return NULL.
+ *
+ * Inputs:
+ * xstate: the thread's storage area for all FPU data
+ * xstate_feature: state which is defined in xsave.h (e.g.
+ * XSTATE_FP, XSTATE_SSE, etc...)
+ * Output:
+ * address of the state in the xsave area, or NULL if the
+ * field is not present in the xsave buffer.
+ */
+void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
+{
+ int feature_nr = fls64(xstate_feature) - 1;
+ /*
+ * Do we even *have* xsave state?
+ */
+ if (!boot_cpu_has(X86_FEATURE_XSAVE))
+ return NULL;
+
+ xsave = &current->thread.fpu.state.xsave;
+ /*
+ * We should not ever be requesting features that we
+ * have not enabled. Remember that pcntxt_mask is
+ * what we write to the XCR0 register.
+ */
+ WARN_ONCE(!(xfeatures_mask & xstate_feature),
+ "get of unsupported state");
+ /*
+ * This assumes the last 'xsave*' instruction to
+ * have requested that 'xstate_feature' be saved.
+ * If it did not, we might be seeing and old value
+ * of the field in the buffer.
+ *
+ * This can happen because the last 'xsave' did not
+ * request that this feature be saved (unlikely)
+ * or because the "init optimization" caused it
+ * to not be saved.
+ */
+ if (!(xsave->header.xfeatures & xstate_feature))
+ return NULL;
+
+ return (void *)xsave + xstate_comp_offsets[feature_nr];
+}
+EXPORT_SYMBOL_GPL(get_xsave_addr);
+
+/*
+ * This wraps up the common operations that need to occur when retrieving
+ * data from xsave state. It first ensures that the current task was
+ * using the FPU and retrieves the data in to a buffer. It then calculates
+ * the offset of the requested field in the buffer.
+ *
+ * This function is safe to call whether the FPU is in use or not.
+ *
+ * Note that this only works on the current task.
+ *
+ * Inputs:
+ * @xsave_state: state which is defined in xsave.h (e.g. XSTATE_FP,
+ * XSTATE_SSE, etc...)
+ * Output:
+ * address of the state in the xsave area or NULL if the state
+ * is not present or is in its 'init state'.
+ */
+const void *get_xsave_field_ptr(int xsave_state)
+{
+ struct fpu *fpu = &current->thread.fpu;
+
+ if (!fpu->fpstate_active)
+ return NULL;
+ /*
+ * fpu__save() takes the CPU's xstate registers
+ * and saves them off to the 'fpu memory buffer.
+ */
+ fpu__save(fpu);
+
+ return get_xsave_addr(&fpu->state.xsave, xsave_state);
+}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2b55ee6db053..5a4668136e98 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -167,7 +167,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
clear_bss();
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
- set_intr_gate(i, early_idt_handlers[i]);
+ set_intr_gate(i, early_idt_handler_array[i]);
load_idt((const struct desc_ptr *)&idt_descr);
copy_bootdata(__va(real_mode_data));
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index d031bad9e07e..0e2d96ffd158 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -62,9 +62,16 @@
#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
#endif
-/* Number of possible pages in the lowmem region */
-LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
-
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
+
/* Enough space to fit pagetables for the low memory linear map */
MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
@@ -478,21 +485,22 @@ is486:
__INIT
setup_once:
/*
- * Set up a idt with 256 entries pointing to ignore_int,
- * interrupt gates. It doesn't actually load idt - that needs
- * to be done on each CPU. Interrupts are enabled elsewhere,
- * when we can be relatively sure everything is ok.
+ * Set up a idt with 256 interrupt gates that push zero if there
+ * is no error code and then jump to early_idt_handler_common.
+ * It doesn't actually load the idt - that needs to be done on
+ * each CPU. Interrupts are enabled elsewhere, when we can be
+ * relatively sure everything is ok.
*/
movl $idt_table,%edi
- movl $early_idt_handlers,%eax
+ movl $early_idt_handler_array,%eax
movl $NUM_EXCEPTION_VECTORS,%ecx
1:
movl %eax,(%edi)
movl %eax,4(%edi)
/* interrupt gate, dpl=0, present */
movl $(0x8E000000 + __KERNEL_CS),2(%edi)
- addl $9,%eax
+ addl $EARLY_IDT_HANDLER_SIZE,%eax
addl $8,%edi
loop 1b
@@ -524,30 +532,32 @@ setup_once:
andl $0,setup_once_ref /* Once is enough, thanks */
ret
-ENTRY(early_idt_handlers)
+ENTRY(early_idt_handler_array)
# 36(%esp) %eflags
# 32(%esp) %cs
# 28(%esp) %eip
# 24(%rsp) error code
i = 0
.rept NUM_EXCEPTION_VECTORS
- .if (EXCEPTION_ERRCODE_MASK >> i) & 1
- ASM_NOP2
- .else
+ .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
pushl $0 # Dummy error code, to make stack frame uniform
.endif
pushl $i # 20(%esp) Vector number
- jmp early_idt_handler
+ jmp early_idt_handler_common
i = i + 1
+ .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
.endr
-ENDPROC(early_idt_handlers)
+ENDPROC(early_idt_handler_array)
- /* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+ /*
+ * The stack is the hardware frame, an error code or zero, and the
+ * vector number.
+ */
cld
cmpl $2,(%esp) # X86_TRAP_NMI
- je is_nmi # Ignore NMI
+ je .Lis_nmi # Ignore NMI
cmpl $2,%ss:early_recursion_flag
je hlt_loop
@@ -600,10 +610,10 @@ ex_entry:
pop %ecx
pop %eax
decl %ss:early_recursion_flag
-is_nmi:
+.Lis_nmi:
addl $8,%esp /* drop vector number and error code */
iret
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
/* This is the default interrupt "handler" :-) */
ALIGN
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index ae6588b301c2..e5c27f729a38 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -321,30 +321,32 @@ bad_address:
jmp bad_address
__INIT
- .globl early_idt_handlers
-early_idt_handlers:
+ENTRY(early_idt_handler_array)
# 104(%rsp) %rflags
# 96(%rsp) %cs
# 88(%rsp) %rip
# 80(%rsp) error code
i = 0
.rept NUM_EXCEPTION_VECTORS
- .if (EXCEPTION_ERRCODE_MASK >> i) & 1
- ASM_NOP2
- .else
+ .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
pushq $0 # Dummy error code, to make stack frame uniform
.endif
pushq $i # 72(%rsp) Vector number
- jmp early_idt_handler
+ jmp early_idt_handler_common
i = i + 1
+ .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
.endr
+ENDPROC(early_idt_handler_array)
-/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+ /*
+ * The stack is the hardware frame, an error code or zero, and the
+ * vector number.
+ */
cld
cmpl $2,(%rsp) # X86_TRAP_NMI
- je is_nmi # Ignore NMI
+ je .Lis_nmi # Ignore NMI
cmpl $2,early_recursion_flag(%rip)
jz 1f
@@ -409,10 +411,10 @@ ENTRY(early_idt_handler)
popq %rcx
popq %rax
decl early_recursion_flag(%rip)
-is_nmi:
+.Lis_nmi:
addq $16,%rsp # drop vector number and error code
INTERRUPT_RETURN
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
__INITDATA
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 3acbff4716b0..10757d0a3fcf 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -12,6 +12,7 @@
#include <linux/pm.h>
#include <linux/io.h>
+#include <asm/irqdomain.h>
#include <asm/fixmap.h>
#include <asm/hpet.h>
#include <asm/time.h>
@@ -305,8 +306,6 @@ static void hpet_legacy_clockevent_register(void)
printk(KERN_DEBUG "hpet clockevent registered\n");
}
-static int hpet_setup_msi_irq(unsigned int irq);
-
static void hpet_set_mode(enum clock_event_mode mode,
struct clock_event_device *evt, int timer)
{
@@ -357,7 +356,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
hpet_enable_legacy_int();
} else {
struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
- hpet_setup_msi_irq(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));
enable_irq(hdev->irq);
@@ -423,6 +422,7 @@ static int hpet_legacy_next_event(unsigned long delta,
static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
static struct hpet_dev *hpet_devs;
+static struct irq_domain *hpet_domain;
void hpet_msi_unmask(struct irq_data *data)
{
@@ -473,31 +473,6 @@ static int hpet_msi_next_event(unsigned long delta,
return hpet_next_event(delta, evt, hdev->num);
}
-static int hpet_setup_msi_irq(unsigned int irq)
-{
- if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) {
- irq_free_hwirq(irq);
- return -EINVAL;
- }
- return 0;
-}
-
-static int hpet_assign_irq(struct hpet_dev *dev)
-{
- unsigned int irq = irq_alloc_hwirq(-1);
-
- if (!irq)
- return -EINVAL;
-
- irq_set_handler_data(irq, dev);
-
- if (hpet_setup_msi_irq(irq))
- return -EINVAL;
-
- dev->irq = irq;
- return 0;
-}
-
static irqreturn_t hpet_interrupt_handler(int irq, void *data)
{
struct hpet_dev *dev = (struct hpet_dev *)data;
@@ -540,9 +515,6 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
if (!(hdev->flags & HPET_DEV_VALID))
return;
- if (hpet_setup_msi_irq(hdev->irq))
- return;
-
hdev->cpu = cpu;
per_cpu(cpu_hpet_dev, cpu) = hdev;
evt->name = hdev->name;
@@ -574,7 +546,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
unsigned int id;
unsigned int num_timers;
unsigned int num_timers_used = 0;
- int i;
+ int i, irq;
if (hpet_msi_disable)
return;
@@ -587,6 +559,10 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
num_timers++; /* Value read out starts from 0 */
hpet_print_config();
+ hpet_domain = hpet_create_irq_domain(hpet_blockid);
+ if (!hpet_domain)
+ return;
+
hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL);
if (!hpet_devs)
return;
@@ -604,12 +580,14 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
hdev->flags = 0;
if (cfg & HPET_TN_PERIODIC_CAP)
hdev->flags |= HPET_DEV_PERI_CAP;
+ sprintf(hdev->name, "hpet%d", i);
hdev->num = i;
- sprintf(hdev->name, "hpet%d", i);
- if (hpet_assign_irq(hdev))
+ irq = hpet_assign_irq(hpet_domain, hdev, hdev->num);
+ if (irq <= 0)
continue;
+ hdev->irq = irq;
hdev->flags |= HPET_DEV_FSB_CAP;
hdev->flags |= HPET_DEV_VALID;
num_timers_used++;
@@ -709,10 +687,6 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
}
#else
-static int hpet_setup_msi_irq(unsigned int irq)
-{
- return 0;
-}
static void hpet_msi_capability_lookup(unsigned int start_timer)
{
return;
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 05fd74f537d6..64341aa485ae 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -40,7 +40,5 @@ EXPORT_SYMBOL(empty_zero_page);
#ifdef CONFIG_PREEMPT
EXPORT_SYMBOL(___preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
-EXPORT_SYMBOL(___preempt_schedule_context);
-#endif
+EXPORT_SYMBOL(___preempt_schedule_notrace);
#endif
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
deleted file mode 100644
index 009183276bb7..000000000000
--- a/arch/x86/kernel/i387.c
+++ /dev/null
@@ -1,656 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- */
-#include <linux/module.h>
-#include <linux/regset.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-
-#include <asm/sigcontext.h>
-#include <asm/processor.h>
-#include <asm/math_emu.h>
-#include <asm/tlbflush.h>
-#include <asm/uaccess.h>
-#include <asm/ptrace.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/user.h>
-
-static DEFINE_PER_CPU(bool, in_kernel_fpu);
-
-void kernel_fpu_disable(void)
-{
- WARN_ON(this_cpu_read(in_kernel_fpu));
- this_cpu_write(in_kernel_fpu, true);
-}
-
-void kernel_fpu_enable(void)
-{
- this_cpu_write(in_kernel_fpu, false);
-}
-
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- *
- * Except for the eagerfpu case when we return true; in the likely case
- * the thread has FPU but we are not going to set/clear TS.
- */
-static inline bool interrupted_kernel_fpu_idle(void)
-{
- if (this_cpu_read(in_kernel_fpu))
- return false;
-
- if (use_eager_fpu())
- return true;
-
- return !__thread_has_fpu(current) &&
- (read_cr0() & X86_CR0_TS);
-}
-
-/*
- * Were we in user mode (or vm86 mode) when we were
- * interrupted?
- *
- * Doing kernel_fpu_begin/end() is ok if we are running
- * in an interrupt context from user mode - we'll just
- * save the FPU state as required.
- */
-static inline bool interrupted_user_mode(void)
-{
- struct pt_regs *regs = get_irq_regs();
- return regs && user_mode(regs);
-}
-
-/*
- * Can we use the FPU in kernel mode with the
- * whole "kernel_fpu_begin/end()" sequence?
- *
- * It's always ok in process context (ie "not interrupt")
- * but it is sometimes ok even from an irq.
- */
-bool irq_fpu_usable(void)
-{
- return !in_interrupt() ||
- interrupted_user_mode() ||
- interrupted_kernel_fpu_idle();
-}
-EXPORT_SYMBOL(irq_fpu_usable);
-
-void __kernel_fpu_begin(void)
-{
- struct task_struct *me = current;
-
- this_cpu_write(in_kernel_fpu, true);
-
- if (__thread_has_fpu(me)) {
- __save_init_fpu(me);
- } else {
- this_cpu_write(fpu_owner_task, NULL);
- if (!use_eager_fpu())
- clts();
- }
-}
-EXPORT_SYMBOL(__kernel_fpu_begin);
-
-void __kernel_fpu_end(void)
-{
- struct task_struct *me = current;
-
- if (__thread_has_fpu(me)) {
- if (WARN_ON(restore_fpu_checking(me)))
- fpu_reset_state(me);
- } else if (!use_eager_fpu()) {
- stts();
- }
-
- this_cpu_write(in_kernel_fpu, false);
-}
-EXPORT_SYMBOL(__kernel_fpu_end);
-
-void unlazy_fpu(struct task_struct *tsk)
-{
- preempt_disable();
- if (__thread_has_fpu(tsk)) {
- if (use_eager_fpu()) {
- __save_fpu(tsk);
- } else {
- __save_init_fpu(tsk);
- __thread_fpu_end(tsk);
- }
- }
- preempt_enable();
-}
-EXPORT_SYMBOL(unlazy_fpu);
-
-unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
-unsigned int xstate_size;
-EXPORT_SYMBOL_GPL(xstate_size);
-static struct i387_fxsave_struct fx_scratch;
-
-static void mxcsr_feature_mask_init(void)
-{
- unsigned long mask = 0;
-
- if (cpu_has_fxsr) {
- memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
- asm volatile("fxsave %0" : "+m" (fx_scratch));
- mask = fx_scratch.mxcsr_mask;
- if (mask == 0)
- mask = 0x0000ffbf;
- }
- mxcsr_feature_mask &= mask;
-}
-
-static void init_thread_xstate(void)
-{
- /*
- * Note that xstate_size might be overwriten later during
- * xsave_init().
- */
-
- if (!cpu_has_fpu) {
- /*
- * Disable xsave as we do not support it if i387
- * emulation is enabled.
- */
- setup_clear_cpu_cap(X86_FEATURE_XSAVE);
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
- xstate_size = sizeof(struct i387_soft_struct);
- return;
- }
-
- if (cpu_has_fxsr)
- xstate_size = sizeof(struct i387_fxsave_struct);
- else
- xstate_size = sizeof(struct i387_fsave_struct);
-}
-
-/*
- * Called at bootup to set up the initial FPU state that is later cloned
- * into all processes.
- */
-
-void fpu_init(void)
-{
- unsigned long cr0;
- unsigned long cr4_mask = 0;
-
-#ifndef CONFIG_MATH_EMULATION
- if (!cpu_has_fpu) {
- pr_emerg("No FPU found and no math emulation present\n");
- pr_emerg("Giving up\n");
- for (;;)
- asm volatile("hlt");
- }
-#endif
- if (cpu_has_fxsr)
- cr4_mask |= X86_CR4_OSFXSR;
- if (cpu_has_xmm)
- cr4_mask |= X86_CR4_OSXMMEXCPT;
- if (cr4_mask)
- cr4_set_bits(cr4_mask);
-
- cr0 = read_cr0();
- cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
- if (!cpu_has_fpu)
- cr0 |= X86_CR0_EM;
- write_cr0(cr0);
-
- /*
- * init_thread_xstate is only called once to avoid overriding
- * xstate_size during boot time or during CPU hotplug.
- */
- if (xstate_size == 0)
- init_thread_xstate();
-
- mxcsr_feature_mask_init();
- xsave_init();
- eager_fpu_init();
-}
-
-void fpu_finit(struct fpu *fpu)
-{
- if (!cpu_has_fpu) {
- finit_soft_fpu(&fpu->state->soft);
- return;
- }
-
- memset(fpu->state, 0, xstate_size);
-
- if (cpu_has_fxsr) {
- fx_finit(&fpu->state->fxsave);
- } else {
- struct i387_fsave_struct *fp = &fpu->state->fsave;
- fp->cwd = 0xffff037fu;
- fp->swd = 0xffff0000u;
- fp->twd = 0xffffffffu;
- fp->fos = 0xffff0000u;
- }
-}
-EXPORT_SYMBOL_GPL(fpu_finit);
-
-/*
- * The _current_ task is using the FPU for the first time
- * so initialize it and set the mxcsr to its default
- * value at reset if we support XMM instructions and then
- * remember the current task has used the FPU.
- */
-int init_fpu(struct task_struct *tsk)
-{
- int ret;
-
- if (tsk_used_math(tsk)) {
- if (cpu_has_fpu && tsk == current)
- unlazy_fpu(tsk);
- task_disable_lazy_fpu_restore(tsk);
- return 0;
- }
-
- /*
- * Memory allocation at the first usage of the FPU and other state.
- */
- ret = fpu_alloc(&tsk->thread.fpu);
- if (ret)
- return ret;
-
- fpu_finit(&tsk->thread.fpu);
-
- set_stopped_child_used_math(tsk);
- return 0;
-}
-EXPORT_SYMBOL_GPL(init_fpu);
-
-/*
- * The xstateregs_active() routine is the same as the fpregs_active() routine,
- * as the "regset->n" for the xstate regset will be updated based on the feature
- * capabilites supported by the xsave.
- */
-int fpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
- return tsk_used_math(target) ? regset->n : 0;
-}
-
-int xfpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
- return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0;
-}
-
-int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_fxsr)
- return -ENODEV;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- sanitize_i387_state(target);
-
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fxsave, 0, -1);
-}
-
-int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_fxsr)
- return -ENODEV;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- sanitize_i387_state(target);
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fxsave, 0, -1);
-
- /*
- * mxcsr reserved bits must be masked to zero for security reasons.
- */
- target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
-
- /*
- * update the header bits in the xsave header, indicating the
- * presence of FP and SSE state.
- */
- if (cpu_has_xsave)
- target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
- return ret;
-}
-
-int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- struct xsave_struct *xsave;
- int ret;
-
- if (!cpu_has_xsave)
- return -ENODEV;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- xsave = &target->thread.fpu.state->xsave;
-
- /*
- * Copy the 48bytes defined by the software first into the xstate
- * memory layout in the thread struct, so that we can copy the entire
- * xstateregs to the user using one user_regset_copyout().
- */
- memcpy(&xsave->i387.sw_reserved,
- xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
- /*
- * Copy the xstate memory layout.
- */
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
- return ret;
-}
-
-int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- struct xsave_struct *xsave;
- int ret;
-
- if (!cpu_has_xsave)
- return -ENODEV;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- xsave = &target->thread.fpu.state->xsave;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
- /*
- * mxcsr reserved bits must be masked to zero for security reasons.
- */
- xsave->i387.mxcsr &= mxcsr_feature_mask;
- xsave->xsave_hdr.xstate_bv &= pcntxt_mask;
- /*
- * These bits must be zero.
- */
- memset(&xsave->xsave_hdr.reserved, 0, 48);
- return ret;
-}
-
-#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-
-/*
- * FPU tag word conversions.
- */
-
-static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
-{
- unsigned int tmp; /* to avoid 16 bit prefixes in the code */
-
- /* Transform each pair of bits into 01 (valid) or 00 (empty) */
- tmp = ~twd;
- tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
- /* and move the valid bits to the lower byte. */
- tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
- tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
- tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
-
- return tmp;
-}
-
-#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16)
-#define FP_EXP_TAG_VALID 0
-#define FP_EXP_TAG_ZERO 1
-#define FP_EXP_TAG_SPECIAL 2
-#define FP_EXP_TAG_EMPTY 3
-
-static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
-{
- struct _fpxreg *st;
- u32 tos = (fxsave->swd >> 11) & 7;
- u32 twd = (unsigned long) fxsave->twd;
- u32 tag;
- u32 ret = 0xffff0000u;
- int i;
-
- for (i = 0; i < 8; i++, twd >>= 1) {
- if (twd & 0x1) {
- st = FPREG_ADDR(fxsave, (i - tos) & 7);
-
- switch (st->exponent & 0x7fff) {
- case 0x7fff:
- tag = FP_EXP_TAG_SPECIAL;
- break;
- case 0x0000:
- if (!st->significand[0] &&
- !st->significand[1] &&
- !st->significand[2] &&
- !st->significand[3])
- tag = FP_EXP_TAG_ZERO;
- else
- tag = FP_EXP_TAG_SPECIAL;
- break;
- default:
- if (st->significand[3] & 0x8000)
- tag = FP_EXP_TAG_VALID;
- else
- tag = FP_EXP_TAG_SPECIAL;
- break;
- }
- } else {
- tag = FP_EXP_TAG_EMPTY;
- }
- ret |= tag << (2 * i);
- }
- return ret;
-}
-
-/*
- * FXSR floating point environment conversions.
- */
-
-void
-convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
-{
- struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
- struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
- struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
- int i;
-
- env->cwd = fxsave->cwd | 0xffff0000u;
- env->swd = fxsave->swd | 0xffff0000u;
- env->twd = twd_fxsr_to_i387(fxsave);
-
-#ifdef CONFIG_X86_64
- env->fip = fxsave->rip;
- env->foo = fxsave->rdp;
- /*
- * should be actually ds/cs at fpu exception time, but
- * that information is not available in 64bit mode.
- */
- env->fcs = task_pt_regs(tsk)->cs;
- if (tsk == current) {
- savesegment(ds, env->fos);
- } else {
- env->fos = tsk->thread.ds;
- }
- env->fos |= 0xffff0000;
-#else
- env->fip = fxsave->fip;
- env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
- env->foo = fxsave->foo;
- env->fos = fxsave->fos;
-#endif
-
- for (i = 0; i < 8; ++i)
- memcpy(&to[i], &from[i], sizeof(to[0]));
-}
-
-void convert_to_fxsr(struct task_struct *tsk,
- const struct user_i387_ia32_struct *env)
-
-{
- struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
- struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
- struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
- int i;
-
- fxsave->cwd = env->cwd;
- fxsave->swd = env->swd;
- fxsave->twd = twd_i387_to_fxsr(env->twd);
- fxsave->fop = (u16) ((u32) env->fcs >> 16);
-#ifdef CONFIG_X86_64
- fxsave->rip = env->fip;
- fxsave->rdp = env->foo;
- /* cs and ds ignored */
-#else
- fxsave->fip = env->fip;
- fxsave->fcs = (env->fcs & 0xffff);
- fxsave->foo = env->foo;
- fxsave->fos = env->fos;
-#endif
-
- for (i = 0; i < 8; ++i)
- memcpy(&to[i], &from[i], sizeof(from[0]));
-}
-
-int fpregs_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- struct user_i387_ia32_struct env;
- int ret;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
-
- if (!cpu_has_fxsr)
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fsave, 0,
- -1);
-
- sanitize_i387_state(target);
-
- if (kbuf && pos == 0 && count == sizeof(env)) {
- convert_from_fxsr(kbuf, target);
- return 0;
- }
-
- convert_from_fxsr(&env, target);
-
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
-}
-
-int fpregs_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- struct user_i387_ia32_struct env;
- int ret;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- sanitize_i387_state(target);
-
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
-
- if (!cpu_has_fxsr)
- return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fsave, 0,
- -1);
-
- if (pos > 0 || count < sizeof(env))
- convert_from_fxsr(&env, target);
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
- if (!ret)
- convert_to_fxsr(target, &env);
-
- /*
- * update the header bit in the xsave header, indicating the
- * presence of FP.
- */
- if (cpu_has_xsave)
- target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP;
- return ret;
-}
-
-/*
- * FPU state for core dumps.
- * This is only used for a.out dumps now.
- * It is declared generically using elf_fpregset_t (which is
- * struct user_i387_struct) but is in fact only used for 32-bit
- * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
- */
-int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu)
-{
- struct task_struct *tsk = current;
- int fpvalid;
-
- fpvalid = !!used_math();
- if (fpvalid)
- fpvalid = !fpregs_get(tsk, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- fpu, NULL);
-
- return fpvalid;
-}
-EXPORT_SYMBOL(dump_fpu);
-
-#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
-
-static int __init no_387(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_FPU);
- return 1;
-}
-
-__setup("no387", no_387);
-
-void fpu_detect(struct cpuinfo_x86 *c)
-{
- unsigned long cr0;
- u16 fsw, fcw;
-
- fsw = fcw = 0xffff;
-
- cr0 = read_cr0();
- cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
- write_cr0(cr0);
-
- asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
- : "+m" (fsw), "+m" (fcw));
-
- if (fsw == 0 && (fcw & 0x103f) == 0x003f)
- set_cpu_cap(c, X86_FEATURE_FPU);
- else
- clear_cpu_cap(c, X86_FEATURE_FPU);
-
- /* The final cr0 value is set in fpu_init() */
-}
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index e7cc5370cd2f..16cb827a5b27 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -329,8 +329,8 @@ static void init_8259A(int auto_eoi)
*/
outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */
- /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
- outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+ /* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */
+ outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR);
/* 8259A-1 (the master) has a slave on IR2 */
outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);
@@ -342,8 +342,8 @@ static void init_8259A(int auto_eoi)
outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */
- /* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */
- outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
+ /* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */
+ outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR);
/* 8259A-2 is a slave on master's IR2 */
outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
/* (slave's support for AEOI in flat mode is to be investigated) */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index e5952c225532..88b366487b0e 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -22,6 +22,12 @@
#define CREATE_TRACE_POINTS
#include <asm/trace/irq_vectors.h>
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
+
atomic_t irq_err_count;
/* Function pointer for generic interrupt vector handling */
@@ -116,6 +122,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
seq_puts(p, " Threshold APIC interrupts\n");
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ seq_printf(p, "%*s: ", prec, "DFR");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count);
+ seq_puts(p, " Deferred Error APIC interrupts\n");
+#endif
#ifdef CONFIG_X86_MCE
seq_printf(p, "%*s: ", prec, "MCE");
for_each_online_cpu(j)
@@ -136,6 +148,18 @@ int arch_show_interrupts(struct seq_file *p, int prec)
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
#endif
+#ifdef CONFIG_HAVE_KVM
+ seq_printf(p, "%*s: ", prec, "PIN");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
+ seq_puts(p, " Posted-interrupt notification event\n");
+
+ seq_printf(p, "%*s: ", prec, "PIW");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->kvm_posted_intr_wakeup_ipis);
+ seq_puts(p, " Posted-interrupt wakeup event\n");
+#endif
return 0;
}
@@ -192,8 +216,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
unsigned vector = ~regs->orig_ax;
unsigned irq;
- irq_enter();
- exit_idle();
+ entering_irq();
irq = __this_cpu_read(vector_irq[vector]);
@@ -209,7 +232,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
}
}
- irq_exit();
+ exiting_irq();
set_irq_regs(old_regs);
return 1;
@@ -237,6 +260,18 @@ __visible void smp_x86_platform_ipi(struct pt_regs *regs)
}
#ifdef CONFIG_HAVE_KVM
+static void dummy_handler(void) {}
+static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler;
+
+void kvm_set_posted_intr_wakeup_handler(void (*handler)(void))
+{
+ if (handler)
+ kvm_posted_intr_wakeup_handler = handler;
+ else
+ kvm_posted_intr_wakeup_handler = dummy_handler;
+}
+EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler);
+
/*
* Handler for POSTED_INTERRUPT_VECTOR.
*/
@@ -244,16 +279,23 @@ __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- ack_APIC_irq();
-
- irq_enter();
-
- exit_idle();
-
+ entering_ack_irq();
inc_irq_stat(kvm_posted_intr_ipis);
+ exiting_irq();
+ set_irq_regs(old_regs);
+}
- irq_exit();
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ entering_ack_irq();
+ inc_irq_stat(kvm_posted_intr_wakeup_ipis);
+ kvm_posted_intr_wakeup_handler();
+ exiting_irq();
set_irq_regs(old_regs);
}
#endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index f9fd86a7fcc7..cd74f5978ab9 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -21,12 +21,6 @@
#include <asm/apic.h>
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
#ifdef CONFIG_DEBUG_STACKOVERFLOW
int sysctl_panic_on_stackoverflow __read_mostly;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 394e643d7830..bc4604e500a3 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -20,12 +20,6 @@
#include <asm/idle.h>
#include <asm/apic.h>
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
int sysctl_panic_on_stackoverflow;
/*
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 15d741ddfeeb..dc5fa6a1e8d6 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -10,12 +10,6 @@
#include <asm/apic.h>
#include <asm/trace/irq_vectors.h>
-static inline void irq_work_entering_irq(void)
-{
- irq_enter();
- ack_APIC_irq();
-}
-
static inline void __smp_irq_work_interrupt(void)
{
inc_irq_stat(apic_irq_work_irqs);
@@ -24,14 +18,14 @@ static inline void __smp_irq_work_interrupt(void)
__visible void smp_irq_work_interrupt(struct pt_regs *regs)
{
- irq_work_entering_irq();
+ ipi_entering_ack_irq();
__smp_irq_work_interrupt();
exiting_irq();
}
__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
{
- irq_work_entering_irq();
+ ipi_entering_ack_irq();
trace_irq_work_entry(IRQ_WORK_VECTOR);
__smp_irq_work_interrupt();
trace_irq_work_exit(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index cd10a6437264..a3a5e158ed69 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -86,7 +86,7 @@ void __init init_IRQ(void)
int i;
/*
- * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
+ * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15.
* If these IRQ's are handled by legacy interrupt-controllers like PIC,
* then this configuration will likely be static after the boot. If
* these IRQ's are handled by more mordern controllers like IO-APIC,
@@ -94,7 +94,7 @@ void __init init_IRQ(void)
* irq's migrate etc.
*/
for (i = 0; i < nr_legacy_irqs(); i++)
- per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i;
+ per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i;
x86_init.irqs.intr_init();
}
@@ -135,6 +135,10 @@ static void __init apic_intr_init(void)
alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt);
+#endif
+
#ifdef CONFIG_X86_LOCAL_APIC
/* self generated IPI for local APIC timer */
alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
@@ -144,6 +148,8 @@ static void __init apic_intr_init(void)
#ifdef CONFIG_HAVE_KVM
/* IPI for KVM to deliver posted interrupt */
alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
+ /* IPI for KVM to deliver interrupt to wake up tasks */
+ alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
#endif
/* IPI vectors for APIC spurious and error interrupts */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 9435620062df..47190bd399e7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -331,7 +331,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
apic_write(APIC_EOI, APIC_EOI_ACK);
}
-void kvm_guest_cpu_init(void)
+static void kvm_guest_cpu_init(void)
{
if (!kvm_para_available())
return;
@@ -584,6 +584,39 @@ static void kvm_kick_cpu(int cpu)
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void kvm_wait(u8 *ptr, u8 val)
+{
+ unsigned long flags;
+
+ if (in_nmi())
+ return;
+
+ local_irq_save(flags);
+
+ if (READ_ONCE(*ptr) != val)
+ goto out;
+
+ /*
+ * halt until it's our turn and kicked. Note that we do safe halt
+ * for irq enabled case to avoid hang when lock info is overwritten
+ * in irq spinlock slowpath and no spurious interrupt occur to save us.
+ */
+ if (arch_irqs_disabled_flags(flags))
+ halt();
+ else
+ safe_halt();
+
+out:
+ local_irq_restore(flags);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
enum kvm_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
@@ -655,7 +688,7 @@ static inline void spin_time_accum_blocked(u64 start)
static struct dentry *d_spin_debug;
static struct dentry *d_kvm_debug;
-struct dentry *kvm_init_debugfs(void)
+static struct dentry *kvm_init_debugfs(void)
{
d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
if (!d_kvm_debug)
@@ -817,6 +850,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
}
}
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
@@ -828,8 +863,16 @@ void __init kvm_spinlock_init(void)
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ __pv_init_lock_hash();
+ pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_lock_ops.wait = kvm_wait;
+ pv_lock_ops.kick = kvm_kick_cpu;
+#else /* !CONFIG_QUEUED_SPINLOCKS */
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
pv_lock_ops.unlock_kick = kvm_unlock_kick;
+#endif
}
static __init int kvm_spinlock_init_jump(void)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 42caaef897c8..49487b488061 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -24,6 +24,7 @@
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/memblock.h>
+#include <linux/sched.h>
#include <asm/x86_init.h>
#include <asm/reboot.h>
@@ -217,8 +218,10 @@ static void kvm_shutdown(void)
void __init kvmclock_init(void)
{
+ struct pvclock_vcpu_time_info *vcpu_time;
unsigned long mem;
- int size;
+ int size, cpu;
+ u8 flags;
size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
@@ -264,7 +267,14 @@ void __init kvmclock_init(void)
pv_info.name = "KVM";
if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
- pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+ pvclock_set_flags(~0);
+
+ cpu = get_cpu();
+ vcpu_time = &hv_clock[cpu].pvti;
+ flags = pvclock_read_flags(vcpu_time);
+ if (flags & PVCLOCK_COUNTS_FROM_ZERO)
+ set_sched_clock_stable();
+ put_cpu();
}
int __init kvm_setup_vsyscall_timeinfo(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 415480d3ea84..819ab3f9c9c7 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -17,6 +17,7 @@
#include <linux/ftrace.h>
#include <linux/io.h>
#include <linux/suspend.h>
+#include <linux/vmalloc.h>
#include <asm/init.h>
#include <asm/pgtable.h>
@@ -25,6 +26,7 @@
#include <asm/io_apic.h>
#include <asm/debugreg.h>
#include <asm/kexec-bzimage64.h>
+#include <asm/setup.h>
#ifdef CONFIG_KEXEC_FILE
static struct kexec_file_ops *kexec_file_loaders[] = {
@@ -334,7 +336,7 @@ void arch_crash_save_vmcoreinfo(void)
VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
#endif
vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
- (unsigned long)&_text - __START_KERNEL);
+ kaslr_offset());
}
/* arch-dependent functionality related to kexec file-based syscall */
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 2d2a237f2c73..30ca7607cbbb 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -19,8 +19,8 @@
#include <linux/module.h>
#include <linux/smp.h>
#include <linux/pci.h>
-#include <linux/irqdomain.h>
+#include <asm/irqdomain.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
#include <asm/pgalloc.h>
@@ -113,11 +113,6 @@ static void __init MP_bus_info(struct mpc_bus *m)
pr_warn("Unknown bustype %s - ignoring\n", str);
}
-static struct irq_domain_ops mp_ioapic_irqdomain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
-};
-
static void __init MP_ioapic_info(struct mpc_ioapic *m)
{
struct ioapic_domain_cfg cfg = {
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index bbb6c7316341..33ee3e0efd65 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -8,11 +8,33 @@
#include <asm/paravirt.h>
+#ifdef CONFIG_QUEUED_SPINLOCKS
+__visible void __native_queued_spin_unlock(struct qspinlock *lock)
+{
+ native_queued_spin_unlock(lock);
+}
+
+PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
+
+bool pv_is_native_spin_unlock(void)
+{
+ return pv_lock_ops.queued_spin_unlock.func ==
+ __raw_callee_save___native_queued_spin_unlock;
+}
+#endif
+
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+ .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
+ .wait = paravirt_nop,
+ .kick = paravirt_nop,
+#else /* !CONFIG_QUEUED_SPINLOCKS */
.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
.unlock_kick = paravirt_nop,
-#endif
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+#endif /* SMP */
};
EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c614dd492f5f..58bcfb67c01f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -154,7 +154,9 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
ret = paravirt_patch_ident_64(insnbuf, len);
else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
+#ifdef CONFIG_X86_32
type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
+#endif
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
/* If operation requires a jmp, then jmp */
@@ -371,7 +373,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
.load_sp0 = native_load_sp0,
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+#if defined(CONFIG_X86_32)
.irq_enable_sysexit = native_irq_enable_sysexit,
#endif
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index d9f32e6d6ab6..e1b013696dde 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
DEF_NATIVE(pv_cpu_ops, clts, "clts");
DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
+#endif
+
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
{
/* arg in %eax, return in %eax */
@@ -24,6 +28,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
return 0;
}
+extern bool pv_is_native_spin_unlock(void);
+
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
{
@@ -47,14 +53,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_mmu_ops, write_cr3);
PATCH_SITE(pv_cpu_ops, clts);
PATCH_SITE(pv_cpu_ops, read_tsc);
-
- patch_site:
- ret = paravirt_patch_insns(ibuf, len, start, end);
- break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+ case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+ if (pv_is_native_spin_unlock()) {
+ start = start_pv_lock_ops_queued_spin_unlock;
+ end = end_pv_lock_ops_queued_spin_unlock;
+ goto patch_site;
+ }
+#endif
default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
+
+patch_site:
+ ret = paravirt_patch_insns(ibuf, len, start, end);
+ break;
}
#undef PATCH_SITE
return ret;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index a1da6737ba5b..8aa05583bc42 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
DEF_NATIVE(, mov32, "mov %edi, %eax");
DEF_NATIVE(, mov64, "mov %rdi, %rax");
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
+#endif
+
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
{
return paravirt_patch_insns(insnbuf, len,
@@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
start__mov64, end__mov64);
}
+extern bool pv_is_native_spin_unlock(void);
+
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
{
@@ -49,7 +55,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_irq_ops, irq_enable);
PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
PATCH_SITE(pv_cpu_ops, usergs_sysret32);
PATCH_SITE(pv_cpu_ops, usergs_sysret64);
PATCH_SITE(pv_cpu_ops, swapgs);
@@ -59,14 +64,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_cpu_ops, clts);
PATCH_SITE(pv_mmu_ops, flush_tlb_single);
PATCH_SITE(pv_cpu_ops, wbinvd);
-
- patch_site:
- ret = paravirt_patch_insns(ibuf, len, start, end);
- break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+ case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+ if (pv_is_native_spin_unlock()) {
+ start = start_pv_lock_ops_queued_spin_unlock;
+ end = end_pv_lock_ops_queued_spin_unlock;
+ goto patch_site;
+ }
+#endif
default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
+
+patch_site:
+ ret = paravirt_patch_insns(ibuf, len, start, end);
+ break;
}
#undef PATCH_SITE
return ret;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index a25e202bb319..353972c1946c 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -140,6 +140,51 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
free_pages((unsigned long)vaddr, get_order(size));
}
+void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, struct dma_attrs *attrs)
+{
+ struct dma_map_ops *ops = get_dma_ops(dev);
+ void *memory;
+
+ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+
+ if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+ return memory;
+
+ if (!dev)
+ dev = &x86_dma_fallback_dev;
+
+ if (!is_device_dma_capable(dev))
+ return NULL;
+
+ if (!ops->alloc)
+ return NULL;
+
+ memory = ops->alloc(dev, size, dma_handle,
+ dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
+ debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
+
+ return memory;
+}
+EXPORT_SYMBOL(dma_alloc_attrs);
+
+void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t bus,
+ struct dma_attrs *attrs)
+{
+ struct dma_map_ops *ops = get_dma_ops(dev);
+
+ WARN_ON(irqs_disabled()); /* for portability */
+
+ if (dma_release_from_coherent(dev, get_order(size), vaddr))
+ return;
+
+ debug_dma_free_coherent(dev, size, vaddr, bus);
+ if (ops->free)
+ ops->free(dev, size, vaddr, bus, attrs);
+}
+EXPORT_SYMBOL(dma_free_attrs);
+
/*
* See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
* parameter documentation.
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 77dd0ad58be4..adf0392d549a 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
{
void *vaddr;
+ /*
+ * Don't print a warning when the first allocation attempt fails.
+ * swiotlb_alloc_coherent() will print a warning when the DMA
+ * memory allocation ultimately failed.
+ */
+ flags |= __GFP_NOWARN;
+
vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
attrs);
if (vaddr)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6e338e3b1dc0..9cad694ed7c4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -25,8 +25,7 @@
#include <asm/idle.h>
#include <asm/uaccess.h>
#include <asm/mwait.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/debugreg.h>
#include <asm/nmi.h>
#include <asm/tlbflush.h>
@@ -76,9 +75,6 @@ void idle_notifier_unregister(struct notifier_block *n)
EXPORT_SYMBOL_GPL(idle_notifier_unregister);
#endif
-struct kmem_cache *task_xstate_cachep;
-EXPORT_SYMBOL_GPL(task_xstate_cachep);
-
/*
* this gets called so that we can store lazy state into memory and copy the
* current task into the new thread.
@@ -87,36 +83,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
*dst = *src;
- dst->thread.fpu_counter = 0;
- dst->thread.fpu.has_fpu = 0;
- dst->thread.fpu.state = NULL;
- task_disable_lazy_fpu_restore(dst);
- if (tsk_used_math(src)) {
- int err = fpu_alloc(&dst->thread.fpu);
- if (err)
- return err;
- fpu_copy(dst, src);
- }
- return 0;
-}
-
-void free_thread_xstate(struct task_struct *tsk)
-{
- fpu_free(&tsk->thread.fpu);
-}
-
-void arch_release_task_struct(struct task_struct *tsk)
-{
- free_thread_xstate(tsk);
-}
-
-void arch_task_cache_init(void)
-{
- task_xstate_cachep =
- kmem_cache_create("task_xstate", xstate_size,
- __alignof__(union thread_xstate),
- SLAB_PANIC | SLAB_NOTRACK, NULL);
- setup_xstate_comp();
+ return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
}
/*
@@ -127,6 +94,7 @@ void exit_thread(void)
struct task_struct *me = current;
struct thread_struct *t = &me->thread;
unsigned long *bp = t->io_bitmap_ptr;
+ struct fpu *fpu = &t->fpu;
if (bp) {
struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
@@ -142,7 +110,7 @@ void exit_thread(void)
kfree(bp);
}
- drop_fpu(me);
+ fpu__drop(fpu);
}
void flush_thread(void)
@@ -152,19 +120,7 @@ void flush_thread(void)
flush_ptrace_hw_breakpoint(tsk);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
- if (!use_eager_fpu()) {
- /* FPU state will be reallocated lazily at the first use. */
- drop_fpu(tsk);
- free_thread_xstate(tsk);
- } else {
- if (!tsk_used_math(tsk)) {
- /* kthread execs. TODO: cleanup this horror. */
- if (WARN_ON(init_fpu(tsk)))
- force_sig(SIGKILL, tsk);
- user_fpu_begin();
- }
- restore_init_xstate();
- }
+ fpu__clear(&tsk->thread.fpu);
}
static void hard_disable_TSC(void)
@@ -445,11 +401,10 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
}
/*
- * MONITOR/MWAIT with no hints, used for default default C1 state.
- * This invokes MWAIT with interrutps enabled and no flags,
- * which is backwards compatible with the original MWAIT implementation.
+ * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT
+ * with interrupts enabled and no flags, which is backwards compatible with the
+ * original MWAIT implementation.
*/
-
static void mwait_idle(void)
{
if (!current_set_polling_and_test()) {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8ed2106b06da..c09c99ccf3e3 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -39,8 +39,7 @@
#include <asm/pgtable.h>
#include <asm/ldt.h>
#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/desc.h>
#ifdef CONFIG_MATH_EMULATION
#include <asm/math_emu.h>
@@ -242,14 +241,16 @@ __visible __notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread,
- *next = &next_p->thread;
+ *next = &next_p->thread;
+ struct fpu *prev_fpu = &prev->fpu;
+ struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
- fpu_switch_t fpu;
+ fpu_switch_t fpu_switch;
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
- fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+ fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
/*
* Save away %gs. No need to save %fs, as it was saved on the
@@ -296,19 +297,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
* Leave lazy mode, flushing any hypercalls made here.
* This must be done before restoring TLS segments so
* the GDT and LDT are properly updated, and must be
- * done before math_state_restore, so the TS bit is up
+ * done before fpu__restore(), so the TS bit is up
* to date.
*/
arch_end_context_switch(next_p);
/*
- * Reload esp0, kernel_stack, and current_top_of_stack. This changes
+ * Reload esp0 and cpu_current_top_of_stack. This changes
* current_thread_info().
*/
load_sp0(tss, next);
- this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) +
- THREAD_SIZE);
this_cpu_write(cpu_current_top_of_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE);
@@ -319,7 +317,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
if (prev->gs | next->gs)
lazy_load_gs(next->gs);
- switch_fpu_finish(next_p, fpu);
+ switch_fpu_finish(next_fpu, fpu_switch);
this_cpu_write(current_task, next_p);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ddfdbf74f174..843f92e4c711 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -38,8 +38,7 @@
#include <asm/pgtable.h>
#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
@@ -274,12 +273,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread;
struct thread_struct *next = &next_p->thread;
+ struct fpu *prev_fpu = &prev->fpu;
+ struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
unsigned fsindex, gsindex;
- fpu_switch_t fpu;
+ fpu_switch_t fpu_switch;
- fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+ fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
/* We must save %fs and %gs before load_TLS() because
* %fs and %gs may be cleared by load_TLS().
@@ -299,7 +300,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
* Leave lazy mode, flushing any hypercalls made here. This
* must be done after loading TLS entries in the GDT but before
* loading segments that might reference them, and and it must
- * be done before math_state_restore, so the TS bit is up to
+ * be done before fpu__restore(), so the TS bit is up to
* date.
*/
arch_end_context_switch(next_p);
@@ -391,7 +392,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
prev->gsindex = gsindex;
- switch_fpu_finish(next_p, fpu);
+ switch_fpu_finish(next_fpu, fpu_switch);
/*
* Switch the PDA and FPU contexts.
@@ -409,9 +410,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
/* Reload esp0 and ss1. This changes current_thread_info(). */
load_sp0(tss, next);
- this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) + THREAD_SIZE);
-
/*
* Now maybe reload the debug registers and handle I/O bitmaps
*/
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index a7bc79480719..9be72bc3613f 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -11,7 +11,6 @@
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/ptrace.h>
-#include <linux/regset.h>
#include <linux/tracehook.h>
#include <linux/user.h>
#include <linux/elf.h>
@@ -28,8 +27,9 @@
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
#include <asm/debugreg.h>
#include <asm/ldt.h>
#include <asm/desc.h>
@@ -1297,7 +1297,7 @@ static struct user_regset x86_64_regsets[] __read_mostly = {
.core_note_type = NT_PRFPREG,
.n = sizeof(struct user_i387_struct) / sizeof(long),
.size = sizeof(long), .align = sizeof(long),
- .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+ .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
},
[REGSET_XSTATE] = {
.core_note_type = NT_X86_XSTATE,
@@ -1338,13 +1338,13 @@ static struct user_regset x86_32_regsets[] __read_mostly = {
.core_note_type = NT_PRFPREG,
.n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
.size = sizeof(u32), .align = sizeof(u32),
- .active = fpregs_active, .get = fpregs_get, .set = fpregs_set
+ .active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set
},
[REGSET_XFP] = {
.core_note_type = NT_PRXFPREG,
.n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
.size = sizeof(u32), .align = sizeof(u32),
- .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+ .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
},
[REGSET_XSTATE] = {
.core_note_type = NT_X86_XSTATE,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d74ac33290ae..39ca113676fe 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -531,12 +531,14 @@ static void __init reserve_crashkernel_low(void)
if (ret != 0) {
/*
* two parts from lib/swiotlb.c:
- * swiotlb size: user specified with swiotlb= or default.
- * swiotlb overflow buffer: now is hardcoded to 32k.
- * We round it to 8M for other buffers that
- * may need to stay low too.
+ * -swiotlb size: user-specified with swiotlb= or default.
+ *
+ * -swiotlb overflow buffer: now hardcoded to 32k. We round it
+ * to 8M for other buffers that may need to stay low too. Also
+ * make sure we allocate enough extra low memory so that we
+ * don't run out of DMA buffers for 32-bit devices.
*/
- low_size = swiotlb_size_or_default() + (8UL<<20);
+ low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20);
auto_set = true;
} else {
/* passed with crashkernel=0,low ? */
@@ -834,7 +836,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
{
if (kaslr_enabled()) {
pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
- (unsigned long)&_text - __START_KERNEL,
+ kaslr_offset(),
__START_KERNEL,
__START_KERNEL_map,
MODULES_VADDR-1);
@@ -1222,8 +1224,7 @@ void __init setup_arch(char **cmdline_p)
init_cpu_to_node();
init_apic_mappings();
- if (x86_io_apic_ops.init)
- x86_io_apic_ops.init();
+ io_apic_init_mappings();
kvm_guest_init();
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 1ea14fd53933..206996c1669d 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -26,8 +26,8 @@
#include <asm/processor.h>
#include <asm/ucontext.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
#include <asm/vdso.h>
#include <asm/mce.h>
#include <asm/sighandling.h>
@@ -103,7 +103,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
get_user_ex(buf, &sc->fpstate);
} get_user_catch(err);
- err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
+ err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32));
force_iret();
@@ -199,6 +199,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
unsigned long sp = regs->sp;
unsigned long buf_fx = 0;
int onsigstack = on_sig_stack(sp);
+ struct fpu *fpu = &current->thread.fpu;
/* redzone */
if (config_enabled(CONFIG_X86_64))
@@ -218,9 +219,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
}
}
- if (used_math()) {
- sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
- &buf_fx, &math_size);
+ if (fpu->fpstate_active) {
+ sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+ &buf_fx, &math_size);
*fpstate = (void __user *)sp;
}
@@ -234,8 +235,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
return (void __user *)-1L;
/* save i387 and extended state */
- if (used_math() &&
- save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
+ if (fpu->fpstate_active &&
+ copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
return (void __user *)-1L;
return (void __user *)sp;
@@ -593,6 +594,22 @@ badframe:
return 0;
}
+static inline int is_ia32_compat_frame(void)
+{
+ return config_enabled(CONFIG_IA32_EMULATION) &&
+ test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+ return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+ return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
static int
setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
{
@@ -617,6 +634,7 @@ static void
handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
bool stepping, failed;
+ struct fpu *fpu = &current->thread.fpu;
/* Are we from a system call? */
if (syscall_get_nr(current, regs) >= 0) {
@@ -665,8 +683,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
/*
* Ensure the signal handler starts with the new fpu state.
*/
- if (used_math())
- fpu_reset_state(current);
+ if (fpu->fpstate_active)
+ fpu__clear(fpu);
}
signal_setup_done(failed, ksig, stepping);
}
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index be8e1bde07aa..15aaa69bbb5e 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -170,8 +170,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
asmlinkage __visible void smp_reboot_interrupt(void)
{
- ack_APIC_irq();
- irq_enter();
+ ipi_entering_ack_irq();
stop_this_cpu(NULL);
irq_exit();
}
@@ -265,12 +264,6 @@ __visible void smp_reschedule_interrupt(struct pt_regs *regs)
*/
}
-static inline void smp_entering_irq(void)
-{
- ack_APIC_irq();
- irq_enter();
-}
-
__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
{
/*
@@ -279,7 +272,7 @@ __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
* scheduler_ipi(). This is OK, since those functions are allowed
* to nest.
*/
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_reschedule_entry(RESCHEDULE_VECTOR);
__smp_reschedule_interrupt();
trace_reschedule_exit(RESCHEDULE_VECTOR);
@@ -297,14 +290,14 @@ static inline void __smp_call_function_interrupt(void)
__visible void smp_call_function_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
__smp_call_function_interrupt();
exiting_irq();
}
__visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_call_function_entry(CALL_FUNCTION_VECTOR);
__smp_call_function_interrupt();
trace_call_function_exit(CALL_FUNCTION_VECTOR);
@@ -319,14 +312,14 @@ static inline void __smp_call_function_single_interrupt(void)
__visible void smp_call_function_single_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
__smp_call_function_single_interrupt();
exiting_irq();
}
__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
__smp_call_function_single_interrupt();
trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 50e547eac8cd..8add66b22f33 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,8 +68,7 @@
#include <asm/mwait.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
@@ -314,10 +313,10 @@ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
}
-#define link_mask(_m, c1, c2) \
+#define link_mask(mfunc, c1, c2) \
do { \
- cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \
- cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \
+ cpumask_set_cpu((c1), mfunc(c2)); \
+ cpumask_set_cpu((c2), mfunc(c1)); \
} while (0)
static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -398,9 +397,9 @@ void set_cpu_sibling_map(int cpu)
cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
if (!has_mp) {
- cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+ cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
- cpumask_set_cpu(cpu, cpu_core_mask(cpu));
+ cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
c->booted_cores = 1;
return;
}
@@ -409,32 +408,34 @@ void set_cpu_sibling_map(int cpu)
o = &cpu_data(i);
if ((i == cpu) || (has_smt && match_smt(c, o)))
- link_mask(sibling, cpu, i);
+ link_mask(topology_sibling_cpumask, cpu, i);
if ((i == cpu) || (has_mp && match_llc(c, o)))
- link_mask(llc_shared, cpu, i);
+ link_mask(cpu_llc_shared_mask, cpu, i);
}
/*
* This needs a separate iteration over the cpus because we rely on all
- * cpu_sibling_mask links to be set-up.
+ * topology_sibling_cpumask links to be set-up.
*/
for_each_cpu(i, cpu_sibling_setup_mask) {
o = &cpu_data(i);
if ((i == cpu) || (has_mp && match_die(c, o))) {
- link_mask(core, cpu, i);
+ link_mask(topology_core_cpumask, cpu, i);
/*
* Does this new cpu bringup a new core?
*/
- if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) {
+ if (cpumask_weight(
+ topology_sibling_cpumask(cpu)) == 1) {
/*
* for each core in package, increment
* the booted_cores for this new cpu
*/
- if (cpumask_first(cpu_sibling_mask(i)) == i)
+ if (cpumask_first(
+ topology_sibling_cpumask(i)) == i)
c->booted_cores++;
/*
* increment the core count for all
@@ -514,6 +515,40 @@ void __inquire_remote_apic(int apicid)
}
/*
+ * The Multiprocessor Specification 1.4 (1997) example code suggests
+ * that there should be a 10ms delay between the BSP asserting INIT
+ * and de-asserting INIT, when starting a remote processor.
+ * But that slows boot and resume on modern processors, which include
+ * many cores and don't require that delay.
+ *
+ * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
+ * Modern processor families are quirked to remove the delay entirely.
+ */
+#define UDELAY_10MS_DEFAULT 10000
+
+static unsigned int init_udelay = UDELAY_10MS_DEFAULT;
+
+static int __init cpu_init_udelay(char *str)
+{
+ get_option(&str, &init_udelay);
+
+ return 0;
+}
+early_param("cpu_init_udelay", cpu_init_udelay);
+
+static void __init smp_quirk_init_udelay(void)
+{
+ /* if cmdline changed it from default, leave it alone */
+ if (init_udelay != UDELAY_10MS_DEFAULT)
+ return;
+
+ /* if modern processor, use no delay */
+ if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+ ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+ init_udelay = 0;
+}
+
+/*
* Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
* INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
* won't ... remember to clear down the APIC, etc later.
@@ -555,7 +590,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
static int
wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
- unsigned long send_status, accept_status = 0;
+ unsigned long send_status = 0, accept_status = 0;
int maxlvt, num_starts, j;
maxlvt = lapic_get_maxlvt();
@@ -583,7 +618,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
- mdelay(10);
+ udelay(init_udelay);
pr_debug("Deasserting INIT\n");
@@ -651,6 +686,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
+
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
accept_status = (apic_read(APIC_ESR) & 0xEF);
@@ -792,8 +828,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
clear_tsk_thread_flag(idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
#endif
- per_cpu(kernel_stack, cpu) =
- (unsigned long)task_stack_page(idle) + THREAD_SIZE;
}
/*
@@ -1009,8 +1043,8 @@ static __init void disable_smp(void)
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
else
physid_set_mask_of_physid(0, &phys_cpu_present_map);
- cpumask_set_cpu(0, cpu_sibling_mask(0));
- cpumask_set_cpu(0, cpu_core_mask(0));
+ cpumask_set_cpu(0, topology_sibling_cpumask(0));
+ cpumask_set_cpu(0, topology_core_cpumask(0));
}
enum {
@@ -1176,6 +1210,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
uv_system_init();
set_mtrr_aps_delayed_init();
+
+ smp_quirk_init_udelay();
}
void arch_enable_nonboot_cpus_begin(void)
@@ -1293,22 +1329,22 @@ static void remove_siblinginfo(int cpu)
int sibling;
struct cpuinfo_x86 *c = &cpu_data(cpu);
- for_each_cpu(sibling, cpu_core_mask(cpu)) {
- cpumask_clear_cpu(cpu, cpu_core_mask(sibling));
+ for_each_cpu(sibling, topology_core_cpumask(cpu)) {
+ cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
/*/
* last thread sibling in this cpu core going down
*/
- if (cpumask_weight(cpu_sibling_mask(cpu)) == 1)
+ if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1)
cpu_data(sibling).booted_cores--;
}
- for_each_cpu(sibling, cpu_sibling_mask(cpu))
- cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+ for_each_cpu(sibling, topology_sibling_cpumask(cpu))
+ cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
cpumask_clear(cpu_llc_shared_mask(cpu));
- cpumask_clear(cpu_sibling_mask(cpu));
- cpumask_clear(cpu_core_mask(cpu));
+ cpumask_clear(topology_sibling_cpumask(cpu));
+ cpumask_clear(topology_core_cpumask(cpu));
c->phys_proc_id = 0;
c->cpu_core_id = 0;
cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 324ab5247687..f5791927aa64 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -54,12 +54,13 @@
#include <asm/ftrace.h>
#include <asm/traps.h>
#include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/mce.h>
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
#include <asm/alternative.h>
+#include <asm/fpu/xstate.h>
+#include <asm/trace/mpx.h>
#include <asm/mpx.h>
#ifdef CONFIG_X86_64
@@ -72,8 +73,7 @@ gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss;
#else
#include <asm/processor-flags.h>
#include <asm/setup.h>
-
-asmlinkage int system_call(void);
+#include <asm/proto.h>
#endif
/* Must be page-aligned because the real IDT is used in a fixmap. */
@@ -371,10 +371,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
{
- struct task_struct *tsk = current;
- struct xsave_struct *xsave_buf;
enum ctx_state prev_state;
- struct bndcsr *bndcsr;
+ const struct bndcsr *bndcsr;
siginfo_t *info;
prev_state = exception_enter();
@@ -393,15 +391,15 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
/*
* We need to look at BNDSTATUS to resolve this exception.
- * It is not directly accessible, though, so we need to
- * do an xsave and then pull it out of the xsave buffer.
+ * A NULL here might mean that it is in its 'init state',
+ * which is all zeros which indicates MPX was not
+ * responsible for the exception.
*/
- fpu_save_init(&tsk->thread.fpu);
- xsave_buf = &(tsk->thread.fpu.state->xsave);
- bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
if (!bndcsr)
goto exit_trap;
+ trace_bounds_exception_mpx(bndcsr);
/*
* The error code field of the BNDSTATUS register communicates status
* information of a bound range exception #BR or operation involving
@@ -409,11 +407,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
*/
switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
case 2: /* Bound directory has invalid entry. */
- if (mpx_handle_bd_fault(xsave_buf))
+ if (mpx_handle_bd_fault())
goto exit_trap;
break; /* Success, it was handled */
case 1: /* Bound violation. */
- info = mpx_generate_siginfo(regs, xsave_buf);
+ info = mpx_generate_siginfo(regs);
if (IS_ERR(info)) {
/*
* We failed to decode the MPX instruction. Act as if
@@ -709,8 +707,8 @@ NOKPROBE_SYMBOL(do_debug);
static void math_error(struct pt_regs *regs, int error_code, int trapnr)
{
struct task_struct *task = current;
+ struct fpu *fpu = &task->thread.fpu;
siginfo_t info;
- unsigned short err;
char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
"simd exception";
@@ -718,8 +716,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
return;
conditional_sti(regs);
- if (!user_mode(regs))
- {
+ if (!user_mode(regs)) {
if (!fixup_exception(regs)) {
task->thread.error_code = error_code;
task->thread.trap_nr = trapnr;
@@ -731,62 +728,20 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
/*
* Save the info for the exception handler and clear the error.
*/
- unlazy_fpu(task);
- task->thread.trap_nr = trapnr;
+ fpu__save(fpu);
+
+ task->thread.trap_nr = trapnr;
task->thread.error_code = error_code;
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
- if (trapnr == X86_TRAP_MF) {
- unsigned short cwd, swd;
- /*
- * (~cwd & swd) will mask out exceptions that are not set to unmasked
- * status. 0x3f is the exception bits in these regs, 0x200 is the
- * C1 reg you need in case of a stack fault, 0x040 is the stack
- * fault bit. We should only be taking one exception at a time,
- * so if this combination doesn't produce any single exception,
- * then we have a bad program that isn't synchronizing its FPU usage
- * and it will suffer the consequences since we won't be able to
- * fully reproduce the context of the exception
- */
- cwd = get_fpu_cwd(task);
- swd = get_fpu_swd(task);
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
- err = swd & ~cwd;
- } else {
- /*
- * The SIMD FPU exceptions are handled a little differently, as there
- * is only a single status/control register. Thus, to determine which
- * unmasked exception was caught we must mask the exception mask bits
- * at 0x1f80, and then use these to mask the exception bits at 0x3f.
- */
- unsigned short mxcsr = get_fpu_mxcsr(task);
- err = ~(mxcsr >> 7) & mxcsr;
- }
+ info.si_code = fpu__exception_code(fpu, trapnr);
- if (err & 0x001) { /* Invalid op */
- /*
- * swd & 0x240 == 0x040: Stack Underflow
- * swd & 0x240 == 0x240: Stack Overflow
- * User must clear the SF bit (0x40) if set
- */
- info.si_code = FPE_FLTINV;
- } else if (err & 0x004) { /* Divide by Zero */
- info.si_code = FPE_FLTDIV;
- } else if (err & 0x008) { /* Overflow */
- info.si_code = FPE_FLTOVF;
- } else if (err & 0x012) { /* Denormal, Underflow */
- info.si_code = FPE_FLTUND;
- } else if (err & 0x020) { /* Precision */
- info.si_code = FPE_FLTRES;
- } else {
- /*
- * If we're using IRQ 13, or supposedly even some trap
- * X86_TRAP_MF implementations, it's possible
- * we get a spurious trap, which is not an error.
- */
+ /* Retry when we get spurious exceptions: */
+ if (!info.si_code)
return;
- }
+
force_sig_info(SIGFPE, &info, task);
}
@@ -813,62 +768,8 @@ dotraplinkage void
do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
{
conditional_sti(regs);
-#if 0
- /* No need to warn about this any longer. */
- pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n");
-#endif
-}
-
-asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void)
-{
}
-asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
-{
-}
-
-/*
- * 'math_state_restore()' saves the current math information in the
- * old math state array, and gets the new ones from the current task
- *
- * Careful.. There are problems with IBM-designed IRQ13 behaviour.
- * Don't touch unless you *really* know how it works.
- *
- * Must be called with kernel preemption disabled (eg with local
- * local interrupts as in the case of do_device_not_available).
- */
-void math_state_restore(void)
-{
- struct task_struct *tsk = current;
-
- if (!tsk_used_math(tsk)) {
- local_irq_enable();
- /*
- * does a slab alloc which can sleep
- */
- if (init_fpu(tsk)) {
- /*
- * ran out of memory!
- */
- do_group_exit(SIGKILL);
- return;
- }
- local_irq_disable();
- }
-
- /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */
- kernel_fpu_disable();
- __thread_fpu_begin(tsk);
- if (unlikely(restore_fpu_checking(tsk))) {
- fpu_reset_state(tsk);
- force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
- } else {
- tsk->thread.fpu_counter++;
- }
- kernel_fpu_enable();
-}
-EXPORT_SYMBOL_GPL(math_state_restore);
-
dotraplinkage void
do_device_not_available(struct pt_regs *regs, long error_code)
{
@@ -889,7 +790,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
return;
}
#endif
- math_state_restore(); /* interrupts still off */
+ fpu__restore(&current->thread.fpu); /* interrupts still off */
#ifdef CONFIG_X86_32
conditional_sti(regs);
#endif
@@ -992,13 +893,13 @@ void __init trap_init(void)
set_bit(i, used_vectors);
#ifdef CONFIG_IA32_EMULATION
- set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
+ set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat);
set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
#ifdef CONFIG_X86_32
- set_system_trap_gate(SYSCALL_VECTOR, &system_call);
- set_bit(SYSCALL_VECTOR, used_vectors);
+ set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32);
+ set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
/*
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 26488487bc61..dd8d0791dfb5 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -113,7 +113,7 @@ static void check_tsc_warp(unsigned int timeout)
*/
static inline unsigned int loop_timeout(int cpu)
{
- return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20;
+ return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20;
}
/*
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 0b81ad67da07..66476244731e 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -29,6 +29,7 @@
#include <linux/kdebug.h>
#include <asm/processor.h>
#include <asm/insn.h>
+#include <asm/mmu_context.h>
/* Post-execution fixups. */
@@ -312,11 +313,6 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
}
#ifdef CONFIG_X86_64
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
- return !config_enabled(CONFIG_IA32_EMULATION) ||
- !(mm->context.ia32_compat == TIF_IA32);
-}
/*
* If arch_uprobe->insn doesn't use rip-relative addressing, return
* immediately. Otherwise, rewrite the instruction so that it accesses
@@ -497,10 +493,6 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
}
}
#else /* 32-bit: */
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
- return false;
-}
/*
* No RIP-relative addressing on 32-bit
*/
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 37d8fa4438f0..a0695be19864 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -75,7 +75,5 @@ EXPORT_SYMBOL(native_load_gs_index);
#ifdef CONFIG_PREEMPT
EXPORT_SYMBOL(___preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
-EXPORT_SYMBOL(___preempt_schedule_context);
-#endif
+EXPORT_SYMBOL(___preempt_schedule_notrace);
#endif
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 234b0722de53..3839628d962e 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -11,7 +11,6 @@
#include <asm/bios_ebda.h>
#include <asm/paravirt.h>
#include <asm/pci_x86.h>
-#include <asm/pci.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#include <asm/apic.h>
@@ -111,11 +110,9 @@ EXPORT_SYMBOL_GPL(x86_platform);
#if defined(CONFIG_PCI_MSI)
struct x86_msi_ops x86_msi = {
.setup_msi_irqs = native_setup_msi_irqs,
- .compose_msi_msg = native_compose_msi_msg,
.teardown_msi_irq = native_teardown_msi_irq,
.teardown_msi_irqs = default_teardown_msi_irqs,
.restore_msi_irqs = default_restore_msi_irqs,
- .setup_hpet_msi = default_setup_hpet_msi,
};
/* MSI arch specific hooks */
@@ -141,13 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
#endif
struct x86_io_apic_ops x86_io_apic_ops = {
- .init = native_io_apic_init_mappings,
.read = native_io_apic_read,
- .write = native_io_apic_write,
- .modify = native_io_apic_modify,
.disable = native_disable_io_apic,
- .print_entries = native_io_apic_print_entries,
- .set_affinity = native_ioapic_set_affinity,
- .setup_entry = native_setup_ioapic_entry,
- .eoi_ioapic_pin = native_eoi_ioapic_pin,
};
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
deleted file mode 100644
index 87a815b85f3e..000000000000
--- a/arch/x86/kernel/xsave.c
+++ /dev/null
@@ -1,724 +0,0 @@
-/*
- * xsave/xrstor support.
- *
- * Author: Suresh Siddha <suresh.b.siddha@intel.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/bootmem.h>
-#include <linux/compat.h>
-#include <linux/cpu.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/sigframe.h>
-#include <asm/tlbflush.h>
-#include <asm/xcr.h>
-
-/*
- * Supported feature mask by the CPU and the kernel.
- */
-u64 pcntxt_mask;
-
-/*
- * Represents init state for the supported extended state.
- */
-struct xsave_struct *init_xstate_buf;
-
-static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
-static unsigned int *xstate_offsets, *xstate_sizes;
-static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8];
-static unsigned int xstate_features;
-
-/*
- * If a processor implementation discern that a processor state component is
- * in its initialized state it may modify the corresponding bit in the
- * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory
- * layout in the case of xsaveopt. While presenting the xstate information to
- * the user, we always ensure that the memory layout of a feature will be in
- * the init state if the corresponding header bit is zero. This is to ensure
- * that the user doesn't see some stale state in the memory layout during
- * signal handling, debugging etc.
- */
-void __sanitize_i387_state(struct task_struct *tsk)
-{
- struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
- int feature_bit = 0x2;
- u64 xstate_bv;
-
- if (!fx)
- return;
-
- xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
-
- /*
- * None of the feature bits are in init state. So nothing else
- * to do for us, as the memory layout is up to date.
- */
- if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
- return;
-
- /*
- * FP is in init state
- */
- if (!(xstate_bv & XSTATE_FP)) {
- fx->cwd = 0x37f;
- fx->swd = 0;
- fx->twd = 0;
- fx->fop = 0;
- fx->rip = 0;
- fx->rdp = 0;
- memset(&fx->st_space[0], 0, 128);
- }
-
- /*
- * SSE is in init state
- */
- if (!(xstate_bv & XSTATE_SSE))
- memset(&fx->xmm_space[0], 0, 256);
-
- xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2;
-
- /*
- * Update all the other memory layouts for which the corresponding
- * header bit is in the init state.
- */
- while (xstate_bv) {
- if (xstate_bv & 0x1) {
- int offset = xstate_offsets[feature_bit];
- int size = xstate_sizes[feature_bit];
-
- memcpy(((void *) fx) + offset,
- ((void *) init_xstate_buf) + offset,
- size);
- }
-
- xstate_bv >>= 1;
- feature_bit++;
- }
-}
-
-/*
- * Check for the presence of extended state information in the
- * user fpstate pointer in the sigcontext.
- */
-static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
- void __user *fpstate,
- struct _fpx_sw_bytes *fx_sw)
-{
- int min_xstate_size = sizeof(struct i387_fxsave_struct) +
- sizeof(struct xsave_hdr_struct);
- unsigned int magic2;
-
- if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
- return -1;
-
- /* Check for the first magic field and other error scenarios. */
- if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
- fx_sw->xstate_size < min_xstate_size ||
- fx_sw->xstate_size > xstate_size ||
- fx_sw->xstate_size > fx_sw->extended_size)
- return -1;
-
- /*
- * Check for the presence of second magic word at the end of memory
- * layout. This detects the case where the user just copied the legacy
- * fpstate layout with out copying the extended state information
- * in the memory layout.
- */
- if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
- || magic2 != FP_XSTATE_MAGIC2)
- return -1;
-
- return 0;
-}
-
-/*
- * Signal frame handlers.
- */
-static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
-{
- if (use_fxsr()) {
- struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
- struct user_i387_ia32_struct env;
- struct _fpstate_ia32 __user *fp = buf;
-
- convert_from_fxsr(&env, tsk);
-
- if (__copy_to_user(buf, &env, sizeof(env)) ||
- __put_user(xsave->i387.swd, &fp->status) ||
- __put_user(X86_FXSR_MAGIC, &fp->magic))
- return -1;
- } else {
- struct i387_fsave_struct __user *fp = buf;
- u32 swd;
- if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
- return -1;
- }
-
- return 0;
-}
-
-static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
-{
- struct xsave_struct __user *x = buf;
- struct _fpx_sw_bytes *sw_bytes;
- u32 xstate_bv;
- int err;
-
- /* Setup the bytes not touched by the [f]xsave and reserved for SW. */
- sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
- err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
-
- if (!use_xsave())
- return err;
-
- err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
-
- /*
- * Read the xstate_bv which we copied (directly from the cpu or
- * from the state in task struct) to the user buffers.
- */
- err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
-
- /*
- * For legacy compatible, we always set FP/SSE bits in the bit
- * vector while saving the state to the user context. This will
- * enable us capturing any changes(during sigreturn) to
- * the FP/SSE bits by the legacy applications which don't touch
- * xstate_bv in the xsave header.
- *
- * xsave aware apps can change the xstate_bv in the xsave
- * header as well as change any contents in the memory layout.
- * xrestore as part of sigreturn will capture all the changes.
- */
- xstate_bv |= XSTATE_FPSSE;
-
- err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
-
- return err;
-}
-
-static inline int save_user_xstate(struct xsave_struct __user *buf)
-{
- int err;
-
- if (use_xsave())
- err = xsave_user(buf);
- else if (use_fxsr())
- err = fxsave_user((struct i387_fxsave_struct __user *) buf);
- else
- err = fsave_user((struct i387_fsave_struct __user *) buf);
-
- if (unlikely(err) && __clear_user(buf, xstate_size))
- err = -EFAULT;
- return err;
-}
-
-/*
- * Save the fpu, extended register state to the user signal frame.
- *
- * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
- * state is copied.
- * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
- *
- * buf == buf_fx for 64-bit frames and 32-bit fsave frame.
- * buf != buf_fx for 32-bit frames with fxstate.
- *
- * If the fpu, extended register state is live, save the state directly
- * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
- * copy the thread's fpu state to the user frame starting at 'buf_fx'.
- *
- * If this is a 32-bit frame with fxstate, put a fsave header before
- * the aligned state at 'buf_fx'.
- *
- * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
- * indicating the absence/presence of the extended state to the user.
- */
-int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
-{
- struct xsave_struct *xsave = &current->thread.fpu.state->xsave;
- struct task_struct *tsk = current;
- int ia32_fxstate = (buf != buf_fx);
-
- ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
- config_enabled(CONFIG_IA32_EMULATION));
-
- if (!access_ok(VERIFY_WRITE, buf, size))
- return -EACCES;
-
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_get(current, NULL, 0,
- sizeof(struct user_i387_ia32_struct), NULL,
- (struct _fpstate_ia32 __user *) buf) ? -1 : 1;
-
- if (user_has_fpu()) {
- /* Save the live register state to the user directly. */
- if (save_user_xstate(buf_fx))
- return -1;
- /* Update the thread's fxstate to save the fsave header. */
- if (ia32_fxstate)
- fpu_fxsave(&tsk->thread.fpu);
- } else {
- sanitize_i387_state(tsk);
- if (__copy_to_user(buf_fx, xsave, xstate_size))
- return -1;
- }
-
- /* Save the fsave header for the 32-bit frames. */
- if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
- return -1;
-
- if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
- return -1;
-
- return 0;
-}
-
-static inline void
-sanitize_restored_xstate(struct task_struct *tsk,
- struct user_i387_ia32_struct *ia32_env,
- u64 xstate_bv, int fx_only)
-{
- struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
- struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
-
- if (use_xsave()) {
- /* These bits must be zero. */
- memset(xsave_hdr->reserved, 0, 48);
-
- /*
- * Init the state that is not present in the memory
- * layout and not enabled by the OS.
- */
- if (fx_only)
- xsave_hdr->xstate_bv = XSTATE_FPSSE;
- else
- xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
- }
-
- if (use_fxsr()) {
- /*
- * mscsr reserved bits must be masked to zero for security
- * reasons.
- */
- xsave->i387.mxcsr &= mxcsr_feature_mask;
-
- convert_to_fxsr(tsk, ia32_env);
- }
-}
-
-/*
- * Restore the extended state if present. Otherwise, restore the FP/SSE state.
- */
-static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
-{
- if (use_xsave()) {
- if ((unsigned long)buf % 64 || fx_only) {
- u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
- xrstor_state(init_xstate_buf, init_bv);
- return fxrstor_user(buf);
- } else {
- u64 init_bv = pcntxt_mask & ~xbv;
- if (unlikely(init_bv))
- xrstor_state(init_xstate_buf, init_bv);
- return xrestore_user(buf, xbv);
- }
- } else if (use_fxsr()) {
- return fxrstor_user(buf);
- } else
- return frstor_user(buf);
-}
-
-int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
-{
- int ia32_fxstate = (buf != buf_fx);
- struct task_struct *tsk = current;
- int state_size = xstate_size;
- u64 xstate_bv = 0;
- int fx_only = 0;
-
- ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
- config_enabled(CONFIG_IA32_EMULATION));
-
- if (!buf) {
- fpu_reset_state(tsk);
- return 0;
- }
-
- if (!access_ok(VERIFY_READ, buf, size))
- return -EACCES;
-
- if (!used_math() && init_fpu(tsk))
- return -1;
-
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_set(current, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- NULL, buf) != 0;
-
- if (use_xsave()) {
- struct _fpx_sw_bytes fx_sw_user;
- if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
- /*
- * Couldn't find the extended state information in the
- * memory layout. Restore just the FP/SSE and init all
- * the other extended state.
- */
- state_size = sizeof(struct i387_fxsave_struct);
- fx_only = 1;
- } else {
- state_size = fx_sw_user.xstate_size;
- xstate_bv = fx_sw_user.xstate_bv;
- }
- }
-
- if (ia32_fxstate) {
- /*
- * For 32-bit frames with fxstate, copy the user state to the
- * thread's fpu state, reconstruct fxstate from the fsave
- * header. Sanitize the copied state etc.
- */
- struct fpu *fpu = &tsk->thread.fpu;
- struct user_i387_ia32_struct env;
- int err = 0;
-
- /*
- * Drop the current fpu which clears used_math(). This ensures
- * that any context-switch during the copy of the new state,
- * avoids the intermediate state from getting restored/saved.
- * Thus avoiding the new restored state from getting corrupted.
- * We will be ready to restore/save the state only after
- * set_used_math() is again set.
- */
- drop_fpu(tsk);
-
- if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
- __copy_from_user(&env, buf, sizeof(env))) {
- fpu_finit(fpu);
- err = -1;
- } else {
- sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
- }
-
- set_used_math();
- if (use_eager_fpu()) {
- preempt_disable();
- math_state_restore();
- preempt_enable();
- }
-
- return err;
- } else {
- /*
- * For 64-bit frames and 32-bit fsave frames, restore the user
- * state to the registers directly (with exceptions handled).
- */
- user_fpu_begin();
- if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
- fpu_reset_state(tsk);
- return -1;
- }
- }
-
- return 0;
-}
-
-/*
- * Prepare the SW reserved portion of the fxsave memory layout, indicating
- * the presence of the extended state information in the memory layout
- * pointed by the fpstate pointer in the sigcontext.
- * This will be saved when ever the FP and extended state context is
- * saved on the user stack during the signal handler delivery to the user.
- */
-static void prepare_fx_sw_frame(void)
-{
- int fsave_header_size = sizeof(struct i387_fsave_struct);
- int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
-
- if (config_enabled(CONFIG_X86_32))
- size += fsave_header_size;
-
- fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
- fx_sw_reserved.extended_size = size;
- fx_sw_reserved.xstate_bv = pcntxt_mask;
- fx_sw_reserved.xstate_size = xstate_size;
-
- if (config_enabled(CONFIG_IA32_EMULATION)) {
- fx_sw_reserved_ia32 = fx_sw_reserved;
- fx_sw_reserved_ia32.extended_size += fsave_header_size;
- }
-}
-
-/*
- * Enable the extended processor state save/restore feature
- */
-static inline void xstate_enable(void)
-{
- cr4_set_bits(X86_CR4_OSXSAVE);
- xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-}
-
-/*
- * Record the offsets and sizes of different state managed by the xsave
- * memory layout.
- */
-static void __init setup_xstate_features(void)
-{
- int eax, ebx, ecx, edx, leaf = 0x2;
-
- xstate_features = fls64(pcntxt_mask);
- xstate_offsets = alloc_bootmem(xstate_features * sizeof(int));
- xstate_sizes = alloc_bootmem(xstate_features * sizeof(int));
-
- do {
- cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
-
- if (eax == 0)
- break;
-
- xstate_offsets[leaf] = ebx;
- xstate_sizes[leaf] = eax;
-
- leaf++;
- } while (1);
-}
-
-/*
- * This function sets up offsets and sizes of all extended states in
- * xsave area. This supports both standard format and compacted format
- * of the xsave aread.
- *
- * Input: void
- * Output: void
- */
-void setup_xstate_comp(void)
-{
- unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8];
- int i;
-
- /*
- * The FP xstates and SSE xstates are legacy states. They are always
- * in the fixed offsets in the xsave area in either compacted form
- * or standard form.
- */
- xstate_comp_offsets[0] = 0;
- xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space);
-
- if (!cpu_has_xsaves) {
- for (i = 2; i < xstate_features; i++) {
- if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
- xstate_comp_offsets[i] = xstate_offsets[i];
- xstate_comp_sizes[i] = xstate_sizes[i];
- }
- }
- return;
- }
-
- xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
- for (i = 2; i < xstate_features; i++) {
- if (test_bit(i, (unsigned long *)&pcntxt_mask))
- xstate_comp_sizes[i] = xstate_sizes[i];
- else
- xstate_comp_sizes[i] = 0;
-
- if (i > 2)
- xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
- + xstate_comp_sizes[i-1];
-
- }
-}
-
-/*
- * setup the xstate image representing the init state
- */
-static void __init setup_init_fpu_buf(void)
-{
- /*
- * Setup init_xstate_buf to represent the init state of
- * all the features managed by the xsave
- */
- init_xstate_buf = alloc_bootmem_align(xstate_size,
- __alignof__(struct xsave_struct));
- fx_finit(&init_xstate_buf->i387);
-
- if (!cpu_has_xsave)
- return;
-
- setup_xstate_features();
-
- if (cpu_has_xsaves) {
- init_xstate_buf->xsave_hdr.xcomp_bv =
- (u64)1 << 63 | pcntxt_mask;
- init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask;
- }
-
- /*
- * Init all the features state with header_bv being 0x0
- */
- xrstor_state_booting(init_xstate_buf, -1);
- /*
- * Dump the init state again. This is to identify the init state
- * of any feature which is not represented by all zero's.
- */
- xsave_state_booting(init_xstate_buf, -1);
-}
-
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
-static int __init eager_fpu_setup(char *s)
-{
- if (!strcmp(s, "on"))
- eagerfpu = ENABLE;
- else if (!strcmp(s, "off"))
- eagerfpu = DISABLE;
- else if (!strcmp(s, "auto"))
- eagerfpu = AUTO;
- return 1;
-}
-__setup("eagerfpu=", eager_fpu_setup);
-
-
-/*
- * Calculate total size of enabled xstates in XCR0/pcntxt_mask.
- */
-static void __init init_xstate_size(void)
-{
- unsigned int eax, ebx, ecx, edx;
- int i;
-
- if (!cpu_has_xsaves) {
- cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- xstate_size = ebx;
- return;
- }
-
- xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
- for (i = 2; i < 64; i++) {
- if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
- cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
- xstate_size += eax;
- }
- }
-}
-
-/*
- * Enable and initialize the xsave feature.
- */
-static void __init xstate_enable_boot_cpu(void)
-{
- unsigned int eax, ebx, ecx, edx;
-
- if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
- WARN(1, KERN_ERR "XSTATE_CPUID missing\n");
- return;
- }
-
- cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- pcntxt_mask = eax + ((u64)edx << 32);
-
- if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
- pr_err("FP/SSE not shown under xsave features 0x%llx\n",
- pcntxt_mask);
- BUG();
- }
-
- /*
- * Support only the state known to OS.
- */
- pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
-
- xstate_enable();
-
- /*
- * Recompute the context size for enabled features
- */
- init_xstate_size();
-
- update_regset_xstate_info(xstate_size, pcntxt_mask);
- prepare_fx_sw_frame();
- setup_init_fpu_buf();
-
- /* Auto enable eagerfpu for xsaveopt */
- if (cpu_has_xsaveopt && eagerfpu != DISABLE)
- eagerfpu = ENABLE;
-
- if (pcntxt_mask & XSTATE_EAGER) {
- if (eagerfpu == DISABLE) {
- pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n",
- pcntxt_mask & XSTATE_EAGER);
- pcntxt_mask &= ~XSTATE_EAGER;
- } else {
- eagerfpu = ENABLE;
- }
- }
-
- pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n",
- pcntxt_mask, xstate_size,
- cpu_has_xsaves ? "compacted form" : "standard form");
-}
-
-/*
- * For the very first instance, this calls xstate_enable_boot_cpu();
- * for all subsequent instances, this calls xstate_enable().
- *
- * This is somewhat obfuscated due to the lack of powerful enough
- * overrides for the section checks.
- */
-void xsave_init(void)
-{
- static __refdata void (*next_func)(void) = xstate_enable_boot_cpu;
- void (*this_func)(void);
-
- if (!cpu_has_xsave)
- return;
-
- this_func = next_func;
- next_func = xstate_enable;
- this_func();
-}
-
-/*
- * setup_init_fpu_buf() is __init and it is OK to call it here because
- * init_xstate_buf will be unset only once during boot.
- */
-void __init_refok eager_fpu_init(void)
-{
- WARN_ON(used_math());
- current_thread_info()->status = 0;
-
- if (eagerfpu == ENABLE)
- setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
-
- if (!cpu_has_eager_fpu) {
- stts();
- return;
- }
-
- if (!init_xstate_buf)
- setup_init_fpu_buf();
-}
-
-/*
- * Given the xsave area and a state inside, this function returns the
- * address of the state.
- *
- * This is the API that is called to get xstate address in either
- * standard format or compacted format of xsave area.
- *
- * Inputs:
- * xsave: base address of the xsave area;
- * xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE,
- * etc.)
- * Output:
- * address of the state in the xsave area.
- */
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
-{
- int feature = fls64(xstate) - 1;
- if (!test_bit(feature, (unsigned long *)&pcntxt_mask))
- return NULL;
-
- return (void *)xsave + xstate_comp_offsets[feature];
-}
-EXPORT_SYMBOL_GPL(get_xsave_addr);
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 413a7bf9efbb..d8a1d56276e1 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -86,15 +86,16 @@ config KVM_MMU_AUDIT
auditing of KVM MMU events at runtime.
config KVM_DEVICE_ASSIGNMENT
- bool "KVM legacy PCI device assignment support"
+ bool "KVM legacy PCI device assignment support (DEPRECATED)"
depends on KVM && PCI && IOMMU_API
- default y
+ default n
---help---
Provide support for legacy PCI device assignment through KVM. The
kernel now also supports a full featured userspace device driver
- framework through VFIO, which supersedes much of this support.
+ framework through VFIO, which supersedes this support and provides
+ better security.
- If unsure, say Y.
+ If unsure, say N.
# OK, it's a little counter-intuitive to do this, but it puts it neatly under
# the virtualization menu.
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 16e8f962eaad..67d215cb8953 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,10 +12,10 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
- i8254.o ioapic.o irq_comm.o cpuid.o pmu.o
+ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o
kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o
-kvm-intel-y += vmx.o
-kvm-amd-y += svm.o
+kvm-intel-y += vmx.o pmu_intel.o
+kvm-amd-y += svm.o pmu_amd.o
obj-$(CONFIG_KVM) += kvm.o
obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 59b69f6a2844..64dd46793099 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,12 +16,14 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
+#include <asm/fpu/internal.h> /* For use_eager_fpu. Ugh! */
#include <asm/user.h>
-#include <asm/xsave.h>
+#include <asm/fpu/xstate.h>
#include "cpuid.h"
#include "lapic.h"
#include "mmu.h"
#include "trace.h"
+#include "pmu.h"
static u32 xstate_required_size(u64 xstate_bv, bool compacted)
{
@@ -95,6 +97,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
+ vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+
/*
* The existing code assumes virtual address is 48-bit in the canonical
* address checks; exit if it is ever changed.
@@ -107,7 +111,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
/* Update physical-address width */
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
- kvm_pmu_cpuid_update(vcpu);
+ kvm_pmu_refresh(vcpu);
return 0;
}
@@ -411,6 +415,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
}
break;
}
+ case 6: /* Thermal management */
+ entry->eax = 0x4; /* allow ARAT */
+ entry->ebx = 0;
+ entry->ecx = 0;
+ entry->edx = 0;
+ break;
case 7: {
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* Mask ebx against host capability word 9 */
@@ -587,7 +597,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
break;
case 3: /* Processor serial number */
case 5: /* MONITOR/MWAIT */
- case 6: /* Thermal management */
case 0xC0000002:
case 0xC0000003:
case 0xC0000004:
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index c3b1ad9fca81..dd05b9cef6ae 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -70,6 +70,14 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
}
+static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+ return best && (best->edx & bit(X86_FEATURE_LM));
+}
+
static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
@@ -117,4 +125,12 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
best = kvm_find_cpuid_entry(vcpu, 7, 0);
return best && (best->ebx & bit(X86_FEATURE_RTM));
}
+
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 7, 0);
+ return best && (best->ebx & bit(X86_FEATURE_MPX));
+}
#endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 630bcb0d7a04..e7a4fde5d631 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -25,6 +25,7 @@
#include <linux/module.h>
#include <asm/kvm_emulate.h>
#include <linux/stringify.h>
+#include <asm/debugreg.h>
#include "x86.h"
#include "tss.h"
@@ -523,13 +524,9 @@ static void masked_increment(ulong *reg, ulong mask, int inc)
static inline void
register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
{
- ulong mask;
+ ulong *preg = reg_rmw(ctxt, reg);
- if (ctxt->ad_bytes == sizeof(unsigned long))
- mask = ~0UL;
- else
- mask = ad_mask(ctxt);
- masked_increment(reg_rmw(ctxt, reg), mask, inc);
+ assign_register(preg, *preg + inc, ctxt->ad_bytes);
}
static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
@@ -2262,6 +2259,260 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
return rc;
}
+static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
+{
+ u32 eax, ebx, ecx, edx;
+
+ eax = 0x80000001;
+ ecx = 0;
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ return edx & bit(X86_FEATURE_LM);
+}
+
+#define GET_SMSTATE(type, smbase, offset) \
+ ({ \
+ type __val; \
+ int r = ctxt->ops->read_std(ctxt, smbase + offset, &__val, \
+ sizeof(__val), NULL); \
+ if (r != X86EMUL_CONTINUE) \
+ return X86EMUL_UNHANDLEABLE; \
+ __val; \
+ })
+
+static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
+{
+ desc->g = (flags >> 23) & 1;
+ desc->d = (flags >> 22) & 1;
+ desc->l = (flags >> 21) & 1;
+ desc->avl = (flags >> 20) & 1;
+ desc->p = (flags >> 15) & 1;
+ desc->dpl = (flags >> 13) & 3;
+ desc->s = (flags >> 12) & 1;
+ desc->type = (flags >> 8) & 15;
+}
+
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+{
+ struct desc_struct desc;
+ int offset;
+ u16 selector;
+
+ selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+
+ if (n < 3)
+ offset = 0x7f84 + n * 12;
+ else
+ offset = 0x7f2c + (n - 3) * 12;
+
+ set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+ ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
+ return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+{
+ struct desc_struct desc;
+ int offset;
+ u16 selector;
+ u32 base3;
+
+ offset = 0x7e00 + n * 16;
+
+ selector = GET_SMSTATE(u16, smbase, offset);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
+ set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
+ base3 = GET_SMSTATE(u32, smbase, offset + 12);
+
+ ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
+ return X86EMUL_CONTINUE;
+}
+
+static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
+ u64 cr0, u64 cr4)
+{
+ int bad;
+
+ /*
+ * First enable PAE, long mode needs it before CR0.PG = 1 is set.
+ * Then enable protected mode. However, PCID cannot be enabled
+ * if EFER.LMA=0, so set it separately.
+ */
+ bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+
+ bad = ctxt->ops->set_cr(ctxt, 0, cr0);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+
+ if (cr4 & X86_CR4_PCIDE) {
+ bad = ctxt->ops->set_cr(ctxt, 4, cr4);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+ }
+
+ return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+ struct desc_struct desc;
+ struct desc_ptr dt;
+ u16 selector;
+ u32 val, cr0, cr4;
+ int i;
+
+ cr0 = GET_SMSTATE(u32, smbase, 0x7ffc);
+ ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+ ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0);
+
+ for (i = 0; i < 8; i++)
+ *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+
+ val = GET_SMSTATE(u32, smbase, 0x7fcc);
+ ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+ val = GET_SMSTATE(u32, smbase, 0x7fc8);
+ ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+ selector = GET_SMSTATE(u32, smbase, 0x7fc4);
+ set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c));
+ ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
+
+ selector = GET_SMSTATE(u32, smbase, 0x7fc0);
+ set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78));
+ ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
+
+ dt.address = GET_SMSTATE(u32, smbase, 0x7f74);
+ dt.size = GET_SMSTATE(u32, smbase, 0x7f70);
+ ctxt->ops->set_gdt(ctxt, &dt);
+
+ dt.address = GET_SMSTATE(u32, smbase, 0x7f58);
+ dt.size = GET_SMSTATE(u32, smbase, 0x7f54);
+ ctxt->ops->set_idt(ctxt, &dt);
+
+ for (i = 0; i < 6; i++) {
+ int r = rsm_load_seg_32(ctxt, smbase, i);
+ if (r != X86EMUL_CONTINUE)
+ return r;
+ }
+
+ cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+
+ return rsm_enter_protected_mode(ctxt, cr0, cr4);
+}
+
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+ struct desc_struct desc;
+ struct desc_ptr dt;
+ u64 val, cr0, cr4;
+ u32 base3;
+ u16 selector;
+ int i;
+
+ for (i = 0; i < 16; i++)
+ *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+
+ ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78);
+ ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+
+ val = GET_SMSTATE(u32, smbase, 0x7f68);
+ ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+ val = GET_SMSTATE(u32, smbase, 0x7f60);
+ ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+ cr0 = GET_SMSTATE(u64, smbase, 0x7f58);
+ ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u64, smbase, 0x7f50));
+ cr4 = GET_SMSTATE(u64, smbase, 0x7f48);
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
+ val = GET_SMSTATE(u64, smbase, 0x7ed0);
+ ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
+
+ selector = GET_SMSTATE(u32, smbase, 0x7e90);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94));
+ set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98));
+ base3 = GET_SMSTATE(u32, smbase, 0x7e9c);
+ ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
+
+ dt.size = GET_SMSTATE(u32, smbase, 0x7e84);
+ dt.address = GET_SMSTATE(u64, smbase, 0x7e88);
+ ctxt->ops->set_idt(ctxt, &dt);
+
+ selector = GET_SMSTATE(u32, smbase, 0x7e70);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74));
+ set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78));
+ base3 = GET_SMSTATE(u32, smbase, 0x7e7c);
+ ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
+
+ dt.size = GET_SMSTATE(u32, smbase, 0x7e64);
+ dt.address = GET_SMSTATE(u64, smbase, 0x7e68);
+ ctxt->ops->set_gdt(ctxt, &dt);
+
+ for (i = 0; i < 6; i++) {
+ int r = rsm_load_seg_64(ctxt, smbase, i);
+ if (r != X86EMUL_CONTINUE)
+ return r;
+ }
+
+ return rsm_enter_protected_mode(ctxt, cr0, cr4);
+}
+
+static int em_rsm(struct x86_emulate_ctxt *ctxt)
+{
+ unsigned long cr0, cr4, efer;
+ u64 smbase;
+ int ret;
+
+ if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0)
+ return emulate_ud(ctxt);
+
+ /*
+ * Get back to real mode, to prepare a safe state in which to load
+ * CR0/CR3/CR4/EFER. Also this will ensure that addresses passed
+ * to read_std/write_std are not virtual.
+ *
+ * CR4.PCIDE must be zero, because it is a 64-bit mode only feature.
+ */
+ cr0 = ctxt->ops->get_cr(ctxt, 0);
+ if (cr0 & X86_CR0_PE)
+ ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PAE)
+ ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
+ efer = 0;
+ ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+
+ smbase = ctxt->ops->get_smbase(ctxt);
+ if (emulator_has_longmode(ctxt))
+ ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+ else
+ ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+
+ if (ret != X86EMUL_CONTINUE) {
+ /* FIXME: should triple fault */
+ return X86EMUL_UNHANDLEABLE;
+ }
+
+ if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+ ctxt->ops->set_nmi_mask(ctxt, false);
+
+ ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK;
+ ctxt->emul_flags &= ~X86EMUL_SMM_MASK;
+ return X86EMUL_CONTINUE;
+}
+
static void
setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
struct desc_struct *cs, struct desc_struct *ss)
@@ -2573,6 +2824,30 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt,
return true;
}
+static void string_registers_quirk(struct x86_emulate_ctxt *ctxt)
+{
+ /*
+ * Intel CPUs mask the counter and pointers in quite strange
+ * manner when ECX is zero due to REP-string optimizations.
+ */
+#ifdef CONFIG_X86_64
+ if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt))
+ return;
+
+ *reg_write(ctxt, VCPU_REGS_RCX) = 0;
+
+ switch (ctxt->b) {
+ case 0xa4: /* movsb */
+ case 0xa5: /* movsd/w */
+ *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1;
+ /* fall through */
+ case 0xaa: /* stosb */
+ case 0xab: /* stosd/w */
+ *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1;
+ }
+#endif
+}
+
static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt,
struct tss_segment_16 *tss)
{
@@ -2849,7 +3124,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
ulong old_tss_base =
ops->get_cached_segment_base(ctxt, VCPU_SREG_TR);
u32 desc_limit;
- ulong desc_addr;
+ ulong desc_addr, dr7;
/* FIXME: old_tss_base == ~0 ? */
@@ -2934,6 +3209,9 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
ret = em_push(ctxt);
}
+ ops->get_dr(ctxt, 7, &dr7);
+ ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN));
+
return ret;
}
@@ -3840,7 +4118,7 @@ static const struct opcode group5[] = {
F(DstMem | SrcNone | Lock, em_inc),
F(DstMem | SrcNone | Lock, em_dec),
I(SrcMem | NearBranch, em_call_near_abs),
- I(SrcMemFAddr | ImplicitOps | Stack, em_call_far),
+ I(SrcMemFAddr | ImplicitOps, em_call_far),
I(SrcMem | NearBranch, em_jmp_abs),
I(SrcMemFAddr | ImplicitOps, em_jmp_far),
I(SrcMem | Stack, em_push), D(Undefined),
@@ -4173,7 +4451,7 @@ static const struct opcode twobyte_table[256] = {
F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
/* 0xA8 - 0xAF */
I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
- DI(ImplicitOps, rsm),
+ II(No64 | EmulateOnUD | ImplicitOps, em_rsm, rsm),
F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
@@ -4871,7 +5149,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
fetch_possible_mmx_operand(ctxt, &ctxt->dst);
}
- if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
+ if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
rc = emulator_check_intercept(ctxt, ctxt->intercept,
X86_ICPT_PRE_EXCEPT);
if (rc != X86EMUL_CONTINUE)
@@ -4900,7 +5178,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
goto done;
}
- if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
+ if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
rc = emulator_check_intercept(ctxt, ctxt->intercept,
X86_ICPT_POST_EXCEPT);
if (rc != X86EMUL_CONTINUE)
@@ -4910,6 +5188,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
if (ctxt->rep_prefix && (ctxt->d & String)) {
/* All REP prefixes have the same first termination condition */
if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
+ string_registers_quirk(ctxt);
ctxt->eip = ctxt->_eip;
ctxt->eflags &= ~X86_EFLAGS_RF;
goto done;
@@ -4953,7 +5232,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
special_insn:
- if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
+ if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
rc = emulator_check_intercept(ctxt, ctxt->intercept,
X86_ICPT_POST_MEMACCESS);
if (rc != X86EMUL_CONTINUE)
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 28146f03c514..856f79105bb5 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -349,6 +349,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
irqe.delivery_mode = entry->fields.delivery_mode << 8;
irqe.level = 1;
irqe.shorthand = 0;
+ irqe.msi_redir_hint = false;
if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
ioapic->irr_delivered |= 1 << irq;
@@ -637,11 +638,9 @@ void kvm_ioapic_destroy(struct kvm *kvm)
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
cancel_delayed_work_sync(&ioapic->eoi_inject);
- if (ioapic) {
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
- kvm->arch.vioapic = NULL;
- kfree(ioapic);
- }
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
+ kvm->arch.vioapic = NULL;
+ kfree(ioapic);
}
int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 72298b3ac025..9efff9e5b58c 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -31,6 +31,8 @@
#include "ioapic.h"
+#include "lapic.h"
+
static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level,
bool line_status)
@@ -48,11 +50,6 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
line_status);
}
-inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
-{
- return irq->delivery_mode == APIC_DM_LOWEST;
-}
-
int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq, unsigned long *dest_map)
{
@@ -60,7 +57,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_vcpu *vcpu, *lowest = NULL;
if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
- kvm_is_dm_lowest_prio(irq)) {
+ kvm_lowest_prio_delivery(irq)) {
printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
irq->delivery_mode = APIC_DM_FIXED;
}
@@ -76,7 +73,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
irq->dest_id, irq->dest_mode))
continue;
- if (!kvm_is_dm_lowest_prio(irq)) {
+ if (!kvm_lowest_prio_delivery(irq)) {
if (r < 0)
r = 0;
r += kvm_apic_set_irq(vcpu, irq, dest_map);
@@ -106,9 +103,10 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
irq->delivery_mode = e->msi.data & 0x700;
+ irq->msi_redir_hint = ((e->msi.address_lo
+ & MSI_ADDR_REDIRECTION_LOWPRI) > 0);
irq->level = 1;
irq->shorthand = 0;
- /* TODO Deal with RH bit of MSI message address */
}
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 544076c4f44b..e1e89ee4af75 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -99,4 +99,9 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu)
return vcpu->arch.hflags & HF_GUEST_MASK;
}
+static inline bool is_smm(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.hflags & HF_SMM_MASK;
+}
+
#endif
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 629af0f1c5c4..36e9de1b4127 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -240,6 +240,15 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
recalculate_apic_map(apic->vcpu->kvm);
}
+static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id)
+{
+ u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+
+ apic_set_reg(apic, APIC_ID, id << 24);
+ apic_set_reg(apic, APIC_LDR, ldr);
+ recalculate_apic_map(apic->vcpu->kvm);
+}
+
static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
{
return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
@@ -728,7 +737,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
dst = map->logical_map[cid];
- if (irq->delivery_mode == APIC_DM_LOWEST) {
+ if (kvm_lowest_prio_delivery(irq)) {
int l = -1;
for_each_set_bit(i, &bitmap, 16) {
if (!dst[i])
@@ -799,7 +808,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
break;
case APIC_DM_SMI:
- apic_debug("Ignoring guest SMI\n");
+ result = 1;
+ kvm_make_request(KVM_REQ_SMI, vcpu);
+ kvm_vcpu_kick(vcpu);
break;
case APIC_DM_NMI:
@@ -914,9 +925,10 @@ static void apic_send_ipi(struct kvm_lapic *apic)
irq.vector = icr_low & APIC_VECTOR_MASK;
irq.delivery_mode = icr_low & APIC_MODE_MASK;
irq.dest_mode = icr_low & APIC_DEST_MASK;
- irq.level = icr_low & APIC_INT_ASSERT;
+ irq.level = (icr_low & APIC_INT_ASSERT) != 0;
irq.trig_mode = icr_low & APIC_INT_LEVELTRIG;
irq.shorthand = icr_low & APIC_SHORT_MASK;
+ irq.msi_redir_hint = false;
if (apic_x2apic_mode(apic))
irq.dest_id = icr_high;
else
@@ -926,10 +938,11 @@ static void apic_send_ipi(struct kvm_lapic *apic)
apic_debug("icr_high 0x%x, icr_low 0x%x, "
"short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, "
- "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n",
+ "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x, "
+ "msi_redir_hint 0x%x\n",
icr_high, icr_low, irq.shorthand, irq.dest_id,
irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
- irq.vector);
+ irq.vector, irq.msi_redir_hint);
kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL);
}
@@ -1090,6 +1103,17 @@ static void update_divide_count(struct kvm_lapic *apic)
apic->divide_count);
}
+static void apic_update_lvtt(struct kvm_lapic *apic)
+{
+ u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) &
+ apic->lapic_timer.timer_mode_mask;
+
+ if (apic->lapic_timer.timer_mode != timer_mode) {
+ apic->lapic_timer.timer_mode = timer_mode;
+ hrtimer_cancel(&apic->lapic_timer.timer);
+ }
+}
+
static void apic_timer_expired(struct kvm_lapic *apic)
{
struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1298,6 +1322,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
apic_set_reg(apic, APIC_LVTT + 0x10 * i,
lvt_val | APIC_LVT_MASKED);
}
+ apic_update_lvtt(apic);
atomic_set(&apic->lapic_timer.pending, 0);
}
@@ -1330,20 +1355,13 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
break;
- case APIC_LVTT: {
- u32 timer_mode = val & apic->lapic_timer.timer_mode_mask;
-
- if (apic->lapic_timer.timer_mode != timer_mode) {
- apic->lapic_timer.timer_mode = timer_mode;
- hrtimer_cancel(&apic->lapic_timer.timer);
- }
-
+ case APIC_LVTT:
if (!kvm_apic_sw_enabled(apic))
val |= APIC_LVT_MASKED;
val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
apic_set_reg(apic, APIC_LVTT, val);
+ apic_update_lvtt(apic);
break;
- }
case APIC_TMICT:
if (apic_lvtt_tscdeadline(apic))
@@ -1536,9 +1554,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
if ((old_value ^ value) & X2APIC_ENABLE) {
if (value & X2APIC_ENABLE) {
- u32 id = kvm_apic_id(apic);
- u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
- kvm_apic_set_ldr(apic, ldr);
+ kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id);
kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true);
} else
kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false);
@@ -1557,7 +1573,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
}
-void kvm_lapic_reset(struct kvm_vcpu *vcpu)
+void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct kvm_lapic *apic;
int i;
@@ -1571,19 +1587,22 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
/* Stop the timer in case it's a reset to an active apic */
hrtimer_cancel(&apic->lapic_timer.timer);
- kvm_apic_set_id(apic, vcpu->vcpu_id);
+ if (!init_event)
+ kvm_apic_set_id(apic, vcpu->vcpu_id);
kvm_apic_set_version(apic->vcpu);
for (i = 0; i < APIC_LVT_NUM; i++)
apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
- apic->lapic_timer.timer_mode = 0;
- apic_set_reg(apic, APIC_LVT0,
- SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
+ apic_update_lvtt(apic);
+ if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED))
+ apic_set_reg(apic, APIC_LVT0,
+ SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
apic_set_reg(apic, APIC_DFR, 0xffffffffU);
apic_set_spiv(apic, 0xff);
apic_set_reg(apic, APIC_TASKPRI, 0);
- kvm_apic_set_ldr(apic, 0);
+ if (!apic_x2apic_mode(apic))
+ kvm_apic_set_ldr(apic, 0);
apic_set_reg(apic, APIC_ESR, 0);
apic_set_reg(apic, APIC_ICR, 0);
apic_set_reg(apic, APIC_ICR2, 0);
@@ -1712,7 +1731,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE);
static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
- kvm_lapic_reset(vcpu);
+ kvm_lapic_reset(vcpu, false);
kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
return 0;
@@ -1802,6 +1821,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
apic_update_ppr(apic);
hrtimer_cancel(&apic->lapic_timer.timer);
+ apic_update_lvtt(apic);
update_divide_count(apic);
start_apic_timer(apic);
apic->irr_pending = true;
@@ -2043,11 +2063,22 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
return;
- pe = xchg(&apic->pending_events, 0);
+ /*
+ * INITs are latched while in SMM. Because an SMM CPU cannot
+ * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs
+ * and delay processing of INIT until the next RSM.
+ */
+ if (is_smm(vcpu)) {
+ WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
+ if (test_bit(KVM_APIC_SIPI, &apic->pending_events))
+ clear_bit(KVM_APIC_SIPI, &apic->pending_events);
+ return;
+ }
+ pe = xchg(&apic->pending_events, 0);
if (test_bit(KVM_APIC_INIT, &pe)) {
- kvm_lapic_reset(vcpu);
- kvm_vcpu_reset(vcpu);
+ kvm_lapic_reset(vcpu, true);
+ kvm_vcpu_reset(vcpu, true);
if (kvm_vcpu_is_bsp(apic->vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 9d28383fc1e7..f2f4e10ab772 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -48,7 +48,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu);
int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu);
void kvm_apic_accept_events(struct kvm_vcpu *vcpu);
-void kvm_lapic_reset(struct kvm_vcpu *vcpu);
+void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event);
u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu);
@@ -150,7 +150,18 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm)
static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.apic->pending_events;
+ return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events;
+}
+
+static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
+{
+ return (irq->delivery_mode == APIC_DM_LOWEST ||
+ irq->msi_redir_hint);
+}
+
+static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
+{
+ return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
}
bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d43867c33bc4..f807496b62c2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -223,15 +223,15 @@ static unsigned int get_mmio_spte_generation(u64 spte)
return gen;
}
-static unsigned int kvm_current_mmio_generation(struct kvm *kvm)
+static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu)
{
- return kvm_memslots(kvm)->generation & MMIO_GEN_MASK;
+ return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK;
}
-static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
+static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
unsigned access)
{
- unsigned int gen = kvm_current_mmio_generation(kvm);
+ unsigned int gen = kvm_current_mmio_generation(vcpu);
u64 mask = generation_mmio_spte_mask(gen);
access &= ACC_WRITE_MASK | ACC_USER_MASK;
@@ -258,22 +258,22 @@ static unsigned get_mmio_spte_access(u64 spte)
return (spte & ~mask) & ~PAGE_MASK;
}
-static bool set_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
+static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
pfn_t pfn, unsigned access)
{
if (unlikely(is_noslot_pfn(pfn))) {
- mark_mmio_spte(kvm, sptep, gfn, access);
+ mark_mmio_spte(vcpu, sptep, gfn, access);
return true;
}
return false;
}
-static bool check_mmio_spte(struct kvm *kvm, u64 spte)
+static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
{
unsigned int kvm_gen, spte_gen;
- kvm_gen = kvm_current_mmio_generation(kvm);
+ kvm_gen = kvm_current_mmio_generation(vcpu);
spte_gen = get_mmio_spte_generation(spte);
trace_check_mmio_spte(spte, kvm_gen, spte_gen);
@@ -804,30 +804,36 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
return &slot->arch.lpage_info[level - 2][idx];
}
-static void account_shadowed(struct kvm *kvm, gfn_t gfn)
+static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
struct kvm_lpage_info *linfo;
+ gfn_t gfn;
int i;
- slot = gfn_to_memslot(kvm, gfn);
- for (i = PT_DIRECTORY_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ gfn = sp->gfn;
+ slots = kvm_memslots_for_spte_role(kvm, sp->role);
+ slot = __gfn_to_memslot(slots, gfn);
+ for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
linfo = lpage_info_slot(gfn, slot, i);
linfo->write_count += 1;
}
kvm->arch.indirect_shadow_pages++;
}
-static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
+static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
struct kvm_lpage_info *linfo;
+ gfn_t gfn;
int i;
- slot = gfn_to_memslot(kvm, gfn);
- for (i = PT_DIRECTORY_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ gfn = sp->gfn;
+ slots = kvm_memslots_for_spte_role(kvm, sp->role);
+ slot = __gfn_to_memslot(slots, gfn);
+ for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
linfo = lpage_info_slot(gfn, slot, i);
linfo->write_count -= 1;
WARN_ON(linfo->write_count < 0);
@@ -835,14 +841,14 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
kvm->arch.indirect_shadow_pages--;
}
-static int has_wrprotected_page(struct kvm *kvm,
+static int has_wrprotected_page(struct kvm_vcpu *vcpu,
gfn_t gfn,
int level)
{
struct kvm_memory_slot *slot;
struct kvm_lpage_info *linfo;
- slot = gfn_to_memslot(kvm, gfn);
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
if (slot) {
linfo = lpage_info_slot(gfn, slot, level);
return linfo->write_count;
@@ -858,8 +864,7 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
page_size = kvm_host_page_size(kvm, gfn);
- for (i = PT_PAGE_TABLE_LEVEL;
- i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) {
+ for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
if (page_size >= KVM_HPAGE_SIZE(i))
ret = i;
else
@@ -875,7 +880,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
{
struct kvm_memory_slot *slot;
- slot = gfn_to_memslot(vcpu->kvm, gfn);
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
if (!slot || slot->flags & KVM_MEMSLOT_INVALID ||
(no_dirty_log && slot->dirty_bitmap))
slot = NULL;
@@ -900,7 +905,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
- if (has_wrprotected_page(vcpu->kvm, large_gfn, level))
+ if (has_wrprotected_page(vcpu, large_gfn, level))
break;
return level - 1;
@@ -1042,12 +1047,14 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
/*
* Take gfn and return the reverse mapping to it.
*/
-static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
+static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp)
{
+ struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
- slot = gfn_to_memslot(kvm, gfn);
- return __gfn_to_rmap(gfn, level, slot);
+ slots = kvm_memslots_for_spte_role(kvm, sp->role);
+ slot = __gfn_to_memslot(slots, gfn);
+ return __gfn_to_rmap(gfn, sp->role.level, slot);
}
static bool rmap_can_add(struct kvm_vcpu *vcpu)
@@ -1065,7 +1072,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
sp = page_header(__pa(spte));
kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
- rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp);
return pte_list_add(vcpu, spte, rmapp);
}
@@ -1077,7 +1084,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
sp = page_header(__pa(spte));
gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
- rmapp = gfn_to_rmap(kvm, gfn, sp->role.level);
+ rmapp = gfn_to_rmap(kvm, gfn, sp);
pte_list_remove(spte, rmapp);
}
@@ -1142,6 +1149,11 @@ static u64 *rmap_get_next(struct rmap_iterator *iter)
return NULL;
}
+#define for_each_rmap_spte(_rmap_, _iter_, _spte_) \
+ for (_spte_ = rmap_get_first(*_rmap_, _iter_); \
+ _spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;}); \
+ _spte_ = rmap_get_next(_iter_))
+
static void drop_spte(struct kvm *kvm, u64 *sptep)
{
if (mmu_spte_clear_track_bits(sptep))
@@ -1205,12 +1217,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
struct rmap_iterator iter;
bool flush = false;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
flush |= spte_write_protect(kvm, sptep, pt_protect);
- sptep = rmap_get_next(&iter);
- }
return flush;
}
@@ -1232,12 +1240,8 @@ static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
struct rmap_iterator iter;
bool flush = false;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
flush |= spte_clear_dirty(kvm, sptep);
- sptep = rmap_get_next(&iter);
- }
return flush;
}
@@ -1259,12 +1263,8 @@ static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp)
struct rmap_iterator iter;
bool flush = false;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
flush |= spte_set_dirty(kvm, sptep);
- sptep = rmap_get_next(&iter);
- }
return flush;
}
@@ -1342,42 +1342,45 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
-static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
+static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
{
struct kvm_memory_slot *slot;
unsigned long *rmapp;
int i;
bool write_protected = false;
- slot = gfn_to_memslot(kvm, gfn);
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
- for (i = PT_PAGE_TABLE_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
rmapp = __gfn_to_rmap(gfn, i, slot);
- write_protected |= __rmap_write_protect(kvm, rmapp, true);
+ write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true);
}
return write_protected;
}
-static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
- struct kvm_memory_slot *slot, gfn_t gfn, int level,
- unsigned long data)
+static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp)
{
u64 *sptep;
struct rmap_iterator iter;
- int need_tlb_flush = 0;
+ bool flush = false;
while ((sptep = rmap_get_first(*rmapp, &iter))) {
BUG_ON(!(*sptep & PT_PRESENT_MASK));
- rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n",
- sptep, *sptep, gfn, level);
+ rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);
drop_spte(kvm, sptep);
- need_tlb_flush = 1;
+ flush = true;
}
- return need_tlb_flush;
+ return flush;
+}
+
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
+ struct kvm_memory_slot *slot, gfn_t gfn, int level,
+ unsigned long data)
+{
+ return kvm_zap_rmapp(kvm, rmapp);
}
static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
@@ -1394,8 +1397,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
WARN_ON(pte_huge(*ptep));
new_pfn = pte_pfn(*ptep);
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!is_shadow_present_pte(*sptep));
+restart:
+ for_each_rmap_spte(rmapp, &iter, sptep) {
rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
sptep, *sptep, gfn, level);
@@ -1403,7 +1406,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
if (pte_write(*ptep)) {
drop_spte(kvm, sptep);
- sptep = rmap_get_first(*rmapp, &iter);
+ goto restart;
} else {
new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
new_spte |= (u64)new_pfn << PAGE_SHIFT;
@@ -1414,7 +1417,6 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
mmu_spte_clear_track_bits(sptep);
mmu_spte_set(sptep, new_spte);
- sptep = rmap_get_next(&iter);
}
}
@@ -1424,6 +1426,74 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
return 0;
}
+struct slot_rmap_walk_iterator {
+ /* input fields. */
+ struct kvm_memory_slot *slot;
+ gfn_t start_gfn;
+ gfn_t end_gfn;
+ int start_level;
+ int end_level;
+
+ /* output fields. */
+ gfn_t gfn;
+ unsigned long *rmap;
+ int level;
+
+ /* private field. */
+ unsigned long *end_rmap;
+};
+
+static void
+rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level)
+{
+ iterator->level = level;
+ iterator->gfn = iterator->start_gfn;
+ iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot);
+ iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level,
+ iterator->slot);
+}
+
+static void
+slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator,
+ struct kvm_memory_slot *slot, int start_level,
+ int end_level, gfn_t start_gfn, gfn_t end_gfn)
+{
+ iterator->slot = slot;
+ iterator->start_level = start_level;
+ iterator->end_level = end_level;
+ iterator->start_gfn = start_gfn;
+ iterator->end_gfn = end_gfn;
+
+ rmap_walk_init_level(iterator, iterator->start_level);
+}
+
+static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator)
+{
+ return !!iterator->rmap;
+}
+
+static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
+{
+ if (++iterator->rmap <= iterator->end_rmap) {
+ iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level));
+ return;
+ }
+
+ if (++iterator->level > iterator->end_level) {
+ iterator->rmap = NULL;
+ return;
+ }
+
+ rmap_walk_init_level(iterator, iterator->level);
+}
+
+#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_, \
+ _start_gfn, _end_gfn, _iter_) \
+ for (slot_rmap_walk_init(_iter_, _slot_, _start_level_, \
+ _end_level_, _start_gfn, _end_gfn); \
+ slot_rmap_walk_okay(_iter_); \
+ slot_rmap_walk_next(_iter_))
+
static int kvm_handle_hva_range(struct kvm *kvm,
unsigned long start,
unsigned long end,
@@ -1435,48 +1505,36 @@ static int kvm_handle_hva_range(struct kvm *kvm,
int level,
unsigned long data))
{
- int j;
- int ret = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
+ struct slot_rmap_walk_iterator iterator;
+ int ret = 0;
+ int i;
- slots = kvm_memslots(kvm);
-
- kvm_for_each_memslot(memslot, slots) {
- unsigned long hva_start, hva_end;
- gfn_t gfn_start, gfn_end;
-
- hva_start = max(start, memslot->userspace_addr);
- hva_end = min(end, memslot->userspace_addr +
- (memslot->npages << PAGE_SHIFT));
- if (hva_start >= hva_end)
- continue;
- /*
- * {gfn(page) | page intersects with [hva_start, hva_end)} =
- * {gfn_start, gfn_start+1, ..., gfn_end-1}.
- */
- gfn_start = hva_to_gfn_memslot(hva_start, memslot);
- gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
-
- for (j = PT_PAGE_TABLE_LEVEL;
- j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
- unsigned long idx, idx_end;
- unsigned long *rmapp;
- gfn_t gfn = gfn_start;
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ slots = __kvm_memslots(kvm, i);
+ kvm_for_each_memslot(memslot, slots) {
+ unsigned long hva_start, hva_end;
+ gfn_t gfn_start, gfn_end;
+ hva_start = max(start, memslot->userspace_addr);
+ hva_end = min(end, memslot->userspace_addr +
+ (memslot->npages << PAGE_SHIFT));
+ if (hva_start >= hva_end)
+ continue;
/*
- * {idx(page_j) | page_j intersects with
- * [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}.
+ * {gfn(page) | page intersects with [hva_start, hva_end)} =
+ * {gfn_start, gfn_start+1, ..., gfn_end-1}.
*/
- idx = gfn_to_index(gfn_start, memslot->base_gfn, j);
- idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j);
-
- rmapp = __gfn_to_rmap(gfn_start, j, memslot);
-
- for (; idx <= idx_end;
- ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j)))
- ret |= handler(kvm, rmapp++, memslot,
- gfn, j, data);
+ gfn_start = hva_to_gfn_memslot(hva_start, memslot);
+ gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
+
+ for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL,
+ PT_MAX_HUGEPAGE_LEVEL,
+ gfn_start, gfn_end - 1,
+ &iterator)
+ ret |= handler(kvm, iterator.rmap, memslot,
+ iterator.gfn, iterator.level, data);
}
}
@@ -1518,16 +1576,13 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
BUG_ON(!shadow_accessed_mask);
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;
- sptep = rmap_get_next(&iter)) {
- BUG_ON(!is_shadow_present_pte(*sptep));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
if (*sptep & shadow_accessed_mask) {
young = 1;
clear_bit((ffs(shadow_accessed_mask) - 1),
(unsigned long *)sptep);
}
- }
+
trace_kvm_age_page(gfn, level, slot, young);
return young;
}
@@ -1548,15 +1603,11 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
if (!shadow_accessed_mask)
goto out;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;
- sptep = rmap_get_next(&iter)) {
- BUG_ON(!is_shadow_present_pte(*sptep));
-
+ for_each_rmap_spte(rmapp, &iter, sptep)
if (*sptep & shadow_accessed_mask) {
young = 1;
break;
}
- }
out:
return young;
}
@@ -1570,7 +1621,7 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
sp = page_header(__pa(spte));
- rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp);
kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0);
kvm_flush_remote_tlbs(vcpu->kvm);
@@ -1990,7 +2041,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu,
bool protected = false;
for_each_sp(pages, sp, parents, i)
- protected |= rmap_write_protect(vcpu->kvm, sp->gfn);
+ protected |= rmap_write_protect(vcpu, sp->gfn);
if (protected)
kvm_flush_remote_tlbs(vcpu->kvm);
@@ -2088,12 +2139,12 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
hlist_add_head(&sp->hash_link,
&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
if (!direct) {
- if (rmap_write_protect(vcpu->kvm, gfn))
+ if (rmap_write_protect(vcpu, gfn))
kvm_flush_remote_tlbs(vcpu->kvm);
if (level > PT_PAGE_TABLE_LEVEL && need_sync)
kvm_sync_pages(vcpu, gfn);
- account_shadowed(vcpu->kvm, gfn);
+ account_shadowed(vcpu->kvm, sp);
}
sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
init_shadow_page_table(sp);
@@ -2274,7 +2325,7 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
kvm_mmu_unlink_parents(kvm, sp);
if (!sp->role.invalid && !sp->role.direct)
- unaccount_shadowed(kvm, sp->gfn);
+ unaccount_shadowed(kvm, sp);
if (sp->unsync)
kvm_unlink_unsync_page(kvm, sp);
@@ -2386,111 +2437,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
}
EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
-/*
- * The function is based on mtrr_type_lookup() in
- * arch/x86/kernel/cpu/mtrr/generic.c
- */
-static int get_mtrr_type(struct mtrr_state_type *mtrr_state,
- u64 start, u64 end)
-{
- int i;
- u64 base, mask;
- u8 prev_match, curr_match;
- int num_var_ranges = KVM_NR_VAR_MTRR;
-
- if (!mtrr_state->enabled)
- return 0xFF;
-
- /* Make end inclusive end, instead of exclusive */
- end--;
-
- /* Look in fixed ranges. Just return the type as per start */
- if (mtrr_state->have_fixed && (start < 0x100000)) {
- int idx;
-
- if (start < 0x80000) {
- idx = 0;
- idx += (start >> 16);
- return mtrr_state->fixed_ranges[idx];
- } else if (start < 0xC0000) {
- idx = 1 * 8;
- idx += ((start - 0x80000) >> 14);
- return mtrr_state->fixed_ranges[idx];
- } else if (start < 0x1000000) {
- idx = 3 * 8;
- idx += ((start - 0xC0000) >> 12);
- return mtrr_state->fixed_ranges[idx];
- }
- }
-
- /*
- * Look in variable ranges
- * Look of multiple ranges matching this address and pick type
- * as per MTRR precedence
- */
- if (!(mtrr_state->enabled & 2))
- return mtrr_state->def_type;
-
- prev_match = 0xFF;
- for (i = 0; i < num_var_ranges; ++i) {
- unsigned short start_state, end_state;
-
- if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11)))
- continue;
-
- base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) +
- (mtrr_state->var_ranges[i].base_lo & PAGE_MASK);
- mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) +
- (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK);
-
- start_state = ((start & mask) == (base & mask));
- end_state = ((end & mask) == (base & mask));
- if (start_state != end_state)
- return 0xFE;
-
- if ((start & mask) != (base & mask))
- continue;
-
- curr_match = mtrr_state->var_ranges[i].base_lo & 0xff;
- if (prev_match == 0xFF) {
- prev_match = curr_match;
- continue;
- }
-
- if (prev_match == MTRR_TYPE_UNCACHABLE ||
- curr_match == MTRR_TYPE_UNCACHABLE)
- return MTRR_TYPE_UNCACHABLE;
-
- if ((prev_match == MTRR_TYPE_WRBACK &&
- curr_match == MTRR_TYPE_WRTHROUGH) ||
- (prev_match == MTRR_TYPE_WRTHROUGH &&
- curr_match == MTRR_TYPE_WRBACK)) {
- prev_match = MTRR_TYPE_WRTHROUGH;
- curr_match = MTRR_TYPE_WRTHROUGH;
- }
-
- if (prev_match != curr_match)
- return MTRR_TYPE_UNCACHABLE;
- }
-
- if (prev_match != 0xFF)
- return prev_match;
-
- return mtrr_state->def_type;
-}
-
-u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
- u8 mtrr;
-
- mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT,
- (gfn << PAGE_SHIFT) + PAGE_SIZE);
- if (mtrr == 0xfe || mtrr == 0xff)
- mtrr = MTRR_TYPE_WRBACK;
- return mtrr;
-}
-EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type);
-
static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
trace_kvm_mmu_unsync_page(sp);
@@ -2541,7 +2487,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
u64 spte;
int ret = 0;
- if (set_mmio_spte(vcpu->kvm, sptep, gfn, pfn, pte_access))
+ if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
return 0;
spte = PT_PRESENT_MASK;
@@ -2578,7 +2524,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
* be fixed if guest refault.
*/
if (level > PT_PAGE_TABLE_LEVEL &&
- has_wrprotected_page(vcpu->kvm, gfn, level))
+ has_wrprotected_page(vcpu, gfn, level))
goto done;
spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
@@ -2602,7 +2548,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
}
if (pte_access & ACC_WRITE_MASK) {
- mark_page_dirty(vcpu->kvm, gfn);
+ kvm_vcpu_mark_page_dirty(vcpu, gfn);
spte |= shadow_dirty_mask;
}
@@ -2692,15 +2638,17 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
u64 *start, u64 *end)
{
struct page *pages[PTE_PREFETCH_NUM];
+ struct kvm_memory_slot *slot;
unsigned access = sp->role.access;
int i, ret;
gfn_t gfn;
gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt);
- if (!gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK))
+ slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK);
+ if (!slot)
return -1;
- ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start);
+ ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start);
if (ret <= 0)
return -1;
@@ -2818,7 +2766,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn)
return 1;
if (pfn == KVM_PFN_ERR_HWPOISON) {
- kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current);
+ kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current);
return 0;
}
@@ -2841,7 +2789,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
level == PT_PAGE_TABLE_LEVEL &&
PageTransCompound(pfn_to_page(pfn)) &&
- !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) {
+ !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
unsigned long mask;
/*
* mmu_notifier_retry was successful and we hold the
@@ -2933,7 +2881,7 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
* Compare with set_spte where instead shadow_dirty_mask is set.
*/
if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte)
- mark_page_dirty(vcpu->kvm, gfn);
+ kvm_vcpu_mark_page_dirty(vcpu, gfn);
return true;
}
@@ -3388,7 +3336,7 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
gfn_t gfn = get_mmio_spte_gfn(spte);
unsigned access = get_mmio_spte_access(spte);
- if (!check_mmio_spte(vcpu->kvm, spte))
+ if (!check_mmio_spte(vcpu, spte))
return RET_MMIO_PF_INVALID;
if (direct)
@@ -3460,7 +3408,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
arch.direct_map = vcpu->arch.mmu.direct_map;
arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
- return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
+ return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}
static bool can_do_async_pf(struct kvm_vcpu *vcpu)
@@ -3475,10 +3423,12 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu)
static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
gva_t gva, pfn_t *pfn, bool write, bool *writable)
{
+ struct kvm_memory_slot *slot;
bool async;
- *pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable);
-
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ async = false;
+ *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable);
if (!async)
return false; /* *pfn has correct page already */
@@ -3492,11 +3442,20 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
return true;
}
- *pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable);
-
+ *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable);
return false;
}
+static bool
+check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
+{
+ int page_num = KVM_PAGES_PER_HPAGE(level);
+
+ gfn &= ~(page_num - 1);
+
+ return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
+}
+
static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
bool prefault)
{
@@ -3522,9 +3481,17 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
if (r)
return r;
- force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn);
+ if (mapping_level_dirty_bitmap(vcpu, gfn) ||
+ !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL))
+ force_pt_level = 1;
+ else
+ force_pt_level = 0;
+
if (likely(!force_pt_level)) {
level = mapping_level(vcpu, gfn);
+ if (level > PT_DIRECTORY_LEVEL &&
+ !check_hugepage_cache_consistency(vcpu, gfn, level))
+ level = PT_DIRECTORY_LEVEL;
gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
} else
level = PT_PAGE_TABLE_LEVEL;
@@ -3590,7 +3557,7 @@ static void inject_page_fault(struct kvm_vcpu *vcpu,
vcpu->arch.mmu.inject_page_fault(vcpu, fault);
}
-static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
+static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
unsigned access, int *nr_present)
{
if (unlikely(is_mmio_spte(*sptep))) {
@@ -3600,7 +3567,7 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
}
(*nr_present)++;
- mark_mmio_spte(kvm, sptep, gfn, access);
+ mark_mmio_spte(vcpu, sptep, gfn, access);
return true;
}
@@ -3736,8 +3703,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
}
}
-void update_permission_bitmask(struct kvm_vcpu *vcpu,
- struct kvm_mmu *mmu, bool ept)
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu, bool ept)
{
unsigned bit, byte, pfec;
u8 map;
@@ -3878,6 +3845,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
struct kvm_mmu *context = &vcpu->arch.mmu;
context->base_role.word = 0;
+ context->base_role.smm = is_smm(vcpu);
context->page_fault = tdp_page_fault;
context->sync_page = nonpaging_sync_page;
context->invlpg = nonpaging_invlpg;
@@ -3918,6 +3886,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
{
bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+ bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
struct kvm_mmu *context = &vcpu->arch.mmu;
MMU_WARN_ON(VALID_PAGE(context->root_hpa));
@@ -3936,6 +3905,9 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
context->base_role.cr0_wp = is_write_protection(vcpu);
context->base_role.smep_andnot_wp
= smep && !is_write_protection(vcpu);
+ context->base_role.smap_andnot_wp
+ = smap && !is_write_protection(vcpu);
+ context->base_role.smm = is_smm(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
@@ -4107,7 +4079,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
*gpa &= ~(gpa_t)7;
*bytes = 8;
- r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8);
+ r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8);
if (r)
gentry = 0;
new = (const u8 *)&gentry;
@@ -4207,12 +4179,19 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
const u8 *new, int bytes)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
- union kvm_mmu_page_role mask = { .word = 0 };
struct kvm_mmu_page *sp;
LIST_HEAD(invalid_list);
u64 entry, gentry, *spte;
int npte;
bool remote_flush, local_flush, zap_page;
+ union kvm_mmu_page_role mask = { };
+
+ mask.cr0_wp = 1;
+ mask.cr4_pae = 1;
+ mask.nxe = 1;
+ mask.smep_andnot_wp = 1;
+ mask.smap_andnot_wp = 1;
+ mask.smm = 1;
/*
* If we don't have indirect shadow pages, it means no page is
@@ -4238,7 +4217,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
++vcpu->kvm->stat.mmu_pte_write;
kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
- mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (detect_write_misaligned(sp, gpa, bytes) ||
detect_write_flooding(sp)) {
@@ -4412,36 +4390,115 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
init_kvm_mmu(vcpu);
}
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
- struct kvm_memory_slot *memslot)
+/* The return value indicates if tlb flush on all vcpus is needed. */
+typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap);
+
+/* The caller should hold mmu-lock before calling this function. */
+static bool
+slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, int start_level, int end_level,
+ gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb)
{
- gfn_t last_gfn;
- int i;
+ struct slot_rmap_walk_iterator iterator;
bool flush = false;
- last_gfn = memslot->base_gfn + memslot->npages - 1;
+ for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn,
+ end_gfn, &iterator) {
+ if (iterator.rmap)
+ flush |= fn(kvm, iterator.rmap);
- spin_lock(&kvm->mmu_lock);
+ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+ if (flush && lock_flush_tlb) {
+ kvm_flush_remote_tlbs(kvm);
+ flush = false;
+ }
+ cond_resched_lock(&kvm->mmu_lock);
+ }
+ }
- for (i = PT_PAGE_TABLE_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- unsigned long *rmapp;
- unsigned long last_index, index;
+ if (flush && lock_flush_tlb) {
+ kvm_flush_remote_tlbs(kvm);
+ flush = false;
+ }
- rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
- last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
+ return flush;
+}
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= __rmap_write_protect(kvm, rmapp,
- false);
+static bool
+slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, int start_level, int end_level,
+ bool lock_flush_tlb)
+{
+ return slot_handle_level_range(kvm, memslot, fn, start_level,
+ end_level, memslot->base_gfn,
+ memslot->base_gfn + memslot->npages - 1,
+ lock_flush_tlb);
+}
+
+static bool
+slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, bool lock_flush_tlb)
+{
+ return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
+ PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
+}
+
+static bool
+slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, bool lock_flush_tlb)
+{
+ return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1,
+ PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
+}
+
+static bool
+slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ slot_level_handler fn, bool lock_flush_tlb)
+{
+ return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
+ PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
+}
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int i;
+
+ spin_lock(&kvm->mmu_lock);
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ slots = __kvm_memslots(kvm, i);
+ kvm_for_each_memslot(memslot, slots) {
+ gfn_t start, end;
+
+ start = max(gfn_start, memslot->base_gfn);
+ end = min(gfn_end, memslot->base_gfn + memslot->npages);
+ if (start >= end)
+ continue;
+
+ slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
+ PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL,
+ start, end - 1, true);
}
}
spin_unlock(&kvm->mmu_lock);
+}
+
+static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp)
+{
+ return __rmap_write_protect(kvm, rmapp, false);
+}
+
+void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
+ struct kvm_memory_slot *memslot)
+{
+ bool flush;
+
+ spin_lock(&kvm->mmu_lock);
+ flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect,
+ false);
+ spin_unlock(&kvm->mmu_lock);
/*
* kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log()
@@ -4474,9 +4531,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
pfn_t pfn;
struct kvm_mmu_page *sp;
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
- BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+restart:
+ for_each_rmap_spte(rmapp, &iter, sptep) {
sp = page_header(__pa(sptep));
pfn = spte_to_pfn(*sptep);
@@ -4491,71 +4547,31 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
!kvm_is_reserved_pfn(pfn) &&
PageTransCompound(pfn_to_page(pfn))) {
drop_spte(kvm, sptep);
- sptep = rmap_get_first(*rmapp, &iter);
need_tlb_flush = 1;
- } else
- sptep = rmap_get_next(&iter);
+ goto restart;
+ }
}
return need_tlb_flush;
}
void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
- struct kvm_memory_slot *memslot)
+ const struct kvm_memory_slot *memslot)
{
- bool flush = false;
- unsigned long *rmapp;
- unsigned long last_index, index;
-
+ /* FIXME: const-ify all uses of struct kvm_memory_slot. */
spin_lock(&kvm->mmu_lock);
-
- rmapp = memslot->arch.rmap[0];
- last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1,
- memslot->base_gfn, PT_PAGE_TABLE_LEVEL);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
- if (flush) {
- kvm_flush_remote_tlbs(kvm);
- flush = false;
- }
- cond_resched_lock(&kvm->mmu_lock);
- }
- }
-
- if (flush)
- kvm_flush_remote_tlbs(kvm);
-
+ slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot,
+ kvm_mmu_zap_collapsible_spte, true);
spin_unlock(&kvm->mmu_lock);
}
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
- gfn_t last_gfn;
- unsigned long *rmapp;
- unsigned long last_index, index;
- bool flush = false;
-
- last_gfn = memslot->base_gfn + memslot->npages - 1;
+ bool flush;
spin_lock(&kvm->mmu_lock);
-
- rmapp = memslot->arch.rmap[PT_PAGE_TABLE_LEVEL - 1];
- last_index = gfn_to_index(last_gfn, memslot->base_gfn,
- PT_PAGE_TABLE_LEVEL);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= __rmap_clear_dirty(kvm, rmapp);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
- }
-
+ flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false);
spin_unlock(&kvm->mmu_lock);
lockdep_assert_held(&kvm->slots_lock);
@@ -4574,31 +4590,11 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty);
void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
- gfn_t last_gfn;
- int i;
- bool flush = false;
-
- last_gfn = memslot->base_gfn + memslot->npages - 1;
+ bool flush;
spin_lock(&kvm->mmu_lock);
-
- for (i = PT_PAGE_TABLE_LEVEL + 1; /* skip rmap for 4K page */
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- unsigned long *rmapp;
- unsigned long last_index, index;
-
- rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
- last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= __rmap_write_protect(kvm, rmapp,
- false);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
- }
- }
+ flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
+ false);
spin_unlock(&kvm->mmu_lock);
/* see kvm_mmu_slot_remove_write_access */
@@ -4612,31 +4608,10 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access);
void kvm_mmu_slot_set_dirty(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
- gfn_t last_gfn;
- int i;
- bool flush = false;
-
- last_gfn = memslot->base_gfn + memslot->npages - 1;
+ bool flush;
spin_lock(&kvm->mmu_lock);
-
- for (i = PT_PAGE_TABLE_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- unsigned long *rmapp;
- unsigned long last_index, index;
-
- rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
- last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
-
- for (index = 0; index <= last_index; ++index, ++rmapp) {
- if (*rmapp)
- flush |= __rmap_set_dirty(kvm, rmapp);
-
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
- }
- }
-
+ flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
spin_unlock(&kvm->mmu_lock);
lockdep_assert_held(&kvm->slots_lock);
@@ -4733,13 +4708,13 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
}
-void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
+void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots)
{
/*
* The very rare case: if the generation-number is round,
* zap all shadow pages.
*/
- if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
+ if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) {
printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
kvm_mmu_invalidate_zap_all_pages(kvm);
}
@@ -4861,15 +4836,18 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
unsigned int nr_pages = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
+ int i;
- slots = kvm_memslots(kvm);
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ slots = __kvm_memslots(kvm, i);
- kvm_for_each_memslot(memslot, slots)
- nr_pages += memslot->npages;
+ kvm_for_each_memslot(memslot, slots)
+ nr_pages += memslot->npages;
+ }
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
nr_mmu_pages = max(nr_mmu_pages,
- (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+ (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
return nr_mmu_pages;
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index c7d65637c851..398d21c0f6dd 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -43,6 +43,7 @@
#define PT_PDPE_LEVEL 3
#define PT_DIRECTORY_LEVEL 2
#define PT_PAGE_TABLE_LEVEL 1
+#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1)
static inline u64 rsvd_bits(int s, int e)
{
@@ -71,8 +72,6 @@ enum {
int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
-void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- bool ept);
static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
{
@@ -166,8 +165,11 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
int index = (pfec >> 1) +
(smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
+ WARN_ON(pfec & PFERR_RSVD_MASK);
+
return (mmu->permissions[index] >> pte_access) & 1;
}
void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
#endif
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 9ade5cfb5a4c..a4f62e6f2db2 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -114,7 +114,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
return;
gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);
- pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn);
+ pfn = kvm_vcpu_gfn_to_pfn_atomic(vcpu, gfn);
if (is_error_pfn(pfn))
return;
@@ -131,12 +131,16 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
unsigned long *rmapp;
struct kvm_mmu_page *rev_sp;
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *slot;
gfn_t gfn;
rev_sp = page_header(__pa(sptep));
gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt);
- if (!gfn_to_memslot(kvm, gfn)) {
+ slots = kvm_memslots_for_spte_role(kvm, rev_sp->role);
+ slot = __gfn_to_memslot(slots, gfn);
+ if (!slot) {
if (!__ratelimit(&ratelimit_state))
return;
audit_printk(kvm, "no memslot for gfn %llx\n", gfn);
@@ -146,7 +150,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
return;
}
- rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level);
+ rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot);
if (!*rmapp) {
if (!__ratelimit(&ratelimit_state))
return;
@@ -191,19 +195,21 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
unsigned long *rmapp;
u64 *sptep;
struct rmap_iterator iter;
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *slot;
if (sp->role.direct || sp->unsync || sp->role.invalid)
return;
- rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL);
+ slots = kvm_memslots_for_spte_role(kvm, sp->role);
+ slot = __gfn_to_memslot(slots, sp->gfn);
+ rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot);
- for (sptep = rmap_get_first(*rmapp, &iter); sptep;
- sptep = rmap_get_next(&iter)) {
+ for_each_rmap_spte(rmapp, &iter, sptep)
if (is_writable_pte(*sptep))
audit_printk(kvm, "shadow page has writable "
"mappings: gfn %llx role %x\n",
sp->gfn, sp->role.word);
- }
}
static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
new file mode 100644
index 000000000000..de1d2d8062e2
--- /dev/null
+++ b/arch/x86/kvm/mtrr.c
@@ -0,0 +1,699 @@
+/*
+ * vMTRR implementation
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright(C) 2015 Intel Corporation.
+ *
+ * Authors:
+ * Yaniv Kamay <yaniv@qumranet.com>
+ * Avi Kivity <avi@qumranet.com>
+ * Marcelo Tosatti <mtosatti@redhat.com>
+ * Paolo Bonzini <pbonzini@redhat.com>
+ * Xiao Guangrong <guangrong.xiao@linux.intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/mtrr.h>
+
+#include "cpuid.h"
+#include "mmu.h"
+
+#define IA32_MTRR_DEF_TYPE_E (1ULL << 11)
+#define IA32_MTRR_DEF_TYPE_FE (1ULL << 10)
+#define IA32_MTRR_DEF_TYPE_TYPE_MASK (0xff)
+
+static bool msr_mtrr_valid(unsigned msr)
+{
+ switch (msr) {
+ case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1:
+ case MSR_MTRRfix64K_00000:
+ case MSR_MTRRfix16K_80000:
+ case MSR_MTRRfix16K_A0000:
+ case MSR_MTRRfix4K_C0000:
+ case MSR_MTRRfix4K_C8000:
+ case MSR_MTRRfix4K_D0000:
+ case MSR_MTRRfix4K_D8000:
+ case MSR_MTRRfix4K_E0000:
+ case MSR_MTRRfix4K_E8000:
+ case MSR_MTRRfix4K_F0000:
+ case MSR_MTRRfix4K_F8000:
+ case MSR_MTRRdefType:
+ case MSR_IA32_CR_PAT:
+ return true;
+ case 0x2f8:
+ return true;
+ }
+ return false;
+}
+
+static bool valid_pat_type(unsigned t)
+{
+ return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
+}
+
+static bool valid_mtrr_type(unsigned t)
+{
+ return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
+}
+
+bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+ int i;
+ u64 mask;
+
+ if (!msr_mtrr_valid(msr))
+ return false;
+
+ if (msr == MSR_IA32_CR_PAT) {
+ for (i = 0; i < 8; i++)
+ if (!valid_pat_type((data >> (i * 8)) & 0xff))
+ return false;
+ return true;
+ } else if (msr == MSR_MTRRdefType) {
+ if (data & ~0xcff)
+ return false;
+ return valid_mtrr_type(data & 0xff);
+ } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
+ for (i = 0; i < 8 ; i++)
+ if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
+ return false;
+ return true;
+ }
+
+ /* variable MTRRs */
+ WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
+
+ mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
+ if ((msr & 1) == 0) {
+ /* MTRR base */
+ if (!valid_mtrr_type(data & 0xff))
+ return false;
+ mask |= 0xf00;
+ } else
+ /* MTRR mask */
+ mask |= 0x7ff;
+ if (data & mask) {
+ kvm_inject_gp(vcpu, 0);
+ return false;
+ }
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
+
+static bool mtrr_is_enabled(struct kvm_mtrr *mtrr_state)
+{
+ return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_E);
+}
+
+static bool fixed_mtrr_is_enabled(struct kvm_mtrr *mtrr_state)
+{
+ return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_FE);
+}
+
+static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state)
+{
+ return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
+}
+
+/*
+* Three terms are used in the following code:
+* - segment, it indicates the address segments covered by fixed MTRRs.
+* - unit, it corresponds to the MSR entry in the segment.
+* - range, a range is covered in one memory cache type.
+*/
+struct fixed_mtrr_segment {
+ u64 start;
+ u64 end;
+
+ int range_shift;
+
+ /* the start position in kvm_mtrr.fixed_ranges[]. */
+ int range_start;
+};
+
+static struct fixed_mtrr_segment fixed_seg_table[] = {
+ /* MSR_MTRRfix64K_00000, 1 unit. 64K fixed mtrr. */
+ {
+ .start = 0x0,
+ .end = 0x80000,
+ .range_shift = 16, /* 64K */
+ .range_start = 0,
+ },
+
+ /*
+ * MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000, 2 units,
+ * 16K fixed mtrr.
+ */
+ {
+ .start = 0x80000,
+ .end = 0xc0000,
+ .range_shift = 14, /* 16K */
+ .range_start = 8,
+ },
+
+ /*
+ * MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000, 8 units,
+ * 4K fixed mtrr.
+ */
+ {
+ .start = 0xc0000,
+ .end = 0x100000,
+ .range_shift = 12, /* 12K */
+ .range_start = 24,
+ }
+};
+
+/*
+ * The size of unit is covered in one MSR, one MSR entry contains
+ * 8 ranges so that unit size is always 8 * 2^range_shift.
+ */
+static u64 fixed_mtrr_seg_unit_size(int seg)
+{
+ return 8 << fixed_seg_table[seg].range_shift;
+}
+
+static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit)
+{
+ switch (msr) {
+ case MSR_MTRRfix64K_00000:
+ *seg = 0;
+ *unit = 0;
+ break;
+ case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000:
+ *seg = 1;
+ *unit = msr - MSR_MTRRfix16K_80000;
+ break;
+ case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000:
+ *seg = 2;
+ *unit = msr - MSR_MTRRfix4K_C0000;
+ break;
+ default:
+ return false;
+ }
+
+ return true;
+}
+
+static void fixed_mtrr_seg_unit_range(int seg, int unit, u64 *start, u64 *end)
+{
+ struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
+ u64 unit_size = fixed_mtrr_seg_unit_size(seg);
+
+ *start = mtrr_seg->start + unit * unit_size;
+ *end = *start + unit_size;
+ WARN_ON(*end > mtrr_seg->end);
+}
+
+static int fixed_mtrr_seg_unit_range_index(int seg, int unit)
+{
+ struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
+
+ WARN_ON(mtrr_seg->start + unit * fixed_mtrr_seg_unit_size(seg)
+ > mtrr_seg->end);
+
+ /* each unit has 8 ranges. */
+ return mtrr_seg->range_start + 8 * unit;
+}
+
+static int fixed_mtrr_seg_end_range_index(int seg)
+{
+ struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
+ int n;
+
+ n = (mtrr_seg->end - mtrr_seg->start) >> mtrr_seg->range_shift;
+ return mtrr_seg->range_start + n - 1;
+}
+
+static bool fixed_msr_to_range(u32 msr, u64 *start, u64 *end)
+{
+ int seg, unit;
+
+ if (!fixed_msr_to_seg_unit(msr, &seg, &unit))
+ return false;
+
+ fixed_mtrr_seg_unit_range(seg, unit, start, end);
+ return true;
+}
+
+static int fixed_msr_to_range_index(u32 msr)
+{
+ int seg, unit;
+
+ if (!fixed_msr_to_seg_unit(msr, &seg, &unit))
+ return -1;
+
+ return fixed_mtrr_seg_unit_range_index(seg, unit);
+}
+
+static int fixed_mtrr_addr_to_seg(u64 addr)
+{
+ struct fixed_mtrr_segment *mtrr_seg;
+ int seg, seg_num = ARRAY_SIZE(fixed_seg_table);
+
+ for (seg = 0; seg < seg_num; seg++) {
+ mtrr_seg = &fixed_seg_table[seg];
+ if (mtrr_seg->start >= addr && addr < mtrr_seg->end)
+ return seg;
+ }
+
+ return -1;
+}
+
+static int fixed_mtrr_addr_seg_to_range_index(u64 addr, int seg)
+{
+ struct fixed_mtrr_segment *mtrr_seg;
+ int index;
+
+ mtrr_seg = &fixed_seg_table[seg];
+ index = mtrr_seg->range_start;
+ index += (addr - mtrr_seg->start) >> mtrr_seg->range_shift;
+ return index;
+}
+
+static u64 fixed_mtrr_range_end_addr(int seg, int index)
+{
+ struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
+ int pos = index - mtrr_seg->range_start;
+
+ return mtrr_seg->start + ((pos + 1) << mtrr_seg->range_shift);
+}
+
+static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end)
+{
+ u64 mask;
+
+ *start = range->base & PAGE_MASK;
+
+ mask = range->mask & PAGE_MASK;
+ mask |= ~0ULL << boot_cpu_data.x86_phys_bits;
+
+ /* This cannot overflow because writing to the reserved bits of
+ * variable MTRRs causes a #GP.
+ */
+ *end = (*start | ~mask) + 1;
+}
+
+static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr)
+{
+ struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+ gfn_t start, end;
+ int index;
+
+ if (msr == MSR_IA32_CR_PAT || !tdp_enabled ||
+ !kvm_arch_has_noncoherent_dma(vcpu->kvm))
+ return;
+
+ if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType)
+ return;
+
+ /* fixed MTRRs. */
+ if (fixed_msr_to_range(msr, &start, &end)) {
+ if (!fixed_mtrr_is_enabled(mtrr_state))
+ return;
+ } else if (msr == MSR_MTRRdefType) {
+ start = 0x0;
+ end = ~0ULL;
+ } else {
+ /* variable range MTRRs. */
+ index = (msr - 0x200) / 2;
+ var_mtrr_range(&mtrr_state->var_ranges[index], &start, &end);
+ }
+
+ kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end));
+}
+
+static bool var_mtrr_range_is_valid(struct kvm_mtrr_range *range)
+{
+ return (range->mask & (1 << 11)) != 0;
+}
+
+static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+ struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+ struct kvm_mtrr_range *tmp, *cur;
+ int index, is_mtrr_mask;
+
+ index = (msr - 0x200) / 2;
+ is_mtrr_mask = msr - 0x200 - 2 * index;
+ cur = &mtrr_state->var_ranges[index];
+
+ /* remove the entry if it's in the list. */
+ if (var_mtrr_range_is_valid(cur))
+ list_del(&mtrr_state->var_ranges[index].node);
+
+ if (!is_mtrr_mask)
+ cur->base = data;
+ else
+ cur->mask = data;
+
+ /* add it to the list if it's enabled. */
+ if (var_mtrr_range_is_valid(cur)) {
+ list_for_each_entry(tmp, &mtrr_state->head, node)
+ if (cur->base >= tmp->base)
+ break;
+ list_add_tail(&cur->node, &tmp->node);
+ }
+}
+
+int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+ int index;
+
+ if (!kvm_mtrr_valid(vcpu, msr, data))
+ return 1;
+
+ index = fixed_msr_to_range_index(msr);
+ if (index >= 0)
+ *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index] = data;
+ else if (msr == MSR_MTRRdefType)
+ vcpu->arch.mtrr_state.deftype = data;
+ else if (msr == MSR_IA32_CR_PAT)
+ vcpu->arch.pat = data;
+ else
+ set_var_mtrr_msr(vcpu, msr, data);
+
+ update_mtrr(vcpu, msr);
+ return 0;
+}
+
+int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+ int index;
+
+ /* MSR_MTRRcap is a readonly MSR. */
+ if (msr == MSR_MTRRcap) {
+ /*
+ * SMRR = 0
+ * WC = 1
+ * FIX = 1
+ * VCNT = KVM_NR_VAR_MTRR
+ */
+ *pdata = 0x500 | KVM_NR_VAR_MTRR;
+ return 0;
+ }
+
+ if (!msr_mtrr_valid(msr))
+ return 1;
+
+ index = fixed_msr_to_range_index(msr);
+ if (index >= 0)
+ *pdata = *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index];
+ else if (msr == MSR_MTRRdefType)
+ *pdata = vcpu->arch.mtrr_state.deftype;
+ else if (msr == MSR_IA32_CR_PAT)
+ *pdata = vcpu->arch.pat;
+ else { /* Variable MTRRs */
+ int is_mtrr_mask;
+
+ index = (msr - 0x200) / 2;
+ is_mtrr_mask = msr - 0x200 - 2 * index;
+ if (!is_mtrr_mask)
+ *pdata = vcpu->arch.mtrr_state.var_ranges[index].base;
+ else
+ *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask;
+ }
+
+ return 0;
+}
+
+void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu)
+{
+ INIT_LIST_HEAD(&vcpu->arch.mtrr_state.head);
+}
+
+struct mtrr_iter {
+ /* input fields. */
+ struct kvm_mtrr *mtrr_state;
+ u64 start;
+ u64 end;
+
+ /* output fields. */
+ int mem_type;
+ /* [start, end) is not fully covered in MTRRs? */
+ bool partial_map;
+
+ /* private fields. */
+ union {
+ /* used for fixed MTRRs. */
+ struct {
+ int index;
+ int seg;
+ };
+
+ /* used for var MTRRs. */
+ struct {
+ struct kvm_mtrr_range *range;
+ /* max address has been covered in var MTRRs. */
+ u64 start_max;
+ };
+ };
+
+ bool fixed;
+};
+
+static bool mtrr_lookup_fixed_start(struct mtrr_iter *iter)
+{
+ int seg, index;
+
+ if (!fixed_mtrr_is_enabled(iter->mtrr_state))
+ return false;
+
+ seg = fixed_mtrr_addr_to_seg(iter->start);
+ if (seg < 0)
+ return false;
+
+ iter->fixed = true;
+ index = fixed_mtrr_addr_seg_to_range_index(iter->start, seg);
+ iter->index = index;
+ iter->seg = seg;
+ return true;
+}
+
+static bool match_var_range(struct mtrr_iter *iter,
+ struct kvm_mtrr_range *range)
+{
+ u64 start, end;
+
+ var_mtrr_range(range, &start, &end);
+ if (!(start >= iter->end || end <= iter->start)) {
+ iter->range = range;
+
+ /*
+ * the function is called when we do kvm_mtrr.head walking.
+ * Range has the minimum base address which interleaves
+ * [looker->start_max, looker->end).
+ */
+ iter->partial_map |= iter->start_max < start;
+
+ /* update the max address has been covered. */
+ iter->start_max = max(iter->start_max, end);
+ return true;
+ }
+
+ return false;
+}
+
+static void __mtrr_lookup_var_next(struct mtrr_iter *iter)
+{
+ struct kvm_mtrr *mtrr_state = iter->mtrr_state;
+
+ list_for_each_entry_continue(iter->range, &mtrr_state->head, node)
+ if (match_var_range(iter, iter->range))
+ return;
+
+ iter->range = NULL;
+ iter->partial_map |= iter->start_max < iter->end;
+}
+
+static void mtrr_lookup_var_start(struct mtrr_iter *iter)
+{
+ struct kvm_mtrr *mtrr_state = iter->mtrr_state;
+
+ iter->fixed = false;
+ iter->start_max = iter->start;
+ iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
+
+ __mtrr_lookup_var_next(iter);
+}
+
+static void mtrr_lookup_fixed_next(struct mtrr_iter *iter)
+{
+ /* terminate the lookup. */
+ if (fixed_mtrr_range_end_addr(iter->seg, iter->index) >= iter->end) {
+ iter->fixed = false;
+ iter->range = NULL;
+ return;
+ }
+
+ iter->index++;
+
+ /* have looked up for all fixed MTRRs. */
+ if (iter->index >= ARRAY_SIZE(iter->mtrr_state->fixed_ranges))
+ return mtrr_lookup_var_start(iter);
+
+ /* switch to next segment. */
+ if (iter->index > fixed_mtrr_seg_end_range_index(iter->seg))
+ iter->seg++;
+}
+
+static void mtrr_lookup_var_next(struct mtrr_iter *iter)
+{
+ __mtrr_lookup_var_next(iter);
+}
+
+static void mtrr_lookup_start(struct mtrr_iter *iter)
+{
+ if (!mtrr_is_enabled(iter->mtrr_state)) {
+ iter->partial_map = true;
+ return;
+ }
+
+ if (!mtrr_lookup_fixed_start(iter))
+ mtrr_lookup_var_start(iter);
+}
+
+static void mtrr_lookup_init(struct mtrr_iter *iter,
+ struct kvm_mtrr *mtrr_state, u64 start, u64 end)
+{
+ iter->mtrr_state = mtrr_state;
+ iter->start = start;
+ iter->end = end;
+ iter->partial_map = false;
+ iter->fixed = false;
+ iter->range = NULL;
+
+ mtrr_lookup_start(iter);
+}
+
+static bool mtrr_lookup_okay(struct mtrr_iter *iter)
+{
+ if (iter->fixed) {
+ iter->mem_type = iter->mtrr_state->fixed_ranges[iter->index];
+ return true;
+ }
+
+ if (iter->range) {
+ iter->mem_type = iter->range->base & 0xff;
+ return true;
+ }
+
+ return false;
+}
+
+static void mtrr_lookup_next(struct mtrr_iter *iter)
+{
+ if (iter->fixed)
+ mtrr_lookup_fixed_next(iter);
+ else
+ mtrr_lookup_var_next(iter);
+}
+
+#define mtrr_for_each_mem_type(_iter_, _mtrr_, _gpa_start_, _gpa_end_) \
+ for (mtrr_lookup_init(_iter_, _mtrr_, _gpa_start_, _gpa_end_); \
+ mtrr_lookup_okay(_iter_); mtrr_lookup_next(_iter_))
+
+u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+ struct mtrr_iter iter;
+ u64 start, end;
+ int type = -1;
+ const int wt_wb_mask = (1 << MTRR_TYPE_WRBACK)
+ | (1 << MTRR_TYPE_WRTHROUGH);
+
+ start = gfn_to_gpa(gfn);
+ end = start + PAGE_SIZE;
+
+ mtrr_for_each_mem_type(&iter, mtrr_state, start, end) {
+ int curr_type = iter.mem_type;
+
+ /*
+ * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR
+ * Precedences.
+ */
+
+ if (type == -1) {
+ type = curr_type;
+ continue;
+ }
+
+ /*
+ * If two or more variable memory ranges match and the
+ * memory types are identical, then that memory type is
+ * used.
+ */
+ if (type == curr_type)
+ continue;
+
+ /*
+ * If two or more variable memory ranges match and one of
+ * the memory types is UC, the UC memory type used.
+ */
+ if (curr_type == MTRR_TYPE_UNCACHABLE)
+ return MTRR_TYPE_UNCACHABLE;
+
+ /*
+ * If two or more variable memory ranges match and the
+ * memory types are WT and WB, the WT memory type is used.
+ */
+ if (((1 << type) & wt_wb_mask) &&
+ ((1 << curr_type) & wt_wb_mask)) {
+ type = MTRR_TYPE_WRTHROUGH;
+ continue;
+ }
+
+ /*
+ * For overlaps not defined by the above rules, processor
+ * behavior is undefined.
+ */
+
+ /* We use WB for this undefined behavior. :( */
+ return MTRR_TYPE_WRBACK;
+ }
+
+ /* It is not covered by MTRRs. */
+ if (iter.partial_map) {
+ /*
+ * We just check one page, partially covered by MTRRs is
+ * impossible.
+ */
+ WARN_ON(type != -1);
+ type = mtrr_default_type(mtrr_state);
+ }
+ return type;
+}
+EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
+
+bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
+ int page_num)
+{
+ struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+ struct mtrr_iter iter;
+ u64 start, end;
+ int type = -1;
+
+ start = gfn_to_gpa(gfn);
+ end = gfn_to_gpa(gfn + page_num);
+ mtrr_for_each_mem_type(&iter, mtrr_state, start, end) {
+ if (type == -1) {
+ type = iter.mem_type;
+ continue;
+ }
+
+ if (type != iter.mem_type)
+ return false;
+ }
+
+ if (!iter.partial_map)
+ return true;
+
+ if (type == -1)
+ return true;
+
+ return type == mtrr_default_type(mtrr_state);
+}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index fd49c867b25a..0f67d7e24800 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -256,7 +256,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
if (ret)
return ret;
- mark_page_dirty(vcpu->kvm, table_gfn);
+ kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
walker->ptes[level] = pte;
}
return 0;
@@ -338,7 +338,7 @@ retry_walk:
real_gfn = gpa_to_gfn(real_gfn);
- host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+ host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn,
&walker->pte_writable[walker->level - 1]);
if (unlikely(kvm_is_error_hva(host_addr)))
goto error;
@@ -511,11 +511,11 @@ static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu,
base_gpa = pte_gpa & ~mask;
index = (pte_gpa - base_gpa) / sizeof(pt_element_t);
- r = kvm_read_guest_atomic(vcpu->kvm, base_gpa,
+ r = kvm_vcpu_read_guest_atomic(vcpu, base_gpa,
gw->prefetch_ptes, sizeof(gw->prefetch_ptes));
curr_pte = gw->prefetch_ptes[index];
} else
- r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa,
+ r = kvm_vcpu_read_guest_atomic(vcpu, pte_gpa,
&curr_pte, sizeof(curr_pte));
return r || curr_pte != gw->ptes[level - 1];
@@ -718,6 +718,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
mmu_is_nested(vcpu));
if (likely(r != RET_MMIO_PF_INVALID))
return r;
+
+ /*
+ * page fault with PFEC.RSVD = 1 is caused by shadow
+ * page fault, should not be used to walk guest page
+ * table.
+ */
+ error_code &= ~PFERR_RSVD_MASK;
};
r = mmu_topup_memory_caches(vcpu);
@@ -862,8 +869,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
if (!rmap_can_add(vcpu))
break;
- if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
- sizeof(pt_element_t)))
+ if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
+ sizeof(pt_element_t)))
break;
FNAME(update_pte)(vcpu, sp, sptep, &gpte);
@@ -949,8 +956,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
- if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
- sizeof(pt_element_t)))
+ if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
+ sizeof(pt_element_t)))
return -EINVAL;
if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
@@ -963,7 +970,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
pte_access &= FNAME(gpte_access)(vcpu, gpte);
FNAME(protect_clean_gpte)(&pte_access, gpte);
- if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access,
+ if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access,
&nr_present))
continue;
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 29fbf9dfdc54..31aa2c85dc97 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -1,11 +1,12 @@
/*
* Kernel-based Virtual Machine -- Performance Monitoring Unit support
*
- * Copyright 2011 Red Hat, Inc. and/or its affiliates.
+ * Copyright 2015 Red Hat, Inc. and/or its affiliates.
*
* Authors:
* Avi Kivity <avi@redhat.com>
* Gleb Natapov <gleb@redhat.com>
+ * Wei Huang <wei@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
@@ -19,88 +20,39 @@
#include "x86.h"
#include "cpuid.h"
#include "lapic.h"
+#include "pmu.h"
+
+/* NOTE:
+ * - Each perf counter is defined as "struct kvm_pmc";
+ * - There are two types of perf counters: general purpose (gp) and fixed.
+ * gp counters are stored in gp_counters[] and fixed counters are stored
+ * in fixed_counters[] respectively. Both of them are part of "struct
+ * kvm_pmu";
+ * - pmu.c understands the difference between gp counters and fixed counters.
+ * However AMD doesn't support fixed-counters;
+ * - There are three types of index to access perf counters (PMC):
+ * 1. MSR (named msr): For example Intel has MSR_IA32_PERFCTRn and AMD
+ * has MSR_K7_PERFCTRn.
+ * 2. MSR Index (named idx): This normally is used by RDPMC instruction.
+ * For instance AMD RDPMC instruction uses 0000_0003h in ECX to access
+ * C001_0007h (MSR_K7_PERCTR3). Intel has a similar mechanism, except
+ * that it also supports fixed counters. idx can be used to as index to
+ * gp and fixed counters.
+ * 3. Global PMC Index (named pmc): pmc is an index specific to PMU
+ * code. Each pmc, stored in kvm_pmc.idx field, is unique across
+ * all perf counters (both gp and fixed). The mapping relationship
+ * between pmc and perf counters is as the following:
+ * * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters
+ * [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed
+ * * AMD: [0 .. AMD64_NUM_COUNTERS-1] <=> gp counters
+ */
-static struct kvm_arch_event_perf_mapping {
- u8 eventsel;
- u8 unit_mask;
- unsigned event_type;
- bool inexact;
-} arch_events[] = {
- /* Index must match CPUID 0x0A.EBX bit vector */
- [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES },
- [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
- [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES },
- [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES },
- [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
- [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
- [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
- [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
-};
-
-/* mapping between fixed pmc index and arch_events array */
-static int fixed_pmc_events[] = {1, 0, 7};
-
-static bool pmc_is_gp(struct kvm_pmc *pmc)
-{
- return pmc->type == KVM_PMC_GP;
-}
-
-static inline u64 pmc_bitmask(struct kvm_pmc *pmc)
-{
- struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
-
- return pmu->counter_bitmask[pmc->type];
-}
-
-static inline bool pmc_enabled(struct kvm_pmc *pmc)
-{
- struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
- return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl);
-}
-
-static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
- u32 base)
-{
- if (msr >= base && msr < base + pmu->nr_arch_gp_counters)
- return &pmu->gp_counters[msr - base];
- return NULL;
-}
-
-static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
-{
- int base = MSR_CORE_PERF_FIXED_CTR0;
- if (msr >= base && msr < base + pmu->nr_arch_fixed_counters)
- return &pmu->fixed_counters[msr - base];
- return NULL;
-}
-
-static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx)
-{
- return get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + idx);
-}
-
-static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx)
-{
- if (idx < INTEL_PMC_IDX_FIXED)
- return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0);
- else
- return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED);
-}
-
-void kvm_deliver_pmi(struct kvm_vcpu *vcpu)
-{
- if (vcpu->arch.apic)
- kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
-}
-
-static void trigger_pmi(struct irq_work *irq_work)
+static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
{
- struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu,
- irq_work);
- struct kvm_vcpu *vcpu = container_of(pmu, struct kvm_vcpu,
- arch.pmu);
+ struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work);
+ struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
- kvm_deliver_pmi(vcpu);
+ kvm_pmu_deliver_pmi(vcpu);
}
static void kvm_perf_overflow(struct perf_event *perf_event,
@@ -108,63 +60,46 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
struct pt_regs *regs)
{
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
- struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
- if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
+ struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+ if (!test_and_set_bit(pmc->idx,
+ (unsigned long *)&pmu->reprogram_pmi)) {
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
}
}
static void kvm_perf_overflow_intr(struct perf_event *perf_event,
- struct perf_sample_data *data, struct pt_regs *regs)
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
- struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
- if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
+ struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+ if (!test_and_set_bit(pmc->idx,
+ (unsigned long *)&pmu->reprogram_pmi)) {
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+
/*
* Inject PMI. If vcpu was in a guest mode during NMI PMI
* can be ejected on a guest mode re-entry. Otherwise we can't
* be sure that vcpu wasn't executing hlt instruction at the
- * time of vmexit and is not going to re-enter guest mode until,
+ * time of vmexit and is not going to re-enter guest mode until
* woken up. So we should wake it, but this is impossible from
* NMI context. Do it from irq work instead.
*/
if (!kvm_is_in_guest())
- irq_work_queue(&pmc->vcpu->arch.pmu.irq_work);
+ irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
else
kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
}
}
-static u64 read_pmc(struct kvm_pmc *pmc)
-{
- u64 counter, enabled, running;
-
- counter = pmc->counter;
-
- if (pmc->perf_event)
- counter += perf_event_read_value(pmc->perf_event,
- &enabled, &running);
-
- /* FIXME: Scaling needed? */
-
- return counter & pmc_bitmask(pmc);
-}
-
-static void stop_counter(struct kvm_pmc *pmc)
-{
- if (pmc->perf_event) {
- pmc->counter = read_pmc(pmc);
- perf_event_release_kernel(pmc->perf_event);
- pmc->perf_event = NULL;
- }
-}
-
-static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
- unsigned config, bool exclude_user, bool exclude_kernel,
- bool intr, bool in_tx, bool in_tx_cp)
+static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
+ unsigned config, bool exclude_user,
+ bool exclude_kernel, bool intr,
+ bool in_tx, bool in_tx_cp)
{
struct perf_event *event;
struct perf_event_attr attr = {
@@ -177,6 +112,7 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
.exclude_kernel = exclude_kernel,
.config = config,
};
+
if (in_tx)
attr.config |= HSW_IN_TX;
if (in_tx_cp)
@@ -188,33 +124,16 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
intr ? kvm_perf_overflow_intr :
kvm_perf_overflow, pmc);
if (IS_ERR(event)) {
- printk_once("kvm: pmu event creation failed %ld\n",
- PTR_ERR(event));
+ printk_once("kvm_pmu: event creation failed %ld\n",
+ PTR_ERR(event));
return;
}
pmc->perf_event = event;
- clear_bit(pmc->idx, (unsigned long*)&pmc->vcpu->arch.pmu.reprogram_pmi);
-}
-
-static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select,
- u8 unit_mask)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(arch_events); i++)
- if (arch_events[i].eventsel == event_select
- && arch_events[i].unit_mask == unit_mask
- && (pmu->available_event_types & (1 << i)))
- break;
-
- if (i == ARRAY_SIZE(arch_events))
- return PERF_COUNT_HW_MAX;
-
- return arch_events[i].event_type;
+ clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi);
}
-static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
+void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
{
unsigned config, type = PERF_TYPE_RAW;
u8 event_select, unit_mask;
@@ -224,21 +143,22 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
pmc->eventsel = eventsel;
- stop_counter(pmc);
+ pmc_stop_counter(pmc);
- if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_enabled(pmc))
+ if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
return;
event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
- ARCH_PERFMON_EVENTSEL_INV |
- ARCH_PERFMON_EVENTSEL_CMASK |
- HSW_IN_TX |
- HSW_IN_TX_CHECKPOINTED))) {
- config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
- unit_mask);
+ ARCH_PERFMON_EVENTSEL_INV |
+ ARCH_PERFMON_EVENTSEL_CMASK |
+ HSW_IN_TX |
+ HSW_IN_TX_CHECKPOINTED))) {
+ config = kvm_x86_ops->pmu_ops->find_arch_event(pmc_to_pmu(pmc),
+ event_select,
+ unit_mask);
if (config != PERF_COUNT_HW_MAX)
type = PERF_TYPE_HARDWARE;
}
@@ -246,56 +166,36 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
if (type == PERF_TYPE_RAW)
config = eventsel & X86_RAW_EVENT_MASK;
- reprogram_counter(pmc, type, config,
- !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
- !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
- eventsel & ARCH_PERFMON_EVENTSEL_INT,
- (eventsel & HSW_IN_TX),
- (eventsel & HSW_IN_TX_CHECKPOINTED));
+ pmc_reprogram_counter(pmc, type, config,
+ !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
+ !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
+ eventsel & ARCH_PERFMON_EVENTSEL_INT,
+ (eventsel & HSW_IN_TX),
+ (eventsel & HSW_IN_TX_CHECKPOINTED));
}
+EXPORT_SYMBOL_GPL(reprogram_gp_counter);
-static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
+void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
{
- unsigned en = en_pmi & 0x3;
- bool pmi = en_pmi & 0x8;
+ unsigned en_field = ctrl & 0x3;
+ bool pmi = ctrl & 0x8;
- stop_counter(pmc);
+ pmc_stop_counter(pmc);
- if (!en || !pmc_enabled(pmc))
+ if (!en_field || !pmc_is_enabled(pmc))
return;
- reprogram_counter(pmc, PERF_TYPE_HARDWARE,
- arch_events[fixed_pmc_events[idx]].event_type,
- !(en & 0x2), /* exclude user */
- !(en & 0x1), /* exclude kernel */
- pmi, false, false);
+ pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
+ kvm_x86_ops->pmu_ops->find_fixed_event(idx),
+ !(en_field & 0x2), /* exclude user */
+ !(en_field & 0x1), /* exclude kernel */
+ pmi, false, false);
}
+EXPORT_SYMBOL_GPL(reprogram_fixed_counter);
-static inline u8 fixed_en_pmi(u64 ctrl, int idx)
+void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx)
{
- return (ctrl >> (idx * 4)) & 0xf;
-}
-
-static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
-{
- int i;
-
- for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
- u8 en_pmi = fixed_en_pmi(data, i);
- struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i);
-
- if (fixed_en_pmi(pmu->fixed_ctr_ctrl, i) == en_pmi)
- continue;
-
- reprogram_fixed_counter(pmc, en_pmi, i);
- }
-
- pmu->fixed_ctr_ctrl = data;
-}
-
-static void reprogram_idx(struct kvm_pmu *pmu, int idx)
-{
- struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx);
+ struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx);
if (!pmc)
return;
@@ -303,274 +203,107 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx)
if (pmc_is_gp(pmc))
reprogram_gp_counter(pmc, pmc->eventsel);
else {
- int fidx = idx - INTEL_PMC_IDX_FIXED;
- reprogram_fixed_counter(pmc,
- fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx);
+ int idx = pmc_idx - INTEL_PMC_IDX_FIXED;
+ u8 ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, idx);
+
+ reprogram_fixed_counter(pmc, ctrl, idx);
}
}
+EXPORT_SYMBOL_GPL(reprogram_counter);
-static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
+void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ u64 bitmask;
int bit;
- u64 diff = pmu->global_ctrl ^ data;
-
- pmu->global_ctrl = data;
-
- for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX)
- reprogram_idx(pmu, bit);
-}
-bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr)
-{
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
- int ret;
-
- switch (msr) {
- case MSR_CORE_PERF_FIXED_CTR_CTRL:
- case MSR_CORE_PERF_GLOBAL_STATUS:
- case MSR_CORE_PERF_GLOBAL_CTRL:
- case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
- ret = pmu->version > 1;
- break;
- default:
- ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)
- || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0)
- || get_fixed_pmc(pmu, msr);
- break;
- }
- return ret;
-}
+ bitmask = pmu->reprogram_pmi;
-int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
-{
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
- struct kvm_pmc *pmc;
+ for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
+ struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit);
- switch (index) {
- case MSR_CORE_PERF_FIXED_CTR_CTRL:
- *data = pmu->fixed_ctr_ctrl;
- return 0;
- case MSR_CORE_PERF_GLOBAL_STATUS:
- *data = pmu->global_status;
- return 0;
- case MSR_CORE_PERF_GLOBAL_CTRL:
- *data = pmu->global_ctrl;
- return 0;
- case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
- *data = pmu->global_ovf_ctrl;
- return 0;
- default:
- if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) ||
- (pmc = get_fixed_pmc(pmu, index))) {
- *data = read_pmc(pmc);
- return 0;
- } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
- *data = pmc->eventsel;
- return 0;
+ if (unlikely(!pmc || !pmc->perf_event)) {
+ clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
+ continue;
}
- }
- return 1;
-}
-int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
-{
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
- struct kvm_pmc *pmc;
- u32 index = msr_info->index;
- u64 data = msr_info->data;
-
- switch (index) {
- case MSR_CORE_PERF_FIXED_CTR_CTRL:
- if (pmu->fixed_ctr_ctrl == data)
- return 0;
- if (!(data & 0xfffffffffffff444ull)) {
- reprogram_fixed_counters(pmu, data);
- return 0;
- }
- break;
- case MSR_CORE_PERF_GLOBAL_STATUS:
- if (msr_info->host_initiated) {
- pmu->global_status = data;
- return 0;
- }
- break; /* RO MSR */
- case MSR_CORE_PERF_GLOBAL_CTRL:
- if (pmu->global_ctrl == data)
- return 0;
- if (!(data & pmu->global_ctrl_mask)) {
- global_ctrl_changed(pmu, data);
- return 0;
- }
- break;
- case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
- if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) {
- if (!msr_info->host_initiated)
- pmu->global_status &= ~data;
- pmu->global_ovf_ctrl = data;
- return 0;
- }
- break;
- default:
- if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) ||
- (pmc = get_fixed_pmc(pmu, index))) {
- if (!msr_info->host_initiated)
- data = (s64)(s32)data;
- pmc->counter += data - read_pmc(pmc);
- return 0;
- } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
- if (data == pmc->eventsel)
- return 0;
- if (!(data & pmu->reserved_bits)) {
- reprogram_gp_counter(pmc, data);
- return 0;
- }
- }
+ reprogram_counter(pmu, bit);
}
- return 1;
}
-int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc)
+/* check if idx is a valid index to access PMU */
+int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
{
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
- bool fixed = pmc & (1u << 30);
- pmc &= ~(3u << 30);
- return (!fixed && pmc >= pmu->nr_arch_gp_counters) ||
- (fixed && pmc >= pmu->nr_arch_fixed_counters);
+ return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx);
}
-int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data)
+int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
- bool fast_mode = pmc & (1u << 31);
- bool fixed = pmc & (1u << 30);
- struct kvm_pmc *counters;
- u64 ctr;
-
- pmc &= ~(3u << 30);
- if (!fixed && pmc >= pmu->nr_arch_gp_counters)
- return 1;
- if (fixed && pmc >= pmu->nr_arch_fixed_counters)
+ bool fast_mode = idx & (1u << 31);
+ struct kvm_pmc *pmc;
+ u64 ctr_val;
+
+ pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx);
+ if (!pmc)
return 1;
- counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
- ctr = read_pmc(&counters[pmc]);
+
+ ctr_val = pmc_read_counter(pmc);
if (fast_mode)
- ctr = (u32)ctr;
- *data = ctr;
+ ctr_val = (u32)ctr_val;
+ *data = ctr_val;
return 0;
}
-void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
+void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
{
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
- struct kvm_cpuid_entry2 *entry;
- union cpuid10_eax eax;
- union cpuid10_edx edx;
-
- pmu->nr_arch_gp_counters = 0;
- pmu->nr_arch_fixed_counters = 0;
- pmu->counter_bitmask[KVM_PMC_GP] = 0;
- pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
- pmu->version = 0;
- pmu->reserved_bits = 0xffffffff00200000ull;
-
- entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
- if (!entry)
- return;
- eax.full = entry->eax;
- edx.full = entry->edx;
-
- pmu->version = eax.split.version_id;
- if (!pmu->version)
- return;
-
- pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
- INTEL_PMC_MAX_GENERIC);
- pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
- pmu->available_event_types = ~entry->ebx &
- ((1ull << eax.split.mask_length) - 1);
-
- if (pmu->version == 1) {
- pmu->nr_arch_fixed_counters = 0;
- } else {
- pmu->nr_arch_fixed_counters =
- min_t(int, edx.split.num_counters_fixed,
- INTEL_PMC_MAX_FIXED);
- pmu->counter_bitmask[KVM_PMC_FIXED] =
- ((u64)1 << edx.split.bit_width_fixed) - 1;
- }
+ if (vcpu->arch.apic)
+ kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
+}
- pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
- (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
- pmu->global_ctrl_mask = ~pmu->global_ctrl;
+bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+ return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+}
- entry = kvm_find_cpuid_entry(vcpu, 7, 0);
- if (entry &&
- (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
- (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
- pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
+{
+ return kvm_x86_ops->pmu_ops->get_msr(vcpu, msr, data);
}
-void kvm_pmu_init(struct kvm_vcpu *vcpu)
+int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
- int i;
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
+ return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info);
+}
- memset(pmu, 0, sizeof(*pmu));
- for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
- pmu->gp_counters[i].type = KVM_PMC_GP;
- pmu->gp_counters[i].vcpu = vcpu;
- pmu->gp_counters[i].idx = i;
- }
- for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
- pmu->fixed_counters[i].type = KVM_PMC_FIXED;
- pmu->fixed_counters[i].vcpu = vcpu;
- pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
- }
- init_irq_work(&pmu->irq_work, trigger_pmi);
- kvm_pmu_cpuid_update(vcpu);
+/* refresh PMU settings. This function generally is called when underlying
+ * settings are changed (such as changes of PMU CPUID by guest VMs), which
+ * should rarely happen.
+ */
+void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
+{
+ kvm_x86_ops->pmu_ops->refresh(vcpu);
}
void kvm_pmu_reset(struct kvm_vcpu *vcpu)
{
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
- int i;
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
irq_work_sync(&pmu->irq_work);
- for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
- struct kvm_pmc *pmc = &pmu->gp_counters[i];
- stop_counter(pmc);
- pmc->counter = pmc->eventsel = 0;
- }
+ kvm_x86_ops->pmu_ops->reset(vcpu);
+}
- for (i = 0; i < INTEL_PMC_MAX_FIXED; i++)
- stop_counter(&pmu->fixed_counters[i]);
+void kvm_pmu_init(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
- pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
- pmu->global_ovf_ctrl = 0;
+ memset(pmu, 0, sizeof(*pmu));
+ kvm_x86_ops->pmu_ops->init(vcpu);
+ init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
+ kvm_pmu_refresh(vcpu);
}
void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
{
kvm_pmu_reset(vcpu);
}
-
-void kvm_handle_pmu_event(struct kvm_vcpu *vcpu)
-{
- struct kvm_pmu *pmu = &vcpu->arch.pmu;
- u64 bitmask;
- int bit;
-
- bitmask = pmu->reprogram_pmi;
-
- for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
- struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit);
-
- if (unlikely(!pmc || !pmc->perf_event)) {
- clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
- continue;
- }
-
- reprogram_idx(pmu, bit);
- }
-}
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
new file mode 100644
index 000000000000..f96e1f962587
--- /dev/null
+++ b/arch/x86/kvm/pmu.h
@@ -0,0 +1,118 @@
+#ifndef __KVM_X86_PMU_H
+#define __KVM_X86_PMU_H
+
+#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu)
+#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu))
+#define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu)
+
+/* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */
+#define fixed_ctrl_field(ctrl_reg, idx) (((ctrl_reg) >> ((idx)*4)) & 0xf)
+
+struct kvm_event_hw_type_mapping {
+ u8 eventsel;
+ u8 unit_mask;
+ unsigned event_type;
+};
+
+struct kvm_pmu_ops {
+ unsigned (*find_arch_event)(struct kvm_pmu *pmu, u8 event_select,
+ u8 unit_mask);
+ unsigned (*find_fixed_event)(int idx);
+ bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
+ struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
+ struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx);
+ int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
+ bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
+ int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
+ int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+ void (*refresh)(struct kvm_vcpu *vcpu);
+ void (*init)(struct kvm_vcpu *vcpu);
+ void (*reset)(struct kvm_vcpu *vcpu);
+};
+
+static inline u64 pmc_bitmask(struct kvm_pmc *pmc)
+{
+ struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+ return pmu->counter_bitmask[pmc->type];
+}
+
+static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
+{
+ u64 counter, enabled, running;
+
+ counter = pmc->counter;
+ if (pmc->perf_event)
+ counter += perf_event_read_value(pmc->perf_event,
+ &enabled, &running);
+ /* FIXME: Scaling needed? */
+ return counter & pmc_bitmask(pmc);
+}
+
+static inline void pmc_stop_counter(struct kvm_pmc *pmc)
+{
+ if (pmc->perf_event) {
+ pmc->counter = pmc_read_counter(pmc);
+ perf_event_release_kernel(pmc->perf_event);
+ pmc->perf_event = NULL;
+ }
+}
+
+static inline bool pmc_is_gp(struct kvm_pmc *pmc)
+{
+ return pmc->type == KVM_PMC_GP;
+}
+
+static inline bool pmc_is_fixed(struct kvm_pmc *pmc)
+{
+ return pmc->type == KVM_PMC_FIXED;
+}
+
+static inline bool pmc_is_enabled(struct kvm_pmc *pmc)
+{
+ return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc);
+}
+
+/* returns general purpose PMC with the specified MSR. Note that it can be
+ * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a
+ * paramenter to tell them apart.
+ */
+static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
+ u32 base)
+{
+ if (msr >= base && msr < base + pmu->nr_arch_gp_counters)
+ return &pmu->gp_counters[msr - base];
+
+ return NULL;
+}
+
+/* returns fixed PMC with the specified MSR */
+static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
+{
+ int base = MSR_CORE_PERF_FIXED_CTR0;
+
+ if (msr >= base && msr < base + pmu->nr_arch_fixed_counters)
+ return &pmu->fixed_counters[msr - base];
+
+ return NULL;
+}
+
+void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel);
+void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx);
+void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
+
+void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
+void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
+int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
+int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx);
+bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
+int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
+int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
+void kvm_pmu_reset(struct kvm_vcpu *vcpu);
+void kvm_pmu_init(struct kvm_vcpu *vcpu);
+void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
+
+extern struct kvm_pmu_ops intel_pmu_ops;
+extern struct kvm_pmu_ops amd_pmu_ops;
+#endif /* __KVM_X86_PMU_H */
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
new file mode 100644
index 000000000000..886aa25a7131
--- /dev/null
+++ b/arch/x86/kvm/pmu_amd.c
@@ -0,0 +1,207 @@
+/*
+ * KVM PMU support for AMD
+ *
+ * Copyright 2015, Red Hat, Inc. and/or its affiliates.
+ *
+ * Author:
+ * Wei Huang <wei@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Implementation is based on pmu_intel.c file
+ */
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include "x86.h"
+#include "cpuid.h"
+#include "lapic.h"
+#include "pmu.h"
+
+/* duplicated from amd_perfmon_event_map, K7 and above should work. */
+static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
+ [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
+ [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
+ [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
+ [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+ [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+ [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
+ [6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
+ [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
+};
+
+static unsigned amd_find_arch_event(struct kvm_pmu *pmu,
+ u8 event_select,
+ u8 unit_mask)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++)
+ if (amd_event_mapping[i].eventsel == event_select
+ && amd_event_mapping[i].unit_mask == unit_mask)
+ break;
+
+ if (i == ARRAY_SIZE(amd_event_mapping))
+ return PERF_COUNT_HW_MAX;
+
+ return amd_event_mapping[i].event_type;
+}
+
+/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */
+static unsigned amd_find_fixed_event(int idx)
+{
+ return PERF_COUNT_HW_MAX;
+}
+
+/* check if a PMC is enabled by comparing it against global_ctrl bits. Because
+ * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE).
+ */
+static bool amd_pmc_is_enabled(struct kvm_pmc *pmc)
+{
+ return true;
+}
+
+static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
+{
+ return get_gp_pmc(pmu, MSR_K7_EVNTSEL0 + pmc_idx, MSR_K7_EVNTSEL0);
+}
+
+/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
+static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+ idx &= ~(3u << 30);
+
+ return (idx >= pmu->nr_arch_gp_counters);
+}
+
+/* idx is the ECX register of RDPMC instruction */
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_pmc *counters;
+
+ idx &= ~(3u << 30);
+ if (idx >= pmu->nr_arch_gp_counters)
+ return NULL;
+ counters = pmu->gp_counters;
+
+ return &counters[idx];
+}
+
+static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ int ret = false;
+
+ ret = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0) ||
+ get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0);
+
+ return ret;
+}
+
+static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_pmc *pmc;
+
+ /* MSR_K7_PERFCTRn */
+ pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0);
+ if (pmc) {
+ *data = pmc_read_counter(pmc);
+ return 0;
+ }
+ /* MSR_K7_EVNTSELn */
+ pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0);
+ if (pmc) {
+ *data = pmc->eventsel;
+ return 0;
+ }
+
+ return 1;
+}
+
+static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_pmc *pmc;
+ u32 msr = msr_info->index;
+ u64 data = msr_info->data;
+
+ /* MSR_K7_PERFCTRn */
+ pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0);
+ if (pmc) {
+ if (!msr_info->host_initiated)
+ data = (s64)data;
+ pmc->counter += data - pmc_read_counter(pmc);
+ return 0;
+ }
+ /* MSR_K7_EVNTSELn */
+ pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0);
+ if (pmc) {
+ if (data == pmc->eventsel)
+ return 0;
+ if (!(data & pmu->reserved_bits)) {
+ reprogram_gp_counter(pmc, data);
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+ pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
+ pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
+ pmu->reserved_bits = 0xffffffff00200000ull;
+ /* not applicable to AMD; but clean them to prevent any fall out */
+ pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
+ pmu->nr_arch_fixed_counters = 0;
+ pmu->version = 0;
+ pmu->global_status = 0;
+}
+
+static void amd_pmu_init(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ int i;
+
+ for (i = 0; i < AMD64_NUM_COUNTERS ; i++) {
+ pmu->gp_counters[i].type = KVM_PMC_GP;
+ pmu->gp_counters[i].vcpu = vcpu;
+ pmu->gp_counters[i].idx = i;
+ }
+}
+
+static void amd_pmu_reset(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ int i;
+
+ for (i = 0; i < AMD64_NUM_COUNTERS; i++) {
+ struct kvm_pmc *pmc = &pmu->gp_counters[i];
+
+ pmc_stop_counter(pmc);
+ pmc->counter = pmc->eventsel = 0;
+ }
+}
+
+struct kvm_pmu_ops amd_pmu_ops = {
+ .find_arch_event = amd_find_arch_event,
+ .find_fixed_event = amd_find_fixed_event,
+ .pmc_is_enabled = amd_pmc_is_enabled,
+ .pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
+ .msr_idx_to_pmc = amd_msr_idx_to_pmc,
+ .is_valid_msr_idx = amd_is_valid_msr_idx,
+ .is_valid_msr = amd_is_valid_msr,
+ .get_msr = amd_pmu_get_msr,
+ .set_msr = amd_pmu_set_msr,
+ .refresh = amd_pmu_refresh,
+ .init = amd_pmu_init,
+ .reset = amd_pmu_reset,
+};
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
new file mode 100644
index 000000000000..ab38af4f4947
--- /dev/null
+++ b/arch/x86/kvm/pmu_intel.c
@@ -0,0 +1,358 @@
+/*
+ * KVM PMU support for Intel CPUs
+ *
+ * Copyright 2011 Red Hat, Inc. and/or its affiliates.
+ *
+ * Authors:
+ * Avi Kivity <avi@redhat.com>
+ * Gleb Natapov <gleb@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include <asm/perf_event.h>
+#include "x86.h"
+#include "cpuid.h"
+#include "lapic.h"
+#include "pmu.h"
+
+static struct kvm_event_hw_type_mapping intel_arch_events[] = {
+ /* Index must match CPUID 0x0A.EBX bit vector */
+ [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES },
+ [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
+ [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES },
+ [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES },
+ [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
+ [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+ [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
+ [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
+};
+
+/* mapping between fixed pmc index and intel_arch_events array */
+static int fixed_pmc_events[] = {1, 0, 7};
+
+static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
+{
+ int i;
+
+ for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
+ u8 new_ctrl = fixed_ctrl_field(data, i);
+ u8 old_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, i);
+ struct kvm_pmc *pmc;
+
+ pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i);
+
+ if (old_ctrl == new_ctrl)
+ continue;
+
+ reprogram_fixed_counter(pmc, new_ctrl, i);
+ }
+
+ pmu->fixed_ctr_ctrl = data;
+}
+
+/* function is called when global control register has been updated. */
+static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
+{
+ int bit;
+ u64 diff = pmu->global_ctrl ^ data;
+
+ pmu->global_ctrl = data;
+
+ for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX)
+ reprogram_counter(pmu, bit);
+}
+
+static unsigned intel_find_arch_event(struct kvm_pmu *pmu,
+ u8 event_select,
+ u8 unit_mask)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++)
+ if (intel_arch_events[i].eventsel == event_select
+ && intel_arch_events[i].unit_mask == unit_mask
+ && (pmu->available_event_types & (1 << i)))
+ break;
+
+ if (i == ARRAY_SIZE(intel_arch_events))
+ return PERF_COUNT_HW_MAX;
+
+ return intel_arch_events[i].event_type;
+}
+
+static unsigned intel_find_fixed_event(int idx)
+{
+ if (idx >= ARRAY_SIZE(fixed_pmc_events))
+ return PERF_COUNT_HW_MAX;
+
+ return intel_arch_events[fixed_pmc_events[idx]].event_type;
+}
+
+/* check if a PMC is enabled by comparising it with globl_ctrl bits. */
+static bool intel_pmc_is_enabled(struct kvm_pmc *pmc)
+{
+ struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+ return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl);
+}
+
+static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
+{
+ if (pmc_idx < INTEL_PMC_IDX_FIXED)
+ return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + pmc_idx,
+ MSR_P6_EVNTSEL0);
+ else {
+ u32 idx = pmc_idx - INTEL_PMC_IDX_FIXED;
+
+ return get_fixed_pmc(pmu, idx + MSR_CORE_PERF_FIXED_CTR0);
+ }
+}
+
+/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
+static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ bool fixed = idx & (1u << 30);
+
+ idx &= ~(3u << 30);
+
+ return (!fixed && idx >= pmu->nr_arch_gp_counters) ||
+ (fixed && idx >= pmu->nr_arch_fixed_counters);
+}
+
+static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
+ unsigned idx)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ bool fixed = idx & (1u << 30);
+ struct kvm_pmc *counters;
+
+ idx &= ~(3u << 30);
+ if (!fixed && idx >= pmu->nr_arch_gp_counters)
+ return NULL;
+ if (fixed && idx >= pmu->nr_arch_fixed_counters)
+ return NULL;
+ counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
+
+ return &counters[idx];
+}
+
+static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ int ret;
+
+ switch (msr) {
+ case MSR_CORE_PERF_FIXED_CTR_CTRL:
+ case MSR_CORE_PERF_GLOBAL_STATUS:
+ case MSR_CORE_PERF_GLOBAL_CTRL:
+ case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+ ret = pmu->version > 1;
+ break;
+ default:
+ ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) ||
+ get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) ||
+ get_fixed_pmc(pmu, msr);
+ break;
+ }
+
+ return ret;
+}
+
+static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_pmc *pmc;
+
+ switch (msr) {
+ case MSR_CORE_PERF_FIXED_CTR_CTRL:
+ *data = pmu->fixed_ctr_ctrl;
+ return 0;
+ case MSR_CORE_PERF_GLOBAL_STATUS:
+ *data = pmu->global_status;
+ return 0;
+ case MSR_CORE_PERF_GLOBAL_CTRL:
+ *data = pmu->global_ctrl;
+ return 0;
+ case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+ *data = pmu->global_ovf_ctrl;
+ return 0;
+ default:
+ if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
+ (pmc = get_fixed_pmc(pmu, msr))) {
+ *data = pmc_read_counter(pmc);
+ return 0;
+ } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
+ *data = pmc->eventsel;
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_pmc *pmc;
+ u32 msr = msr_info->index;
+ u64 data = msr_info->data;
+
+ switch (msr) {
+ case MSR_CORE_PERF_FIXED_CTR_CTRL:
+ if (pmu->fixed_ctr_ctrl == data)
+ return 0;
+ if (!(data & 0xfffffffffffff444ull)) {
+ reprogram_fixed_counters(pmu, data);
+ return 0;
+ }
+ break;
+ case MSR_CORE_PERF_GLOBAL_STATUS:
+ if (msr_info->host_initiated) {
+ pmu->global_status = data;
+ return 0;
+ }
+ break; /* RO MSR */
+ case MSR_CORE_PERF_GLOBAL_CTRL:
+ if (pmu->global_ctrl == data)
+ return 0;
+ if (!(data & pmu->global_ctrl_mask)) {
+ global_ctrl_changed(pmu, data);
+ return 0;
+ }
+ break;
+ case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+ if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) {
+ if (!msr_info->host_initiated)
+ pmu->global_status &= ~data;
+ pmu->global_ovf_ctrl = data;
+ return 0;
+ }
+ break;
+ default:
+ if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
+ (pmc = get_fixed_pmc(pmu, msr))) {
+ if (!msr_info->host_initiated)
+ data = (s64)(s32)data;
+ pmc->counter += data - pmc_read_counter(pmc);
+ return 0;
+ } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
+ if (data == pmc->eventsel)
+ return 0;
+ if (!(data & pmu->reserved_bits)) {
+ reprogram_gp_counter(pmc, data);
+ return 0;
+ }
+ }
+ }
+
+ return 1;
+}
+
+static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_cpuid_entry2 *entry;
+ union cpuid10_eax eax;
+ union cpuid10_edx edx;
+
+ pmu->nr_arch_gp_counters = 0;
+ pmu->nr_arch_fixed_counters = 0;
+ pmu->counter_bitmask[KVM_PMC_GP] = 0;
+ pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
+ pmu->version = 0;
+ pmu->reserved_bits = 0xffffffff00200000ull;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+ if (!entry)
+ return;
+ eax.full = entry->eax;
+ edx.full = entry->edx;
+
+ pmu->version = eax.split.version_id;
+ if (!pmu->version)
+ return;
+
+ pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
+ INTEL_PMC_MAX_GENERIC);
+ pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
+ pmu->available_event_types = ~entry->ebx &
+ ((1ull << eax.split.mask_length) - 1);
+
+ if (pmu->version == 1) {
+ pmu->nr_arch_fixed_counters = 0;
+ } else {
+ pmu->nr_arch_fixed_counters =
+ min_t(int, edx.split.num_counters_fixed,
+ INTEL_PMC_MAX_FIXED);
+ pmu->counter_bitmask[KVM_PMC_FIXED] =
+ ((u64)1 << edx.split.bit_width_fixed) - 1;
+ }
+
+ pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+ (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
+ pmu->global_ctrl_mask = ~pmu->global_ctrl;
+
+ entry = kvm_find_cpuid_entry(vcpu, 7, 0);
+ if (entry &&
+ (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
+ (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
+ pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+}
+
+static void intel_pmu_init(struct kvm_vcpu *vcpu)
+{
+ int i;
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+ for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
+ pmu->gp_counters[i].type = KVM_PMC_GP;
+ pmu->gp_counters[i].vcpu = vcpu;
+ pmu->gp_counters[i].idx = i;
+ }
+
+ for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
+ pmu->fixed_counters[i].type = KVM_PMC_FIXED;
+ pmu->fixed_counters[i].vcpu = vcpu;
+ pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
+ }
+}
+
+static void intel_pmu_reset(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ int i;
+
+ for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
+ struct kvm_pmc *pmc = &pmu->gp_counters[i];
+
+ pmc_stop_counter(pmc);
+ pmc->counter = pmc->eventsel = 0;
+ }
+
+ for (i = 0; i < INTEL_PMC_MAX_FIXED; i++)
+ pmc_stop_counter(&pmu->fixed_counters[i]);
+
+ pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
+ pmu->global_ovf_ctrl = 0;
+}
+
+struct kvm_pmu_ops intel_pmu_ops = {
+ .find_arch_event = intel_find_arch_event,
+ .find_fixed_event = intel_find_fixed_event,
+ .pmc_is_enabled = intel_pmc_is_enabled,
+ .pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
+ .msr_idx_to_pmc = intel_msr_idx_to_pmc,
+ .is_valid_msr_idx = intel_is_valid_msr_idx,
+ .is_valid_msr = intel_is_valid_msr,
+ .get_msr = intel_pmu_get_msr,
+ .set_msr = intel_pmu_set_msr,
+ .refresh = intel_pmu_refresh,
+ .init = intel_pmu_init,
+ .reset = intel_pmu_reset,
+};
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ce741b8650f6..851a9a1c6dfc 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -21,6 +21,7 @@
#include "kvm_cache_regs.h"
#include "x86.h"
#include "cpuid.h"
+#include "pmu.h"
#include <linux/module.h>
#include <linux/mod_devicetable.h>
@@ -511,8 +512,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- if (svm->vmcb->control.next_rip != 0)
+ if (svm->vmcb->control.next_rip != 0) {
+ WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
svm->next_rip = svm->vmcb->control.next_rip;
+ }
if (!svm->next_rip) {
if (emulate_instruction(vcpu, EMULTYPE_SKIP) !=
@@ -1082,7 +1085,7 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
return target_tsc - tsc;
}
-static void init_vmcb(struct vcpu_svm *svm)
+static void init_vmcb(struct vcpu_svm *svm, bool init_event)
{
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
@@ -1153,17 +1156,17 @@ static void init_vmcb(struct vcpu_svm *svm)
init_sys_seg(&save->ldtr, SEG_TYPE_LDT);
init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16);
- svm_set_efer(&svm->vcpu, 0);
+ if (!init_event)
+ svm_set_efer(&svm->vcpu, 0);
save->dr6 = 0xffff0ff0;
kvm_set_rflags(&svm->vcpu, 2);
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
/*
- * This is the guest-visible cr0 value.
* svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
+ * It also updates the guest-visible cr0 value.
*/
- svm->vcpu.arch.cr0 = 0;
(void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
save->cr4 = X86_CR4_PAE;
@@ -1176,7 +1179,7 @@ static void init_vmcb(struct vcpu_svm *svm)
clr_exception_intercept(svm, PF_VECTOR);
clr_cr_intercept(svm, INTERCEPT_CR3_READ);
clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
- save->g_pat = 0x0007040600070406ULL;
+ save->g_pat = svm->vcpu.arch.pat;
save->cr3 = 0;
save->cr4 = 0;
}
@@ -1195,13 +1198,19 @@ static void init_vmcb(struct vcpu_svm *svm)
enable_gif(svm);
}
-static void svm_vcpu_reset(struct kvm_vcpu *vcpu)
+static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct vcpu_svm *svm = to_svm(vcpu);
u32 dummy;
u32 eax = 1;
- init_vmcb(svm);
+ if (!init_event) {
+ svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
+ MSR_IA32_APICBASE_ENABLE;
+ if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
+ svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
+ }
+ init_vmcb(svm, init_event);
kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy);
kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
@@ -1257,12 +1266,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
clear_page(svm->vmcb);
svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
svm->asid_generation = 0;
- init_vmcb(svm);
-
- svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
- MSR_IA32_APICBASE_ENABLE;
- if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
- svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
+ init_vmcb(svm, false);
svm_init_osvw(&svm->vcpu);
@@ -1575,7 +1579,8 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
* does not do it - this results in some delay at
* reboot
*/
- cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+ if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED))
+ cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
mark_dirty(svm->vmcb, VMCB_CR);
update_cr0_intercept(svm);
@@ -1883,7 +1888,7 @@ static int shutdown_interception(struct vcpu_svm *svm)
* so reinitialize it.
*/
clear_page(svm->vmcb);
- init_vmcb(svm);
+ init_vmcb(svm, false);
kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
return 0;
@@ -1953,8 +1958,8 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
u64 pdpte;
int ret;
- ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte,
- offset_in_page(cr3) + index * 8, 8);
+ ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte,
+ offset_in_page(cr3) + index * 8, 8);
if (ret)
return 0;
return pdpte;
@@ -2112,7 +2117,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
might_sleep();
- page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
+ page = kvm_vcpu_gfn_to_page(&svm->vcpu, gpa >> PAGE_SHIFT);
if (is_error_page(page))
goto error;
@@ -2151,7 +2156,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
mask = (0xf >> (4 - size)) << start_bit;
val = 0;
- if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, iopm_len))
+ if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len))
return NESTED_EXIT_DONE;
return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
@@ -2176,7 +2181,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
/* Offset is in 32 bit units but need in 8 bit units */
offset *= 4;
- if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4))
+ if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4))
return NESTED_EXIT_DONE;
return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
@@ -2447,7 +2452,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
p = msrpm_offsets[i];
offset = svm->nested.vmcb_msrpm + (p * 4);
- if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4))
+ if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4))
return false;
svm->nested.msrpm[p] = svm->msrpm[p] | value;
@@ -3067,42 +3072,42 @@ static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
svm_scale_tsc(vcpu, host_tsc);
}
-static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
+static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
struct vcpu_svm *svm = to_svm(vcpu);
- switch (ecx) {
+ switch (msr_info->index) {
case MSR_IA32_TSC: {
- *data = svm->vmcb->control.tsc_offset +
+ msr_info->data = svm->vmcb->control.tsc_offset +
svm_scale_tsc(vcpu, native_read_tsc());
break;
}
case MSR_STAR:
- *data = svm->vmcb->save.star;
+ msr_info->data = svm->vmcb->save.star;
break;
#ifdef CONFIG_X86_64
case MSR_LSTAR:
- *data = svm->vmcb->save.lstar;
+ msr_info->data = svm->vmcb->save.lstar;
break;
case MSR_CSTAR:
- *data = svm->vmcb->save.cstar;
+ msr_info->data = svm->vmcb->save.cstar;
break;
case MSR_KERNEL_GS_BASE:
- *data = svm->vmcb->save.kernel_gs_base;
+ msr_info->data = svm->vmcb->save.kernel_gs_base;
break;
case MSR_SYSCALL_MASK:
- *data = svm->vmcb->save.sfmask;
+ msr_info->data = svm->vmcb->save.sfmask;
break;
#endif
case MSR_IA32_SYSENTER_CS:
- *data = svm->vmcb->save.sysenter_cs;
+ msr_info->data = svm->vmcb->save.sysenter_cs;
break;
case MSR_IA32_SYSENTER_EIP:
- *data = svm->sysenter_eip;
+ msr_info->data = svm->sysenter_eip;
break;
case MSR_IA32_SYSENTER_ESP:
- *data = svm->sysenter_esp;
+ msr_info->data = svm->sysenter_esp;
break;
/*
* Nobody will change the following 5 values in the VMCB so we can
@@ -3110,31 +3115,31 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
* implemented.
*/
case MSR_IA32_DEBUGCTLMSR:
- *data = svm->vmcb->save.dbgctl;
+ msr_info->data = svm->vmcb->save.dbgctl;
break;
case MSR_IA32_LASTBRANCHFROMIP:
- *data = svm->vmcb->save.br_from;
+ msr_info->data = svm->vmcb->save.br_from;
break;
case MSR_IA32_LASTBRANCHTOIP:
- *data = svm->vmcb->save.br_to;
+ msr_info->data = svm->vmcb->save.br_to;
break;
case MSR_IA32_LASTINTFROMIP:
- *data = svm->vmcb->save.last_excp_from;
+ msr_info->data = svm->vmcb->save.last_excp_from;
break;
case MSR_IA32_LASTINTTOIP:
- *data = svm->vmcb->save.last_excp_to;
+ msr_info->data = svm->vmcb->save.last_excp_to;
break;
case MSR_VM_HSAVE_PA:
- *data = svm->nested.hsave_msr;
+ msr_info->data = svm->nested.hsave_msr;
break;
case MSR_VM_CR:
- *data = svm->nested.vm_cr_msr;
+ msr_info->data = svm->nested.vm_cr_msr;
break;
case MSR_IA32_UCODE_REV:
- *data = 0x01000065;
+ msr_info->data = 0x01000065;
break;
default:
- return kvm_get_msr_common(vcpu, ecx, data);
+ return kvm_get_msr_common(vcpu, msr_info);
}
return 0;
}
@@ -3142,16 +3147,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
static int rdmsr_interception(struct vcpu_svm *svm)
{
u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
- u64 data;
+ struct msr_data msr_info;
- if (svm_get_msr(&svm->vcpu, ecx, &data)) {
+ msr_info.index = ecx;
+ msr_info.host_initiated = false;
+ if (svm_get_msr(&svm->vcpu, &msr_info)) {
trace_kvm_msr_read_ex(ecx);
kvm_inject_gp(&svm->vcpu, 0);
} else {
- trace_kvm_msr_read(ecx, data);
+ trace_kvm_msr_read(ecx, msr_info.data);
- kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff);
- kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32);
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RAX,
+ msr_info.data & 0xffffffff);
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RDX,
+ msr_info.data >> 32);
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
skip_emulated_instruction(&svm->vcpu);
}
@@ -3388,6 +3397,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_MWAIT] = mwait_interception,
[SVM_EXIT_XSETBV] = xsetbv_interception,
[SVM_EXIT_NPF] = pf_interception,
+ [SVM_EXIT_RSM] = emulate_on_interception,
};
static void dump_vmcb(struct kvm_vcpu *vcpu)
@@ -4073,6 +4083,11 @@ static bool svm_cpu_has_accelerated_tpr(void)
return false;
}
+static bool svm_has_high_real_mode_segbase(void)
+{
+ return true;
+}
+
static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
return 0;
@@ -4317,7 +4332,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
break;
}
- vmcb->control.next_rip = info->next_rip;
+ /* TODO: Advertise NRIPS to guest hypervisor unconditionally */
+ if (static_cpu_has(X86_FEATURE_NRIPS))
+ vmcb->control.next_rip = info->next_rip;
vmcb->control.exit_code = icpt_info.exit_code;
vmexit = nested_svm_exit_handled(svm);
@@ -4346,6 +4363,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.hardware_enable = svm_hardware_enable,
.hardware_disable = svm_hardware_disable,
.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
+ .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
.vcpu_create = svm_create_vcpu,
.vcpu_free = svm_free_vcpu,
@@ -4381,6 +4399,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
+ .fpu_activate = svm_fpu_activate,
.fpu_deactivate = svm_fpu_deactivate,
.tlb_flush = svm_flush_tlb,
@@ -4439,6 +4458,8 @@ static struct kvm_x86_ops svm_x86_ops = {
.handle_external_intr = svm_handle_external_intr,
.sched_in = svm_sched_in,
+
+ .pmu_ops = &amd_pmu_ops,
};
static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 7c7bc8bef21f..4eae7c35ddf5 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -952,6 +952,28 @@ TRACE_EVENT(kvm_wait_lapic_expire,
__entry->delta < 0 ? "early" : "late")
);
+TRACE_EVENT(kvm_enter_smm,
+ TP_PROTO(unsigned int vcpu_id, u64 smbase, bool entering),
+ TP_ARGS(vcpu_id, smbase, entering),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, vcpu_id )
+ __field( u64, smbase )
+ __field( bool, entering )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu_id;
+ __entry->smbase = smbase;
+ __entry->entering = entering;
+ ),
+
+ TP_printk("vcpu %u: %s SMM, smbase 0x%llx",
+ __entry->vcpu_id,
+ __entry->entering ? "entering" : "leaving",
+ __entry->smbase)
+);
+
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7b61687bd79..ab53d80b0f64 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -40,14 +40,14 @@
#include <asm/vmx.h>
#include <asm/virtext.h>
#include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
+#include <asm/fpu/internal.h>
#include <asm/perf_event.h>
#include <asm/debugreg.h>
#include <asm/kexec.h>
#include <asm/apic.h>
#include "trace.h"
+#include "pmu.h"
#define __ex(x) __kvm_handle_fault_on_reboot(x)
#define __ex_clear(x, reg) \
@@ -786,7 +786,7 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
{
- struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT);
+ struct page *page = kvm_vcpu_gfn_to_page(vcpu, addr >> PAGE_SHIFT);
if (is_error_page(page))
return NULL;
@@ -1883,7 +1883,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
* If the FPU is not active (through the host task or
* the guest vcpu), then restore the cr0.TS bit.
*/
- if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+ if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded)
stts();
load_gdt(this_cpu_ptr(&host_gdt));
}
@@ -2170,8 +2170,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
if (is_guest_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_nested;
- else if (irqchip_in_kernel(vcpu->kvm) &&
- apic_x2apic_mode(vcpu->arch.apic)) {
+ else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
if (is_long_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
else
@@ -2623,76 +2622,69 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
* Returns 0 on success, non-0 otherwise.
* Assumes vcpu_load() was already called.
*/
-static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
- u64 data;
struct shared_msr_entry *msr;
- if (!pdata) {
- printk(KERN_ERR "BUG: get_msr called with NULL pdata\n");
- return -EINVAL;
- }
-
- switch (msr_index) {
+ switch (msr_info->index) {
#ifdef CONFIG_X86_64
case MSR_FS_BASE:
- data = vmcs_readl(GUEST_FS_BASE);
+ msr_info->data = vmcs_readl(GUEST_FS_BASE);
break;
case MSR_GS_BASE:
- data = vmcs_readl(GUEST_GS_BASE);
+ msr_info->data = vmcs_readl(GUEST_GS_BASE);
break;
case MSR_KERNEL_GS_BASE:
vmx_load_host_state(to_vmx(vcpu));
- data = to_vmx(vcpu)->msr_guest_kernel_gs_base;
+ msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base;
break;
#endif
case MSR_EFER:
- return kvm_get_msr_common(vcpu, msr_index, pdata);
+ return kvm_get_msr_common(vcpu, msr_info);
case MSR_IA32_TSC:
- data = guest_read_tsc();
+ msr_info->data = guest_read_tsc();
break;
case MSR_IA32_SYSENTER_CS:
- data = vmcs_read32(GUEST_SYSENTER_CS);
+ msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
break;
case MSR_IA32_SYSENTER_EIP:
- data = vmcs_readl(GUEST_SYSENTER_EIP);
+ msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP);
break;
case MSR_IA32_SYSENTER_ESP:
- data = vmcs_readl(GUEST_SYSENTER_ESP);
+ msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
case MSR_IA32_BNDCFGS:
if (!vmx_mpx_supported())
return 1;
- data = vmcs_read64(GUEST_BNDCFGS);
+ msr_info->data = vmcs_read64(GUEST_BNDCFGS);
break;
case MSR_IA32_FEATURE_CONTROL:
if (!nested_vmx_allowed(vcpu))
return 1;
- data = to_vmx(vcpu)->nested.msr_ia32_feature_control;
+ msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control;
break;
case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
if (!nested_vmx_allowed(vcpu))
return 1;
- return vmx_get_vmx_msr(vcpu, msr_index, pdata);
+ return vmx_get_vmx_msr(vcpu, msr_info->index, &msr_info->data);
case MSR_IA32_XSS:
if (!vmx_xsaves_supported())
return 1;
- data = vcpu->arch.ia32_xss;
+ msr_info->data = vcpu->arch.ia32_xss;
break;
case MSR_TSC_AUX:
if (!to_vmx(vcpu)->rdtscp_enabled)
return 1;
/* Otherwise falls through */
default:
- msr = find_msr_entry(to_vmx(vcpu), msr_index);
+ msr = find_msr_entry(to_vmx(vcpu), msr_info->index);
if (msr) {
- data = msr->data;
+ msr_info->data = msr->data;
break;
}
- return kvm_get_msr_common(vcpu, msr_index, pdata);
+ return kvm_get_msr_common(vcpu, msr_info);
}
- *pdata = data;
return 0;
}
@@ -4123,7 +4115,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
kvm_userspace_mem.flags = 0;
kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE;
kvm_userspace_mem.memory_size = PAGE_SIZE;
- r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
+ r = __x86_set_memory_region(kvm, &kvm_userspace_mem);
if (r)
goto out;
@@ -4158,7 +4150,7 @@ static int alloc_identity_pagetable(struct kvm *kvm)
kvm_userspace_mem.guest_phys_addr =
kvm->arch.ept_identity_map_addr;
kvm_userspace_mem.memory_size = PAGE_SIZE;
- r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
+ r = __x86_set_memory_region(kvm, &kvm_userspace_mem);
return r;
}
@@ -4667,16 +4659,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
- if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
- u32 msr_low, msr_high;
- u64 host_pat;
- rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
- host_pat = msr_low | ((u64) msr_high << 32);
- /* Write the default value follow host pat */
- vmcs_write64(GUEST_IA32_PAT, host_pat);
- /* Keep arch.pat sync with GUEST_IA32_PAT */
- vmx->vcpu.arch.pat = host_pat;
- }
+ if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
+ vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
u32 index = vmx_msr_index[i];
@@ -4708,22 +4692,27 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
return 0;
}
-static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
+static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct msr_data apic_base_msr;
+ u64 cr0;
vmx->rmode.vm86_active = 0;
vmx->soft_vnmi_blocked = 0;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
- kvm_set_cr8(&vmx->vcpu, 0);
- apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
- if (kvm_vcpu_is_reset_bsp(&vmx->vcpu))
- apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
- apic_base_msr.host_initiated = true;
- kvm_set_apic_base(&vmx->vcpu, &apic_base_msr);
+ kvm_set_cr8(vcpu, 0);
+
+ if (!init_event) {
+ apic_base_msr.data = APIC_DEFAULT_PHYS_BASE |
+ MSR_IA32_APICBASE_ENABLE;
+ if (kvm_vcpu_is_reset_bsp(vcpu))
+ apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
+ apic_base_msr.host_initiated = true;
+ kvm_set_apic_base(vcpu, &apic_base_msr);
+ }
vmx_segment_cache_clear(vmx);
@@ -4747,9 +4736,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);
- vmcs_write32(GUEST_SYSENTER_CS, 0);
- vmcs_writel(GUEST_SYSENTER_ESP, 0);
- vmcs_writel(GUEST_SYSENTER_EIP, 0);
+ if (!init_event) {
+ vmcs_write32(GUEST_SYSENTER_CS, 0);
+ vmcs_writel(GUEST_SYSENTER_ESP, 0);
+ vmcs_writel(GUEST_SYSENTER_EIP, 0);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+ }
vmcs_writel(GUEST_RFLAGS, 0x02);
kvm_rip_write(vcpu, 0xfff0);
@@ -4764,18 +4756,15 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
- /* Special registers */
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
-
setup_msrs(vmx);
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */
- if (cpu_has_vmx_tpr_shadow()) {
+ if (cpu_has_vmx_tpr_shadow() && !init_event) {
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
- if (vm_need_tpr_shadow(vmx->vcpu.kvm))
+ if (vm_need_tpr_shadow(vcpu->kvm))
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
- __pa(vmx->vcpu.arch.apic->regs));
+ __pa(vcpu->arch.apic->regs));
vmcs_write32(TPR_THRESHOLD, 0);
}
@@ -4787,12 +4776,14 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
if (vmx->vpid != 0)
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
- vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
- vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */
- vmx_set_cr4(&vmx->vcpu, 0);
- vmx_set_efer(&vmx->vcpu, 0);
- vmx_fpu_activate(&vmx->vcpu);
- update_exception_bitmap(&vmx->vcpu);
+ cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+ vmx_set_cr0(vcpu, cr0); /* enter rmode */
+ vmx->vcpu.arch.cr0 = cr0;
+ vmx_set_cr4(vcpu, 0);
+ if (!init_event)
+ vmx_set_efer(vcpu, 0);
+ vmx_fpu_activate(vcpu);
+ update_exception_bitmap(vcpu);
vpid_sync_context(vmx);
}
@@ -4965,7 +4956,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
.flags = 0,
};
- ret = kvm_set_memory_region(kvm, &tss_mem);
+ ret = x86_set_memory_region(kvm, &tss_mem);
if (ret)
return ret;
kvm->arch.tss_addr = addr;
@@ -5475,19 +5466,21 @@ static int handle_cpuid(struct kvm_vcpu *vcpu)
static int handle_rdmsr(struct kvm_vcpu *vcpu)
{
u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
- u64 data;
+ struct msr_data msr_info;
- if (vmx_get_msr(vcpu, ecx, &data)) {
+ msr_info.index = ecx;
+ msr_info.host_initiated = false;
+ if (vmx_get_msr(vcpu, &msr_info)) {
trace_kvm_msr_read_ex(ecx);
kvm_inject_gp(vcpu, 0);
return 1;
}
- trace_kvm_msr_read(ecx, data);
+ trace_kvm_msr_read(ecx, msr_info.data);
/* FIXME: handling of bits 32:63 of rax, rdx */
- vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u;
- vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u;
+ vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u;
+ vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u;
skip_emulated_instruction(vcpu);
return 1;
}
@@ -5710,9 +5703,6 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
return 0;
}
- /* clear all local breakpoint enable flags */
- vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x155);
-
/*
* TODO: What about debug traps on tss switch?
* Are we supposed to inject them and update dr6?
@@ -7333,7 +7323,7 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
bitmap += (port & 0x7fff) / 8;
if (last_bitmap != bitmap)
- if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1))
+ if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1))
return true;
if (b & (1 << (port & 7)))
return true;
@@ -7377,7 +7367,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
/* Then read the msr_index'th bit from this bitmap: */
if (msr_index < 1024*8) {
unsigned char b;
- if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1))
+ if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1))
return true;
return 1 & (b >> (msr_index & 7));
} else
@@ -7642,9 +7632,9 @@ static void vmx_disable_pml(struct vcpu_vmx *vmx)
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}
-static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx)
+static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
{
- struct kvm *kvm = vmx->vcpu.kvm;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 *pml_buf;
u16 pml_idx;
@@ -7666,7 +7656,7 @@ static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx)
gpa = pml_buf[pml_idx];
WARN_ON(gpa & (PAGE_SIZE - 1));
- mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+ kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
}
/* reset PML index */
@@ -7691,6 +7681,158 @@ static void kvm_flush_pml_buffers(struct kvm *kvm)
kvm_vcpu_kick(vcpu);
}
+static void vmx_dump_sel(char *name, uint32_t sel)
+{
+ pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
+ name, vmcs_read32(sel),
+ vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR),
+ vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR),
+ vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR));
+}
+
+static void vmx_dump_dtsel(char *name, uint32_t limit)
+{
+ pr_err("%s limit=0x%08x, base=0x%016lx\n",
+ name, vmcs_read32(limit),
+ vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
+}
+
+static void dump_vmcs(void)
+{
+ u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
+ u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
+ u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
+ u32 secondary_exec_control = 0;
+ unsigned long cr4 = vmcs_readl(GUEST_CR4);
+ u64 efer = vmcs_readl(GUEST_IA32_EFER);
+ int i, n;
+
+ if (cpu_has_secondary_exec_ctrls())
+ secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+
+ pr_err("*** Guest State ***\n");
+ pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
+ vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW),
+ vmcs_readl(CR0_GUEST_HOST_MASK));
+ pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
+ cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK));
+ pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3));
+ if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
+ (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA))
+ {
+ pr_err("PDPTR0 = 0x%016lx PDPTR1 = 0x%016lx\n",
+ vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1));
+ pr_err("PDPTR2 = 0x%016lx PDPTR3 = 0x%016lx\n",
+ vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3));
+ }
+ pr_err("RSP = 0x%016lx RIP = 0x%016lx\n",
+ vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP));
+ pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n",
+ vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7));
+ pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
+ vmcs_readl(GUEST_SYSENTER_ESP),
+ vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP));
+ vmx_dump_sel("CS: ", GUEST_CS_SELECTOR);
+ vmx_dump_sel("DS: ", GUEST_DS_SELECTOR);
+ vmx_dump_sel("SS: ", GUEST_SS_SELECTOR);
+ vmx_dump_sel("ES: ", GUEST_ES_SELECTOR);
+ vmx_dump_sel("FS: ", GUEST_FS_SELECTOR);
+ vmx_dump_sel("GS: ", GUEST_GS_SELECTOR);
+ vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT);
+ vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
+ vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
+ vmx_dump_sel("TR: ", GUEST_TR_SELECTOR);
+ if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
+ (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
+ pr_err("EFER = 0x%016llx PAT = 0x%016lx\n",
+ efer, vmcs_readl(GUEST_IA32_PAT));
+ pr_err("DebugCtl = 0x%016lx DebugExceptions = 0x%016lx\n",
+ vmcs_readl(GUEST_IA32_DEBUGCTL),
+ vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
+ if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+ pr_err("PerfGlobCtl = 0x%016lx\n",
+ vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL));
+ if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS)
+ pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS));
+ pr_err("Interruptibility = %08x ActivityState = %08x\n",
+ vmcs_read32(GUEST_INTERRUPTIBILITY_INFO),
+ vmcs_read32(GUEST_ACTIVITY_STATE));
+ if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
+ pr_err("InterruptStatus = %04x\n",
+ vmcs_read16(GUEST_INTR_STATUS));
+
+ pr_err("*** Host State ***\n");
+ pr_err("RIP = 0x%016lx RSP = 0x%016lx\n",
+ vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP));
+ pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n",
+ vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR),
+ vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR),
+ vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR),
+ vmcs_read16(HOST_TR_SELECTOR));
+ pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n",
+ vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE),
+ vmcs_readl(HOST_TR_BASE));
+ pr_err("GDTBase=%016lx IDTBase=%016lx\n",
+ vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE));
+ pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n",
+ vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3),
+ vmcs_readl(HOST_CR4));
+ pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
+ vmcs_readl(HOST_IA32_SYSENTER_ESP),
+ vmcs_read32(HOST_IA32_SYSENTER_CS),
+ vmcs_readl(HOST_IA32_SYSENTER_EIP));
+ if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER))
+ pr_err("EFER = 0x%016lx PAT = 0x%016lx\n",
+ vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT));
+ if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+ pr_err("PerfGlobCtl = 0x%016lx\n",
+ vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL));
+
+ pr_err("*** Control State ***\n");
+ pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n",
+ pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control);
+ pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl);
+ pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n",
+ vmcs_read32(EXCEPTION_BITMAP),
+ vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK),
+ vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH));
+ pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n",
+ vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
+ vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE),
+ vmcs_read32(VM_ENTRY_INSTRUCTION_LEN));
+ pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n",
+ vmcs_read32(VM_EXIT_INTR_INFO),
+ vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
+ vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
+ pr_err(" reason=%08x qualification=%016lx\n",
+ vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION));
+ pr_err("IDTVectoring: info=%08x errcode=%08x\n",
+ vmcs_read32(IDT_VECTORING_INFO_FIELD),
+ vmcs_read32(IDT_VECTORING_ERROR_CODE));
+ pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET));
+ if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW)
+ pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD));
+ if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR)
+ pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV));
+ if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT))
+ pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER));
+ n = vmcs_read32(CR3_TARGET_COUNT);
+ for (i = 0; i + 1 < n; i += 4)
+ pr_err("CR3 target%u=%016lx target%u=%016lx\n",
+ i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2),
+ i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2));
+ if (i < n)
+ pr_err("CR3 target%u=%016lx\n",
+ i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2));
+ if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING)
+ pr_err("PLE Gap=%08x Window=%08x\n",
+ vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW));
+ if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID)
+ pr_err("Virtual processor ID = 0x%04x\n",
+ vmcs_read16(VIRTUAL_PROCESSOR_ID));
+}
+
/*
* The guest has exited. See if we can fix it or if we need userspace
* assistance.
@@ -7709,7 +7851,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
* flushed already.
*/
if (enable_pml)
- vmx_flush_pml_buffer(vmx);
+ vmx_flush_pml_buffer(vcpu);
/* If guest state is invalid, start emulating */
if (vmx->emulation_required)
@@ -7723,6 +7865,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
}
if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
+ dump_vmcs();
vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
vcpu->run->fail_entry.hardware_entry_failure_reason
= exit_reason;
@@ -7996,6 +8139,11 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
local_irq_enable();
}
+static bool vmx_has_high_real_mode_segbase(void)
+{
+ return enable_unrestricted_guest || emulate_invalid_guest_state;
+}
+
static bool vmx_mpx_supported(void)
{
return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) &&
@@ -8480,7 +8628,8 @@ static int get_ept_level(void)
static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
- u64 ret;
+ u8 cache;
+ u64 ipat = 0;
/* For VT-d and EPT combination
* 1. MMIO: always map as UC
@@ -8493,16 +8642,27 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
* 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
* consistent with host MTRR
*/
- if (is_mmio)
- ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
- else if (kvm_arch_has_noncoherent_dma(vcpu->kvm))
- ret = kvm_get_guest_memory_type(vcpu, gfn) <<
- VMX_EPT_MT_EPTE_SHIFT;
- else
- ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT)
- | VMX_EPT_IPAT_BIT;
+ if (is_mmio) {
+ cache = MTRR_TYPE_UNCACHABLE;
+ goto exit;
+ }
- return ret;
+ if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+ ipat = VMX_EPT_IPAT_BIT;
+ cache = MTRR_TYPE_WRBACK;
+ goto exit;
+ }
+
+ if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
+ ipat = VMX_EPT_IPAT_BIT;
+ cache = MTRR_TYPE_UNCACHABLE;
+ goto exit;
+ }
+
+ cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
+
+exit:
+ return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat;
}
static int vmx_get_lpage_level(void)
@@ -8924,7 +9084,7 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
struct vmx_msr_entry *e)
{
/* x2APIC MSR accesses are not allowed */
- if (apic_x2apic_mode(vcpu->arch.apic) && e->index >> 8 == 0x8)
+ if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)
return -EINVAL;
if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */
e->index == MSR_IA32_UCODE_REV)
@@ -8966,8 +9126,8 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
msr.host_initiated = false;
for (i = 0; i < count; i++) {
- if (kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e),
- &e, sizeof(e))) {
+ if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
+ &e, sizeof(e))) {
pr_warn_ratelimited(
"%s cannot read MSR entry (%u, 0x%08llx)\n",
__func__, i, gpa + i * sizeof(e));
@@ -8999,9 +9159,10 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
struct vmx_msr_entry e;
for (i = 0; i < count; i++) {
- if (kvm_read_guest(vcpu->kvm,
- gpa + i * sizeof(e),
- &e, 2 * sizeof(u32))) {
+ struct msr_data msr_info;
+ if (kvm_vcpu_read_guest(vcpu,
+ gpa + i * sizeof(e),
+ &e, 2 * sizeof(u32))) {
pr_warn_ratelimited(
"%s cannot read MSR entry (%u, 0x%08llx)\n",
__func__, i, gpa + i * sizeof(e));
@@ -9013,19 +9174,21 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
__func__, i, e.index, e.reserved);
return -EINVAL;
}
- if (kvm_get_msr(vcpu, e.index, &e.value)) {
+ msr_info.host_initiated = false;
+ msr_info.index = e.index;
+ if (kvm_get_msr(vcpu, &msr_info)) {
pr_warn_ratelimited(
"%s cannot read MSR (%u, 0x%x)\n",
__func__, i, e.index);
return -EINVAL;
}
- if (kvm_write_guest(vcpu->kvm,
- gpa + i * sizeof(e) +
- offsetof(struct vmx_msr_entry, value),
- &e.value, sizeof(e.value))) {
+ if (kvm_vcpu_write_guest(vcpu,
+ gpa + i * sizeof(e) +
+ offsetof(struct vmx_msr_entry, value),
+ &msr_info.data, sizeof(msr_info.data))) {
pr_warn_ratelimited(
"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
- __func__, i, e.index, e.value);
+ __func__, i, e.index, msr_info.data);
return -EINVAL;
}
}
@@ -10150,6 +10313,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.hardware_enable = hardware_enable,
.hardware_disable = hardware_disable,
.cpu_has_accelerated_tpr = report_flexpriority,
+ .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
.vcpu_create = vmx_create_vcpu,
.vcpu_free = vmx_free_vcpu,
@@ -10185,6 +10349,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
+ .fpu_activate = vmx_fpu_activate,
.fpu_deactivate = vmx_fpu_deactivate,
.tlb_flush = vmx_flush_tlb,
@@ -10254,6 +10419,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
.flush_log_dirty = vmx_flush_log_dirty,
.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
+
+ .pmu_ops = &intel_pmu_ops,
};
static int __init vmx_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c73efcd03e29..ac165c2fb8e5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -28,6 +28,7 @@
#include "x86.h"
#include "cpuid.h"
#include "assigned-dev.h"
+#include "pmu.h"
#include <linux/clocksource.h>
#include <linux/interrupt.h>
@@ -57,11 +58,9 @@
#include <asm/debugreg.h>
#include <asm/msr.h>
#include <asm/desc.h>
-#include <asm/mtrr.h>
#include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h> /* Ugh! */
-#include <asm/xcr.h>
+#include <linux/kernel_stat.h>
+#include <asm/fpu/internal.h> /* Ugh! */
#include <asm/pvclock.h>
#include <asm/div64.h>
@@ -99,6 +98,9 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
unsigned int min_timer_period_us = 500;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
+static bool __read_mostly kvmclock_periodic_sync = true;
+module_param(kvmclock_periodic_sync, bool, S_IRUGO);
+
bool kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
u32 kvm_max_guest_tsc_khz;
@@ -475,7 +477,7 @@ EXPORT_SYMBOL_GPL(kvm_require_dr);
/*
* This function will be used to read from the physical memory of the currently
- * running guest. The difference to kvm_read_guest_page is that this function
+ * running guest. The difference to kvm_vcpu_read_guest_page is that this function
* can read from guest physical or from the guest's guest physical memory.
*/
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
@@ -493,7 +495,7 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
real_gfn = gpa_to_gfn(real_gfn);
- return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len);
+ return kvm_vcpu_read_guest_page(vcpu, real_gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu);
@@ -572,8 +574,7 @@ out:
int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
unsigned long old_cr0 = kvm_read_cr0(vcpu);
- unsigned long update_bits = X86_CR0_PG | X86_CR0_WP |
- X86_CR0_CD | X86_CR0_NW;
+ unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;
cr0 |= X86_CR0_ET;
@@ -619,6 +620,10 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
if ((cr0 ^ old_cr0) & update_bits)
kvm_mmu_reset_context(vcpu);
+
+ if ((cr0 ^ old_cr0) & X86_CR0_CD)
+ kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
+
return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr0);
@@ -702,8 +707,9 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long old_cr4 = kvm_read_cr4(vcpu);
- unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE |
- X86_CR4_PAE | X86_CR4_SMEP;
+ unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+ X86_CR4_SMEP | X86_CR4_SMAP;
+
if (cr4 & CR4_RESERVED_BITS)
return 1;
@@ -744,9 +750,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
(!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
kvm_mmu_reset_context(vcpu);
- if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
- update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
-
if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
kvm_update_cpuid(vcpu);
@@ -910,7 +913,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu)
u64 data;
int err;
- err = kvm_pmu_read_pmc(vcpu, ecx, &data);
+ err = kvm_pmu_rdpmc(vcpu, ecx, &data);
if (err)
return err;
kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data);
@@ -925,17 +928,11 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
*
* This list is modified at module load time to reflect the
* capabilities of the host cpu. This capabilities test skips MSRs that are
- * kvm-specific. Those are put in the beginning of the list.
+ * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
+ * may depend on host virtualization features rather than host cpu features.
*/
-#define KVM_SAVE_MSRS_BEGIN 12
static u32 msrs_to_save[] = {
- MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
- MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
- HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
- HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
- HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
- MSR_KVM_PV_EOI_EN,
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
MSR_STAR,
#ifdef CONFIG_X86_64
@@ -947,14 +944,24 @@ static u32 msrs_to_save[] = {
static unsigned num_msrs_to_save;
-static const u32 emulated_msrs[] = {
+static u32 emulated_msrs[] = {
+ MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+ MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
+ HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
+ HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
+ HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
+ MSR_KVM_PV_EOI_EN,
+
MSR_IA32_TSC_ADJUST,
MSR_IA32_TSCDEADLINE,
MSR_IA32_MISC_ENABLE,
MSR_IA32_MCG_STATUS,
MSR_IA32_MCG_CTL,
+ MSR_IA32_SMBASE,
};
+static unsigned num_emulated_msrs;
+
bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
{
if (efer & efer_reserved_bits)
@@ -1048,6 +1055,21 @@ EXPORT_SYMBOL_GPL(kvm_set_msr);
/*
* Adapt set_msr() to msr_io()'s calling convention
*/
+static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
+{
+ struct msr_data msr;
+ int r;
+
+ msr.index = index;
+ msr.host_initiated = true;
+ r = kvm_get_msr(vcpu, &msr);
+ if (r)
+ return r;
+
+ *data = msr.data;
+ return 0;
+}
+
static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
struct msr_data msr;
@@ -1700,6 +1722,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
vcpu->pvclock_set_guest_stopped_request = false;
}
+ pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
+
/* If the host uses TSC clocksource, then it is stable */
if (use_master_clock)
pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
@@ -1770,127 +1794,14 @@ static void kvmclock_sync_fn(struct work_struct *work)
kvmclock_sync_work);
struct kvm *kvm = container_of(ka, struct kvm, arch);
+ if (!kvmclock_periodic_sync)
+ return;
+
schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0);
schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
KVMCLOCK_SYNC_PERIOD);
}
-static bool msr_mtrr_valid(unsigned msr)
-{
- switch (msr) {
- case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1:
- case MSR_MTRRfix64K_00000:
- case MSR_MTRRfix16K_80000:
- case MSR_MTRRfix16K_A0000:
- case MSR_MTRRfix4K_C0000:
- case MSR_MTRRfix4K_C8000:
- case MSR_MTRRfix4K_D0000:
- case MSR_MTRRfix4K_D8000:
- case MSR_MTRRfix4K_E0000:
- case MSR_MTRRfix4K_E8000:
- case MSR_MTRRfix4K_F0000:
- case MSR_MTRRfix4K_F8000:
- case MSR_MTRRdefType:
- case MSR_IA32_CR_PAT:
- return true;
- case 0x2f8:
- return true;
- }
- return false;
-}
-
-static bool valid_pat_type(unsigned t)
-{
- return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
-}
-
-static bool valid_mtrr_type(unsigned t)
-{
- return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
-}
-
-bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
- int i;
- u64 mask;
-
- if (!msr_mtrr_valid(msr))
- return false;
-
- if (msr == MSR_IA32_CR_PAT) {
- for (i = 0; i < 8; i++)
- if (!valid_pat_type((data >> (i * 8)) & 0xff))
- return false;
- return true;
- } else if (msr == MSR_MTRRdefType) {
- if (data & ~0xcff)
- return false;
- return valid_mtrr_type(data & 0xff);
- } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
- for (i = 0; i < 8 ; i++)
- if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
- return false;
- return true;
- }
-
- /* variable MTRRs */
- WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
-
- mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
- if ((msr & 1) == 0) {
- /* MTRR base */
- if (!valid_mtrr_type(data & 0xff))
- return false;
- mask |= 0xf00;
- } else
- /* MTRR mask */
- mask |= 0x7ff;
- if (data & mask) {
- kvm_inject_gp(vcpu, 0);
- return false;
- }
-
- return true;
-}
-EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
-
-static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
- u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
-
- if (!kvm_mtrr_valid(vcpu, msr, data))
- return 1;
-
- if (msr == MSR_MTRRdefType) {
- vcpu->arch.mtrr_state.def_type = data;
- vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10;
- } else if (msr == MSR_MTRRfix64K_00000)
- p[0] = data;
- else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
- p[1 + msr - MSR_MTRRfix16K_80000] = data;
- else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
- p[3 + msr - MSR_MTRRfix4K_C0000] = data;
- else if (msr == MSR_IA32_CR_PAT)
- vcpu->arch.pat = data;
- else { /* Variable MTRRs */
- int idx, is_mtrr_mask;
- u64 *pt;
-
- idx = (msr - 0x200) / 2;
- is_mtrr_mask = msr - 0x200 - 2 * idx;
- if (!is_mtrr_mask)
- pt =
- (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
- else
- pt =
- (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
- *pt = data;
- }
-
- kvm_mmu_reset_context(vcpu);
- return 0;
-}
-
static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
u64 mcg_cap = vcpu->arch.mcg_cap;
@@ -1949,7 +1860,7 @@ static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
r = PTR_ERR(page);
goto out;
}
- if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
+ if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE))
goto out_free;
r = 0;
out_free:
@@ -2049,13 +1960,13 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
break;
}
gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
- addr = gfn_to_hva(vcpu->kvm, gfn);
+ addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
if (kvm_is_error_hva(addr))
return 1;
if (__clear_user((void __user *)addr, PAGE_SIZE))
return 1;
vcpu->arch.hv_vapic = data;
- mark_page_dirty(vcpu->kvm, gfn);
+ kvm_vcpu_mark_page_dirty(vcpu, gfn);
if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
return 1;
break;
@@ -2182,7 +2093,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
__func__, data);
break;
case 0x200 ... 0x2ff:
- return set_msr_mtrr(vcpu, msr, data);
+ return kvm_mtrr_set_msr(vcpu, msr, data);
case MSR_IA32_APICBASE:
return kvm_set_apic_base(vcpu, msr_info);
case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
@@ -2202,6 +2113,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_MISC_ENABLE:
vcpu->arch.ia32_misc_enable_msr = data;
break;
+ case MSR_IA32_SMBASE:
+ if (!msr_info->host_initiated)
+ return 1;
+ vcpu->arch.smbase = data;
+ break;
case MSR_KVM_WALL_CLOCK_NEW:
case MSR_KVM_WALL_CLOCK:
vcpu->kvm->arch.wall_clock = data;
@@ -2222,6 +2138,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
&vcpu->requests);
ka->boot_vcpu_runs_old_kvmclock = tmp;
+
+ ka->kvmclock_offset = -get_kernel_ns();
}
vcpu->arch.time = data;
@@ -2283,37 +2201,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
return set_msr_mce(vcpu, msr, data);
- /* Performance counters are not protected by a CPUID bit,
- * so we should check all of them in the generic path for the sake of
- * cross vendor migration.
- * Writing a zero into the event select MSRs disables them,
- * which we perfectly emulate ;-). Any other value should be at least
- * reported, some guests depend on them.
- */
- case MSR_K7_EVNTSEL0:
- case MSR_K7_EVNTSEL1:
- case MSR_K7_EVNTSEL2:
- case MSR_K7_EVNTSEL3:
- if (data != 0)
- vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: "
- "0x%x data 0x%llx\n", msr, data);
- break;
- /* at least RHEL 4 unconditionally writes to the perfctr registers,
- * so we ignore writes to make it happy.
- */
- case MSR_K7_PERFCTR0:
- case MSR_K7_PERFCTR1:
- case MSR_K7_PERFCTR2:
- case MSR_K7_PERFCTR3:
- vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: "
- "0x%x data 0x%llx\n", msr, data);
- break;
- case MSR_P6_PERFCTR0:
- case MSR_P6_PERFCTR1:
- pr = true;
- case MSR_P6_EVNTSEL0:
- case MSR_P6_EVNTSEL1:
- if (kvm_pmu_msr(vcpu, msr))
+ case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
+ case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1:
+ pr = true; /* fall through */
+ case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
+ case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1:
+ if (kvm_pmu_is_valid_msr(vcpu, msr))
return kvm_pmu_set_msr(vcpu, msr_info);
if (pr || data != 0)
@@ -2359,7 +2252,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
default:
if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
return xen_hvm_config(vcpu, data);
- if (kvm_pmu_msr(vcpu, msr))
+ if (kvm_pmu_is_valid_msr(vcpu, msr))
return kvm_pmu_set_msr(vcpu, msr_info);
if (!ignore_msrs) {
vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
@@ -2381,48 +2274,12 @@ EXPORT_SYMBOL_GPL(kvm_set_msr_common);
* Returns 0 on success, non-0 otherwise.
* Assumes vcpu_load() was already called.
*/
-int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
- return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
+ return kvm_x86_ops->get_msr(vcpu, msr);
}
EXPORT_SYMBOL_GPL(kvm_get_msr);
-static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
- u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
-
- if (!msr_mtrr_valid(msr))
- return 1;
-
- if (msr == MSR_MTRRdefType)
- *pdata = vcpu->arch.mtrr_state.def_type +
- (vcpu->arch.mtrr_state.enabled << 10);
- else if (msr == MSR_MTRRfix64K_00000)
- *pdata = p[0];
- else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
- *pdata = p[1 + msr - MSR_MTRRfix16K_80000];
- else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
- *pdata = p[3 + msr - MSR_MTRRfix4K_C0000];
- else if (msr == MSR_IA32_CR_PAT)
- *pdata = vcpu->arch.pat;
- else { /* Variable MTRRs */
- int idx, is_mtrr_mask;
- u64 *pt;
-
- idx = (msr - 0x200) / 2;
- is_mtrr_mask = msr - 0x200 - 2 * idx;
- if (!is_mtrr_mask)
- pt =
- (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
- else
- pt =
- (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
- *pdata = *pt;
- }
-
- return 0;
-}
-
static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 data;
@@ -2520,11 +2377,11 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
return 0;
}
-int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
u64 data;
- switch (msr) {
+ switch (msr_info->index) {
case MSR_IA32_PLATFORM_ID:
case MSR_IA32_EBL_CR_POWERON:
case MSR_IA32_DEBUGCTLMSR:
@@ -2535,38 +2392,28 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_K8_SYSCFG:
case MSR_K7_HWCR:
case MSR_VM_HSAVE_PA:
- case MSR_K7_EVNTSEL0:
- case MSR_K7_EVNTSEL1:
- case MSR_K7_EVNTSEL2:
- case MSR_K7_EVNTSEL3:
- case MSR_K7_PERFCTR0:
- case MSR_K7_PERFCTR1:
- case MSR_K7_PERFCTR2:
- case MSR_K7_PERFCTR3:
case MSR_K8_INT_PENDING_MSG:
case MSR_AMD64_NB_CFG:
case MSR_FAM10H_MMIO_CONF_BASE:
case MSR_AMD64_BU_CFG2:
- data = 0;
+ msr_info->data = 0;
break;
- case MSR_P6_PERFCTR0:
- case MSR_P6_PERFCTR1:
- case MSR_P6_EVNTSEL0:
- case MSR_P6_EVNTSEL1:
- if (kvm_pmu_msr(vcpu, msr))
- return kvm_pmu_get_msr(vcpu, msr, pdata);
- data = 0;
+ case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
+ case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
+ case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1:
+ case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1:
+ if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
+ return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data);
+ msr_info->data = 0;
break;
case MSR_IA32_UCODE_REV:
- data = 0x100000000ULL;
+ msr_info->data = 0x100000000ULL;
break;
case MSR_MTRRcap:
- data = 0x500 | KVM_NR_VAR_MTRR;
- break;
case 0x200 ... 0x2ff:
- return get_msr_mtrr(vcpu, msr, pdata);
+ return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
case 0xcd: /* fsb frequency */
- data = 3;
+ msr_info->data = 3;
break;
/*
* MSR_EBC_FREQUENCY_ID
@@ -2580,48 +2427,53 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
* multiplying by zero otherwise.
*/
case MSR_EBC_FREQUENCY_ID:
- data = 1 << 24;
+ msr_info->data = 1 << 24;
break;
case MSR_IA32_APICBASE:
- data = kvm_get_apic_base(vcpu);
+ msr_info->data = kvm_get_apic_base(vcpu);
break;
case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
- return kvm_x2apic_msr_read(vcpu, msr, pdata);
+ return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
break;
case MSR_IA32_TSCDEADLINE:
- data = kvm_get_lapic_tscdeadline_msr(vcpu);
+ msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu);
break;
case MSR_IA32_TSC_ADJUST:
- data = (u64)vcpu->arch.ia32_tsc_adjust_msr;
+ msr_info->data = (u64)vcpu->arch.ia32_tsc_adjust_msr;
break;
case MSR_IA32_MISC_ENABLE:
- data = vcpu->arch.ia32_misc_enable_msr;
+ msr_info->data = vcpu->arch.ia32_misc_enable_msr;
+ break;
+ case MSR_IA32_SMBASE:
+ if (!msr_info->host_initiated)
+ return 1;
+ msr_info->data = vcpu->arch.smbase;
break;
case MSR_IA32_PERF_STATUS:
/* TSC increment by tick */
- data = 1000ULL;
+ msr_info->data = 1000ULL;
/* CPU multiplier */
data |= (((uint64_t)4ULL) << 40);
break;
case MSR_EFER:
- data = vcpu->arch.efer;
+ msr_info->data = vcpu->arch.efer;
break;
case MSR_KVM_WALL_CLOCK:
case MSR_KVM_WALL_CLOCK_NEW:
- data = vcpu->kvm->arch.wall_clock;
+ msr_info->data = vcpu->kvm->arch.wall_clock;
break;
case MSR_KVM_SYSTEM_TIME:
case MSR_KVM_SYSTEM_TIME_NEW:
- data = vcpu->arch.time;
+ msr_info->data = vcpu->arch.time;
break;
case MSR_KVM_ASYNC_PF_EN:
- data = vcpu->arch.apf.msr_val;
+ msr_info->data = vcpu->arch.apf.msr_val;
break;
case MSR_KVM_STEAL_TIME:
- data = vcpu->arch.st.msr_val;
+ msr_info->data = vcpu->arch.st.msr_val;
break;
case MSR_KVM_PV_EOI_EN:
- data = vcpu->arch.pv_eoi.msr_val;
+ msr_info->data = vcpu->arch.pv_eoi.msr_val;
break;
case MSR_IA32_P5_MC_ADDR:
case MSR_IA32_P5_MC_TYPE:
@@ -2629,7 +2481,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_IA32_MCG_CTL:
case MSR_IA32_MCG_STATUS:
case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
- return get_msr_mce(vcpu, msr, pdata);
+ return get_msr_mce(vcpu, msr_info->index, &msr_info->data);
case MSR_K7_CLK_CTL:
/*
* Provide expected ramp-up count for K7. All other
@@ -2640,17 +2492,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
* type 6, model 8 and higher from exploding due to
* the rdmsr failing.
*/
- data = 0x20000000;
+ msr_info->data = 0x20000000;
break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
- if (kvm_hv_msr_partition_wide(msr)) {
+ if (kvm_hv_msr_partition_wide(msr_info->index)) {
int r;
mutex_lock(&vcpu->kvm->lock);
- r = get_msr_hyperv_pw(vcpu, msr, pdata);
+ r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data);
mutex_unlock(&vcpu->kvm->lock);
return r;
} else
- return get_msr_hyperv(vcpu, msr, pdata);
+ return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data);
break;
case MSR_IA32_BBL_CR_CTL3:
/* This legacy MSR exists but isn't fully documented in current
@@ -2663,31 +2515,30 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
* L2 cache control register 3: 64GB range, 256KB size,
* enabled, latency 0x1, configured
*/
- data = 0xbe702111;
+ msr_info->data = 0xbe702111;
break;
case MSR_AMD64_OSVW_ID_LENGTH:
if (!guest_cpuid_has_osvw(vcpu))
return 1;
- data = vcpu->arch.osvw.length;
+ msr_info->data = vcpu->arch.osvw.length;
break;
case MSR_AMD64_OSVW_STATUS:
if (!guest_cpuid_has_osvw(vcpu))
return 1;
- data = vcpu->arch.osvw.status;
+ msr_info->data = vcpu->arch.osvw.status;
break;
default:
- if (kvm_pmu_msr(vcpu, msr))
- return kvm_pmu_get_msr(vcpu, msr, pdata);
+ if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
+ return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data);
if (!ignore_msrs) {
- vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
+ vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index);
return 1;
} else {
- vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr);
- data = 0;
+ vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index);
+ msr_info->data = 0;
}
break;
}
- *pdata = data;
return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_msr_common);
@@ -2800,12 +2651,25 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_HYPERV_TIME:
case KVM_CAP_IOAPIC_POLARITY_IGNORED:
case KVM_CAP_TSC_DEADLINE_TIMER:
+ case KVM_CAP_ENABLE_CAP_VM:
+ case KVM_CAP_DISABLE_QUIRKS:
#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
case KVM_CAP_ASSIGN_DEV_IRQ:
case KVM_CAP_PCI_2_3:
#endif
r = 1;
break;
+ case KVM_CAP_X86_SMM:
+ /* SMBASE is usually relocated above 1M on modern chipsets,
+ * and SMM handlers might indeed rely on 4G segment limits,
+ * so do not report SMM to be available if real mode is
+ * emulated via vm86 mode. Still, do not go to great lengths
+ * to avoid userspace's usage of the feature, because it is a
+ * fringe case that is not enabled except via specific settings
+ * of the module parameters.
+ */
+ r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+ break;
case KVM_CAP_COALESCED_MMIO:
r = KVM_COALESCED_MMIO_PAGE_OFFSET;
break;
@@ -2862,7 +2726,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
goto out;
n = msr_list.nmsrs;
- msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
+ msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs;
if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
goto out;
r = -E2BIG;
@@ -2874,7 +2738,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
goto out;
if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
&emulated_msrs,
- ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
+ num_emulated_msrs * sizeof(u32)))
goto out;
r = 0;
break;
@@ -3018,6 +2882,13 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
return 0;
}
+static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu)
+{
+ kvm_make_request(KVM_REQ_SMI, vcpu);
+
+ return 0;
+}
+
static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
struct kvm_tpr_access_ctl *tac)
{
@@ -3123,8 +2994,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->sipi_vector = 0; /* never valid when reporting to user space */
+ events->smi.smm = is_smm(vcpu);
+ events->smi.pending = vcpu->arch.smi_pending;
+ events->smi.smm_inside_nmi =
+ !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK);
+ events->smi.latched_init = kvm_lapic_latched_init(vcpu);
+
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
- | KVM_VCPUEVENT_VALID_SHADOW);
+ | KVM_VCPUEVENT_VALID_SHADOW
+ | KVM_VCPUEVENT_VALID_SMM);
memset(&events->reserved, 0, sizeof(events->reserved));
}
@@ -3133,7 +3011,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
{
if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SIPI_VECTOR
- | KVM_VCPUEVENT_VALID_SHADOW))
+ | KVM_VCPUEVENT_VALID_SHADOW
+ | KVM_VCPUEVENT_VALID_SMM))
return -EINVAL;
process_nmi(vcpu);
@@ -3158,6 +3037,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
kvm_vcpu_has_lapic(vcpu))
vcpu->arch.apic->sipi_vector = events->sipi_vector;
+ if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+ if (events->smi.smm)
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ else
+ vcpu->arch.hflags &= ~HF_SMM_MASK;
+ vcpu->arch.smi_pending = events->smi.pending;
+ if (events->smi.smm_inside_nmi)
+ vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
+ else
+ vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
+ if (kvm_vcpu_has_lapic(vcpu)) {
+ if (events->smi.latched_init)
+ set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+ else
+ clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+ }
+ }
+
kvm_make_request(KVM_REQ_EVENT, vcpu);
return 0;
@@ -3196,8 +3093,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
{
- struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
- u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+ struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
+ u64 xstate_bv = xsave->header.xfeatures;
u64 valid;
/*
@@ -3232,7 +3129,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
{
- struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+ struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
u64 valid;
@@ -3243,9 +3140,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
memcpy(xsave, src, XSAVE_HDR_OFFSET);
/* Set XSTATE_BV and possibly XCOMP_BV. */
- xsave->xsave_hdr.xstate_bv = xstate_bv;
+ xsave->header.xfeatures = xstate_bv;
if (cpu_has_xsaves)
- xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+ xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
/*
* Copy each region from the non-compacted offset to the
@@ -3277,8 +3174,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
fill_xsave((u8 *) guest_xsave->region, vcpu);
} else {
memcpy(guest_xsave->region,
- &vcpu->arch.guest_fpu.state->fxsave,
- sizeof(struct i387_fxsave_struct));
+ &vcpu->arch.guest_fpu.state.fxsave,
+ sizeof(struct fxregs_state));
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
XSTATE_FPSSE;
}
@@ -3302,8 +3199,8 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
} else {
if (xstate_bv & ~XSTATE_FPSSE)
return -EINVAL;
- memcpy(&vcpu->arch.guest_fpu.state->fxsave,
- guest_xsave->region, sizeof(struct i387_fxsave_struct));
+ memcpy(&vcpu->arch.guest_fpu.state.fxsave,
+ guest_xsave->region, sizeof(struct fxregs_state));
}
return 0;
}
@@ -3417,6 +3314,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = kvm_vcpu_ioctl_nmi(vcpu);
break;
}
+ case KVM_SMI: {
+ r = kvm_vcpu_ioctl_smi(vcpu);
+ break;
+ }
case KVM_SET_CPUID: {
struct kvm_cpuid __user *cpuid_arg = argp;
struct kvm_cpuid cpuid;
@@ -3456,7 +3357,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
}
case KVM_GET_MSRS:
- r = msr_io(vcpu, argp, kvm_get_msr, 1);
+ r = msr_io(vcpu, argp, do_get_msr, 1);
break;
case KVM_SET_MSRS:
r = msr_io(vcpu, argp, do_set_msr, 0);
@@ -3847,6 +3748,26 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
return 0;
}
+static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+ struct kvm_enable_cap *cap)
+{
+ int r;
+
+ if (cap->flags)
+ return -EINVAL;
+
+ switch (cap->cap) {
+ case KVM_CAP_DISABLE_QUIRKS:
+ kvm->arch.disabled_quirks = cap->args[0];
+ r = 0;
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ return r;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -4099,7 +4020,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = 0;
break;
}
+ case KVM_ENABLE_CAP: {
+ struct kvm_enable_cap cap;
+ r = -EFAULT;
+ if (copy_from_user(&cap, argp, sizeof(cap)))
+ goto out;
+ r = kvm_vm_ioctl_enable_cap(kvm, &cap);
+ break;
+ }
default:
r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
}
@@ -4112,8 +4041,7 @@ static void kvm_init_msr_list(void)
u32 dummy[2];
unsigned i, j;
- /* skip the first msrs in the list. KVM-specific */
- for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) {
+ for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
continue;
@@ -4138,6 +4066,22 @@ static void kvm_init_msr_list(void)
j++;
}
num_msrs_to_save = j;
+
+ for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
+ switch (emulated_msrs[i]) {
+ case MSR_IA32_SMBASE:
+ if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
+ continue;
+ break;
+ default:
+ break;
+ }
+
+ if (j < i)
+ emulated_msrs[j] = emulated_msrs[i];
+ j++;
+ }
+ num_emulated_msrs = j;
}
static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -4255,8 +4199,8 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
if (gpa == UNMAPPED_GVA)
return X86EMUL_PROPAGATE_FAULT;
- ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data,
- offset, toread);
+ ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data,
+ offset, toread);
if (ret < 0) {
r = X86EMUL_IO_NEEDED;
goto out;
@@ -4289,8 +4233,8 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
offset = addr & (PAGE_SIZE-1);
if (WARN_ON(offset + bytes > PAGE_SIZE))
bytes = (unsigned)PAGE_SIZE - offset;
- ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val,
- offset, bytes);
+ ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, val,
+ offset, bytes);
if (unlikely(ret < 0))
return X86EMUL_IO_NEEDED;
@@ -4336,7 +4280,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
if (gpa == UNMAPPED_GVA)
return X86EMUL_PROPAGATE_FAULT;
- ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite);
+ ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite);
if (ret < 0) {
r = X86EMUL_IO_NEEDED;
goto out;
@@ -4389,7 +4333,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
{
int ret;
- ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
+ ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes);
if (ret < 0)
return 0;
kvm_mmu_pte_write(vcpu, gpa, val, bytes);
@@ -4423,7 +4367,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
void *val, int bytes)
{
- return !kvm_read_guest(vcpu->kvm, gpa, val, bytes);
+ return !kvm_vcpu_read_guest(vcpu, gpa, val, bytes);
}
static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
@@ -4621,7 +4565,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
goto emul_write;
- page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+ page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
if (is_error_page(page))
goto emul_write;
@@ -4649,7 +4593,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
if (!exchanged)
return X86EMUL_CMPXCHG_FAILED;
- mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
+ kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
kvm_mmu_pte_write(vcpu, gpa, new, bytes);
return X86EMUL_CONTINUE;
@@ -4948,7 +4892,17 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
u32 msr_index, u64 *pdata)
{
- return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
+ struct msr_data msr;
+ int r;
+
+ msr.index = msr_index;
+ msr.host_initiated = false;
+ r = kvm_get_msr(emul_to_vcpu(ctxt), &msr);
+ if (r)
+ return r;
+
+ *pdata = msr.data;
+ return 0;
}
static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
@@ -4962,16 +4916,30 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
return kvm_set_msr(emul_to_vcpu(ctxt), &msr);
}
+static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
+{
+ struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+ return vcpu->arch.smbase;
+}
+
+static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+ struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+ vcpu->arch.smbase = smbase;
+}
+
static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
u32 pmc)
{
- return kvm_pmu_check_pmc(emul_to_vcpu(ctxt), pmc);
+ return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc);
}
static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
u32 pmc, u64 *pdata)
{
- return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata);
+ return kvm_pmu_rdpmc(emul_to_vcpu(ctxt), pmc, pdata);
}
static void emulator_halt(struct x86_emulate_ctxt *ctxt)
@@ -5047,6 +5015,8 @@ static const struct x86_emulate_ops emulate_ops = {
.cpl = emulator_get_cpl,
.get_dr = emulator_get_dr,
.set_dr = emulator_set_dr,
+ .get_smbase = emulator_get_smbase,
+ .set_smbase = emulator_set_smbase,
.set_msr = emulator_set_msr,
.get_msr = emulator_get_msr,
.check_pmc = emulator_check_pmc,
@@ -5108,7 +5078,10 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
(cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 :
cs_db ? X86EMUL_MODE_PROT32 :
X86EMUL_MODE_PROT16;
- ctxt->guest_mode = is_guest_mode(vcpu);
+ BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
+ BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
+ BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
+ ctxt->emul_flags = vcpu->arch.hflags;
init_decode_cache(ctxt);
vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
@@ -5277,6 +5250,34 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
static int complete_emulated_pio(struct kvm_vcpu *vcpu);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.hflags & HF_SMM_MASK)) {
+ /* This is a good place to trace that we are exiting SMM. */
+ trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false);
+
+ if (unlikely(vcpu->arch.smi_pending)) {
+ kvm_make_request(KVM_REQ_SMI, vcpu);
+ vcpu->arch.smi_pending = 0;
+ } else {
+ /* Process a latched INIT, if any. */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ }
+ }
+
+ kvm_mmu_reset_context(vcpu);
+}
+
+static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
+{
+ unsigned changed = vcpu->arch.hflags ^ emul_flags;
+
+ vcpu->arch.hflags = emul_flags;
+
+ if (changed & HF_SMM_MASK)
+ kvm_smm_changed(vcpu);
+}
+
static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
unsigned long *db)
{
@@ -5476,6 +5477,8 @@ restart:
unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
+ if (vcpu->arch.hflags != ctxt->emul_flags)
+ kvm_set_hflags(vcpu, ctxt->emul_flags);
kvm_rip_write(vcpu, ctxt->eip);
if (r == EMULATE_DONE)
kvm_vcpu_check_singlestep(vcpu, rflags, &r);
@@ -5954,6 +5957,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
lapic_irq.shorthand = 0;
lapic_irq.dest_mode = 0;
lapic_irq.dest_id = apicid;
+ lapic_irq.msi_redir_hint = false;
lapic_irq.delivery_mode = APIC_DM_REMRD;
kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
@@ -6041,6 +6045,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
struct kvm_run *kvm_run = vcpu->run;
kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+ kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
kvm_run->cr8 = kvm_get_cr8(vcpu);
kvm_run->apic_base = kvm_get_apic_base(vcpu);
if (irqchip_in_kernel(vcpu->kvm))
@@ -6164,6 +6169,233 @@ static void process_nmi(struct kvm_vcpu *vcpu)
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
+#define put_smstate(type, buf, offset, val) \
+ *(type *)((buf) + (offset) - 0x7e00) = val
+
+static u32 process_smi_get_segment_flags(struct kvm_segment *seg)
+{
+ u32 flags = 0;
+ flags |= seg->g << 23;
+ flags |= seg->db << 22;
+ flags |= seg->l << 21;
+ flags |= seg->avl << 20;
+ flags |= seg->present << 15;
+ flags |= seg->dpl << 13;
+ flags |= seg->s << 12;
+ flags |= seg->type << 8;
+ return flags;
+}
+
+static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
+{
+ struct kvm_segment seg;
+ int offset;
+
+ kvm_get_segment(vcpu, &seg, n);
+ put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector);
+
+ if (n < 3)
+ offset = 0x7f84 + n * 12;
+ else
+ offset = 0x7f2c + (n - 3) * 12;
+
+ put_smstate(u32, buf, offset + 8, seg.base);
+ put_smstate(u32, buf, offset + 4, seg.limit);
+ put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg));
+}
+
+static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+{
+ struct kvm_segment seg;
+ int offset;
+ u16 flags;
+
+ kvm_get_segment(vcpu, &seg, n);
+ offset = 0x7e00 + n * 16;
+
+ flags = process_smi_get_segment_flags(&seg) >> 8;
+ put_smstate(u16, buf, offset, seg.selector);
+ put_smstate(u16, buf, offset + 2, flags);
+ put_smstate(u32, buf, offset + 4, seg.limit);
+ put_smstate(u64, buf, offset + 8, seg.base);
+}
+
+static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf)
+{
+ struct desc_ptr dt;
+ struct kvm_segment seg;
+ unsigned long val;
+ int i;
+
+ put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu));
+ put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu));
+ put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu));
+ put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu));
+
+ for (i = 0; i < 8; i++)
+ put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read(vcpu, i));
+
+ kvm_get_dr(vcpu, 6, &val);
+ put_smstate(u32, buf, 0x7fcc, (u32)val);
+ kvm_get_dr(vcpu, 7, &val);
+ put_smstate(u32, buf, 0x7fc8, (u32)val);
+
+ kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
+ put_smstate(u32, buf, 0x7fc4, seg.selector);
+ put_smstate(u32, buf, 0x7f64, seg.base);
+ put_smstate(u32, buf, 0x7f60, seg.limit);
+ put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg));
+
+ kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
+ put_smstate(u32, buf, 0x7fc0, seg.selector);
+ put_smstate(u32, buf, 0x7f80, seg.base);
+ put_smstate(u32, buf, 0x7f7c, seg.limit);
+ put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg));
+
+ kvm_x86_ops->get_gdt(vcpu, &dt);
+ put_smstate(u32, buf, 0x7f74, dt.address);
+ put_smstate(u32, buf, 0x7f70, dt.size);
+
+ kvm_x86_ops->get_idt(vcpu, &dt);
+ put_smstate(u32, buf, 0x7f58, dt.address);
+ put_smstate(u32, buf, 0x7f54, dt.size);
+
+ for (i = 0; i < 6; i++)
+ process_smi_save_seg_32(vcpu, buf, i);
+
+ put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
+
+ /* revision id */
+ put_smstate(u32, buf, 0x7efc, 0x00020000);
+ put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
+}
+
+static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
+{
+#ifdef CONFIG_X86_64
+ struct desc_ptr dt;
+ struct kvm_segment seg;
+ unsigned long val;
+ int i;
+
+ for (i = 0; i < 16; i++)
+ put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read(vcpu, i));
+
+ put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu));
+ put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu));
+
+ kvm_get_dr(vcpu, 6, &val);
+ put_smstate(u64, buf, 0x7f68, val);
+ kvm_get_dr(vcpu, 7, &val);
+ put_smstate(u64, buf, 0x7f60, val);
+
+ put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu));
+ put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu));
+ put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu));
+
+ put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase);
+
+ /* revision id */
+ put_smstate(u32, buf, 0x7efc, 0x00020064);
+
+ put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer);
+
+ kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
+ put_smstate(u16, buf, 0x7e90, seg.selector);
+ put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8);
+ put_smstate(u32, buf, 0x7e94, seg.limit);
+ put_smstate(u64, buf, 0x7e98, seg.base);
+
+ kvm_x86_ops->get_idt(vcpu, &dt);
+ put_smstate(u32, buf, 0x7e84, dt.size);
+ put_smstate(u64, buf, 0x7e88, dt.address);
+
+ kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
+ put_smstate(u16, buf, 0x7e70, seg.selector);
+ put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8);
+ put_smstate(u32, buf, 0x7e74, seg.limit);
+ put_smstate(u64, buf, 0x7e78, seg.base);
+
+ kvm_x86_ops->get_gdt(vcpu, &dt);
+ put_smstate(u32, buf, 0x7e64, dt.size);
+ put_smstate(u64, buf, 0x7e68, dt.address);
+
+ for (i = 0; i < 6; i++)
+ process_smi_save_seg_64(vcpu, buf, i);
+#else
+ WARN_ON_ONCE(1);
+#endif
+}
+
+static void process_smi(struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment cs, ds;
+ char buf[512];
+ u32 cr0;
+
+ if (is_smm(vcpu)) {
+ vcpu->arch.smi_pending = true;
+ return;
+ }
+
+ trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ memset(buf, 0, 512);
+ if (guest_cpuid_has_longmode(vcpu))
+ process_smi_save_state_64(vcpu, buf);
+ else
+ process_smi_save_state_32(vcpu, buf);
+
+ kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
+
+ if (kvm_x86_ops->get_nmi_mask(vcpu))
+ vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
+ else
+ kvm_x86_ops->set_nmi_mask(vcpu, true);
+
+ kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
+ kvm_rip_write(vcpu, 0x8000);
+
+ cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
+ kvm_x86_ops->set_cr0(vcpu, cr0);
+ vcpu->arch.cr0 = cr0;
+
+ kvm_x86_ops->set_cr4(vcpu, 0);
+
+ __kvm_set_dr(vcpu, 7, DR7_FIXED_1);
+
+ cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
+ cs.base = vcpu->arch.smbase;
+
+ ds.selector = 0;
+ ds.base = 0;
+
+ cs.limit = ds.limit = 0xffffffff;
+ cs.type = ds.type = 0x3;
+ cs.dpl = ds.dpl = 0;
+ cs.db = ds.db = 0;
+ cs.s = ds.s = 1;
+ cs.l = ds.l = 0;
+ cs.g = ds.g = 1;
+ cs.avl = ds.avl = 0;
+ cs.present = ds.present = 1;
+ cs.unusable = ds.unusable = 0;
+ cs.padding = ds.padding = 0;
+
+ kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_DS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_ES);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_FS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+
+ if (guest_cpuid_has_longmode(vcpu))
+ kvm_x86_ops->set_efer(vcpu, 0);
+
+ kvm_update_cpuid(vcpu);
+ kvm_mmu_reset_context(vcpu);
+}
+
static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
{
u64 eoi_exit_bitmap[4];
@@ -6197,6 +6429,8 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
return;
page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+ if (is_error_page(page))
+ return;
kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
/*
@@ -6270,12 +6504,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
}
if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
record_steal_time(vcpu);
+ if (kvm_check_request(KVM_REQ_SMI, vcpu))
+ process_smi(vcpu);
if (kvm_check_request(KVM_REQ_NMI, vcpu))
process_nmi(vcpu);
if (kvm_check_request(KVM_REQ_PMU, vcpu))
- kvm_handle_pmu_event(vcpu);
+ kvm_pmu_handle_event(vcpu);
if (kvm_check_request(KVM_REQ_PMI, vcpu))
- kvm_deliver_pmi(vcpu);
+ kvm_pmu_deliver_pmi(vcpu);
if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu))
vcpu_scan_ioapic(vcpu);
if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
@@ -6347,7 +6583,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (req_immediate_exit)
smp_send_reschedule(vcpu->cpu);
- kvm_guest_enter();
+ __kvm_guest_enter();
if (unlikely(vcpu->arch.switch_db_regs)) {
set_debugreg(0, 7);
@@ -6597,11 +6833,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
+ struct fpu *fpu = &current->thread.fpu;
int r;
sigset_t sigsaved;
- if (!tsk_used_math(current) && init_fpu(current))
- return -ENOMEM;
+ fpu__activate_curr(fpu);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
@@ -6971,8 +7207,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct i387_fxsave_struct *fxsave =
- &vcpu->arch.guest_fpu.state->fxsave;
+ struct fxregs_state *fxsave =
+ &vcpu->arch.guest_fpu.state.fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
@@ -6988,8 +7224,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct i387_fxsave_struct *fxsave =
- &vcpu->arch.guest_fpu.state->fxsave;
+ struct fxregs_state *fxsave =
+ &vcpu->arch.guest_fpu.state.fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
@@ -7003,17 +7239,11 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
return 0;
}
-int fx_init(struct kvm_vcpu *vcpu)
+static void fx_init(struct kvm_vcpu *vcpu)
{
- int err;
-
- err = fpu_alloc(&vcpu->arch.guest_fpu);
- if (err)
- return err;
-
- fpu_finit(&vcpu->arch.guest_fpu);
+ fpstate_init(&vcpu->arch.guest_fpu.state);
if (cpu_has_xsaves)
- vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+ vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
host_xcr0 | XSTATE_COMPACTION_ENABLED;
/*
@@ -7022,14 +7252,6 @@ int fx_init(struct kvm_vcpu *vcpu)
vcpu->arch.xcr0 = XSTATE_FP;
vcpu->arch.cr0 |= X86_CR0_ET;
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(fx_init);
-
-static void fx_free(struct kvm_vcpu *vcpu)
-{
- fpu_free(&vcpu->arch.guest_fpu);
}
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
@@ -7045,7 +7267,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
kvm_put_guest_xcr0(vcpu);
vcpu->guest_fpu_loaded = 1;
__kernel_fpu_begin();
- fpu_restore_checking(&vcpu->arch.guest_fpu);
+ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
trace_kvm_fpu(1);
}
@@ -7053,14 +7275,25 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
kvm_put_guest_xcr0(vcpu);
- if (!vcpu->guest_fpu_loaded)
+ if (!vcpu->guest_fpu_loaded) {
+ vcpu->fpu_counter = 0;
return;
+ }
vcpu->guest_fpu_loaded = 0;
- fpu_save_init(&vcpu->arch.guest_fpu);
+ copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
__kernel_fpu_end();
++vcpu->stat.fpu_reload;
- kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+ /*
+ * If using eager FPU mode, or if the guest is a frequent user
+ * of the FPU, just leave the FPU active for next time.
+ * Every 255 times fpu_counter rolls over to 0; a guest that uses
+ * the FPU in bursts will revert to loading it on demand.
+ */
+ if (!vcpu->arch.eager_fpu) {
+ if (++vcpu->fpu_counter < 5)
+ kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+ }
trace_kvm_fpu(0);
}
@@ -7069,32 +7302,40 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
kvmclock_reset(vcpu);
free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
- fx_free(vcpu);
kvm_x86_ops->vcpu_free(vcpu);
}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
unsigned int id)
{
+ struct kvm_vcpu *vcpu;
+
if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
printk_once(KERN_WARNING
"kvm: SMP vm created on host with unstable TSC; "
"guest TSC will not be reliable\n");
- return kvm_x86_ops->vcpu_create(kvm, id);
+
+ vcpu = kvm_x86_ops->vcpu_create(kvm, id);
+
+ /*
+ * Activate fpu unconditionally in case the guest needs eager FPU. It will be
+ * deactivated soon if it doesn't.
+ */
+ kvm_x86_ops->fpu_activate(vcpu);
+ return vcpu;
}
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
int r;
- vcpu->arch.mtrr_state.have_fixed = 1;
+ kvm_vcpu_mtrr_init(vcpu);
r = vcpu_load(vcpu);
if (r)
return r;
- kvm_vcpu_reset(vcpu);
+ kvm_vcpu_reset(vcpu, false);
kvm_mmu_setup(vcpu);
vcpu_put(vcpu);
-
return r;
}
@@ -7111,6 +7352,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
kvm_write_tsc(vcpu, &msr);
vcpu_put(vcpu);
+ if (!kvmclock_periodic_sync)
+ return;
+
schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
KVMCLOCK_SYNC_PERIOD);
}
@@ -7125,12 +7369,13 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
- fx_free(vcpu);
kvm_x86_ops->vcpu_free(vcpu);
}
-void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
+void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
+ vcpu->arch.hflags = 0;
+
atomic_set(&vcpu->arch.nmi_queued, 0);
vcpu->arch.nmi_pending = 0;
vcpu->arch.nmi_injected = false;
@@ -7156,13 +7401,16 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
kvm_async_pf_hash_reset(vcpu);
vcpu->arch.apf.halted = false;
- kvm_pmu_reset(vcpu);
+ if (!init_event) {
+ kvm_pmu_reset(vcpu);
+ vcpu->arch.smbase = 0x30000;
+ }
memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
vcpu->arch.regs_avail = ~0;
vcpu->arch.regs_dirty = ~0;
- kvm_x86_ops->vcpu_reset(vcpu);
+ kvm_x86_ops->vcpu_reset(vcpu, init_event);
}
void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
@@ -7351,9 +7599,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
goto fail_free_mce_banks;
}
- r = fx_init(vcpu);
- if (r)
- goto fail_free_wbinvd_dirty_mask;
+ fx_init(vcpu);
vcpu->arch.ia32_tsc_adjust_msr = 0x0;
vcpu->arch.pv_time_enabled = false;
@@ -7363,12 +7609,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+ vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
+
kvm_async_pf_hash_reset(vcpu);
kvm_pmu_init(vcpu);
return 0;
-fail_free_wbinvd_dirty_mask:
- free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
+
fail_free_mce_banks:
kfree(vcpu->arch.mce_banks);
fail_free_lapic:
@@ -7470,6 +7717,40 @@ void kvm_arch_sync_events(struct kvm *kvm)
kvm_free_pit(kvm);
}
+int __x86_set_memory_region(struct kvm *kvm,
+ const struct kvm_userspace_memory_region *mem)
+{
+ int i, r;
+
+ /* Called with kvm->slots_lock held. */
+ BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM);
+
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ struct kvm_userspace_memory_region m = *mem;
+
+ m.slot |= i << 16;
+ r = __kvm_set_memory_region(kvm, &m);
+ if (r < 0)
+ return r;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__x86_set_memory_region);
+
+int x86_set_memory_region(struct kvm *kvm,
+ const struct kvm_userspace_memory_region *mem)
+{
+ int r;
+
+ mutex_lock(&kvm->slots_lock);
+ r = __x86_set_memory_region(kvm, mem);
+ mutex_unlock(&kvm->slots_lock);
+
+ return r;
+}
+EXPORT_SYMBOL_GPL(x86_set_memory_region);
+
void kvm_arch_destroy_vm(struct kvm *kvm)
{
if (current->mm == kvm->mm) {
@@ -7481,13 +7762,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
struct kvm_userspace_memory_region mem;
memset(&mem, 0, sizeof(mem));
mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
- kvm_set_memory_region(kvm, &mem);
+ x86_set_memory_region(kvm, &mem);
mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
- kvm_set_memory_region(kvm, &mem);
+ x86_set_memory_region(kvm, &mem);
mem.slot = TSS_PRIVATE_MEMSLOT;
- kvm_set_memory_region(kvm, &mem);
+ x86_set_memory_region(kvm, &mem);
}
kvm_iommu_unmap_guest(kvm);
kfree(kvm->arch.vpic);
@@ -7576,18 +7857,18 @@ out_free:
return -ENOMEM;
}
-void kvm_arch_memslots_updated(struct kvm *kvm)
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
{
/*
* memslots->generation has been incremented.
* mmio generation may have reached its maximum value.
*/
- kvm_mmu_invalidate_mmio_sptes(kvm);
+ kvm_mmu_invalidate_mmio_sptes(kvm, slots);
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
/*
@@ -7665,14 +7946,14 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+ const struct kvm_userspace_memory_region *mem,
const struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
- struct kvm_memory_slot *new;
int nr_mmu_pages = 0;
- if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) {
+ if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) {
int ret;
ret = vm_munmap(old->userspace_addr,
@@ -7689,9 +7970,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
if (nr_mmu_pages)
kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
- /* It's OK to get 'new' slot here as it has already been installed */
- new = id_to_memslot(kvm->memslots, mem->slot);
-
/*
* Dirty logging tracks sptes in 4k granularity, meaning that large
* sptes have to be split. If live migration is successful, the guest
@@ -7716,9 +7994,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
* been zapped so no dirty logging staff is needed for old slot. For
* KVM_MR_FLAGS_ONLY, the old slot is essentially the same one as the
* new and it's also covered when dealing with the new slot.
+ *
+ * FIXME: const-ify all uses of struct kvm_memory_slot.
*/
if (change != KVM_MR_DELETE)
- kvm_mmu_slot_apply_flags(kvm, new);
+ kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new);
}
void kvm_arch_flush_shadow_all(struct kvm *kvm)
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index f5fef1868096..edc8cdcd786b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -4,6 +4,8 @@
#include <linux/kvm_host.h>
#include "kvm_cache_regs.h"
+#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL
+
static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
{
vcpu->arch.exception.pending = false;
@@ -160,7 +162,13 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
gva_t addr, void *val, unsigned int bytes,
struct x86_exception *exception);
+void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
+u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
+ int page_num);
#define KVM_SUPPORTED_XCR0 (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
| XSTATE_BNDREGS | XSTATE_BNDCSR \
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 8f9a133cc099..f2dc08c003eb 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -70,7 +70,7 @@
#include <asm/e820.h>
#include <asm/mce.h>
#include <asm/io.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/stackprotector.h>
#include <asm/reboot.h> /* for struct machine_ops */
#include <asm/kvm_para.h>
@@ -90,7 +90,7 @@ struct lguest_data lguest_data = {
.noirq_iret = (u32)lguest_noirq_iret,
.kernel_address = PAGE_OFFSET,
.blocked_interrupts = { 1 }, /* Block timer interrupts */
- .syscall_vec = SYSCALL_VECTOR,
+ .syscall_vec = IA32_SYSCALL_VECTOR,
};
/*G:037
@@ -866,7 +866,7 @@ static void __init lguest_init_IRQ(void)
for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
/* Some systems map "vectors" to interrupts weirdly. Not us! */
__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
- if (i != SYSCALL_VECTOR)
+ if (i != IA32_SYSCALL_VECTOR)
set_intr_gate(i, irq_entries_start +
8 * (i - FIRST_EXTERNAL_VECTOR));
}
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 1530afb07c85..f2587888d987 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -17,7 +17,6 @@ clean-files := inat-tables.c
obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
lib-y := delay.o misc.o cmdline.o
-lib-y += thunk_$(BITS).o
lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
@@ -40,6 +39,6 @@ else
lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
lib-y += clear_page_64.o copy_page_64.o
lib-y += memmove_64.o memset_64.o
- lib-y += copy_user_64.o copy_user_nocache_64.o
+ lib-y += copy_user_64.o
lib-y += cmpxchg16b_emu.o
endif
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 00933d5e992f..9b0ca8fe80fc 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -11,26 +11,23 @@
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
/* if you want SMP support, implement these with real spinlocks */
.macro LOCK reg
- pushfl_cfi
+ pushfl
cli
.endm
.macro UNLOCK reg
- popfl_cfi
+ popfl
.endm
#define BEGIN(op) \
.macro endp; \
- CFI_ENDPROC; \
ENDPROC(atomic64_##op##_386); \
.purgem endp; \
.endm; \
ENTRY(atomic64_##op##_386); \
- CFI_STARTPROC; \
LOCK v;
#define ENDP endp
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 082a85167a5b..db3ae85440ff 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -11,7 +11,6 @@
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
.macro read64 reg
movl %ebx, %eax
@@ -22,16 +21,11 @@
.endm
ENTRY(atomic64_read_cx8)
- CFI_STARTPROC
-
read64 %ecx
ret
- CFI_ENDPROC
ENDPROC(atomic64_read_cx8)
ENTRY(atomic64_set_cx8)
- CFI_STARTPROC
-
1:
/* we don't need LOCK_PREFIX since aligned 64-bit writes
* are atomic on 586 and newer */
@@ -39,28 +33,23 @@ ENTRY(atomic64_set_cx8)
jne 1b
ret
- CFI_ENDPROC
ENDPROC(atomic64_set_cx8)
ENTRY(atomic64_xchg_cx8)
- CFI_STARTPROC
-
1:
LOCK_PREFIX
cmpxchg8b (%esi)
jne 1b
ret
- CFI_ENDPROC
ENDPROC(atomic64_xchg_cx8)
.macro addsub_return func ins insc
ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebp
- pushl_cfi_reg ebx
- pushl_cfi_reg esi
- pushl_cfi_reg edi
+ pushl %ebp
+ pushl %ebx
+ pushl %esi
+ pushl %edi
movl %eax, %esi
movl %edx, %edi
@@ -79,12 +68,11 @@ ENTRY(atomic64_\func\()_return_cx8)
10:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg edi
- popl_cfi_reg esi
- popl_cfi_reg ebx
- popl_cfi_reg ebp
+ popl %edi
+ popl %esi
+ popl %ebx
+ popl %ebp
ret
- CFI_ENDPROC
ENDPROC(atomic64_\func\()_return_cx8)
.endm
@@ -93,8 +81,7 @@ addsub_return sub sub sbb
.macro incdec_return func ins insc
ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
@@ -109,9 +96,8 @@ ENTRY(atomic64_\func\()_return_cx8)
10:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_\func\()_return_cx8)
.endm
@@ -119,8 +105,7 @@ incdec_return inc add adc
incdec_return dec sub sbb
ENTRY(atomic64_dec_if_positive_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
@@ -136,18 +121,16 @@ ENTRY(atomic64_dec_if_positive_cx8)
2:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_dec_if_positive_cx8)
ENTRY(atomic64_add_unless_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebp
- pushl_cfi_reg ebx
+ pushl %ebp
+ pushl %ebx
/* these just push these two parameters on the stack */
- pushl_cfi_reg edi
- pushl_cfi_reg ecx
+ pushl %edi
+ pushl %ecx
movl %eax, %ebp
movl %edx, %edi
@@ -168,21 +151,18 @@ ENTRY(atomic64_add_unless_cx8)
movl $1, %eax
3:
addl $8, %esp
- CFI_ADJUST_CFA_OFFSET -8
- popl_cfi_reg ebx
- popl_cfi_reg ebp
+ popl %ebx
+ popl %ebp
ret
4:
cmpl %edx, 4(%esp)
jne 2b
xorl %eax, %eax
jmp 3b
- CFI_ENDPROC
ENDPROC(atomic64_add_unless_cx8)
ENTRY(atomic64_inc_not_zero_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
@@ -199,7 +179,6 @@ ENTRY(atomic64_inc_not_zero_cx8)
movl $1, %eax
3:
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 9bc944a91274..c1e623209853 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -26,7 +26,6 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/errno.h>
#include <asm/asm.h>
@@ -50,9 +49,8 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
* alignment for the unrolled loop.
*/
ENTRY(csum_partial)
- CFI_STARTPROC
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %esi
+ pushl %ebx
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
movl 12(%esp),%esi # Function arg: unsigned char *buff
@@ -129,10 +127,9 @@ ENTRY(csum_partial)
jz 8f
roll $8, %eax
8:
- popl_cfi_reg ebx
- popl_cfi_reg esi
+ popl %ebx
+ popl %esi
ret
- CFI_ENDPROC
ENDPROC(csum_partial)
#else
@@ -140,9 +137,8 @@ ENDPROC(csum_partial)
/* Version for PentiumII/PPro */
ENTRY(csum_partial)
- CFI_STARTPROC
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %esi
+ pushl %ebx
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
movl 12(%esp),%esi # Function arg: const unsigned char *buf
@@ -249,10 +245,9 @@ ENTRY(csum_partial)
jz 90f
roll $8, %eax
90:
- popl_cfi_reg ebx
- popl_cfi_reg esi
+ popl %ebx
+ popl %esi
ret
- CFI_ENDPROC
ENDPROC(csum_partial)
#endif
@@ -287,12 +282,10 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
#define FP 12
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
subl $4,%esp
- CFI_ADJUST_CFA_OFFSET 4
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %edi
+ pushl %esi
+ pushl %ebx
movl ARGBASE+16(%esp),%eax # sum
movl ARGBASE+12(%esp),%ecx # len
movl ARGBASE+4(%esp),%esi # src
@@ -401,12 +394,11 @@ DST( movb %cl, (%edi) )
.previous
- popl_cfi_reg ebx
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi %ecx # equivalent to addl $4,%esp
+ popl %ebx
+ popl %esi
+ popl %edi
+ popl %ecx # equivalent to addl $4,%esp
ret
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
#else
@@ -426,10 +418,9 @@ ENDPROC(csum_partial_copy_generic)
#define ARGBASE 12
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
- pushl_cfi_reg ebx
- pushl_cfi_reg edi
- pushl_cfi_reg esi
+ pushl %ebx
+ pushl %edi
+ pushl %esi
movl ARGBASE+4(%esp),%esi #src
movl ARGBASE+8(%esp),%edi #dst
movl ARGBASE+12(%esp),%ecx #len
@@ -489,11 +480,10 @@ DST( movb %dl, (%edi) )
jmp 7b
.previous
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi_reg ebx
+ popl %esi
+ popl %edi
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
#undef ROUND
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index e67e579c93bd..a2fe51b00cce 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,4 @@
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
@@ -15,7 +14,6 @@
* %rdi - page
*/
ENTRY(clear_page)
- CFI_STARTPROC
ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \
"jmp clear_page_c_e", X86_FEATURE_ERMS
@@ -24,11 +22,9 @@ ENTRY(clear_page)
xorl %eax,%eax
rep stosq
ret
- CFI_ENDPROC
ENDPROC(clear_page)
ENTRY(clear_page_orig)
- CFI_STARTPROC
xorl %eax,%eax
movl $4096/64,%ecx
@@ -48,14 +44,11 @@ ENTRY(clear_page_orig)
jnz .Lloop
nop
ret
- CFI_ENDPROC
ENDPROC(clear_page_orig)
ENTRY(clear_page_c_e)
- CFI_STARTPROC
movl $4096,%ecx
xorl %eax,%eax
rep stosb
ret
- CFI_ENDPROC
ENDPROC(clear_page_c_e)
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 40a172541ee2..9b330242e740 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -6,7 +6,6 @@
*
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/percpu.h>
.text
@@ -21,7 +20,6 @@
* %al : Operation successful
*/
ENTRY(this_cpu_cmpxchg16b_emu)
-CFI_STARTPROC
#
# Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
@@ -32,7 +30,7 @@ CFI_STARTPROC
# *atomic* on a single cpu (as provided by the this_cpu_xx class of
# macros).
#
- pushfq_cfi
+ pushfq
cli
cmpq PER_CPU_VAR((%rsi)), %rax
@@ -43,17 +41,13 @@ CFI_STARTPROC
movq %rbx, PER_CPU_VAR((%rsi))
movq %rcx, PER_CPU_VAR(8(%rsi))
- CFI_REMEMBER_STATE
- popfq_cfi
+ popfq
mov $1, %al
ret
- CFI_RESTORE_STATE
.Lnot_same:
- popfq_cfi
+ popfq
xor %al,%al
ret
-CFI_ENDPROC
-
ENDPROC(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index b4807fce5177..ad5349778490 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,6 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
.text
@@ -20,14 +19,13 @@
* %ecx : high 32 bits of new value
*/
ENTRY(cmpxchg8b_emu)
-CFI_STARTPROC
#
# Emulate 'cmpxchg8b (%esi)' on UP except we don't
# set the whole ZF thing (caller will just compare
# eax:edx with the expected value)
#
- pushfl_cfi
+ pushfl
cli
cmpl (%esi), %eax
@@ -38,18 +36,15 @@ CFI_STARTPROC
movl %ebx, (%esi)
movl %ecx, 4(%esi)
- CFI_REMEMBER_STATE
- popfl_cfi
+ popfl
ret
- CFI_RESTORE_STATE
.Lnot_same:
movl (%esi), %eax
.Lhalf_same:
movl 4(%esi), %edx
- popfl_cfi
+ popfl
ret
-CFI_ENDPROC
ENDPROC(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 8239dbcbf984..009f98216b7e 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,7 +1,6 @@
/* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
@@ -13,22 +12,16 @@
*/
ALIGN
ENTRY(copy_page)
- CFI_STARTPROC
ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
movl $4096/8, %ecx
rep movsq
ret
- CFI_ENDPROC
ENDPROC(copy_page)
ENTRY(copy_page_regs)
- CFI_STARTPROC
subq $2*8, %rsp
- CFI_ADJUST_CFA_OFFSET 2*8
movq %rbx, (%rsp)
- CFI_REL_OFFSET rbx, 0
movq %r12, 1*8(%rsp)
- CFI_REL_OFFSET r12, 1*8
movl $(4096/64)-5, %ecx
.p2align 4
@@ -87,11 +80,7 @@ ENTRY(copy_page_regs)
jnz .Loop2
movq (%rsp), %rbx
- CFI_RESTORE rbx
movq 1*8(%rsp), %r12
- CFI_RESTORE r12
addq $2*8, %rsp
- CFI_ADJUST_CFA_OFFSET -2*8
ret
- CFI_ENDPROC
ENDPROC(copy_page_regs)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fa997dfaef24..982ce34f4a9b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -7,7 +7,6 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/current.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
@@ -16,33 +15,8 @@
#include <asm/asm.h>
#include <asm/smap.h>
- .macro ALIGN_DESTINATION
- /* check for bad alignment of destination */
- movl %edi,%ecx
- andl $7,%ecx
- jz 102f /* already aligned */
- subl $8,%ecx
- negl %ecx
- subl %ecx,%edx
-100: movb (%rsi),%al
-101: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 100b
-102:
- .section .fixup,"ax"
-103: addl %ecx,%edx /* ecx is zerorest also */
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
- .endm
-
/* Standard copy_to_user with segment limit checking */
ENTRY(_copy_to_user)
- CFI_STARTPROC
GET_THREAD_INFO(%rax)
movq %rdi,%rcx
addq %rdx,%rcx
@@ -54,12 +28,10 @@ ENTRY(_copy_to_user)
X86_FEATURE_REP_GOOD, \
"jmp copy_user_enhanced_fast_string", \
X86_FEATURE_ERMS
- CFI_ENDPROC
ENDPROC(_copy_to_user)
/* Standard copy_from_user with segment limit checking */
ENTRY(_copy_from_user)
- CFI_STARTPROC
GET_THREAD_INFO(%rax)
movq %rsi,%rcx
addq %rdx,%rcx
@@ -71,14 +43,12 @@ ENTRY(_copy_from_user)
X86_FEATURE_REP_GOOD, \
"jmp copy_user_enhanced_fast_string", \
X86_FEATURE_ERMS
- CFI_ENDPROC
ENDPROC(_copy_from_user)
.section .fixup,"ax"
/* must zero dest */
ENTRY(bad_from_user)
bad_from_user:
- CFI_STARTPROC
movl %edx,%ecx
xorl %eax,%eax
rep
@@ -86,7 +56,6 @@ bad_from_user:
bad_to_user:
movl %edx,%eax
ret
- CFI_ENDPROC
ENDPROC(bad_from_user)
.previous
@@ -104,7 +73,6 @@ ENDPROC(bad_from_user)
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_unrolled)
- CFI_STARTPROC
ASM_STAC
cmpl $8,%edx
jb 20f /* less then 8 bytes, go to byte copy loop */
@@ -186,7 +154,6 @@ ENTRY(copy_user_generic_unrolled)
_ASM_EXTABLE(19b,40b)
_ASM_EXTABLE(21b,50b)
_ASM_EXTABLE(22b,50b)
- CFI_ENDPROC
ENDPROC(copy_user_generic_unrolled)
/* Some CPUs run faster using the string copy instructions.
@@ -208,7 +175,6 @@ ENDPROC(copy_user_generic_unrolled)
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_string)
- CFI_STARTPROC
ASM_STAC
cmpl $8,%edx
jb 2f /* less than 8 bytes, go to byte copy loop */
@@ -233,7 +199,6 @@ ENTRY(copy_user_generic_string)
_ASM_EXTABLE(1b,11b)
_ASM_EXTABLE(3b,12b)
- CFI_ENDPROC
ENDPROC(copy_user_generic_string)
/*
@@ -249,7 +214,6 @@ ENDPROC(copy_user_generic_string)
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_enhanced_fast_string)
- CFI_STARTPROC
ASM_STAC
movl %edx,%ecx
1: rep
@@ -264,5 +228,94 @@ ENTRY(copy_user_enhanced_fast_string)
.previous
_ASM_EXTABLE(1b,12b)
- CFI_ENDPROC
ENDPROC(copy_user_enhanced_fast_string)
+
+/*
+ * copy_user_nocache - Uncached memory copy with exception handling
+ * This will force destination/source out of cache for more performance.
+ */
+ENTRY(__copy_user_nocache)
+ ASM_STAC
+ cmpl $8,%edx
+ jb 20f /* less then 8 bytes, go to byte copy loop */
+ ALIGN_DESTINATION
+ movl %edx,%ecx
+ andl $63,%edx
+ shrl $6,%ecx
+ jz 17f
+1: movq (%rsi),%r8
+2: movq 1*8(%rsi),%r9
+3: movq 2*8(%rsi),%r10
+4: movq 3*8(%rsi),%r11
+5: movnti %r8,(%rdi)
+6: movnti %r9,1*8(%rdi)
+7: movnti %r10,2*8(%rdi)
+8: movnti %r11,3*8(%rdi)
+9: movq 4*8(%rsi),%r8
+10: movq 5*8(%rsi),%r9
+11: movq 6*8(%rsi),%r10
+12: movq 7*8(%rsi),%r11
+13: movnti %r8,4*8(%rdi)
+14: movnti %r9,5*8(%rdi)
+15: movnti %r10,6*8(%rdi)
+16: movnti %r11,7*8(%rdi)
+ leaq 64(%rsi),%rsi
+ leaq 64(%rdi),%rdi
+ decl %ecx
+ jnz 1b
+17: movl %edx,%ecx
+ andl $7,%edx
+ shrl $3,%ecx
+ jz 20f
+18: movq (%rsi),%r8
+19: movnti %r8,(%rdi)
+ leaq 8(%rsi),%rsi
+ leaq 8(%rdi),%rdi
+ decl %ecx
+ jnz 18b
+20: andl %edx,%edx
+ jz 23f
+ movl %edx,%ecx
+21: movb (%rsi),%al
+22: movb %al,(%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz 21b
+23: xorl %eax,%eax
+ ASM_CLAC
+ sfence
+ ret
+
+ .section .fixup,"ax"
+30: shll $6,%ecx
+ addl %ecx,%edx
+ jmp 60f
+40: lea (%rdx,%rcx,8),%rdx
+ jmp 60f
+50: movl %ecx,%edx
+60: sfence
+ jmp copy_user_handle_tail
+ .previous
+
+ _ASM_EXTABLE(1b,30b)
+ _ASM_EXTABLE(2b,30b)
+ _ASM_EXTABLE(3b,30b)
+ _ASM_EXTABLE(4b,30b)
+ _ASM_EXTABLE(5b,30b)
+ _ASM_EXTABLE(6b,30b)
+ _ASM_EXTABLE(7b,30b)
+ _ASM_EXTABLE(8b,30b)
+ _ASM_EXTABLE(9b,30b)
+ _ASM_EXTABLE(10b,30b)
+ _ASM_EXTABLE(11b,30b)
+ _ASM_EXTABLE(12b,30b)
+ _ASM_EXTABLE(13b,30b)
+ _ASM_EXTABLE(14b,30b)
+ _ASM_EXTABLE(15b,30b)
+ _ASM_EXTABLE(16b,30b)
+ _ASM_EXTABLE(18b,40b)
+ _ASM_EXTABLE(19b,40b)
+ _ASM_EXTABLE(21b,50b)
+ _ASM_EXTABLE(22b,50b)
+ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
deleted file mode 100644
index 6a4f43c2d9e6..000000000000
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ /dev/null
@@ -1,136 +0,0 @@
-/*
- * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
- * Copyright 2002 Andi Kleen, SuSE Labs.
- * Subject to the GNU Public License v2.
- *
- * Functions to copy from and to user space.
- */
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-
-#define FIX_ALIGNMENT 1
-
-#include <asm/current.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
- .macro ALIGN_DESTINATION
-#ifdef FIX_ALIGNMENT
- /* check for bad alignment of destination */
- movl %edi,%ecx
- andl $7,%ecx
- jz 102f /* already aligned */
- subl $8,%ecx
- negl %ecx
- subl %ecx,%edx
-100: movb (%rsi),%al
-101: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 100b
-102:
- .section .fixup,"ax"
-103: addl %ecx,%edx /* ecx is zerorest also */
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
-#endif
- .endm
-
-/*
- * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
- */
-ENTRY(__copy_user_nocache)
- CFI_STARTPROC
- ASM_STAC
- cmpl $8,%edx
- jb 20f /* less then 8 bytes, go to byte copy loop */
- ALIGN_DESTINATION
- movl %edx,%ecx
- andl $63,%edx
- shrl $6,%ecx
- jz 17f
-1: movq (%rsi),%r8
-2: movq 1*8(%rsi),%r9
-3: movq 2*8(%rsi),%r10
-4: movq 3*8(%rsi),%r11
-5: movnti %r8,(%rdi)
-6: movnti %r9,1*8(%rdi)
-7: movnti %r10,2*8(%rdi)
-8: movnti %r11,3*8(%rdi)
-9: movq 4*8(%rsi),%r8
-10: movq 5*8(%rsi),%r9
-11: movq 6*8(%rsi),%r10
-12: movq 7*8(%rsi),%r11
-13: movnti %r8,4*8(%rdi)
-14: movnti %r9,5*8(%rdi)
-15: movnti %r10,6*8(%rdi)
-16: movnti %r11,7*8(%rdi)
- leaq 64(%rsi),%rsi
- leaq 64(%rdi),%rdi
- decl %ecx
- jnz 1b
-17: movl %edx,%ecx
- andl $7,%edx
- shrl $3,%ecx
- jz 20f
-18: movq (%rsi),%r8
-19: movnti %r8,(%rdi)
- leaq 8(%rsi),%rsi
- leaq 8(%rdi),%rdi
- decl %ecx
- jnz 18b
-20: andl %edx,%edx
- jz 23f
- movl %edx,%ecx
-21: movb (%rsi),%al
-22: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 21b
-23: xorl %eax,%eax
- ASM_CLAC
- sfence
- ret
-
- .section .fixup,"ax"
-30: shll $6,%ecx
- addl %ecx,%edx
- jmp 60f
-40: lea (%rdx,%rcx,8),%rdx
- jmp 60f
-50: movl %ecx,%edx
-60: sfence
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(1b,30b)
- _ASM_EXTABLE(2b,30b)
- _ASM_EXTABLE(3b,30b)
- _ASM_EXTABLE(4b,30b)
- _ASM_EXTABLE(5b,30b)
- _ASM_EXTABLE(6b,30b)
- _ASM_EXTABLE(7b,30b)
- _ASM_EXTABLE(8b,30b)
- _ASM_EXTABLE(9b,30b)
- _ASM_EXTABLE(10b,30b)
- _ASM_EXTABLE(11b,30b)
- _ASM_EXTABLE(12b,30b)
- _ASM_EXTABLE(13b,30b)
- _ASM_EXTABLE(14b,30b)
- _ASM_EXTABLE(15b,30b)
- _ASM_EXTABLE(16b,30b)
- _ASM_EXTABLE(18b,40b)
- _ASM_EXTABLE(19b,40b)
- _ASM_EXTABLE(21b,50b)
- _ASM_EXTABLE(22b,50b)
- CFI_ENDPROC
-ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 9734182966f3..7e48807b2fa1 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -6,7 +6,6 @@
* for more details. No warranty for anything given at all.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/errno.h>
#include <asm/asm.h>
@@ -47,23 +46,16 @@
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
cmpl $3*64, %edx
jle .Lignore
.Lignore:
subq $7*8, %rsp
- CFI_ADJUST_CFA_OFFSET 7*8
movq %rbx, 2*8(%rsp)
- CFI_REL_OFFSET rbx, 2*8
movq %r12, 3*8(%rsp)
- CFI_REL_OFFSET r12, 3*8
movq %r14, 4*8(%rsp)
- CFI_REL_OFFSET r14, 4*8
movq %r13, 5*8(%rsp)
- CFI_REL_OFFSET r13, 5*8
movq %rbp, 6*8(%rsp)
- CFI_REL_OFFSET rbp, 6*8
movq %r8, (%rsp)
movq %r9, 1*8(%rsp)
@@ -206,22 +198,14 @@ ENTRY(csum_partial_copy_generic)
addl %ebx, %eax
adcl %r9d, %eax /* carry */
- CFI_REMEMBER_STATE
.Lende:
movq 2*8(%rsp), %rbx
- CFI_RESTORE rbx
movq 3*8(%rsp), %r12
- CFI_RESTORE r12
movq 4*8(%rsp), %r14
- CFI_RESTORE r14
movq 5*8(%rsp), %r13
- CFI_RESTORE r13
movq 6*8(%rsp), %rbp
- CFI_RESTORE rbp
addq $7*8, %rsp
- CFI_ADJUST_CFA_OFFSET -7*8
ret
- CFI_RESTORE_STATE
/* Exception handlers. Very simple, zeroing is done in the wrappers */
.Lbad_source:
@@ -237,5 +221,4 @@ ENTRY(csum_partial_copy_generic)
jz .Lende
movl $-EFAULT, (%rax)
jmp .Lende
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index a4512359656a..46668cda4ffd 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -26,7 +26,6 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/page_types.h>
#include <asm/errno.h>
#include <asm/asm-offsets.h>
@@ -36,7 +35,6 @@
.text
ENTRY(__get_user_1)
- CFI_STARTPROC
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
@@ -45,11 +43,9 @@ ENTRY(__get_user_1)
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_1)
ENTRY(__get_user_2)
- CFI_STARTPROC
add $1,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
@@ -60,11 +56,9 @@ ENTRY(__get_user_2)
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_2)
ENTRY(__get_user_4)
- CFI_STARTPROC
add $3,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
@@ -75,11 +69,9 @@ ENTRY(__get_user_4)
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_4)
ENTRY(__get_user_8)
- CFI_STARTPROC
#ifdef CONFIG_X86_64
add $7,%_ASM_AX
jc bad_get_user
@@ -104,28 +96,23 @@ ENTRY(__get_user_8)
ASM_CLAC
ret
#endif
- CFI_ENDPROC
ENDPROC(__get_user_8)
bad_get_user:
- CFI_STARTPROC
xor %edx,%edx
mov $(-EFAULT),%_ASM_AX
ASM_CLAC
ret
- CFI_ENDPROC
END(bad_get_user)
#ifdef CONFIG_X86_32
bad_get_user_8:
- CFI_STARTPROC
xor %edx,%edx
xor %ecx,%ecx
mov $(-EFAULT),%_ASM_AX
ASM_CLAC
ret
- CFI_ENDPROC
END(bad_get_user_8)
#endif
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index 05a95e713da8..33147fef3452 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -16,15 +16,12 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
/*
* override generic version in lib/iomap_copy.c
*/
ENTRY(__iowrite32_copy)
- CFI_STARTPROC
movl %edx,%ecx
rep movsd
ret
- CFI_ENDPROC
ENDPROC(__iowrite32_copy)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index b046664f5a1c..16698bba87de 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -2,7 +2,6 @@
#include <linux/linkage.h>
#include <asm/cpufeature.h>
-#include <asm/dwarf2.h>
#include <asm/alternative-asm.h>
/*
@@ -53,7 +52,6 @@ ENTRY(memcpy_erms)
ENDPROC(memcpy_erms)
ENTRY(memcpy_orig)
- CFI_STARTPROC
movq %rdi, %rax
cmpq $0x20, %rdx
@@ -178,5 +176,4 @@ ENTRY(memcpy_orig)
.Lend:
retq
- CFI_ENDPROC
ENDPROC(memcpy_orig)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0f8a0d0331b9..ca2afdd6d98e 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,7 +6,6 @@
* - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
@@ -27,7 +26,6 @@
ENTRY(memmove)
ENTRY(__memmove)
- CFI_STARTPROC
/* Handle more 32 bytes in loop */
mov %rdi, %rax
@@ -207,6 +205,5 @@ ENTRY(__memmove)
movb %r11b, (%rdi)
13:
retq
- CFI_ENDPROC
ENDPROC(__memmove)
ENDPROC(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 93118fb23976..2661fad05827 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,7 +1,6 @@
/* Copyright 2002 Andi Kleen, SuSE Labs */
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
@@ -66,7 +65,6 @@ ENTRY(memset_erms)
ENDPROC(memset_erms)
ENTRY(memset_orig)
- CFI_STARTPROC
movq %rdi,%r10
/* expand byte value */
@@ -78,7 +76,6 @@ ENTRY(memset_orig)
movl %edi,%r9d
andl $7,%r9d
jnz .Lbad_alignment
- CFI_REMEMBER_STATE
.Lafter_bad_alignment:
movq %rdx,%rcx
@@ -128,7 +125,6 @@ ENTRY(memset_orig)
movq %r10,%rax
ret
- CFI_RESTORE_STATE
.Lbad_alignment:
cmpq $7,%rdx
jbe .Lhandle_7
@@ -139,5 +135,4 @@ ENTRY(memset_orig)
subq %r8,%rdx
jmp .Lafter_bad_alignment
.Lfinal:
- CFI_ENDPROC
ENDPROC(memset_orig)
diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c
index c9f2d9ba8dd8..e5e3ed8dc079 100644
--- a/arch/x86/lib/mmx_32.c
+++ b/arch/x86/lib/mmx_32.c
@@ -22,7 +22,7 @@
#include <linux/sched.h>
#include <linux/types.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/asm.h>
void *_mmx_memcpy(void *to, const void *from, size_t len)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index 3ca5218fbece..c81556409bbb 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,5 @@
#include <linux/linkage.h>
#include <linux/errno.h>
-#include <asm/dwarf2.h>
#include <asm/asm.h>
#include <asm/msr.h>
@@ -13,9 +12,8 @@
*/
.macro op_safe_regs op
ENTRY(\op\()_safe_regs)
- CFI_STARTPROC
- pushq_cfi_reg rbx
- pushq_cfi_reg rbp
+ pushq %rbx
+ pushq %rbp
movq %rdi, %r10 /* Save pointer */
xorl %r11d, %r11d /* Return value */
movl (%rdi), %eax
@@ -25,7 +23,6 @@ ENTRY(\op\()_safe_regs)
movl 20(%rdi), %ebp
movl 24(%rdi), %esi
movl 28(%rdi), %edi
- CFI_REMEMBER_STATE
1: \op
2: movl %eax, (%r10)
movl %r11d, %eax /* Return value */
@@ -35,16 +32,14 @@ ENTRY(\op\()_safe_regs)
movl %ebp, 20(%r10)
movl %esi, 24(%r10)
movl %edi, 28(%r10)
- popq_cfi_reg rbp
- popq_cfi_reg rbx
+ popq %rbp
+ popq %rbx
ret
3:
- CFI_RESTORE_STATE
movl $-EIO, %r11d
jmp 2b
_ASM_EXTABLE(1b, 3b)
- CFI_ENDPROC
ENDPROC(\op\()_safe_regs)
.endm
@@ -52,13 +47,12 @@ ENDPROC(\op\()_safe_regs)
.macro op_safe_regs op
ENTRY(\op\()_safe_regs)
- CFI_STARTPROC
- pushl_cfi_reg ebx
- pushl_cfi_reg ebp
- pushl_cfi_reg esi
- pushl_cfi_reg edi
- pushl_cfi $0 /* Return value */
- pushl_cfi %eax
+ pushl %ebx
+ pushl %ebp
+ pushl %esi
+ pushl %edi
+ pushl $0 /* Return value */
+ pushl %eax
movl 4(%eax), %ecx
movl 8(%eax), %edx
movl 12(%eax), %ebx
@@ -66,32 +60,28 @@ ENTRY(\op\()_safe_regs)
movl 24(%eax), %esi
movl 28(%eax), %edi
movl (%eax), %eax
- CFI_REMEMBER_STATE
1: \op
-2: pushl_cfi %eax
+2: pushl %eax
movl 4(%esp), %eax
- popl_cfi (%eax)
+ popl (%eax)
addl $4, %esp
- CFI_ADJUST_CFA_OFFSET -4
movl %ecx, 4(%eax)
movl %edx, 8(%eax)
movl %ebx, 12(%eax)
movl %ebp, 20(%eax)
movl %esi, 24(%eax)
movl %edi, 28(%eax)
- popl_cfi %eax
- popl_cfi_reg edi
- popl_cfi_reg esi
- popl_cfi_reg ebp
- popl_cfi_reg ebx
+ popl %eax
+ popl %edi
+ popl %esi
+ popl %ebp
+ popl %ebx
ret
3:
- CFI_RESTORE_STATE
movl $-EIO, 4(%esp)
jmp 2b
_ASM_EXTABLE(1b, 3b)
- CFI_ENDPROC
ENDPROC(\op\()_safe_regs)
.endm
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index fc6ba17a7eec..e0817a12d323 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -11,7 +11,6 @@
* return value.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/thread_info.h>
#include <asm/errno.h>
#include <asm/asm.h>
@@ -30,11 +29,9 @@
* as they get called from within inline assembly.
*/
-#define ENTER CFI_STARTPROC ; \
- GET_THREAD_INFO(%_ASM_BX)
+#define ENTER GET_THREAD_INFO(%_ASM_BX)
#define EXIT ASM_CLAC ; \
- ret ; \
- CFI_ENDPROC
+ ret
.text
ENTRY(__put_user_1)
@@ -87,7 +84,6 @@ ENTRY(__put_user_8)
ENDPROC(__put_user_8)
bad_put_user:
- CFI_STARTPROC
movl $-EFAULT,%eax
EXIT
END(bad_put_user)
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
index 2322abe4da3b..40027db99140 100644
--- a/arch/x86/lib/rwsem.S
+++ b/arch/x86/lib/rwsem.S
@@ -15,7 +15,6 @@
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
#define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg)
#define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l)
@@ -34,10 +33,10 @@
*/
#define save_common_regs \
- pushl_cfi_reg ecx
+ pushl %ecx
#define restore_common_regs \
- popl_cfi_reg ecx
+ popl %ecx
/* Avoid uglifying the argument copying x86-64 needs to do. */
.macro movq src, dst
@@ -64,50 +63,45 @@
*/
#define save_common_regs \
- pushq_cfi_reg rdi; \
- pushq_cfi_reg rsi; \
- pushq_cfi_reg rcx; \
- pushq_cfi_reg r8; \
- pushq_cfi_reg r9; \
- pushq_cfi_reg r10; \
- pushq_cfi_reg r11
+ pushq %rdi; \
+ pushq %rsi; \
+ pushq %rcx; \
+ pushq %r8; \
+ pushq %r9; \
+ pushq %r10; \
+ pushq %r11
#define restore_common_regs \
- popq_cfi_reg r11; \
- popq_cfi_reg r10; \
- popq_cfi_reg r9; \
- popq_cfi_reg r8; \
- popq_cfi_reg rcx; \
- popq_cfi_reg rsi; \
- popq_cfi_reg rdi
+ popq %r11; \
+ popq %r10; \
+ popq %r9; \
+ popq %r8; \
+ popq %rcx; \
+ popq %rsi; \
+ popq %rdi
#endif
/* Fix up special calling conventions */
ENTRY(call_rwsem_down_read_failed)
- CFI_STARTPROC
save_common_regs
- __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(push,) %__ASM_REG(dx)
movq %rax,%rdi
call rwsem_down_read_failed
- __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(pop,) %__ASM_REG(dx)
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_down_read_failed)
ENTRY(call_rwsem_down_write_failed)
- CFI_STARTPROC
save_common_regs
movq %rax,%rdi
call rwsem_down_write_failed
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_down_write_failed)
ENTRY(call_rwsem_wake)
- CFI_STARTPROC
/* do nothing if still outstanding active readers */
__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
jnz 1f
@@ -116,17 +110,14 @@ ENTRY(call_rwsem_wake)
call rwsem_wake
restore_common_regs
1: ret
- CFI_ENDPROC
ENDPROC(call_rwsem_wake)
ENTRY(call_rwsem_downgrade_wake)
- CFI_STARTPROC
save_common_regs
- __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(push,) %__ASM_REG(dx)
movq %rax,%rdi
call rwsem_downgrade_wake
- __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(pop,) %__ASM_REG(dx)
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index e2f5e21c03b3..91d93b95bd86 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -647,7 +647,8 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space.
*
@@ -668,7 +669,8 @@ EXPORT_SYMBOL(_copy_to_user);
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space.
*
diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c
index dc8adad10a2f..dd76a05729b0 100644
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -30,7 +30,7 @@ static void fclex(void)
}
/* Needs to be externally visible */
-void finit_soft_fpu(struct i387_soft_struct *soft)
+void fpstate_init_soft(struct swregs_state *soft)
{
struct address *oaddr, *iaddr;
memset(soft, 0, sizeof(*soft));
@@ -52,7 +52,7 @@ void finit_soft_fpu(struct i387_soft_struct *soft)
void finit(void)
{
- finit_soft_fpu(&current->thread.fpu.state->soft);
+ fpstate_init_soft(&current->thread.fpu.state.soft);
}
/*
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 9b868124128d..f37e84ab49f3 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -31,7 +31,7 @@
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/user.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
#include "fpu_system.h"
#include "fpu_emu.h"
@@ -147,13 +147,9 @@ void math_emulate(struct math_emu_info *info)
unsigned long code_base = 0;
unsigned long code_limit = 0; /* Initialized to stop compiler warnings */
struct desc_struct code_descriptor;
+ struct fpu *fpu = &current->thread.fpu;
- if (!used_math()) {
- if (init_fpu(current)) {
- do_group_exit(SIGKILL);
- return;
- }
- }
+ fpu__activate_curr(fpu);
#ifdef RE_ENTRANT_CHECKING
if (emulating) {
@@ -673,7 +669,7 @@ void math_abort(struct math_emu_info *info, unsigned int signal)
#endif /* PARANOID */
}
-#define S387 ((struct i387_soft_struct *)s387)
+#define S387 ((struct swregs_state *)s387)
#define sstatus_word() \
((S387->swd & ~SW_Top & 0xffff) | ((S387->ftop << SW_Top_Shift) & SW_Top))
@@ -682,14 +678,14 @@ int fpregs_soft_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+ struct swregs_state *s387 = &target->thread.fpu.state.soft;
void *space = s387->st_space;
int ret;
int offset, other, i, tags, regnr, tag, newtop;
RE_ENTRANT_CHECK_OFF;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, s387, 0,
- offsetof(struct i387_soft_struct, st_space));
+ offsetof(struct swregs_state, st_space));
RE_ENTRANT_CHECK_ON;
if (ret)
@@ -734,7 +730,7 @@ int fpregs_soft_get(struct task_struct *target,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
- struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+ struct swregs_state *s387 = &target->thread.fpu.state.soft;
const void *space = s387->st_space;
int ret;
int offset = (S387->ftop & 7) * 10, other = 80 - offset;
@@ -752,7 +748,7 @@ int fpregs_soft_get(struct task_struct *target,
#endif /* PECULIAR_486 */
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, s387, 0,
- offsetof(struct i387_soft_struct, st_space));
+ offsetof(struct swregs_state, st_space));
/* Copy all registers in stack order. */
if (!ret)
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 2c614410a5f3..9ccecb61a4fa 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -31,7 +31,7 @@
#define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \
== (1 << 10))
-#define I387 (current->thread.fpu.state)
+#define I387 (&current->thread.fpu.state)
#define FPU_info (I387->soft.info)
#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs))
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 181c53bac3a7..9dc909841739 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -13,6 +13,7 @@
#include <linux/hugetlb.h> /* hstate_index_to_shift */
#include <linux/prefetch.h> /* prefetchw */
#include <linux/context_tracking.h> /* exception_enter(), ... */
+#include <linux/uaccess.h> /* faulthandler_disabled() */
#include <asm/traps.h> /* dotraplinkage, ... */
#include <asm/pgalloc.h> /* pgd_*(), ... */
@@ -1126,9 +1127,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
/*
* If we're in an interrupt, have no user context or are running
- * in an atomic region then we must not take the fault:
+ * in a region with pagefaults disabled then we must not take the fault
*/
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(faulthandler_disabled() || !mm)) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 4500142bc4aa..eecb207a2037 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -35,7 +35,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
unsigned long vaddr;
int idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
@@ -100,6 +100,7 @@ void __kunmap_atomic(void *kvaddr)
#endif
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 1d553186c434..8533b46e6bee 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -40,7 +40,7 @@
*/
uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
[_PAGE_CACHE_MODE_WB ] = 0 | 0 ,
- [_PAGE_CACHE_MODE_WC ] = _PAGE_PWT | 0 ,
+ [_PAGE_CACHE_MODE_WC ] = 0 | _PAGE_PCD,
[_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD,
[_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD,
[_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD,
@@ -50,11 +50,11 @@ EXPORT_SYMBOL(__cachemode2pte_tbl);
uint8_t __pte2cachemode_tbl[8] = {
[__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB,
- [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_WC,
+ [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC,
[__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
- [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC,
+ [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
};
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 9ca35fc60cfe..9c0ff045fdd4 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -59,6 +59,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
unsigned long vaddr;
int idx, type;
+ preempt_disable();
pagefault_disable();
type = kmap_atomic_idx_push();
@@ -77,13 +78,13 @@ void __iomem *
iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
{
/*
- * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
- * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
- * MTRR is UC or WC. UC_MINUS gets the real intention, of the
- * user, which is "WC if the MTRR is WC, UC if you can't do that."
+ * For non-PAT systems, translate non-WB request to UC- just in
+ * case the caller set the PWT bit to prot directly without using
+ * pgprot_writecombine(). UC- translates to uncached if the MTRR
+ * is UC or WC. UC- gets the real intention, of the user, which is
+ * "WC if the MTRR is WC, UC if you can't do that."
*/
- if (!pat_enabled && pgprot_val(prot) ==
- (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC)))
+ if (!pat_enabled() && pgprot2cachemode(prot) != _PAGE_CACHE_MODE_WB)
prot = __pgprot(__PAGE_KERNEL |
cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
@@ -117,5 +118,6 @@ iounmap_atomic(void __iomem *kvaddr)
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 70e7444c6835..cc5ccc415cc0 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -42,6 +42,9 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
case _PAGE_CACHE_MODE_WC:
err = _set_memory_wc(vaddr, nrpages);
break;
+ case _PAGE_CACHE_MODE_WT:
+ err = _set_memory_wt(vaddr, nrpages);
+ break;
case _PAGE_CACHE_MODE_WB:
err = _set_memory_wb(vaddr, nrpages);
break;
@@ -172,6 +175,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
prot = __pgprot(pgprot_val(prot) |
cachemode2protval(_PAGE_CACHE_MODE_WC));
break;
+ case _PAGE_CACHE_MODE_WT:
+ prot = __pgprot(pgprot_val(prot) |
+ cachemode2protval(_PAGE_CACHE_MODE_WT));
+ break;
case _PAGE_CACHE_MODE_WB:
break;
}
@@ -234,10 +241,11 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
{
/*
* Ideally, this should be:
- * pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
+ * pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
*
* Till we fix all X drivers to use ioremap_wc(), we will use
- * UC MINUS.
+ * UC MINUS. Drivers that are certain they need or can already
+ * be converted over to strong UC can use ioremap_uc().
*/
enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
@@ -247,6 +255,39 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
EXPORT_SYMBOL(ioremap_nocache);
/**
+ * ioremap_uc - map bus memory into CPU space as strongly uncachable
+ * @phys_addr: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap_uc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked with a strong
+ * preference as completely uncachable on the CPU when possible. For non-PAT
+ * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT
+ * systems this will set the PAT entry for the pages as strong UC. This call
+ * will honor existing caching rules from things like the PCI bus. Note that
+ * there are other caches and buffers on many busses. In particular driver
+ * authors should read up on PCI writes.
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size)
+{
+ enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC;
+
+ return __ioremap_caller(phys_addr, size, pcm,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL_GPL(ioremap_uc);
+
+/**
* ioremap_wc - map memory into CPU space write combined
* @phys_addr: bus address of the memory
* @size: size of the resource to map
@@ -258,14 +299,28 @@ EXPORT_SYMBOL(ioremap_nocache);
*/
void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
{
- if (pat_enabled)
- return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
__builtin_return_address(0));
- else
- return ioremap_nocache(phys_addr, size);
}
EXPORT_SYMBOL(ioremap_wc);
+/**
+ * ioremap_wt - map memory into CPU space write through
+ * @phys_addr: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * This version of ioremap ensures that the memory is marked write through.
+ * Write through stores data into memory while keeping the cache up-to-date.
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size)
+{
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
{
return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
@@ -331,7 +386,7 @@ void iounmap(volatile void __iomem *addr)
}
EXPORT_SYMBOL(iounmap);
-int arch_ioremap_pud_supported(void)
+int __init arch_ioremap_pud_supported(void)
{
#ifdef CONFIG_X86_64
return cpu_has_gbpages;
@@ -340,7 +395,7 @@ int arch_ioremap_pud_supported(void)
#endif
}
-int arch_ioremap_pmd_supported(void)
+int __init arch_ioremap_pmd_supported(void)
{
return cpu_has_pse;
}
@@ -353,18 +408,18 @@ void *xlate_dev_mem_ptr(phys_addr_t phys)
{
unsigned long start = phys & PAGE_MASK;
unsigned long offset = phys & ~PAGE_MASK;
- unsigned long vaddr;
+ void *vaddr;
/* If page is RAM, we can use __va. Otherwise ioremap and unmap. */
if (page_is_ram(start >> PAGE_SHIFT))
return __va(phys);
- vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE);
+ vaddr = ioremap_cache(start, PAGE_SIZE);
/* Only add the offset on success and return NULL if the ioremap() failed: */
if (vaddr)
vaddr += offset;
- return (void *)vaddr;
+ return vaddr;
}
void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
@@ -373,7 +428,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
return;
iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK));
- return;
}
static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index c439ec478216..7a657f58bbea 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -10,13 +10,15 @@
#include <linux/syscalls.h>
#include <linux/sched/sysctl.h>
-#include <asm/i387.h>
#include <asm/insn.h>
#include <asm/mman.h>
#include <asm/mmu_context.h>
#include <asm/mpx.h>
#include <asm/processor.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace/mpx.h>
static const char *mpx_mapping_name(struct vm_area_struct *vma)
{
@@ -32,6 +34,22 @@ static int is_mpx_vma(struct vm_area_struct *vma)
return (vma->vm_ops == &mpx_vma_ops);
}
+static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
+{
+ if (is_64bit_mm(mm))
+ return MPX_BD_SIZE_BYTES_64;
+ else
+ return MPX_BD_SIZE_BYTES_32;
+}
+
+static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
+{
+ if (is_64bit_mm(mm))
+ return MPX_BT_SIZE_BYTES_64;
+ else
+ return MPX_BT_SIZE_BYTES_32;
+}
+
/*
* This is really a simplified "vm_mmap". it only handles MPX
* bounds tables (the bounds directory is user-allocated).
@@ -47,8 +65,8 @@ static unsigned long mpx_mmap(unsigned long len)
vm_flags_t vm_flags;
struct vm_area_struct *vma;
- /* Only bounds table and bounds directory can be allocated here */
- if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES)
+ /* Only bounds table can be allocated here */
+ if (len != mpx_bt_size_bytes(mm))
return -EINVAL;
down_write(&mm->mmap_sem);
@@ -272,10 +290,9 @@ bad_opcode:
*
* The caller is expected to kfree() the returned siginfo_t.
*/
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf)
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
{
- struct bndreg *bndregs, *bndreg;
+ const struct bndreg *bndregs, *bndreg;
siginfo_t *info = NULL;
struct insn insn;
uint8_t bndregno;
@@ -295,8 +312,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
err = -EINVAL;
goto err_out;
}
- /* get the bndregs _area_ of the xsave structure */
- bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+ /* get bndregs field from current task's xsave area */
+ bndregs = get_xsave_field_ptr(XSTATE_BNDREGS);
if (!bndregs) {
err = -EINVAL;
goto err_out;
@@ -334,6 +351,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
err = -EINVAL;
goto err_out;
}
+ trace_mpx_bounds_register_exception(info->si_addr, bndreg);
return info;
err_out:
/* info might be NULL, but kfree() handles that */
@@ -341,25 +359,18 @@ err_out:
return ERR_PTR(err);
}
-static __user void *task_get_bounds_dir(struct task_struct *tsk)
+static __user void *mpx_get_bounds_dir(void)
{
- struct bndcsr *bndcsr;
+ const struct bndcsr *bndcsr;
if (!cpu_feature_enabled(X86_FEATURE_MPX))
return MPX_INVALID_BOUNDS_DIR;
/*
- * 32-bit binaries on 64-bit kernels are currently
- * unsupported.
- */
- if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
- return MPX_INVALID_BOUNDS_DIR;
- /*
* The bounds directory pointer is stored in a register
* only accessible if we first do an xsave.
*/
- fpu_save_init(&tsk->thread.fpu);
- bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
if (!bndcsr)
return MPX_INVALID_BOUNDS_DIR;
@@ -378,10 +389,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
}
-int mpx_enable_management(struct task_struct *tsk)
+int mpx_enable_management(void)
{
void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
- struct mm_struct *mm = tsk->mm;
+ struct mm_struct *mm = current->mm;
int ret = 0;
/*
@@ -390,11 +401,12 @@ int mpx_enable_management(struct task_struct *tsk)
* directory into XSAVE/XRSTOR Save Area and enable MPX through
* XRSTOR instruction.
*
- * fpu_xsave() is expected to be very expensive. Storing the bounds
- * directory here means that we do not have to do xsave in the unmap
- * path; we can just use mm->bd_addr instead.
+ * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
+ * expected to be relatively expensive. Storing the bounds
+ * directory here means that we do not have to do xsave in the
+ * unmap path; we can just use mm->bd_addr instead.
*/
- bd_base = task_get_bounds_dir(tsk);
+ bd_base = mpx_get_bounds_dir();
down_write(&mm->mmap_sem);
mm->bd_addr = bd_base;
if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
@@ -404,7 +416,7 @@ int mpx_enable_management(struct task_struct *tsk)
return ret;
}
-int mpx_disable_management(struct task_struct *tsk)
+int mpx_disable_management(void)
{
struct mm_struct *mm = current->mm;
@@ -417,29 +429,59 @@ int mpx_disable_management(struct task_struct *tsk)
return 0;
}
+static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
+ unsigned long *curval,
+ unsigned long __user *addr,
+ unsigned long old_val, unsigned long new_val)
+{
+ int ret;
+ /*
+ * user_atomic_cmpxchg_inatomic() actually uses sizeof()
+ * the pointer that we pass to it to figure out how much
+ * data to cmpxchg. We have to be careful here not to
+ * pass a pointer to a 64-bit data type when we only want
+ * a 32-bit copy.
+ */
+ if (is_64bit_mm(mm)) {
+ ret = user_atomic_cmpxchg_inatomic(curval,
+ addr, old_val, new_val);
+ } else {
+ u32 uninitialized_var(curval_32);
+ u32 old_val_32 = old_val;
+ u32 new_val_32 = new_val;
+ u32 __user *addr_32 = (u32 __user *)addr;
+
+ ret = user_atomic_cmpxchg_inatomic(&curval_32,
+ addr_32, old_val_32, new_val_32);
+ *curval = curval_32;
+ }
+ return ret;
+}
+
/*
- * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
- * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * With 32-bit mode, a bounds directory is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
* and the size of each bounds table is 4MB.
*/
-static int allocate_bt(long __user *bd_entry)
+static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
{
unsigned long expected_old_val = 0;
unsigned long actual_old_val = 0;
unsigned long bt_addr;
+ unsigned long bd_new_entry;
int ret = 0;
/*
* Carve the virtual space out of userspace for the new
* bounds table:
*/
- bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+ bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
if (IS_ERR((void *)bt_addr))
return PTR_ERR((void *)bt_addr);
/*
* Set the valid flag (kinda like _PAGE_PRESENT in a pte)
*/
- bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+ bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
/*
* Go poke the address of the new bounds table in to the
@@ -452,8 +494,8 @@ static int allocate_bt(long __user *bd_entry)
* mmap_sem at this point, unlike some of the other part
* of the MPX code that have to pagefault_disable().
*/
- ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
- expected_old_val, bt_addr);
+ ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, bd_entry,
+ expected_old_val, bd_new_entry);
if (ret)
goto out_unmap;
@@ -481,9 +523,10 @@ static int allocate_bt(long __user *bd_entry)
ret = -EINVAL;
goto out_unmap;
}
+ trace_mpx_new_bounds_table(bt_addr);
return 0;
out_unmap:
- vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+ vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
return ret;
}
@@ -498,12 +541,13 @@ out_unmap:
* bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
* and the size of each bound table is 4MB.
*/
-static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+static int do_mpx_bt_fault(void)
{
unsigned long bd_entry, bd_base;
- struct bndcsr *bndcsr;
+ const struct bndcsr *bndcsr;
+ struct mm_struct *mm = current->mm;
- bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
if (!bndcsr)
return -EINVAL;
/*
@@ -520,13 +564,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
* the directory is.
*/
if ((bd_entry < bd_base) ||
- (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+ (bd_entry >= bd_base + mpx_bd_size_bytes(mm)))
return -EINVAL;
- return allocate_bt((long __user *)bd_entry);
+ return allocate_bt(mm, (long __user *)bd_entry);
}
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+int mpx_handle_bd_fault(void)
{
/*
* Userspace never asked us to manage the bounds tables,
@@ -535,7 +579,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
if (!kernel_managing_mpx_tables(current->mm))
return -EINVAL;
- if (do_mpx_bt_fault(xsave_buf)) {
+ if (do_mpx_bt_fault()) {
force_sig(SIGSEGV, current);
/*
* The force_sig() is essentially "handling" this
@@ -572,29 +616,55 @@ static int mpx_resolve_fault(long __user *addr, int write)
return 0;
}
+static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
+ unsigned long bd_entry)
+{
+ unsigned long bt_addr = bd_entry;
+ int align_to_bytes;
+ /*
+ * Bit 0 in a bt_entry is always the valid bit.
+ */
+ bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
+ /*
+ * Tables are naturally aligned at 8-byte boundaries
+ * on 64-bit and 4-byte boundaries on 32-bit. The
+ * documentation makes it appear that the low bits
+ * are ignored by the hardware, so we do the same.
+ */
+ if (is_64bit_mm(mm))
+ align_to_bytes = 8;
+ else
+ align_to_bytes = 4;
+ bt_addr &= ~(align_to_bytes-1);
+ return bt_addr;
+}
+
/*
* Get the base of bounds tables pointed by specific bounds
* directory entry.
*/
static int get_bt_addr(struct mm_struct *mm,
- long __user *bd_entry, unsigned long *bt_addr)
+ long __user *bd_entry_ptr,
+ unsigned long *bt_addr_result)
{
int ret;
int valid_bit;
+ unsigned long bd_entry;
+ unsigned long bt_addr;
- if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+ if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr)))
return -EFAULT;
while (1) {
int need_write = 0;
pagefault_disable();
- ret = get_user(*bt_addr, bd_entry);
+ ret = get_user(bd_entry, bd_entry_ptr);
pagefault_enable();
if (!ret)
break;
if (ret == -EFAULT)
- ret = mpx_resolve_fault(bd_entry, need_write);
+ ret = mpx_resolve_fault(bd_entry_ptr, need_write);
/*
* If we could not resolve the fault, consider it
* userspace's fault and error out.
@@ -603,8 +673,8 @@ static int get_bt_addr(struct mm_struct *mm,
return ret;
}
- valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
- *bt_addr &= MPX_BT_ADDR_MASK;
+ valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
+ bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);
/*
* When the kernel is managing bounds tables, a bounds directory
@@ -613,7 +683,7 @@ static int get_bt_addr(struct mm_struct *mm,
* data in the address field, we know something is wrong. This
* -EINVAL return will cause a SIGSEGV.
*/
- if (!valid_bit && *bt_addr)
+ if (!valid_bit && bt_addr)
return -EINVAL;
/*
* Do we have an completely zeroed bt entry? That is OK. It
@@ -624,19 +694,100 @@ static int get_bt_addr(struct mm_struct *mm,
if (!valid_bit)
return -ENOENT;
+ *bt_addr_result = bt_addr;
return 0;
}
+static inline int bt_entry_size_bytes(struct mm_struct *mm)
+{
+ if (is_64bit_mm(mm))
+ return MPX_BT_ENTRY_BYTES_64;
+ else
+ return MPX_BT_ENTRY_BYTES_32;
+}
+
+/*
+ * Take a virtual address and turns it in to the offset in bytes
+ * inside of the bounds table where the bounds table entry
+ * controlling 'addr' can be found.
+ */
+static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
+ unsigned long addr)
+{
+ unsigned long bt_table_nr_entries;
+ unsigned long offset = addr;
+
+ if (is_64bit_mm(mm)) {
+ /* Bottom 3 bits are ignored on 64-bit */
+ offset >>= 3;
+ bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
+ } else {
+ /* Bottom 2 bits are ignored on 32-bit */
+ offset >>= 2;
+ bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
+ }
+ /*
+ * We know the size of the table in to which we are
+ * indexing, and we have eliminated all the low bits
+ * which are ignored for indexing.
+ *
+ * Mask out all the high bits which we do not need
+ * to index in to the table. Note that the tables
+ * are always powers of two so this gives us a proper
+ * mask.
+ */
+ offset &= (bt_table_nr_entries-1);
+ /*
+ * We now have an entry offset in terms of *entries* in
+ * the table. We need to scale it back up to bytes.
+ */
+ offset *= bt_entry_size_bytes(mm);
+ return offset;
+}
+
+/*
+ * How much virtual address space does a single bounds
+ * directory entry cover?
+ *
+ * Note, we need a long long because 4GB doesn't fit in
+ * to a long on 32-bit.
+ */
+static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
+{
+ unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+ if (is_64bit_mm(mm))
+ return virt_space / MPX_BD_NR_ENTRIES_64;
+ else
+ return virt_space / MPX_BD_NR_ENTRIES_32;
+}
+
/*
* Free the backing physical pages of bounds table 'bt_addr'.
* Assume start...end is within that bounds table.
*/
-static int zap_bt_entries(struct mm_struct *mm,
+static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
unsigned long bt_addr,
- unsigned long start, unsigned long end)
+ unsigned long start_mapping, unsigned long end_mapping)
{
struct vm_area_struct *vma;
unsigned long addr, len;
+ unsigned long start;
+ unsigned long end;
+
+ /*
+ * if we 'end' on a boundary, the offset will be 0 which
+ * is not what we want. Back it up a byte to get the
+ * last bt entry. Then once we have the entry itself,
+ * move 'end' back up by the table entry size.
+ */
+ start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping);
+ end = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1);
+ /*
+ * Move end back up by one entry. Among other things
+ * this ensures that it remains page-aligned and does
+ * not screw up zap_page_range()
+ */
+ end += bt_entry_size_bytes(mm);
/*
* Find the first overlapping vma. If vma->vm_start > start, there
@@ -648,7 +799,7 @@ static int zap_bt_entries(struct mm_struct *mm,
return -EINVAL;
/*
- * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+ * A NUMA policy on a VM_MPX VMA could cause this bounds table to
* be split. So we need to look across the entire 'start -> end'
* range of this bounds table, find all of the VM_MPX VMAs, and
* zap only those.
@@ -666,27 +817,65 @@ static int zap_bt_entries(struct mm_struct *mm,
len = min(vma->vm_end, end) - addr;
zap_page_range(vma, addr, len, NULL);
+ trace_mpx_unmap_zap(addr, addr+len);
vma = vma->vm_next;
addr = vma->vm_start;
}
-
return 0;
}
-static int unmap_single_bt(struct mm_struct *mm,
+static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
+ unsigned long addr)
+{
+ /*
+ * There are several ways to derive the bd offsets. We
+ * use the following approach here:
+ * 1. We know the size of the virtual address space
+ * 2. We know the number of entries in a bounds table
+ * 3. We know that each entry covers a fixed amount of
+ * virtual address space.
+ * So, we can just divide the virtual address by the
+ * virtual space used by one entry to determine which
+ * entry "controls" the given virtual address.
+ */
+ if (is_64bit_mm(mm)) {
+ int bd_entry_size = 8; /* 64-bit pointer */
+ /*
+ * Take the 64-bit addressing hole in to account.
+ */
+ addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
+ return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+ } else {
+ int bd_entry_size = 4; /* 32-bit pointer */
+ /*
+ * 32-bit has no hole so this case needs no mask
+ */
+ return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+ }
+ /*
+ * The two return calls above are exact copies. If we
+ * pull out a single copy and put it in here, gcc won't
+ * realize that we're doing a power-of-2 divide and use
+ * shifts. It uses a real divide. If we put them up
+ * there, it manages to figure it out (gcc 4.8.3).
+ */
+}
+
+static int unmap_entire_bt(struct mm_struct *mm,
long __user *bd_entry, unsigned long bt_addr)
{
unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
- unsigned long actual_old_val = 0;
+ unsigned long uninitialized_var(actual_old_val);
int ret;
while (1) {
int need_write = 1;
+ unsigned long cleared_bd_entry = 0;
pagefault_disable();
- ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
- expected_old_val, 0);
+ ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
+ bd_entry, expected_old_val, cleared_bd_entry);
pagefault_enable();
if (!ret)
break;
@@ -705,9 +894,8 @@ static int unmap_single_bt(struct mm_struct *mm,
if (actual_old_val != expected_old_val) {
/*
* Someone else raced with us to unmap the table.
- * There was no bounds table pointed to by the
- * directory, so declare success. Somebody freed
- * it.
+ * That is OK, since we were both trying to do
+ * the same thing. Declare success.
*/
if (!actual_old_val)
return 0;
@@ -720,176 +908,113 @@ static int unmap_single_bt(struct mm_struct *mm,
*/
return -EINVAL;
}
-
/*
* Note, we are likely being called under do_munmap() already. To
* avoid recursion, do_munmap() will check whether it comes
* from one bounds table through VM_MPX flag.
*/
- return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES);
+ return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
}
-/*
- * If the bounds table pointed by bounds directory 'bd_entry' is
- * not shared, unmap this whole bounds table. Otherwise, only free
- * those backing physical pages of bounds table entries covered
- * in this virtual address region start...end.
- */
-static int unmap_shared_bt(struct mm_struct *mm,
- long __user *bd_entry, unsigned long start,
- unsigned long end, bool prev_shared, bool next_shared)
+static int try_unmap_single_bt(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
{
- unsigned long bt_addr;
- int ret;
-
- ret = get_bt_addr(mm, bd_entry, &bt_addr);
+ struct vm_area_struct *next;
+ struct vm_area_struct *prev;
/*
- * We could see an "error" ret for not-present bounds
- * tables (not really an error), or actual errors, but
- * stop unmapping either way.
+ * "bta" == Bounds Table Area: the area controlled by the
+ * bounds table that we are unmapping.
*/
- if (ret)
- return ret;
-
- if (prev_shared && next_shared)
- ret = zap_bt_entries(mm, bt_addr,
- bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
- bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
- else if (prev_shared)
- ret = zap_bt_entries(mm, bt_addr,
- bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
- bt_addr+MPX_BT_SIZE_BYTES);
- else if (next_shared)
- ret = zap_bt_entries(mm, bt_addr, bt_addr,
- bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
- else
- ret = unmap_single_bt(mm, bd_entry, bt_addr);
-
- return ret;
-}
-
-/*
- * A virtual address region being munmap()ed might share bounds table
- * with adjacent VMAs. We only need to free the backing physical
- * memory of these shared bounds tables entries covered in this virtual
- * address region.
- */
-static int unmap_edge_bts(struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
+ unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1);
+ unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm);
+ unsigned long uninitialized_var(bt_addr);
+ void __user *bde_vaddr;
int ret;
- long __user *bde_start, *bde_end;
- struct vm_area_struct *prev, *next;
- bool prev_shared = false, next_shared = false;
-
- bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
- bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-
/*
- * Check whether bde_start and bde_end are shared with adjacent
- * VMAs.
- *
- * We already unliked the VMAs from the mm's rbtree so 'start'
+ * We already unlinked the VMAs from the mm's rbtree so 'start'
* is guaranteed to be in a hole. This gets us the first VMA
* before the hole in to 'prev' and the next VMA after the hole
* in to 'next'.
*/
next = find_vma_prev(mm, start, &prev);
- if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
- == bde_start)
- prev_shared = true;
- if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
- == bde_end)
- next_shared = true;
-
/*
- * This virtual address region being munmap()ed is only
- * covered by one bounds table.
- *
- * In this case, if this table is also shared with adjacent
- * VMAs, only part of the backing physical memory of the bounds
- * table need be freeed. Otherwise the whole bounds table need
- * be unmapped.
- */
- if (bde_start == bde_end) {
- return unmap_shared_bt(mm, bde_start, start, end,
- prev_shared, next_shared);
+ * Do not count other MPX bounds table VMAs as neighbors.
+ * Although theoretically possible, we do not allow bounds
+ * tables for bounds tables so our heads do not explode.
+ * If we count them as neighbors here, we may end up with
+ * lots of tables even though we have no actual table
+ * entries in use.
+ */
+ while (next && is_mpx_vma(next))
+ next = next->vm_next;
+ while (prev && is_mpx_vma(prev))
+ prev = prev->vm_prev;
+ /*
+ * We know 'start' and 'end' lie within an area controlled
+ * by a single bounds table. See if there are any other
+ * VMAs controlled by that bounds table. If there are not
+ * then we can "expand" the are we are unmapping to possibly
+ * cover the entire table.
+ */
+ next = find_vma_prev(mm, start, &prev);
+ if ((!prev || prev->vm_end <= bta_start_vaddr) &&
+ (!next || next->vm_start >= bta_end_vaddr)) {
+ /*
+ * No neighbor VMAs controlled by same bounds
+ * table. Try to unmap the whole thing
+ */
+ start = bta_start_vaddr;
+ end = bta_end_vaddr;
}
+ bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
+ ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
/*
- * If more than one bounds tables are covered in this virtual
- * address region being munmap()ed, we need to separately check
- * whether bde_start and bde_end are shared with adjacent VMAs.
+ * No bounds table there, so nothing to unmap.
*/
- ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
- if (ret)
- return ret;
- ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+ if (ret == -ENOENT) {
+ ret = 0;
+ return 0;
+ }
if (ret)
return ret;
-
- return 0;
+ /*
+ * We are unmapping an entire table. Either because the
+ * unmap that started this whole process was large enough
+ * to cover an entire table, or that the unmap was small
+ * but was the area covered by a bounds table.
+ */
+ if ((start == bta_start_vaddr) &&
+ (end == bta_end_vaddr))
+ return unmap_entire_bt(mm, bde_vaddr, bt_addr);
+ return zap_bt_entries_mapping(mm, bt_addr, start, end);
}
static int mpx_unmap_tables(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
- int ret;
- long __user *bd_entry, *bde_start, *bde_end;
- unsigned long bt_addr;
-
- /*
- * "Edge" bounds tables are those which are being used by the region
- * (start -> end), but that may be shared with adjacent areas. If they
- * turn out to be completely unshared, they will be freed. If they are
- * shared, we will free the backing store (like an MADV_DONTNEED) for
- * areas used by this region.
- */
- ret = unmap_edge_bts(mm, start, end);
- switch (ret) {
- /* non-present tables are OK */
- case 0:
- case -ENOENT:
- /* Success, or no tables to unmap */
- break;
- case -EINVAL:
- case -EFAULT:
- default:
- return ret;
- }
-
- /*
- * Only unmap the bounds table that are
- * 1. fully covered
- * 2. not at the edges of the mapping, even if full aligned
- */
- bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
- bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
- for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
- ret = get_bt_addr(mm, bd_entry, &bt_addr);
- switch (ret) {
- case 0:
- break;
- case -ENOENT:
- /* No table here, try the next one */
- continue;
- case -EINVAL:
- case -EFAULT:
- default:
- /*
- * Note: we are being strict here.
- * Any time we run in to an issue
- * unmapping tables, we stop and
- * SIGSEGV.
- */
- return ret;
- }
-
- ret = unmap_single_bt(mm, bd_entry, bt_addr);
+ unsigned long one_unmap_start;
+ trace_mpx_unmap_search(start, end);
+
+ one_unmap_start = start;
+ while (one_unmap_start < end) {
+ int ret;
+ unsigned long next_unmap_start = ALIGN(one_unmap_start+1,
+ bd_entry_virt_space(mm));
+ unsigned long one_unmap_end = end;
+ /*
+ * if the end is beyond the current bounds table,
+ * move it back so we only deal with a single one
+ * at a time
+ */
+ if (one_unmap_end > next_unmap_start)
+ one_unmap_end = next_unmap_start;
+ ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end);
if (ret)
return ret;
- }
+ one_unmap_start = next_unmap_start;
+ }
return 0;
}
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 6629f397b467..8ff686aa7e8c 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -9,6 +9,7 @@
#include <linux/random.h>
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/vmalloc.h>
#include <asm/cacheflush.h>
#include <asm/pgtable.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 89af288ec674..727158cb3b3c 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -14,6 +14,7 @@
#include <linux/percpu.h>
#include <linux/gfp.h>
#include <linux/pci.h>
+#include <linux/vmalloc.h>
#include <asm/e820.h>
#include <asm/processor.h>
@@ -129,16 +130,15 @@ within(unsigned long addr, unsigned long start, unsigned long end)
*/
void clflush_cache_range(void *vaddr, unsigned int size)
{
- void *vend = vaddr + size - 1;
+ unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+ void *vend = vaddr + size;
+ void *p;
mb();
- for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
- clflushopt(vaddr);
- /*
- * Flush any possible final partial cacheline:
- */
- clflushopt(vend);
+ for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+ p < vend; p += boot_cpu_data.x86_clflush_size)
+ clflushopt(p);
mb();
}
@@ -418,13 +418,11 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr)
phys_addr_t phys_addr;
unsigned long offset;
enum pg_level level;
- unsigned long psize;
unsigned long pmask;
pte_t *pte;
pte = lookup_address(virt_addr, &level);
BUG_ON(!pte);
- psize = page_level_size(level);
pmask = page_level_mask(level);
offset = virt_addr & ~pmask;
phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
@@ -1468,6 +1466,9 @@ int _set_memory_uc(unsigned long addr, int numpages)
{
/*
* for now UC MINUS. see comments in ioremap_nocache()
+ * If you really need strong UC use ioremap_uc(), but note
+ * that you cannot override IO areas with set_memory_*() as
+ * these helpers cannot work with IO memory.
*/
return change_page_attr_set(&addr, numpages,
cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
@@ -1502,12 +1503,10 @@ EXPORT_SYMBOL(set_memory_uc);
static int _set_memory_array(unsigned long *addr, int addrinarray,
enum page_cache_mode new_type)
{
+ enum page_cache_mode set_type;
int i, j;
int ret;
- /*
- * for now UC MINUS. see comments in ioremap_nocache()
- */
for (i = 0; i < addrinarray; i++) {
ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
new_type, NULL);
@@ -1515,9 +1514,12 @@ static int _set_memory_array(unsigned long *addr, int addrinarray,
goto out_free;
}
+ /* If WC, set to UC- first and then WC */
+ set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+ _PAGE_CACHE_MODE_UC_MINUS : new_type;
+
ret = change_page_attr_set(addr, addrinarray,
- cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
- 1);
+ cachemode2pgprot(set_type), 1);
if (!ret && new_type == _PAGE_CACHE_MODE_WC)
ret = change_page_attr_set_clr(addr, addrinarray,
@@ -1549,6 +1551,12 @@ int set_memory_array_wc(unsigned long *addr, int addrinarray)
}
EXPORT_SYMBOL(set_memory_array_wc);
+int set_memory_array_wt(unsigned long *addr, int addrinarray)
+{
+ return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WT);
+}
+EXPORT_SYMBOL_GPL(set_memory_array_wt);
+
int _set_memory_wc(unsigned long addr, int numpages)
{
int ret;
@@ -1571,27 +1579,42 @@ int set_memory_wc(unsigned long addr, int numpages)
{
int ret;
- if (!pat_enabled)
- return set_memory_uc(addr, numpages);
-
ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
_PAGE_CACHE_MODE_WC, NULL);
if (ret)
- goto out_err;
+ return ret;
ret = _set_memory_wc(addr, numpages);
if (ret)
- goto out_free;
-
- return 0;
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
-out_free:
- free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
-out_err:
return ret;
}
EXPORT_SYMBOL(set_memory_wc);
+int _set_memory_wt(unsigned long addr, int numpages)
+{
+ return change_page_attr_set(&addr, numpages,
+ cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0);
+}
+
+int set_memory_wt(unsigned long addr, int numpages)
+{
+ int ret;
+
+ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+ _PAGE_CACHE_MODE_WT, NULL);
+ if (ret)
+ return ret;
+
+ ret = _set_memory_wt(addr, numpages);
+ if (ret)
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(set_memory_wt);
+
int _set_memory_wb(unsigned long addr, int numpages)
{
/* WB cache mode is hard wired to all cache attribute bits being 0 */
@@ -1682,6 +1705,7 @@ static int _set_pages_array(struct page **pages, int addrinarray,
{
unsigned long start;
unsigned long end;
+ enum page_cache_mode set_type;
int i;
int free_idx;
int ret;
@@ -1695,8 +1719,12 @@ static int _set_pages_array(struct page **pages, int addrinarray,
goto err_out;
}
+ /* If WC, set to UC- first and then WC */
+ set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+ _PAGE_CACHE_MODE_UC_MINUS : new_type;
+
ret = cpa_set_pages_array(pages, addrinarray,
- cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS));
+ cachemode2pgprot(set_type));
if (!ret && new_type == _PAGE_CACHE_MODE_WC)
ret = change_page_attr_set_clr(NULL, addrinarray,
cachemode2pgprot(
@@ -1730,6 +1758,12 @@ int set_pages_array_wc(struct page **pages, int addrinarray)
}
EXPORT_SYMBOL(set_pages_array_wc);
+int set_pages_array_wt(struct page **pages, int addrinarray)
+{
+ return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WT);
+}
+EXPORT_SYMBOL_GPL(set_pages_array_wt);
+
int set_pages_wb(struct page *page, int numpages)
{
unsigned long addr = (unsigned long)page_address(page);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 35af6771a95a..188e3e07eeeb 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -33,13 +33,17 @@
#include "pat_internal.h"
#include "mm_internal.h"
-#ifdef CONFIG_X86_PAT
-int __read_mostly pat_enabled = 1;
+#undef pr_fmt
+#define pr_fmt(fmt) "" fmt
+
+static bool boot_cpu_done;
+
+static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
static inline void pat_disable(const char *reason)
{
- pat_enabled = 0;
- printk(KERN_INFO "%s\n", reason);
+ __pat_enabled = 0;
+ pr_info("x86/PAT: %s\n", reason);
}
static int __init nopat(char *str)
@@ -48,13 +52,12 @@ static int __init nopat(char *str)
return 0;
}
early_param("nopat", nopat);
-#else
-static inline void pat_disable(const char *reason)
+
+bool pat_enabled(void)
{
- (void)reason;
+ return !!__pat_enabled;
}
-#endif
-
+EXPORT_SYMBOL_GPL(pat_enabled);
int pat_debug_enable;
@@ -65,22 +68,24 @@ static int __init pat_debug_setup(char *str)
}
__setup("debugpat", pat_debug_setup);
-static u64 __read_mostly boot_pat_state;
-
#ifdef CONFIG_X86_PAT
/*
- * X86 PAT uses page flags WC and Uncached together to keep track of
- * memory type of pages that have backing page struct. X86 PAT supports 3
- * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and
- * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not
- * been changed from its default (value of -1 used to denote this).
- * Note we do not support _PAGE_CACHE_MODE_UC here.
+ * X86 PAT uses page flags arch_1 and uncached together to keep track of
+ * memory type of pages that have backing page struct.
+ *
+ * X86 PAT supports 4 different memory types:
+ * - _PAGE_CACHE_MODE_WB
+ * - _PAGE_CACHE_MODE_WC
+ * - _PAGE_CACHE_MODE_UC_MINUS
+ * - _PAGE_CACHE_MODE_WT
+ *
+ * _PAGE_CACHE_MODE_WB is the default type.
*/
-#define _PGMT_DEFAULT 0
+#define _PGMT_WB 0
#define _PGMT_WC (1UL << PG_arch_1)
#define _PGMT_UC_MINUS (1UL << PG_uncached)
-#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_WT (1UL << PG_uncached | 1UL << PG_arch_1)
#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1)
#define _PGMT_CLEAR_MASK (~_PGMT_MASK)
@@ -88,14 +93,14 @@ static inline enum page_cache_mode get_page_memtype(struct page *pg)
{
unsigned long pg_flags = pg->flags & _PGMT_MASK;
- if (pg_flags == _PGMT_DEFAULT)
- return -1;
+ if (pg_flags == _PGMT_WB)
+ return _PAGE_CACHE_MODE_WB;
else if (pg_flags == _PGMT_WC)
return _PAGE_CACHE_MODE_WC;
else if (pg_flags == _PGMT_UC_MINUS)
return _PAGE_CACHE_MODE_UC_MINUS;
else
- return _PAGE_CACHE_MODE_WB;
+ return _PAGE_CACHE_MODE_WT;
}
static inline void set_page_memtype(struct page *pg,
@@ -112,11 +117,12 @@ static inline void set_page_memtype(struct page *pg,
case _PAGE_CACHE_MODE_UC_MINUS:
memtype_flags = _PGMT_UC_MINUS;
break;
- case _PAGE_CACHE_MODE_WB:
- memtype_flags = _PGMT_WB;
+ case _PAGE_CACHE_MODE_WT:
+ memtype_flags = _PGMT_WT;
break;
+ case _PAGE_CACHE_MODE_WB:
default:
- memtype_flags = _PGMT_DEFAULT;
+ memtype_flags = _PGMT_WB;
break;
}
@@ -174,78 +180,154 @@ 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(void)
+void pat_init_cache_modes(u64 pat)
{
- int i;
enum page_cache_mode cache;
char pat_msg[33];
- u64 pat;
+ int i;
- rdmsrl(MSR_IA32_CR_PAT, pat);
pat_msg[32] = 0;
for (i = 7; i >= 0; i--) {
cache = pat_get_cache_mode((pat >> (i * 8)) & 7,
pat_msg + 4 * i);
update_cache_mode_entry(i, cache);
}
- pr_info("PAT configuration [0-7]: %s\n", pat_msg);
+ pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
}
#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8))
-void pat_init(void)
+static void pat_bsp_init(u64 pat)
{
- u64 pat;
- bool boot_cpu = !boot_pat_state;
+ u64 tmp_pat;
- if (!pat_enabled)
+ if (!cpu_has_pat) {
+ pat_disable("PAT not supported by CPU.");
return;
+ }
- if (!cpu_has_pat) {
- if (!boot_pat_state) {
- pat_disable("PAT not supported by CPU.");
- return;
- } else {
- /*
- * If this happens we are on a secondary CPU, but
- * switched to PAT on the boot CPU. We have no way to
- * undo PAT.
- */
- printk(KERN_ERR "PAT enabled, "
- "but not supported by secondary CPU\n");
- BUG();
- }
+ if (!pat_enabled())
+ goto done;
+
+ rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
+ if (!tmp_pat) {
+ pat_disable("PAT MSR is 0, disabled.");
+ return;
}
- /* Set PWT to Write-Combining. All other bits stay the same */
- /*
- * PTE encoding used in Linux:
- * PAT
- * |PCD
- * ||PWT
- * |||
- * 000 WB _PAGE_CACHE_WB
- * 001 WC _PAGE_CACHE_WC
- * 010 UC- _PAGE_CACHE_UC_MINUS
- * 011 UC _PAGE_CACHE_UC
- * PAT bit unused
- */
- pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
- PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
-
- /* Boot CPU check */
- if (!boot_pat_state) {
- rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
- if (!boot_pat_state) {
- pat_disable("PAT read returns always zero, disabled.");
- return;
- }
+ wrmsrl(MSR_IA32_CR_PAT, pat);
+
+done:
+ pat_init_cache_modes(pat);
+}
+
+static void pat_ap_init(u64 pat)
+{
+ if (!pat_enabled())
+ return;
+
+ if (!cpu_has_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.
+ */
+ panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n");
}
wrmsrl(MSR_IA32_CR_PAT, pat);
+}
+
+void pat_init(void)
+{
+ u64 pat;
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (!pat_enabled()) {
+ /*
+ * 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.
+ *
+ * PTE encoding:
+ *
+ * PCD
+ * |PWT PAT
+ * || slot
+ * 00 0 WB : _PAGE_CACHE_MODE_WB
+ * 01 1 WT : _PAGE_CACHE_MODE_WT
+ * 10 2 UC-: _PAGE_CACHE_MODE_UC_MINUS
+ * 11 3 UC : _PAGE_CACHE_MODE_UC
+ *
+ * NOTE: When WC or WP is used, it is redirected to UC- per
+ * the default setup in __cachemode2pte_tbl[].
+ */
+ 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);
- if (boot_cpu)
- pat_init_cache_modes();
+ } else 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
+ * upper four entries unusable. To be on the safe side, we don't
+ * use those.
+ *
+ * PTE encoding:
+ * PAT
+ * |PCD
+ * ||PWT PAT
+ * ||| slot
+ * 000 0 WB : _PAGE_CACHE_MODE_WB
+ * 001 1 WC : _PAGE_CACHE_MODE_WC
+ * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS
+ * 011 3 UC : _PAGE_CACHE_MODE_UC
+ * PAT bit unused
+ *
+ * NOTE: When WT or WP is used, it is redirected to UC- per
+ * the default setup in __cachemode2pte_tbl[].
+ */
+ pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+ PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
+ } else {
+ /*
+ * Full PAT support. We put WT in slot 7 to improve
+ * robustness in the presence of errata that might cause
+ * the high PAT bit to be ignored. This way, a buggy slot 7
+ * access will hit slot 3, and slot 3 is UC, so at worst
+ * we lose performance without causing a correctness issue.
+ * Pentium 4 erratum N46 is an example for such an erratum,
+ * although we try not to use PAT at all on affected CPUs.
+ *
+ * PTE encoding:
+ * PAT
+ * |PCD
+ * ||PWT PAT
+ * ||| slot
+ * 000 0 WB : _PAGE_CACHE_MODE_WB
+ * 001 1 WC : _PAGE_CACHE_MODE_WC
+ * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS
+ * 011 3 UC : _PAGE_CACHE_MODE_UC
+ * 100 4 WB : Reserved
+ * 101 5 WC : Reserved
+ * 110 6 UC-: Reserved
+ * 111 7 WT : _PAGE_CACHE_MODE_WT
+ *
+ * The reserved slots are unused, but mapped to their
+ * corresponding types in the presence of PAT errata.
+ */
+ pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+ PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT);
+ }
+
+ if (!boot_cpu_done) {
+ pat_bsp_init(pat);
+ boot_cpu_done = true;
+ } else {
+ pat_ap_init(pat);
+ }
}
#undef PAT
@@ -267,9 +349,9 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end,
* request is for WB.
*/
if (req_type == _PAGE_CACHE_MODE_WB) {
- u8 mtrr_type;
+ u8 mtrr_type, uniform;
- mtrr_type = mtrr_type_lookup(start, end);
+ mtrr_type = mtrr_type_lookup(start, end, &uniform);
if (mtrr_type != MTRR_TYPE_WRBACK)
return _PAGE_CACHE_MODE_UC_MINUS;
@@ -324,9 +406,14 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
/*
* For RAM pages, we use page flags to mark the pages with appropriate type.
- * Here we do two pass:
- * - Find the memtype of all the pages in the range, look for any conflicts
- * - In case of no conflicts, set the new memtype for pages in the range
+ * The page flags are limited to four types, WB (default), WC, WT and UC-.
+ * WP request fails with -EINVAL, and UC gets redirected to UC-. Setting
+ * a new memory type is only allowed for a page mapped with the default WB
+ * type.
+ *
+ * Here we do two passes:
+ * - Find the memtype of all the pages in the range, look for any conflicts.
+ * - In case of no conflicts, set the new memtype for pages in the range.
*/
static int reserve_ram_pages_type(u64 start, u64 end,
enum page_cache_mode req_type,
@@ -335,6 +422,12 @@ static int reserve_ram_pages_type(u64 start, u64 end,
struct page *page;
u64 pfn;
+ if (req_type == _PAGE_CACHE_MODE_WP) {
+ if (new_type)
+ *new_type = _PAGE_CACHE_MODE_UC_MINUS;
+ return -EINVAL;
+ }
+
if (req_type == _PAGE_CACHE_MODE_UC) {
/* We do not support strong UC */
WARN_ON_ONCE(1);
@@ -346,8 +439,8 @@ static int reserve_ram_pages_type(u64 start, u64 end,
page = pfn_to_page(pfn);
type = get_page_memtype(page);
- if (type != -1) {
- pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
+ if (type != _PAGE_CACHE_MODE_WB) {
+ pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
start, end - 1, type, req_type);
if (new_type)
*new_type = type;
@@ -373,7 +466,7 @@ static int free_ram_pages_type(u64 start, u64 end)
for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
page = pfn_to_page(pfn);
- set_page_memtype(page, -1);
+ set_page_memtype(page, _PAGE_CACHE_MODE_WB);
}
return 0;
}
@@ -384,6 +477,7 @@ static int free_ram_pages_type(u64 start, u64 end)
* - _PAGE_CACHE_MODE_WC
* - _PAGE_CACHE_MODE_UC_MINUS
* - _PAGE_CACHE_MODE_UC
+ * - _PAGE_CACHE_MODE_WT
*
* If new_type is NULL, function will return an error if it cannot reserve the
* region with req_type. If new_type is non-NULL, function will return
@@ -400,14 +494,10 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
BUG_ON(start >= end); /* end is exclusive */
- if (!pat_enabled) {
+ if (!pat_enabled()) {
/* This is identical to page table setting without PAT */
- if (new_type) {
- if (req_type == _PAGE_CACHE_MODE_WC)
- *new_type = _PAGE_CACHE_MODE_UC_MINUS;
- else
- *new_type = req_type;
- }
+ if (new_type)
+ *new_type = req_type;
return 0;
}
@@ -451,9 +541,9 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
err = rbt_memtype_check_insert(new, new_type);
if (err) {
- printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
- start, end - 1,
- cattr_name(new->type), cattr_name(req_type));
+ pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
+ start, end - 1,
+ cattr_name(new->type), cattr_name(req_type));
kfree(new);
spin_unlock(&memtype_lock);
@@ -475,7 +565,7 @@ int free_memtype(u64 start, u64 end)
int is_range_ram;
struct memtype *entry;
- if (!pat_enabled)
+ if (!pat_enabled())
return 0;
/* Low ISA region is always mapped WB. No need to track */
@@ -497,8 +587,8 @@ int free_memtype(u64 start, u64 end)
spin_unlock(&memtype_lock);
if (!entry) {
- printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
- current->comm, current->pid, start, end - 1);
+ pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
+ current->comm, current->pid, start, end - 1);
return -EINVAL;
}
@@ -517,7 +607,7 @@ int free_memtype(u64 start, u64 end)
* Only to be called when PAT is enabled
*
* Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS
- * or _PAGE_CACHE_MODE_UC
+ * or _PAGE_CACHE_MODE_WT.
*/
static enum page_cache_mode lookup_memtype(u64 paddr)
{
@@ -529,16 +619,9 @@ static enum page_cache_mode lookup_memtype(u64 paddr)
if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
struct page *page;
- page = pfn_to_page(paddr >> PAGE_SHIFT);
- rettype = get_page_memtype(page);
- /*
- * -1 from get_page_memtype() implies RAM page is in its
- * default state and not reserved, and hence of type WB
- */
- if (rettype == -1)
- rettype = _PAGE_CACHE_MODE_WB;
- return rettype;
+ page = pfn_to_page(paddr >> PAGE_SHIFT);
+ return get_page_memtype(page);
}
spin_lock(&memtype_lock);
@@ -623,13 +706,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
u64 to = from + size;
u64 cursor = from;
- if (!pat_enabled)
+ if (!pat_enabled())
return 1;
while (cursor < to) {
if (!devmem_is_allowed(pfn)) {
- printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
- current->comm, from, to - 1);
+ pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
+ current->comm, from, to - 1);
return 0;
}
cursor += PAGE_SIZE;
@@ -659,7 +742,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
* caching for the high addresses through the KEN pin, but
* we maintain the tradition of paranoia in this code.
*/
- if (!pat_enabled &&
+ if (!pat_enabled() &&
!(boot_cpu_has(X86_FEATURE_MTRR) ||
boot_cpu_has(X86_FEATURE_K6_MTRR) ||
boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
@@ -698,8 +781,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size,
size;
if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) {
- printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
- "for [mem %#010Lx-%#010Lx]\n",
+ pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n",
current->comm, current->pid,
cattr_name(pcm),
base, (unsigned long long)(base + size-1));
@@ -729,12 +811,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
* the type requested matches the type of first page in the range.
*/
if (is_ram) {
- if (!pat_enabled)
+ if (!pat_enabled())
return 0;
pcm = lookup_memtype(paddr);
if (want_pcm != pcm) {
- printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
+ pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
cattr_name(want_pcm),
(unsigned long long)paddr,
@@ -755,13 +837,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
if (strict_prot ||
!is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
free_memtype(paddr, paddr + size);
- printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
- " for [mem %#010Lx-%#010Lx], got %s\n",
- current->comm, current->pid,
- cattr_name(want_pcm),
- (unsigned long long)paddr,
- (unsigned long long)(paddr + size - 1),
- cattr_name(pcm));
+ pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n",
+ current->comm, current->pid,
+ cattr_name(want_pcm),
+ (unsigned long long)paddr,
+ (unsigned long long)(paddr + size - 1),
+ cattr_name(pcm));
return -EINVAL;
}
/*
@@ -844,7 +925,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
return ret;
}
- if (!pat_enabled)
+ if (!pat_enabled())
return 0;
/*
@@ -872,7 +953,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
{
enum page_cache_mode pcm;
- if (!pat_enabled)
+ if (!pat_enabled())
return 0;
/* Set prot based on lookup */
@@ -913,14 +994,18 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
pgprot_t pgprot_writecombine(pgprot_t prot)
{
- if (pat_enabled)
- return __pgprot(pgprot_val(prot) |
+ return __pgprot(pgprot_val(prot) |
cachemode2protval(_PAGE_CACHE_MODE_WC));
- else
- return pgprot_noncached(prot);
}
EXPORT_SYMBOL_GPL(pgprot_writecombine);
+pgprot_t pgprot_writethrough(pgprot_t prot)
+{
+ return __pgprot(pgprot_val(prot) |
+ cachemode2protval(_PAGE_CACHE_MODE_WT));
+}
+EXPORT_SYMBOL_GPL(pgprot_writethrough);
+
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
static struct memtype *memtype_get_idx(loff_t pos)
@@ -996,7 +1081,7 @@ static const struct file_operations memtype_fops = {
static int __init pat_memtype_list_init(void)
{
- if (pat_enabled) {
+ if (pat_enabled()) {
debugfs_create_file("pat_memtype_list", S_IRUSR,
arch_debugfs_dir, NULL, &memtype_fops);
}
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index f6411620305d..a739bfc40690 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -4,7 +4,7 @@
extern int pat_debug_enable;
#define dprintk(fmt, arg...) \
- do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)
+ do { if (pat_debug_enable) pr_info("x86/PAT: " fmt, ##arg); } while (0)
struct memtype {
u64 start;
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 6582adcc8bd9..63931080366a 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -160,9 +160,9 @@ success:
return 0;
failure:
- printk(KERN_INFO "%s:%d conflicting memory types "
- "%Lx-%Lx %s<->%s\n", current->comm, current->pid, start,
- end, cattr_name(found_type), cattr_name(match->type));
+ pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
+ current->comm, current->pid, start, end,
+ cattr_name(found_type), cattr_name(match->type));
return -EBUSY;
}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 0b97d2c75df3..fb0a9dd1d6e4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -563,16 +563,31 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
}
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+/**
+ * pud_set_huge - setup kernel PUD mapping
+ *
+ * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
+ * function sets up a huge page only if any of the following conditions are met:
+ *
+ * - MTRRs are disabled, or
+ *
+ * - MTRRs are enabled and the range is completely covered by a single MTRR, or
+ *
+ * - MTRRs are enabled and the corresponding MTRR memory type is WB, which
+ * has no effect on the requested PAT memory type.
+ *
+ * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger
+ * page mapping attempt fails.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
- u8 mtrr;
+ u8 mtrr, uniform;
- /*
- * Do not use a huge page when the range is covered by non-WB type
- * of MTRRs.
- */
- mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE);
- if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+ mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform);
+ if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+ (mtrr != MTRR_TYPE_WRBACK))
return 0;
prot = pgprot_4k_2_large(prot);
@@ -584,17 +599,24 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
return 1;
}
+/**
+ * pmd_set_huge - setup kernel PMD mapping
+ *
+ * See text over pud_set_huge() above.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
{
- u8 mtrr;
+ u8 mtrr, uniform;
- /*
- * Do not use a huge page when the range is covered by non-WB type
- * of MTRRs.
- */
- mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE);
- if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+ mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform);
+ if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+ (mtrr != MTRR_TYPE_WRBACK)) {
+ pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n",
+ __func__, addr, addr + PMD_SIZE);
return 0;
+ }
prot = pgprot_4k_2_large(prot);
@@ -605,6 +627,11 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
return 1;
}
+/**
+ * pud_clear_huge - clear kernel PUD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PUD map is found).
+ */
int pud_clear_huge(pud_t *pud)
{
if (pud_large(*pud)) {
@@ -615,6 +642,11 @@ int pud_clear_huge(pud_t *pud)
return 0;
}
+/**
+ * pmd_clear_huge - clear kernel PMD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PMD map is found).
+ */
int pmd_clear_huge(pmd_t *pmd)
{
if (pmd_large(*pmd)) {
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 6440221ced0d..4093216b3791 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -8,7 +8,6 @@
* of the License.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
/*
* Calling convention :
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 99f76103c6b7..579a8fd74be0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -12,6 +12,7 @@
#include <linux/filter.h>
#include <linux/if_vlan.h>
#include <asm/cacheflush.h>
+#include <linux/bpf.h>
int bpf_jit_enable __read_mostly;
@@ -37,7 +38,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
return ptr + len;
}
-#define EMIT(bytes, len) do { prog = emit_code(prog, bytes, len); } while (0)
+#define EMIT(bytes, len) \
+ do { prog = emit_code(prog, bytes, len); cnt += len; } while (0)
#define EMIT1(b1) EMIT(b1, 1)
#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
@@ -186,31 +188,31 @@ struct jit_context {
#define BPF_MAX_INSN_SIZE 128
#define BPF_INSN_SAFETY 64
-static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
- int oldproglen, struct jit_context *ctx)
+#define STACKSIZE \
+ (MAX_BPF_STACK + \
+ 32 /* space for rbx, r13, r14, r15 */ + \
+ 8 /* space for skb_copy_bits() buffer */)
+
+#define PROLOGUE_SIZE 51
+
+/* emit x64 prologue code for BPF program and check it's size.
+ * bpf_tail_call helper will skip it while jumping into another program
+ */
+static void emit_prologue(u8 **pprog)
{
- struct bpf_insn *insn = bpf_prog->insnsi;
- int insn_cnt = bpf_prog->len;
- bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
- bool seen_exit = false;
- u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
- int i;
- int proglen = 0;
- u8 *prog = temp;
- int stacksize = MAX_BPF_STACK +
- 32 /* space for rbx, r13, r14, r15 */ +
- 8 /* space for skb_copy_bits() buffer */;
+ u8 *prog = *pprog;
+ int cnt = 0;
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
- /* sub rsp, stacksize */
- EMIT3_off32(0x48, 0x81, 0xEC, stacksize);
+ /* sub rsp, STACKSIZE */
+ EMIT3_off32(0x48, 0x81, 0xEC, STACKSIZE);
/* all classic BPF filters use R6(rbx) save it */
/* mov qword ptr [rbp-X],rbx */
- EMIT3_off32(0x48, 0x89, 0x9D, -stacksize);
+ EMIT3_off32(0x48, 0x89, 0x9D, -STACKSIZE);
/* bpf_convert_filter() maps classic BPF register X to R7 and uses R8
* as temporary, so all tcpdump filters need to spill/fill R7(r13) and
@@ -221,16 +223,112 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
*/
/* mov qword ptr [rbp-X],r13 */
- EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8);
+ EMIT3_off32(0x4C, 0x89, 0xAD, -STACKSIZE + 8);
/* mov qword ptr [rbp-X],r14 */
- EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16);
+ EMIT3_off32(0x4C, 0x89, 0xB5, -STACKSIZE + 16);
/* mov qword ptr [rbp-X],r15 */
- EMIT3_off32(0x4C, 0x89, 0xBD, -stacksize + 24);
+ EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24);
/* clear A and X registers */
EMIT2(0x31, 0xc0); /* xor eax, eax */
EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */
+ /* clear tail_cnt: mov qword ptr [rbp-X], rax */
+ EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32);
+
+ BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
+ *pprog = prog;
+}
+
+/* generate the following code:
+ * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
+ * if (index >= array->map.max_entries)
+ * goto out;
+ * if (++tail_call_cnt > MAX_TAIL_CALL_CNT)
+ * goto out;
+ * prog = array->prog[index];
+ * if (prog == NULL)
+ * goto out;
+ * goto *(prog->bpf_func + prologue_size);
+ * out:
+ */
+static void emit_bpf_tail_call(u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int label1, label2, label3;
+ int cnt = 0;
+
+ /* rdi - pointer to ctx
+ * rsi - pointer to bpf_array
+ * rdx - index in bpf_array
+ */
+
+ /* if (index >= array->map.max_entries)
+ * goto out;
+ */
+ EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */
+ offsetof(struct bpf_array, map.max_entries));
+ EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */
+#define OFFSET1 44 /* number of bytes to jump */
+ EMIT2(X86_JBE, OFFSET1); /* jbe out */
+ label1 = cnt;
+
+ /* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+ * goto out;
+ */
+ EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
+ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
+#define OFFSET2 33
+ EMIT2(X86_JA, OFFSET2); /* ja out */
+ label2 = cnt;
+ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
+ EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
+
+ /* prog = array->prog[index]; */
+ EMIT4(0x48, 0x8D, 0x44, 0xD6); /* lea rax, [rsi + rdx * 8 + 0x50] */
+ EMIT1(offsetof(struct bpf_array, prog));
+ EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */
+
+ /* if (prog == NULL)
+ * goto out;
+ */
+ EMIT4(0x48, 0x83, 0xF8, 0x00); /* cmp rax, 0 */
+#define OFFSET3 10
+ EMIT2(X86_JE, OFFSET3); /* je out */
+ label3 = cnt;
+
+ /* goto *(prog->bpf_func + prologue_size); */
+ EMIT4(0x48, 0x8B, 0x40, /* mov rax, qword ptr [rax + 32] */
+ offsetof(struct bpf_prog, bpf_func));
+ EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE); /* add rax, prologue_size */
+
+ /* now we're ready to jump into next BPF program
+ * rdi == ctx (1st arg)
+ * rax == prog->bpf_func + prologue_size
+ */
+ EMIT2(0xFF, 0xE0); /* jmp rax */
+
+ /* out: */
+ BUILD_BUG_ON(cnt - label1 != OFFSET1);
+ BUILD_BUG_ON(cnt - label2 != OFFSET2);
+ BUILD_BUG_ON(cnt - label3 != OFFSET3);
+ *pprog = prog;
+}
+
+static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+ int oldproglen, struct jit_context *ctx)
+{
+ struct bpf_insn *insn = bpf_prog->insnsi;
+ int insn_cnt = bpf_prog->len;
+ bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
+ bool seen_exit = false;
+ u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
+ int i, cnt = 0;
+ int proglen = 0;
+ u8 *prog = temp;
+
+ emit_prologue(&prog);
+
if (seen_ld_abs) {
/* r9d : skb->len - skb->data_len (headlen)
* r10 : skb->data
@@ -739,6 +837,10 @@ xadd: if (is_imm8(insn->off))
}
break;
+ case BPF_JMP | BPF_CALL | BPF_X:
+ emit_bpf_tail_call(&prog);
+ break;
+
/* cond jump */
case BPF_JMP | BPF_JEQ | BPF_X:
case BPF_JMP | BPF_JNE | BPF_X:
@@ -891,13 +993,13 @@ common_load:
/* update cleanup_addr */
ctx->cleanup_addr = proglen;
/* mov rbx, qword ptr [rbp-X] */
- EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize);
+ EMIT3_off32(0x48, 0x8B, 0x9D, -STACKSIZE);
/* mov r13, qword ptr [rbp-X] */
- EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8);
+ EMIT3_off32(0x4C, 0x8B, 0xAD, -STACKSIZE + 8);
/* mov r14, qword ptr [rbp-X] */
- EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16);
+ EMIT3_off32(0x4C, 0x8B, 0xB5, -STACKSIZE + 16);
/* mov r15, qword ptr [rbp-X] */
- EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24);
+ EMIT3_off32(0x4C, 0x8B, 0xBD, -STACKSIZE + 24);
EMIT1(0xC9); /* leave */
EMIT1(0xC3); /* ret */
@@ -966,7 +1068,12 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
}
ctx.cleanup_addr = proglen;
- for (pass = 0; pass < 10; pass++) {
+ /* JITed image shrinks with every pass and the loop iterates
+ * until the image stops shrinking. Very large bpf programs
+ * may converge on the last pass. In such case do one more
+ * pass to emit the final image
+ */
+ for (pass = 0; pass < 10 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
image = NULL;
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index d93963340c3c..ff9911707160 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -81,6 +81,17 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
},
},
+ /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */
+ /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */
+ {
+ .callback = set_use_crs,
+ .ident = "Foxconn K8M890-8237A",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"),
+ DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"),
+ DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+ },
+ },
/* Now for the blacklist.. */
@@ -121,8 +132,10 @@ void __init pci_acpi_crs_quirks(void)
{
int year;
- if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
- pci_use_crs = false;
+ if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) {
+ if (iomem_resource.end <= 0xffffffff)
+ pci_use_crs = false;
+ }
dmi_check_system(pci_crs_quirks);
@@ -482,9 +495,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
{
- struct pci_sysdata *sd = bridge->bus->sysdata;
-
- ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+ /*
+ * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+ * here, pci_create_root_bus() has been called by someone else and
+ * sysdata is likely to be different from what we expect. Let it go in
+ * that case.
+ */
+ if (!bridge->dev.parent) {
+ struct pci_sysdata *sd = bridge->bus->sysdata;
+ ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+ }
return 0;
}
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 349c0d32cc0b..0a9f2caf358f 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -429,12 +429,12 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
* Caller can followup with UC MINUS request and add a WC mtrr if there
* is a free mtrr slot.
*/
- if (!pat_enabled && write_combine)
+ if (!pat_enabled() && write_combine)
return -EINVAL;
- if (pat_enabled && write_combine)
+ if (pat_enabled() && write_combine)
prot |= cachemode2protval(_PAGE_CACHE_MODE_WC);
- else if (pat_enabled || boot_cpu_data.x86 > 3)
+ else if (pat_enabled() || boot_cpu_data.x86 > 3)
/*
* ioremap() and ioremap_nocache() defaults to UC MINUS for now.
* To avoid attribute conflicts, request UC MINUS here
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 852aa4c92da0..27062303c881 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -208,6 +208,7 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
static int intel_mid_pci_irq_enable(struct pci_dev *dev)
{
+ struct irq_alloc_info info;
int polarity;
if (dev->irq_managed && dev->irq > 0)
@@ -217,14 +218,13 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
polarity = 0; /* active high */
else
polarity = 1; /* active low */
+ ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity);
/*
* MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
* IOAPIC RTE entries, so we just enable RTE for the device.
*/
- if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev)))
- return -EBUSY;
- if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
+ if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info) < 0)
return -EBUSY;
dev->irq_managed = 1;
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 5dc6ca5e1741..9bd115484745 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -146,19 +146,20 @@ static void __init pirq_peer_trick(void)
/*
* Code for querying and setting of IRQ routes on various interrupt routers.
+ * PIC Edge/Level Control Registers (ELCR) 0x4d0 & 0x4d1.
*/
-void eisa_set_level_irq(unsigned int irq)
+void elcr_set_level_irq(unsigned int irq)
{
unsigned char mask = 1 << (irq & 7);
unsigned int port = 0x4d0 + (irq >> 3);
unsigned char val;
- static u16 eisa_irq_mask;
+ static u16 elcr_irq_mask;
- if (irq >= 16 || (1 << irq) & eisa_irq_mask)
+ if (irq >= 16 || (1 << irq) & elcr_irq_mask)
return;
- eisa_irq_mask |= (1 << irq);
+ elcr_irq_mask |= (1 << irq);
printk(KERN_DEBUG "PCI: setting IRQ %u as level-triggered\n", irq);
val = inb(port);
if (!(val & mask)) {
@@ -965,11 +966,11 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
} else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
msg = "found";
- eisa_set_level_irq(irq);
+ elcr_set_level_irq(irq);
} else if (newirq && r->set &&
(dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
if (r->set(pirq_router_dev, dev, pirq, newirq)) {
- eisa_set_level_irq(newirq);
+ elcr_set_level_irq(newirq);
msg = "assigned";
irq = newirq;
}
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index a62e0be3a2f1..f1a6c8e86ddd 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -1,4 +1,5 @@
# Platform specific code goes here
+obj-y += atom/
obj-y += ce4100/
obj-y += efi/
obj-y += geode/
diff --git a/arch/x86/platform/atom/Makefile b/arch/x86/platform/atom/Makefile
new file mode 100644
index 000000000000..0a3a40cbc794
--- /dev/null
+++ b/arch/x86/platform/atom/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
new file mode 100644
index 000000000000..5ca8ead91579
--- /dev/null
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -0,0 +1,183 @@
+/*
+ * Intel SOC Punit device state debug driver
+ * Punit controls power management for North Complex devices (Graphics
+ * blocks, Image Signal Processing, video processing, display, DSP etc.)
+ *
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/io.h>
+#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
+
+/* Side band Interface port */
+#define PUNIT_PORT 0x04
+/* Power gate status reg */
+#define PWRGT_STATUS 0x61
+/* Subsystem config/status Video processor */
+#define VED_SS_PM0 0x32
+/* Subsystem config/status ISP (Image Signal Processor) */
+#define ISP_SS_PM0 0x39
+/* Subsystem config/status Input/output controller */
+#define MIO_SS_PM 0x3B
+/* Shift bits for getting status for video, isp and i/o */
+#define SSS_SHIFT 24
+/* Shift bits for getting status for graphics rendering */
+#define RENDER_POS 0
+/* Shift bits for getting status for media control */
+#define MEDIA_POS 2
+/* Shift bits for getting status for Valley View/Baytrail display */
+#define VLV_DISPLAY_POS 6
+/* Subsystem config/status display for Cherry Trail SOC */
+#define CHT_DSP_SSS 0x36
+/* Shift bits for getting status for display */
+#define CHT_DSP_SSS_POS 16
+
+struct punit_device {
+ char *name;
+ int reg;
+ int sss_pos;
+};
+
+static const struct punit_device punit_device_byt[] = {
+ { "GFX RENDER", PWRGT_STATUS, RENDER_POS },
+ { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS },
+ { "DISPLAY", PWRGT_STATUS, VLV_DISPLAY_POS },
+ { "VED", VED_SS_PM0, SSS_SHIFT },
+ { "ISP", ISP_SS_PM0, SSS_SHIFT },
+ { "MIO", MIO_SS_PM, SSS_SHIFT },
+ { NULL }
+};
+
+static const struct punit_device punit_device_cht[] = {
+ { "GFX RENDER", PWRGT_STATUS, RENDER_POS },
+ { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS },
+ { "DISPLAY", CHT_DSP_SSS, CHT_DSP_SSS_POS },
+ { "VED", VED_SS_PM0, SSS_SHIFT },
+ { "ISP", ISP_SS_PM0, SSS_SHIFT },
+ { "MIO", MIO_SS_PM, SSS_SHIFT },
+ { NULL }
+};
+
+static const char * const dstates[] = {"D0", "D0i1", "D0i2", "D0i3"};
+
+static int punit_dev_state_show(struct seq_file *seq_file, void *unused)
+{
+ u32 punit_pwr_status;
+ struct punit_device *punit_devp = seq_file->private;
+ int index;
+ int status;
+
+ seq_puts(seq_file, "\n\nPUNIT NORTH COMPLEX DEVICES :\n");
+ while (punit_devp->name) {
+ status = iosf_mbi_read(PUNIT_PORT, BT_MBI_PMC_READ,
+ punit_devp->reg,
+ &punit_pwr_status);
+ if (status) {
+ seq_printf(seq_file, "%9s : Read Failed\n",
+ punit_devp->name);
+ } else {
+ index = (punit_pwr_status >> punit_devp->sss_pos) & 3;
+ seq_printf(seq_file, "%9s : %s\n", punit_devp->name,
+ dstates[index]);
+ }
+ punit_devp++;
+ }
+
+ return 0;
+}
+
+static int punit_dev_state_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, punit_dev_state_show, inode->i_private);
+}
+
+static const struct file_operations punit_dev_state_ops = {
+ .open = punit_dev_state_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static struct dentry *punit_dbg_file;
+
+static int punit_dbgfs_register(struct punit_device *punit_device)
+{
+ static struct dentry *dev_state;
+
+ punit_dbg_file = debugfs_create_dir("punit_atom", NULL);
+ if (!punit_dbg_file)
+ return -ENXIO;
+
+ dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO,
+ punit_dbg_file, punit_device,
+ &punit_dev_state_ops);
+ if (!dev_state) {
+ pr_err("punit_dev_state register failed\n");
+ debugfs_remove(punit_dbg_file);
+ return -ENXIO;
+ }
+
+ return 0;
+}
+
+static void punit_dbgfs_unregister(void)
+{
+ debugfs_remove_recursive(punit_dbg_file);
+}
+
+#define ICPU(model, drv_data) \
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\
+ (kernel_ulong_t)&drv_data }
+
+static const struct x86_cpu_id intel_punit_cpu_ids[] = {
+ ICPU(55, punit_device_byt), /* Valleyview, Bay Trail */
+ ICPU(76, punit_device_cht), /* Braswell, Cherry Trail */
+ {}
+};
+
+MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids);
+
+static int __init punit_atom_debug_init(void)
+{
+ const struct x86_cpu_id *id;
+ int ret;
+
+ id = x86_match_cpu(intel_punit_cpu_ids);
+ if (!id)
+ return -ENODEV;
+
+ ret = punit_dbgfs_register((struct punit_device *)id->driver_data);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static void __exit punit_atom_debug_exit(void)
+{
+ punit_dbgfs_unregister();
+}
+
+module_init(punit_atom_debug_init);
+module_exit(punit_atom_debug_exit);
+
+MODULE_AUTHOR("Kumar P, Mahesh <mahesh.kumar.p@intel.com>");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_DESCRIPTION("Driver for Punit devices states debugging");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 02744df576d5..3b984c3aa1b0 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -501,6 +501,8 @@ void __init efi_init(void)
if (efi_enabled(EFI_DBG))
print_efi_memmap();
+
+ efi_esrt_init();
}
void __init efi_late_init(void)
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
index 0b283d4d0ad7..de734134bc8d 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
@@ -27,6 +27,7 @@ static struct platform_device wdt_dev = {
static int tangier_probe(struct platform_device *pdev)
{
int gsi;
+ struct irq_alloc_info info;
struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
if (!pdata)
@@ -34,8 +35,8 @@ static int tangier_probe(struct platform_device *pdev)
/* IOAPIC builds identity mapping between GSI and IRQ on MID */
gsi = pdata->irq;
- if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) ||
- mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) {
+ ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0);
+ if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) {
dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
gsi);
return -EINVAL;
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 3005f0c89f2e..01d54ea766c1 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -81,26 +81,34 @@ static unsigned long __init intel_mid_calibrate_tsc(void)
return 0;
}
+static void __init intel_mid_setup_bp_timer(void)
+{
+ apbt_time_init();
+ setup_boot_APIC_clock();
+}
+
static void __init intel_mid_time_init(void)
{
sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
+
switch (intel_mid_timer_options) {
case INTEL_MID_TIMER_APBT_ONLY:
break;
case INTEL_MID_TIMER_LAPIC_APBT:
- x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+ /* Use apbt and local apic */
+ x86_init.timers.setup_percpu_clockev = intel_mid_setup_bp_timer;
x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
- break;
+ return;
default:
if (!boot_cpu_has(X86_FEATURE_ARAT))
break;
+ /* Lapic only, no apbt */
x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
return;
}
- /* we need at least one APB timer */
- pre_init_apic_IRQ0();
- apbt_time_init();
+
+ x86_init.timers.setup_percpu_clockev = apbt_time_init;
}
static void intel_mid_arch_setup(void)
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index c14ad34776c4..ce992e8cc065 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -95,18 +95,16 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table)
pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n",
totallen, (u32)pentry->phys_addr,
pentry->freq_hz, pentry->irq);
- if (!pentry->irq)
- continue;
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
-/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
- mp_irq.irqflag = 5;
- mp_irq.srcbus = MP_BUS_ISA;
- mp_irq.srcbusirq = pentry->irq; /* IRQ */
- mp_irq.dstapic = MP_APIC_ALL;
- mp_irq.dstirq = pentry->irq;
- mp_save_irq(&mp_irq);
- mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ /* triggering mode edge bit 2-3, active high polarity bit 0-1 */
+ mp_irq.irqflag = 5;
+ mp_irq.srcbus = MP_BUS_ISA;
+ mp_irq.srcbusirq = pentry->irq; /* IRQ */
+ mp_irq.dstapic = MP_APIC_ALL;
+ mp_irq.dstirq = pentry->irq;
+ mp_save_irq(&mp_irq);
+ mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
}
return 0;
@@ -177,7 +175,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
mp_irq.dstapic = MP_APIC_ALL;
mp_irq.dstirq = pentry->irq;
mp_save_irq(&mp_irq);
- mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+ mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
}
return 0;
}
@@ -436,6 +434,7 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
struct devs_id *dev = NULL;
int num, i, ret;
int polarity;
+ struct irq_alloc_info info;
sb = (struct sfi_table_simple *)table;
num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
@@ -469,9 +468,8 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
polarity = 1;
}
- ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE);
- if (ret == 0)
- ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC);
+ ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity);
+ ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info);
WARN_ON(ret < 0);
}
diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c
index 2a8a74f3bd76..6c7111bbd1e9 100644
--- a/arch/x86/platform/sfi/sfi.c
+++ b/arch/x86/platform/sfi/sfi.c
@@ -25,8 +25,8 @@
#include <linux/init.h>
#include <linux/sfi.h>
#include <linux/io.h>
-#include <linux/irqdomain.h>
+#include <asm/irqdomain.h>
#include <asm/io_apic.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
@@ -71,9 +71,6 @@ static int __init sfi_parse_cpus(struct sfi_table_header *table)
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
-static struct irq_domain_ops sfi_ioapic_irqdomain_ops = {
- .map = mp_irqdomain_map,
-};
static int __init sfi_parse_ioapic(struct sfi_table_header *table)
{
@@ -82,7 +79,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table)
int i, num;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_STRICT,
- .ops = &sfi_ioapic_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
sb = (struct sfi_table_simple *)table;
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 0ce673645432..8570abe68be1 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -13,22 +13,37 @@
#include <linux/slab.h>
#include <linux/irq.h>
+#include <asm/irqdomain.h>
#include <asm/apic.h>
#include <asm/uv/uv_irq.h>
#include <asm/uv/uv_hub.h>
/* MMR offset and pnode of hub sourcing interrupts for a given irq */
-struct uv_irq_2_mmr_pnode{
- struct rb_node list;
+struct uv_irq_2_mmr_pnode {
unsigned long offset;
int pnode;
- int irq;
};
-static DEFINE_SPINLOCK(uv_irq_lock);
-static struct rb_root uv_irq_root;
+static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info)
+{
+ unsigned long mmr_value;
+ struct uv_IO_APIC_route_entry *entry;
+
+ BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
+ sizeof(unsigned long));
+
+ mmr_value = 0;
+ entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+ entry->vector = cfg->vector;
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->polarity = 0;
+ entry->trigger = 0;
+ entry->mask = 0;
+ entry->dest = cfg->dest_apicid;
-static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
+ uv_write_global_mmr64(info->pnode, info->offset, mmr_value);
+}
static void uv_noop(struct irq_data *data) { }
@@ -37,6 +52,23 @@ static void uv_ack_apic(struct irq_data *data)
ack_APIC_irq();
}
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
+{
+ struct irq_data *parent = data->parent_data;
+ struct irq_cfg *cfg = irqd_cfg(data);
+ int ret;
+
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret >= 0) {
+ uv_program_mmr(cfg, data->chip_data);
+ send_cleanup_vector(cfg);
+ }
+
+ return ret;
+}
+
static struct irq_chip uv_irq_chip = {
.name = "UV-CORE",
.irq_mask = uv_noop,
@@ -45,189 +77,99 @@ static struct irq_chip uv_irq_chip = {
.irq_set_affinity = uv_set_irq_affinity,
};
-/*
- * Add offset and pnode information of the hub sourcing interrupts to the
- * rb tree for a specific irq.
- */
-static int uv_set_irq_2_mmr_info(int irq, unsigned long offset, unsigned blade)
+static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- struct rb_node **link = &uv_irq_root.rb_node;
- struct rb_node *parent = NULL;
- struct uv_irq_2_mmr_pnode *n;
- struct uv_irq_2_mmr_pnode *e;
- unsigned long irqflags;
-
- n = kmalloc_node(sizeof(struct uv_irq_2_mmr_pnode), GFP_KERNEL,
- uv_blade_to_memory_nid(blade));
- if (!n)
+ struct uv_irq_2_mmr_pnode *chip_data;
+ struct irq_alloc_info *info = arg;
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+ int ret;
+
+ if (nr_irqs > 1 || !info || info->type != X86_IRQ_ALLOC_TYPE_UV)
+ return -EINVAL;
+
+ chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL,
+ irq_data->node);
+ if (!chip_data)
return -ENOMEM;
- n->irq = irq;
- n->offset = offset;
- n->pnode = uv_blade_to_pnode(blade);
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- /* Find the right place in the rbtree: */
- while (*link) {
- parent = *link;
- e = rb_entry(parent, struct uv_irq_2_mmr_pnode, list);
-
- if (unlikely(irq == e->irq)) {
- /* irq entry exists */
- e->pnode = uv_blade_to_pnode(blade);
- e->offset = offset;
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- kfree(n);
- return 0;
- }
-
- if (irq < e->irq)
- link = &(*link)->rb_left;
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+ if (ret >= 0) {
+ if (info->uv_limit == UV_AFFINITY_CPU)
+ irq_set_status_flags(virq, IRQ_NO_BALANCING);
else
- link = &(*link)->rb_right;
+ irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+
+ chip_data->pnode = uv_blade_to_pnode(info->uv_blade);
+ chip_data->offset = info->uv_offset;
+ irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data,
+ handle_percpu_irq, NULL, info->uv_name);
+ } else {
+ kfree(chip_data);
}
- /* Insert the node into the rbtree. */
- rb_link_node(&n->list, parent, link);
- rb_insert_color(&n->list, &uv_irq_root);
-
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return 0;
+ return ret;
}
-/* Retrieve offset and pnode information from the rb tree for a specific irq */
-int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode)
+static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
{
- struct uv_irq_2_mmr_pnode *e;
- struct rb_node *n;
- unsigned long irqflags;
-
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- n = uv_irq_root.rb_node;
- while (n) {
- e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
-
- if (e->irq == irq) {
- *offset = e->offset;
- *pnode = e->pnode;
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return 0;
- }
-
- if (irq < e->irq)
- n = n->rb_left;
- else
- n = n->rb_right;
- }
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return -1;
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+ BUG_ON(nr_irqs != 1);
+ kfree(irq_data->chip_data);
+ irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
+ irq_clear_status_flags(virq, IRQ_NO_BALANCING);
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
}
/*
* Re-target the irq to the specified CPU and enable the specified MMR located
* on the specified blade to allow the sending of MSIs to the specified CPU.
*/
-static int
-arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
- unsigned long mmr_offset, int limit)
+static void uv_domain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
- const struct cpumask *eligible_cpu = cpumask_of(cpu);
- struct irq_cfg *cfg = irq_cfg(irq);
- unsigned long mmr_value;
- struct uv_IO_APIC_route_entry *entry;
- int mmr_pnode, err;
- unsigned int dest;
-
- BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
- sizeof(unsigned long));
-
- err = assign_irq_vector(irq, cfg, eligible_cpu);
- if (err != 0)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest);
- if (err != 0)
- return err;
-
- if (limit == UV_AFFINITY_CPU)
- irq_set_status_flags(irq, IRQ_NO_BALANCING);
- else
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-
- irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
- irq_name);
-
- mmr_value = 0;
- entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
- entry->vector = cfg->vector;
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->polarity = 0;
- entry->trigger = 0;
- entry->mask = 0;
- entry->dest = dest;
-
- mmr_pnode = uv_blade_to_pnode(mmr_blade);
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
-
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
-
- return irq;
+ uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
}
/*
* Disable the specified MMR located on the specified blade so that MSIs are
* longer allowed to be sent.
*/
-static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset)
+static void uv_domain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
unsigned long mmr_value;
struct uv_IO_APIC_route_entry *entry;
- BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
- sizeof(unsigned long));
-
mmr_value = 0;
entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
entry->mask = 1;
-
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+ uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
}
-static int
-uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest;
- unsigned long mmr_value, mmr_offset;
- struct uv_IO_APIC_route_entry *entry;
- int mmr_pnode;
-
- if (apic_set_affinity(data, mask, &dest))
- return -1;
-
- mmr_value = 0;
- entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-
- entry->vector = cfg->vector;
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->polarity = 0;
- entry->trigger = 0;
- entry->mask = 0;
- entry->dest = dest;
-
- /* Get previously stored MMR and pnode of hub sourcing interrupts */
- if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
- return -1;
-
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+static const struct irq_domain_ops uv_domain_ops = {
+ .alloc = uv_domain_alloc,
+ .free = uv_domain_free,
+ .activate = uv_domain_activate,
+ .deactivate = uv_domain_deactivate,
+};
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
+static struct irq_domain *uv_get_irq_domain(void)
+{
+ static struct irq_domain *uv_domain;
+ static DEFINE_MUTEX(uv_lock);
+
+ mutex_lock(&uv_lock);
+ if (uv_domain == NULL) {
+ uv_domain = irq_domain_add_tree(NULL, &uv_domain_ops, NULL);
+ if (uv_domain)
+ uv_domain->parent = x86_vector_domain;
+ }
+ mutex_unlock(&uv_lock);
- return IRQ_SET_MASK_OK_NOCOPY;
+ return uv_domain;
}
/*
@@ -238,19 +180,21 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
unsigned long mmr_offset, int limit)
{
- int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade));
+ struct irq_alloc_info info;
+ struct irq_domain *domain = uv_get_irq_domain();
- if (!irq)
- return -EBUSY;
+ if (!domain)
+ return -ENOMEM;
- ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset,
- limit);
- if (ret == irq)
- uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade);
- else
- irq_free_hwirq(irq);
+ init_irq_alloc_info(&info, cpumask_of(cpu));
+ info.type = X86_IRQ_ALLOC_TYPE_UV;
+ info.uv_limit = limit;
+ info.uv_blade = mmr_blade;
+ info.uv_offset = mmr_offset;
+ info.uv_name = irq_name;
- return ret;
+ return irq_domain_alloc_irqs(domain, 1,
+ uv_blade_to_memory_nid(mmr_blade), &info);
}
EXPORT_SYMBOL_GPL(uv_setup_irq);
@@ -263,26 +207,6 @@ EXPORT_SYMBOL_GPL(uv_setup_irq);
*/
void uv_teardown_irq(unsigned int irq)
{
- struct uv_irq_2_mmr_pnode *e;
- struct rb_node *n;
- unsigned long irqflags;
-
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- n = uv_irq_root.rb_node;
- while (n) {
- e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
- if (e->irq == irq) {
- arch_disable_uv_irq(e->pnode, e->offset);
- rb_erase(n, &uv_irq_root);
- kfree(e);
- break;
- }
- if (irq < e->irq)
- n = n->rb_left;
- else
- n = n->rb_right;
- }
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- irq_free_hwirq(irq);
+ irq_domain_free_irqs(irq, 1);
}
EXPORT_SYMBOL_GPL(uv_teardown_irq);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 757678fb26e1..0d7dd1f5ac36 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -18,10 +18,9 @@
#include <asm/mtrr.h>
#include <asm/page.h>
#include <asm/mce.h>
-#include <asm/xcr.h>
#include <asm/suspend.h>
+#include <asm/fpu/internal.h>
#include <asm/debugreg.h>
-#include <asm/fpu-internal.h> /* pcntxt_mask */
#include <asm/cpu.h>
#ifdef CONFIG_X86_32
@@ -155,6 +154,8 @@ static void fix_processor_context(void)
#endif
load_TR_desc(); /* This does ltr */
load_LDT(&current->active_mm->context); /* This does lldt */
+
+ fpu__resume_cpu();
}
/**
@@ -221,12 +222,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
#endif
- /*
- * restore XCR0 for xsave capable cpu's.
- */
- if (cpu_has_xsave)
- xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-
fix_processor_context();
do_fpu_end();
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 3c4469a7a929..e2386cb4e0c3 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -78,9 +78,9 @@ ENTRY(restore_image)
/* code below has been relocated to a safe page */
ENTRY(core_restore_code)
-loop:
+.Lloop:
testq %rdx, %rdx
- jz done
+ jz .Ldone
/* get addresses from the pbe and copy the page */
movq pbe_address(%rdx), %rsi
@@ -91,8 +91,8 @@ loop:
/* progress to the next pbe */
movq pbe_next(%rdx), %rdx
- jmp loop
-done:
+ jmp .Lloop
+.Ldone:
/* jump to the restore_registers address from the image header */
jmpq *%rax
/*
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index acb384d24669..a8fecc226946 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -26,7 +26,7 @@ else
obj-y += syscalls_64.o vdso/
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \
../lib/rwsem.o
endif
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7e8a1a650435..b9531d343134 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -39,7 +39,8 @@
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
#define read_barrier_depends() do { } while (0)
#define smp_read_barrier_depends() do { } while (0)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 46957ead3060..0b95c9b8283f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1181,10 +1181,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.read_tscp = native_read_tscp,
.iret = xen_iret,
- .irq_enable_sysexit = xen_sysexit,
#ifdef CONFIG_X86_64
.usergs_sysret32 = xen_sysret32,
.usergs_sysret64 = xen_sysret64,
+#else
+ .irq_enable_sysexit = xen_sysexit,
#endif
.load_tr_desc = paravirt_nop,
@@ -1423,7 +1424,7 @@ static void xen_pvh_set_cr_flags(int cpu)
return;
/*
* For BSP, PSE PGE are set in probe_page_size_mask(), for APs
- * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
+ * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
*/
if (cpu_has_pse)
cr4_set_bits_and_update_boot(X86_CR4_PSE);
@@ -1467,6 +1468,7 @@ 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)
@@ -1574,8 +1576,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
* Modify the cache mode translation tables to match Xen's PAT
* configuration.
*/
-
- pat_init_cache_modes();
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ pat_init_cache_modes(pat);
/* keep using Xen gdt for now; no urgent need to change it */
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b47124d4cd67..8b7f18e200aa 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -67,6 +67,7 @@
#include <linux/seq_file.h>
#include <linux/bootmem.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
#include <asm/cache.h>
#include <asm/setup.h>
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 956374c1edbc..9e2ba5c6e1dd 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -17,6 +17,56 @@
#include "xen-ops.h"
#include "debugfs.h"
+static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
+static DEFINE_PER_CPU(char *, irq_name);
+static bool xen_pvspin = true;
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void xen_qlock_kick(int cpu)
+{
+ xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
+}
+
+/*
+ * Halt the current CPU & release it back to the host
+ */
+static void xen_qlock_wait(u8 *byte, u8 val)
+{
+ int irq = __this_cpu_read(lock_kicker_irq);
+
+ /* If kicker interrupts not initialized yet, just spin */
+ if (irq == -1)
+ return;
+
+ /* clear pending */
+ xen_clear_irq_pending(irq);
+ barrier();
+
+ /*
+ * We check the byte value after clearing pending IRQ to make sure
+ * that we won't miss a wakeup event because of the clearing.
+ *
+ * The sync_clear_bit() call in xen_clear_irq_pending() is atomic.
+ * So it is effectively a memory barrier for x86.
+ */
+ if (READ_ONCE(*byte) != val)
+ return;
+
+ /*
+ * If an interrupt happens here, it will leave the wakeup irq
+ * pending, which will cause xen_poll_irq() to return
+ * immediately.
+ */
+
+ /* Block until irq becomes pending (or perhaps a spurious wakeup) */
+ xen_poll_irq(irq);
+}
+
+#else /* CONFIG_QUEUED_SPINLOCKS */
+
enum xen_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
@@ -100,12 +150,9 @@ struct xen_lock_waiting {
__ticket_t want;
};
-static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(char *, irq_name);
static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
static cpumask_t waiting_cpus;
-static bool xen_pvspin = true;
__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
{
int irq = __this_cpu_read(lock_kicker_irq);
@@ -217,6 +264,7 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
}
}
}
+#endif /* CONFIG_QUEUED_SPINLOCKS */
static irqreturn_t dummy_handler(int irq, void *dev_id)
{
@@ -280,8 +328,16 @@ void __init xen_init_spinlocks(void)
return;
}
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ __pv_init_lock_hash();
+ pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_lock_ops.wait = xen_qlock_wait;
+ pv_lock_ops.kick = xen_qlock_kick;
+#else
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
pv_lock_ops.unlock_kick = xen_unlock_kick;
+#endif
}
/*
@@ -310,7 +366,7 @@ static __init int xen_parse_nopvspin(char *arg)
}
early_param("xen_nopvspin", xen_parse_nopvspin);
-#ifdef CONFIG_XEN_DEBUG_FS
+#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS)
static struct dentry *d_spin_debug;
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 985fc3ee0973..f22667abf7b9 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -15,6 +15,8 @@
#include <asm/percpu.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
#include <xen/interface/xen.h>
@@ -47,29 +49,13 @@ ENTRY(xen_iret)
ENDPATCH(xen_iret)
RELOC(xen_iret, 1b+1)
-/*
- * sysexit is not used for 64-bit processes, so it's only ever used to
- * return to 32-bit compat userspace.
- */
-ENTRY(xen_sysexit)
- pushq $__USER32_DS
- pushq %rcx
- pushq $X86_EFLAGS_IF
- pushq $__USER32_CS
- pushq %rdx
-
- pushq $0
-1: jmp hypercall_iret
-ENDPATCH(xen_sysexit)
-RELOC(xen_sysexit, 1b+1)
-
ENTRY(xen_sysret64)
/*
* We're already on the usermode stack at this point, but
* still with the kernel gs, so we can easily switch back
*/
movq %rsp, PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack), %rsp
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq $__USER_DS
pushq PER_CPU_VAR(rsp_scratch)
@@ -88,7 +74,7 @@ ENTRY(xen_sysret32)
* still with the kernel gs, so we can easily switch back
*/
movq %rsp, PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack), %rsp
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq $__USER32_DS
pushq PER_CPU_VAR(rsp_scratch)
@@ -128,7 +114,7 @@ RELOC(xen_sysret32, 1b+1)
/* Normal 64-bit system call target */
ENTRY(xen_syscall_target)
undo_xen_syscall
- jmp system_call_after_swapgs
+ jmp entry_SYSCALL_64_after_swapgs
ENDPROC(xen_syscall_target)
#ifdef CONFIG_IA32_EMULATION
@@ -136,13 +122,13 @@ ENDPROC(xen_syscall_target)
/* 32-bit compat syscall target */
ENTRY(xen_syscall32_target)
undo_xen_syscall
- jmp ia32_cstar_target
+ jmp entry_SYSCALL_compat
ENDPROC(xen_syscall32_target)
/* 32-bit compat sysenter target */
ENTRY(xen_sysenter_target)
undo_xen_syscall
- jmp ia32_sysenter_target
+ jmp entry_SYSENTER_compat
ENDPROC(xen_sysenter_target)
#else /* !CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9e195c683549..c20fe29e65f4 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -134,7 +134,9 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long);
/* These are not functions, and cannot be called normally */
__visible void xen_iret(void);
+#ifdef CONFIG_X86_32
__visible void xen_sysexit(void);
+#endif
__visible void xen_sysret32(void);
__visible void xen_sysret64(void);
__visible void xen_adjust_exception_frame(void);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 87be10e8b57a..e5b872ba2484 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -151,7 +151,7 @@ config HAVE_SMP
the CPU core definition and currently needs to be selected manually.
Multiprocessor support in implemented with external cache and
- interrupt controlers.
+ interrupt controllers.
The MX interrupt distributer adds Interprocessor Interrupts
and causes the IRQ numbers to be increased by 4 for devices
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 172a02a6ad14..ba78ccf651e7 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -185,4 +185,17 @@ static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
return -EINVAL;
}
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag,
+ struct dma_attrs *attrs)
+{
+ return NULL;
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
+{
+}
+
#endif /* _XTENSA_DMA_MAPPING_H */
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index fe1600a09438..c39bb6e61911 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -59,6 +59,7 @@ static inline void __iomem *ioremap_cache(unsigned long offset,
}
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
{
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 9e3571a6535c..83a44a33cfa1 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -15,10 +15,10 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/hardirq.h>
+#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/hardirq.h>
-#include <asm/uaccess.h>
#include <asm/pgalloc.h>
DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST;
@@ -57,7 +57,7 @@ void do_page_fault(struct pt_regs *regs)
/* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm) {
+ if (faulthandler_disabled() || !mm) {
bad_page_fault(regs, address, SIGSEGV);
return;
}
diff --git a/arch/xtensa/mm/highmem.c b/arch/xtensa/mm/highmem.c
index 8cfb71ec0937..184ceadccc1a 100644
--- a/arch/xtensa/mm/highmem.c
+++ b/arch/xtensa/mm/highmem.c
@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page)
enum fixed_addresses idx;
unsigned long vaddr;
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
@@ -79,6 +80,7 @@ void __kunmap_atomic(void *kvaddr)
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);